From 8053f21675b073b379cbca258ee4a3f3850dfa94 Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Tue, 26 Jul 2016 14:55:51 -0700 Subject: [PATCH 001/531] ASoC: dapm: Add a dummy snd_pcm_runtime to avoid NULL pointer access The SND_SOC_DAPM_PRE_PMU case would call startup()/hw_params() that might access substream->runtime through other functions. For example: Unable to handle kernel NULL pointer dereference at virtual address [....] PC is at snd_pcm_hw_rule_add+0x24/0x1b0 LR is at snd_pcm_hw_constraint_list+0x20/0x28 [....] Process arecord (pid: 424, stack limit = 0xffffffc1ecaf0020) Call trace: [] snd_pcm_hw_rule_add+0x24/0x1b0 [] snd_pcm_hw_constraint_list+0x20/0x28 [] cs53l30_pcm_startup+0x24/0x30 [] snd_soc_dai_link_event+0x290/0x354 [] dapm_seq_check_event.isra.31+0x134/0x2c8 [] dapm_seq_run_coalesced+0x94/0x1c8 [] dapm_seq_run+0xa4/0x404 [] dapm_power_widgets+0x524/0x984 [] snd_soc_dapm_stream_event+0x8c/0xa8 [] soc_pcm_prepare+0x10c/0x1ec [] snd_pcm_do_prepare+0x1c/0x38 [] snd_pcm_action_single+0x40/0x88 [] snd_pcm_action_nonatomic+0x70/0x90 [] snd_pcm_common_ioctl1+0xb6c/0xdd8 [] snd_pcm_capture_ioctl1+0x200/0x334 [] snd_pcm_ioctl_compat+0x648/0x95c [] compat_SyS_ioctl+0xac/0xfc4 [] el0_svc_naked+0x24/0x28 ---[ end trace 0dc4f99c2759c35c ]--- So this patch adds a dummy runtime for the original dummy substream to merely avoid the NULL pointer access. Signed-off-by: Nicolin Chen Signed-off-by: Mark Brown --- sound/soc/soc-dapm.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 8698c26773b3..d908ff8f9755 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -3493,6 +3493,7 @@ static int snd_soc_dai_link_event(struct snd_soc_dapm_widget *w, const struct snd_soc_pcm_stream *config = w->params + w->params_select; struct snd_pcm_substream substream; struct snd_pcm_hw_params *params = NULL; + struct snd_pcm_runtime *runtime = NULL; u64 fmt; int ret; @@ -3541,6 +3542,14 @@ static int snd_soc_dai_link_event(struct snd_soc_dapm_widget *w, memset(&substream, 0, sizeof(substream)); + /* Allocate a dummy snd_pcm_runtime for startup() and other ops() */ + runtime = kzalloc(sizeof(*runtime), GFP_KERNEL); + if (!runtime) { + ret = -ENOMEM; + goto out; + } + substream.runtime = runtime; + switch (event) { case SND_SOC_DAPM_PRE_PMU: substream.stream = SNDRV_PCM_STREAM_CAPTURE; @@ -3606,6 +3615,7 @@ static int snd_soc_dai_link_event(struct snd_soc_dapm_widget *w, } out: + kfree(runtime); kfree(params); return ret; } From 93ca33c99f22a0a096f83f19c9f887aeb67507a1 Mon Sep 17 00:00:00 2001 From: Hiroyuki Yokoyama Date: Mon, 25 Jul 2016 01:52:43 +0000 Subject: [PATCH 002/531] ASoC: rsnd: Fixup SRCm_IFSVR calculate method This patch fixes the calculation accuracy degradation of SRCm_IFSVR register value. Signed-off-by: Hiroyuki Yokoyama Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- sound/soc/sh/rcar/src.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/sound/soc/sh/rcar/src.c b/sound/soc/sh/rcar/src.c index e39f916d0f2f..969a5169de25 100644 --- a/sound/soc/sh/rcar/src.c +++ b/sound/soc/sh/rcar/src.c @@ -226,8 +226,12 @@ static void rsnd_src_set_convert_rate(struct rsnd_dai_stream *io, ifscr = 0; fsrate = 0; if (fin != fout) { + u64 n; + ifscr = 1; - fsrate = 0x0400000 / fout * fin; + n = (u64)0x0400000 * fin; + do_div(n, fout); + fsrate = n; } /* From 9b622e2bbcf049c82e2550d35fb54ac205965f50 Mon Sep 17 00:00:00 2001 From: Tomasz Majchrzak Date: Thu, 28 Jul 2016 10:28:25 +0200 Subject: [PATCH 003/531] raid10: increment write counter after bio is split md pending write counter must be incremented after bio is split, otherwise it gets decremented too many times in end bio callback and becomes negative. Signed-off-by: Tomasz Majchrzak Reviewed-by: Artur Paszkiewicz Signed-off-by: Shaohua Li --- drivers/md/raid10.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index ed29fc899f06..1a632a8c8005 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1064,6 +1064,8 @@ static void __make_request(struct mddev *mddev, struct bio *bio) int max_sectors; int sectors; + md_write_start(mddev, bio); + /* * Register the new request and wait if the reconstruction * thread has put up a bar for new requests. @@ -1445,8 +1447,6 @@ static void raid10_make_request(struct mddev *mddev, struct bio *bio) return; } - md_write_start(mddev, bio); - do { /* From 3980bd3b406addb327d858aebd19e229ea340b9a Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sun, 31 Jul 2016 23:38:36 -0400 Subject: [PATCH 004/531] ext4: reserve xattr index for the Hurd The Hurd is using inode fields which restricts it from using more advanced ext4 file system features, due to design choices made over a decade ago. By giving the Hurd an extended attribute index field we allow it to move the translator and author fields out of the core inode fields, and hopefully we can get rid of ugly hacks such as EXT4_OS_HURD and EXT4_MOUNT2_HURD_COMPAT somday. For more information please see: https://summerofcode.withgoogle.com/projects/#5869799859027968 Signed-off-by: Theodore Ts'o --- fs/ext4/xattr.h | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h index 69dd3e6566e0..a92e783fa057 100644 --- a/fs/ext4/xattr.h +++ b/fs/ext4/xattr.h @@ -24,6 +24,7 @@ #define EXT4_XATTR_INDEX_SYSTEM 7 #define EXT4_XATTR_INDEX_RICHACL 8 #define EXT4_XATTR_INDEX_ENCRYPTION 9 +#define EXT4_XATTR_INDEX_HURD 10 /* Reserved for Hurd */ struct ext4_xattr_header { __le32 h_magic; /* magic number for identification */ From 829fa70dddadf9dd041d62b82cd7cea63943899d Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Mon, 1 Aug 2016 00:51:02 -0400 Subject: [PATCH 005/531] ext4: validate that metadata blocks do not overlap superblock A number of fuzzing failures seem to be caused by allocation bitmaps or other metadata blocks being pointed at the superblock. This can cause kernel BUG or WARNings once the superblock is overwritten, so validate the group descriptor blocks to make sure this doesn't happen. Cc: stable@vger.kernel.org Signed-off-by: Theodore Ts'o --- fs/ext4/super.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index c13a4e464738..da3146e8d49a 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2211,6 +2211,7 @@ void ext4_group_desc_csum_set(struct super_block *sb, __u32 block_group, /* Called at mount-time, super-block is locked */ static int ext4_check_descriptors(struct super_block *sb, + ext4_fsblk_t sb_block, ext4_group_t *first_not_zeroed) { struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -2241,6 +2242,11 @@ static int ext4_check_descriptors(struct super_block *sb, grp = i; block_bitmap = ext4_block_bitmap(sb, gdp); + if (block_bitmap == sb_block) { + ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " + "Block bitmap for group %u overlaps " + "superblock", i); + } if (block_bitmap < first_block || block_bitmap > last_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Block bitmap for group %u not in group " @@ -2248,6 +2254,11 @@ static int ext4_check_descriptors(struct super_block *sb, return 0; } inode_bitmap = ext4_inode_bitmap(sb, gdp); + if (inode_bitmap == sb_block) { + ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " + "Inode bitmap for group %u overlaps " + "superblock", i); + } if (inode_bitmap < first_block || inode_bitmap > last_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode bitmap for group %u not in group " @@ -2255,6 +2266,11 @@ static int ext4_check_descriptors(struct super_block *sb, return 0; } inode_table = ext4_inode_table(sb, gdp); + if (inode_table == sb_block) { + ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " + "Inode table for group %u overlaps " + "superblock", i); + } if (inode_table < first_block || inode_table + sbi->s_itb_per_group - 1 > last_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " @@ -3757,7 +3773,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount2; } } - if (!ext4_check_descriptors(sb, &first_not_zeroed)) { + if (!ext4_check_descriptors(sb, logical_sb_block, &first_not_zeroed)) { ext4_msg(sb, KERN_ERR, "group descriptors corrupted!"); ret = -EFSCORRUPTED; goto failed_mount2; From 2392f7fd695246df4fb5f0b5fb88ce37cdb01764 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Tue, 26 Jul 2016 18:06:39 +0530 Subject: [PATCH 006/531] ASoC: Intel: Skylake: Check list empty while getting module info Module list can be NULL so check if the list is empty before accessing the list. Signed-off-by: Senthilnathan Veppur Signed-off-by: Vinod Koul Signed-off-by: Mark Brown --- sound/soc/intel/skylake/skl-sst-utils.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/sound/soc/intel/skylake/skl-sst-utils.c b/sound/soc/intel/skylake/skl-sst-utils.c index 25fcb796bd86..ddcb52a51854 100644 --- a/sound/soc/intel/skylake/skl-sst-utils.c +++ b/sound/soc/intel/skylake/skl-sst-utils.c @@ -123,6 +123,11 @@ int snd_skl_get_module_info(struct skl_sst *ctx, u8 *uuid, uuid_mod = (uuid_le *)uuid; + if (list_empty(&ctx->uuid_list)) { + dev_err(ctx->dev, "Module list is empty\n"); + return -EINVAL; + } + list_for_each_entry(module, &ctx->uuid_list, list) { if (uuid_le_cmp(*uuid_mod, module->uuid) == 0) { dfw_config->module_id = module->id; From ff00d3b4e5e4395c825e8ec628f25932d812f31a Mon Sep 17 00:00:00 2001 From: ZhengYuan Liu Date: Thu, 28 Jul 2016 14:22:14 +0800 Subject: [PATCH 007/531] raid5: fix incorrectly counter of conf->empty_inactive_list_nr The counter conf->empty_inactive_list_nr is only used for determine if the raid5 is congested which is deal with in function raid5_congested(). It was increased in get_free_stripe() when conf->inactive_list got to be empty and decreased in release_inactive_stripe_list() when splice temp_inactive_list to conf->inactive_list. However, this may have a problem when raid5_get_active_stripe or stripe_add_to_batch_list was called, because these two functions may call list_del_init(&sh->lru) to delete sh from "conf->inactive_list + hash" which may cause "conf->inactive_list + hash" to be empty when atomic_inc_not_zero(&sh->count) got false. So a check should be done at these two point and increase empty_inactive_list_nr accordingly. Otherwise the counter may get to be negative number which would influence async readahead from VFS. Signed-off-by: ZhengYuan Liu Signed-off-by: Shaohua Li --- drivers/md/raid5.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index d189e894b921..e379b89fd8b1 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -659,6 +659,7 @@ raid5_get_active_stripe(struct r5conf *conf, sector_t sector, { struct stripe_head *sh; int hash = stripe_hash_locks_hash(sector); + int inc_empty_inactive_list_flag; pr_debug("get_stripe, sector %llu\n", (unsigned long long)sector); @@ -703,7 +704,12 @@ raid5_get_active_stripe(struct r5conf *conf, sector_t sector, atomic_inc(&conf->active_stripes); BUG_ON(list_empty(&sh->lru) && !test_bit(STRIPE_EXPANDING, &sh->state)); + inc_empty_inactive_list_flag = 0; + if (!list_empty(conf->inactive_list + hash)) + inc_empty_inactive_list_flag = 1; list_del_init(&sh->lru); + if (list_empty(conf->inactive_list + hash) && inc_empty_inactive_list_flag) + atomic_inc(&conf->empty_inactive_list_nr); if (sh->group) { sh->group->stripes_cnt--; sh->group = NULL; @@ -762,6 +768,7 @@ static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh sector_t head_sector, tmp_sec; int hash; int dd_idx; + int inc_empty_inactive_list_flag; /* Don't cross chunks, so stripe pd_idx/qd_idx is the same */ tmp_sec = sh->sector; @@ -779,7 +786,12 @@ static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh atomic_inc(&conf->active_stripes); BUG_ON(list_empty(&head->lru) && !test_bit(STRIPE_EXPANDING, &head->state)); + inc_empty_inactive_list_flag = 0; + if (!list_empty(conf->inactive_list + hash)) + inc_empty_inactive_list_flag = 1; list_del_init(&head->lru); + if (list_empty(conf->inactive_list + hash) && inc_empty_inactive_list_flag) + atomic_inc(&conf->empty_inactive_list_nr); if (head->group) { head->group->stripes_cnt--; head->group = NULL; From 1f85e118c81d15aa9e002604dfb69c823d4aac16 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Wed, 3 Aug 2016 01:24:05 +0000 Subject: [PATCH 008/531] ASoC: simple-card-utils: add missing MODULE_xxx() simple-card-utils might be used as module, but MODULE_xxx() information was missed. This patch adds it. Otherwise, we will have below error, and can't use it. Specil thanks to Kevin. > insmod simple-card-utils.ko simple_card_utils: module license 'unspecified' taints kernel. Disabling lock debugging due to kernel taint simple_card_utils: Unknown symbol snd_soc_of_parse_daifmt (err 0) simple_card_utils: Unknown symbol snd_soc_of_parse_card_name (err 0) insmod: can't insert 'simple-card-utils.ko': \ unknown symbol in module, or unknown parameter Reported-by: Kevin Hilman Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- sound/soc/generic/Makefile | 6 +++--- sound/soc/generic/simple-card-utils.c | 6 ++++++ 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/sound/soc/generic/Makefile b/sound/soc/generic/Makefile index 45602ca8536e..2d53c8d70705 100644 --- a/sound/soc/generic/Makefile +++ b/sound/soc/generic/Makefile @@ -1,5 +1,5 @@ -obj-$(CONFIG_SND_SIMPLE_CARD_UTILS) := simple-card-utils.o - +snd-soc-simple-card-utils-objs := simple-card-utils.o snd-soc-simple-card-objs := simple-card.o -obj-$(CONFIG_SND_SIMPLE_CARD) += snd-soc-simple-card.o +obj-$(CONFIG_SND_SIMPLE_CARD_UTILS) += snd-soc-simple-card-utils.o +obj-$(CONFIG_SND_SIMPLE_CARD) += snd-soc-simple-card.o diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c index d89a9a1b2471..9599de69a880 100644 --- a/sound/soc/generic/simple-card-utils.c +++ b/sound/soc/generic/simple-card-utils.c @@ -7,6 +7,7 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ +#include #include #include @@ -95,3 +96,8 @@ int asoc_simple_card_parse_card_name(struct snd_soc_card *card, return 0; } EXPORT_SYMBOL_GPL(asoc_simple_card_parse_card_name); + +/* Module information */ +MODULE_AUTHOR("Kuninori Morimoto "); +MODULE_DESCRIPTION("ALSA SoC Simple Card Utils"); +MODULE_LICENSE("GPL v2"); From 1bc610e7a17dcf5165f1ed4e0201ee080ba1a0df Mon Sep 17 00:00:00 2001 From: Sylwester Nawrocki Date: Thu, 4 Aug 2016 11:51:25 +0200 Subject: [PATCH 009/531] ASoC: samsung: Fix clock handling in S3C24XX_UDA134X card There is no "pclk" alias in the s3c2440 clk driver for "soc-audio" device so related clk_get() fails, which prevents any operation of the S3C24XX_UDA134X sound card. Instead we get the clock on behalf of the I2S device, i.e. we use the I2S block gate clock which has PCLK is its parent clock. Without this patch there is an error like: s3c24xx_uda134x_startup cannot get pclk ASoC: UDA134X startup failed: -2 Signed-off-by: Sylwester Nawrocki Signed-off-by: Mark Brown --- sound/soc/samsung/s3c24xx_uda134x.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/sound/soc/samsung/s3c24xx_uda134x.c b/sound/soc/samsung/s3c24xx_uda134x.c index 50849e137fc0..92e88bca386e 100644 --- a/sound/soc/samsung/s3c24xx_uda134x.c +++ b/sound/soc/samsung/s3c24xx_uda134x.c @@ -58,10 +58,12 @@ static struct platform_device *s3c24xx_uda134x_snd_device; static int s3c24xx_uda134x_startup(struct snd_pcm_substream *substream) { - int ret = 0; + struct snd_soc_pcm_runtime *rtd = substream->private_data; + struct snd_soc_dai *cpu_dai = rtd->cpu_dai; #ifdef ENFORCE_RATES struct snd_pcm_runtime *runtime = substream->runtime; #endif + int ret = 0; mutex_lock(&clk_lock); pr_debug("%s %d\n", __func__, clk_users); @@ -71,8 +73,7 @@ static int s3c24xx_uda134x_startup(struct snd_pcm_substream *substream) printk(KERN_ERR "%s cannot get xtal\n", __func__); ret = PTR_ERR(xtal); } else { - pclk = clk_get(&s3c24xx_uda134x_snd_device->dev, - "pclk"); + pclk = clk_get(cpu_dai->dev, "iis"); if (IS_ERR(pclk)) { printk(KERN_ERR "%s cannot get pclk\n", __func__); From ca6ac305f017472a172e53345264abdb495eba46 Mon Sep 17 00:00:00 2001 From: John Hsu Date: Thu, 4 Aug 2016 16:52:06 +0800 Subject: [PATCH 010/531] ASoC: nau8825: fix bug in playback when suspend In chromium, the following steps will make codec function fail. \1. plug in headphones, Play music \2. run "powerd_dbus_suspend" \3. resume from S3 After resume, the jack detection will restart and make configuration for the headset. Meanwhile, the playback prepares and starts to work. The two sequences will conflict and make wrong register configuration. Originally, the driver adds protection for the case when it finds the playback is active. But the "powerd_dbus_suspend" command will close the pcm stream before suspend. Therefore, the driver can't detect the playback after resume, and the protection not works. For the issue, the driver raises protection every time after resume. The protection will release after jack detection and configuration completes, and then the playback just will goes on. Signed-off-by: John Hsu Signed-off-by: Mark Brown --- sound/soc/codecs/nau8825.c | 51 +++++++++----------------------------- 1 file changed, 12 insertions(+), 39 deletions(-) diff --git a/sound/soc/codecs/nau8825.c b/sound/soc/codecs/nau8825.c index 5c9707ac4bbf..20d2f1578b87 100644 --- a/sound/soc/codecs/nau8825.c +++ b/sound/soc/codecs/nau8825.c @@ -212,31 +212,6 @@ static const unsigned short logtable[256] = { 0xfa2f, 0xfaea, 0xfba5, 0xfc60, 0xfd1a, 0xfdd4, 0xfe8e, 0xff47 }; -static struct snd_soc_dai *nau8825_get_codec_dai(struct nau8825 *nau8825) -{ - struct snd_soc_codec *codec = snd_soc_dapm_to_codec(nau8825->dapm); - struct snd_soc_component *component = &codec->component; - struct snd_soc_dai *codec_dai, *_dai; - - list_for_each_entry_safe(codec_dai, _dai, &component->dai_list, list) { - if (!strncmp(codec_dai->name, NUVOTON_CODEC_DAI, - strlen(NUVOTON_CODEC_DAI))) - return codec_dai; - } - return NULL; -} - -static bool nau8825_dai_is_active(struct nau8825 *nau8825) -{ - struct snd_soc_dai *codec_dai = nau8825_get_codec_dai(nau8825); - - if (codec_dai) { - if (codec_dai->playback_active || codec_dai->capture_active) - return true; - } - return false; -} - /** * nau8825_sema_acquire - acquire the semaphore of nau88l25 * @nau8825: component to register the codec private data with @@ -1205,6 +1180,8 @@ static int nau8825_hw_params(struct snd_pcm_substream *substream, struct nau8825 *nau8825 = snd_soc_codec_get_drvdata(codec); unsigned int val_len = 0; + nau8825_sema_acquire(nau8825, 2 * HZ); + switch (params_width(params)) { case 16: val_len |= NAU8825_I2S_DL_16; @@ -1225,6 +1202,9 @@ static int nau8825_hw_params(struct snd_pcm_substream *substream, regmap_update_bits(nau8825->regmap, NAU8825_REG_I2S_PCM_CTRL1, NAU8825_I2S_DL_MASK, val_len); + /* Release the semaphone. */ + nau8825_sema_release(nau8825); + return 0; } @@ -1234,6 +1214,8 @@ static int nau8825_set_dai_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt) struct nau8825 *nau8825 = snd_soc_codec_get_drvdata(codec); unsigned int ctrl1_val = 0, ctrl2_val = 0; + nau8825_sema_acquire(nau8825, 2 * HZ); + switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) { case SND_SOC_DAIFMT_CBM_CFM: ctrl2_val |= NAU8825_I2S_MS_MASTER; @@ -1282,6 +1264,9 @@ static int nau8825_set_dai_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt) regmap_update_bits(nau8825->regmap, NAU8825_REG_I2S_PCM_CTRL2, NAU8825_I2S_MS_MASK, ctrl2_val); + /* Release the semaphone. */ + nau8825_sema_release(nau8825); + return 0; } @@ -2241,20 +2226,8 @@ static int __maybe_unused nau8825_resume(struct snd_soc_codec *codec) regcache_cache_only(nau8825->regmap, false); regcache_sync(nau8825->regmap); - if (nau8825_is_jack_inserted(nau8825->regmap)) { - /* If the jack is inserted, we need to check whether the play- - * back is active before suspend. If active, the driver has to - * raise the protection for cross talk function to avoid the - * playback recovers before cross talk process finish. Other- - * wise, the playback will be interfered by cross talk func- - * tion. It is better to apply hardware related parameters - * before starting playback or record. - */ - if (nau8825_dai_is_active(nau8825)) { - nau8825->xtalk_protect = true; - nau8825_sema_acquire(nau8825, 0); - } - } + nau8825->xtalk_protect = true; + nau8825_sema_acquire(nau8825, 0); enable_irq(nau8825->irq); return 0; From 06746c672cdd60715ee57ab1aced95a9e536fd4d Mon Sep 17 00:00:00 2001 From: John Hsu Date: Thu, 4 Aug 2016 16:52:07 +0800 Subject: [PATCH 011/531] ASoC: nau8825: fix static check error about semaphone control The patch is to fix the static check error as the following. The patch commit b50455fab459 ("ASoC: nau8825: cross talk suppression measurement function") from Jun 7, 2016, leads to the following static checker warning: sound/soc/codecs/nau8825.c:265 nau8825_sema_acquire() warn: 'sem:&nau8825->xtalk_sem' is sometimes locked here and sometimes unlocked. The semaphone acquire function has return value, and some callers can do error handling when lock fails. Signed-off-by: John Hsu Signed-off-by: Mark Brown --- sound/soc/codecs/nau8825.c | 29 +++++++++++++++++++++-------- 1 file changed, 21 insertions(+), 8 deletions(-) diff --git a/sound/soc/codecs/nau8825.c b/sound/soc/codecs/nau8825.c index 20d2f1578b87..2e59a85e360b 100644 --- a/sound/soc/codecs/nau8825.c +++ b/sound/soc/codecs/nau8825.c @@ -225,19 +225,26 @@ static const unsigned short logtable[256] = { * Acquires the semaphore without jiffies. If no more tasks are allowed * to acquire the semaphore, calling this function will put the task to * sleep until the semaphore is released. - * It returns if the semaphore was acquired. + * If the semaphore is not released within the specified number of jiffies, + * this function returns -ETIME. + * If the sleep is interrupted by a signal, this function will return -EINTR. + * It returns 0 if the semaphore was acquired successfully. */ -static void nau8825_sema_acquire(struct nau8825 *nau8825, long timeout) +static int nau8825_sema_acquire(struct nau8825 *nau8825, long timeout) { int ret; - if (timeout) + if (timeout) { ret = down_timeout(&nau8825->xtalk_sem, timeout); - else + if (ret < 0) + dev_warn(nau8825->dev, "Acquire semaphone timeout\n"); + } else { ret = down_interruptible(&nau8825->xtalk_sem); + if (ret < 0) + dev_warn(nau8825->dev, "Acquire semaphone fail\n"); + } - if (ret < 0) - dev_warn(nau8825->dev, "Acquire semaphone fail\n"); + return ret; } /** @@ -1596,8 +1603,11 @@ static irqreturn_t nau8825_interrupt(int irq, void *data) * cess and restore changes if process * is ongoing when ejection. */ + int ret; nau8825->xtalk_protect = true; - nau8825_sema_acquire(nau8825, 0); + ret = nau8825_sema_acquire(nau8825, 0); + if (ret < 0) + nau8825->xtalk_protect = false; } /* Startup cross talk detection process */ nau8825->xtalk_state = NAU8825_XTALK_PREPARE; @@ -2223,11 +2233,14 @@ static int __maybe_unused nau8825_suspend(struct snd_soc_codec *codec) static int __maybe_unused nau8825_resume(struct snd_soc_codec *codec) { struct nau8825 *nau8825 = snd_soc_codec_get_drvdata(codec); + int ret; regcache_cache_only(nau8825->regmap, false); regcache_sync(nau8825->regmap); nau8825->xtalk_protect = true; - nau8825_sema_acquire(nau8825, 0); + ret = nau8825_sema_acquire(nau8825, 0); + if (ret < 0) + nau8825->xtalk_protect = false; enable_irq(nau8825->irq); return 0; From 5d764912a0ee6db83e962c1501b5b9e58ba14e15 Mon Sep 17 00:00:00 2001 From: Adam Thomson Date: Thu, 4 Aug 2016 15:35:37 +0100 Subject: [PATCH 012/531] ASoC: da7213: Default to 64 BCLKs per WCLK to support all formats Previously code defaulted to 32 BCLKS per WCLK which meant 24 and 32 bit DAI formats would not work properly. This patch fixes the issue by defaulting to 64 BCLKs per WCLK. Signed-off-by: Adam Thomson Signed-off-by: Mark Brown --- sound/soc/codecs/da7213.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/soc/codecs/da7213.c b/sound/soc/codecs/da7213.c index e5527bc570ae..bcf1834c5648 100644 --- a/sound/soc/codecs/da7213.c +++ b/sound/soc/codecs/da7213.c @@ -1247,8 +1247,8 @@ static int da7213_set_dai_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt) return -EINVAL; } - /* By default only 32 BCLK per WCLK is supported */ - dai_clk_mode |= DA7213_DAI_BCLKS_PER_WCLK_32; + /* By default only 64 BCLK per WCLK is supported */ + dai_clk_mode |= DA7213_DAI_BCLKS_PER_WCLK_64; snd_soc_write(codec, DA7213_DAI_CLK_MODE, dai_clk_mode); snd_soc_update_bits(codec, DA7213_DAI_CTRL, DA7213_DAI_FORMAT_MASK, From d9dd26b20cff88b45d861ec786d86b1c9bd2ee60 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Sat, 30 Jul 2016 10:05:31 -0700 Subject: [PATCH 013/531] MD: hold mddev lock to change bitmap location Changing the location changes a lot of things. Holding the lock to avoid race. This makes the .quiesce called with mddev lock hold too. Acked-by: NeilBrown Signed-off-by: Shaohua Li --- drivers/md/bitmap.c | 47 +++++++++++++++++++++++++++++++-------------- 1 file changed, 33 insertions(+), 14 deletions(-) diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index 6fff794e0c72..13041ee37ad6 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -2183,19 +2183,29 @@ location_show(struct mddev *mddev, char *page) static ssize_t location_store(struct mddev *mddev, const char *buf, size_t len) { + int rv; + rv = mddev_lock(mddev); + if (rv) + return rv; if (mddev->pers) { - if (!mddev->pers->quiesce) - return -EBUSY; - if (mddev->recovery || mddev->sync_thread) - return -EBUSY; + if (!mddev->pers->quiesce) { + rv = -EBUSY; + goto out; + } + if (mddev->recovery || mddev->sync_thread) { + rv = -EBUSY; + goto out; + } } if (mddev->bitmap || mddev->bitmap_info.file || mddev->bitmap_info.offset) { /* bitmap already configured. Only option is to clear it */ - if (strncmp(buf, "none", 4) != 0) - return -EBUSY; + if (strncmp(buf, "none", 4) != 0) { + rv = -EBUSY; + goto out; + } if (mddev->pers) { mddev->pers->quiesce(mddev, 1); bitmap_destroy(mddev); @@ -2214,21 +2224,25 @@ location_store(struct mddev *mddev, const char *buf, size_t len) /* nothing to be done */; else if (strncmp(buf, "file:", 5) == 0) { /* Not supported yet */ - return -EINVAL; + rv = -EINVAL; + goto out; } else { - int rv; if (buf[0] == '+') rv = kstrtoll(buf+1, 10, &offset); else rv = kstrtoll(buf, 10, &offset); if (rv) - return rv; - if (offset == 0) - return -EINVAL; + goto out; + if (offset == 0) { + rv = -EINVAL; + goto out; + } if (mddev->bitmap_info.external == 0 && mddev->major_version == 0 && - offset != mddev->bitmap_info.default_offset) - return -EINVAL; + offset != mddev->bitmap_info.default_offset) { + rv = -EINVAL; + goto out; + } mddev->bitmap_info.offset = offset; if (mddev->pers) { struct bitmap *bitmap; @@ -2245,7 +2259,7 @@ location_store(struct mddev *mddev, const char *buf, size_t len) mddev->pers->quiesce(mddev, 0); if (rv) { bitmap_destroy(mddev); - return rv; + goto out; } } } @@ -2257,6 +2271,11 @@ location_store(struct mddev *mddev, const char *buf, size_t len) set_bit(MD_CHANGE_DEVS, &mddev->flags); md_wakeup_thread(mddev->thread); } + rv = 0; +out: + mddev_unlock(mddev); + if (rv) + return rv; return len; } From 11367799f3d12a5074c4a3c0fa4ea8da2a21a2a4 Mon Sep 17 00:00:00 2001 From: Alexey Obitotskiy Date: Wed, 3 Aug 2016 10:02:56 +0200 Subject: [PATCH 014/531] md: Prevent IO hold during accessing to faulty raid5 array After array enters in faulty state (e.g. number of failed drives becomes more then accepted for raid5 level) it sets error flags (one of this flags is MD_CHANGE_PENDING). For internal metadata arrays MD_CHANGE_PENDING cleared into md_update_sb, but not for external metadata arrays. MD_CHANGE_PENDING flag set prevents to finish all new or non-finished IOs to array and hold them in pending state. In some cases this can leads to deadlock situation. For example, we have faulty array (2 of 4 drives failed) and udev handle array state changes and blkid started (or other userspace application that used array to read/write) but unable to finish reads due to IO hold. At the same time we unable to get exclusive access to array (to stop array in our case) because another external application still use this array. Fix makes possible to return IO with errors immediately. So external application can finish working with array and give exclusive access to other applications to perform required management actions with array. Signed-off-by: Alexey Obitotskiy Signed-off-by: Shaohua Li --- drivers/md/raid5.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index e379b89fd8b1..4f8f5242ea3b 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -4640,7 +4640,9 @@ static void handle_stripe(struct stripe_head *sh) } if (!bio_list_empty(&s.return_bi)) { - if (test_bit(MD_CHANGE_PENDING, &conf->mddev->flags)) { + if (test_bit(MD_CHANGE_PENDING, &conf->mddev->flags) && + (s.failed <= conf->max_degraded || + conf->mddev->external == 0)) { spin_lock_irq(&conf->device_lock); bio_list_merge(&conf->return_bi, &s.return_bi); spin_unlock_irq(&conf->device_lock); From 925baf394bb0e65d85330afe467393f66f910353 Mon Sep 17 00:00:00 2001 From: Baruch Siach Date: Wed, 27 Jul 2016 08:41:49 +0300 Subject: [PATCH 015/531] tools/gpio: fix gpio-event-mon header comment Fixes: 97f69747d8b1 ('tools/gpio: add the gpio-event-mon tool') Signed-off-by: Baruch Siach Signed-off-by: Linus Walleij --- tools/gpio/gpio-event-mon.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/gpio/gpio-event-mon.c b/tools/gpio/gpio-event-mon.c index 448ed96b3b4f..1c14c2595158 100644 --- a/tools/gpio/gpio-event-mon.c +++ b/tools/gpio/gpio-event-mon.c @@ -1,5 +1,5 @@ /* - * gpio-hammer - example swiss army knife to shake GPIO lines on a system + * gpio-event-mon - monitor GPIO line events from userspace * * Copyright (C) 2016 Linus Walleij * From 626d2f07de89bf6be3d7301524d0ab3375b81b9c Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Thu, 4 Aug 2016 19:59:41 +0900 Subject: [PATCH 016/531] dmaengine: usb-dmac: check CHCR.DE bit in usb_dmac_isr_channel() The USB-DMAC's interruption happens even if the CHCR.DE is not set to 1 because CHCR.NULLE is set to 1. So, this driver should call usb_dmac_isr_transfer_end() if the DE bit is set to 1 only. Otherwise, the desc is possible to be NULL in the usb_dmac_isr_transfer_end(). Fixes: 0c1c8ff32fa2 ("dmaengine: usb-dmac: Add Renesas USB DMA Controller (USB-DMAC) driver) Cc: # v4.1+ Signed-off-by: Yoshihiro Shimoda Signed-off-by: Vinod Koul --- drivers/dma/sh/usb-dmac.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/drivers/dma/sh/usb-dmac.c b/drivers/dma/sh/usb-dmac.c index 749f1bd5d65d..06ecdc38cee0 100644 --- a/drivers/dma/sh/usb-dmac.c +++ b/drivers/dma/sh/usb-dmac.c @@ -600,27 +600,30 @@ static irqreturn_t usb_dmac_isr_channel(int irq, void *dev) { struct usb_dmac_chan *chan = dev; irqreturn_t ret = IRQ_NONE; - u32 mask = USB_DMACHCR_TE; - u32 check_bits = USB_DMACHCR_TE | USB_DMACHCR_SP; + u32 mask = 0; u32 chcr; + bool xfer_end = false; spin_lock(&chan->vc.lock); chcr = usb_dmac_chan_read(chan, USB_DMACHCR); - if (chcr & check_bits) - mask |= USB_DMACHCR_DE | check_bits; + if (chcr & (USB_DMACHCR_TE | USB_DMACHCR_SP)) { + mask |= USB_DMACHCR_DE | USB_DMACHCR_TE | USB_DMACHCR_SP; + if (chcr & USB_DMACHCR_DE) + xfer_end = true; + ret |= IRQ_HANDLED; + } if (chcr & USB_DMACHCR_NULL) { /* An interruption of TE will happen after we set FTE */ mask |= USB_DMACHCR_NULL; chcr |= USB_DMACHCR_FTE; ret |= IRQ_HANDLED; } - usb_dmac_chan_write(chan, USB_DMACHCR, chcr & ~mask); + if (mask) + usb_dmac_chan_write(chan, USB_DMACHCR, chcr & ~mask); - if (chcr & check_bits) { + if (xfer_end) usb_dmac_isr_transfer_end(chan); - ret |= IRQ_HANDLED; - } spin_unlock(&chan->vc.lock); From 0956254a2d5b9e2141385514553aeef694dfe3b5 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 8 Aug 2016 15:08:49 +0200 Subject: [PATCH 017/531] ovl: don't copy up opaqueness When a copy up of a directory occurs which has the opaque xattr set, the xattr remains in the upper directory. The immediate behavior with overlayfs is that the upper directory is not treated as opaque, however after a remount the opaque flag is used and upper directory is treated as opaque. This causes files created in the lower layer to be hidden when using multiple lower directories. Fix by not copying up the opaque flag. To reproduce: ----8<---------8<---------8<---------8<---------8<---------8<---- mkdir -p l/d/s u v w mnt mount -t overlay overlay -olowerdir=l,upperdir=u,workdir=w mnt rm -rf mnt/d/ mkdir -p mnt/d/n umount mnt mount -t overlay overlay -olowerdir=u:l,upperdir=v,workdir=w mnt touch mnt/d/foo umount mnt mount -t overlay overlay -olowerdir=u:l,upperdir=v,workdir=w mnt ls mnt/d ----8<---------8<---------8<---------8<---------8<---------8<---- output should be: "foo n" Reported-by: Derek McGowan Link: https://bugzilla.kernel.org/show_bug.cgi?id=151291 Signed-off-by: Miklos Szeredi Cc: --- fs/overlayfs/copy_up.c | 2 ++ fs/overlayfs/inode.c | 2 +- fs/overlayfs/overlayfs.h | 1 + 3 files changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 54e5d6681786..43fdc2765aea 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -80,6 +80,8 @@ int ovl_copy_xattr(struct dentry *old, struct dentry *new) } for (name = buf; name < (buf + list_size); name += strlen(name) + 1) { + if (ovl_is_private_xattr(name)) + continue; retry: size = vfs_getxattr(old, name, value, value_size); if (size == -ERANGE) diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 1b885c156028..024352f1d405 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -191,7 +191,7 @@ static int ovl_readlink(struct dentry *dentry, char __user *buf, int bufsiz) return err; } -static bool ovl_is_private_xattr(const char *name) +bool ovl_is_private_xattr(const char *name) { #define OVL_XATTR_PRE_NAME OVL_XATTR_PREFIX "." return strncmp(name, OVL_XATTR_PRE_NAME, diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index e4f5c9536bfe..34839bd2b6b8 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -193,6 +193,7 @@ int ovl_removexattr(struct dentry *dentry, const char *name); struct posix_acl *ovl_get_acl(struct inode *inode, int type); int ovl_open_maybe_copy_up(struct dentry *dentry, unsigned int file_flags); int ovl_update_time(struct inode *inode, struct timespec *ts, int flags); +bool ovl_is_private_xattr(const char *name); struct inode *ovl_new_inode(struct super_block *sb, umode_t mode); struct inode *ovl_get_inode(struct super_block *sb, struct inode *realinode); From fd837b08d98c0c9f4f31998f2ed55b9d8694082c Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Mon, 8 Aug 2016 17:29:28 +0100 Subject: [PATCH 018/531] KVM: arm64: ITS: return 1 on successful MSI injection According to the KVM API documentation a successful MSI injection should return a value > 0 on success. Return possible errors in vgic_its_trigger_msi() and report a successful injection back to userland, while also reporting the case where the MSI could not be delivered due to the guest not having the LPI mapped, for instance. Signed-off-by: Andre Przywara Reviewed-by: Eric Auger Reviewed-by: Christoffer Dall Signed-off-by: Christoffer Dall --- include/linux/irqchip/arm-gic-v3.h | 1 + virt/kvm/arm/vgic/vgic-its.c | 54 ++++++++++++++++++++---------- 2 files changed, 37 insertions(+), 18 deletions(-) diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 56b0b7ec66aa..99ac022edc60 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -337,6 +337,7 @@ */ #define E_ITS_MOVI_UNMAPPED_INTERRUPT 0x010107 #define E_ITS_MOVI_UNMAPPED_COLLECTION 0x010109 +#define E_ITS_INT_UNMAPPED_INTERRUPT 0x010307 #define E_ITS_CLEAR_UNMAPPED_INTERRUPT 0x010507 #define E_ITS_MAPD_DEVICE_OOR 0x010801 #define E_ITS_MAPC_PROCNUM_OOR 0x010902 diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index 07411cf967b9..1bd8adbeae26 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -441,39 +441,48 @@ static unsigned long vgic_mmio_read_its_idregs(struct kvm *kvm, * Find the target VCPU and the LPI number for a given devid/eventid pair * and make this IRQ pending, possibly injecting it. * Must be called with the its_lock mutex held. + * Returns 0 on success, a positive error value for any ITS mapping + * related errors and negative error values for generic errors. */ -static void vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its, - u32 devid, u32 eventid) +static int vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its, + u32 devid, u32 eventid) { + struct kvm_vcpu *vcpu; struct its_itte *itte; if (!its->enabled) - return; + return -EBUSY; itte = find_itte(its, devid, eventid); - /* Triggering an unmapped IRQ gets silently dropped. */ - if (itte && its_is_collection_mapped(itte->collection)) { - struct kvm_vcpu *vcpu; + if (!itte || !its_is_collection_mapped(itte->collection)) + return E_ITS_INT_UNMAPPED_INTERRUPT; - vcpu = kvm_get_vcpu(kvm, itte->collection->target_addr); - if (vcpu && vcpu->arch.vgic_cpu.lpis_enabled) { - spin_lock(&itte->irq->irq_lock); - itte->irq->pending = true; - vgic_queue_irq_unlock(kvm, itte->irq); - } - } + vcpu = kvm_get_vcpu(kvm, itte->collection->target_addr); + if (!vcpu) + return E_ITS_INT_UNMAPPED_INTERRUPT; + + if (!vcpu->arch.vgic_cpu.lpis_enabled) + return -EBUSY; + + spin_lock(&itte->irq->irq_lock); + itte->irq->pending = true; + vgic_queue_irq_unlock(kvm, itte->irq); + + return 0; } /* * Queries the KVM IO bus framework to get the ITS pointer from the given * doorbell address. * We then call vgic_its_trigger_msi() with the decoded data. + * According to the KVM_SIGNAL_MSI API description returns 1 on success. */ int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi) { u64 address; struct kvm_io_device *kvm_io_dev; struct vgic_io_device *iodev; + int ret; if (!vgic_has_its(kvm)) return -ENODEV; @@ -490,10 +499,21 @@ int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi) iodev = container_of(kvm_io_dev, struct vgic_io_device, dev); mutex_lock(&iodev->its->its_lock); - vgic_its_trigger_msi(kvm, iodev->its, msi->devid, msi->data); + ret = vgic_its_trigger_msi(kvm, iodev->its, msi->devid, msi->data); mutex_unlock(&iodev->its->its_lock); - return 0; + if (ret < 0) + return ret; + + /* + * KVM_SIGNAL_MSI demands a return value > 0 for success and 0 + * if the guest has blocked the MSI. So we map any LPI mapping + * related error to that. + */ + if (ret) + return 0; + else + return 1; } /* Requires the its_lock to be held. */ @@ -981,9 +1001,7 @@ static int vgic_its_cmd_handle_int(struct kvm *kvm, struct vgic_its *its, u32 msi_data = its_cmd_get_id(its_cmd); u64 msi_devid = its_cmd_get_deviceid(its_cmd); - vgic_its_trigger_msi(kvm, its, msi_devid, msi_data); - - return 0; + return vgic_its_trigger_msi(kvm, its, msi_devid, msi_data); } /* From 8b078c603249239f597dc395ac182667c8e0af9c Mon Sep 17 00:00:00 2001 From: Mathias Koehrer Date: Tue, 9 Aug 2016 10:33:31 +0200 Subject: [PATCH 019/531] PCI: Update "pci=resource_alignment" documentation Some uio based PCI drivers, e.g., uio_cif, do not work if the assigned PCI memory resources are not page aligned. By using the kernel option "pci=resource_alignment=@:." it is possible to request page alignment for memory resources of devices. However, this is cumbersome when using several devices, and the bus/slot/func addresses may change if devices are added to or removed from the system. Extend the "pci=resource_alignment" option so we can specify the relevant devices via PCI vendor, device, subvendor, and subdevice IDs. The specification of the devices via IDs is indicated by a leading string "pci:" as argument to "pci=resource_alignment". The format of the specification is pci::[::] Examples: pci=resource_alignment=4096@pci:8086:9c22:103c:198f pci=resource_alignment=pci:8086:9c22 # defaults to PAGE_SIZE align [bhelgaas: changelog, use actual vendor/device IDs in examples] Signed-off-by: Mathias Koehrer Signed-off-by: Bjorn Helgaas --- Documentation/kernel-parameters.txt | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 46c030a49186..a4f4d693e2c1 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -3032,6 +3032,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted. PAGE_SIZE is used as alignment. PCI-PCI bridge can be specified, if resource windows need to be expanded. + To specify the alignment for several + instances of a device, the PCI vendor, + device, subvendor, and subdevice may be + specified, e.g., 4096@pci:8086:9c22:103c:198f ecrc= Enable/disable PCIe ECRC (transaction layer end-to-end CRC checking). bios: Use BIOS/firmware settings. This is the From 06f4e94898918bcad00cdd4d349313a439d6911e Mon Sep 17 00:00:00 2001 From: Zefan Li Date: Tue, 9 Aug 2016 11:25:01 +0800 Subject: [PATCH 020/531] cpuset: make sure new tasks conform to the current config of the cpuset A new task inherits cpus_allowed and mems_allowed masks from its parent, but if someone changes cpuset's config by writing to cpuset.cpus/cpuset.mems before this new task is inserted into the cgroup's task list, the new task won't be updated accordingly. Signed-off-by: Zefan Li Signed-off-by: Tejun Heo Cc: stable@vger.kernel.org --- kernel/cpuset.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/kernel/cpuset.c b/kernel/cpuset.c index c7fd2778ed50..c27e53326bef 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -2069,6 +2069,20 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css) mutex_unlock(&cpuset_mutex); } +/* + * Make sure the new task conform to the current state of its parent, + * which could have been changed by cpuset just after it inherits the + * state from the parent and before it sits on the cgroup's task list. + */ +void cpuset_fork(struct task_struct *task) +{ + if (task_css_is_root(task, cpuset_cgrp_id)) + return; + + set_cpus_allowed_ptr(task, ¤t->cpus_allowed); + task->mems_allowed = current->mems_allowed; +} + struct cgroup_subsys cpuset_cgrp_subsys = { .css_alloc = cpuset_css_alloc, .css_online = cpuset_css_online, @@ -2079,6 +2093,7 @@ struct cgroup_subsys cpuset_cgrp_subsys = { .attach = cpuset_attach, .post_attach = cpuset_post_attach, .bind = cpuset_bind, + .fork = cpuset_fork, .legacy_cftypes = files, .early_init = true, }; From 99e5e886a0a59df267ff6838f763b789847df982 Mon Sep 17 00:00:00 2001 From: Christoffer Dall Date: Mon, 1 Aug 2016 20:25:33 +0200 Subject: [PATCH 021/531] KVM: arm64: vgic-its: Handle errors from vgic_add_lpi During low memory conditions, we could be dereferencing a NULL pointer when vgic_add_lpi fails to allocate memory. Consider for example this call sequence: vgic_its_cmd_handle_mapi itte->irq = vgic_add_lpi(kvm, lpi_nr); update_lpi_config(kvm, itte->irq, NULL); ret = kvm_read_guest(kvm, propbase + irq->intid ^^^^ kaboom? Instead, return an error pointer from vgic_add_lpi and check the return value from its single caller. Signed-off-by: Christoffer Dall --- virt/kvm/arm/vgic/vgic-its.c | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index 1bd8adbeae26..d06330abd5e8 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -51,7 +51,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid) irq = kzalloc(sizeof(struct vgic_irq), GFP_KERNEL); if (!irq) - return NULL; + return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&irq->lpi_list); INIT_LIST_HEAD(&irq->ap_list); @@ -522,7 +522,8 @@ static void its_free_itte(struct kvm *kvm, struct its_itte *itte) list_del(&itte->itte_list); /* This put matches the get in vgic_add_lpi. */ - vgic_put_irq(kvm, itte->irq); + if (itte->irq) + vgic_put_irq(kvm, itte->irq); kfree(itte); } @@ -713,10 +714,11 @@ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its, u32 device_id = its_cmd_get_deviceid(its_cmd); u32 event_id = its_cmd_get_id(its_cmd); u32 coll_id = its_cmd_get_collection(its_cmd); - struct its_itte *itte; + struct its_itte *itte, *new_itte = NULL; struct its_device *device; struct its_collection *collection, *new_coll = NULL; int lpi_nr; + struct vgic_irq *irq; device = find_its_device(its, device_id); if (!device) @@ -747,13 +749,24 @@ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its, return -ENOMEM; } + new_itte = itte; itte->event_id = event_id; list_add_tail(&itte->itte_list, &device->itt_head); } itte->collection = collection; itte->lpi = lpi_nr; - itte->irq = vgic_add_lpi(kvm, lpi_nr); + + irq = vgic_add_lpi(kvm, lpi_nr); + if (IS_ERR(irq)) { + if (new_coll) + vgic_its_free_collection(its, coll_id); + if (new_itte) + its_free_itte(kvm, new_itte); + return PTR_ERR(irq); + } + itte->irq = irq; + update_affinity_itte(kvm, itte); /* From 2cccbb368a2bf27d98cf36bb424fbbf5572c0fab Mon Sep 17 00:00:00 2001 From: Christoffer Dall Date: Tue, 2 Aug 2016 22:05:42 +0200 Subject: [PATCH 022/531] KVM: arm64: vgic-its: Plug race in vgic_put_irq Right now the following sequence of events can happen: 1. Thread X calls vgic_put_irq 2. Thread Y calls vgic_add_lpi 3. Thread Y gets lpi_list_lock 4. Thread X drops the ref count to 0 and blocks on lpi_list_lock 5. Thread Y finds the irq via the lpi_list_lock, raises the ref count to 1, and release the lpi_list_lock. 6. Thread X proceeds and frees the irq. Avoid this by holding the spinlock around the kref_put. Reviewed-by: Andre Przywara Signed-off-by: Christoffer Dall --- virt/kvm/arm/vgic/vgic.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c index e7aeac719e09..e83b7fe4baae 100644 --- a/virt/kvm/arm/vgic/vgic.c +++ b/virt/kvm/arm/vgic/vgic.c @@ -117,17 +117,17 @@ static void vgic_irq_release(struct kref *ref) void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq) { - struct vgic_dist *dist; + struct vgic_dist *dist = &kvm->arch.vgic; if (irq->intid < VGIC_MIN_LPI) return; - if (!kref_put(&irq->refcount, vgic_irq_release)) - return; - - dist = &kvm->arch.vgic; - spin_lock(&dist->lpi_list_lock); + if (!kref_put(&irq->refcount, vgic_irq_release)) { + spin_unlock(&dist->lpi_list_lock); + return; + }; + list_del(&irq->lpi_list); dist->lpi_list_count--; spin_unlock(&dist->lpi_list_lock); From 6f4deb18a505523eb7925d646574a95f9e982ff7 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 8 Aug 2016 15:58:56 +0200 Subject: [PATCH 023/531] gpio: max730x: set gpiochip data pointer before using it gpiochip_add_data() has to be called before calling max7301_direction_input() [ 4.389883] Unable to handle kernel paging request for data at address 0x00000018 [ 4.397282] Faulting instruction address: 0xc01a8cbc [ 4.402023] Oops: Kernel access of bad area, sig: 11 [#1] [ 4.407331] PREEMPT CMPC885 [ 4.410131] CPU: 0 PID: 6 Comm: kworker/u2:0 Not tainted 4.5.0-gacdfdee #39 [ 4.418592] Workqueue: deferwq deferred_probe_work_func [ 4.423711] task: c60798b0 ti: c608a000 task.ti: c608a000 [ 4.429038] NIP: c01a8cbc LR: c01a8e24 CTR: c01ff028 [ 4.433953] REGS: c608bad0 TRAP: 0300 Not tainted (4.5.0-s3k-dev-gacdfdee-svn-dirty) [ 4.441847] MSR: 00009032 CR: 33039553 XER: a000f940 [ 4.448395] DAR: 00000018 DSISR: c0000000 GPR00: c01a8e24 c608bb80 c60798b0 c60d6f6c 00000004 00000002 07de2900 00700000 GPR08: 00000000 00000000 c608a000 00001032 35039553 00000000 c002f37c c6010b64 GPR16: c6010a48 c6010a14 c6010a00 00000000 c0450000 c0453568 c0453438 c050db14 GPR24: c62662bc 00000009 ffffffaa c60d6f5d 00000001 00000000 00000000 00000000 [ 4.480371] NIP [c01a8cbc] max7301_direction_input+0x20/0x9c [ 4.485951] LR [c01a8e24] __max730x_probe+0xec/0x138 [ 4.490812] Call Trace: [ 4.493268] [c608bba0] [c01a8e24] __max730x_probe+0xec/0x138 [ 4.498878] [c608bbc0] [c01cc368] driver_probe_device+0x190/0x38c [ 4.504895] [c608bbf0] [c01ca918] bus_for_each_drv+0x58/0xb4 [ 4.510489] [c608bc20] [c01cc04c] __device_attach+0x8c/0x110 [ 4.516082] [c608bc50] [c01cab80] bus_probe_device+0x34/0xb8 [ 4.521673] [c608bc70] [c01c96c8] device_add+0x3c0/0x598 [ 4.526925] [c608bcb0] [c0200f90] spi_add_device+0x114/0x160 [ 4.532512] [c608bcd0] [c02018d0] spi_register_master+0x6e0/0x7c8 [ 4.538537] [c608bd20] [c02019fc] devm_spi_register_master+0x44/0x8c [ 4.544824] [c608bd40] [c0203854] of_fsl_spi_probe+0x458/0x57c [ 4.550587] [c608bda0] [c01cd828] platform_drv_probe+0x30/0x74 [ 4.556366] [c608bdb0] [c01cc368] driver_probe_device+0x190/0x38c [ 4.562383] [c608bde0] [c01ca918] bus_for_each_drv+0x58/0xb4 [ 4.567977] [c608be10] [c01cc04c] __device_attach+0x8c/0x110 [ 4.573572] [c608be40] [c01cab80] bus_probe_device+0x34/0xb8 [ 4.579170] [c608be60] [c01cb9b4] deferred_probe_work_func+0xa4/0xc4 [ 4.585438] [c608be80] [c0029c04] process_one_work+0x22c/0x414 [ 4.591201] [c608bea0] [c002a100] worker_thread+0x314/0x5c0 [ 4.596722] [c608bef0] [c002f444] kthread+0xc8/0xcc [ 4.601538] [c608bf40] [c000af84] ret_from_kernel_thread+0x5c/0x64 [ 4.607596] Instruction dump: [ 4.610530] 7c0803a6 bba10014 38210020 4e800020 7c0802a6 9421ffe0 38840004 bf810010 [ 4.618188] 90010024 549cf0be 83c30010 549d0f7c <813e0018> 7fc3f378 7d3f2430 57ff07fe [ 4.626041] ---[ end trace 303adb021dd4caf2 ]--- Cc: stable@vger.kernel.org fixes: 5e45e01916197 ("gpio: max730x: use gpiochip data pointer") Signed-off-by: Christophe Leroy Signed-off-by: Linus Walleij --- drivers/gpio/gpio-max730x.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpio/gpio-max730x.c b/drivers/gpio/gpio-max730x.c index 08807368f007..946d09195598 100644 --- a/drivers/gpio/gpio-max730x.c +++ b/drivers/gpio/gpio-max730x.c @@ -192,6 +192,10 @@ int __max730x_probe(struct max7301 *ts) ts->chip.parent = dev; ts->chip.owner = THIS_MODULE; + ret = gpiochip_add_data(&ts->chip, ts); + if (ret) + goto exit_destroy; + /* * initialize pullups according to platform data and cache the * register values for later use. @@ -213,10 +217,6 @@ int __max730x_probe(struct max7301 *ts) } } - ret = gpiochip_add_data(&ts->chip, ts); - if (ret) - goto exit_destroy; - return ret; exit_destroy: From 18b43e89d295cc65151c505c643c98fb2c320e59 Mon Sep 17 00:00:00 2001 From: Daniel Mentz Date: Thu, 4 Aug 2016 17:56:53 -0700 Subject: [PATCH 024/531] ARC: Call trace_hardirqs_on() before enabling irqs trace_hardirqs_on_caller() in lockdep.c expects to be called before, not after interrupts are actually enabled. The following comment in kernel/locking/lockdep.c substantiates this claim: " /* * We're enabling irqs and according to our state above irqs weren't * already enabled, yet we find the hardware thinks they are in fact * enabled.. someone messed up their IRQ state tracing. */ " An example can be found in include/linux/irqflags.h: do { trace_hardirqs_on(); raw_local_irq_enable(); } while (0) Without this change, we hit the following DEBUG_LOCKS_WARN_ON. [ 7.760000] ------------[ cut here ]------------ [ 7.760000] WARNING: CPU: 0 PID: 1 at kernel/locking/lockdep.c:2711 resume_user_mode_begin+0x48/0xf0 [ 7.770000] DEBUG_LOCKS_WARN_ON(!irqs_disabled()) [ 7.780000] Modules linked in: [ 7.780000] CPU: 0 PID: 1 Comm: init Not tainted 4.7.0-00003-gc668bb9-dirty #366 [ 7.790000] [ 7.790000] Stack Trace: [ 7.790000] arc_unwind_core.constprop.1+0xa4/0x118 [ 7.800000] warn_slowpath_fmt+0x72/0x158 [ 7.800000] resume_user_mode_begin+0x48/0xf0 [ 7.810000] ---[ end trace 6f6a7a8fae20d2f0 ]--- Signed-off-by: Daniel Mentz Cc: Signed-off-by: Vineet Gupta --- arch/arc/include/asm/irqflags-compact.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arc/include/asm/irqflags-compact.h b/arch/arc/include/asm/irqflags-compact.h index c1d36458bfb7..4c6eed80cd8b 100644 --- a/arch/arc/include/asm/irqflags-compact.h +++ b/arch/arc/include/asm/irqflags-compact.h @@ -188,10 +188,10 @@ static inline int arch_irqs_disabled(void) .endm .macro IRQ_ENABLE scratch + TRACE_ASM_IRQ_ENABLE lr \scratch, [status32] or \scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK) flag \scratch - TRACE_ASM_IRQ_ENABLE .endm #endif /* __ASSEMBLY__ */ From 45c3b08a117e2232fc8d7b9e849ead36386f4f96 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Mon, 13 Jun 2016 16:38:27 +0200 Subject: [PATCH 025/531] ARC: Elide redundant setup of DMA callbacks For resources shared by all cores such as SLC and IOC, only the master core needs to do any setups / enabling / disabling etc. Cc: Signed-off-by: Vineet Gupta --- arch/arc/mm/cache.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index 5a294b2c3cb3..0b10efe3a6a7 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -921,6 +921,15 @@ void arc_cache_init(void) printk(arc_cache_mumbojumbo(0, str, sizeof(str))); + /* + * Only master CPU needs to execute rest of function: + * - Assume SMP so all cores will have same cache config so + * any geomtry checks will be same for all + * - IOC setup / dma callbacks only need to be setup once + */ + if (cpu) + return; + if (IS_ENABLED(CONFIG_ARC_HAS_ICACHE)) { struct cpuinfo_arc_cache *ic = &cpuinfo_arc700[cpu].icache; From ed0ab110235c659fdb3f73d27907b1b45b89cf30 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Thu, 14 Jul 2016 10:42:35 +0800 Subject: [PATCH 026/531] clk: sunxi-ng: Fix inverted test condition in ccu_helper_wait_for_lock The condition passed to read*_poll_timeout() is the break condition, i.e. wait for this condition to happen and return success. The original code assumed the opposite, resulting in a warning when the PLL clock rate was changed but never lost it's lock as far as the readout indicated. This was verified by checking the read out register value. Fixes: 1d80c14248d6 ("clk: sunxi-ng: Add common infrastructure") Signed-off-by: Chen-Yu Tsai Acked-by: Maxime Ripard Signed-off-by: Stephen Boyd --- drivers/clk/sunxi-ng/ccu_common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/sunxi-ng/ccu_common.c b/drivers/clk/sunxi-ng/ccu_common.c index fc17b5295e16..51d4bac97ab3 100644 --- a/drivers/clk/sunxi-ng/ccu_common.c +++ b/drivers/clk/sunxi-ng/ccu_common.c @@ -31,7 +31,7 @@ void ccu_helper_wait_for_lock(struct ccu_common *common, u32 lock) return; WARN_ON(readl_relaxed_poll_timeout(common->base + common->reg, reg, - !(reg & lock), 100, 70000)); + reg & lock, 100, 70000)); } int sunxi_ccu_probe(struct device_node *node, void __iomem *reg, From 70fcad495b9903d362bdbf9ffba23259294064c8 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Thu, 11 Aug 2016 14:39:00 +0100 Subject: [PATCH 027/531] ASoC: Fix leak of rtd in soc_bind_dai_link If we fail to find a platform we simply return EPROBE_DEFER, but we have allocated the rtd pointer. All error paths before soc_add_pcm_runtime need to call soc_free_pcm_runtime first to avoid leaking the rtd pointer. A suitable error path already exists and is used else where in the function so simply use that here as well. Signed-off-by: Charles Keepax Signed-off-by: Mark Brown --- sound/soc/soc-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 16369cad4803..b0e23db83695 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -1056,7 +1056,7 @@ static int soc_bind_dai_link(struct snd_soc_card *card, if (!rtd->platform) { dev_err(card->dev, "ASoC: platform %s not registered\n", dai_link->platform_name); - return -EPROBE_DEFER; + goto _err_defer; } soc_add_pcm_runtime(card, rtd); From fa54aade5338937146bb6b8af93d2c27f6787ae1 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Thu, 11 Aug 2016 14:40:04 +0100 Subject: [PATCH 028/531] ASoC: wm2000: Fix return of uninitialised varible Anything that sets ret in wm2000_anc_transition will have immediately returned anyway as such we will always return an uninitialised ret at the bottom of the function. Simply replace the return with a return 0; Signed-off-by: Charles Keepax Signed-off-by: Mark Brown --- sound/soc/codecs/wm2000.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/codecs/wm2000.c b/sound/soc/codecs/wm2000.c index a67ea10f41a1..f2664396be6f 100644 --- a/sound/soc/codecs/wm2000.c +++ b/sound/soc/codecs/wm2000.c @@ -581,7 +581,7 @@ static int wm2000_anc_transition(struct wm2000_priv *wm2000, if (anc_transitions[i].dest == ANC_OFF) clk_disable_unprepare(wm2000->mclk); - return ret; + return 0; } static int wm2000_anc_set_mode(struct wm2000_priv *wm2000) From d0141191a20289f8955c1e03dad08e42e6f71ca9 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 11 Aug 2016 11:50:30 -0400 Subject: [PATCH 029/531] ext4: fix xattr shifting when expanding inodes The code in ext4_expand_extra_isize_ea() treated new_extra_isize argument sometimes as the desired target i_extra_isize and sometimes as the amount by which we need to grow current i_extra_isize. These happen to coincide when i_extra_isize is 0 which used to be the common case and so nobody noticed this until recently when we added i_projid to the inode and so i_extra_isize now needs to grow from 28 to 32 bytes. The result of these bugs was that we sometimes unnecessarily decided to move xattrs out of inode even if there was enough space and we often ended up corrupting in-inode xattrs because arguments to ext4_xattr_shift_entries() were just wrong. This could demonstrate itself as BUG_ON in ext4_xattr_shift_entries() triggering. Fix the problem by introducing new isize_diff variable and use it where appropriate. CC: stable@vger.kernel.org # 4.4.x Reported-by: Dave Chinner Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o --- fs/ext4/xattr.c | 27 ++++++++++++++------------- 1 file changed, 14 insertions(+), 13 deletions(-) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 39e9cfb1b371..cb1d7b4482de 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1353,11 +1353,13 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, size_t min_offs, free; int total_ino; void *base, *start, *end; - int extra_isize = 0, error = 0, tried_min_extra_isize = 0; + int error = 0, tried_min_extra_isize = 0; int s_min_extra_isize = le16_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_min_extra_isize); + int isize_diff; /* How much do we need to grow i_extra_isize */ down_write(&EXT4_I(inode)->xattr_sem); retry: + isize_diff = new_extra_isize - EXT4_I(inode)->i_extra_isize; if (EXT4_I(inode)->i_extra_isize >= new_extra_isize) { up_write(&EXT4_I(inode)->xattr_sem); return 0; @@ -1382,7 +1384,7 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, goto cleanup; free = ext4_xattr_free_space(last, &min_offs, base, &total_ino); - if (free >= new_extra_isize) { + if (free >= isize_diff) { entry = IFIRST(header); ext4_xattr_shift_entries(entry, EXT4_I(inode)->i_extra_isize - new_extra_isize, (void *)raw_inode + @@ -1414,7 +1416,7 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, end = bh->b_data + bh->b_size; min_offs = end - base; free = ext4_xattr_free_space(first, &min_offs, base, NULL); - if (free < new_extra_isize) { + if (free < isize_diff) { if (!tried_min_extra_isize && s_min_extra_isize) { tried_min_extra_isize++; new_extra_isize = s_min_extra_isize; @@ -1428,7 +1430,7 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, free = inode->i_sb->s_blocksize; } - while (new_extra_isize > 0) { + while (isize_diff > 0) { size_t offs, size, entry_size; struct ext4_xattr_entry *small_entry = NULL; struct ext4_xattr_info i = { @@ -1459,7 +1461,7 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, EXT4_XATTR_SIZE(le32_to_cpu(last->e_value_size)) + EXT4_XATTR_LEN(last->e_name_len); if (total_size <= free && total_size < min_total_size) { - if (total_size < new_extra_isize) { + if (total_size < isize_diff) { small_entry = last; } else { entry = last; @@ -1516,20 +1518,19 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, goto cleanup; entry = IFIRST(header); - if (entry_size + EXT4_XATTR_SIZE(size) >= new_extra_isize) - shift_bytes = new_extra_isize; + if (entry_size + EXT4_XATTR_SIZE(size) >= isize_diff) + shift_bytes = isize_diff; else shift_bytes = entry_size + size; /* Adjust the offsets and shift the remaining entries ahead */ - ext4_xattr_shift_entries(entry, EXT4_I(inode)->i_extra_isize - - shift_bytes, (void *)raw_inode + - EXT4_GOOD_OLD_INODE_SIZE + extra_isize + shift_bytes, + ext4_xattr_shift_entries(entry, -shift_bytes, + (void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE + + EXT4_I(inode)->i_extra_isize + shift_bytes, (void *)header, total_ino - entry_size, inode->i_sb->s_blocksize); - extra_isize += shift_bytes; - new_extra_isize -= shift_bytes; - EXT4_I(inode)->i_extra_isize = extra_isize; + isize_diff -= shift_bytes; + EXT4_I(inode)->i_extra_isize += shift_bytes; i.name = b_entry_name; i.value = buffer; From 418c12d08dc64a45107c467ec1ba29b5e69b0715 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 11 Aug 2016 11:58:32 -0400 Subject: [PATCH 030/531] ext4: fix xattr shifting when expanding inodes part 2 When multiple xattrs need to be moved out of inode, we did not properly recompute total size of xattr headers in the inode and the new header position. Thus when moving the second and further xattr we asked ext4_xattr_shift_entries() to move too much and from the wrong place, resulting in possible xattr value corruption or general memory corruption. CC: stable@vger.kernel.org # 4.4.x Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o --- fs/ext4/xattr.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index cb1d7b4482de..b18b1ff7cc27 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1516,6 +1516,7 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, error = ext4_xattr_ibody_set(handle, inode, &i, is); if (error) goto cleanup; + total_ino -= entry_size; entry = IFIRST(header); if (entry_size + EXT4_XATTR_SIZE(size) >= isize_diff) @@ -1526,11 +1527,11 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, ext4_xattr_shift_entries(entry, -shift_bytes, (void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE + EXT4_I(inode)->i_extra_isize + shift_bytes, - (void *)header, total_ino - entry_size, - inode->i_sb->s_blocksize); + (void *)header, total_ino, inode->i_sb->s_blocksize); isize_diff -= shift_bytes; EXT4_I(inode)->i_extra_isize += shift_bytes; + header = IHDR(inode, raw_inode); i.name = b_entry_name; i.value = buffer; From 443a8c41cd49de66a3fda45b32b9860ea0292b84 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 11 Aug 2016 12:00:01 -0400 Subject: [PATCH 031/531] ext4: properly align shifted xattrs when expanding inodes We did not count with the padding of xattr value when computing desired shift of xattrs in the inode when expanding i_extra_isize. As a result we could create unaligned start of inline xattrs. Account for alignment properly. CC: stable@vger.kernel.org # 4.4.x- Signed-off-by: Jan Kara --- fs/ext4/xattr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index b18b1ff7cc27..c893f00b6dc0 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1522,7 +1522,7 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, if (entry_size + EXT4_XATTR_SIZE(size) >= isize_diff) shift_bytes = isize_diff; else - shift_bytes = entry_size + size; + shift_bytes = entry_size + EXT4_XATTR_SIZE(size); /* Adjust the offsets and shift the remaining entries ahead */ ext4_xattr_shift_entries(entry, -shift_bytes, (void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE + From 2e81a4eeedcaa66e35f58b81e0755b87057ce392 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 11 Aug 2016 12:38:55 -0400 Subject: [PATCH 032/531] ext4: avoid deadlock when expanding inode size When we need to move xattrs into external xattr block, we call ext4_xattr_block_set() from ext4_expand_extra_isize_ea(). That may end up calling ext4_mark_inode_dirty() again which will recurse back into the inode expansion code leading to deadlocks. Protect from recursion using EXT4_STATE_NO_EXPAND inode flag and move its management into ext4_expand_extra_isize_ea() since its manipulation is safe there (due to xattr_sem) from possible races with ext4_xattr_set_handle() which plays with it as well. CC: stable@vger.kernel.org # 4.4.x Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o --- fs/ext4/inode.c | 2 -- fs/ext4/xattr.c | 19 +++++++++++++------ 2 files changed, 13 insertions(+), 8 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 5a6277d80f7c..13c95b290263 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5466,8 +5466,6 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode) sbi->s_want_extra_isize, iloc, handle); if (ret) { - ext4_set_inode_state(inode, - EXT4_STATE_NO_EXPAND); if (mnt_count != le16_to_cpu(sbi->s_es->s_mnt_count)) { ext4_warning(inode->i_sb, diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index c893f00b6dc0..2eb935ca5d9e 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1358,12 +1358,14 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, int isize_diff; /* How much do we need to grow i_extra_isize */ down_write(&EXT4_I(inode)->xattr_sem); + /* + * Set EXT4_STATE_NO_EXPAND to avoid recursion when marking inode dirty + */ + ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND); retry: isize_diff = new_extra_isize - EXT4_I(inode)->i_extra_isize; - if (EXT4_I(inode)->i_extra_isize >= new_extra_isize) { - up_write(&EXT4_I(inode)->xattr_sem); - return 0; - } + if (EXT4_I(inode)->i_extra_isize >= new_extra_isize) + goto out; header = IHDR(inode, raw_inode); entry = IFIRST(header); @@ -1392,8 +1394,7 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, (void *)header, total_ino, inode->i_sb->s_blocksize); EXT4_I(inode)->i_extra_isize = new_extra_isize; - error = 0; - goto cleanup; + goto out; } /* @@ -1553,6 +1554,8 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, kfree(bs); } brelse(bh); +out: + ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND); up_write(&EXT4_I(inode)->xattr_sem); return 0; @@ -1564,6 +1567,10 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, kfree(is); kfree(bs); brelse(bh); + /* + * We deliberately leave EXT4_STATE_NO_EXPAND set here since inode + * size expansion failed. + */ up_write(&EXT4_I(inode)->xattr_sem); return error; } From 9b4b3f6a062b22550e62523efe5213776cdd426b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 11 Aug 2016 07:26:01 -0700 Subject: [PATCH 033/531] ahci: disable correct irq for dummy ports irq already contains the interrupt number for the port, don't add the port index to it. Signed-off-by: Christoph Hellwig Signed-off-by: Tejun Heo Fixes: d684a90d38e2 ("ahci: per-port msix support") Cc: stable@vger.kernel.org v4.5+ --- drivers/ata/libahci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index 7461a587b39b..dcf2c724fd06 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -2524,7 +2524,7 @@ static int ahci_host_activate_multi_irqs(struct ata_host *host, /* Do not receive interrupts sent by dummy ports */ if (!pp) { - disable_irq(irq + i); + disable_irq(irq); continue; } From a3f457d9636b3f5ae4fc6502cb0c95f60f5e342b Mon Sep 17 00:00:00 2001 From: Chris Zhong Date: Tue, 9 Aug 2016 11:02:33 -0700 Subject: [PATCH 034/531] clk: rockchip: fix rk3399 aclk_vio gate bit Fix incorrect rk3399 aclk_vio gating bit, it should be 0, not 10. Fixes: 115510053e5e ("clk: rockchip: add clock controller for the RK3399") Signed-off-by: Chris Zhong Reviewed-by: Xing Zheng Reviewed-by: Guenter Roeck Signed-off-by: Heiko Stuebner --- drivers/clk/rockchip/clk-rk3399.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/rockchip/clk-rk3399.c b/drivers/clk/rockchip/clk-rk3399.c index c109d80e7a8a..314eab67bc0f 100644 --- a/drivers/clk/rockchip/clk-rk3399.c +++ b/drivers/clk/rockchip/clk-rk3399.c @@ -1071,7 +1071,7 @@ static struct rockchip_clk_branch rk3399_clk_branches[] __initdata = { /* vio */ COMPOSITE(ACLK_VIO, "aclk_vio", mux_pll_src_cpll_gpll_ppll_p, CLK_IGNORE_UNUSED, RK3399_CLKSEL_CON(42), 6, 2, MFLAGS, 0, 5, DFLAGS, - RK3399_CLKGATE_CON(11), 10, GFLAGS), + RK3399_CLKGATE_CON(11), 0, GFLAGS), COMPOSITE_NOMUX(PCLK_VIO, "pclk_vio", "aclk_vio", 0, RK3399_CLKSEL_CON(43), 0, 5, DFLAGS, RK3399_CLKGATE_CON(11), 1, GFLAGS), From e0cb1b84163720ec67ff0e54397fd3f57ad4a4dd Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Wed, 10 Aug 2016 09:29:43 +0200 Subject: [PATCH 035/531] clk: renesas: r8a7795: Fix SD clocks According to the datasheet, SDn clocks are from the SDSRC clock. And the SDSRC has a 1/2 divider. So, we should have ".sdsrc" as an internal core clock. Otherwise, since the sdhi driver will calculate clock for a sd card using the wrong parent clock rate, and then performance will be not good. Fixes: 90c073e53909da85 ("clk: shmobile: r8a7795: Add SD divider support") Signed-off-by: Yoshihiro Shimoda Acked-by: Dirk Behme Tested-by: Wolfram Sang Signed-off-by: Geert Uytterhoeven Cc: stable@vger.kernel.org Signed-off-by: Stephen Boyd --- drivers/clk/renesas/r8a7795-cpg-mssr.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/clk/renesas/r8a7795-cpg-mssr.c b/drivers/clk/renesas/r8a7795-cpg-mssr.c index d359c92e13a6..e38bf60c0ff4 100644 --- a/drivers/clk/renesas/r8a7795-cpg-mssr.c +++ b/drivers/clk/renesas/r8a7795-cpg-mssr.c @@ -69,6 +69,7 @@ static const struct cpg_core_clk r8a7795_core_clks[] __initconst = { DEF_FIXED(".s1", CLK_S1, CLK_PLL1_DIV2, 3, 1), DEF_FIXED(".s2", CLK_S2, CLK_PLL1_DIV2, 4, 1), DEF_FIXED(".s3", CLK_S3, CLK_PLL1_DIV2, 6, 1), + DEF_FIXED(".sdsrc", CLK_SDSRC, CLK_PLL1_DIV2, 2, 1), /* Core Clock Outputs */ DEF_FIXED("ztr", R8A7795_CLK_ZTR, CLK_PLL1_DIV2, 6, 1), @@ -87,10 +88,10 @@ static const struct cpg_core_clk r8a7795_core_clks[] __initconst = { DEF_FIXED("s3d2", R8A7795_CLK_S3D2, CLK_S3, 2, 1), DEF_FIXED("s3d4", R8A7795_CLK_S3D4, CLK_S3, 4, 1), - DEF_GEN3_SD("sd0", R8A7795_CLK_SD0, CLK_PLL1_DIV2, 0x0074), - DEF_GEN3_SD("sd1", R8A7795_CLK_SD1, CLK_PLL1_DIV2, 0x0078), - DEF_GEN3_SD("sd2", R8A7795_CLK_SD2, CLK_PLL1_DIV2, 0x0268), - DEF_GEN3_SD("sd3", R8A7795_CLK_SD3, CLK_PLL1_DIV2, 0x026c), + DEF_GEN3_SD("sd0", R8A7795_CLK_SD0, CLK_SDSRC, 0x0074), + DEF_GEN3_SD("sd1", R8A7795_CLK_SD1, CLK_SDSRC, 0x0078), + DEF_GEN3_SD("sd2", R8A7795_CLK_SD2, CLK_SDSRC, 0x0268), + DEF_GEN3_SD("sd3", R8A7795_CLK_SD3, CLK_SDSRC, 0x026c), DEF_FIXED("cl", R8A7795_CLK_CL, CLK_PLL1_DIV2, 48, 1), DEF_FIXED("cp", R8A7795_CLK_CP, CLK_EXTAL, 2, 1), From 20c389e656a89e2302017bf3f499cb5a31a2a7ba Mon Sep 17 00:00:00 2001 From: Xing Zheng Date: Tue, 2 Aug 2016 15:19:58 +0800 Subject: [PATCH 036/531] clk: rockchip: fix incorrect aclk_emmc source gate bits on rk3399 Dues to incorrect diagram, we need to fix incorrect bits for (c/g)pll_aclk_emmc_src: cpll_aclk_emmc_src --> G6[13] gpll_aclk_emmc_src --> G6[12] Fixes: 115510053e5e ("clk: rockchip: add clock controller for the RK3399") Signed-off-by: Xing Zheng Reviewed-by: Shawn Lin Signed-off-by: Heiko Stuebner --- drivers/clk/rockchip/clk-rk3399.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/clk/rockchip/clk-rk3399.c b/drivers/clk/rockchip/clk-rk3399.c index 314eab67bc0f..01fa60ebd6d4 100644 --- a/drivers/clk/rockchip/clk-rk3399.c +++ b/drivers/clk/rockchip/clk-rk3399.c @@ -923,9 +923,9 @@ static struct rockchip_clk_branch rk3399_clk_branches[] __initdata = { RK3399_CLKGATE_CON(6), 14, GFLAGS), GATE(0, "cpll_aclk_emmc_src", "cpll", CLK_IGNORE_UNUSED, - RK3399_CLKGATE_CON(6), 12, GFLAGS), - GATE(0, "gpll_aclk_emmc_src", "gpll", CLK_IGNORE_UNUSED, RK3399_CLKGATE_CON(6), 13, GFLAGS), + GATE(0, "gpll_aclk_emmc_src", "gpll", CLK_IGNORE_UNUSED, + RK3399_CLKGATE_CON(6), 12, GFLAGS), COMPOSITE_NOGATE(ACLK_EMMC, "aclk_emmc", mux_aclk_emmc_p, CLK_IGNORE_UNUSED, RK3399_CLKSEL_CON(21), 7, 1, MFLAGS, 0, 5, DFLAGS), GATE(ACLK_EMMC_CORE, "aclk_emmccore", "aclk_emmc", CLK_IGNORE_UNUSED, From b33ecca87df99fa6fff8a1d455de96f436934dcf Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Mon, 8 Aug 2016 21:55:39 +0200 Subject: [PATCH 037/531] phy-sun4i-usb: Add support for peripheral-only mode Use the new of_usb_get_dr_mode_by_phy() function to get the dr_mode from the musb controller node instead of assuming that having an id_det gpio means otg mode, and not having one means host mode. Implement peripheral-only mode by adding a sun4i_usb_phy0_get_id_det helper which looks at the dr_mode, always registering our extcon and always monitoring vbus. If dr_mode is not specified in the dts, do not register phy0 as we then do not know how to treat it. This is actually a good thing as this means we will not be registering phy0 on devices where the otg controller is not enabled in the devicetree. Signed-off-by: Hans de Goede Acked-by: Kishon Vijay Abraham I Signed-off-by: Kishon Vijay Abraham I --- drivers/phy/phy-sun4i-usb.c | 68 +++++++++++++++++++++++++------------ 1 file changed, 46 insertions(+), 22 deletions(-) diff --git a/drivers/phy/phy-sun4i-usb.c b/drivers/phy/phy-sun4i-usb.c index 0a45bc6088ae..8c7eb335622e 100644 --- a/drivers/phy/phy-sun4i-usb.c +++ b/drivers/phy/phy-sun4i-usb.c @@ -40,6 +40,7 @@ #include #include #include +#include #include #define REG_ISCR 0x00 @@ -110,6 +111,7 @@ struct sun4i_usb_phy_cfg { struct sun4i_usb_phy_data { void __iomem *base; const struct sun4i_usb_phy_cfg *cfg; + enum usb_dr_mode dr_mode; struct mutex mutex; struct sun4i_usb_phy { struct phy *phy; @@ -120,6 +122,7 @@ struct sun4i_usb_phy_data { bool regulator_on; int index; } phys[MAX_PHYS]; + int first_phy; /* phy0 / otg related variables */ struct extcon_dev *extcon; bool phy0_init; @@ -285,16 +288,10 @@ static int sun4i_usb_phy_init(struct phy *_phy) sun4i_usb_phy0_update_iscr(_phy, 0, ISCR_DPDM_PULLUP_EN); sun4i_usb_phy0_update_iscr(_phy, 0, ISCR_ID_PULLUP_EN); - if (data->id_det_gpio) { - /* OTG mode, force ISCR and cable state updates */ - data->id_det = -1; - data->vbus_det = -1; - queue_delayed_work(system_wq, &data->detect, 0); - } else { - /* Host only mode */ - sun4i_usb_phy0_set_id_detect(_phy, 0); - sun4i_usb_phy0_set_vbus_detect(_phy, 1); - } + /* Force ISCR and cable state updates */ + data->id_det = -1; + data->vbus_det = -1; + queue_delayed_work(system_wq, &data->detect, 0); } return 0; @@ -319,6 +316,19 @@ static int sun4i_usb_phy_exit(struct phy *_phy) return 0; } +static int sun4i_usb_phy0_get_id_det(struct sun4i_usb_phy_data *data) +{ + switch (data->dr_mode) { + case USB_DR_MODE_OTG: + return gpiod_get_value_cansleep(data->id_det_gpio); + case USB_DR_MODE_HOST: + return 0; + case USB_DR_MODE_PERIPHERAL: + default: + return 1; + } +} + static int sun4i_usb_phy0_get_vbus_det(struct sun4i_usb_phy_data *data) { if (data->vbus_det_gpio) @@ -432,7 +442,10 @@ static void sun4i_usb_phy0_id_vbus_det_scan(struct work_struct *work) struct phy *phy0 = data->phys[0].phy; int id_det, vbus_det, id_notify = 0, vbus_notify = 0; - id_det = gpiod_get_value_cansleep(data->id_det_gpio); + if (phy0 == NULL) + return; + + id_det = sun4i_usb_phy0_get_id_det(data); vbus_det = sun4i_usb_phy0_get_vbus_det(data); mutex_lock(&phy0->mutex); @@ -448,7 +461,8 @@ static void sun4i_usb_phy0_id_vbus_det_scan(struct work_struct *work) * without vbus detection report vbus low for long enough for * the musb-ip to end the current device session. */ - if (!sun4i_usb_phy0_have_vbus_det(data) && id_det == 0) { + if (data->dr_mode == USB_DR_MODE_OTG && + !sun4i_usb_phy0_have_vbus_det(data) && id_det == 0) { sun4i_usb_phy0_set_vbus_detect(phy0, 0); msleep(200); sun4i_usb_phy0_set_vbus_detect(phy0, 1); @@ -474,7 +488,8 @@ static void sun4i_usb_phy0_id_vbus_det_scan(struct work_struct *work) * without vbus detection report vbus low for long enough to * the musb-ip to end the current host session. */ - if (!sun4i_usb_phy0_have_vbus_det(data) && id_det == 1) { + if (data->dr_mode == USB_DR_MODE_OTG && + !sun4i_usb_phy0_have_vbus_det(data) && id_det == 1) { mutex_lock(&phy0->mutex); sun4i_usb_phy0_set_vbus_detect(phy0, 0); msleep(1000); @@ -519,7 +534,8 @@ static struct phy *sun4i_usb_phy_xlate(struct device *dev, { struct sun4i_usb_phy_data *data = dev_get_drvdata(dev); - if (args->args[0] >= data->cfg->num_phys) + if (args->args[0] < data->first_phy || + args->args[0] >= data->cfg->num_phys) return ERR_PTR(-ENODEV); return data->phys[args->args[0]].phy; @@ -593,13 +609,17 @@ static int sun4i_usb_phy_probe(struct platform_device *pdev) return -EPROBE_DEFER; } - /* vbus_det without id_det makes no sense, and is not supported */ - if (sun4i_usb_phy0_have_vbus_det(data) && !data->id_det_gpio) { - dev_err(dev, "usb0_id_det missing or invalid\n"); - return -ENODEV; - } - - if (data->id_det_gpio) { + data->dr_mode = of_usb_get_dr_mode_by_phy(np, 0); + switch (data->dr_mode) { + case USB_DR_MODE_OTG: + /* otg without id_det makes no sense, and is not supported */ + if (!data->id_det_gpio) { + dev_err(dev, "usb0_id_det missing or invalid\n"); + return -ENODEV; + } + /* fall through */ + case USB_DR_MODE_HOST: + case USB_DR_MODE_PERIPHERAL: data->extcon = devm_extcon_dev_allocate(dev, sun4i_usb_phy0_cable); if (IS_ERR(data->extcon)) @@ -610,9 +630,13 @@ static int sun4i_usb_phy_probe(struct platform_device *pdev) dev_err(dev, "failed to register extcon: %d\n", ret); return ret; } + break; + default: + dev_info(dev, "dr_mode unknown, not registering usb phy0\n"); + data->first_phy = 1; } - for (i = 0; i < data->cfg->num_phys; i++) { + for (i = data->first_phy; i < data->cfg->num_phys; i++) { struct sun4i_usb_phy *phy = data->phys + i; char name[16]; From 1766e7b3763a0707c2fda9689a7866dceed07b7a Mon Sep 17 00:00:00 2001 From: David Lechner Date: Wed, 10 Aug 2016 18:49:27 +0530 Subject: [PATCH 038/531] mfd: da8xx-cfgchip: New header file for CFGCHIP registers Create a new header file for TI DA8XX SoC CFGCHIPx registers. This will be used by a number of planned drivers including a new USB PHY driver and common clock framework drivers. The same defines *will* be removed from the platform_data header, once all the users start using the new syscon device header. This also fixes the following compiler error caused due to a dependent patch not merged. drivers/phy/phy-da8xx-usb.c:19:37: fatal error: linux/mfd/da8xx-cfgchip.h: No such file or directory #include Signed-off-by: David Lechner Acked-by: Lee Jones Reported-by: Arnd Bergmann Signed-off-by: Kishon Vijay Abraham I --- include/linux/mfd/da8xx-cfgchip.h | 153 ++++++++++++++++++++++++++++++ 1 file changed, 153 insertions(+) create mode 100644 include/linux/mfd/da8xx-cfgchip.h diff --git a/include/linux/mfd/da8xx-cfgchip.h b/include/linux/mfd/da8xx-cfgchip.h new file mode 100644 index 000000000000..304985e288d2 --- /dev/null +++ b/include/linux/mfd/da8xx-cfgchip.h @@ -0,0 +1,153 @@ +/* + * TI DaVinci DA8xx CHIPCFGx registers for syscon consumers. + * + * Copyright (C) 2016 David Lechner + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __LINUX_MFD_DA8XX_CFGCHIP_H +#define __LINUX_MFD_DA8XX_CFGCHIP_H + +#include + +/* register offset (32-bit registers) */ +#define CFGCHIP(n) ((n) * 4) + +/* CFGCHIP0 (PLL0/EDMA3_0) register bits */ +#define CFGCHIP0_PLL_MASTER_LOCK BIT(4) +#define CFGCHIP0_EDMA30TC1DBS(n) ((n) << 2) +#define CFGCHIP0_EDMA30TC1DBS_MASK CFGCHIP0_EDMA30TC1DBS(0x3) +#define CFGCHIP0_EDMA30TC1DBS_16 CFGCHIP0_EDMA30TC1DBS(0x0) +#define CFGCHIP0_EDMA30TC1DBS_32 CFGCHIP0_EDMA30TC1DBS(0x1) +#define CFGCHIP0_EDMA30TC1DBS_64 CFGCHIP0_EDMA30TC1DBS(0x2) +#define CFGCHIP0_EDMA30TC0DBS(n) ((n) << 0) +#define CFGCHIP0_EDMA30TC0DBS_MASK CFGCHIP0_EDMA30TC0DBS(0x3) +#define CFGCHIP0_EDMA30TC0DBS_16 CFGCHIP0_EDMA30TC0DBS(0x0) +#define CFGCHIP0_EDMA30TC0DBS_32 CFGCHIP0_EDMA30TC0DBS(0x1) +#define CFGCHIP0_EDMA30TC0DBS_64 CFGCHIP0_EDMA30TC0DBS(0x2) + +/* CFGCHIP1 (eCAP/HPI/EDMA3_1/eHRPWM TBCLK/McASP0 AMUTEIN) register bits */ +#define CFGCHIP1_CAP2SRC(n) ((n) << 27) +#define CFGCHIP1_CAP2SRC_MASK CFGCHIP1_CAP2SRC(0x1f) +#define CFGCHIP1_CAP2SRC_ECAP_PIN CFGCHIP1_CAP2SRC(0x0) +#define CFGCHIP1_CAP2SRC_MCASP0_TX CFGCHIP1_CAP2SRC(0x1) +#define CFGCHIP1_CAP2SRC_MCASP0_RX CFGCHIP1_CAP2SRC(0x2) +#define CFGCHIP1_CAP2SRC_EMAC_C0_RX_THRESHOLD CFGCHIP1_CAP2SRC(0x7) +#define CFGCHIP1_CAP2SRC_EMAC_C0_RX CFGCHIP1_CAP2SRC(0x8) +#define CFGCHIP1_CAP2SRC_EMAC_C0_TX CFGCHIP1_CAP2SRC(0x9) +#define CFGCHIP1_CAP2SRC_EMAC_C0_MISC CFGCHIP1_CAP2SRC(0xa) +#define CFGCHIP1_CAP2SRC_EMAC_C1_RX_THRESHOLD CFGCHIP1_CAP2SRC(0xb) +#define CFGCHIP1_CAP2SRC_EMAC_C1_RX CFGCHIP1_CAP2SRC(0xc) +#define CFGCHIP1_CAP2SRC_EMAC_C1_TX CFGCHIP1_CAP2SRC(0xd) +#define CFGCHIP1_CAP2SRC_EMAC_C1_MISC CFGCHIP1_CAP2SRC(0xe) +#define CFGCHIP1_CAP2SRC_EMAC_C2_RX_THRESHOLD CFGCHIP1_CAP2SRC(0xf) +#define CFGCHIP1_CAP2SRC_EMAC_C2_RX CFGCHIP1_CAP2SRC(0x10) +#define CFGCHIP1_CAP2SRC_EMAC_C2_TX CFGCHIP1_CAP2SRC(0x11) +#define CFGCHIP1_CAP2SRC_EMAC_C2_MISC CFGCHIP1_CAP2SRC(0x12) +#define CFGCHIP1_CAP1SRC(n) ((n) << 22) +#define CFGCHIP1_CAP1SRC_MASK CFGCHIP1_CAP1SRC(0x1f) +#define CFGCHIP1_CAP1SRC_ECAP_PIN CFGCHIP1_CAP1SRC(0x0) +#define CFGCHIP1_CAP1SRC_MCASP0_TX CFGCHIP1_CAP1SRC(0x1) +#define CFGCHIP1_CAP1SRC_MCASP0_RX CFGCHIP1_CAP1SRC(0x2) +#define CFGCHIP1_CAP1SRC_EMAC_C0_RX_THRESHOLD CFGCHIP1_CAP1SRC(0x7) +#define CFGCHIP1_CAP1SRC_EMAC_C0_RX CFGCHIP1_CAP1SRC(0x8) +#define CFGCHIP1_CAP1SRC_EMAC_C0_TX CFGCHIP1_CAP1SRC(0x9) +#define CFGCHIP1_CAP1SRC_EMAC_C0_MISC CFGCHIP1_CAP1SRC(0xa) +#define CFGCHIP1_CAP1SRC_EMAC_C1_RX_THRESHOLD CFGCHIP1_CAP1SRC(0xb) +#define CFGCHIP1_CAP1SRC_EMAC_C1_RX CFGCHIP1_CAP1SRC(0xc) +#define CFGCHIP1_CAP1SRC_EMAC_C1_TX CFGCHIP1_CAP1SRC(0xd) +#define CFGCHIP1_CAP1SRC_EMAC_C1_MISC CFGCHIP1_CAP1SRC(0xe) +#define CFGCHIP1_CAP1SRC_EMAC_C2_RX_THRESHOLD CFGCHIP1_CAP1SRC(0xf) +#define CFGCHIP1_CAP1SRC_EMAC_C2_RX CFGCHIP1_CAP1SRC(0x10) +#define CFGCHIP1_CAP1SRC_EMAC_C2_TX CFGCHIP1_CAP1SRC(0x11) +#define CFGCHIP1_CAP1SRC_EMAC_C2_MISC CFGCHIP1_CAP1SRC(0x12) +#define CFGCHIP1_CAP0SRC(n) ((n) << 17) +#define CFGCHIP1_CAP0SRC_MASK CFGCHIP1_CAP0SRC(0x1f) +#define CFGCHIP1_CAP0SRC_ECAP_PIN CFGCHIP1_CAP0SRC(0x0) +#define CFGCHIP1_CAP0SRC_MCASP0_TX CFGCHIP1_CAP0SRC(0x1) +#define CFGCHIP1_CAP0SRC_MCASP0_RX CFGCHIP1_CAP0SRC(0x2) +#define CFGCHIP1_CAP0SRC_EMAC_C0_RX_THRESHOLD CFGCHIP1_CAP0SRC(0x7) +#define CFGCHIP1_CAP0SRC_EMAC_C0_RX CFGCHIP1_CAP0SRC(0x8) +#define CFGCHIP1_CAP0SRC_EMAC_C0_TX CFGCHIP1_CAP0SRC(0x9) +#define CFGCHIP1_CAP0SRC_EMAC_C0_MISC CFGCHIP1_CAP0SRC(0xa) +#define CFGCHIP1_CAP0SRC_EMAC_C1_RX_THRESHOLD CFGCHIP1_CAP0SRC(0xb) +#define CFGCHIP1_CAP0SRC_EMAC_C1_RX CFGCHIP1_CAP0SRC(0xc) +#define CFGCHIP1_CAP0SRC_EMAC_C1_TX CFGCHIP1_CAP0SRC(0xd) +#define CFGCHIP1_CAP0SRC_EMAC_C1_MISC CFGCHIP1_CAP0SRC(0xe) +#define CFGCHIP1_CAP0SRC_EMAC_C2_RX_THRESHOLD CFGCHIP1_CAP0SRC(0xf) +#define CFGCHIP1_CAP0SRC_EMAC_C2_RX CFGCHIP1_CAP0SRC(0x10) +#define CFGCHIP1_CAP0SRC_EMAC_C2_TX CFGCHIP1_CAP0SRC(0x11) +#define CFGCHIP1_CAP0SRC_EMAC_C2_MISC CFGCHIP1_CAP0SRC(0x12) +#define CFGCHIP1_HPIBYTEAD BIT(16) +#define CFGCHIP1_HPIENA BIT(15) +#define CFGCHIP0_EDMA31TC0DBS(n) ((n) << 13) +#define CFGCHIP0_EDMA31TC0DBS_MASK CFGCHIP0_EDMA31TC0DBS(0x3) +#define CFGCHIP0_EDMA31TC0DBS_16 CFGCHIP0_EDMA31TC0DBS(0x0) +#define CFGCHIP0_EDMA31TC0DBS_32 CFGCHIP0_EDMA31TC0DBS(0x1) +#define CFGCHIP0_EDMA31TC0DBS_64 CFGCHIP0_EDMA31TC0DBS(0x2) +#define CFGCHIP1_TBCLKSYNC BIT(12) +#define CFGCHIP1_AMUTESEL0(n) ((n) << 0) +#define CFGCHIP1_AMUTESEL0_MASK CFGCHIP1_AMUTESEL0(0xf) +#define CFGCHIP1_AMUTESEL0_LOW CFGCHIP1_AMUTESEL0(0x0) +#define CFGCHIP1_AMUTESEL0_BANK_0 CFGCHIP1_AMUTESEL0(0x1) +#define CFGCHIP1_AMUTESEL0_BANK_1 CFGCHIP1_AMUTESEL0(0x2) +#define CFGCHIP1_AMUTESEL0_BANK_2 CFGCHIP1_AMUTESEL0(0x3) +#define CFGCHIP1_AMUTESEL0_BANK_3 CFGCHIP1_AMUTESEL0(0x4) +#define CFGCHIP1_AMUTESEL0_BANK_4 CFGCHIP1_AMUTESEL0(0x5) +#define CFGCHIP1_AMUTESEL0_BANK_5 CFGCHIP1_AMUTESEL0(0x6) +#define CFGCHIP1_AMUTESEL0_BANK_6 CFGCHIP1_AMUTESEL0(0x7) +#define CFGCHIP1_AMUTESEL0_BANK_7 CFGCHIP1_AMUTESEL0(0x8) + +/* CFGCHIP2 (USB PHY) register bits */ +#define CFGCHIP2_PHYCLKGD BIT(17) +#define CFGCHIP2_VBUSSENSE BIT(16) +#define CFGCHIP2_RESET BIT(15) +#define CFGCHIP2_OTGMODE(n) ((n) << 13) +#define CFGCHIP2_OTGMODE_MASK CFGCHIP2_OTGMODE(0x3) +#define CFGCHIP2_OTGMODE_NO_OVERRIDE CFGCHIP2_OTGMODE(0x0) +#define CFGCHIP2_OTGMODE_FORCE_HOST CFGCHIP2_OTGMODE(0x1) +#define CFGCHIP2_OTGMODE_FORCE_DEVICE CFGCHIP2_OTGMODE(0x2) +#define CFGCHIP2_OTGMODE_FORCE_HOST_VBUS_LOW CFGCHIP2_OTGMODE(0x3) +#define CFGCHIP2_USB1PHYCLKMUX BIT(12) +#define CFGCHIP2_USB2PHYCLKMUX BIT(11) +#define CFGCHIP2_PHYPWRDN BIT(10) +#define CFGCHIP2_OTGPWRDN BIT(9) +#define CFGCHIP2_DATPOL BIT(8) +#define CFGCHIP2_USB1SUSPENDM BIT(7) +#define CFGCHIP2_PHY_PLLON BIT(6) +#define CFGCHIP2_SESENDEN BIT(5) +#define CFGCHIP2_VBDTCTEN BIT(4) +#define CFGCHIP2_REFFREQ(n) ((n) << 0) +#define CFGCHIP2_REFFREQ_MASK CFGCHIP2_REFFREQ(0xf) +#define CFGCHIP2_REFFREQ_12MHZ CFGCHIP2_REFFREQ(0x1) +#define CFGCHIP2_REFFREQ_24MHZ CFGCHIP2_REFFREQ(0x2) +#define CFGCHIP2_REFFREQ_48MHZ CFGCHIP2_REFFREQ(0x3) +#define CFGCHIP2_REFFREQ_19_2MHZ CFGCHIP2_REFFREQ(0x4) +#define CFGCHIP2_REFFREQ_38_4MHZ CFGCHIP2_REFFREQ(0x5) +#define CFGCHIP2_REFFREQ_13MHZ CFGCHIP2_REFFREQ(0x6) +#define CFGCHIP2_REFFREQ_26MHZ CFGCHIP2_REFFREQ(0x7) +#define CFGCHIP2_REFFREQ_20MHZ CFGCHIP2_REFFREQ(0x8) +#define CFGCHIP2_REFFREQ_40MHZ CFGCHIP2_REFFREQ(0x9) + +/* CFGCHIP3 (EMAC/uPP/PLL1/ASYNC3/PRU/DIV4.5/EMIFA) register bits */ +#define CFGCHIP3_RMII_SEL BIT(8) +#define CFGCHIP3_UPP_TX_CLKSRC BIT(6) +#define CFGCHIP3_PLL1_MASTER_LOCK BIT(5) +#define CFGCHIP3_ASYNC3_CLKSRC BIT(4) +#define CFGCHIP3_PRUEVTSEL BIT(3) +#define CFGCHIP3_DIV45PENA BIT(2) +#define CFGCHIP3_EMA_CLKSRC BIT(1) + +/* CFGCHIP4 (McASP0 AMUNTEIN) register bits */ +#define CFGCHIP4_AMUTECLR0 BIT(0) + +#endif /* __LINUX_MFD_DA8XX_CFGCHIP_H */ From bf8ca651e1f8f054b39b6b3b95d6f515c3c857d5 Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Wed, 10 Aug 2016 18:04:44 +0800 Subject: [PATCH 039/531] phy: brcm-sata: Return proper error if brcm_sata_phy_init fails Return proper error instead of 0 if brcm_sata_phy_init fails. Signed-off-by: Axel Lin Signed-off-by: Kishon Vijay Abraham I --- drivers/phy/phy-brcm-sata.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/phy/phy-brcm-sata.c b/drivers/phy/phy-brcm-sata.c index 18d662610075..8ffc44afdb75 100644 --- a/drivers/phy/phy-brcm-sata.c +++ b/drivers/phy/phy-brcm-sata.c @@ -367,7 +367,7 @@ static int brcm_sata_phy_init(struct phy *phy) rc = -ENODEV; }; - return 0; + return rc; } static const struct phy_ops phy_ops = { From 017300da3a4547d85e52c2484fc0bd759e1bbcdb Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Wed, 6 Jul 2016 08:00:06 +0200 Subject: [PATCH 040/531] phy: sun9i-usb: fix error handling This is likely that checking 'phy->hsic_clk' instead of 'phy->clk' is expected here. Signed-off-by: Christophe JAILLET Acked-by: Chen-Yu Tsai --- drivers/phy/phy-sun9i-usb.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/phy/phy-sun9i-usb.c b/drivers/phy/phy-sun9i-usb.c index ac4f31abefe3..28fce4bce638 100644 --- a/drivers/phy/phy-sun9i-usb.c +++ b/drivers/phy/phy-sun9i-usb.c @@ -141,9 +141,9 @@ static int sun9i_usb_phy_probe(struct platform_device *pdev) } phy->hsic_clk = devm_clk_get(dev, "hsic_12M"); - if (IS_ERR(phy->clk)) { + if (IS_ERR(phy->hsic_clk)) { dev_err(dev, "failed to get hsic_12M clock\n"); - return PTR_ERR(phy->clk); + return PTR_ERR(phy->hsic_clk); } phy->reset = devm_reset_control_get(dev, "hsic"); From 979cf59acc9d634cc140aadd0d2915947ab303cc Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Fri, 12 Aug 2016 11:45:18 +0000 Subject: [PATCH 041/531] ASoC: Intel: Skylake: Fix error return code in skl_probe() Fix to return error code -ENODEV from the error handling case instead of 0, as done elsewhere in this function. Fixes: 87b2bdf02278 ("ASoC: Intel: Skylake: Initialize NHLT table") Signed-off-by: Wei Yongjun Acked-By: Vinod Koul Signed-off-by: Mark Brown --- sound/soc/intel/skylake/skl.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c index cd59536a761d..e3e764167765 100644 --- a/sound/soc/intel/skylake/skl.c +++ b/sound/soc/intel/skylake/skl.c @@ -672,8 +672,10 @@ static int skl_probe(struct pci_dev *pci, skl->nhlt = skl_nhlt_init(bus->dev); - if (skl->nhlt == NULL) + if (skl->nhlt == NULL) { + err = -ENODEV; goto out_free; + } skl_nhlt_update_topology_bin(skl); From 4608d96fb491125657fd8183a35921e4d4e27bc8 Mon Sep 17 00:00:00 2001 From: Xing Zheng Date: Tue, 2 Aug 2016 15:19:57 +0800 Subject: [PATCH 042/531] clk: rockchip: fix incorrect GATE bits for {c, g}pll_aclk_perihp_src on rk3399 Sorry to refer incorrect clock diagram, we double check it that the bits configuration of the Xpll_aclk_perihp_src need to be fixed: bit 1 - shows aclk_perihp_cpll_src_en bit 0 - shows aclk_perihp_gpll_src_en Through the testing that plug/unplug the USB ethernet cable on the RK3399 kevin board. 1. the hclk_host0 and hclk_host1 are endpoint clocks: cpll --> G5[1] --> aclk_perihp_cpll_src --\ |--> hclk_host0 | --> ... ---> | gpll --> G5[0] --> aclk_perihp_gpll_src --/ |--> hclk_host1 2. there is no clock below the cpll_aclk_perihp_src, and the hclk_hostX are below the gpll_aclk_perihp_src: pll_cpll 1 1 800000000 0 0 cpll 7 19 800000000 0 0 cpll_aclk_perihp_src 0 0 800000000 0 0 ... pll_gpll 1 1 594000000 0 0 gpll 10 10 594000000 0 0 gpll_aclk_perihp_src 2 2 594000000 0 0 hclk_perihp 5 5 74250000 0 0 hclk_host1_arb 2 2 74250000 0 0 hclk_host1 2 2 74250000 0 0 hclk_host0_arb 2 2 74250000 0 0 hclk_host0 2 2 74250000 0 0 3. by default, G5[0] and G5[1] are enabled: localhost ~ # mem r 0xff760314 0x000003e0 4. close the G5[1] (aclk_perihp_cpll_src), and plug/unplug USB ethernet cable, the DUT still works well: localhost ~ # mem w 0xff760314 0xffff03e2 localhost ~ # mem r 0xff760314 0x000003e2 plug/unplug, the work statue is ok 5. close the G5[0] (aclk_perihp_gpll_src), , and plug/unplug USB ethernet cable, the DUT will be crashed: localhost ~ # mem w 0xff760314 0xffff03e1 localhost ~ # mem r 0xff760314 0x000003e1 plug/unplug, the DUT is crashed Summary: bit 1 - shows aclk_perihp_cpll_src_en bit 0 - shows aclk_perihp_gpll_src_en Fixes: 3bd14ae9da91 ("clk: rockchip: fix incorrect parent for rk3399's {c,g}pll_aclk_perihp_src") Signed-off-by: Xing Zheng [here the clock-documentation in the manual was actually stating the wrong bits and thus only Xing's testing above revealed the issue] Signed-off-by: Heiko Stuebner --- drivers/clk/rockchip/clk-rk3399.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/clk/rockchip/clk-rk3399.c b/drivers/clk/rockchip/clk-rk3399.c index 01fa60ebd6d4..ec5b2fd77c50 100644 --- a/drivers/clk/rockchip/clk-rk3399.c +++ b/drivers/clk/rockchip/clk-rk3399.c @@ -833,9 +833,9 @@ static struct rockchip_clk_branch rk3399_clk_branches[] __initdata = { /* perihp */ GATE(0, "cpll_aclk_perihp_src", "cpll", CLK_IGNORE_UNUSED, - RK3399_CLKGATE_CON(5), 0, GFLAGS), - GATE(0, "gpll_aclk_perihp_src", "gpll", CLK_IGNORE_UNUSED, RK3399_CLKGATE_CON(5), 1, GFLAGS), + GATE(0, "gpll_aclk_perihp_src", "gpll", CLK_IGNORE_UNUSED, + RK3399_CLKGATE_CON(5), 0, GFLAGS), COMPOSITE(ACLK_PERIHP, "aclk_perihp", mux_aclk_perihp_p, CLK_IGNORE_UNUSED, RK3399_CLKSEL_CON(14), 7, 1, MFLAGS, 0, 5, DFLAGS, RK3399_CLKGATE_CON(5), 2, GFLAGS), From 1c8d477a77e2d1d3504419e7f2e02e6422becf9a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 14 Aug 2016 12:47:49 -0400 Subject: [PATCH 043/531] pNFS/flexfiles: Fix layoutstat periodic reporting Putting the periodicity timer in the mirror instances is causing non-scalable reporting behaviour and missed reporting intervals. When you recall layouts and/or implement client side mirroring, it leads to consecutive reports with only a few ms between RPC calls. Signed-off-by: Trond Myklebust Fixes: d0379a5d066a9 ("pNFS/flexfiles: Support server-supplied...") --- fs/nfs/flexfilelayout/flexfilelayout.c | 8 ++++---- fs/nfs/flexfilelayout/flexfilelayout.h | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index e6206eaf2bdf..ee1c94c7614c 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -37,6 +37,7 @@ ff_layout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags) if (ffl) { INIT_LIST_HEAD(&ffl->error_list); INIT_LIST_HEAD(&ffl->mirrors); + ffl->last_report_time = ktime_get(); return &ffl->generic_hdr; } else return NULL; @@ -640,19 +641,18 @@ nfs4_ff_layoutstat_start_io(struct nfs4_ff_layout_mirror *mirror, { static const ktime_t notime = {0}; s64 report_interval = FF_LAYOUTSTATS_REPORT_INTERVAL; + struct nfs4_flexfile_layout *ffl = FF_LAYOUT_FROM_HDR(mirror->layout); nfs4_ff_start_busy_timer(&layoutstat->busy_timer, now); if (ktime_equal(mirror->start_time, notime)) mirror->start_time = now; - if (ktime_equal(mirror->last_report_time, notime)) - mirror->last_report_time = now; if (mirror->report_interval != 0) report_interval = (s64)mirror->report_interval * 1000LL; else if (layoutstats_timer != 0) report_interval = (s64)layoutstats_timer * 1000LL; - if (ktime_to_ms(ktime_sub(now, mirror->last_report_time)) >= + if (ktime_to_ms(ktime_sub(now, ffl->last_report_time)) >= report_interval) { - mirror->last_report_time = now; + ffl->last_report_time = now; return true; } diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h index 1bcdb15d0c41..3ee0c9fcea76 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.h +++ b/fs/nfs/flexfilelayout/flexfilelayout.h @@ -84,7 +84,6 @@ struct nfs4_ff_layout_mirror { struct nfs4_ff_layoutstat read_stat; struct nfs4_ff_layoutstat write_stat; ktime_t start_time; - ktime_t last_report_time; u32 report_interval; }; @@ -101,6 +100,7 @@ struct nfs4_flexfile_layout { struct pnfs_ds_commit_info commit_info; struct list_head mirrors; struct list_head error_list; /* nfs4_ff_layout_ds_err */ + ktime_t last_report_time; /* Layoutstat report times */ }; static inline struct nfs4_flexfile_layout * From 5a5a1d614287a647b36dff3f40c2b0ceabbc83ec Mon Sep 17 00:00:00 2001 From: Alexey Khoroshilov Date: Fri, 12 Aug 2016 01:05:08 +0300 Subject: [PATCH 044/531] USB: serial: mos7720: fix non-atomic allocation in write path There is an allocation with GFP_KERNEL flag in mos7720_write(), while it may be called from interrupt context. Follow-up for commit 191252837626 ("USB: kobil_sct: fix non-atomic allocation in write path") Found by Linux Driver Verification project (linuxtesting.org). Signed-off-by: Alexey Khoroshilov Cc: stable Signed-off-by: Johan Hovold --- drivers/usb/serial/mos7720.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/serial/mos7720.c b/drivers/usb/serial/mos7720.c index 5608af4a369d..de9992b492b0 100644 --- a/drivers/usb/serial/mos7720.c +++ b/drivers/usb/serial/mos7720.c @@ -1252,7 +1252,7 @@ static int mos7720_write(struct tty_struct *tty, struct usb_serial_port *port, if (urb->transfer_buffer == NULL) { urb->transfer_buffer = kmalloc(URB_TRANSFER_BUFFER_SIZE, - GFP_KERNEL); + GFP_ATOMIC); if (!urb->transfer_buffer) goto exit; } From 3b7c7e52efda0d4640060de747768360ba70a7c0 Mon Sep 17 00:00:00 2001 From: Alexey Khoroshilov Date: Fri, 12 Aug 2016 01:05:09 +0300 Subject: [PATCH 045/531] USB: serial: mos7840: fix non-atomic allocation in write path There is an allocation with GFP_KERNEL flag in mos7840_write(), while it may be called from interrupt context. Follow-up for commit 191252837626 ("USB: kobil_sct: fix non-atomic allocation in write path") Found by Linux Driver Verification project (linuxtesting.org). Signed-off-by: Alexey Khoroshilov Cc: stable Signed-off-by: Johan Hovold --- drivers/usb/serial/mos7840.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/usb/serial/mos7840.c b/drivers/usb/serial/mos7840.c index ed378fb232e7..57426d703a09 100644 --- a/drivers/usb/serial/mos7840.c +++ b/drivers/usb/serial/mos7840.c @@ -1340,8 +1340,8 @@ static int mos7840_write(struct tty_struct *tty, struct usb_serial_port *port, } if (urb->transfer_buffer == NULL) { - urb->transfer_buffer = - kmalloc(URB_TRANSFER_BUFFER_SIZE, GFP_KERNEL); + urb->transfer_buffer = kmalloc(URB_TRANSFER_BUFFER_SIZE, + GFP_ATOMIC); if (!urb->transfer_buffer) goto exit; } From 7ef9153d9af5fe7ce32dcc0f558bfcfc3d2b3016 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 15 Aug 2016 15:17:41 +0200 Subject: [PATCH 046/531] misc: delete bh1780 driver The Rohm BH1780 ambient light sensor has a new driver with extended functionality (proper runtime PM) in the appropriate framework IIO, it can be found at: drivers/iio/light/bh1780.c The MISC driver symbol CONFIG_SENSORS_BH1780 does not appear in any defconfigs, so it should safe to delete. Cc: Hemanth V Signed-off-by: Linus Walleij Signed-off-by: Greg Kroah-Hartman --- drivers/misc/Kconfig | 10 -- drivers/misc/Makefile | 1 - drivers/misc/bh1780gli.c | 259 --------------------------------------- 3 files changed, 270 deletions(-) delete mode 100644 drivers/misc/bh1780gli.c diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig index a216b4667742..d00252828966 100644 --- a/drivers/misc/Kconfig +++ b/drivers/misc/Kconfig @@ -345,16 +345,6 @@ config SENSORS_TSL2550 This driver can also be built as a module. If so, the module will be called tsl2550. -config SENSORS_BH1780 - tristate "ROHM BH1780GLI ambient light sensor" - depends on I2C && SYSFS - help - If you say yes here you get support for the ROHM BH1780GLI - ambient light sensor. - - This driver can also be built as a module. If so, the module - will be called bh1780gli. - config SENSORS_BH1770 tristate "BH1770GLC / SFH7770 combined ALS - Proximity sensor" depends on I2C diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile index 7410c6d9a34d..fb32516ddfe2 100644 --- a/drivers/misc/Makefile +++ b/drivers/misc/Makefile @@ -19,7 +19,6 @@ obj-$(CONFIG_TIFM_CORE) += tifm_core.o obj-$(CONFIG_TIFM_7XX1) += tifm_7xx1.o obj-$(CONFIG_PHANTOM) += phantom.o obj-$(CONFIG_QCOM_COINCELL) += qcom-coincell.o -obj-$(CONFIG_SENSORS_BH1780) += bh1780gli.o obj-$(CONFIG_SENSORS_BH1770) += bh1770glc.o obj-$(CONFIG_SENSORS_APDS990X) += apds990x.o obj-$(CONFIG_SGI_IOC4) += ioc4.o diff --git a/drivers/misc/bh1780gli.c b/drivers/misc/bh1780gli.c deleted file mode 100644 index 7f90ce5a569a..000000000000 --- a/drivers/misc/bh1780gli.c +++ /dev/null @@ -1,259 +0,0 @@ -/* - * bh1780gli.c - * ROHM Ambient Light Sensor Driver - * - * Copyright (C) 2010 Texas Instruments - * Author: Hemanth V - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program. If not, see . - */ -#include -#include -#include -#include -#include -#include -#include - -#define BH1780_REG_CONTROL 0x80 -#define BH1780_REG_PARTID 0x8A -#define BH1780_REG_MANFID 0x8B -#define BH1780_REG_DLOW 0x8C -#define BH1780_REG_DHIGH 0x8D - -#define BH1780_REVMASK (0xf) -#define BH1780_POWMASK (0x3) -#define BH1780_POFF (0x0) -#define BH1780_PON (0x3) - -/* power on settling time in ms */ -#define BH1780_PON_DELAY 2 - -struct bh1780_data { - struct i2c_client *client; - int power_state; - /* lock for sysfs operations */ - struct mutex lock; -}; - -static int bh1780_write(struct bh1780_data *ddata, u8 reg, u8 val, char *msg) -{ - int ret = i2c_smbus_write_byte_data(ddata->client, reg, val); - if (ret < 0) - dev_err(&ddata->client->dev, - "i2c_smbus_write_byte_data failed error %d Register (%s)\n", - ret, msg); - return ret; -} - -static int bh1780_read(struct bh1780_data *ddata, u8 reg, char *msg) -{ - int ret = i2c_smbus_read_byte_data(ddata->client, reg); - if (ret < 0) - dev_err(&ddata->client->dev, - "i2c_smbus_read_byte_data failed error %d Register (%s)\n", - ret, msg); - return ret; -} - -static ssize_t bh1780_show_lux(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct platform_device *pdev = to_platform_device(dev); - struct bh1780_data *ddata = platform_get_drvdata(pdev); - int lsb, msb; - - lsb = bh1780_read(ddata, BH1780_REG_DLOW, "DLOW"); - if (lsb < 0) - return lsb; - - msb = bh1780_read(ddata, BH1780_REG_DHIGH, "DHIGH"); - if (msb < 0) - return msb; - - return sprintf(buf, "%d\n", (msb << 8) | lsb); -} - -static ssize_t bh1780_show_power_state(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct platform_device *pdev = to_platform_device(dev); - struct bh1780_data *ddata = platform_get_drvdata(pdev); - int state; - - state = bh1780_read(ddata, BH1780_REG_CONTROL, "CONTROL"); - if (state < 0) - return state; - - return sprintf(buf, "%d\n", state & BH1780_POWMASK); -} - -static ssize_t bh1780_store_power_state(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - struct platform_device *pdev = to_platform_device(dev); - struct bh1780_data *ddata = platform_get_drvdata(pdev); - unsigned long val; - int error; - - error = kstrtoul(buf, 0, &val); - if (error) - return error; - - if (val < BH1780_POFF || val > BH1780_PON) - return -EINVAL; - - mutex_lock(&ddata->lock); - - error = bh1780_write(ddata, BH1780_REG_CONTROL, val, "CONTROL"); - if (error < 0) { - mutex_unlock(&ddata->lock); - return error; - } - - msleep(BH1780_PON_DELAY); - ddata->power_state = val; - mutex_unlock(&ddata->lock); - - return count; -} - -static DEVICE_ATTR(lux, S_IRUGO, bh1780_show_lux, NULL); - -static DEVICE_ATTR(power_state, S_IWUSR | S_IRUGO, - bh1780_show_power_state, bh1780_store_power_state); - -static struct attribute *bh1780_attributes[] = { - &dev_attr_power_state.attr, - &dev_attr_lux.attr, - NULL -}; - -static const struct attribute_group bh1780_attr_group = { - .attrs = bh1780_attributes, -}; - -static int bh1780_probe(struct i2c_client *client, - const struct i2c_device_id *id) -{ - int ret; - struct bh1780_data *ddata; - struct i2c_adapter *adapter = to_i2c_adapter(client->dev.parent); - - if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE)) - return -EIO; - - ddata = devm_kzalloc(&client->dev, sizeof(struct bh1780_data), - GFP_KERNEL); - if (ddata == NULL) - return -ENOMEM; - - ddata->client = client; - i2c_set_clientdata(client, ddata); - - ret = bh1780_read(ddata, BH1780_REG_PARTID, "PART ID"); - if (ret < 0) - return ret; - - dev_info(&client->dev, "Ambient Light Sensor, Rev : %d\n", - (ret & BH1780_REVMASK)); - - mutex_init(&ddata->lock); - - return sysfs_create_group(&client->dev.kobj, &bh1780_attr_group); -} - -static int bh1780_remove(struct i2c_client *client) -{ - sysfs_remove_group(&client->dev.kobj, &bh1780_attr_group); - - return 0; -} - -#ifdef CONFIG_PM_SLEEP -static int bh1780_suspend(struct device *dev) -{ - struct bh1780_data *ddata; - int state, ret; - struct i2c_client *client = to_i2c_client(dev); - - ddata = i2c_get_clientdata(client); - state = bh1780_read(ddata, BH1780_REG_CONTROL, "CONTROL"); - if (state < 0) - return state; - - ddata->power_state = state & BH1780_POWMASK; - - ret = bh1780_write(ddata, BH1780_REG_CONTROL, BH1780_POFF, - "CONTROL"); - - if (ret < 0) - return ret; - - return 0; -} - -static int bh1780_resume(struct device *dev) -{ - struct bh1780_data *ddata; - int state, ret; - struct i2c_client *client = to_i2c_client(dev); - - ddata = i2c_get_clientdata(client); - state = ddata->power_state; - ret = bh1780_write(ddata, BH1780_REG_CONTROL, state, - "CONTROL"); - - if (ret < 0) - return ret; - - return 0; -} -#endif /* CONFIG_PM_SLEEP */ - -static SIMPLE_DEV_PM_OPS(bh1780_pm, bh1780_suspend, bh1780_resume); - -static const struct i2c_device_id bh1780_id[] = { - { "bh1780", 0 }, - { }, -}; - -MODULE_DEVICE_TABLE(i2c, bh1780_id); - -#ifdef CONFIG_OF -static const struct of_device_id of_bh1780_match[] = { - { .compatible = "rohm,bh1780gli", }, - {}, -}; - -MODULE_DEVICE_TABLE(of, of_bh1780_match); -#endif - -static struct i2c_driver bh1780_driver = { - .probe = bh1780_probe, - .remove = bh1780_remove, - .id_table = bh1780_id, - .driver = { - .name = "bh1780", - .pm = &bh1780_pm, - .of_match_table = of_match_ptr(of_bh1780_match), - }, -}; - -module_i2c_driver(bh1780_driver); - -MODULE_DESCRIPTION("BH1780GLI Ambient Light Sensor Driver"); -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Hemanth V "); From bb9947c3a14e781eb0f137728e7e55ec8d848991 Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Thu, 14 Jul 2016 11:06:11 +0000 Subject: [PATCH 047/531] iio: pressure: bmp280: fix wrong pointer passed to PTR_ERR() PTR_ERR should access the value just tested by IS_ERR, otherwise the wrong error code will be returned. Signed-off-by: Wei Yongjun Reviewed-by: Linus Walleij Signed-off-by: Jonathan Cameron --- drivers/iio/pressure/bmp280-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c index 6943688e66df..94e27b2600f3 100644 --- a/drivers/iio/pressure/bmp280-core.c +++ b/drivers/iio/pressure/bmp280-core.c @@ -970,7 +970,7 @@ int bmp280_common_probe(struct device *dev, data->vdda = devm_regulator_get(dev, "vdda"); if (IS_ERR(data->vdda)) { dev_err(dev, "failed to get VDDA regulator\n"); - ret = PTR_ERR(data->vddd); + ret = PTR_ERR(data->vdda); goto out_disable_vddd; } ret = regulator_enable(data->vdda); From 776b645315d372e06e46167194605d308aa1a790 Mon Sep 17 00:00:00 2001 From: Phil Turnbull Date: Thu, 21 Jul 2016 11:23:13 -0400 Subject: [PATCH 048/531] staging: iio: ad5933: Return correct value for AD5933_OUT_RANGE. The 'break' statement after calling ad5933_cmd only breaks out of the 'for' loop, which then unconditionally sets the return value to -EINVAL. Move the initialisation of 'ret' so we return the correct value. Signed-off-by: Phil Turnbull Signed-off-by: Jonathan Cameron --- drivers/staging/iio/impedance-analyzer/ad5933.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/staging/iio/impedance-analyzer/ad5933.c b/drivers/staging/iio/impedance-analyzer/ad5933.c index 170ac980abcb..24c348d2f5bb 100644 --- a/drivers/staging/iio/impedance-analyzer/ad5933.c +++ b/drivers/staging/iio/impedance-analyzer/ad5933.c @@ -419,6 +419,7 @@ static ssize_t ad5933_store(struct device *dev, mutex_lock(&indio_dev->mlock); switch ((u32)this_attr->address) { case AD5933_OUT_RANGE: + ret = -EINVAL; for (i = 0; i < 4; i++) if (val == st->range_avail[i]) { st->ctrl_hb &= ~AD5933_CTRL_RANGE(0x3); @@ -426,7 +427,6 @@ static ssize_t ad5933_store(struct device *dev, ret = ad5933_cmd(st, 0); break; } - ret = -EINVAL; break; case AD5933_IN_PGA_GAIN: if (sysfs_streq(buf, "1")) { From b2f0c09664b72b2f8c581383a9337ac3092e42c8 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Mon, 11 Jul 2016 13:50:01 +0200 Subject: [PATCH 049/531] iio: sw-trigger: Fix config group initialization Use the IS_ENABLED() helper macro to ensure that the configfs group is initialized either when configfs is built-in or when configfs is built as a module. Otherwise software trigger creation will result in undefined behaviour when configfs is built as a mdoule since the configfs group for the trigger is not properly initialized. Fixes: b662f809d410 ("iio: core: Introduce IIO software triggers") Signed-off-by: Lars-Peter Clausen Acked-by: Daniel Baluta Cc: Signed-off-by: Jonathan Cameron --- include/linux/iio/sw_trigger.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/iio/sw_trigger.h b/include/linux/iio/sw_trigger.h index 5198f8ed08a4..c97eab67558f 100644 --- a/include/linux/iio/sw_trigger.h +++ b/include/linux/iio/sw_trigger.h @@ -62,7 +62,7 @@ void iio_swt_group_init_type_name(struct iio_sw_trigger *t, const char *name, struct config_item_type *type) { -#ifdef CONFIG_CONFIGFS_FS +#if IS_ENABLED(CONFIG_CONFIGFS_FS) config_group_init_type_name(&t->group, name, type); #endif } From 7d3cc21dab5313a02f2f3ca8164529b828a030d1 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Mon, 11 Jul 2016 13:54:17 +0200 Subject: [PATCH 050/531] iio: ad799x: Fix buffered capture for ad7991/ad7995/ad7999 The data buffer for captured mode for the ad799x driver is allocated in the update_scan_mode() callback. This callback is not set in the iio_info struct for the ad7791/ad7995/ad7999, which means that the data buffer is not allocated when a captured transfer is started. As a result the driver crashes when the first sample is received. To fix this properly set the update_scan_mode() callback. Fixes: d8dca33027c1 ("staging:iio:ad799x: Preallocate sample buffer") Signed-off-by: Lars-Peter Clausen Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/adc/ad799x.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iio/adc/ad799x.c b/drivers/iio/adc/ad799x.c index b6163764489c..9704090b7908 100644 --- a/drivers/iio/adc/ad799x.c +++ b/drivers/iio/adc/ad799x.c @@ -527,6 +527,7 @@ static struct attribute_group ad799x_event_attrs_group = { static const struct iio_info ad7991_info = { .read_raw = &ad799x_read_raw, .driver_module = THIS_MODULE, + .update_scan_mode = ad799x_update_scan_mode, }; static const struct iio_info ad7993_4_7_8_noirq_info = { From b234f683dde97aebb7009c6aecab651d32ad70b4 Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Mon, 11 Jul 2016 08:25:07 -0700 Subject: [PATCH 051/531] iio: accel: bma220_spi: set up buffer timestamps for non-zero values Use the iio_pollfunc_store_time parameter during triggered buffer set-up to get valid timestamps. Signed-off-by: Alison Schofield Cc: Daniel Baluta Reviewed-By: Tiberiu Breana Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/accel/bma220_spi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/accel/bma220_spi.c b/drivers/iio/accel/bma220_spi.c index 1098d10df8e8..5099f295dd37 100644 --- a/drivers/iio/accel/bma220_spi.c +++ b/drivers/iio/accel/bma220_spi.c @@ -253,7 +253,7 @@ static int bma220_probe(struct spi_device *spi) if (ret < 0) return ret; - ret = iio_triggered_buffer_setup(indio_dev, NULL, + ret = iio_triggered_buffer_setup(indio_dev, iio_pollfunc_store_time, bma220_trigger_handler, NULL); if (ret < 0) { dev_err(&spi->dev, "iio triggered buffer setup failed\n"); From 3c68858df7c2f0c4c343bb4702733fe827491f9e Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Mon, 11 Jul 2016 08:26:13 -0700 Subject: [PATCH 052/531] iio: humidity: am2315: set up buffer timestamps for non-zero values Use the iio_pollfunc_store_time parameter during triggered buffer set-up to get valid timestamps. Signed-off-by: Alison Schofield Cc: Daniel Baluta Reviewed-By: Tiberiu Breana Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/humidity/am2315.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/humidity/am2315.c b/drivers/iio/humidity/am2315.c index 3e200f69e886..ff96b6d0fdae 100644 --- a/drivers/iio/humidity/am2315.c +++ b/drivers/iio/humidity/am2315.c @@ -244,7 +244,7 @@ static int am2315_probe(struct i2c_client *client, indio_dev->channels = am2315_channels; indio_dev->num_channels = ARRAY_SIZE(am2315_channels); - ret = iio_triggered_buffer_setup(indio_dev, NULL, + ret = iio_triggered_buffer_setup(indio_dev, iio_pollfunc_store_time, am2315_trigger_handler, NULL); if (ret < 0) { dev_err(&client->dev, "iio triggered buffer setup failed\n"); From f8adf645db03345af2d9a8b6095b02327ea50885 Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Mon, 11 Jul 2016 08:26:56 -0700 Subject: [PATCH 053/531] iio: proximity: as3935: set up buffer timestamps for non-zero values Use the iio_pollfunc_store_time parameter during triggered buffer set-up to get valid timestamps. Signed-off-by: Alison Schofield Cc: Daniel Baluta Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/proximity/as3935.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/proximity/as3935.c b/drivers/iio/proximity/as3935.c index 2e3a70e1b245..5656deb17261 100644 --- a/drivers/iio/proximity/as3935.c +++ b/drivers/iio/proximity/as3935.c @@ -397,7 +397,7 @@ static int as3935_probe(struct spi_device *spi) return ret; } - ret = iio_triggered_buffer_setup(indio_dev, NULL, + ret = iio_triggered_buffer_setup(indio_dev, iio_pollfunc_store_time, &as3935_trigger_handler, NULL); if (ret) { From 45e98152850c36560484f3fa3bb857a4bfe1a419 Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Tue, 19 Jul 2016 12:25:00 -0400 Subject: [PATCH 054/531] iio: stx104: Unregister IIO device on remove callback The devm_iio_device_register function should not be used if custom operations must be performed in the remove callback. This patch replaces the dem_iio_device_register call with a iio_device_register call and respective iio_device_unregister call in the remove callback. Fixes: 765550e4d98d ("iio: stx104: Add GPIO support for the Apex Embedded Systems STX104") Signed-off-by: William Breathitt Gray Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/dac/stx104.c | 38 +++++++++++++++++++++++++++++--------- 1 file changed, 29 insertions(+), 9 deletions(-) diff --git a/drivers/iio/dac/stx104.c b/drivers/iio/dac/stx104.c index 792a97164cb2..bebbd00304ce 100644 --- a/drivers/iio/dac/stx104.c +++ b/drivers/iio/dac/stx104.c @@ -65,6 +65,16 @@ struct stx104_gpio { unsigned int out_state; }; +/** + * struct stx104_dev - STX104 device private data structure + * @indio_dev: IIO device + * @chip: instance of the gpio_chip + */ +struct stx104_dev { + struct iio_dev *indio_dev; + struct gpio_chip *chip; +}; + static int stx104_read_raw(struct iio_dev *indio_dev, struct iio_chan_spec const *chan, int *val, int *val2, long mask) { @@ -107,6 +117,7 @@ static const struct iio_chan_spec stx104_channels[STX104_NUM_CHAN] = { static int stx104_gpio_get_direction(struct gpio_chip *chip, unsigned int offset) { + /* GPIO 0-3 are input only, while the rest are output only */ if (offset < 4) return 1; @@ -169,6 +180,7 @@ static int stx104_probe(struct device *dev, unsigned int id) struct iio_dev *indio_dev; struct stx104_iio *priv; struct stx104_gpio *stx104gpio; + struct stx104_dev *stx104dev; int err; indio_dev = devm_iio_device_alloc(dev, sizeof(*priv)); @@ -179,6 +191,10 @@ static int stx104_probe(struct device *dev, unsigned int id) if (!stx104gpio) return -ENOMEM; + stx104dev = devm_kzalloc(dev, sizeof(*stx104dev), GFP_KERNEL); + if (!stx104dev) + return -ENOMEM; + if (!devm_request_region(dev, base[id], STX104_EXTENT, dev_name(dev))) { dev_err(dev, "Unable to lock port addresses (0x%X-0x%X)\n", @@ -199,12 +215,6 @@ static int stx104_probe(struct device *dev, unsigned int id) outw(0, base[id] + 4); outw(0, base[id] + 6); - err = devm_iio_device_register(dev, indio_dev); - if (err) { - dev_err(dev, "IIO device registering failed (%d)\n", err); - return err; - } - stx104gpio->chip.label = dev_name(dev); stx104gpio->chip.parent = dev; stx104gpio->chip.owner = THIS_MODULE; @@ -220,7 +230,9 @@ static int stx104_probe(struct device *dev, unsigned int id) spin_lock_init(&stx104gpio->lock); - dev_set_drvdata(dev, stx104gpio); + stx104dev->indio_dev = indio_dev; + stx104dev->chip = &stx104gpio->chip; + dev_set_drvdata(dev, stx104dev); err = gpiochip_add_data(&stx104gpio->chip, stx104gpio); if (err) { @@ -228,14 +240,22 @@ static int stx104_probe(struct device *dev, unsigned int id) return err; } + err = iio_device_register(indio_dev); + if (err) { + dev_err(dev, "IIO device registering failed (%d)\n", err); + gpiochip_remove(&stx104gpio->chip); + return err; + } + return 0; } static int stx104_remove(struct device *dev, unsigned int id) { - struct stx104_gpio *const stx104gpio = dev_get_drvdata(dev); + struct stx104_dev *const stx104dev = dev_get_drvdata(dev); - gpiochip_remove(&stx104gpio->chip); + iio_device_unregister(stx104dev->indio_dev); + gpiochip_remove(stx104dev->chip); return 0; } From 193e2d4fd91c5e5d563395f9577621dac4f4df31 Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Mon, 18 Jul 2016 17:56:43 -0700 Subject: [PATCH 055/531] iio: add Kconfig selects needed for triggered buffer compiles Select IIO_BUFFER and IIO_TRIGGERED_BUFFER to compile. Remove IIO_TRIGGER if present since IIO_BUFFER selects it. Signed-off-by: Alison Schofield Cc: Daniel Baluta Signed-off-by: Jonathan Cameron --- drivers/iio/accel/Kconfig | 5 ++++- drivers/iio/humidity/Kconfig | 2 ++ drivers/iio/light/Kconfig | 2 ++ 3 files changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/iio/accel/Kconfig b/drivers/iio/accel/Kconfig index 89d78208de3f..78f148ea9d9f 100644 --- a/drivers/iio/accel/Kconfig +++ b/drivers/iio/accel/Kconfig @@ -20,6 +20,8 @@ config BMA180 config BMA220 tristate "Bosch BMA220 3-Axis Accelerometer Driver" depends on SPI + select IIO_BUFFER + select IIO_TRIGGERED_BUFFER help Say yes here to add support for the Bosch BMA220 triaxial acceleration sensor. @@ -234,7 +236,8 @@ config STK8312 config STK8BA50 tristate "Sensortek STK8BA50 3-Axis Accelerometer Driver" depends on I2C - depends on IIO_TRIGGER + select IIO_BUFFER + select IIO_TRIGGERED_BUFFER help Say yes here to get support for the Sensortek STK8BA50 3-axis accelerometer. diff --git a/drivers/iio/humidity/Kconfig b/drivers/iio/humidity/Kconfig index 738a86d9e4a9..d04124345992 100644 --- a/drivers/iio/humidity/Kconfig +++ b/drivers/iio/humidity/Kconfig @@ -6,6 +6,8 @@ menu "Humidity sensors" config AM2315 tristate "Aosong AM2315 relative humidity and temperature sensor" depends on I2C + select IIO_BUFFER + select IIO_TRIGGERED_BUFFER help If you say yes here you get support for the Aosong AM2315 relative humidity and ambient temperature sensor. diff --git a/drivers/iio/light/Kconfig b/drivers/iio/light/Kconfig index 7c566f516572..12ceb11bc7c5 100644 --- a/drivers/iio/light/Kconfig +++ b/drivers/iio/light/Kconfig @@ -238,6 +238,8 @@ config MAX44000 tristate "MAX44000 Ambient and Infrared Proximity Sensor" depends on I2C select REGMAP_I2C + select IIO_BUFFER + select IIO_TRIGGERED_BUFFER help Say Y here if you want to build support for Maxim Integrated's MAX44000 ambient and infrared proximity sensor device. From 31f453eac56bdc41f434126bc2d5933b9fb720ec Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 27 Jul 2016 22:32:58 +0200 Subject: [PATCH 056/531] iio: pressure: bmp280: fix runtime suspend/resume crash In commit 3d838118c6aa ("iio: pressure: bmp280: add power management") For some reason the code in the runtime suspend/resume hooks got wrong (I suspect in the ambition to cut down boilerplate) and it seems it was tested without CONFIG_PM and crashes like so for me: Unable to handle kernel NULL pointer dereference at virtual address 0000000c pgd = c0204000 [0000000c] *pgd=00000000 Internal error: Oops: 5 [#1] PREEMPT SMP ARM Modules linked in: CPU: 1 PID: 89 Comm: kworker/1:2 Not tainted 4.7.0-03348-g90dc3680458a-dirty #99 Hardware name: Generic DT based system Workqueue: pm pm_runtime_work task: df3c6300 ti: dec8a000 task.ti: dec8a000 PC is at regulator_disable+0x0/0x6c LR is at bmp280_runtime_suspend+0x3c/0xa4 Dereferencing the BMP280 state container properly fixes the problem, sorry for screwing up. Fixes: 3d838118c6aa ("iio: pressure: bmp280: add power management") Signed-off-by: Linus Walleij Tested-by: Jarkko Nikula Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/pressure/bmp280-core.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c index 94e27b2600f3..e5a533cbd53f 100644 --- a/drivers/iio/pressure/bmp280-core.c +++ b/drivers/iio/pressure/bmp280-core.c @@ -1079,7 +1079,8 @@ EXPORT_SYMBOL(bmp280_common_remove); #ifdef CONFIG_PM static int bmp280_runtime_suspend(struct device *dev) { - struct bmp280_data *data = dev_get_drvdata(dev); + struct iio_dev *indio_dev = dev_get_drvdata(dev); + struct bmp280_data *data = iio_priv(indio_dev); int ret; ret = regulator_disable(data->vdda); @@ -1090,7 +1091,8 @@ static int bmp280_runtime_suspend(struct device *dev) static int bmp280_runtime_resume(struct device *dev) { - struct bmp280_data *data = dev_get_drvdata(dev); + struct iio_dev *indio_dev = dev_get_drvdata(dev); + struct bmp280_data *data = iio_priv(indio_dev); int ret; ret = regulator_enable(data->vddd); From 7b142d8fd0bd4c9bf06ccb72ac4daedb503f0124 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Thu, 16 Jun 2016 00:45:33 +0200 Subject: [PATCH 057/531] android: binder: fix dangling pointer comparison If /dev/binder is opened and the opener process then e.g. calls execve, proc->vma_vm_mm will still point to the location of the now-freed mm_struct. If the process then calls ioctl(binder_fd, ...), the dangling proc->vma_vm_mm pointer will be compared to current->mm. Let the binder take a reference to the mm_struct to avoid this. v2: use the right refcounter Fixes: a906d6931f3c ("android: binder: Sanity check at binder ioctl") Signed-off-by: Jann Horn Reviewed-by: Chen Feng Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 16288e777ec3..09fdb425e2f5 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2962,6 +2962,7 @@ static int binder_open(struct inode *nodp, struct file *filp) return -ENOMEM; get_task_struct(current); proc->tsk = current; + atomic_inc(¤t->mm->mm_count); proc->vma_vm_mm = current->mm; INIT_LIST_HEAD(&proc->todo); init_waitqueue_head(&proc->wait); @@ -3167,6 +3168,7 @@ static void binder_deferred_release(struct binder_proc *proc) vfree(proc->buffer); } + mmdrop(proc->vma_vm_mm); put_task_struct(proc->tsk); binder_debug(BINDER_DEBUG_OPEN_CLOSE, From f6b6a28e2dbc401416ff12f775d75281c9b41918 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Fri, 29 Jul 2016 16:15:18 -0300 Subject: [PATCH 058/531] nvme: Prevent controller state invalid transition Acquiring the nvme_ctrl lock before reading ctrl->state in nvme_change_ctrl_state() should prevent a theoretical invalid state transition, in the event of two threads racing inside that function. I haven't been able to observe this happening with the current code, and the current state machine seems to be simple enough to not be affected by these invalid transitions, but future modifications could make it more likely to happen. Signed-off-by: Gabriel Krisman Bertazi Reviewed-by: Sagi Grimberg Reviewed-by: Steve Wise Signed-off-by: Jens Axboe --- drivers/nvme/host/core.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 7ff2e820bbf4..7f75d661237f 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -81,10 +81,12 @@ EXPORT_SYMBOL_GPL(nvme_cancel_request); bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, enum nvme_ctrl_state new_state) { - enum nvme_ctrl_state old_state = ctrl->state; + enum nvme_ctrl_state old_state; bool changed = false; spin_lock_irq(&ctrl->lock); + + old_state = ctrl->state; switch (new_state) { case NVME_CTRL_LIVE: switch (old_state) { @@ -140,11 +142,12 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, default: break; } - spin_unlock_irq(&ctrl->lock); if (changed) ctrl->state = new_state; + spin_unlock_irq(&ctrl->lock); + return changed; } EXPORT_SYMBOL_GPL(nvme_change_ctrl_state); From 0d9dcf852334b796bacc7020364afba3122db81e Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Mon, 8 Aug 2016 11:14:36 -0700 Subject: [PATCH 059/531] iio: humidity: hdc100x: fix sensor data reads of temp and humidity Replace the i2c_smbus_read_byte commmands used to retrieve the sensor data with an i2c_master_recv command. The smbus read byte method fails because the device does not expect a stop condition after sending the first byte. When we issue the second read, we are getting the first byte again. Net effect is that of the 14 bits used for the measurement, the 8 most significant bits are correct, the lower 6 are not. None of the smbus read protocols follow the pattern this device requires (S Addr Rd [A] Data [A] Data NA P), hence the switch to an i2c receive transaction. Applicable from original introduction of this driver, but will require backporting due to churn in the code. Signed-off-by: Alison Schofield Cc: Daniel Baluta Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/humidity/hdc100x.c | 27 +++++++-------------------- 1 file changed, 7 insertions(+), 20 deletions(-) diff --git a/drivers/iio/humidity/hdc100x.c b/drivers/iio/humidity/hdc100x.c index a03832a5fc95..e0c9c70c2a4a 100644 --- a/drivers/iio/humidity/hdc100x.c +++ b/drivers/iio/humidity/hdc100x.c @@ -142,7 +142,7 @@ static int hdc100x_get_measurement(struct hdc100x_data *data, struct i2c_client *client = data->client; int delay = data->adc_int_us[chan->address]; int ret; - int val; + __be16 val; /* start measurement */ ret = i2c_smbus_write_byte(client, chan->address); @@ -154,26 +154,13 @@ static int hdc100x_get_measurement(struct hdc100x_data *data, /* wait for integration time to pass */ usleep_range(delay, delay + 1000); - /* - * i2c_smbus_read_word_data cannot() be used here due to the command - * value not being understood and causes NAKs preventing any reading - * from being accessed. - */ - ret = i2c_smbus_read_byte(client); + /* read measurement */ + ret = i2c_master_recv(data->client, (char *)&val, sizeof(val)); if (ret < 0) { - dev_err(&client->dev, "cannot read high byte measurement"); + dev_err(&client->dev, "cannot read sensor data\n"); return ret; } - val = ret << 8; - - ret = i2c_smbus_read_byte(client); - if (ret < 0) { - dev_err(&client->dev, "cannot read low byte measurement"); - return ret; - } - val |= ret; - - return val; + return be16_to_cpu(val); } static int hdc100x_get_heater_status(struct hdc100x_data *data) @@ -272,8 +259,8 @@ static int hdc100x_probe(struct i2c_client *client, struct iio_dev *indio_dev; struct hdc100x_data *data; - if (!i2c_check_functionality(client->adapter, - I2C_FUNC_SMBUS_WORD_DATA | I2C_FUNC_SMBUS_BYTE)) + if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_WORD_DATA | + I2C_FUNC_SMBUS_BYTE | I2C_FUNC_I2C)) return -EOPNOTSUPP; indio_dev = devm_iio_device_alloc(&client->dev, sizeof(*data)); From ddbc719f99cf9aed6918cef98cb3475fd4fc4fa6 Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Tue, 26 Jul 2016 20:17:43 -0700 Subject: [PATCH 060/531] tools: iio: iio_generic_buffer: initialize channel array pointer Uninitialized channel pointer causes segmentation fault when we call free(channel) during cleanup() with no channels initialized. This happens when you exit early for usage errors. Initialize the pointer to NULL when it is declared. Signed-off-by: Alison Schofield Cc: Daniel Baluta Tested-by: Gregor Boirie Signed-off-by: Jonathan Cameron --- tools/iio/iio_generic_buffer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/iio/iio_generic_buffer.c b/tools/iio/iio_generic_buffer.c index 0e8a1f7a292d..ae68bf0e2d51 100644 --- a/tools/iio/iio_generic_buffer.c +++ b/tools/iio/iio_generic_buffer.c @@ -348,7 +348,7 @@ int main(int argc, char **argv) int notrigger = 0; char *dummy; - struct iio_channel_info *channels; + struct iio_channel_info *channels = NULL; register_cleanup(); From c2ab447454d498e709d9011c0f2d2945ee321f9b Mon Sep 17 00:00:00 2001 From: Anders Darander Date: Mon, 8 Aug 2016 14:42:16 +0200 Subject: [PATCH 061/531] iio: adc: at91: unbreak channel adc channel 3 The driver always assumes that an input device has been created when reading channel 3. This causes a kernel panic when dereferencing st->ts_input. The change was introduced in commit 84882b060301 ("iio: adc: at91_adc: Add support for touchscreens without TSMR"). Earlier versions only entered that part of the if-else statement if only the following flags are set: AT91_ADC_IER_XRDY | AT91_ADC_IER_YRDY | AT91_ADC_IER_PRDY Signed-off-by: Anders Darander Acked-by: Alexandre Belloni Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/adc/at91_adc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iio/adc/at91_adc.c b/drivers/iio/adc/at91_adc.c index 52430ba171f3..0438c68015e8 100644 --- a/drivers/iio/adc/at91_adc.c +++ b/drivers/iio/adc/at91_adc.c @@ -381,8 +381,8 @@ static irqreturn_t at91_adc_rl_interrupt(int irq, void *private) st->ts_bufferedmeasure = false; input_report_key(st->ts_input, BTN_TOUCH, 0); input_sync(st->ts_input); - } else if (status & AT91_ADC_EOC(3)) { - /* Conversion finished */ + } else if (status & AT91_ADC_EOC(3) && st->ts_input) { + /* Conversion finished and we've a touchscreen */ if (st->ts_bufferedmeasure) { /* * Last measurement is always discarded, since it can From 99f1c013194e64d4b67d5d318148303b0e1585e1 Mon Sep 17 00:00:00 2001 From: Oleg Drokin Date: Thu, 14 Jul 2016 23:40:21 -0400 Subject: [PATCH 062/531] staging/lustre/llite: Close atomic_open race with several openers Right now, if it's an open of a negative dentry, a race is possible with several openers who all try to instantiate/rehash the same dentry and would hit a BUG_ON in d_add. But in fact if we got a negative dentry in atomic_open, that means we just revalidated it so no point in talking to MDS at all, just return ENOENT and make the race go away completely. Signed-off-by: Oleg Drokin Cc: stable # 4.7+ Signed-off-by: Greg Kroah-Hartman --- drivers/staging/lustre/lustre/llite/namei.c | 43 ++++++++++++--------- 1 file changed, 24 insertions(+), 19 deletions(-) diff --git a/drivers/staging/lustre/lustre/llite/namei.c b/drivers/staging/lustre/lustre/llite/namei.c index 3664bfd0178b..2c4dc69731e8 100644 --- a/drivers/staging/lustre/lustre/llite/namei.c +++ b/drivers/staging/lustre/lustre/llite/namei.c @@ -388,6 +388,7 @@ static int ll_lookup_it_finish(struct ptlrpc_request *request, struct inode *inode = NULL; __u64 bits = 0; int rc = 0; + struct dentry *alias; /* NB 1 request reference will be taken away by ll_intent_lock() * when I return @@ -412,26 +413,12 @@ static int ll_lookup_it_finish(struct ptlrpc_request *request, */ } - /* Only hash *de if it is unhashed (new dentry). - * Atoimc_open may passing hashed dentries for open. - */ - if (d_unhashed(*de)) { - struct dentry *alias; - - alias = ll_splice_alias(inode, *de); - if (IS_ERR(alias)) { - rc = PTR_ERR(alias); - goto out; - } - *de = alias; - } else if (!it_disposition(it, DISP_LOOKUP_NEG) && - !it_disposition(it, DISP_OPEN_CREATE)) { - /* With DISP_OPEN_CREATE dentry will be - * instantiated in ll_create_it. - */ - LASSERT(!d_inode(*de)); - d_instantiate(*de, inode); + alias = ll_splice_alias(inode, *de); + if (IS_ERR(alias)) { + rc = PTR_ERR(alias); + goto out; } + *de = alias; if (!it_disposition(it, DISP_LOOKUP_NEG)) { /* we have lookup look - unhide dentry */ @@ -587,6 +574,24 @@ static int ll_atomic_open(struct inode *dir, struct dentry *dentry, dentry, PFID(ll_inode2fid(dir)), dir, file, open_flags, mode, *opened); + /* Only negative dentries enter here */ + LASSERT(!d_inode(dentry)); + + if (!d_in_lookup(dentry)) { + /* A valid negative dentry that just passed revalidation, + * there's little point to try and open it server-side, + * even though there's a minuscle chance it might succeed. + * Either way it's a valid race to just return -ENOENT here. + */ + if (!(open_flags & O_CREAT)) + return -ENOENT; + + /* Otherwise we just unhash it to be rehashed afresh via + * lookup if necessary + */ + d_drop(dentry); + } + it = kzalloc(sizeof(*it), GFP_NOFS); if (!it) return -ENOMEM; From d9ae449b3d14d7c55f69af329972f175d180e68d Mon Sep 17 00:00:00 2001 From: Christoffer Dall Date: Wed, 3 Aug 2016 18:03:44 +0200 Subject: [PATCH 063/531] KVM: arm64: vgic-its: Make updates to propbaser/pendbaser atomic There are two problems with the current implementation of the MMIO handlers for the propbaser and pendbaser: First, the write to the value itself is not guaranteed to be an atomic 64-bit write so two concurrent writes to the structure field could be intermixed. Second, because we do a read-modify-update operation without any synchronization, if we have two 32-bit accesses to separate parts of the register, we can loose one of them. By using the atomic cmpxchg64 we should cover both issues above. Reviewed-by: Andre Przywara Signed-off-by: Christoffer Dall --- virt/kvm/arm/vgic/vgic-mmio-v3.c | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c index ff668e0dd586..90d81811fdda 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v3.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c @@ -306,16 +306,19 @@ static void vgic_mmio_write_propbase(struct kvm_vcpu *vcpu, { struct vgic_dist *dist = &vcpu->kvm->arch.vgic; struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - u64 propbaser = dist->propbaser; + u64 old_propbaser, propbaser; /* Storing a value with LPIs already enabled is undefined */ if (vgic_cpu->lpis_enabled) return; - propbaser = update_64bit_reg(propbaser, addr & 4, len, val); - propbaser = vgic_sanitise_propbaser(propbaser); - - dist->propbaser = propbaser; + do { + old_propbaser = dist->propbaser; + propbaser = old_propbaser; + propbaser = update_64bit_reg(propbaser, addr & 4, len, val); + propbaser = vgic_sanitise_propbaser(propbaser); + } while (cmpxchg64(&dist->propbaser, old_propbaser, + propbaser) != old_propbaser); } static unsigned long vgic_mmio_read_pendbase(struct kvm_vcpu *vcpu, @@ -331,16 +334,19 @@ static void vgic_mmio_write_pendbase(struct kvm_vcpu *vcpu, unsigned long val) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - u64 pendbaser = vgic_cpu->pendbaser; + u64 old_pendbaser, pendbaser; /* Storing a value with LPIs already enabled is undefined */ if (vgic_cpu->lpis_enabled) return; - pendbaser = update_64bit_reg(pendbaser, addr & 4, len, val); - pendbaser = vgic_sanitise_pendbaser(pendbaser); - - vgic_cpu->pendbaser = pendbaser; + do { + old_pendbaser = vgic_cpu->pendbaser; + pendbaser = old_pendbaser; + pendbaser = update_64bit_reg(pendbaser, addr & 4, len, val); + pendbaser = vgic_sanitise_pendbaser(pendbaser); + } while (cmpxchg64(&vgic_cpu->pendbaser, old_pendbaser, + pendbaser) != old_pendbaser); } /* From c7735769d5dd79afb07254532fabd9ccbd85b1fa Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Mon, 8 Aug 2016 16:45:43 +0100 Subject: [PATCH 064/531] KVM: arm64: ITS: move ITS registration into first VCPU run Currently we register an ITS device upon userland issuing the CTLR_INIT ioctl to mark initialization of the ITS as done. This deviates from the initialization sequence of the existing GIC devices and does not play well with the way QEMU handles things. To be more in line with what we are used to, register the ITS(es) just before the first VCPU is about to run, so in the map_resources() call. This involves iterating through the list of KVM devices and map each ITS that we find. Signed-off-by: Andre Przywara Reviewed-by: Eric Auger Tested-by: Eric Auger Signed-off-by: Christoffer Dall --- virt/kvm/arm/vgic/vgic-its.c | 43 +++++++++++++++++++++++++++--------- virt/kvm/arm/vgic/vgic-v3.c | 8 +++++++ virt/kvm/arm/vgic/vgic.h | 6 +++++ 3 files changed, 47 insertions(+), 10 deletions(-) diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index d06330abd5e8..1cf9f598c72a 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -1319,13 +1319,13 @@ void vgic_enable_lpis(struct kvm_vcpu *vcpu) its_sync_lpi_pending_table(vcpu); } -static int vgic_its_init_its(struct kvm *kvm, struct vgic_its *its) +static int vgic_register_its_iodev(struct kvm *kvm, struct vgic_its *its) { struct vgic_io_device *iodev = &its->iodev; int ret; - if (its->initialized) - return 0; + if (!its->initialized) + return -EBUSY; if (IS_VGIC_ADDR_UNDEF(its->vgic_its_base)) return -ENXIO; @@ -1342,9 +1342,6 @@ static int vgic_its_init_its(struct kvm *kvm, struct vgic_its *its) KVM_VGIC_V3_ITS_SIZE, &iodev->dev); mutex_unlock(&kvm->slots_lock); - if (!ret) - its->initialized = true; - return ret; } @@ -1466,9 +1463,6 @@ static int vgic_its_set_attr(struct kvm_device *dev, if (type != KVM_VGIC_ITS_ADDR_TYPE) return -ENODEV; - if (its->initialized) - return -EBUSY; - if (copy_from_user(&addr, uaddr, sizeof(addr))) return -EFAULT; @@ -1484,7 +1478,9 @@ static int vgic_its_set_attr(struct kvm_device *dev, case KVM_DEV_ARM_VGIC_GRP_CTRL: switch (attr->attr) { case KVM_DEV_ARM_VGIC_CTRL_INIT: - return vgic_its_init_its(dev->kvm, its); + its->initialized = true; + + return 0; } break; } @@ -1529,3 +1525,30 @@ int kvm_vgic_register_its_device(void) return kvm_register_device_ops(&kvm_arm_vgic_its_ops, KVM_DEV_TYPE_ARM_VGIC_ITS); } + +/* + * Registers all ITSes with the kvm_io_bus framework. + * To follow the existing VGIC initialization sequence, this has to be + * done as late as possible, just before the first VCPU runs. + */ +int vgic_register_its_iodevs(struct kvm *kvm) +{ + struct kvm_device *dev; + int ret = 0; + + list_for_each_entry(dev, &kvm->devices, vm_node) { + if (dev->ops != &kvm_arm_vgic_its_ops) + continue; + + ret = vgic_register_its_iodev(kvm, dev->private); + if (ret) + return ret; + /* + * We don't need to care about tearing down previously + * registered ITSes, as the kvm_io_bus framework removes + * them for us if the VM gets destroyed. + */ + } + + return ret; +} diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index 0506543df38a..9f0dae397d9c 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -289,6 +289,14 @@ int vgic_v3_map_resources(struct kvm *kvm) goto out; } + if (vgic_has_its(kvm)) { + ret = vgic_register_its_iodevs(kvm); + if (ret) { + kvm_err("Unable to register VGIC ITS MMIO regions\n"); + goto out; + } + } + dist->ready = true; out: diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h index 1d8e21d5c13f..6c4625c46368 100644 --- a/virt/kvm/arm/vgic/vgic.h +++ b/virt/kvm/arm/vgic/vgic.h @@ -84,6 +84,7 @@ void vgic_v3_enable(struct kvm_vcpu *vcpu); int vgic_v3_probe(const struct gic_kvm_info *info); int vgic_v3_map_resources(struct kvm *kvm); int vgic_register_redist_iodevs(struct kvm *kvm, gpa_t dist_base_address); +int vgic_register_its_iodevs(struct kvm *kvm); bool vgic_has_its(struct kvm *kvm); int kvm_vgic_register_its_device(void); void vgic_enable_lpis(struct kvm_vcpu *vcpu); @@ -140,6 +141,11 @@ static inline int vgic_register_redist_iodevs(struct kvm *kvm, return -ENODEV; } +static inline int vgic_register_its_iodevs(struct kvm *kvm) +{ + return -ENODEV; +} + static inline bool vgic_has_its(struct kvm *kvm) { return false; From 505a19eec49ab36b314a05bc062749ebdfb0aa90 Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Tue, 9 Aug 2016 10:54:29 +0100 Subject: [PATCH 065/531] KVM: arm64: check for ITS device on MSI injection When userspace provides the doorbell address for an MSI to be injected into the guest, we find a KVM device which feels responsible. Lets check that this device is really an emulated ITS before we make real use of the container_of-ed pointer. [ Moved NULL-pointer check to caller of static function - Christoffer ] Signed-off-by: Andre Przywara Reviewed-by: Christoffer Dall Signed-off-by: Christoffer Dall --- virt/kvm/arm/vgic/vgic-its.c | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index 1cf9f598c72a..9533080b47d3 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -471,6 +471,21 @@ static int vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its, return 0; } +static struct vgic_io_device *vgic_get_its_iodev(struct kvm_io_device *dev) +{ + struct vgic_io_device *iodev; + + if (dev->ops != &kvm_io_gic_ops) + return NULL; + + iodev = container_of(dev, struct vgic_io_device, dev); + + if (iodev->iodev_type != IODEV_ITS) + return NULL; + + return iodev; +} + /* * Queries the KVM IO bus framework to get the ITS pointer from the given * doorbell address. @@ -494,9 +509,11 @@ int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi) kvm_io_dev = kvm_io_bus_get_dev(kvm, KVM_MMIO_BUS, address); if (!kvm_io_dev) - return -ENODEV; + return -EINVAL; - iodev = container_of(kvm_io_dev, struct vgic_io_device, dev); + iodev = vgic_get_its_iodev(kvm_io_dev); + if (!iodev) + return -EINVAL; mutex_lock(&iodev->its->its_lock); ret = vgic_its_trigger_msi(kvm, iodev->its, msi->devid, msi->data); From 83cf8df2d4fa48a80b384fea4b09b12180a2442e Mon Sep 17 00:00:00 2001 From: Valentin Rothberg Date: Tue, 16 Aug 2016 08:27:53 +0200 Subject: [PATCH 066/531] drivers/iio/light/Kconfig: SENSORS_BH1780 cleanup Commit 7ef9153d9af5 ("misc: delete bh1780 driver") has removed the Kconfig option SENSORS_BH1780. Remove the last reference on this option. Signed-off-by: Valentin Rothberg Signed-off-by: Greg Kroah-Hartman --- drivers/iio/light/Kconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/iio/light/Kconfig b/drivers/iio/light/Kconfig index 7c566f516572..69904d55d76d 100644 --- a/drivers/iio/light/Kconfig +++ b/drivers/iio/light/Kconfig @@ -76,7 +76,6 @@ config BH1750 config BH1780 tristate "ROHM BH1780 ambient light sensor" depends on I2C - depends on !SENSORS_BH1780 help Say Y here to build support for the ROHM BH1780GLI ambient light sensor. From 39bbee4e549fbc358b2ef9137c4bf459abd164fb Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 16 Aug 2016 09:24:39 +0100 Subject: [PATCH 067/531] nvme-rdma: initialize ret to zero to avoid returning garbage ret is not initialized so it contains garbage. Ensure garbage is not returned by initializing rc to 0. Signed-off-by: Colin Ian King Signed-off-by: Sagi Grimberg --- drivers/nvme/host/rdma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 8d2875b4c56d..9c69393f6d1f 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1319,7 +1319,7 @@ static int nvme_rdma_route_resolved(struct nvme_rdma_queue *queue) static int nvme_rdma_device_unplug(struct nvme_rdma_queue *queue) { struct nvme_rdma_ctrl *ctrl = queue->ctrl; - int ret; + int ret = 0; /* Own the controller deletion */ if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING)) From 172b1d6b5a9337eb8c1ec294b80e448e03a9ac17 Mon Sep 17 00:00:00 2001 From: Xiaodong Liu Date: Fri, 12 Aug 2016 06:24:42 -0400 Subject: [PATCH 068/531] crypto: sha256-mb - fix ctx pointer and digest copy 1. fix ctx pointer Use req_ctx which is the ctx for the next job that have been completed in the lanes instead of the first completed job rctx, whose completion could have been called and released. 2. fix digest copy Use XMM register to copy another 16 bytes sha256 digest instead of a regular register. Signed-off-by: Xiaodong Liu Signed-off-by: Herbert Xu --- arch/x86/crypto/sha256-mb/sha256_mb.c | 4 ++-- arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S | 7 ++++--- 2 files changed, 6 insertions(+), 5 deletions(-) diff --git a/arch/x86/crypto/sha256-mb/sha256_mb.c b/arch/x86/crypto/sha256-mb/sha256_mb.c index 89fa85e8b10c..6f97fb33ae21 100644 --- a/arch/x86/crypto/sha256-mb/sha256_mb.c +++ b/arch/x86/crypto/sha256-mb/sha256_mb.c @@ -485,10 +485,10 @@ static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx, req = cast_mcryptd_ctx_to_req(req_ctx); if (irqs_disabled()) - rctx->complete(&req->base, ret); + req_ctx->complete(&req->base, ret); else { local_bh_disable(); - rctx->complete(&req->base, ret); + req_ctx->complete(&req->base, ret); local_bh_enable(); } } diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S index b691da981cd9..a78a0694ddef 100644 --- a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S +++ b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S @@ -265,13 +265,14 @@ ENTRY(sha256_mb_mgr_get_comp_job_avx2) vpinsrd $1, _args_digest+1*32(state, idx, 4), %xmm0, %xmm0 vpinsrd $2, _args_digest+2*32(state, idx, 4), %xmm0, %xmm0 vpinsrd $3, _args_digest+3*32(state, idx, 4), %xmm0, %xmm0 - movl _args_digest+4*32(state, idx, 4), tmp2_w + vmovd _args_digest(state , idx, 4) , %xmm0 vpinsrd $1, _args_digest+5*32(state, idx, 4), %xmm1, %xmm1 vpinsrd $2, _args_digest+6*32(state, idx, 4), %xmm1, %xmm1 vpinsrd $3, _args_digest+7*32(state, idx, 4), %xmm1, %xmm1 - vmovdqu %xmm0, _result_digest(job_rax) - movl tmp2_w, _result_digest+1*16(job_rax) + vmovdqu %xmm0, _result_digest(job_rax) + offset = (_result_digest + 1*16) + vmovdqu %xmm1, offset(job_rax) pop %rbx From e67479b13ede47cc2f5beb5b51e67fdb30778ee8 Mon Sep 17 00:00:00 2001 From: Xiaodong Liu Date: Fri, 12 Aug 2016 06:28:31 -0400 Subject: [PATCH 069/531] crypto: sha512-mb - fix ctx pointer 1. fix ctx pointer Use req_ctx which is the ctx for the next job that have been completed in the lanes instead of the first completed job rctx, whose completion could have been called and released. Signed-off-by: Xiaodong Liu Signed-off-by: Herbert Xu --- arch/x86/crypto/sha512-mb/sha512_mb.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/crypto/sha512-mb/sha512_mb.c b/arch/x86/crypto/sha512-mb/sha512_mb.c index f4cf5b78fd36..d210174a52b0 100644 --- a/arch/x86/crypto/sha512-mb/sha512_mb.c +++ b/arch/x86/crypto/sha512-mb/sha512_mb.c @@ -497,10 +497,10 @@ static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx, req = cast_mcryptd_ctx_to_req(req_ctx); if (irqs_disabled()) - rctx->complete(&req->base, ret); + req_ctx->complete(&req->base, ret); else { local_bh_disable(); - rctx->complete(&req->base, ret); + req_ctx->complete(&req->base, ret); local_bh_enable(); } } From b0f12c61de013ecb0abe19d5e64bdab45989de5a Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Tue, 16 Aug 2016 11:24:46 +0100 Subject: [PATCH 070/531] ASoC: compress: Fix leak of a widget list in soc_compr_open_fe After we have called dpcm_path_get we should make sure to call dpcm_path_put on all error paths. This was not happening causing the allocated widget list to be leaked, this patch corrects this by adding a dpcm_path_put to the error path. Signed-off-by: Charles Keepax Signed-off-by: Mark Brown --- sound/soc/soc-compress.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c index d2df46c14c68..bf7b52fce597 100644 --- a/sound/soc/soc-compress.c +++ b/sound/soc/soc-compress.c @@ -121,7 +121,7 @@ static int soc_compr_open_fe(struct snd_compr_stream *cstream) dpcm_be_disconnect(fe, stream); fe->dpcm[stream].runtime = NULL; - goto fe_err; + goto path_err; } dpcm_clear_pending_state(fe, stream); @@ -136,6 +136,8 @@ static int soc_compr_open_fe(struct snd_compr_stream *cstream) return 0; +path_err: + dpcm_path_put(&list); fe_err: if (fe->dai_link->compr_ops && fe->dai_link->compr_ops->shutdown) fe->dai_link->compr_ops->shutdown(cstream); From 3e103a65514c2947e53f3171b21255fbde8b60c6 Mon Sep 17 00:00:00 2001 From: Christoph Huber Date: Mon, 15 Aug 2016 18:59:25 +0200 Subject: [PATCH 071/531] ASoC: atmel_ssc_dai: Don't unconditionally reset SSC on stream startup commit cbaadf0f90d6 ("ASoC: atmel_ssc_dai: refactor the startup and shutdown") refactored code such that the SSC is reset on every startup; this breaks duplex audio (e.g. first start audio playback, then start record, causing the playback to stop/hang) Fixes: cbaadf0f90d6 (ASoC: atmel_ssc_dai: refactor the startup and shutdown) Signed-off-by: Christoph Huber Signed-off-by: Peter Meerwald-Stadler Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- sound/soc/atmel/atmel_ssc_dai.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/sound/soc/atmel/atmel_ssc_dai.c b/sound/soc/atmel/atmel_ssc_dai.c index 54c09acd3fed..16e459aedffe 100644 --- a/sound/soc/atmel/atmel_ssc_dai.c +++ b/sound/soc/atmel/atmel_ssc_dai.c @@ -299,8 +299,9 @@ static int atmel_ssc_startup(struct snd_pcm_substream *substream, clk_enable(ssc_p->ssc->clk); ssc_p->mck_rate = clk_get_rate(ssc_p->ssc->clk); - /* Reset the SSC to keep it at a clean status */ - ssc_writel(ssc_p->ssc->regs, CR, SSC_BIT(CR_SWRST)); + /* Reset the SSC unless initialized to keep it in a clean state */ + if (!ssc_p->initialized) + ssc_writel(ssc_p->ssc->regs, CR, SSC_BIT(CR_SWRST)); if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { dir = 0; From 3256aaef5e9a851f6be47656868020726e102187 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Vincent=20Stehl=C3=A9?= Date: Tue, 16 Aug 2016 15:11:25 +0200 Subject: [PATCH 072/531] nvmet-rdma: Fix use after free MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Avoid dereferencing the queue pointer in nvmet_rdma_release_queue_work() after it has been freed by nvmet_rdma_free_queue(). Fixes: d8f7750a08968b10 ("nvmet-rdma: Correctly handle RDMA device hot removal") Signed-off-by: Vincent Stehlé Cc: Sagi Grimberg Cc: Christoph Hellwig Signed-off-by: Sagi Grimberg --- drivers/nvme/target/rdma.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index b4d648536c3e..5de8d0a0db58 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -978,10 +978,11 @@ static void nvmet_rdma_release_queue_work(struct work_struct *w) container_of(w, struct nvmet_rdma_queue, release_work); struct rdma_cm_id *cm_id = queue->cm_id; struct nvmet_rdma_device *dev = queue->dev; + enum nvmet_rdma_queue_state state = queue->state; nvmet_rdma_free_queue(queue); - if (queue->state != NVMET_RDMA_IN_DEVICE_REMOVAL) + if (state != NVMET_RDMA_IN_DEVICE_REMOVAL) rdma_destroy_id(cm_id); kref_put(&dev->ref, nvmet_rdma_free_dev); From a956beda19a6b39fbc19d0aaf21947acdc18cf74 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 16 Aug 2016 10:26:47 -0400 Subject: [PATCH 073/531] NFS: Allow the mount option retrans=0 We should allow retrans=0 as just meaning that every timeout is a major timeout, and that there is no increment in the timeout value. For instance, this means that we would allow TCP users to specify a flat timeout value of 60s, by specifying "timeo=600,retrans=0" in their mount option string. Siged-off-by: Trond Myklebust --- fs/nfs/client.c | 10 +++++----- fs/nfs/internal.h | 5 ++++- fs/nfs/super.c | 19 +++++++++++++++++-- 3 files changed, 26 insertions(+), 8 deletions(-) diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 003ebce4bbc4..1e106780a237 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -426,7 +426,7 @@ EXPORT_SYMBOL_GPL(nfs_mark_client_ready); * Initialise the timeout values for a connection */ void nfs_init_timeout_values(struct rpc_timeout *to, int proto, - unsigned int timeo, unsigned int retrans) + int timeo, int retrans) { to->to_initval = timeo * HZ / 10; to->to_retries = retrans; @@ -434,9 +434,9 @@ void nfs_init_timeout_values(struct rpc_timeout *to, int proto, switch (proto) { case XPRT_TRANSPORT_TCP: case XPRT_TRANSPORT_RDMA: - if (to->to_retries == 0) + if (retrans == NFS_UNSPEC_RETRANS) to->to_retries = NFS_DEF_TCP_RETRANS; - if (to->to_initval == 0) + if (timeo == NFS_UNSPEC_TIMEO || to->to_retries == 0) to->to_initval = NFS_DEF_TCP_TIMEO * HZ / 10; if (to->to_initval > NFS_MAX_TCP_TIMEOUT) to->to_initval = NFS_MAX_TCP_TIMEOUT; @@ -449,9 +449,9 @@ void nfs_init_timeout_values(struct rpc_timeout *to, int proto, to->to_exponential = 0; break; case XPRT_TRANSPORT_UDP: - if (to->to_retries == 0) + if (retrans == NFS_UNSPEC_RETRANS) to->to_retries = NFS_DEF_UDP_RETRANS; - if (!to->to_initval) + if (timeo == NFS_UNSPEC_TIMEO || to->to_initval == 0) to->to_initval = NFS_DEF_UDP_TIMEO * HZ / 10; if (to->to_initval > NFS_MAX_UDP_TIMEOUT) to->to_initval = NFS_MAX_UDP_TIMEOUT; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 7ce5e023c3c3..74935a19e4bf 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -58,6 +58,9 @@ struct nfs_clone_mount { */ #define NFS_UNSPEC_PORT (-1) +#define NFS_UNSPEC_RETRANS (UINT_MAX) +#define NFS_UNSPEC_TIMEO (UINT_MAX) + /* * Maximum number of pages that readdir can use for creating * a vmapped array of pages. @@ -156,7 +159,7 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *, int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *, struct nfs_fattr *); void nfs_server_insert_lists(struct nfs_server *); void nfs_server_remove_lists(struct nfs_server *); -void nfs_init_timeout_values(struct rpc_timeout *, int, unsigned int, unsigned int); +void nfs_init_timeout_values(struct rpc_timeout *to, int proto, int timeo, int retrans); int nfs_init_server_rpcclient(struct nfs_server *, const struct rpc_timeout *t, rpc_authflavor_t); struct nfs_server *nfs_alloc_server(void); diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 18d446e1a82b..d39601381adf 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -923,6 +923,8 @@ static struct nfs_parsed_mount_data *nfs_alloc_parsed_mount_data(void) data = kzalloc(sizeof(*data), GFP_KERNEL); if (data) { + data->timeo = NFS_UNSPEC_TIMEO; + data->retrans = NFS_UNSPEC_RETRANS; data->acregmin = NFS_DEF_ACREGMIN; data->acregmax = NFS_DEF_ACREGMAX; data->acdirmin = NFS_DEF_ACDIRMIN; @@ -1189,6 +1191,19 @@ static int nfs_get_option_ul(substring_t args[], unsigned long *option) return rc; } +static int nfs_get_option_ul_bound(substring_t args[], unsigned long *option, + unsigned long l_bound, unsigned long u_bound) +{ + int ret; + + ret = nfs_get_option_ul(args, option); + if (ret != 0) + return ret; + if (*option < l_bound || *option > u_bound) + return -ERANGE; + return 0; +} + /* * Error-check and convert a string of mount options from user space into * a data structure. The whole mount string is processed; bad options are @@ -1352,12 +1367,12 @@ static int nfs_parse_mount_options(char *raw, mnt->bsize = option; break; case Opt_timeo: - if (nfs_get_option_ul(args, &option) || option == 0) + if (nfs_get_option_ul_bound(args, &option, 1, INT_MAX)) goto out_invalid_value; mnt->timeo = option; break; case Opt_retrans: - if (nfs_get_option_ul(args, &option) || option == 0) + if (nfs_get_option_ul_bound(args, &option, 0, INT_MAX)) goto out_invalid_value; mnt->retrans = option; break; From 15d03055cf39fe61714aeda8d0a722b3137531ed Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 16 Aug 2016 11:08:22 -0400 Subject: [PATCH 074/531] pNFS/flexfiles: Set reasonable default retrans values for the data channel Prior to this patch, the retrans value was set at 5, meaning that we could see a maximum retransmission timeout value of more than 6 minutes. That's a tad high for NFSv3 where the protocol does allow the server to drop requests at any time. Since this is a data channel, let's just set retrans to 0, and the default timeout to 60s. The user can continue to adjust these defaults using the dataserver_retrans and dataserver_timeo module parameters. Signed-off-by: Trond Myklebust --- fs/nfs/flexfilelayout/flexfilelayoutdev.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index 0aa36be71fce..970efba05ae1 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -17,8 +17,8 @@ #define NFSDBG_FACILITY NFSDBG_PNFS_LD -static unsigned int dataserver_timeo = NFS4_DEF_DS_TIMEO; -static unsigned int dataserver_retrans = NFS4_DEF_DS_RETRANS; +static unsigned int dataserver_timeo = NFS_DEF_TCP_RETRANS; +static unsigned int dataserver_retrans; void nfs4_ff_layout_put_deviceid(struct nfs4_ff_layout_ds *mirror_ds) { From 7afafc8a44bf0ab841b17d450b02aedb3a138985 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 16 Aug 2016 10:59:35 +0300 Subject: [PATCH 075/531] block: Fix secure erase Commit 288dab8a35a0 ("block: add a separate operation type for secure erase") split REQ_OP_SECURE_ERASE from REQ_OP_DISCARD without considering all the places REQ_OP_DISCARD was being used to mean either. Fix those. Signed-off-by: Adrian Hunter Fixes: 288dab8a35a0 ("block: add a separate operation type for secure erase") Signed-off-by: Jens Axboe --- block/bio.c | 21 +++++++++++---------- block/blk-merge.c | 33 +++++++++++++++++++-------------- block/elevator.c | 2 +- drivers/mmc/card/block.c | 1 + drivers/mmc/card/queue.c | 3 ++- drivers/mmc/card/queue.h | 4 +++- include/linux/bio.h | 10 ++++++++-- include/linux/blkdev.h | 6 ++++-- kernel/trace/blktrace.c | 2 +- 9 files changed, 50 insertions(+), 32 deletions(-) diff --git a/block/bio.c b/block/bio.c index f39477538fef..aa7354088008 100644 --- a/block/bio.c +++ b/block/bio.c @@ -667,18 +667,19 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask, bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector; bio->bi_iter.bi_size = bio_src->bi_iter.bi_size; - if (bio_op(bio) == REQ_OP_DISCARD) - goto integrity_clone; - - if (bio_op(bio) == REQ_OP_WRITE_SAME) { + switch (bio_op(bio)) { + case REQ_OP_DISCARD: + case REQ_OP_SECURE_ERASE: + break; + case REQ_OP_WRITE_SAME: bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0]; - goto integrity_clone; + break; + default: + bio_for_each_segment(bv, bio_src, iter) + bio->bi_io_vec[bio->bi_vcnt++] = bv; + break; } - bio_for_each_segment(bv, bio_src, iter) - bio->bi_io_vec[bio->bi_vcnt++] = bv; - -integrity_clone: if (bio_integrity(bio_src)) { int ret; @@ -1788,7 +1789,7 @@ struct bio *bio_split(struct bio *bio, int sectors, * Discards need a mutable bio_vec to accommodate the payload * required by the DSM TRIM and UNMAP commands. */ - if (bio_op(bio) == REQ_OP_DISCARD) + if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE) split = bio_clone_bioset(bio, gfp, bs); else split = bio_clone_fast(bio, gfp, bs); diff --git a/block/blk-merge.c b/block/blk-merge.c index 3eec75a9e91d..72627e3cf91e 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -172,12 +172,18 @@ void blk_queue_split(struct request_queue *q, struct bio **bio, struct bio *split, *res; unsigned nsegs; - if (bio_op(*bio) == REQ_OP_DISCARD) + switch (bio_op(*bio)) { + case REQ_OP_DISCARD: + case REQ_OP_SECURE_ERASE: split = blk_bio_discard_split(q, *bio, bs, &nsegs); - else if (bio_op(*bio) == REQ_OP_WRITE_SAME) + break; + case REQ_OP_WRITE_SAME: split = blk_bio_write_same_split(q, *bio, bs, &nsegs); - else + break; + default: split = blk_bio_segment_split(q, *bio, q->bio_split, &nsegs); + break; + } /* physical segments can be figured out during splitting */ res = split ? split : *bio; @@ -213,7 +219,7 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q, * This should probably be returning 0, but blk_add_request_payload() * (Christoph!!!!) */ - if (bio_op(bio) == REQ_OP_DISCARD) + if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE) return 1; if (bio_op(bio) == REQ_OP_WRITE_SAME) @@ -385,7 +391,9 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio, nsegs = 0; cluster = blk_queue_cluster(q); - if (bio_op(bio) == REQ_OP_DISCARD) { + switch (bio_op(bio)) { + case REQ_OP_DISCARD: + case REQ_OP_SECURE_ERASE: /* * This is a hack - drivers should be neither modifying the * biovec, nor relying on bi_vcnt - but because of @@ -393,19 +401,16 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio, * a payload we need to set up here (thank you Christoph) and * bi_vcnt is really the only way of telling if we need to. */ - - if (bio->bi_vcnt) - goto single_segment; - - return 0; - } - - if (bio_op(bio) == REQ_OP_WRITE_SAME) { -single_segment: + if (!bio->bi_vcnt) + return 0; + /* Fall through */ + case REQ_OP_WRITE_SAME: *sg = sglist; bvec = bio_iovec(bio); sg_set_page(*sg, bvec.bv_page, bvec.bv_len, bvec.bv_offset); return 1; + default: + break; } for_each_bio(bio) diff --git a/block/elevator.c b/block/elevator.c index 7096c22041e7..f7d973a56fd7 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -366,7 +366,7 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq) list_for_each_prev(entry, &q->queue_head) { struct request *pos = list_entry_rq(entry); - if ((req_op(rq) == REQ_OP_DISCARD) != (req_op(pos) == REQ_OP_DISCARD)) + if (req_op(rq) != req_op(pos)) break; if (rq_data_dir(rq) != rq_data_dir(pos)) break; diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index 48a5dd740f3b..82503e6f04b3 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -1726,6 +1726,7 @@ static u8 mmc_blk_prep_packed_list(struct mmc_queue *mq, struct request *req) break; if (req_op(next) == REQ_OP_DISCARD || + req_op(next) == REQ_OP_SECURE_ERASE || req_op(next) == REQ_OP_FLUSH) break; diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c index bf14642a576a..29578e98603d 100644 --- a/drivers/mmc/card/queue.c +++ b/drivers/mmc/card/queue.c @@ -33,7 +33,8 @@ static int mmc_prep_request(struct request_queue *q, struct request *req) /* * We only like normal block requests and discards. */ - if (req->cmd_type != REQ_TYPE_FS && req_op(req) != REQ_OP_DISCARD) { + if (req->cmd_type != REQ_TYPE_FS && req_op(req) != REQ_OP_DISCARD && + req_op(req) != REQ_OP_SECURE_ERASE) { blk_dump_rq_flags(req, "MMC bad request"); return BLKPREP_KILL; } diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h index d62531124d54..fee5e1271465 100644 --- a/drivers/mmc/card/queue.h +++ b/drivers/mmc/card/queue.h @@ -4,7 +4,9 @@ static inline bool mmc_req_is_special(struct request *req) { return req && - (req_op(req) == REQ_OP_FLUSH || req_op(req) == REQ_OP_DISCARD); + (req_op(req) == REQ_OP_FLUSH || + req_op(req) == REQ_OP_DISCARD || + req_op(req) == REQ_OP_SECURE_ERASE); } struct request; diff --git a/include/linux/bio.h b/include/linux/bio.h index 59ffaa68b11b..23ddf4b46a9b 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -71,7 +71,8 @@ static inline bool bio_has_data(struct bio *bio) { if (bio && bio->bi_iter.bi_size && - bio_op(bio) != REQ_OP_DISCARD) + bio_op(bio) != REQ_OP_DISCARD && + bio_op(bio) != REQ_OP_SECURE_ERASE) return true; return false; @@ -79,7 +80,9 @@ static inline bool bio_has_data(struct bio *bio) static inline bool bio_no_advance_iter(struct bio *bio) { - return bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_WRITE_SAME; + return bio_op(bio) == REQ_OP_DISCARD || + bio_op(bio) == REQ_OP_SECURE_ERASE || + bio_op(bio) == REQ_OP_WRITE_SAME; } static inline bool bio_is_rw(struct bio *bio) @@ -199,6 +202,9 @@ static inline unsigned bio_segments(struct bio *bio) if (bio_op(bio) == REQ_OP_DISCARD) return 1; + if (bio_op(bio) == REQ_OP_SECURE_ERASE) + return 1; + if (bio_op(bio) == REQ_OP_WRITE_SAME) return 1; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2c210b6a7bcf..e79055c8b577 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -882,7 +882,7 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq) static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, int op) { - if (unlikely(op == REQ_OP_DISCARD)) + if (unlikely(op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE)) return min(q->limits.max_discard_sectors, UINT_MAX >> 9); if (unlikely(op == REQ_OP_WRITE_SAME)) @@ -913,7 +913,9 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq, if (unlikely(rq->cmd_type != REQ_TYPE_FS)) return q->limits.max_hw_sectors; - if (!q->limits.chunk_sectors || (req_op(rq) == REQ_OP_DISCARD)) + if (!q->limits.chunk_sectors || + req_op(rq) == REQ_OP_DISCARD || + req_op(rq) == REQ_OP_SECURE_ERASE) return blk_queue_get_max_sectors(q, req_op(rq)); return min(blk_max_size_offset(q, offset), diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 7598e6ca817a..dbafc5df03f3 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -223,7 +223,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, what |= MASK_TC_BIT(op_flags, META); what |= MASK_TC_BIT(op_flags, PREFLUSH); what |= MASK_TC_BIT(op_flags, FUA); - if (op == REQ_OP_DISCARD) + if (op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE) what |= BLK_TC_ACT(BLK_TC_DISCARD); if (op == REQ_OP_FLUSH) what |= BLK_TC_ACT(BLK_TC_FLUSH); From 286054a7a8674b256da16564d96772b88896eb35 Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Tue, 16 Aug 2016 17:51:06 +0100 Subject: [PATCH 076/531] KVM: arm64: ITS: avoid re-mapping LPIs When a guest wants to map a device-ID/event-ID combination that is already mapped, we may end up in a situation where an LPI is never "put", thus never being freed. Since the GICv3 spec says that mapping an already mapped LPI is UNPREDICTABLE, lets just bail out early in this situation to avoid any potential leaks. Signed-off-by: Andre Przywara Reviewed-by: Christoffer Dall Signed-off-by: Christoffer Dall --- virt/kvm/arm/vgic/vgic-its.c | 27 +++++++++++++-------------- 1 file changed, 13 insertions(+), 14 deletions(-) diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index 9533080b47d3..4660a7d04eea 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -731,7 +731,7 @@ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its, u32 device_id = its_cmd_get_deviceid(its_cmd); u32 event_id = its_cmd_get_id(its_cmd); u32 coll_id = its_cmd_get_collection(its_cmd); - struct its_itte *itte, *new_itte = NULL; + struct its_itte *itte; struct its_device *device; struct its_collection *collection, *new_coll = NULL; int lpi_nr; @@ -749,6 +749,10 @@ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its, lpi_nr >= max_lpis_propbaser(kvm->arch.vgic.propbaser)) return E_ITS_MAPTI_PHYSICALID_OOR; + /* If there is an existing mapping, behavior is UNPREDICTABLE. */ + if (find_itte(its, device_id, event_id)) + return 0; + collection = find_collection(its, coll_id); if (!collection) { int ret = vgic_its_alloc_collection(its, &collection, coll_id); @@ -757,20 +761,16 @@ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its, new_coll = collection; } - itte = find_itte(its, device_id, event_id); + itte = kzalloc(sizeof(struct its_itte), GFP_KERNEL); if (!itte) { - itte = kzalloc(sizeof(struct its_itte), GFP_KERNEL); - if (!itte) { - if (new_coll) - vgic_its_free_collection(its, coll_id); - return -ENOMEM; - } - - new_itte = itte; - itte->event_id = event_id; - list_add_tail(&itte->itte_list, &device->itt_head); + if (new_coll) + vgic_its_free_collection(its, coll_id); + return -ENOMEM; } + itte->event_id = event_id; + list_add_tail(&itte->itte_list, &device->itt_head); + itte->collection = collection; itte->lpi = lpi_nr; @@ -778,8 +778,7 @@ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its, if (IS_ERR(irq)) { if (new_coll) vgic_its_free_collection(its, coll_id); - if (new_itte) - its_free_itte(kvm, new_itte); + its_free_itte(kvm, itte); return PTR_ERR(irq); } itte->irq = irq; From 67540759151aefafddade3e27c4671ab7b3d230f Mon Sep 17 00:00:00 2001 From: Milian Wolff Date: Tue, 16 Aug 2016 17:39:26 +0200 Subject: [PATCH 077/531] perf unwind: Use addr_location::addr instead of ip for entries This fixes the srcline translation for call chains of user space applications. Before we got: perf report --stdio --no-children -s sym,srcline -g address 8.92% [.] main mandelbrot.h:41 | |--3.70%--main +8390240 | __libc_start_main +139950056726769 | _start +8388650 | |--2.74%--main +8390189 | --2.08%--main +8390296 __libc_start_main +139950056726769 _start +8388650 7.59% [.] main complex:1326 | |--4.79%--main +8390203 | __libc_start_main +139950056726769 | _start +8388650 | --2.80%--main +8390219 7.12% [.] __muldc3 libgcc2.c:1945 | |--3.76%--__muldc3 +139950060519490 | main +8390224 | __libc_start_main +139950056726769 | _start +8388650 | --3.32%--__muldc3 +139950060519512 main +8390224 With this patch applied, we instead get: perf report --stdio --no-children -s sym,srcline -g address 8.92% [.] main mandelbrot.h:41 | |--3.70%--main mandelbrot.h:41 | __libc_start_main +241 | _start +4194346 | |--2.74%--main mandelbrot.h:41 | --2.08%--main mandelbrot.h:41 __libc_start_main +241 _start +4194346 7.59% [.] main complex:1326 | |--4.79%--main complex:1326 | __libc_start_main +241 | _start +4194346 | --2.80%--main complex:1326 7.12% [.] __muldc3 libgcc2.c:1945 | |--3.76%--__muldc3 libgcc2.c:1945 | main mandelbrot.h:39 | __libc_start_main +241 | _start +4194346 | --3.32%--__muldc3 libgcc2.c:1945 main mandelbrot.h:39 Suggested-and-Acked-by: Namhyung Kim Signed-off-by: Milian Wolff Tested-by: Arnaldo Carvalho de Melo LPU-Reference: 20160816153926.11288-1-milian.wolff@kdab.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/unwind-libdw.c | 2 +- tools/perf/util/unwind-libunwind-local.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index cf5e250bc78e..783a53fb7a4e 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -66,7 +66,7 @@ static int entry(u64 ip, struct unwind_info *ui) if (__report_module(&al, ip, ui)) return -1; - e->ip = ip; + e->ip = al.addr; e->map = al.map; e->sym = al.sym; diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 97c0f8fc5561..20c2e5743903 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -542,7 +542,7 @@ static int entry(u64 ip, struct thread *thread, thread__find_addr_location(thread, PERF_RECORD_MISC_USER, MAP__FUNCTION, ip, &al); - e.ip = ip; + e.ip = al.addr; e.map = al.map; e.sym = al.sym; From 4fe0d154880bb6eb833cbe84fa6f385f400f0b9c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 11 Aug 2016 07:11:04 -0700 Subject: [PATCH 078/531] PCI: Use positive flags in pci_alloc_irq_vectors() Instead of passing negative flags like PCI_IRQ_NOMSI to prevent use of certain interrupt types, pass positive flags like PCI_IRQ_LEGACY, PCI_IRQ_MSI, etc., to specify the acceptable interrupt types. This is based on a number of pending driver conversions that just happend to be a whole more obvious to read this way, and given that we have no users in the tree yet it can still easily be done. I've also added a PCI_IRQ_ALL_TYPES catchall to keep the case of accepting all interrupt types very simple. [bhelgaas: changelog, fix PCI_IRQ_AFFINITY doc typo, remove mention of PCI_IRQ_NOLEGACY] Signed-off-by: Christoph Hellwig Signed-off-by: Bjorn Helgaas Reviewed-by: Alexander Gordeev --- Documentation/PCI/MSI-HOWTO.txt | 24 ++++++++++-------------- drivers/pci/msi.c | 15 +++++++-------- include/linux/pci.h | 10 ++++++---- 3 files changed, 23 insertions(+), 26 deletions(-) diff --git a/Documentation/PCI/MSI-HOWTO.txt b/Documentation/PCI/MSI-HOWTO.txt index c55df2911136..cd9c9f6a7cd9 100644 --- a/Documentation/PCI/MSI-HOWTO.txt +++ b/Documentation/PCI/MSI-HOWTO.txt @@ -94,14 +94,11 @@ has a requirements for a minimum number of vectors the driver can pass a min_vecs argument set to this limit, and the PCI core will return -ENOSPC if it can't meet the minimum number of vectors. -The flags argument should normally be set to 0, but can be used to pass the -PCI_IRQ_NOMSI and PCI_IRQ_NOMSIX flag in case a device claims to support -MSI or MSI-X, but the support is broken, or to pass PCI_IRQ_NOLEGACY in -case the device does not support legacy interrupt lines. - -By default this function will spread the interrupts around the available -CPUs, but this feature can be disabled by passing the PCI_IRQ_NOAFFINITY -flag. +The flags argument is used to specify which type of interrupt can be used +by the device and the driver (PCI_IRQ_LEGACY, PCI_IRQ_MSI, PCI_IRQ_MSIX). +A convenient short-hand (PCI_IRQ_ALL_TYPES) is also available to ask for +any possible kind of interrupt. If the PCI_IRQ_AFFINITY flag is set, +pci_alloc_irq_vectors() will spread the interrupts around the available CPUs. To get the Linux IRQ numbers passed to request_irq() and free_irq() and the vectors, use the following function: @@ -131,7 +128,7 @@ larger than the number supported by the device it will automatically be capped to the supported limit, so there is no need to query the number of vectors supported beforehand: - nvec = pci_alloc_irq_vectors(pdev, 1, nvec, 0); + nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_ALL_TYPES) if (nvec < 0) goto out_err; @@ -140,7 +137,7 @@ interrupts it can request a particular number of interrupts by passing that number to pci_alloc_irq_vectors() function as both 'min_vecs' and 'max_vecs' parameters: - ret = pci_alloc_irq_vectors(pdev, nvec, nvec, 0); + ret = pci_alloc_irq_vectors(pdev, nvec, nvec, PCI_IRQ_ALL_TYPES); if (ret < 0) goto out_err; @@ -148,15 +145,14 @@ The most notorious example of the request type described above is enabling the single MSI mode for a device. It could be done by passing two 1s as 'min_vecs' and 'max_vecs': - ret = pci_alloc_irq_vectors(pdev, 1, 1, 0); + ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES); if (ret < 0) goto out_err; Some devices might not support using legacy line interrupts, in which case -the PCI_IRQ_NOLEGACY flag can be used to fail the request if the platform -can't provide MSI or MSI-X interrupts: +the driver can specify that only MSI or MSI-X is acceptable: - nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_NOLEGACY); + nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_MSI | PCI_IRQ_MSIX); if (nvec < 0) goto out_err; diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index a02981efdad5..9233e7f62f47 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -1069,7 +1069,7 @@ static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, nvec = maxvec; for (;;) { - if (!(flags & PCI_IRQ_NOAFFINITY)) { + if (flags & PCI_IRQ_AFFINITY) { dev->irq_affinity = irq_create_affinity_mask(&nvec); if (nvec < minvec) return -ENOSPC; @@ -1105,7 +1105,7 @@ static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, **/ int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec) { - return __pci_enable_msi_range(dev, minvec, maxvec, PCI_IRQ_NOAFFINITY); + return __pci_enable_msi_range(dev, minvec, maxvec, 0); } EXPORT_SYMBOL(pci_enable_msi_range); @@ -1120,7 +1120,7 @@ static int __pci_enable_msix_range(struct pci_dev *dev, return -ERANGE; for (;;) { - if (!(flags & PCI_IRQ_NOAFFINITY)) { + if (flags & PCI_IRQ_AFFINITY) { dev->irq_affinity = irq_create_affinity_mask(&nvec); if (nvec < minvec) return -ENOSPC; @@ -1160,8 +1160,7 @@ static int __pci_enable_msix_range(struct pci_dev *dev, int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int minvec, int maxvec) { - return __pci_enable_msix_range(dev, entries, minvec, maxvec, - PCI_IRQ_NOAFFINITY); + return __pci_enable_msix_range(dev, entries, minvec, maxvec, 0); } EXPORT_SYMBOL(pci_enable_msix_range); @@ -1187,21 +1186,21 @@ int pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, { int vecs = -ENOSPC; - if (!(flags & PCI_IRQ_NOMSIX)) { + if (flags & PCI_IRQ_MSIX) { vecs = __pci_enable_msix_range(dev, NULL, min_vecs, max_vecs, flags); if (vecs > 0) return vecs; } - if (!(flags & PCI_IRQ_NOMSI)) { + if (flags & PCI_IRQ_MSI) { vecs = __pci_enable_msi_range(dev, min_vecs, max_vecs, flags); if (vecs > 0) return vecs; } /* use legacy irq if allowed */ - if (!(flags & PCI_IRQ_NOLEGACY) && min_vecs == 1) + if ((flags & PCI_IRQ_LEGACY) && min_vecs == 1) return 1; return vecs; } diff --git a/include/linux/pci.h b/include/linux/pci.h index 2599a980340f..fbc1fa625c3e 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1251,10 +1251,12 @@ resource_size_t pcibios_iov_resource_alignment(struct pci_dev *dev, int resno); int pci_set_vga_state(struct pci_dev *pdev, bool decode, unsigned int command_bits, u32 flags); -#define PCI_IRQ_NOLEGACY (1 << 0) /* don't use legacy interrupts */ -#define PCI_IRQ_NOMSI (1 << 1) /* don't use MSI interrupts */ -#define PCI_IRQ_NOMSIX (1 << 2) /* don't use MSI-X interrupts */ -#define PCI_IRQ_NOAFFINITY (1 << 3) /* don't auto-assign affinity */ +#define PCI_IRQ_LEGACY (1 << 0) /* allow legacy interrupts */ +#define PCI_IRQ_MSI (1 << 1) /* allow MSI interrupts */ +#define PCI_IRQ_MSIX (1 << 2) /* allow MSI-X interrupts */ +#define PCI_IRQ_AFFINITY (1 << 3) /* auto-assign affinity */ +#define PCI_IRQ_ALL_TYPES \ + (PCI_IRQ_LEGACY | PCI_IRQ_MSI | PCI_IRQ_MSIX) /* kmem_cache style wrapper around pci_alloc_consistent() */ From b347af816ad2086c1dacf9f74973b82f83e877be Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 11 Aug 2016 17:14:45 -0700 Subject: [PATCH 079/531] md: do not count journal as spare in GET_ARRAY_INFO GET_ARRAY_INFO counts journal as spare (spare_disks), which is not accurate. This patch fixes this. Reported-by: Yi Zhang Signed-off-by: Song Liu Signed-off-by: Shaohua Li --- drivers/md/md.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/md/md.c b/drivers/md/md.c index 2c3ab6f5e6be..d750b52376b9 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5851,6 +5851,9 @@ static int get_array_info(struct mddev *mddev, void __user *arg) working++; if (test_bit(In_sync, &rdev->flags)) insync++; + else if (test_bit(Journal, &rdev->flags)) + /* TODO: add journal count to md_u.h */ + ; else spare++; } From 1b856086813be9371929b6cc62045f9fd470f5a0 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 16 Aug 2016 16:48:36 -0700 Subject: [PATCH 080/531] block: Fix race triggered by blk_set_queue_dying() blk_set_queue_dying() can be called while another thread is submitting I/O or changing queue flags, e.g. through dm_stop_queue(). Hence protect the QUEUE_FLAG_DYING flag change with locking. Signed-off-by: Bart Van Assche Cc: Christoph Hellwig Cc: Mike Snitzer Cc: stable Signed-off-by: Jens Axboe --- block/blk-core.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/block/blk-core.c b/block/blk-core.c index 999442ec4601..36c7ac328d8c 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -515,7 +515,9 @@ EXPORT_SYMBOL_GPL(blk_queue_bypass_end); void blk_set_queue_dying(struct request_queue *q) { - queue_flag_set_unlocked(QUEUE_FLAG_DYING, q); + spin_lock_irq(q->queue_lock); + queue_flag_set(QUEUE_FLAG_DYING, q); + spin_unlock_irq(q->queue_lock); if (q->mq_ops) blk_mq_wake_waiters(q); From 9ac715954682b23d293d910ad2697554171035e7 Mon Sep 17 00:00:00 2001 From: Christoffer Dall Date: Wed, 17 Aug 2016 10:46:10 +0200 Subject: [PATCH 081/531] KVM: arm/arm64: Change misleading use of is_error_pfn When converting a gfn to a pfn, we call gfn_to_pfn_prot, which returns various kinds of error values. It turns out that is_error_pfn() only returns true when the gfn was found in a memory slot and could somehow not be used, but it does not return true if the gfn does not belong to any memory slot. Change use to is_error_noslot_pfn() which covers both cases. Note: Since we already check for kvm_is_error_hva(hva) explicitly in the caller of this function while holding the kvm->srcu lock protecting the memory slots, this should never be a problem, but nevertheless this change is warranted as it shows the intention of the code. Reported-by: James Hogan Signed-off-by: Christoffer Dall --- arch/arm/kvm/mmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index bda27b6b1aa2..29d0b23af2a9 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -1309,7 +1309,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, smp_rmb(); pfn = gfn_to_pfn_prot(kvm, gfn, write_fault, &writable); - if (is_error_pfn(pfn)) + if (is_error_noslot_pfn(pfn)) return -EFAULT; if (kvm_is_device_pfn(pfn)) { From 674e70127069f3fd3c58fb0f94c60eb0f6567d78 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 16 Aug 2016 15:03:01 +0100 Subject: [PATCH 082/531] arm64: Document workaround for Cortex-A72 erratum #853709 We already have a workaround for Cortex-A57 erratum #852523, but Cortex-A72 r0p0 to r0p2 do suffer from the same issue (known as erratum #853709). Let's document the fact that we already handle this. Acked-by: Will Deacon Signed-off-by: Marc Zyngier Signed-off-by: Christoffer Dall --- Documentation/arm64/silicon-errata.txt | 1 + arch/arm64/kvm/hyp/switch.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt index 4da60b463995..ccc60324e738 100644 --- a/Documentation/arm64/silicon-errata.txt +++ b/Documentation/arm64/silicon-errata.txt @@ -53,6 +53,7 @@ stable kernels. | ARM | Cortex-A57 | #832075 | ARM64_ERRATUM_832075 | | ARM | Cortex-A57 | #852523 | N/A | | ARM | Cortex-A57 | #834220 | ARM64_ERRATUM_834220 | +| ARM | Cortex-A72 | #853709 | N/A | | ARM | MMU-500 | #841119,#826419 | N/A | | | | | | | Cavium | ThunderX ITS | #22375, #24313 | CAVIUM_ERRATUM_22375 | diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index ae7855f16ec2..5a84b4562603 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -256,7 +256,7 @@ static int __hyp_text __guest_run(struct kvm_vcpu *vcpu) /* * We must restore the 32-bit state before the sysregs, thanks - * to Cortex-A57 erratum #852523. + * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72). */ __sysreg32_restore_state(vcpu); __sysreg_restore_guest_state(guest_ctxt); From cabdc5c59ab46a1ec5ea98c5ac4022111fbfd63a Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 16 Aug 2016 15:03:02 +0100 Subject: [PATCH 083/531] KVM: arm/arm64: timer: Workaround misconfigured timer interrupt Similarily to f005bd7e3b84 ("clocksource/arm_arch_timer: Force per-CPU interrupt to be level-triggered"), make sure we can survive an interrupt that has been misconfigured as edge-triggered by forcing it to be level-triggered (active low is assumed, but the GIC doesn't really care whether this is high or low). Hopefully, the amount of shouting in the kernel log will convince the user to do something about their firmware. Signed-off-by: Marc Zyngier Signed-off-by: Christoffer Dall --- virt/kvm/arm/arch_timer.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c index 4fde8c7dfcfe..77e6ccf14901 100644 --- a/virt/kvm/arm/arch_timer.c +++ b/virt/kvm/arm/arch_timer.c @@ -33,6 +33,7 @@ static struct timecounter *timecounter; static struct workqueue_struct *wqueue; static unsigned int host_vtimer_irq; +static u32 host_vtimer_irq_flags; void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) { @@ -365,7 +366,7 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) static void kvm_timer_init_interrupt(void *info) { - enable_percpu_irq(host_vtimer_irq, 0); + enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags); } int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value) @@ -432,6 +433,14 @@ int kvm_timer_hyp_init(void) } host_vtimer_irq = info->virtual_irq; + host_vtimer_irq_flags = irq_get_trigger_type(host_vtimer_irq); + if (host_vtimer_irq_flags != IRQF_TRIGGER_HIGH && + host_vtimer_irq_flags != IRQF_TRIGGER_LOW) { + kvm_err("Invalid trigger for IRQ%d, assuming level low\n", + host_vtimer_irq); + host_vtimer_irq_flags = IRQF_TRIGGER_LOW; + } + err = request_percpu_irq(host_vtimer_irq, kvm_arch_timer_handler, "kvm guest timer", kvm_get_running_vcpus()); if (err) { From 1e12c4a9393b75a744aada2c8115434572698bc3 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 11 Aug 2016 14:19:42 +0100 Subject: [PATCH 084/531] genirq: Correctly configure the trigger on chained interrupts Commit 1e2a7d78499e ("irqdomain: Don't set type when mapping an IRQ") moved the trigger configuration call from the irqdomain mapping to the interrupt being actually requested. This patch failed to handle the case where we configure a chained interrupt, which doesn't get requested through the usual path. In order to solve this, let's call __irq_set_trigger just before starting the cascade interrupt. Special care must be taken to make the flow handler stick, as the .irq_set_type method could have reset it (it doesn't know we're dealing with a chained interrupt). Based on an initial patch by Jon Hunter. Fixes: 1e2a7d78499e ("irqdomain: Don't set type when mapping an IRQ") Reported-by: John Stultz Reported-by: Linus Walleij Tested-by: John Stultz Acked-by: Jon Hunter Signed-off-by: Marc Zyngier --- kernel/irq/chip.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index b4c1bc7c9ca2..637389088b3f 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -820,6 +820,17 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle, desc->name = name; if (handle != handle_bad_irq && is_chained) { + /* + * We're about to start this interrupt immediately, + * hence the need to set the trigger configuration. + * But the .set_type callback may have overridden the + * flow handler, ignoring that we're dealing with a + * chained interrupt. Reset it immediately because we + * do know better. + */ + __irq_set_trigger(desc, irqd_get_trigger_type(&desc->irq_data)); + desc->handle_irq = handle; + irq_settings_set_noprobe(desc); irq_settings_set_norequest(desc); irq_settings_set_nothread(desc); From b63bebe2355cf2632a2979fd2982c88d080c44b6 Mon Sep 17 00:00:00 2001 From: Vladimir Murzin Date: Wed, 10 Aug 2016 10:49:42 +0100 Subject: [PATCH 085/531] arm64: KVM: remove misleading comment on pmu status Comment about how PMU access is handled is not relavant since v4.6 where proper PMU support was added in. Signed-off-by: Vladimir Murzin Acked-by: Marc Zyngier Signed-off-by: Christoffer Dall --- arch/arm64/kvm/sys_regs.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index b0b225ceca18..af5ea86d1c19 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -823,14 +823,6 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, * Architected system registers. * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2 * - * We could trap ID_DFR0 and tell the guest we don't support performance - * monitoring. Unfortunately the patch to make the kernel check ID_DFR0 was - * NAKed, so it will read the PMCR anyway. - * - * Therefore we tell the guest we have 0 counters. Unfortunately, we - * must always support PMCCNTR (the cycle counter): we just RAZ/WI for - * all PM registers, which doesn't crash the guest kernel at least. - * * Debug handling: We do trap most, if not all debug related system * registers. The implementation is good enough to ensure that a guest * can use these with minimal performance degradation. The drawback is From f7f6f2d94f0027242ddfd665289b107a873fde43 Mon Sep 17 00:00:00 2001 From: Vladimir Murzin Date: Wed, 10 Aug 2016 10:49:43 +0100 Subject: [PATCH 086/531] arm64: KVM: report configured SRE value to 32-bit world After commit b34f2bc ("arm64: KVM: Make ICC_SRE_EL1 access return the configured SRE value") we report SRE value to 64-bit guest, but 32-bit one still handled as RAZ/WI what leads to funny promise we do not keep: "GICv3: GIC: unable to set SRE (disabled at EL2), panic ahead" Instead, return the actual value of the ICC_SRE_EL1 register that the guest should see. [ Tweaked commit message - Christoffer ] Signed-off-by: Vladimir Murzin Acked-by: Marc Zyngier Signed-off-by: Christoffer Dall --- arch/arm64/kvm/sys_regs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index af5ea86d1c19..e51367d159d0 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1352,7 +1352,7 @@ static const struct sys_reg_desc cp15_regs[] = { { Op1( 0), CRn(10), CRm( 3), Op2( 1), access_vm_reg, NULL, c10_AMAIR1 }, /* ICC_SRE */ - { Op1( 0), CRn(12), CRm(12), Op2( 5), trap_raz_wi }, + { Op1( 0), CRn(12), CRm(12), Op2( 5), access_gic_sre }, { Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, c13_CID }, From 568ac888215c7fb2fabe8ea739b00ec3c1f5d440 Mon Sep 17 00:00:00 2001 From: Balbir Singh Date: Wed, 10 Aug 2016 15:43:06 -0400 Subject: [PATCH 087/531] cgroup: reduce read locked section of cgroup_threadgroup_rwsem during fork cgroup_threadgroup_rwsem is acquired in read mode during process exit and fork. It is also grabbed in write mode during __cgroups_proc_write(). I've recently run into a scenario with lots of memory pressure and OOM and I am beginning to see systemd __switch_to+0x1f8/0x350 __schedule+0x30c/0x990 schedule+0x48/0xc0 percpu_down_write+0x114/0x170 __cgroup_procs_write.isra.12+0xb8/0x3c0 cgroup_file_write+0x74/0x1a0 kernfs_fop_write+0x188/0x200 __vfs_write+0x6c/0xe0 vfs_write+0xc0/0x230 SyS_write+0x6c/0x110 system_call+0x38/0xb4 This thread is waiting on the reader of cgroup_threadgroup_rwsem to exit. The reader itself is under memory pressure and has gone into reclaim after fork. There are times the reader also ends up waiting on oom_lock as well. __switch_to+0x1f8/0x350 __schedule+0x30c/0x990 schedule+0x48/0xc0 jbd2_log_wait_commit+0xd4/0x180 ext4_evict_inode+0x88/0x5c0 evict+0xf8/0x2a0 dispose_list+0x50/0x80 prune_icache_sb+0x6c/0x90 super_cache_scan+0x190/0x210 shrink_slab.part.15+0x22c/0x4c0 shrink_zone+0x288/0x3c0 do_try_to_free_pages+0x1dc/0x590 try_to_free_pages+0xdc/0x260 __alloc_pages_nodemask+0x72c/0xc90 alloc_pages_current+0xb4/0x1a0 page_table_alloc+0xc0/0x170 __pte_alloc+0x58/0x1f0 copy_page_range+0x4ec/0x950 copy_process.isra.5+0x15a0/0x1870 _do_fork+0xa8/0x4b0 ppc_clone+0x8/0xc In the meanwhile, all processes exiting/forking are blocked almost stalling the system. This patch moves the threadgroup_change_begin from before cgroup_fork() to just before cgroup_canfork(). There is no nee to worry about threadgroup changes till the task is actually added to the threadgroup. This avoids having to call reclaim with cgroup_threadgroup_rwsem held. tj: Subject and description edits. Signed-off-by: Balbir Singh Acked-by: Zefan Li Cc: Oleg Nesterov Cc: Andrew Morton Cc: stable@vger.kernel.org # v4.2+ Signed-off-by: Tejun Heo --- kernel/fork.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/fork.c b/kernel/fork.c index 52e725d4a866..aaf782327bf3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1404,7 +1404,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->real_start_time = ktime_get_boot_ns(); p->io_context = NULL; p->audit_context = NULL; - threadgroup_change_begin(current); cgroup_fork(p); #ifdef CONFIG_NUMA p->mempolicy = mpol_dup(p->mempolicy); @@ -1556,6 +1555,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, INIT_LIST_HEAD(&p->thread_group); p->task_works = NULL; + threadgroup_change_begin(current); /* * Ensure that the cgroup subsystem policies allow the new process to be * forked. It should be noted the the new process's css_set can be changed @@ -1656,6 +1656,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, bad_fork_cancel_cgroup: cgroup_cancel_fork(p); bad_fork_free_pid: + threadgroup_change_end(current); if (pid != &init_struct_pid) free_pid(pid); bad_fork_cleanup_thread: @@ -1688,7 +1689,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, mpol_put(p->mempolicy); bad_fork_cleanup_threadgroup_lock: #endif - threadgroup_change_end(current); delayacct_tsk_free(p); bad_fork_cleanup_count: atomic_dec(&p->cred->user->processes); From e77e6ff502ea3d193872b5b9033bfd9717b36447 Mon Sep 17 00:00:00 2001 From: Liping Zhang Date: Mon, 15 Aug 2016 21:50:35 +0800 Subject: [PATCH 088/531] netfilter: conntrack: do not dump other netns's conntrack entries via proc We should skip the conntracks that belong to a different namespace, otherwise other unrelated netns's conntrack entries will be dumped via /proc/net/nf_conntrack. Fixes: 56d52d4892d0 ("netfilter: conntrack: use a single hashtable for all namespaces") Signed-off-by: Liping Zhang Reviewed-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_standalone.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 958a1455ca7f..9f267c3ffb39 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -205,6 +205,7 @@ static int ct_seq_show(struct seq_file *s, void *v) struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(hash); const struct nf_conntrack_l3proto *l3proto; const struct nf_conntrack_l4proto *l4proto; + struct net *net = seq_file_net(s); int ret = 0; NF_CT_ASSERT(ct); @@ -215,6 +216,9 @@ static int ct_seq_show(struct seq_file *s, void *v) if (NF_CT_DIRECTION(hash)) goto release; + if (!net_eq(nf_ct_net(ct), net)) + goto release; + l3proto = __nf_ct_l3proto_find(nf_ct_l3num(ct)); NF_CT_ASSERT(l3proto); l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct)); From 2497b84625466dc57b8c3a40cd41a659fe04cca6 Mon Sep 17 00:00:00 2001 From: Liping Zhang Date: Sat, 13 Aug 2016 22:46:04 +0800 Subject: [PATCH 089/531] netfilter: nfnetlink_log: add "nf-logger-3-1" module alias name Otherwise, if nfnetlink_log.ko is not loaded, we cannot add rules to log packets to the userspace when we specify it with arp family, such as: # nft add rule arp filter input log group 0 :1:1-37: Error: Could not process rule: No such file or directory add rule arp filter input log group 0 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Signed-off-by: Liping Zhang Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink_log.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index cbcfdfb586a6..6577db524ef6 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -1147,6 +1147,7 @@ MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_ULOG); MODULE_ALIAS_NF_LOGGER(AF_INET, 1); MODULE_ALIAS_NF_LOGGER(AF_INET6, 1); MODULE_ALIAS_NF_LOGGER(AF_BRIDGE, 1); +MODULE_ALIAS_NF_LOGGER(3, 1); /* NFPROTO_ARP */ module_init(nfnetlink_log_init); module_exit(nfnetlink_log_fini); From 207efcd2b55e0460dfee35663fbb3d05efad990a Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Fri, 12 Aug 2016 13:42:40 +0800 Subject: [PATCH 090/531] md: remove obsolete ret in md_start_sync The ret is not needed anymore since we have already move resync_start into md_do_sync in commit 41a9a0d. Reviewed-by: NeilBrown Signed-off-by: Guoqing Jiang Signed-off-by: Shaohua Li --- drivers/md/md.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index d750b52376b9..19d8e23bda5c 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -8278,16 +8278,13 @@ static int remove_and_add_spares(struct mddev *mddev, static void md_start_sync(struct work_struct *ws) { struct mddev *mddev = container_of(ws, struct mddev, del_work); - int ret = 0; mddev->sync_thread = md_register_thread(md_do_sync, mddev, "resync"); if (!mddev->sync_thread) { - if (!(mddev_is_clustered(mddev) && ret == -EAGAIN)) - printk(KERN_ERR "%s: could not start resync" - " thread...\n", - mdname(mddev)); + printk(KERN_ERR "%s: could not start resync thread...\n", + mdname(mddev)); /* leave the spares where they are, it shouldn't hurt */ clear_bit(MD_RECOVERY_SYNC, &mddev->recovery); clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); From c622ca543bff8e73efacf4dafa0cc9851ecea511 Mon Sep 17 00:00:00 2001 From: Artur Paszkiewicz Date: Tue, 16 Aug 2016 14:26:08 +0200 Subject: [PATCH 091/531] md: don't print the same repeated messages about delayed sync operation This fixes a long-standing bug that caused a flood of messages like: "md: delaying data-check of md1 until md2 has finished (they share one or more physical units)" It can be reproduced like this: 1. Create at least 3 raid1 arrays on a pair of disks, each on different partitions. 2. Request a sync operation like 'check' or 'repair' on 2 arrays by writing to their md/sync_action attribute files. One operation should start and one should be delayed and a message like the above will be printed. 3. Issue a write to the third array. Each write will cause 2 copies of the message to be printed. This happens when wake_up(&resync_wait) is called, usually by md_check_recovery(). Then the delayed sync thread again prints the message and is put to sleep. This patch adds a check in md_do_sync() to prevent printing this message more than once for the same pair of devices. Reported-by: Sven Koehler Link: https://bugzilla.kernel.org/show_bug.cgi?id=151801 Signed-off-by: Artur Paszkiewicz Signed-off-by: Shaohua Li --- drivers/md/md.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 19d8e23bda5c..cc25cbcf10b2 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -7865,6 +7865,7 @@ void md_do_sync(struct md_thread *thread) */ do { + int mddev2_minor = -1; mddev->curr_resync = 2; try_again: @@ -7894,10 +7895,14 @@ void md_do_sync(struct md_thread *thread) prepare_to_wait(&resync_wait, &wq, TASK_INTERRUPTIBLE); if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) && mddev2->curr_resync >= mddev->curr_resync) { - printk(KERN_INFO "md: delaying %s of %s" - " until %s has finished (they" - " share one or more physical units)\n", - desc, mdname(mddev), mdname(mddev2)); + if (mddev2_minor != mddev2->md_minor) { + mddev2_minor = mddev2->md_minor; + printk(KERN_INFO "md: delaying %s of %s" + " until %s has finished (they" + " share one or more physical units)\n", + desc, mdname(mddev), + mdname(mddev2)); + } mddev_put(mddev2); if (signal_pending(current)) flush_signals(current); From 059e232089e45b0befc9933d31209c225e08b426 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 9 Aug 2016 07:50:44 +0100 Subject: [PATCH 092/531] irqchip/gic: Allow self-SGIs for SMP on UP configurations On systems where a single CPU is present, the GIC may not support having SGIs delivered to a target list. In that case, we use the self-SGI mechanism to allow the interrupt to be delivered locally. Tested-by: Fabio Estevam Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-gic.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index c2cab572c511..390fac59c6bc 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -769,6 +769,13 @@ static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq) int cpu; unsigned long flags, map = 0; + if (unlikely(nr_cpu_ids == 1)) { + /* Only one CPU? let's do a self-IPI... */ + writel_relaxed(2 << 24 | irq, + gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT); + return; + } + raw_spin_lock_irqsave(&irq_controller_lock, flags); /* Convert our logical CPU mask into a physical one. */ From ccd9432a5c85f35df7b491a1b701560d247466a5 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Wed, 17 Aug 2016 13:49:19 +0100 Subject: [PATCH 093/531] irqchip/gicv3: Remove disabling redistributor and group1 non-secure interrupts As per the GICv3 specification, to power down a processor using GICv3 and allow automatic power-on if an interrupt must be sent to a processor, software must set Enable to zero for all interrupt groups(by writing to GICC_CTLR or ICC_IGRPEN{0,1}_EL1/3 as appropriate. When commit 3708d52fc6bb ("irqchip: gic-v3: Implement CPU PM notifier") was introduced there were no firmware implementations(in particular PSCI) handling this. Linux kernel may not be aware of the CPU power state details and might fail to identify the power states that require quiescing the CPU interface. Even if it can be aware of those details, it can't determine which CPU power state have been triggered at the platform level and how the power control is implemented. This patch make disabling redistributor and group1 non-secure interrupts in the power down path and re-enabling of redistributor in the power-up path conditional. It will be handled in the kernel if and only if the non-secure accesses are permitted to access and modify control registers. It is left to the platform implementation otherwise. Cc: Marc Zyngier Cc: Lorenzo Pieralisi Cc: Thomas Gleixner Cc: Jason Cooper Tested-by: Christopher Covington Signed-off-by: Sudeep Holla Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-gic-v3.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 6fc56c3466b0..ede5672ab34d 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -667,13 +667,20 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, #endif #ifdef CONFIG_CPU_PM +/* Check whether it's single security state view */ +static bool gic_dist_security_disabled(void) +{ + return readl_relaxed(gic_data.dist_base + GICD_CTLR) & GICD_CTLR_DS; +} + static int gic_cpu_pm_notifier(struct notifier_block *self, unsigned long cmd, void *v) { if (cmd == CPU_PM_EXIT) { - gic_enable_redist(true); + if (gic_dist_security_disabled()) + gic_enable_redist(true); gic_cpu_sys_reg_init(); - } else if (cmd == CPU_PM_ENTER) { + } else if (cmd == CPU_PM_ENTER && gic_dist_security_disabled()) { gic_write_grpen1(0); gic_enable_redist(false); } From aca300183ed4f723837f6619facff0890c46d313 Mon Sep 17 00:00:00 2001 From: Liping Zhang Date: Sat, 13 Aug 2016 23:13:02 +0800 Subject: [PATCH 094/531] netfilter: nfnetlink_acct: report overquota to the right netns We should report the over quota message to the right net namespace instead of the init netns. Signed-off-by: Liping Zhang Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink_acct.h | 4 ++-- net/netfilter/nfnetlink_acct.c | 9 +++++---- net/netfilter/xt_nfacct.c | 2 +- 3 files changed, 8 insertions(+), 7 deletions(-) diff --git a/include/linux/netfilter/nfnetlink_acct.h b/include/linux/netfilter/nfnetlink_acct.h index 80ca889b164e..664da0048625 100644 --- a/include/linux/netfilter/nfnetlink_acct.h +++ b/include/linux/netfilter/nfnetlink_acct.h @@ -15,6 +15,6 @@ struct nf_acct; struct nf_acct *nfnl_acct_find_get(struct net *net, const char *filter_name); void nfnl_acct_put(struct nf_acct *acct); void nfnl_acct_update(const struct sk_buff *skb, struct nf_acct *nfacct); -extern int nfnl_acct_overquota(const struct sk_buff *skb, - struct nf_acct *nfacct); +int nfnl_acct_overquota(struct net *net, const struct sk_buff *skb, + struct nf_acct *nfacct); #endif /* _NFNL_ACCT_H */ diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index 1b4de4bd6958..796605b76d6b 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -443,7 +443,7 @@ void nfnl_acct_update(const struct sk_buff *skb, struct nf_acct *nfacct) } EXPORT_SYMBOL_GPL(nfnl_acct_update); -static void nfnl_overquota_report(struct nf_acct *nfacct) +static void nfnl_overquota_report(struct net *net, struct nf_acct *nfacct) { int ret; struct sk_buff *skb; @@ -458,11 +458,12 @@ static void nfnl_overquota_report(struct nf_acct *nfacct) kfree_skb(skb); return; } - netlink_broadcast(init_net.nfnl, skb, 0, NFNLGRP_ACCT_QUOTA, + netlink_broadcast(net->nfnl, skb, 0, NFNLGRP_ACCT_QUOTA, GFP_ATOMIC); } -int nfnl_acct_overquota(const struct sk_buff *skb, struct nf_acct *nfacct) +int nfnl_acct_overquota(struct net *net, const struct sk_buff *skb, + struct nf_acct *nfacct) { u64 now; u64 *quota; @@ -480,7 +481,7 @@ int nfnl_acct_overquota(const struct sk_buff *skb, struct nf_acct *nfacct) if (now >= *quota && !test_and_set_bit(NFACCT_OVERQUOTA_BIT, &nfacct->flags)) { - nfnl_overquota_report(nfacct); + nfnl_overquota_report(net, nfacct); } return ret; diff --git a/net/netfilter/xt_nfacct.c b/net/netfilter/xt_nfacct.c index 3048a7e3a90a..cf327593852a 100644 --- a/net/netfilter/xt_nfacct.c +++ b/net/netfilter/xt_nfacct.c @@ -26,7 +26,7 @@ static bool nfacct_mt(const struct sk_buff *skb, struct xt_action_param *par) nfnl_acct_update(skb, info->nfacct); - overquota = nfnl_acct_overquota(skb, info->nfacct); + overquota = nfnl_acct_overquota(par->net, skb, info->nfacct); return overquota == NFACCT_UNDERQUOTA ? false : true; } From dcbe35909c8426e1ace74b4b99c4cb403cdaca89 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 17 Aug 2016 09:56:46 -0700 Subject: [PATCH 095/531] netfilter: tproxy: properly refcount tcp listeners inet_lookup_listener() and inet6_lookup_listener() no longer take a reference on the found listener. This minimal patch adds back the refcounting, but we might do this differently in net-next later. Fixes: 3b24d854cb35 ("tcp/dccp: do not touch listener sk_refcnt under synflood") Reported-and-tested-by: Denys Fedoryshchenko Signed-off-by: Eric Dumazet Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_TPROXY.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index 7f4414d26a66..663c4c3c9072 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -127,6 +127,8 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp, daddr, dport, in->ifindex); + if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + sk = NULL; /* NOTE: we return listeners even if bound to * 0.0.0.0, those are filtered out in * xt_socket, since xt_TPROXY needs 0 bound @@ -195,6 +197,8 @@ nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp, daddr, ntohs(dport), in->ifindex); + if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + sk = NULL; /* NOTE: we return listeners even if bound to * 0.0.0.0, those are filtered out in * xt_socket, since xt_TPROXY needs 0 bound From b825b44c4ef4dabfdaf4e82db2263d377ac45d67 Mon Sep 17 00:00:00 2001 From: Jay Freyensee Date: Wed, 17 Aug 2016 15:00:25 -0700 Subject: [PATCH 096/531] nvmet-rdma: +1 to *queue_size from hsqsize/hrqsize The host will be sending sqsize 0-based hsqsize value, the target need to be adjusted as well. Signed-off-by: Jay Freyensee Reviewed-by: Sagi Grimberg Signed-off-by: Sagi Grimberg --- drivers/nvme/target/rdma.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 5de8d0a0db58..1cbe6e053b5b 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -1004,10 +1004,10 @@ nvmet_rdma_parse_cm_connect_req(struct rdma_conn_param *conn, queue->host_qid = le16_to_cpu(req->qid); /* - * req->hsqsize corresponds to our recv queue size + * req->hsqsize corresponds to our recv queue size plus 1 * req->hrqsize corresponds to our send queue size */ - queue->recv_queue_size = le16_to_cpu(req->hsqsize); + queue->recv_queue_size = le16_to_cpu(req->hsqsize) + 1; queue->send_queue_size = le16_to_cpu(req->hrqsize); if (!queue->host_qid && queue->recv_queue_size > NVMF_AQ_DEPTH) From f994d9dc28bc27353acde2caaf718222d92a3e24 Mon Sep 17 00:00:00 2001 From: Jay Freyensee Date: Wed, 17 Aug 2016 15:00:26 -0700 Subject: [PATCH 097/531] fabrics: define admin sqsize min default, per spec Upon admin queue connect(), the rdma qp was being set based on NVMF_AQ_DEPTH. However, the fabrics layer was using the sqsize field value set for I/O queues for the admin queue, which threw the nvme layer and rdma layer off-whack: root@fedora23-fabrics-host1 nvmf]# dmesg [ 3507.798642] nvme_fabrics: nvmf_connect_admin_queue():admin sqsize being sent is: 128 [ 3507.798858] nvme nvme0: creating 16 I/O queues. [ 3507.896407] nvme nvme0: new ctrl: NQN "nullside-nqn", addr 192.168.1.3:4420 Thus, to have a different admin queue value, we use NVMF_AQ_DEPTH for connect() and RDMA private data as the minimum depth specified in the NVMe-over-Fabrics 1.0 spec (and in that RDMA private data we treat hrqsize as 1's-based value, per current understanding of the fabrics spec). Reported-by: Daniel Verkamp Signed-off-by: Jay Freyensee Reviewed-by: Daniel Verkamp Signed-off-by: Sagi Grimberg --- drivers/nvme/host/fabrics.c | 9 ++++++++- drivers/nvme/host/rdma.c | 13 +++++++++++-- 2 files changed, 19 insertions(+), 3 deletions(-) diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index dc996761042f..020302c6ea57 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -363,7 +363,14 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl) cmd.connect.opcode = nvme_fabrics_command; cmd.connect.fctype = nvme_fabrics_type_connect; cmd.connect.qid = 0; - cmd.connect.sqsize = cpu_to_le16(ctrl->sqsize); + + /* + * fabrics spec sets a minimum of depth 32 for admin queue, + * so set the queue with this depth always until + * justification otherwise. + */ + cmd.connect.sqsize = cpu_to_le16(NVMF_AQ_DEPTH - 1); + /* * Set keep-alive timeout in seconds granularity (ms * 1000) * and add a grace period for controller kato enforcement diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 9c69393f6d1f..d44809e6b03f 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1278,8 +1278,17 @@ static int nvme_rdma_route_resolved(struct nvme_rdma_queue *queue) priv.recfmt = cpu_to_le16(NVME_RDMA_CM_FMT_1_0); priv.qid = cpu_to_le16(nvme_rdma_queue_idx(queue)); - priv.hrqsize = cpu_to_le16(queue->queue_size); - priv.hsqsize = cpu_to_le16(queue->queue_size); + /* + * set the admin queue depth to the minimum size + * specified by the Fabrics standard. + */ + if (priv.qid == 0) { + priv.hrqsize = cpu_to_le16(NVMF_AQ_DEPTH); + priv.hsqsize = cpu_to_le16(NVMF_AQ_DEPTH - 1); + } else { + priv.hrqsize = cpu_to_le16(queue->queue_size); + priv.hsqsize = cpu_to_le16(queue->queue_size); + } ret = rdma_connect(queue->cm_id, ¶m); if (ret) { From c5af8654c422cfdd8480be3a244748e18cace6c5 Mon Sep 17 00:00:00 2001 From: Jay Freyensee Date: Wed, 17 Aug 2016 15:00:27 -0700 Subject: [PATCH 098/531] nvme-rdma: fix sqsize/hsqsize per spec Per NVMe-over-Fabrics 1.0 spec, sqsize is represented as a 0-based value. Also per spec, the RDMA binding values shall be set to sqsize, which makes hsqsize 0-based values. Thus, the sqsize during NVMf connect() is now: [root@fedora23-fabrics-host1 for-48]# dmesg [ 318.720645] nvme_fabrics: nvmf_connect_admin_queue(): sqsize for admin queue: 31 [ 318.720884] nvme nvme0: creating 16 I/O queues. [ 318.810114] nvme_fabrics: nvmf_connect_io_queue(): sqsize for i/o queue: 127 Finally, current interpretation implies hrqsize is 1's based so set it appropriately. Reported-by: Daniel Verkamp Signed-off-by: Jay Freyensee Signed-off-by: Sagi Grimberg --- drivers/nvme/host/rdma.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index d44809e6b03f..c133256fd745 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -645,7 +645,8 @@ static int nvme_rdma_init_io_queues(struct nvme_rdma_ctrl *ctrl) int i, ret; for (i = 1; i < ctrl->queue_count; i++) { - ret = nvme_rdma_init_queue(ctrl, i, ctrl->ctrl.sqsize); + ret = nvme_rdma_init_queue(ctrl, i, + ctrl->ctrl.opts->queue_size); if (ret) { dev_info(ctrl->ctrl.device, "failed to initialize i/o queue: %d\n", ret); @@ -1286,8 +1287,13 @@ static int nvme_rdma_route_resolved(struct nvme_rdma_queue *queue) priv.hrqsize = cpu_to_le16(NVMF_AQ_DEPTH); priv.hsqsize = cpu_to_le16(NVMF_AQ_DEPTH - 1); } else { + /* + * current interpretation of the fabrics spec + * is at minimum you make hrqsize sqsize+1, or a + * 1's based representation of sqsize. + */ priv.hrqsize = cpu_to_le16(queue->queue_size); - priv.hsqsize = cpu_to_le16(queue->queue_size); + priv.hsqsize = cpu_to_le16(queue->ctrl->ctrl.sqsize); } ret = rdma_connect(queue->cm_id, ¶m); @@ -1825,7 +1831,7 @@ static int nvme_rdma_create_io_queues(struct nvme_rdma_ctrl *ctrl) memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set)); ctrl->tag_set.ops = &nvme_rdma_mq_ops; - ctrl->tag_set.queue_depth = ctrl->ctrl.sqsize; + ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size; ctrl->tag_set.reserved_tags = 1; /* fabric connect */ ctrl->tag_set.numa_node = NUMA_NO_NODE; ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; @@ -1923,7 +1929,7 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, spin_lock_init(&ctrl->lock); ctrl->queue_count = opts->nr_io_queues + 1; /* +1 for admin queue */ - ctrl->ctrl.sqsize = opts->queue_size; + ctrl->ctrl.sqsize = opts->queue_size - 1; ctrl->ctrl.kato = opts->kato; ret = -ENOMEM; From eadb7cf44105ae8250f0d638dc880c3ed511c4e2 Mon Sep 17 00:00:00 2001 From: Jay Freyensee Date: Wed, 17 Aug 2016 15:00:28 -0700 Subject: [PATCH 099/531] nvme-loop: set sqsize to 0-based value, per spec Signed-off-by: Jay Freyensee Signed-off-by: Sagi Grimberg --- drivers/nvme/target/loop.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index 7affd40a6b33..395e60dad835 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -556,7 +556,7 @@ static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl) memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set)); ctrl->tag_set.ops = &nvme_loop_mq_ops; - ctrl->tag_set.queue_depth = ctrl->ctrl.sqsize; + ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size; ctrl->tag_set.reserved_tags = 1; /* fabric connect */ ctrl->tag_set.numa_node = NUMA_NO_NODE; ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; @@ -620,7 +620,7 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev, ret = -ENOMEM; - ctrl->ctrl.sqsize = opts->queue_size; + ctrl->ctrl.sqsize = opts->queue_size - 1; ctrl->ctrl.kato = opts->kato; ctrl->queues = kcalloc(opts->nr_io_queues + 1, sizeof(*ctrl->queues), From d048c098218e91ed0e10dfa1f0f80e2567fe4ef7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= Date: Mon, 8 Aug 2016 20:16:22 +0200 Subject: [PATCH 100/531] KVM: nVMX: fix msr bitmaps to prevent L2 from accessing L0 x2APIC MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit msr bitmap can be used to avoid a VM exit (interception) on guest MSR accesses. In some configurations of VMX controls, the guest can even directly access host's x2APIC MSRs. See SDM 29.5 VIRTUALIZING MSR-BASED APIC ACCESSES. L2 could read all L0's x2APIC MSRs and write TPR, EOI, and SELF_IPI. To do so, L1 would first trick KVM to disable all possible interceptions by enabling APICv features and then would turn those features off; nested_vmx_merge_msr_bitmap() only disabled interceptions, so VMX would not intercept previously enabled MSRs even though they were not safe with the new configuration. Correctly re-enabling interceptions is not enough as a second bug would still allow L1+L2 to access host's MSRs: msr bitmap was shared for all VMCSs, so L1 could trigger a race to get the desired combination of msr bitmap and VMX controls. This fix allocates a msr bitmap for every L1 VCPU, allows only safe x2APIC MSRs from L1's msr bitmap, and disables msr bitmaps if they would have to intercept everything anyway. Fixes: 3af18d9c5fe9 ("KVM: nVMX: Prepare for using hardware MSR bitmap") Reported-by: Jim Mattson Suggested-by: Wincy Van Reviewed-by: Wanpeng Li Signed-off-by: Radim Krčmář --- arch/x86/kvm/vmx.c | 107 +++++++++++++++++++-------------------------- 1 file changed, 44 insertions(+), 63 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index a45d8580f91e..c66ac2c70d22 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -435,6 +435,8 @@ struct nested_vmx { bool pi_pending; u16 posted_intr_nv; + unsigned long *msr_bitmap; + struct hrtimer preemption_timer; bool preemption_timer_expired; @@ -924,7 +926,6 @@ static unsigned long *vmx_msr_bitmap_legacy; static unsigned long *vmx_msr_bitmap_longmode; static unsigned long *vmx_msr_bitmap_legacy_x2apic; static unsigned long *vmx_msr_bitmap_longmode_x2apic; -static unsigned long *vmx_msr_bitmap_nested; static unsigned long *vmx_vmread_bitmap; static unsigned long *vmx_vmwrite_bitmap; @@ -2508,7 +2509,7 @@ static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu) unsigned long *msr_bitmap; if (is_guest_mode(vcpu)) - msr_bitmap = vmx_msr_bitmap_nested; + msr_bitmap = to_vmx(vcpu)->nested.msr_bitmap; else if (cpu_has_secondary_exec_ctrls() && (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) & SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) { @@ -6363,13 +6364,6 @@ static __init int hardware_setup(void) if (!vmx_msr_bitmap_longmode_x2apic) goto out4; - if (nested) { - vmx_msr_bitmap_nested = - (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_nested) - goto out5; - } - vmx_vmread_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL); if (!vmx_vmread_bitmap) goto out6; @@ -6392,8 +6386,6 @@ static __init int hardware_setup(void) memset(vmx_msr_bitmap_legacy, 0xff, PAGE_SIZE); memset(vmx_msr_bitmap_longmode, 0xff, PAGE_SIZE); - if (nested) - memset(vmx_msr_bitmap_nested, 0xff, PAGE_SIZE); if (setup_vmcs_config(&vmcs_config) < 0) { r = -EIO; @@ -6529,9 +6521,6 @@ static __init int hardware_setup(void) out7: free_page((unsigned long)vmx_vmread_bitmap); out6: - if (nested) - free_page((unsigned long)vmx_msr_bitmap_nested); -out5: free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic); out4: free_page((unsigned long)vmx_msr_bitmap_longmode); @@ -6557,8 +6546,6 @@ static __exit void hardware_unsetup(void) free_page((unsigned long)vmx_io_bitmap_a); free_page((unsigned long)vmx_vmwrite_bitmap); free_page((unsigned long)vmx_vmread_bitmap); - if (nested) - free_page((unsigned long)vmx_msr_bitmap_nested); free_kvm_area(); } @@ -6995,16 +6982,21 @@ static int handle_vmon(struct kvm_vcpu *vcpu) return 1; } + if (cpu_has_vmx_msr_bitmap()) { + vmx->nested.msr_bitmap = + (unsigned long *)__get_free_page(GFP_KERNEL); + if (!vmx->nested.msr_bitmap) + goto out_msr_bitmap; + } + vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL); if (!vmx->nested.cached_vmcs12) - return -ENOMEM; + goto out_cached_vmcs12; if (enable_shadow_vmcs) { shadow_vmcs = alloc_vmcs(); - if (!shadow_vmcs) { - kfree(vmx->nested.cached_vmcs12); - return -ENOMEM; - } + if (!shadow_vmcs) + goto out_shadow_vmcs; /* mark vmcs as shadow */ shadow_vmcs->revision_id |= (1u << 31); /* init shadow vmcs */ @@ -7024,6 +7016,15 @@ static int handle_vmon(struct kvm_vcpu *vcpu) skip_emulated_instruction(vcpu); nested_vmx_succeed(vcpu); return 1; + +out_shadow_vmcs: + kfree(vmx->nested.cached_vmcs12); + +out_cached_vmcs12: + free_page((unsigned long)vmx->nested.msr_bitmap); + +out_msr_bitmap: + return -ENOMEM; } /* @@ -7098,6 +7099,10 @@ static void free_nested(struct vcpu_vmx *vmx) vmx->nested.vmxon = false; free_vpid(vmx->nested.vpid02); nested_release_vmcs12(vmx); + if (vmx->nested.msr_bitmap) { + free_page((unsigned long)vmx->nested.msr_bitmap); + vmx->nested.msr_bitmap = NULL; + } if (enable_shadow_vmcs) free_vmcs(vmx->nested.current_shadow_vmcs); kfree(vmx->nested.cached_vmcs12); @@ -9472,8 +9477,10 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, { int msr; struct page *page; - unsigned long *msr_bitmap; + unsigned long *msr_bitmap_l1; + unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.msr_bitmap; + /* This shortcut is ok because we support only x2APIC MSRs so far. */ if (!nested_cpu_has_virt_x2apic_mode(vmcs12)) return false; @@ -9482,63 +9489,37 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, WARN_ON(1); return false; } - msr_bitmap = (unsigned long *)kmap(page); - if (!msr_bitmap) { + msr_bitmap_l1 = (unsigned long *)kmap(page); + if (!msr_bitmap_l1) { nested_release_page_clean(page); WARN_ON(1); return false; } + memset(msr_bitmap_l0, 0xff, PAGE_SIZE); + if (nested_cpu_has_virt_x2apic_mode(vmcs12)) { if (nested_cpu_has_apic_reg_virt(vmcs12)) for (msr = 0x800; msr <= 0x8ff; msr++) nested_vmx_disable_intercept_for_msr( - msr_bitmap, - vmx_msr_bitmap_nested, + msr_bitmap_l1, msr_bitmap_l0, msr, MSR_TYPE_R); - /* TPR is allowed */ - nested_vmx_disable_intercept_for_msr(msr_bitmap, - vmx_msr_bitmap_nested, + + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, APIC_BASE_MSR + (APIC_TASKPRI >> 4), MSR_TYPE_R | MSR_TYPE_W); + if (nested_cpu_has_vid(vmcs12)) { - /* EOI and self-IPI are allowed */ nested_vmx_disable_intercept_for_msr( - msr_bitmap, - vmx_msr_bitmap_nested, + msr_bitmap_l1, msr_bitmap_l0, APIC_BASE_MSR + (APIC_EOI >> 4), MSR_TYPE_W); nested_vmx_disable_intercept_for_msr( - msr_bitmap, - vmx_msr_bitmap_nested, + msr_bitmap_l1, msr_bitmap_l0, APIC_BASE_MSR + (APIC_SELF_IPI >> 4), MSR_TYPE_W); } - } else { - /* - * Enable reading intercept of all the x2apic - * MSRs. We should not rely on vmcs12 to do any - * optimizations here, it may have been modified - * by L1. - */ - for (msr = 0x800; msr <= 0x8ff; msr++) - __vmx_enable_intercept_for_msr( - vmx_msr_bitmap_nested, - msr, - MSR_TYPE_R); - - __vmx_enable_intercept_for_msr( - vmx_msr_bitmap_nested, - APIC_BASE_MSR + (APIC_TASKPRI >> 4), - MSR_TYPE_W); - __vmx_enable_intercept_for_msr( - vmx_msr_bitmap_nested, - APIC_BASE_MSR + (APIC_EOI >> 4), - MSR_TYPE_W); - __vmx_enable_intercept_for_msr( - vmx_msr_bitmap_nested, - APIC_BASE_MSR + (APIC_SELF_IPI >> 4), - MSR_TYPE_W); } kunmap(page); nested_release_page_clean(page); @@ -9957,10 +9938,10 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) } if (cpu_has_vmx_msr_bitmap() && - exec_control & CPU_BASED_USE_MSR_BITMAPS) { - nested_vmx_merge_msr_bitmap(vcpu, vmcs12); - /* MSR_BITMAP will be set by following vmx_set_efer. */ - } else + exec_control & CPU_BASED_USE_MSR_BITMAPS && + nested_vmx_merge_msr_bitmap(vcpu, vmcs12)) + ; /* MSR_BITMAP will be set by following vmx_set_efer. */ + else exec_control &= ~CPU_BASED_USE_MSR_BITMAPS; /* From dccbfcf52cebb8963246eba5b177b77f26b34da0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= Date: Mon, 8 Aug 2016 20:16:23 +0200 Subject: [PATCH 101/531] KVM: nVMX: postpone VMCS changes on MSR_IA32_APICBASE write MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If vmcs12 does not intercept APIC_BASE writes, then KVM will handle the write with vmcs02 as the current VMCS. This will incorrectly apply modifications intended for vmcs01 to vmcs02 and L2 can use it to gain access to L0's x2APIC registers by disabling virtualized x2APIC while using msr bitmap that assumes enabled. Postpone execution of vmx_set_virtual_x2apic_mode until vmcs01 is the current VMCS. An alternative solution would temporarily make vmcs01 the current VMCS, but it requires more care. Fixes: 8d14695f9542 ("x86, apicv: add virtual x2apic support") Reported-by: Jim Mattson Reviewed-by: Wanpeng Li Signed-off-by: Radim Krčmář --- arch/x86/kvm/vmx.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index c66ac2c70d22..ae111a07acc4 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -422,6 +422,7 @@ struct nested_vmx { struct list_head vmcs02_pool; int vmcs02_num; u64 vmcs01_tsc_offset; + bool change_vmcs01_virtual_x2apic_mode; /* L2 must run next, and mustn't decide to exit to L1. */ bool nested_run_pending; /* @@ -8424,6 +8425,12 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) { u32 sec_exec_control; + /* Postpone execution until vmcs01 is the current VMCS. */ + if (is_guest_mode(vcpu)) { + to_vmx(vcpu)->nested.change_vmcs01_virtual_x2apic_mode = true; + return; + } + /* * There is not point to enable virtualize x2apic without enable * apicv @@ -10749,6 +10756,12 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL, PIN_BASED_VMX_PREEMPTION_TIMER); + if (vmx->nested.change_vmcs01_virtual_x2apic_mode) { + vmx->nested.change_vmcs01_virtual_x2apic_mode = false; + vmx_set_virtual_x2apic_mode(vcpu, + vcpu->arch.apic_base & X2APIC_ENABLE); + } + /* This is needed for same reason as it was needed in prepare_vmcs02 */ vmx->host_rsp = 0; From c95ba92afb238ac565c68968fc72e38ca8d1b6e8 Mon Sep 17 00:00:00 2001 From: Peter Feiner Date: Wed, 17 Aug 2016 09:36:47 -0700 Subject: [PATCH 102/531] kvm: nVMX: fix nested tsc scaling When the host supported TSC scaling, L2 would use a TSC multiplier of 0, which causes a VM entry failure. Now L2's TSC uses the same multiplier as L1. Signed-off-by: Peter Feiner Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index ae111a07acc4..5cede40e2552 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2200,6 +2200,12 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) new.control) != old.control); } +static void decache_tsc_multiplier(struct vcpu_vmx *vmx) +{ + vmx->current_tsc_ratio = vmx->vcpu.arch.tsc_scaling_ratio; + vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio); +} + /* * Switches to specified vcpu, until a matching vcpu_put(), but assumes * vcpu mutex is already taken. @@ -2258,10 +2264,8 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) /* Setup TSC multiplier */ if (kvm_has_tsc_control && - vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) { - vmx->current_tsc_ratio = vcpu->arch.tsc_scaling_ratio; - vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio); - } + vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) + decache_tsc_multiplier(vmx); vmx_vcpu_pi_load(vcpu, cpu); vmx->host_pkru = read_pkru(); @@ -9999,6 +10003,8 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmx->nested.vmcs01_tsc_offset + vmcs12->tsc_offset); else vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset); + if (kvm_has_tsc_control) + decache_tsc_multiplier(vmx); if (enable_vpid) { /* @@ -10755,6 +10761,8 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, else vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL, PIN_BASED_VMX_PREEMPTION_TIMER); + if (kvm_has_tsc_control) + decache_tsc_multiplier(vmx); if (vmx->nested.change_vmcs01_virtual_x2apic_mode) { vmx->nested.change_vmcs01_virtual_x2apic_mode = false; From 5d0bdf2867825a92c0a563957a2fb059149ab0d4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 11 Aug 2016 07:11:05 -0700 Subject: [PATCH 103/531] PCI: Call pci_intx() when using legacy interrupts in pci_alloc_irq_vectors() ahci currently insists on an explicit call to pci_intx() before falling back from MSI or MSI-X to legacy IRQs. As pci_intx() is a no-op if the command register already contains the right value it seems safe and useful to add this call to pci_alloc_irq_vectors() so that ahci can just use pci_alloc_irq_vectors(). Signed-off-by: Christoph Hellwig Signed-off-by: Bjorn Helgaas --- drivers/pci/msi.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 9233e7f62f47..593698e11f96 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -1200,8 +1200,11 @@ int pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, } /* use legacy irq if allowed */ - if ((flags & PCI_IRQ_LEGACY) && min_vecs == 1) + if ((flags & PCI_IRQ_LEGACY) && min_vecs == 1) { + pci_intx(dev, 1); return 1; + } + return vecs; } EXPORT_SYMBOL(pci_alloc_irq_vectors); From 12be15dd5ac928b60323b1ed8f6facd7335bb2cc Mon Sep 17 00:00:00 2001 From: Liping Zhang Date: Sat, 13 Aug 2016 23:13:01 +0800 Subject: [PATCH 104/531] netfilter: nfnetlink_acct: fix race between nfacct del and xt_nfacct destroy Suppose that we input the following commands at first: # nfacct add test # iptables -A INPUT -m nfacct --nfacct-name test And now "test" acct's refcnt is 2, but later when we try to delete the "test" nfacct and the related iptables rule at the same time, race maybe happen: CPU0 CPU1 nfnl_acct_try_del nfnl_acct_put atomic_dec_and_test //ref=1,testfail - - atomic_dec_and_test //ref=0,testok - kfree_rcu atomic_inc //ref=1 - So after the rcu grace period, nf_acct will be freed but it is still linked in the nfnl_acct_list, and we can access it later, then oops will happen. Convert atomic_dec_and_test and atomic_inc combinaiton to one atomic operation atomic_cmpxchg here to fix this problem. Signed-off-by: Liping Zhang Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink_acct.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index 796605b76d6b..70eb2f6a3b01 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -326,14 +326,14 @@ static int nfnl_acct_try_del(struct nf_acct *cur) { int ret = 0; - /* we want to avoid races with nfnl_acct_find_get. */ - if (atomic_dec_and_test(&cur->refcnt)) { + /* We want to avoid races with nfnl_acct_put. So only when the current + * refcnt is 1, we decrease it to 0. + */ + if (atomic_cmpxchg(&cur->refcnt, 1, 0) == 1) { /* We are protected by nfnl mutex. */ list_del_rcu(&cur->head); kfree_rcu(cur, rcu_head); } else { - /* still in use, restore reference counter. */ - atomic_inc(&cur->refcnt); ret = -EBUSY; } return ret; From b75911b66ad508a3c3f006ce37d9f9ebee34da43 Mon Sep 17 00:00:00 2001 From: Liping Zhang Date: Thu, 18 Aug 2016 20:39:05 +0800 Subject: [PATCH 105/531] netfilter: cttimeout: fix use after free error when delete netns In general, when we want to delete a netns, cttimeout_net_exit will be called before ipt_unregister_table, i.e. before ctnl_timeout_put. But after call kfree_rcu in cttimeout_net_exit, we will still decrease the timeout object's refcnt in ctnl_timeout_put, this is incorrect, and will cause a use after free error. It is easy to reproduce this problem: # while : ; do ip netns add xxx ip netns exec xxx nfct add timeout testx inet icmp timeout 200 ip netns exec xxx iptables -t raw -p icmp -I OUTPUT -j CT --timeout testx ip netns del xxx done ======================================================================= BUG kmalloc-96 (Tainted: G B E ): Poison overwritten ----------------------------------------------------------------------- INFO: 0xffff88002b5161e8-0xffff88002b5161e8. First byte 0x6a instead of 0x6b INFO: Allocated in cttimeout_new_timeout+0xd4/0x240 [nfnetlink_cttimeout] age=104 cpu=0 pid=3330 ___slab_alloc+0x4da/0x540 __slab_alloc+0x20/0x40 __kmalloc+0x1c8/0x240 cttimeout_new_timeout+0xd4/0x240 [nfnetlink_cttimeout] nfnetlink_rcv_msg+0x21a/0x230 [nfnetlink] [ ... ] So only when the refcnt decreased to 0, we call kfree_rcu to free the timeout object. And like nfnetlink_acct do, use atomic_cmpxchg to avoid race between ctnl_timeout_try_del and ctnl_timeout_put. Signed-off-by: Liping Zhang Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink_cttimeout.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 4cdcd969b64c..68216cdc7083 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -330,16 +330,16 @@ static int ctnl_timeout_try_del(struct net *net, struct ctnl_timeout *timeout) { int ret = 0; - /* we want to avoid races with nf_ct_timeout_find_get. */ - if (atomic_dec_and_test(&timeout->refcnt)) { + /* We want to avoid races with ctnl_timeout_put. So only when the + * current refcnt is 1, we decrease it to 0. + */ + if (atomic_cmpxchg(&timeout->refcnt, 1, 0) == 1) { /* We are protected by nfnl mutex. */ list_del_rcu(&timeout->head); nf_ct_l4proto_put(timeout->l4proto); ctnl_untimeout(net, timeout); kfree_rcu(timeout, rcu_head); } else { - /* still in use, restore reference counter. */ - atomic_inc(&timeout->refcnt); ret = -EBUSY; } return ret; @@ -543,7 +543,9 @@ ctnl_timeout_find_get(struct net *net, const char *name) static void ctnl_timeout_put(struct ctnl_timeout *timeout) { - atomic_dec(&timeout->refcnt); + if (atomic_dec_and_test(&timeout->refcnt)) + kfree_rcu(timeout, rcu_head); + module_put(THIS_MODULE); } #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ @@ -591,7 +593,9 @@ static void __net_exit cttimeout_net_exit(struct net *net) list_for_each_entry_safe(cur, tmp, &net->nfct_timeout_list, head) { list_del_rcu(&cur->head); nf_ct_l4proto_put(cur->l4proto); - kfree_rcu(cur, rcu_head); + + if (atomic_dec_and_test(&cur->refcnt)) + kfree_rcu(cur, rcu_head); } } From 479e2a86dc6aeaec6013165e1bd3525db6914f3a Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Thu, 18 Aug 2016 14:00:59 +0300 Subject: [PATCH 106/531] ASoC: omap-mcpdm: Drop pdmclk clock handling This reverts commit 65aca64d05b5eaa5ce15e18b458a8d338ddbd478. The patches for twl6040 MFD and clk missed the merge window and causing the McPDM driver to never probe since it is put back to the deferred list because the missing drivers. Signed-off-by: Peter Ujfalusi Signed-off-by: Mark Brown --- .../devicetree/bindings/sound/omap-mcpdm.txt | 10 ---------- sound/soc/omap/omap-mcpdm.c | 17 ----------------- 2 files changed, 27 deletions(-) diff --git a/Documentation/devicetree/bindings/sound/omap-mcpdm.txt b/Documentation/devicetree/bindings/sound/omap-mcpdm.txt index 6f6c2f8e908d..0741dff048dd 100644 --- a/Documentation/devicetree/bindings/sound/omap-mcpdm.txt +++ b/Documentation/devicetree/bindings/sound/omap-mcpdm.txt @@ -8,8 +8,6 @@ Required properties: - interrupts: Interrupt number for McPDM - interrupt-parent: The parent interrupt controller - ti,hwmods: Name of the hwmod associated to the McPDM -- clocks: phandle for the pdmclk provider, likely <&twl6040> -- clock-names: Must be "pdmclk" Example: @@ -21,11 +19,3 @@ mcpdm: mcpdm@40132000 { interrupt-parent = <&gic>; ti,hwmods = "mcpdm"; }; - -In board DTS file the pdmclk needs to be added: - -&mcpdm { - clocks = <&twl6040>; - clock-names = "pdmclk"; - status = "okay"; -}; diff --git a/sound/soc/omap/omap-mcpdm.c b/sound/soc/omap/omap-mcpdm.c index e7cdc51fd806..74d6e6fdcfd0 100644 --- a/sound/soc/omap/omap-mcpdm.c +++ b/sound/soc/omap/omap-mcpdm.c @@ -31,7 +31,6 @@ #include #include #include -#include #include #include #include @@ -55,7 +54,6 @@ struct omap_mcpdm { unsigned long phys_base; void __iomem *io_base; int irq; - struct clk *pdmclk; struct mutex mutex; @@ -390,7 +388,6 @@ static int omap_mcpdm_probe(struct snd_soc_dai *dai) struct omap_mcpdm *mcpdm = snd_soc_dai_get_drvdata(dai); int ret; - clk_prepare_enable(mcpdm->pdmclk); pm_runtime_enable(mcpdm->dev); /* Disable lines while request is ongoing */ @@ -425,7 +422,6 @@ static int omap_mcpdm_remove(struct snd_soc_dai *dai) pm_runtime_disable(mcpdm->dev); - clk_disable_unprepare(mcpdm->pdmclk); return 0; } @@ -445,8 +441,6 @@ static int omap_mcpdm_suspend(struct snd_soc_dai *dai) mcpdm->pm_active_count++; } - clk_disable_unprepare(mcpdm->pdmclk); - return 0; } @@ -454,8 +448,6 @@ static int omap_mcpdm_resume(struct snd_soc_dai *dai) { struct omap_mcpdm *mcpdm = snd_soc_dai_get_drvdata(dai); - clk_prepare_enable(mcpdm->pdmclk); - if (mcpdm->pm_active_count) { while (mcpdm->pm_active_count--) pm_runtime_get_sync(mcpdm->dev); @@ -549,15 +541,6 @@ static int asoc_mcpdm_probe(struct platform_device *pdev) mcpdm->dev = &pdev->dev; - mcpdm->pdmclk = devm_clk_get(&pdev->dev, "pdmclk"); - if (IS_ERR(mcpdm->pdmclk)) { - if (PTR_ERR(mcpdm->pdmclk) == -EPROBE_DEFER) - return -EPROBE_DEFER; - dev_warn(&pdev->dev, "Error getting pdmclk (%ld)!\n", - PTR_ERR(mcpdm->pdmclk)); - mcpdm->pdmclk = NULL; - } - ret = devm_snd_soc_register_component(&pdev->dev, &omap_mcpdm_component, &omap_mcpdm_dai, 1); From ae5b80d2b68eac945b124227dea34462118a6f01 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Thu, 18 Aug 2016 11:51:14 +0200 Subject: [PATCH 107/531] drm/radeon: only apply the SS fractional workaround to RS[78]80 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Looks like some RV6xx have problems with that. bug: https://bugs.freedesktop.org/show_bug.cgi?id=97099 Reviewed-by: Alex Deucher Signed-off-by: Christian König Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/radeon/atombios_crtc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c index a97abc8af657..1dcf39084555 100644 --- a/drivers/gpu/drm/radeon/atombios_crtc.c +++ b/drivers/gpu/drm/radeon/atombios_crtc.c @@ -627,7 +627,9 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc, if (radeon_crtc->ss.refdiv) { radeon_crtc->pll_flags |= RADEON_PLL_USE_REF_DIV; radeon_crtc->pll_reference_div = radeon_crtc->ss.refdiv; - if (rdev->family >= CHIP_RV770) + if (ASIC_IS_AVIVO(rdev) && + rdev->family != CHIP_RS780 && + rdev->family != CHIP_RS880) radeon_crtc->pll_flags |= RADEON_PLL_USE_FRAC_FB_DIV; } } From 51c70261b2575962cb9406cd92246b1cee6a3c71 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 18 Aug 2016 17:21:37 +0200 Subject: [PATCH 108/531] Revert "android: binder: fix dangling pointer comparison" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts commit 7b142d8fd0bd4c9bf06ccb72ac4daedb503f0124. It doesn't seem to be correct, no one seems to have tested it, and the email address of the submitter now bounces :( So revert it. Cc: Jann Horn Cc: Chen Feng Cc: stable Cc: Arve Hjønnevåg Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 09fdb425e2f5..16288e777ec3 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2962,7 +2962,6 @@ static int binder_open(struct inode *nodp, struct file *filp) return -ENOMEM; get_task_struct(current); proc->tsk = current; - atomic_inc(¤t->mm->mm_count); proc->vma_vm_mm = current->mm; INIT_LIST_HEAD(&proc->todo); init_waitqueue_head(&proc->wait); @@ -3168,7 +3167,6 @@ static void binder_deferred_release(struct binder_proc *proc) vfree(proc->buffer); } - mmdrop(proc->vma_vm_mm); put_task_struct(proc->tsk); binder_debug(BINDER_DEBUG_OPEN_CLOSE, From 87a713c8ffca33d8e497a8b6c02034332bd80394 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 10 Aug 2016 23:54:13 +0200 Subject: [PATCH 109/531] 8250/fintek: rename IRQ_MODE macro A bugfix for the fintek driver required defining some macros, but one of them clashes with a system header on ARM: drivers/tty/serial/8250/8250_fintek.c:34:0: error: "IRQ_MODE" redefined [-Werror] #define IRQ_MODE 0x70 In file included from /git/arm-soc/arch/arm/include/asm/ptrace.h:13:0, from /git/arm-soc/arch/arm/include/asm/irqflags.h:6, from /git/arm-soc/include/linux/irqflags.h:15, from /git/arm-soc/arch/arm/include/asm/bitops.h:27, from /git/arm-soc/include/linux/bitops.h:36, from /git/arm-soc/include/linux/kernel.h:10, from /git/arm-soc/include/linux/list.h:8, from /git/arm-soc/include/linux/module.h:9, from /git/arm-soc/drivers/tty/serial/8250/8250_fintek.c:11: arch/arm/include/uapi/asm/ptrace.h:55:0: note: this is the location of the previous definition This renames the newly introduced 'IRQ_MODE' macro to FINTEK_IRQ_MODE. Signed-off-by: Arnd Bergmann Fixes: 4da22f1418cb ("serial: 8250_fintek: fix the mismatched IRQ mode") Link: https://patchwork.kernel.org/patch/9200119/ Acked-by: Ji-Ze Hong (Peter Hong) Acked-by: Ricardo Ribalda Delgado Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_fintek.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/8250/8250_fintek.c b/drivers/tty/serial/8250/8250_fintek.c index 737b4b3957b0..0facc789fe7d 100644 --- a/drivers/tty/serial/8250/8250_fintek.c +++ b/drivers/tty/serial/8250/8250_fintek.c @@ -31,7 +31,7 @@ #define IO_ADDR2 0x60 #define LDN 0x7 -#define IRQ_MODE 0x70 +#define FINTEK_IRQ_MODE 0x70 #define IRQ_SHARE BIT(4) #define IRQ_MODE_MASK (BIT(6) | BIT(5)) #define IRQ_LEVEL_LOW 0 @@ -195,7 +195,7 @@ static int fintek_8250_set_irq_mode(struct fintek_8250 *pdata, bool level_mode) outb(LDN, pdata->base_port + ADDR_PORT); outb(pdata->index, pdata->base_port + DATA_PORT); - outb(IRQ_MODE, pdata->base_port + ADDR_PORT); + outb(FINTEK_IRQ_MODE, pdata->base_port + ADDR_PORT); tmp = inb(pdata->base_port + DATA_PORT); tmp &= ~IRQ_MODE_MASK; From 0215d59b154ab90c56c4fe49bc1deefe8bca18f1 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Thu, 18 Aug 2016 09:28:23 -0700 Subject: [PATCH 110/531] tools lib: Reinstate strlcpy() header guard with __UCLIBC__ MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit perf tools build in recent kernels spews splat when cross compiling with uClibc: | CC util/alias.o | In file included from tools/perf/util/../ui/../util/cache.h:8:0, | from tools/perf/util/../ui/helpline.h:7, | from tools/perf/util/debug.h:8, | from arch/../util/cpumap.h:9, | from arch/../util/env.h:5, | from arch/common.h:4, | from arch/common.c:3: | tools/include/linux/string.h:12:15: warning: redundant redeclaration of ‘strlcpy’ [-Wredundant-decls] | extern size_t strlcpy(char *dest, const char *src, size_t size); ^ This is after commit 61a6445e463a31 ("tools lib: Guard the strlcpy() header with __GLIBC__"). The problem is uClibc also defines __GLIBC__ for exported headers for applications. So add that specific check to not trip for uClibc. Signed-off-by: Vineet Gupta Cc: Adrian Hunter Cc: Alexey Brodkin Cc: David Ahern Cc: Jiri Olsa Cc: Josh Poimboeuf Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Petri Gynther Cc: Wang Nan Cc: linux-snps-arc@lists.infradead.org Link: http://lkml.kernel.org/r/1471537703-16439-1-git-send-email-vgupta@synopsys.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/linux/string.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/tools/include/linux/string.h b/tools/include/linux/string.h index b96879477311..f436d2420a18 100644 --- a/tools/include/linux/string.h +++ b/tools/include/linux/string.h @@ -8,7 +8,11 @@ void *memdup(const void *src, size_t len); int strtobool(const char *s, bool *res); -#ifdef __GLIBC__ +/* + * glibc based builds needs the extern while uClibc doesn't. + * However uClibc headers also define __GLIBC__ hence the hack below + */ +#if defined(__GLIBC__) && !defined(__UCLIBC__) extern size_t strlcpy(char *dest, const char *src, size_t size); #endif From c53412ee8c7ec31373a4176ff7f3a6b79296c05c Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 18 Aug 2016 16:30:28 -0300 Subject: [PATCH 111/531] perf evsel: Do not access outside hw cache name arrays We have to check if the values are >= *_MAX, not just >, fix it. From the bugzilla report: ''In file /tools/perf/util/evsel.c function __perf_evsel__hw_cache_name it appears that there is a bug that reads beyond the end of the buffer. The statement "if (type > PERF_COUNT_HW_CACHE_MAX)" allows type to be equal to the maximum value. Later, when statement "if (!perf_evsel__is_cache_op_valid(type, op))" is executed, the function can access array perf_evsel__hw_cache_stat[type] beyond the end of the buffer. It appears to me that the statement "if (type > PERF_COUNT_HW_CACHE_MAX)" should be "if (type >= PERF_COUNT_HW_CACHE_MAX)" Bug found with Coverity and manual code review. No attempts were made to execute the code with a maximum type value.'' Committer note: Testing it: $ perf record -e $(echo $(perf list cache | cut -d \[ -f1) | sed 's/ /,/g') usleep 1 [ perf record: Woken up 16 times to write data ] [ perf record: Captured and wrote 0.023 MB perf.data (34 samples) ] $ perf evlist L1-dcache-load-misses L1-dcache-loads L1-dcache-stores L1-icache-load-misses LLC-load-misses LLC-loads LLC-store-misses LLC-stores branch-load-misses branch-loads dTLB-load-misses dTLB-loads dTLB-store-misses dTLB-stores iTLB-load-misses iTLB-loads node-load-misses node-loads node-store-misses node-stores $ perf list cache List of pre-defined events (to be used in -e): L1-dcache-load-misses [Hardware cache event] L1-dcache-loads [Hardware cache event] L1-dcache-stores [Hardware cache event] L1-icache-load-misses [Hardware cache event] LLC-load-misses [Hardware cache event] LLC-loads [Hardware cache event] LLC-store-misses [Hardware cache event] LLC-stores [Hardware cache event] branch-load-misses [Hardware cache event] branch-loads [Hardware cache event] dTLB-load-misses [Hardware cache event] dTLB-loads [Hardware cache event] dTLB-store-misses [Hardware cache event] dTLB-stores [Hardware cache event] iTLB-load-misses [Hardware cache event] iTLB-loads [Hardware cache event] node-load-misses [Hardware cache event] node-loads [Hardware cache event] node-store-misses [Hardware cache event] node-stores [Hardware cache event] $ Reported-by: Brian Sweeney Tested-by: Arnaldo Carvalho de Melo Cc: Jiri Olsa Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=153351 Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index d9b80ef881cd..21fd573106ed 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -507,17 +507,17 @@ static int __perf_evsel__hw_cache_name(u64 config, char *bf, size_t size) u8 op, result, type = (config >> 0) & 0xff; const char *err = "unknown-ext-hardware-cache-type"; - if (type > PERF_COUNT_HW_CACHE_MAX) + if (type >= PERF_COUNT_HW_CACHE_MAX) goto out_err; op = (config >> 8) & 0xff; err = "unknown-ext-hardware-cache-op"; - if (op > PERF_COUNT_HW_CACHE_OP_MAX) + if (op >= PERF_COUNT_HW_CACHE_OP_MAX) goto out_err; result = (config >> 16) & 0xff; err = "unknown-ext-hardware-cache-result"; - if (result > PERF_COUNT_HW_CACHE_RESULT_MAX) + if (result >= PERF_COUNT_HW_CACHE_RESULT_MAX) goto out_err; err = "invalid-cache"; From c4e94174983a86c935be1537a73e496b778b0287 Mon Sep 17 00:00:00 2001 From: Li Jun Date: Tue, 16 Aug 2016 19:19:11 +0800 Subject: [PATCH 112/531] usb: chipidea: udc: don't touch DP when controller is in host mode When the controller is configured to be dual role and it's in host mode, if bind udc and gadgt driver, those gadget operations will do gadget disconnect and finally pull down DP line, which will break host function. Cc: # 4.1+ Signed-off-by: Li Jun Signed-off-by: Peter Chen --- drivers/usb/chipidea/udc.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c index 065f5d97aa67..dfec5a176315 100644 --- a/drivers/usb/chipidea/udc.c +++ b/drivers/usb/chipidea/udc.c @@ -1596,8 +1596,11 @@ static int ci_udc_pullup(struct usb_gadget *_gadget, int is_on) { struct ci_hdrc *ci = container_of(_gadget, struct ci_hdrc, gadget); - /* Data+ pullup controlled by OTG state machine in OTG fsm mode */ - if (ci_otg_is_fsm_mode(ci)) + /* + * Data+ pullup controlled by OTG state machine in OTG fsm mode; + * and don't touch Data+ in host mode for dual role config. + */ + if (ci_otg_is_fsm_mode(ci) || ci->role == CI_ROLE_HOST) return 0; pm_runtime_get_sync(&ci->gadget.dev); From b873b798af6386f3c7ca1636d4989e9b8f9d1794 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Thu, 4 Aug 2016 11:38:25 -0700 Subject: [PATCH 113/531] Revert "f2fs: use percpu_rw_semaphore" LKP reported -36.3% regression of fsmark.files_per_sec due to this patch. I've confirmed that fxmark [1] has also slight regression for DWAL. [1] https://github.com/sslab-gatech/fxmark This reverts commit ec795418c41850056feb956534edf059dc1155d4. --- fs/f2fs/f2fs.h | 12 ++++++------ fs/f2fs/node.c | 47 +++++++++++++++++++++++------------------------ fs/f2fs/super.c | 6 +----- 3 files changed, 30 insertions(+), 35 deletions(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 675fa79d86f6..14f5fe2b841e 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -538,7 +538,7 @@ struct f2fs_nm_info { /* NAT cache management */ struct radix_tree_root nat_root;/* root of the nat entry cache */ struct radix_tree_root nat_set_root;/* root of the nat set cache */ - struct percpu_rw_semaphore nat_tree_lock; /* protect nat_tree_lock */ + struct rw_semaphore nat_tree_lock; /* protect nat_tree_lock */ struct list_head nat_entries; /* cached nat entry list (clean) */ unsigned int nat_cnt; /* the # of cached nat entries */ unsigned int dirty_nat_cnt; /* total num of nat entries in set */ @@ -787,7 +787,7 @@ struct f2fs_sb_info { struct f2fs_checkpoint *ckpt; /* raw checkpoint pointer */ struct inode *meta_inode; /* cache meta blocks */ struct mutex cp_mutex; /* checkpoint procedure lock */ - struct percpu_rw_semaphore cp_rwsem; /* blocking FS operations */ + struct rw_semaphore cp_rwsem; /* blocking FS operations */ struct rw_semaphore node_write; /* locking node writes */ wait_queue_head_t cp_wait; unsigned long last_time[MAX_TIME]; /* to store time in jiffies */ @@ -1074,22 +1074,22 @@ static inline void clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f) static inline void f2fs_lock_op(struct f2fs_sb_info *sbi) { - percpu_down_read(&sbi->cp_rwsem); + down_read(&sbi->cp_rwsem); } static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi) { - percpu_up_read(&sbi->cp_rwsem); + up_read(&sbi->cp_rwsem); } static inline void f2fs_lock_all(struct f2fs_sb_info *sbi) { - percpu_down_write(&sbi->cp_rwsem); + down_write(&sbi->cp_rwsem); } static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi) { - percpu_up_write(&sbi->cp_rwsem); + up_write(&sbi->cp_rwsem); } static inline int __get_cp_reason(struct f2fs_sb_info *sbi) diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index b2fa4b615925..f75d197d5beb 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -206,14 +206,14 @@ int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid) struct nat_entry *e; bool need = false; - percpu_down_read(&nm_i->nat_tree_lock); + down_read(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, nid); if (e) { if (!get_nat_flag(e, IS_CHECKPOINTED) && !get_nat_flag(e, HAS_FSYNCED_INODE)) need = true; } - percpu_up_read(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); return need; } @@ -223,11 +223,11 @@ bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid) struct nat_entry *e; bool is_cp = true; - percpu_down_read(&nm_i->nat_tree_lock); + down_read(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, nid); if (e && !get_nat_flag(e, IS_CHECKPOINTED)) is_cp = false; - percpu_up_read(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); return is_cp; } @@ -237,13 +237,13 @@ bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino) struct nat_entry *e; bool need_update = true; - percpu_down_read(&nm_i->nat_tree_lock); + down_read(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, ino); if (e && get_nat_flag(e, HAS_LAST_FSYNC) && (get_nat_flag(e, IS_CHECKPOINTED) || get_nat_flag(e, HAS_FSYNCED_INODE))) need_update = false; - percpu_up_read(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); return need_update; } @@ -284,7 +284,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; - percpu_down_write(&nm_i->nat_tree_lock); + down_write(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, ni->nid); if (!e) { e = grab_nat_entry(nm_i, ni->nid); @@ -334,7 +334,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, set_nat_flag(e, HAS_FSYNCED_INODE, true); set_nat_flag(e, HAS_LAST_FSYNC, fsync_done); } - percpu_up_write(&nm_i->nat_tree_lock); + up_write(&nm_i->nat_tree_lock); } int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) @@ -342,7 +342,8 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) struct f2fs_nm_info *nm_i = NM_I(sbi); int nr = nr_shrink; - percpu_down_write(&nm_i->nat_tree_lock); + if (!down_write_trylock(&nm_i->nat_tree_lock)) + return 0; while (nr_shrink && !list_empty(&nm_i->nat_entries)) { struct nat_entry *ne; @@ -351,7 +352,7 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) __del_from_nat_cache(nm_i, ne); nr_shrink--; } - percpu_up_write(&nm_i->nat_tree_lock); + up_write(&nm_i->nat_tree_lock); return nr - nr_shrink; } @@ -373,13 +374,13 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni) ni->nid = nid; /* Check nat cache */ - percpu_down_read(&nm_i->nat_tree_lock); + down_read(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, nid); if (e) { ni->ino = nat_get_ino(e); ni->blk_addr = nat_get_blkaddr(e); ni->version = nat_get_version(e); - percpu_up_read(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); return; } @@ -403,11 +404,11 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni) node_info_from_raw_nat(ni, &ne); f2fs_put_page(page, 1); cache: - percpu_up_read(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); /* cache nat entry */ - percpu_down_write(&nm_i->nat_tree_lock); + down_write(&nm_i->nat_tree_lock); cache_nat_entry(sbi, nid, &ne); - percpu_up_write(&nm_i->nat_tree_lock); + up_write(&nm_i->nat_tree_lock); } /* @@ -1788,7 +1789,7 @@ void build_free_nids(struct f2fs_sb_info *sbi) ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES, META_NAT, true); - percpu_down_read(&nm_i->nat_tree_lock); + down_read(&nm_i->nat_tree_lock); while (1) { struct page *page = get_current_nat_page(sbi, nid); @@ -1820,7 +1821,7 @@ void build_free_nids(struct f2fs_sb_info *sbi) remove_free_nid(nm_i, nid); } up_read(&curseg->journal_rwsem); - percpu_up_read(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid), nm_i->ra_nid_pages, META_NAT, false); @@ -2209,7 +2210,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi) if (!nm_i->dirty_nat_cnt) return; - percpu_down_write(&nm_i->nat_tree_lock); + down_write(&nm_i->nat_tree_lock); /* * if there are no enough space in journal to store dirty nat @@ -2232,7 +2233,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi) list_for_each_entry_safe(set, tmp, &sets, set_list) __flush_nat_entry_set(sbi, set); - percpu_up_write(&nm_i->nat_tree_lock); + up_write(&nm_i->nat_tree_lock); f2fs_bug_on(sbi, nm_i->dirty_nat_cnt); } @@ -2268,8 +2269,7 @@ static int init_node_manager(struct f2fs_sb_info *sbi) mutex_init(&nm_i->build_lock); spin_lock_init(&nm_i->free_nid_list_lock); - if (percpu_init_rwsem(&nm_i->nat_tree_lock)) - return -ENOMEM; + init_rwsem(&nm_i->nat_tree_lock); nm_i->next_scan_nid = le32_to_cpu(sbi->ckpt->next_free_nid); nm_i->bitmap_size = __bitmap_size(sbi, NAT_BITMAP); @@ -2326,7 +2326,7 @@ void destroy_node_manager(struct f2fs_sb_info *sbi) spin_unlock(&nm_i->free_nid_list_lock); /* destroy nat cache */ - percpu_down_write(&nm_i->nat_tree_lock); + down_write(&nm_i->nat_tree_lock); while ((found = __gang_lookup_nat_cache(nm_i, nid, NATVEC_SIZE, natvec))) { unsigned idx; @@ -2351,9 +2351,8 @@ void destroy_node_manager(struct f2fs_sb_info *sbi) kmem_cache_free(nat_entry_set_slab, setvec[idx]); } } - percpu_up_write(&nm_i->nat_tree_lock); + up_write(&nm_i->nat_tree_lock); - percpu_free_rwsem(&nm_i->nat_tree_lock); kfree(nm_i->nat_bitmap); sbi->nm_info = NULL; kfree(nm_i); diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 1b86d3f638ef..7f863a645ab1 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -706,8 +706,6 @@ static void destroy_percpu_info(struct f2fs_sb_info *sbi) percpu_counter_destroy(&sbi->nr_pages[i]); percpu_counter_destroy(&sbi->alloc_valid_block_count); percpu_counter_destroy(&sbi->total_valid_inode_count); - - percpu_free_rwsem(&sbi->cp_rwsem); } static void f2fs_put_super(struct super_block *sb) @@ -1483,9 +1481,6 @@ static int init_percpu_info(struct f2fs_sb_info *sbi) { int i, err; - if (percpu_init_rwsem(&sbi->cp_rwsem)) - return -ENOMEM; - for (i = 0; i < NR_COUNT_TYPE; i++) { err = percpu_counter_init(&sbi->nr_pages[i], 0, GFP_KERNEL); if (err) @@ -1686,6 +1681,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) sbi->write_io[i].bio = NULL; } + init_rwsem(&sbi->cp_rwsem); init_waitqueue_head(&sbi->cp_wait); init_sb_info(sbi); From 3024c9a1fefb3ac0d1b0b078a2e3f2f69478daab Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Sat, 6 Aug 2016 21:09:41 +0800 Subject: [PATCH 114/531] Revert "f2fs: move i_size_write in f2fs_write_end" This reverts commit a2ee0a300344a6da76186129b078113354fe13d2. When testing with generic/032 of xfstest suit, failure message will be reported as below: generic/032 8s ... [failed, exit status 1] - output mismatch (see results/generic/032.out.bad) --- tests/generic/032.out 2015-01-11 16:52:27.643681072 +0800 +++ results/generic/032.out.bad 2016-08-06 13:44:43.861330500 +0800 @@ -1,5 +1,5 @@ QA output created by 032 -100 iterations -0000000 cdcd cdcd cdcd cdcd cdcd cdcd cdcd cdcd -* -0100000 +1: [768..775]: unwritten +Unwritten extents found! ... (Run 'diff -u tests/generic/032.out results/generic/032.out.bad' to see the entire diff) Ran: generic/032 Failures: generic/032 Failed 1 of 1 tests In write_end(), we should update i_size of inode before unlock page, otherwise, we will lose newly updated data in following race condition. Thread A Thread B - write_end - unlock page - writepages - lock_page - writepage if page is out-of-range of file size, we will skip writting the page. - update i_size Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/data.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index d64d2a515cb2..ccb401eebc11 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -1699,11 +1699,11 @@ static int f2fs_write_end(struct file *file, trace_f2fs_write_end(inode, pos, len, copied); set_page_dirty(page); - f2fs_put_page(page, 1); if (pos + copied > i_size_read(inode)) f2fs_i_size_write(inode, pos + copied); + f2fs_put_page(page, 1); f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); return copied; } From fe8494bfc8c2914fca821d4ae994aef039be5cf1 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Thu, 4 Aug 2016 20:13:02 +0800 Subject: [PATCH 115/531] f2fs: allow copying file range only in between regular files Only if two input files are regular files, we allow copying data in range of them, otherwise, deny it. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/file.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 0e493f63ea41..685e629f768b 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -2086,8 +2086,8 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, if (unlikely(f2fs_readonly(src->i_sb))) return -EROFS; - if (S_ISDIR(src->i_mode) || S_ISDIR(dst->i_mode)) - return -EISDIR; + if (!S_ISREG(src->i_mode) || !S_ISREG(dst->i_mode)) + return -EINVAL; if (f2fs_encrypted_inode(src) || f2fs_encrypted_inode(dst)) return -EOPNOTSUPP; From 20a3d61d46e1fb45efa6eb4637c0dcd3f00a14e9 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Thu, 4 Aug 2016 20:13:03 +0800 Subject: [PATCH 116/531] f2fs: avoid potential deadlock in f2fs_move_file_range Thread A Thread B - inode_lock fileA - inode_lock fileB - inode_lock fileA - inode_lock fileB We may encounter above potential deadlock during moving file range in concurrent scenario. This patch fixes the issue by using inode_trylock instead. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/file.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 685e629f768b..47abb96098e4 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -2093,8 +2093,12 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, return -EOPNOTSUPP; inode_lock(src); - if (src != dst) - inode_lock(dst); + if (src != dst) { + if (!inode_trylock(dst)) { + ret = -EBUSY; + goto out; + } + } ret = -EINVAL; if (pos_in + len > src->i_size || pos_in + len < pos_in) @@ -2152,6 +2156,7 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, out_unlock: if (src != dst) inode_unlock(dst); +out: inode_unlock(src); return ret; } From d9dc1702b297ec4a6bb9c0326a70641b322ba886 Mon Sep 17 00:00:00 2001 From: Eric Wheeler Date: Fri, 17 Jun 2016 15:01:54 -0700 Subject: [PATCH 117/531] bcache: register_bcache(): call blkdev_put() when cache_alloc() fails register_cache() is supposed to return an error string on error so that register_bcache() will will blkdev_put and cleanup other user counters, but it does not set 'char *err' when cache_alloc() fails (eg, due to memory pressure) and thus register_bcache() performs no cleanup. register_bcache() <----------\ <- no jump to err_close, no blkdev_put() | | +->register_cache() | <- fails to set char *err | | +->cache_alloc() ---/ <- returns error This patch sets `char *err` for this failure case so that register_cache() will cause register_bcache() to correctly jump to err_close and do cleanup. This was tested under OOM conditions that triggered the bug. Signed-off-by: Eric Wheeler Cc: Kent Overstreet Cc: stable@vger.kernel.org --- drivers/md/bcache/super.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 95a4ca6ce6ff..6ada14b9a157 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1844,7 +1844,7 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page, struct block_device *bdev, struct cache *ca) { char name[BDEVNAME_SIZE]; - const char *err = NULL; + const char *err = NULL; /* must be set for any error case */ int ret = 0; memcpy(&ca->sb, sb, sizeof(struct cache_sb)); @@ -1861,8 +1861,13 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page, ca->discard = CACHE_DISCARD(&ca->sb); ret = cache_alloc(ca); - if (ret != 0) + if (ret != 0) { + if (ret == -ENOMEM) + err = "cache_alloc(): -ENOMEM"; + else + err = "cache_alloc(): unknown error"; goto err; + } if (kobject_add(&ca->kobj, &part_to_dev(bdev->bd_part)->kobj, "bcache")) { err = "error calling kobject_add"; From acc9cf8c66c66b2cbbdb4a375537edee72be64df Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Wed, 17 Aug 2016 18:21:24 -0700 Subject: [PATCH 118/531] bcache: RESERVE_PRIO is too small by one when prio_buckets() is a power of two. This patch fixes a cachedev registration-time allocation deadlock. This can deadlock on boot if your initrd auto-registeres bcache devices: Allocator thread: [ 720.727614] INFO: task bcache_allocato:3833 blocked for more than 120 seconds. [ 720.732361] [] schedule+0x37/0x90 [ 720.732963] [] bch_bucket_alloc+0x188/0x360 [bcache] [ 720.733538] [] ? prepare_to_wait_event+0xf0/0xf0 [ 720.734137] [] bch_prio_write+0x19d/0x340 [bcache] [ 720.734715] [] bch_allocator_thread+0x3ff/0x470 [bcache] [ 720.735311] [] ? __schedule+0x2dc/0x950 [ 720.735884] [] ? invalidate_buckets+0x980/0x980 [bcache] Registration thread: [ 720.710403] INFO: task bash:3531 blocked for more than 120 seconds. [ 720.715226] [] schedule+0x37/0x90 [ 720.715805] [] __bch_btree_map_nodes+0x12d/0x150 [bcache] [ 720.716409] [] ? bch_btree_insert_check_key+0x1c0/0x1c0 [bcache] [ 720.717008] [] bch_btree_insert+0xf4/0x170 [bcache] [ 720.717586] [] ? prepare_to_wait_event+0xf0/0xf0 [ 720.718191] [] bch_journal_replay+0x14a/0x290 [bcache] [ 720.718766] [] ? ttwu_do_activate.constprop.94+0x5d/0x70 [ 720.719369] [] ? try_to_wake_up+0x1d4/0x350 [ 720.719968] [] run_cache_set+0x580/0x8e0 [bcache] [ 720.720553] [] register_bcache+0xe2e/0x13b0 [bcache] [ 720.721153] [] kobj_attr_store+0xf/0x20 [ 720.721730] [] sysfs_kf_write+0x3d/0x50 [ 720.722327] [] kernfs_fop_write+0x12a/0x180 [ 720.722904] [] __vfs_write+0x37/0x110 [ 720.723503] [] ? __sb_start_write+0x58/0x110 [ 720.724100] [] ? security_file_permission+0x23/0xa0 [ 720.724675] [] vfs_write+0xa9/0x1b0 [ 720.725275] [] ? do_audit_syscall_entry+0x6c/0x70 [ 720.725849] [] SyS_write+0x55/0xd0 [ 720.726451] [] ? do_page_fault+0x30/0x80 [ 720.727045] [] system_call_fastpath+0x12/0x71 The fifo code in upstream bcache can't use the last element in the buffer, which was the cause of the bug: if you asked for a power of two size, it'd give you a fifo that could hold one less than what you asked for rather than allocating a buffer twice as big. Signed-off-by: Kent Overstreet Tested-by: Eric Wheeler Cc: stable@vger.kernel.org --- drivers/md/bcache/super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 6ada14b9a157..6b93e1b77767 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1820,7 +1820,7 @@ static int cache_alloc(struct cache *ca) free = roundup_pow_of_two(ca->sb.nbuckets) >> 10; if (!init_fifo(&ca->free[RESERVE_BTREE], 8, GFP_KERNEL) || - !init_fifo(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) || + !init_fifo_exact(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) || !init_fifo(&ca->free[RESERVE_MOVINGGC], free, GFP_KERNEL) || !init_fifo(&ca->free[RESERVE_NONE], free, GFP_KERNEL) || !init_fifo(&ca->free_inc, free << 2, GFP_KERNEL) || From 90706094d5be614ae7285b3c96c3125bb198618c Mon Sep 17 00:00:00 2001 From: Eric Wheeler Date: Thu, 18 Aug 2016 20:15:26 -0700 Subject: [PATCH 119/531] bcache: pr_err: more meaningful error message when nr_stripes is invalid The original error was thought to be corruption, but was actually caused by: make-bcache --data-offset N where N was in bytes and should have been in sectors. While userspace tools should be updated to check --data-offset beyond end of volume, hopefully this will help others that might not have noticed the units. Signed-off-by: Eric Wheeler Cc: Kent Overstreet --- drivers/md/bcache/super.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 6b93e1b77767..849ad441cd76 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -760,7 +760,8 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size, if (!d->nr_stripes || d->nr_stripes > INT_MAX || d->nr_stripes > SIZE_MAX / sizeof(atomic_t)) { - pr_err("nr_stripes too large"); + pr_err("nr_stripes too large or invalid: %u (start sector beyond end of disk?)", + (unsigned)d->nr_stripes); return -ENOMEM; } From 039a392733600d35c80d406a98151b2a9a0a74b4 Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Tue, 16 Aug 2016 18:40:18 +0300 Subject: [PATCH 120/531] qede: Fix Tx timeout due to xmit_more Driver uses netif_tx_queue_stopped() to make sure the xmit_more indication will be honored, but that only checks for DRV_XOFF. At the same time, it's possible that during transmission the DQL will close the transmission queue with STACK_XOFF indication. In re-configuration flows, when the threshold is relatively low, it's possible that the device has no pending tranmissions, and during tranmission the driver would miss doorbelling the HW. Since there are no pending transmission, there will never be a Tx completion [and thus the DQL would not remove the STACK_XOFF indication], eventually causing the Tx queue to timeout. While we're at it - also doorbell in case driver has to close the transmission queue on its own [although this one is less important - if the ring is full, we're bound to receive completion eventually, which means the doorbell would only be postponed and not indefinetly blocked]. Fixes: 312e06761c99 ("qede: Utilize xmit_more") Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qede/qede_main.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index e4bd02e46e57..a6eb6af8cbe8 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -722,11 +722,14 @@ netdev_tx_t qede_start_xmit(struct sk_buff *skb, txq->tx_db.data.bd_prod = cpu_to_le16(qed_chain_get_prod_idx(&txq->tx_pbl)); - if (!skb->xmit_more || netif_tx_queue_stopped(netdev_txq)) + if (!skb->xmit_more || netif_xmit_stopped(netdev_txq)) qede_update_tx_producer(txq); if (unlikely(qed_chain_get_elem_left(&txq->tx_pbl) < (MAX_SKB_FRAGS + 1))) { + if (skb->xmit_more) + qede_update_tx_producer(txq); + netif_tx_stop_queue(netdev_txq); DP_VERBOSE(edev, NETIF_MSG_TX_QUEUED, "Stop queue was called\n"); From 1423661fed2c40d6d71b5e2e3aa390f85157f9d5 Mon Sep 17 00:00:00 2001 From: David Daney Date: Tue, 16 Aug 2016 13:30:36 -0700 Subject: [PATCH 121/531] net: thunderx: Fix OOPs with ethtool --register-dump The ethtool_ops .get_regs function attempts to read the nonexistent register NIC_QSET_SQ_0_7_CNM_CHG, which produces a "bus error" type OOPs. Fix by not attempting to read, and removing the definition of, NIC_QSET_SQ_0_7_CNM_CHG. A zero is written into the register dump to keep the layout unchanged. Signed-off-by: David Daney Cc: # 4.4.x- Signed-off-by: David S. Miller --- drivers/net/ethernet/cavium/thunder/nic_reg.h | 1 - drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c | 5 ++++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/cavium/thunder/nic_reg.h b/drivers/net/ethernet/cavium/thunder/nic_reg.h index afb10e326b4f..fab35a593898 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_reg.h +++ b/drivers/net/ethernet/cavium/thunder/nic_reg.h @@ -170,7 +170,6 @@ #define NIC_QSET_SQ_0_7_DOOR (0x010838) #define NIC_QSET_SQ_0_7_STATUS (0x010840) #define NIC_QSET_SQ_0_7_DEBUG (0x010848) -#define NIC_QSET_SQ_0_7_CNM_CHG (0x010860) #define NIC_QSET_SQ_0_7_STAT_0_1 (0x010900) #define NIC_QSET_RBDR_0_1_CFG (0x010C00) diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c index d2d8ef270142..ad4fddb55421 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c @@ -382,7 +382,10 @@ static void nicvf_get_regs(struct net_device *dev, p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_DOOR, q); p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_STATUS, q); p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_DEBUG, q); - p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_CNM_CHG, q); + /* Padding, was NIC_QSET_SQ_0_7_CNM_CHG, which + * produces bus errors when read + */ + p[i++] = 0; p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_STAT_0_1, q); reg_offset = NIC_QSET_SQ_0_7_STAT_0_1 | (1 << 3); p[i++] = nicvf_queue_reg_read(nic, reg_offset, q); From e0d8b2908696d30583ae5764e33332e71cbbccc9 Mon Sep 17 00:00:00 2001 From: Hariprasad Shenai Date: Wed, 17 Aug 2016 14:09:28 +0530 Subject: [PATCH 122/531] cxgb4: Fixes resource allocation for ULD's in kdump kernel At present the code to check in kdump kernel was not disabling allocation of resources when CONFIG_CHELSIO_T4_DCB is defined, move the code outside #defines so that it gets disabled irrespective of #define, when in kdump kernel. Signed-off-by: Hariprasad Shenai Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index c45de49dc963..c762a8c8c954 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -4335,6 +4335,11 @@ static void cfg_queues(struct adapter *adap) #endif int ciq_size; + /* Reduce memory usage in kdump environment, disable all offload. + */ + if (is_kdump_kernel()) + adap->params.offload = 0; + for_each_port(adap, i) n10g += is_x_10g_port(&adap2pinfo(adap, i)->link_cfg); #ifdef CONFIG_CHELSIO_T4_DCB @@ -4365,11 +4370,6 @@ static void cfg_queues(struct adapter *adap) if (q10g > netif_get_num_default_rss_queues()) q10g = netif_get_num_default_rss_queues(); - /* Reduce memory usage in kdump environment, disable all offload. - */ - if (is_kdump_kernel()) - adap->params.offload = 0; - for_each_port(adap, i) { struct port_info *pi = adap2pinfo(adap, i); From bb1fceca22492109be12640d49f5ea5a544c6bb4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 17 Aug 2016 05:56:26 -0700 Subject: [PATCH 123/531] tcp: fix use after free in tcp_xmit_retransmit_queue() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When tcp_sendmsg() allocates a fresh and empty skb, it puts it at the tail of the write queue using tcp_add_write_queue_tail() Then it attempts to copy user data into this fresh skb. If the copy fails, we undo the work and remove the fresh skb. Unfortunately, this undo lacks the change done to tp->highest_sack and we can leave a dangling pointer (to a freed skb) Later, tcp_xmit_retransmit_queue() can dereference this pointer and access freed memory. For regular kernels where memory is not unmapped, this might cause SACK bugs because tcp_highest_sack_seq() is buggy, returning garbage instead of tp->snd_nxt, but with various debug features like CONFIG_DEBUG_PAGEALLOC, this can crash the kernel. This bug was found by Marco Grassi thanks to syzkaller. Fixes: 6859d49475d4 ("[TCP]: Abstract tp->highest_sack accessing & point to next skb") Reported-by: Marco Grassi Signed-off-by: Eric Dumazet Cc: Ilpo Järvinen Cc: Yuchung Cheng Cc: Neal Cardwell Acked-by: Neal Cardwell Reviewed-by: Cong Wang Signed-off-by: David S. Miller --- include/net/tcp.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/include/net/tcp.h b/include/net/tcp.h index c00e7d51bb18..7717302cab91 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1523,6 +1523,8 @@ static inline void tcp_check_send_head(struct sock *sk, struct sk_buff *skb_unli { if (sk->sk_send_head == skb_unlinked) sk->sk_send_head = NULL; + if (tcp_sk(sk)->highest_sack == skb_unlinked) + tcp_sk(sk)->highest_sack = NULL; } static inline void tcp_init_send_head(struct sock *sk) From b9f63ae7ba2de2ba19137c5757c0607ce40f3ed5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Wed, 17 Aug 2016 15:37:14 +0200 Subject: [PATCH 124/531] net: bgmac: fix reversed check for MII registration error MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It was failing on successful registration returning meaningless errors. Signed-off-by: Rafał Miłecki Fixes: 55954f3bfdac ("net: ethernet: bgmac: move BCMA MDIO Phy code into a separate file") Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bgmac-bcma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma.c b/drivers/net/ethernet/broadcom/bgmac-bcma.c index 9a9745c4047c..625235db644f 100644 --- a/drivers/net/ethernet/broadcom/bgmac-bcma.c +++ b/drivers/net/ethernet/broadcom/bgmac-bcma.c @@ -159,7 +159,7 @@ static int bgmac_probe(struct bcma_device *core) if (!bgmac_is_bcm4707_family(core)) { mii_bus = bcma_mdio_mii_register(core, bgmac->phyaddr); - if (!IS_ERR(mii_bus)) { + if (IS_ERR(mii_bus)) { err = PTR_ERR(mii_bus); goto err; } From 60bcabd080f53561efa9288be45c128feda1a8bb Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Wed, 17 Aug 2016 15:51:55 +0200 Subject: [PATCH 125/531] kaweth: fix firmware download This fixes the oops discovered by the Umap2 project and Alan Stern. The intf member needs to be set before the firmware is downloaded. Signed-off-by: Oliver Neukum Signed-off-by: David S. Miller --- drivers/net/usb/kaweth.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/usb/kaweth.c b/drivers/net/usb/kaweth.c index 770212baaf05..37bf715ab53b 100644 --- a/drivers/net/usb/kaweth.c +++ b/drivers/net/usb/kaweth.c @@ -1029,6 +1029,7 @@ static int kaweth_probe( kaweth = netdev_priv(netdev); kaweth->dev = udev; kaweth->net = netdev; + kaweth->intf = intf; spin_lock_init(&kaweth->device_lock); init_waitqueue_head(&kaweth->term_wait); @@ -1139,8 +1140,6 @@ static int kaweth_probe( dev_dbg(dev, "Initializing net device.\n"); - kaweth->intf = intf; - kaweth->tx_urb = usb_alloc_urb(0, GFP_KERNEL); if (!kaweth->tx_urb) goto err_free_netdev; From 575ced7f8090c1a4e91e2daf8da9352a6a1fc7a7 Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Wed, 17 Aug 2016 15:51:56 +0200 Subject: [PATCH 126/531] kaweth: fix oops upon failed memory allocation Just return an error upon failure. Signed-off-by: Oliver Neukum Signed-off-by: David S. Miller --- drivers/net/usb/kaweth.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/usb/kaweth.c b/drivers/net/usb/kaweth.c index 37bf715ab53b..528b9c9c4e60 100644 --- a/drivers/net/usb/kaweth.c +++ b/drivers/net/usb/kaweth.c @@ -1009,6 +1009,7 @@ static int kaweth_probe( struct net_device *netdev; const eth_addr_t bcast_addr = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF }; int result = 0; + int rv = -EIO; dev_dbg(dev, "Kawasaki Device Probe (Device number:%d): 0x%4.4x:0x%4.4x:0x%4.4x\n", @@ -1049,6 +1050,10 @@ static int kaweth_probe( /* Download the firmware */ dev_info(dev, "Downloading firmware...\n"); kaweth->firmware_buf = (__u8 *)__get_free_page(GFP_KERNEL); + if (!kaweth->firmware_buf) { + rv = -ENOMEM; + goto err_free_netdev; + } if ((result = kaweth_download_firmware(kaweth, "kaweth/new_code.bin", 100, @@ -1203,7 +1208,7 @@ static int kaweth_probe( err_free_netdev: free_netdev(netdev); - return -EIO; + return rv; } /**************************************************************** From 76507fdfc9b629209ae20cd469da2f6d093a507c Mon Sep 17 00:00:00 2001 From: Robert Jarzmik Date: Sun, 7 Aug 2016 21:01:48 +0200 Subject: [PATCH 127/531] dmaengine: pxa_dma: fix hotchain corner case In the case where a descriptor is chained on a running channel, and as explained in the comment in the code 10 lines above, the success of the chaining is ensured either if : - the DMA is still running - or if the chained transfer is completed Unfortunately the transfer completness test was done on the descriptor to which the transfer was chained, and not the transfer being chained at the end, ie. hot-chained. This corner case is extremely hard to trigger, as usually the DMA chain is still running, and the first case takes care of returning success of the hot-chaining. It was seen by hot-chaining several "small transfers" to a running "big transfer", not in a real-life usecase but by testing the robustness of the driver. Signed-off-by: Robert Jarzmik Signed-off-by: Vinod Koul --- drivers/dma/pxa_dma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/dma/pxa_dma.c b/drivers/dma/pxa_dma.c index dc7850a422b8..2093e528ae00 100644 --- a/drivers/dma/pxa_dma.c +++ b/drivers/dma/pxa_dma.c @@ -638,7 +638,7 @@ static bool pxad_try_hotchain(struct virt_dma_chan *vc, vd_last_issued = list_entry(vc->desc_issued.prev, struct virt_dma_desc, node); pxad_desc_chain(vd_last_issued, vd); - if (is_chan_running(chan) || is_desc_completed(vd_last_issued)) + if (is_chan_running(chan) || is_desc_completed(vd)) return true; } From 98a384eca9c147f890b5ea31ae91da3769e47e07 Mon Sep 17 00:00:00 2001 From: Xunlei Pang Date: Thu, 18 Aug 2016 12:33:28 +0800 Subject: [PATCH 128/531] fib_trie: Fix the description of pos and bits 1) Fix one typo: s/tn/tp/ 2) Fix the description about the "u" bits. Signed-off-by: Xunlei Pang Acked-by: Alexander Duyck Signed-off-by: David S. Miller --- net/ipv4/fib_trie.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index febca0f1008c..e2ffc2a5c7db 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -249,7 +249,7 @@ static inline unsigned long get_index(t_key key, struct key_vector *kv) * index into the parent's child array. That is, they will be used to find * 'n' among tp's children. * - * The bits from (n->pos + n->bits) to (tn->pos - 1) - "S" - are skipped bits + * The bits from (n->pos + n->bits) to (tp->pos - 1) - "S" - are skipped bits * for the node n. * * All the bits we have seen so far are significant to the node n. The rest @@ -258,7 +258,7 @@ static inline unsigned long get_index(t_key key, struct key_vector *kv) * The bits from (n->pos) to (n->pos + n->bits - 1) - "C" - are the index into * n's child array, and will of course be different for each child. * - * The rest of the bits, from 0 to (n->pos + n->bits), are completely unknown + * The rest of the bits, from 0 to (n->pos -1) - "u" - are completely unknown * at this point. */ From e633fc7a1347528c3b4a6bbdeb41f5d63988242c Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Thu, 11 Aug 2016 17:44:05 +0100 Subject: [PATCH 129/531] iommu/io-pgtable-arm-v7s: Fix attributes when splitting blocks Due to the attribute bits being all over the place in the different types of short-descriptor PTEs, when remapping an existing entry, e.g. splitting a section into pages, we take the approach of decomposing the PTE attributes back to the IOMMU API flags to start from scratch. On inspection, though, the existing code seems to have got the read-only bit backwards and ignored the XN bit. How embarrassing... Fortunately the primary user so far, the Mediatek IOMMU, both never splits blocks (because it only serves non-overlapping DMA API calls) and also ignores permissions anyway, but let's put things right before any future users trip up. Cc: Fixes: e5fc9753b1a8 ("iommu/io-pgtable: Add ARMv7 short descriptor support") Signed-off-by: Robin Murphy Signed-off-by: Will Deacon --- drivers/iommu/io-pgtable-arm-v7s.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c index 8c6139986d7d..def8ca1c982d 100644 --- a/drivers/iommu/io-pgtable-arm-v7s.c +++ b/drivers/iommu/io-pgtable-arm-v7s.c @@ -286,12 +286,14 @@ static int arm_v7s_pte_to_prot(arm_v7s_iopte pte, int lvl) int prot = IOMMU_READ; arm_v7s_iopte attr = pte >> ARM_V7S_ATTR_SHIFT(lvl); - if (attr & ARM_V7S_PTE_AP_RDONLY) + if (!(attr & ARM_V7S_PTE_AP_RDONLY)) prot |= IOMMU_WRITE; if ((attr & (ARM_V7S_TEX_MASK << ARM_V7S_TEX_SHIFT)) == 0) prot |= IOMMU_MMIO; else if (pte & ARM_V7S_ATTR_C) prot |= IOMMU_CACHE; + if (pte & ARM_V7S_ATTR_XN(lvl)) + prot |= IOMMU_NOEXEC; return prot; } From aea2037e0d3e23c3be1498feae29f71ca997d9e6 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 29 Jul 2016 11:15:37 +0100 Subject: [PATCH 130/531] iommu/arm-smmu: Fix CMDQ error handling In the unlikely event of a global command queue error, the ARM SMMUv3 driver attempts to convert the problematic command into a CMD_SYNC and resume the command queue. Unfortunately, this code is pretty badly broken: 1. It uses the index into the error string table as the CMDQ index, so we probably read the wrong entry out of the queue 2. The arguments to queue_write are the wrong way round, so we end up writing from the queue onto the stack. These happily cancel out, so the kernel is likely to stay alive, but the command queue will probably fault again when we resume. This patch fixes the error handling code to use the correct queue index and write back the CMD_SYNC to the faulting entry. Cc: Fixes: 48ec83bcbcf5 ("iommu/arm-smmu: Add initial driver support for ARM SMMUv3 devices") Reported-by: Diwakar Subraveti Signed-off-by: Will Deacon --- drivers/iommu/arm-smmu-v3.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index ce801170d5f2..330623f8e344 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -879,7 +879,7 @@ static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu) * We may have concurrent producers, so we need to be careful * not to touch any of the shadow cmdq state. */ - queue_read(cmd, Q_ENT(q, idx), q->ent_dwords); + queue_read(cmd, Q_ENT(q, cons), q->ent_dwords); dev_err(smmu->dev, "skipping command in error state:\n"); for (i = 0; i < ARRAY_SIZE(cmd); ++i) dev_err(smmu->dev, "\t0x%016llx\n", (unsigned long long)cmd[i]); @@ -890,7 +890,7 @@ static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu) return; } - queue_write(cmd, Q_ENT(q, idx), q->ent_dwords); + queue_write(Q_ENT(q, cons), cmd, q->ent_dwords); } static void arm_smmu_cmdq_issue_cmd(struct arm_smmu_device *smmu, From 7611da865c1060b2a7c87a15de663a59035747f8 Mon Sep 17 00:00:00 2001 From: David Daney Date: Thu, 18 Aug 2016 15:41:58 -0700 Subject: [PATCH 131/531] irqchip/gicv3-its: Disable the ITS before initializing it When starting a kexec/kdump kernel, the GIC ITS will already have been enabled. According to the ARM Generic Interrupt Controller Architecture Specification (GIC architecture Version 3.0 and version 4.0), writing to GITS_BASER or GITS_CBASER is "UNPREDICTABLE" when the ITS is enabled. On Cavium Thunder systems, this prevents the ITS from being initializing in the kexec/kdump kernel, resulting in failure to register/enable interrupts for all devices. The fix is to disable the ITS if it is not already in the disabled state. This allows the ITS to be properly initialized and then re-enabled in the kexec/kdump kernel. Acked-by: Marc Zyngier Signed-off-by: David Daney Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-gic-v3-its.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 7ceaba81efb4..36b9c28a5c91 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -1545,7 +1545,12 @@ static int its_force_quiescent(void __iomem *base) u32 val; val = readl_relaxed(base + GITS_CTLR); - if (val & GITS_CTLR_QUIESCENT) + /* + * GIC architecture specification requires the ITS to be both + * disabled and quiescent for writes to GITS_BASER or + * GITS_CBASER to not have UNPREDICTABLE results. + */ + if ((val & GITS_CTLR_QUIESCENT) && !(val & GITS_CTLR_ENABLE)) return 0; /* Disable the generation of all interrupts to this ITS */ From 3714ce1d6655098ee69ede632883e5874d67e4ab Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 5 Aug 2016 19:49:45 +0100 Subject: [PATCH 132/531] iommu/arm-smmu: Disable stalling faults for all endpoints Enabling stalling faults can result in hardware deadlock on poorly designed systems, particularly those with a PCI root complex upstream of the SMMU. Although it's not really Linux's job to save hardware integrators from their own misfortune, it *is* our job to stop userspace (e.g. VFIO clients) from hosing the system for everybody else, even if they might already be required to have elevated privileges. Given that the fault handling code currently executes entirely in IRQ context, there is nothing that can sensibly be done to recover from things like page faults anyway, so let's rip this code out for now and avoid the potential for deadlock. Cc: Fixes: 48ec83bcbcf5 ("iommu/arm-smmu: Add initial driver support for ARM SMMUv3 devices") Reported-by: Matt Evans Signed-off-by: Will Deacon --- drivers/iommu/arm-smmu.c | 34 +++++++--------------------------- 1 file changed, 7 insertions(+), 27 deletions(-) diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index 4f49fe29f202..2db74ebc3240 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -686,8 +686,7 @@ static struct iommu_gather_ops arm_smmu_gather_ops = { static irqreturn_t arm_smmu_context_fault(int irq, void *dev) { - int flags, ret; - u32 fsr, fsynr, resume; + u32 fsr, fsynr; unsigned long iova; struct iommu_domain *domain = dev; struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); @@ -701,34 +700,15 @@ static irqreturn_t arm_smmu_context_fault(int irq, void *dev) if (!(fsr & FSR_FAULT)) return IRQ_NONE; - if (fsr & FSR_IGN) - dev_err_ratelimited(smmu->dev, - "Unexpected context fault (fsr 0x%x)\n", - fsr); - fsynr = readl_relaxed(cb_base + ARM_SMMU_CB_FSYNR0); - flags = fsynr & FSYNR0_WNR ? IOMMU_FAULT_WRITE : IOMMU_FAULT_READ; - iova = readq_relaxed(cb_base + ARM_SMMU_CB_FAR); - if (!report_iommu_fault(domain, smmu->dev, iova, flags)) { - ret = IRQ_HANDLED; - resume = RESUME_RETRY; - } else { - dev_err_ratelimited(smmu->dev, - "Unhandled context fault: iova=0x%08lx, fsynr=0x%x, cb=%d\n", - iova, fsynr, cfg->cbndx); - ret = IRQ_NONE; - resume = RESUME_TERMINATE; - } - /* Clear the faulting FSR */ + dev_err_ratelimited(smmu->dev, + "Unhandled context fault: fsr=0x%x, iova=0x%08lx, fsynr=0x%x, cb=%d\n", + fsr, iova, fsynr, cfg->cbndx); + writel(fsr, cb_base + ARM_SMMU_CB_FSR); - - /* Retry or terminate any stalled transactions */ - if (fsr & FSR_SS) - writel_relaxed(resume, cb_base + ARM_SMMU_CB_RESUME); - - return ret; + return IRQ_HANDLED; } static irqreturn_t arm_smmu_global_fault(int irq, void *dev) @@ -837,7 +817,7 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain, } /* SCTLR */ - reg = SCTLR_CFCFG | SCTLR_CFIE | SCTLR_CFRE | SCTLR_M | SCTLR_EAE_SBOP; + reg = SCTLR_CFIE | SCTLR_CFRE | SCTLR_M | SCTLR_EAE_SBOP; if (stage1) reg |= SCTLR_S1_ASIDPNE; #ifdef __BIG_ENDIAN From 5bc0a11664e17e9f9551983f5b660bd48b57483c Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 16 Aug 2016 14:29:16 +0100 Subject: [PATCH 133/531] iommu/arm-smmu: Don't BUG() if we find aborting STEs with disable_bypass The disable_bypass cmdline option changes the SMMUv3 driver to put down faulting stream table entries by default, as opposed to bypassing transactions from unconfigured devices. In this mode of operation, it is entirely expected to see aborting entries in the stream table if and when we come to installing a valid translation, so don't trigger a BUG() as a result of misdiagnosing these entries as stream table corruption. Cc: Fixes: 48ec83bcbcf5 ("iommu/arm-smmu: Add initial driver support for ARM SMMUv3 devices") Tested-by: Robin Murphy Reported-by: Robin Murphy Reviewed-by: Robin Murphy Signed-off-by: Will Deacon --- drivers/iommu/arm-smmu-v3.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 330623f8e344..641e88761319 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -1034,6 +1034,9 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, case STRTAB_STE_0_CFG_S2_TRANS: ste_live = true; break; + case STRTAB_STE_0_CFG_ABORT: + if (disable_bypass) + break; default: BUG(); /* STE corruption */ } From 7a665d2f60b457c0d77b3e4f01e21c55ffc57069 Mon Sep 17 00:00:00 2001 From: Daniel Verkamp Date: Tue, 28 Jun 2016 11:20:23 -0700 Subject: [PATCH 134/531] nvme-fabrics: change NQN UUID to big-endian format NVM Express 1.2.1 section 7.9, NVMe Qualified Names, specifies that the UUID format of NQN uses a UUID based on RFC 4122. RFC 4122 specifies that the UUID is encoded in big-endian byte order. Switch the NVMe over Fabrics host ID field from little-endian UUID to big-endian UUID to match the specification. Signed-off-by: Daniel Verkamp Reviewed-by: Jay Freyensee Signed-off-by: Sagi Grimberg --- drivers/nvme/host/fabrics.c | 10 +++++----- drivers/nvme/host/fabrics.h | 2 +- include/linux/nvme.h | 2 +- 3 files changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 020302c6ea57..be0b1067c9fa 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -56,7 +56,7 @@ static struct nvmf_host *nvmf_host_add(const char *hostnqn) kref_init(&host->ref); memcpy(host->nqn, hostnqn, NVMF_NQN_SIZE); - uuid_le_gen(&host->id); + uuid_be_gen(&host->id); list_add_tail(&host->list, &nvmf_hosts); out_unlock: @@ -73,9 +73,9 @@ static struct nvmf_host *nvmf_host_default(void) return NULL; kref_init(&host->ref); - uuid_le_gen(&host->id); + uuid_be_gen(&host->id); snprintf(host->nqn, NVMF_NQN_SIZE, - "nqn.2014-08.org.nvmexpress:NVMf:uuid:%pUl", &host->id); + "nqn.2014-08.org.nvmexpress:NVMf:uuid:%pUb", &host->id); mutex_lock(&nvmf_hosts_mutex); list_add_tail(&host->list, &nvmf_hosts); @@ -382,7 +382,7 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl) if (!data) return -ENOMEM; - memcpy(&data->hostid, &ctrl->opts->host->id, sizeof(uuid_le)); + memcpy(&data->hostid, &ctrl->opts->host->id, sizeof(uuid_be)); data->cntlid = cpu_to_le16(0xffff); strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE); strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE); @@ -441,7 +441,7 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid) if (!data) return -ENOMEM; - memcpy(&data->hostid, &ctrl->opts->host->id, sizeof(uuid_le)); + memcpy(&data->hostid, &ctrl->opts->host->id, sizeof(uuid_be)); data->cntlid = cpu_to_le16(ctrl->cntlid); strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE); strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE); diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index 89df52c8be97..46e460aee52d 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -34,7 +34,7 @@ struct nvmf_host { struct kref ref; struct list_head list; char nqn[NVMF_NQN_SIZE]; - uuid_le id; + uuid_be id; }; /** diff --git a/include/linux/nvme.h b/include/linux/nvme.h index d8b37bab2887..7676557ce357 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -794,7 +794,7 @@ struct nvmf_connect_command { }; struct nvmf_connect_data { - uuid_le hostid; + uuid_be hostid; __le16 cntlid; char resv4[238]; char subsysnqn[NVMF_NQN_FIELD_LEN]; From d1e81428826221d7ff8e4d83db784d099cd232a7 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 18 Aug 2016 19:32:59 +0100 Subject: [PATCH 135/531] ASoC: core: Clean up DAPM before the card debugfs Both the card and DAPM cleanups recursively delete their debugfs directories. Since the DAPM debugfs subdirectory for the card is located within the card debugfs this means we end up trying to double free the DAPM subdirectory. Reorder the cleanup to free the card debugfs after we've cleaned up DAPM and it has deleted its own subdirectory. Reported-by: Russell King - ARM Linux Tested-by: Russell King Signed-off-by: Mark Brown --- sound/soc/soc-core.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 16369cad4803..66a33f1e4881 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -2083,14 +2083,13 @@ static int soc_cleanup_card_resources(struct snd_soc_card *card) /* remove auxiliary devices */ soc_remove_aux_devices(card); + snd_soc_dapm_free(&card->dapm); soc_cleanup_card_debugfs(card); /* remove the card */ if (card->remove) card->remove(card); - snd_soc_dapm_free(&card->dapm); - snd_card_free(card->snd_card); return 0; From 06777c4ec78a43977b63f1d5045def057227c2c5 Mon Sep 17 00:00:00 2001 From: Robert Jarzmik Date: Sun, 7 Aug 2016 21:01:49 +0200 Subject: [PATCH 136/531] dmaengine: pxa_dma: fix debug message In a very tight timeframe, the debug message in the transfer completion handler can be misleading, as the completion test report can change just after the message, and the code flow cannot be deduced from the debug message. This is just a cleanup to make debugging easier. Signed-off-by: Robert Jarzmik Signed-off-by: Vinod Koul --- drivers/dma/pxa_dma.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/dma/pxa_dma.c b/drivers/dma/pxa_dma.c index 2093e528ae00..3f56f9ca4482 100644 --- a/drivers/dma/pxa_dma.c +++ b/drivers/dma/pxa_dma.c @@ -671,6 +671,7 @@ static irqreturn_t pxad_chan_handler(int irq, void *dev_id) struct virt_dma_desc *vd, *tmp; unsigned int dcsr; unsigned long flags; + bool vd_completed; dma_cookie_t last_started = 0; BUG_ON(!chan); @@ -681,15 +682,17 @@ static irqreturn_t pxad_chan_handler(int irq, void *dev_id) spin_lock_irqsave(&chan->vc.lock, flags); list_for_each_entry_safe(vd, tmp, &chan->vc.desc_issued, node) { + vd_completed = is_desc_completed(vd); dev_dbg(&chan->vc.chan.dev->device, - "%s(): checking txd %p[%x]: completed=%d\n", - __func__, vd, vd->tx.cookie, is_desc_completed(vd)); + "%s(): checking txd %p[%x]: completed=%d dcsr=0x%x\n", + __func__, vd, vd->tx.cookie, vd_completed, + dcsr); last_started = vd->tx.cookie; if (to_pxad_sw_desc(vd)->cyclic) { vchan_cyclic_callback(vd); break; } - if (is_desc_completed(vd)) { + if (vd_completed) { list_del(&vd->node); vchan_cookie_complete(vd); } else { From 98096d8a787f05b1afe3869aa01e84981915c81d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 18 Aug 2016 11:16:35 -0700 Subject: [PATCH 137/531] nvme-fabrics: get a reference when reusing a nvme_host structure Without this we'll get a use after free after connecting two controller using the same hostnqn and then disconnecting one of them. Signed-off-by: Christoph Hellwig Reviewed-by: Jay Freyensee Signed-off-by: Sagi Grimberg --- drivers/nvme/host/fabrics.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index be0b1067c9fa..4eff49174466 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -47,8 +47,10 @@ static struct nvmf_host *nvmf_host_add(const char *hostnqn) mutex_lock(&nvmf_hosts_mutex); host = __nvmf_host_find(hostnqn); - if (host) + if (host) { + kref_get(&host->ref); goto out_unlock; + } host = kmalloc(sizeof(*host), GFP_KERNEL); if (!host) From aa71987472a974f4f6dc4be377720564079ef42e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 18 Aug 2016 11:16:36 -0700 Subject: [PATCH 138/531] nvme: fabrics drivers don't need the nvme-pci driver So select the NVME_CORE symbol instead of depending on BLK_DEV_NVME. Signed-off-by: Christoph Hellwig Reviewed-by: Jay Freyensee Signed-off-by: Sagi Grimberg --- drivers/nvme/host/Kconfig | 2 +- drivers/nvme/target/Kconfig | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig index db39d53cdfb9..0c644f7bdf80 100644 --- a/drivers/nvme/host/Kconfig +++ b/drivers/nvme/host/Kconfig @@ -31,7 +31,7 @@ config NVME_FABRICS config NVME_RDMA tristate "NVM Express over Fabrics RDMA host driver" depends on INFINIBAND - depends on BLK_DEV_NVME + select NVME_CORE select NVME_FABRICS select SG_POOL help diff --git a/drivers/nvme/target/Kconfig b/drivers/nvme/target/Kconfig index a5c31cbeb481..3a5b9d0576cb 100644 --- a/drivers/nvme/target/Kconfig +++ b/drivers/nvme/target/Kconfig @@ -15,8 +15,8 @@ config NVME_TARGET config NVME_TARGET_LOOP tristate "NVMe loopback device support" - depends on BLK_DEV_NVME depends on NVME_TARGET + select NVME_CORE select NVME_FABRICS select SG_POOL help From 2527ecc9195e9c66252af24c4689e8a67cd4ccb9 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 16 Aug 2016 09:58:25 +0200 Subject: [PATCH 139/531] gpio: Fix OF build problem on UM The UserMode (UM) Linux build was failing in gpiolib-of as it requires ioremap()/iounmap() to exist, which is absent from UM. The non-existence of IO memory is negatively defined as CONFIG_NO_IOMEM which means we need to depend on HAS_IOMEM. Cc: stable@vger.kernel.org Cc: Geert Uytterhoeven Reported-by: kbuild test robot Signed-off-by: Linus Walleij --- drivers/gpio/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 98dd47a30fc7..24f833c3d3ba 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -50,6 +50,7 @@ config GPIO_DEVRES config OF_GPIO def_bool y depends on OF + depends on HAS_IOMEM config GPIO_ACPI def_bool y From 048c28c91e56781082bc17d181e460b81e7e8bcb Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 16 Aug 2016 12:07:31 +0200 Subject: [PATCH 140/531] gpio: make any OF dependent driver depend on OF_GPIO The drivers that depend on OF but not OF_GPIO are wreaking havoc with the autobuilders for archs that have all requirements for OF but not for OF_GPIO, particularly the UM (Usermode) arch does not have iomem (NO_IOMEM) which result in configuring GPIOLIB but without OF_GPIO which is wrong if the driver is using the .of_node of the gpiochip, which only appears with OF_GPIO. After a brief look at the drivers just depending on OF it seems most if not all of them actually require stuff from gpiolib-of so the dependency is wrong in the first place. This simply patches the Kconfig so that all GPIO drivers using OF depend on OF_GPIO rather than just OF. Cc: Rabin Vincent Cc: Pramod Gurav Cc: Andreas Larsson Cc: Gregory CLEMENT Cc: Thierry Reding Cc: Laxman Dewangan Cc: Alexandre Courbot Cc: Geert Uytterhoeven Cc: Phil Reid Signed-off-by: Linus Walleij --- drivers/gpio/Kconfig | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 24f833c3d3ba..66a94103798b 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -189,7 +189,7 @@ config GPIO_EP93XX config GPIO_ETRAXFS bool "Axis ETRAX FS General I/O" depends on CRIS || COMPILE_TEST - depends on OF + depends on OF_GPIO select GPIO_GENERIC select GPIOLIB_IRQCHIP help @@ -215,7 +215,7 @@ config GPIO_GENERIC_PLATFORM config GPIO_GRGPIO tristate "Aeroflex Gaisler GRGPIO support" - depends on OF + depends on OF_GPIO select GPIO_GENERIC select IRQ_DOMAIN help @@ -313,7 +313,7 @@ config GPIO_MPC8XXX config GPIO_MVEBU def_bool y depends on PLAT_ORION - depends on OF + depends on OF_GPIO select GENERIC_IRQ_CHIP config GPIO_MXC @@ -406,7 +406,7 @@ config GPIO_TEGRA bool "NVIDIA Tegra GPIO support" default ARCH_TEGRA depends on ARCH_TEGRA || COMPILE_TEST - depends on OF + depends on OF_GPIO help Say yes here to support GPIO pins on NVIDIA Tegra SoCs. @@ -1100,7 +1100,7 @@ menu "SPI GPIO expanders" config GPIO_74X164 tristate "74x164 serial-in/parallel-out 8-bits shift register" - depends on OF + depends on OF_GPIO help Driver for 74x164 compatible serial-in/parallel-out 8-outputs shift registers. This driver can be used to provide access From a305a4387acb01cecadeeea5151c049a022a1bfc Mon Sep 17 00:00:00 2001 From: Brendan Jackman Date: Wed, 17 Aug 2016 16:14:59 +0100 Subject: [PATCH 141/531] thermal: cpu_cooling: Fix NULL dereference in cpufreq_state2power Currently all CPU cooling devices share a `struct thermal_cooling_device_ops` instance. The thermal core uses the presence of functions in this struct to determine if a cooling device has a power model (see cdev_is_power_actor). cpu_cooling.c adds the power model functions to the shared struct when a device is registered with a power model. Therefore, if a CPU cooling device is registered using [of_]cpufreq_power_cooling_register, _all_ devices will be determined to have a power model, including any registered with [of_]cpufreq_cooling_register. This can result in cpufreq_state2power being called on a device where dyn_power_table is NULL. With this commit, instead of having a shared thermal_cooling_device_ops which is mutated, we have two versions: one with the power functions and one without. Signed-off-by: Brendan Jackman Cc: Amit Daniel Kachhap Cc: Viresh Kumar Cc: Javi Merino Acked-by: Viresh Kumar Acked-by: Javi Merino Signed-off-by: Zhang Rui --- drivers/thermal/cpu_cooling.c | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index 3788ed74c9ab..a32b41783b77 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -740,12 +740,22 @@ static int cpufreq_power2state(struct thermal_cooling_device *cdev, } /* Bind cpufreq callbacks to thermal cooling device ops */ + static struct thermal_cooling_device_ops cpufreq_cooling_ops = { .get_max_state = cpufreq_get_max_state, .get_cur_state = cpufreq_get_cur_state, .set_cur_state = cpufreq_set_cur_state, }; +static struct thermal_cooling_device_ops cpufreq_power_cooling_ops = { + .get_max_state = cpufreq_get_max_state, + .get_cur_state = cpufreq_get_cur_state, + .set_cur_state = cpufreq_set_cur_state, + .get_requested_power = cpufreq_get_requested_power, + .state2power = cpufreq_state2power, + .power2state = cpufreq_power2state, +}; + /* Notifier for cpufreq policy change */ static struct notifier_block thermal_cpufreq_notifier_block = { .notifier_call = cpufreq_thermal_notifier, @@ -795,6 +805,7 @@ __cpufreq_cooling_register(struct device_node *np, struct cpumask temp_mask; unsigned int freq, i, num_cpus; int ret; + struct thermal_cooling_device_ops *cooling_ops; cpumask_and(&temp_mask, clip_cpus, cpu_online_mask); policy = cpufreq_cpu_get(cpumask_first(&temp_mask)); @@ -850,10 +861,6 @@ __cpufreq_cooling_register(struct device_node *np, cpumask_copy(&cpufreq_dev->allowed_cpus, clip_cpus); if (capacitance) { - cpufreq_cooling_ops.get_requested_power = - cpufreq_get_requested_power; - cpufreq_cooling_ops.state2power = cpufreq_state2power; - cpufreq_cooling_ops.power2state = cpufreq_power2state; cpufreq_dev->plat_get_static_power = plat_static_func; ret = build_dyn_power_table(cpufreq_dev, capacitance); @@ -861,6 +868,10 @@ __cpufreq_cooling_register(struct device_node *np, cool_dev = ERR_PTR(ret); goto free_table; } + + cooling_ops = &cpufreq_power_cooling_ops; + } else { + cooling_ops = &cpufreq_cooling_ops; } ret = get_idr(&cpufreq_idr, &cpufreq_dev->id); @@ -885,7 +896,7 @@ __cpufreq_cooling_register(struct device_node *np, cpufreq_dev->id); cool_dev = thermal_of_cooling_device_register(np, dev_name, cpufreq_dev, - &cpufreq_cooling_ops); + cooling_ops); if (IS_ERR(cool_dev)) goto remove_idr; From 57027db00d1094d0abd5776899b00ca55d42d37c Mon Sep 17 00:00:00 2001 From: Markus Elfring Date: Mon, 15 Aug 2016 11:22:40 +0200 Subject: [PATCH 142/531] Thermal-INT3406: Delete owner assignment The field "owner" is set by core. Thus delete an extra initialisation. Generated by: scripts/coccinelle/api/platform_no_drv_owner.cocci Signed-off-by: Markus Elfring Signed-off-by: Zhang Rui --- drivers/thermal/int340x_thermal/int3406_thermal.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/thermal/int340x_thermal/int3406_thermal.c b/drivers/thermal/int340x_thermal/int3406_thermal.c index a578cd257db4..1891f34ab7fc 100644 --- a/drivers/thermal/int340x_thermal/int3406_thermal.c +++ b/drivers/thermal/int340x_thermal/int3406_thermal.c @@ -225,7 +225,6 @@ static struct platform_driver int3406_thermal_driver = { .remove = int3406_thermal_remove, .driver = { .name = "int3406 thermal", - .owner = THIS_MODULE, .acpi_match_table = int3406_thermal_match, }, }; From 55f2ac33adc78d429c470c9ca05e18c36dc24922 Mon Sep 17 00:00:00 2001 From: Caesar Wang Date: Tue, 3 May 2016 20:07:41 +0800 Subject: [PATCH 143/531] thermal: trivial: fix the typo See the thermal code, the obvious typo from my editor. Signed-off-by: Caesar Wang Signed-off-by: Eduardo Valentin Signed-off-by: Zhang Rui --- Documentation/devicetree/bindings/thermal/thermal.txt | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/Documentation/devicetree/bindings/thermal/thermal.txt b/Documentation/devicetree/bindings/thermal/thermal.txt index 41b817f7b670..88b6ea1ad290 100644 --- a/Documentation/devicetree/bindings/thermal/thermal.txt +++ b/Documentation/devicetree/bindings/thermal/thermal.txt @@ -62,7 +62,7 @@ For more examples of cooling devices, refer to the example sections below. Required properties: - #cooling-cells: Used to provide cooling device specific information Type: unsigned while referring to it. Must be at least 2, in order - Size: one cell to specify minimum and maximum cooling state used + Size: one cell to specify minimum and maximum cooling state used in the reference. The first cell is the minimum cooling state requested and the second cell is the maximum cooling state requested in the reference. @@ -119,7 +119,7 @@ Required properties: Optional property: - contribution: The cooling contribution to the thermal zone of the Type: unsigned referred cooling device at the referred trip point. - Size: one cell The contribution is a ratio of the sum + Size: one cell The contribution is a ratio of the sum of all cooling contributions within a thermal zone. Note: Using the THERMAL_NO_LIMIT (-1UL) constant in the cooling-device phandle @@ -145,7 +145,7 @@ Required properties: Size: one cell - thermal-sensors: A list of thermal sensor phandles and sensor specifier - Type: list of used while monitoring the thermal zone. + Type: list of used while monitoring the thermal zone. phandles + sensor specifier @@ -473,7 +473,7 @@ thermal-zones { <&adc>; /* pcb north */ /* hotspot = 100 * bandgap - 120 * adc + 484 */ - coefficients = <100 -120 484>; + coefficients = <100 -120 484>; trips { ... @@ -502,7 +502,7 @@ from the ADC sensor. The binding would be then: thermal-sensors = <&adc>; /* hotspot = 1 * adc + 6000 */ - coefficients = <1 6000>; + coefficients = <1 6000>; (d) - Board thermal From 829bc78aa7628e81a9de717316b85cbee3c5eb86 Mon Sep 17 00:00:00 2001 From: Corentin LABBE Date: Tue, 16 Aug 2016 10:51:38 +0200 Subject: [PATCH 144/531] thermal: imx: fix a possible NULL dereference of_match_device could return NULL, and so cause a NULL pointer dereference later at line 472: data->socdata = of_id->data; For fixing this problem, we use of_device_get_match_data(), this will simplify the code a little by using a standard function for getting the match data. Reported-by: coverity (CID 1324128) Signed-off-by: LABBE Corentin Signed-off-by: Zhang Rui --- drivers/thermal/imx_thermal.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c index c5547bd711db..e473548b5d28 100644 --- a/drivers/thermal/imx_thermal.c +++ b/drivers/thermal/imx_thermal.c @@ -471,8 +471,6 @@ MODULE_DEVICE_TABLE(of, of_imx_thermal_match); static int imx_thermal_probe(struct platform_device *pdev) { - const struct of_device_id *of_id = - of_match_device(of_imx_thermal_match, &pdev->dev); struct imx_thermal_data *data; struct regmap *map; int measure_freq; @@ -490,7 +488,7 @@ static int imx_thermal_probe(struct platform_device *pdev) } data->tempmon = map; - data->socdata = of_id->data; + data->socdata = of_device_get_match_data(&pdev->dev); /* make sure the IRQ flag is clear before enabling irq on i.MX6SX */ if (data->socdata->version == TEMPMON_IMX6SX) { From 21eb45db282317543ca46c821bbb8d5075e02cbe Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Fri, 19 Aug 2016 09:34:24 +0300 Subject: [PATCH 145/531] ASoC: omap-abe-twl6040: Correct dmic-codec device registration The dmic-codec was registered within the platform_driver's probe function, which can cause deferred probe to run in loops as reported and analyzed by Russell King. Use module_init/exit in the driver and handle the dmic-codec device registration and removal at that level instead of the platform_driver probe/remove. Signed-off-by: Peter Ujfalusi Reported-by: Russell King Tested-by: Russell King Signed-off-by: Mark Brown --- sound/soc/omap/omap-abe-twl6040.c | 61 ++++++++++++++++--------------- 1 file changed, 32 insertions(+), 29 deletions(-) diff --git a/sound/soc/omap/omap-abe-twl6040.c b/sound/soc/omap/omap-abe-twl6040.c index 0843a68f277c..f61b3b58083b 100644 --- a/sound/soc/omap/omap-abe-twl6040.c +++ b/sound/soc/omap/omap-abe-twl6040.c @@ -38,10 +38,10 @@ struct abe_twl6040 { int jack_detection; /* board can detect jack events */ int mclk_freq; /* MCLK frequency speed for twl6040 */ - - struct platform_device *dmic_codec_dev; }; +struct platform_device *dmic_codec_dev; + static int omap_abe_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params) { @@ -258,8 +258,6 @@ static int omap_abe_probe(struct platform_device *pdev) if (priv == NULL) return -ENOMEM; - priv->dmic_codec_dev = ERR_PTR(-EINVAL); - if (snd_soc_of_parse_card_name(card, "ti,model")) { dev_err(&pdev->dev, "Card name is not provided\n"); return -ENODEV; @@ -284,13 +282,6 @@ static int omap_abe_probe(struct platform_device *pdev) num_links = 2; abe_twl6040_dai_links[1].cpu_of_node = dai_node; abe_twl6040_dai_links[1].platform_of_node = dai_node; - - priv->dmic_codec_dev = platform_device_register_simple( - "dmic-codec", -1, NULL, 0); - if (IS_ERR(priv->dmic_codec_dev)) { - dev_err(&pdev->dev, "Can't instantiate dmic-codec\n"); - return PTR_ERR(priv->dmic_codec_dev); - } } else { num_links = 1; } @@ -299,16 +290,14 @@ static int omap_abe_probe(struct platform_device *pdev) of_property_read_u32(node, "ti,mclk-freq", &priv->mclk_freq); if (!priv->mclk_freq) { dev_err(&pdev->dev, "MCLK frequency not provided\n"); - ret = -EINVAL; - goto err_unregister; + return -EINVAL; } card->fully_routed = 1; if (!priv->mclk_freq) { dev_err(&pdev->dev, "MCLK frequency missing\n"); - ret = -ENODEV; - goto err_unregister; + return -ENODEV; } card->dai_link = abe_twl6040_dai_links; @@ -317,17 +306,9 @@ static int omap_abe_probe(struct platform_device *pdev) snd_soc_card_set_drvdata(card, priv); ret = snd_soc_register_card(card); - if (ret) { + if (ret) dev_err(&pdev->dev, "snd_soc_register_card() failed: %d\n", ret); - goto err_unregister; - } - - return 0; - -err_unregister: - if (!IS_ERR(priv->dmic_codec_dev)) - platform_device_unregister(priv->dmic_codec_dev); return ret; } @@ -335,13 +316,9 @@ static int omap_abe_probe(struct platform_device *pdev) static int omap_abe_remove(struct platform_device *pdev) { struct snd_soc_card *card = platform_get_drvdata(pdev); - struct abe_twl6040 *priv = snd_soc_card_get_drvdata(card); snd_soc_unregister_card(card); - if (!IS_ERR(priv->dmic_codec_dev)) - platform_device_unregister(priv->dmic_codec_dev); - return 0; } @@ -361,7 +338,33 @@ static struct platform_driver omap_abe_driver = { .remove = omap_abe_remove, }; -module_platform_driver(omap_abe_driver); +static int __init omap_abe_init(void) +{ + int ret; + + dmic_codec_dev = platform_device_register_simple("dmic-codec", -1, NULL, + 0); + if (IS_ERR(dmic_codec_dev)) { + pr_err("%s: dmic-codec device registration failed\n", __func__); + return PTR_ERR(dmic_codec_dev); + } + + ret = platform_driver_register(&omap_abe_driver); + if (ret) { + pr_err("%s: platform driver registration failed\n", __func__); + platform_device_unregister(dmic_codec_dev); + } + + return ret; +} +module_init(omap_abe_init); + +static void __exit omap_abe_exit(void) +{ + platform_driver_unregister(&omap_abe_driver); + platform_device_unregister(dmic_codec_dev); +} +module_exit(omap_abe_exit); MODULE_AUTHOR("Misael Lopez Cruz "); MODULE_DESCRIPTION("ALSA SoC for OMAP boards with ABE and twl6040 codec"); From ba913e4f72fc9cfd03dad968dfb110eb49211d80 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Fri, 19 Aug 2016 14:30:29 +0100 Subject: [PATCH 146/531] MIPS: KVM: Check for pfn noslot case MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When mapping a page into the guest we error check using is_error_pfn(), however this doesn't detect a value of KVM_PFN_NOSLOT, indicating an error HVA for the page. This can only happen on MIPS right now due to unusual memslot management (e.g. being moved / removed / resized), or with an Enhanced Virtual Memory (EVA) configuration where the default KVM_HVA_ERR_* and kvm_is_error_hva() definitions are unsuitable (fixed in a later patch). This case will be treated as a pfn of zero, mapping the first page of physical memory into the guest. It would appear the MIPS KVM port wasn't updated prior to being merged (in v3.10) to take commit 81c52c56e2b4 ("KVM: do not treat noslot pfn as a error pfn") into account (merged v3.8), which converted a bunch of is_error_pfn() calls to is_error_noslot_pfn(). Switch to using is_error_noslot_pfn() instead to catch this case properly. Fixes: 858dd5d45733 ("KVM/MIPS32: MMU/TLB operations for the Guest.") Signed-off-by: James Hogan Cc: Paolo Bonzini Cc: Radim Krčmář Cc: Ralf Baechle Cc: linux-mips@linux-mips.org Cc: kvm@vger.kernel.org Cc: # 3.10.y- Signed-off-by: Paolo Bonzini --- arch/mips/kvm/mmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c index 6cfdcf55572d..121008c0fcc9 100644 --- a/arch/mips/kvm/mmu.c +++ b/arch/mips/kvm/mmu.c @@ -40,7 +40,7 @@ static int kvm_mips_map_page(struct kvm *kvm, gfn_t gfn) srcu_idx = srcu_read_lock(&kvm->srcu); pfn = gfn_to_pfn(kvm, gfn); - if (is_error_pfn(pfn)) { + if (is_error_noslot_pfn(pfn)) { kvm_err("Couldn't get pfn for gfn %#llx!\n", gfn); err = -EFAULT; goto out; From 13f479b9df4e2bbf2d16e7e1b02f3f55f70e2455 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Wed, 17 Aug 2016 09:46:42 +0200 Subject: [PATCH 147/531] drm/radeon: fix radeon_move_blit on 32bit systems MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This bug seems to be present for a very long time. Signed-off-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/radeon/radeon_ttm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index 0c00e192c845..c2e0a1ccdfbc 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -263,8 +263,8 @@ static int radeon_move_blit(struct ttm_buffer_object *bo, rdev = radeon_get_rdev(bo->bdev); ridx = radeon_copy_ring_index(rdev); - old_start = old_mem->start << PAGE_SHIFT; - new_start = new_mem->start << PAGE_SHIFT; + old_start = (u64)old_mem->start << PAGE_SHIFT; + new_start = (u64)new_mem->start << PAGE_SHIFT; switch (old_mem->mem_type) { case TTM_PL_VRAM: From 815d27a46f3119f74fe01fe10bf683aa5bc55597 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Wed, 17 Aug 2016 09:45:25 +0200 Subject: [PATCH 148/531] drm/amdgpu: fix amdgpu_move_blit on 32bit systems MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This bug seems to be present for a very long time. Signed-off-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 9b61c8ba7aaf..141bfcabd19c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -251,8 +251,8 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo, adev = amdgpu_get_adev(bo->bdev); ring = adev->mman.buffer_funcs_ring; - old_start = old_mem->start << PAGE_SHIFT; - new_start = new_mem->start << PAGE_SHIFT; + old_start = (u64)old_mem->start << PAGE_SHIFT; + new_start = (u64)new_mem->start << PAGE_SHIFT; switch (old_mem->mem_type) { case TTM_PL_VRAM: From 847927bb3db2b18744ddec1b4fbb274ac7e05199 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Wed, 17 Aug 2016 14:10:37 +0200 Subject: [PATCH 149/531] drm/amdgpu: fix sdma_v2_4_ring_test_ib MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Typo in checking the return code. Signed-off-by: Christian König Reviewed-by: Alex Deucher Reviewed-by: Chunming Zhou Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c index 1351c7e834a2..a64715d90503 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c @@ -714,7 +714,7 @@ static int sdma_v2_4_ring_test_ib(struct amdgpu_ring *ring, long timeout) DRM_ERROR("amdgpu: IB test timed out\n"); r = -ETIMEDOUT; goto err1; - } else if (r) { + } else if (r < 0) { DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r); goto err1; } From bdf001374bfe12677ae6ec5076452493fb682012 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Tue, 16 Aug 2016 19:52:35 +0200 Subject: [PATCH 150/531] drm/amdgpu: fix timeout value check in amd_sched_job_recovery MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Could be that we don't actually have a timeout set. Signed-off-by: Christian König Acked-by: Alex Deucher Reviewed-by: Chunming Zhou Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/scheduler/gpu_scheduler.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c index ef312bb75fda..963a24d46a93 100644 --- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c @@ -405,7 +405,7 @@ void amd_sched_job_recovery(struct amd_gpu_scheduler *sched) spin_lock(&sched->job_list_lock); s_job = list_first_entry_or_null(&sched->ring_mirror_list, struct amd_sched_job, node); - if (s_job) + if (s_job && sched->timeout != MAX_SCHEDULE_TIMEOUT) schedule_delayed_work(&s_job->work_tdr, sched->timeout); list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) { From 6c647b0eb01cd7326dca093590f5e123e3c68b9c Mon Sep 17 00:00:00 2001 From: Bob Liu Date: Fri, 1 Jul 2016 15:45:57 -0400 Subject: [PATCH 151/531] xen-blkfront: fix places not updated after introducing 64KB page granularity MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Two places didn't get updated when 64KB page granularity was introduced, this patch fix them. Signed-off-by: Bob Liu Acked-by: Roger Pau Monné Signed-off-by: Konrad Rzeszutek Wilk --- drivers/block/xen-blkfront.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index be4fea6a5dd3..6a1756d72dcb 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -1315,7 +1315,7 @@ static void blkif_free_ring(struct blkfront_ring_info *rinfo) rinfo->ring_ref[i] = GRANT_INVALID_REF; } } - free_pages((unsigned long)rinfo->ring.sring, get_order(info->nr_ring_pages * PAGE_SIZE)); + free_pages((unsigned long)rinfo->ring.sring, get_order(info->nr_ring_pages * XEN_PAGE_SIZE)); rinfo->ring.sring = NULL; if (rinfo->irq) @@ -2008,7 +2008,7 @@ static int blkif_recover(struct blkfront_info *info) blkfront_gather_backend_features(info); segs = info->max_indirect_segments ? : BLKIF_MAX_SEGMENTS_PER_REQUEST; - blk_queue_max_segments(info->rq, segs); + blk_queue_max_segments(info->rq, segs / GRANTS_PER_PSEG); for (r_index = 0; r_index < info->nr_rings; r_index++) { struct blkfront_ring_info *rinfo = &info->rinfo[r_index]; From 172335ada40ce26806e514c83a504b45c14a4139 Mon Sep 17 00:00:00 2001 From: Bob Liu Date: Fri, 1 Jul 2016 17:43:39 -0400 Subject: [PATCH 152/531] xen-blkfront: introduce blkif_set_queue_limits() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit blk_mq_update_nr_hw_queues() reset all queue limits to default which it's not as xen-blkfront expected, introducing blkif_set_queue_limits() to reset limits with initial correct values. Signed-off-by: Bob Liu Acked-by: Roger Pau Monné Signed-off-by: Konrad Rzeszutek Wilk --- drivers/block/xen-blkfront.c | 86 ++++++++++++++++++++---------------- 1 file changed, 48 insertions(+), 38 deletions(-) diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 6a1756d72dcb..f84e220a26e6 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -189,6 +189,8 @@ struct blkfront_info struct mutex mutex; struct xenbus_device *xbdev; struct gendisk *gd; + u16 sector_size; + unsigned int physical_sector_size; int vdevice; blkif_vdev_t handle; enum blkif_state connected; @@ -910,9 +912,45 @@ static struct blk_mq_ops blkfront_mq_ops = { .map_queue = blk_mq_map_queue, }; +static void blkif_set_queue_limits(struct blkfront_info *info) +{ + struct request_queue *rq = info->rq; + struct gendisk *gd = info->gd; + unsigned int segments = info->max_indirect_segments ? : + BLKIF_MAX_SEGMENTS_PER_REQUEST; + + queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq); + + if (info->feature_discard) { + queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, rq); + blk_queue_max_discard_sectors(rq, get_capacity(gd)); + rq->limits.discard_granularity = info->discard_granularity; + rq->limits.discard_alignment = info->discard_alignment; + if (info->feature_secdiscard) + queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, rq); + } + + /* Hard sector size and max sectors impersonate the equiv. hardware. */ + blk_queue_logical_block_size(rq, info->sector_size); + blk_queue_physical_block_size(rq, info->physical_sector_size); + blk_queue_max_hw_sectors(rq, (segments * XEN_PAGE_SIZE) / 512); + + /* Each segment in a request is up to an aligned page in size. */ + blk_queue_segment_boundary(rq, PAGE_SIZE - 1); + blk_queue_max_segment_size(rq, PAGE_SIZE); + + /* Ensure a merged request will fit in a single I/O ring slot. */ + blk_queue_max_segments(rq, segments / GRANTS_PER_PSEG); + + /* Make sure buffer addresses are sector-aligned. */ + blk_queue_dma_alignment(rq, 511); + + /* Make sure we don't use bounce buffers. */ + blk_queue_bounce_limit(rq, BLK_BOUNCE_ANY); +} + static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size, - unsigned int physical_sector_size, - unsigned int segments) + unsigned int physical_sector_size) { struct request_queue *rq; struct blkfront_info *info = gd->private_data; @@ -944,36 +982,11 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size, } rq->queuedata = info; - queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq); - - if (info->feature_discard) { - queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, rq); - blk_queue_max_discard_sectors(rq, get_capacity(gd)); - rq->limits.discard_granularity = info->discard_granularity; - rq->limits.discard_alignment = info->discard_alignment; - if (info->feature_secdiscard) - queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, rq); - } - - /* Hard sector size and max sectors impersonate the equiv. hardware. */ - blk_queue_logical_block_size(rq, sector_size); - blk_queue_physical_block_size(rq, physical_sector_size); - blk_queue_max_hw_sectors(rq, (segments * XEN_PAGE_SIZE) / 512); - - /* Each segment in a request is up to an aligned page in size. */ - blk_queue_segment_boundary(rq, PAGE_SIZE - 1); - blk_queue_max_segment_size(rq, PAGE_SIZE); - - /* Ensure a merged request will fit in a single I/O ring slot. */ - blk_queue_max_segments(rq, segments / GRANTS_PER_PSEG); - - /* Make sure buffer addresses are sector-aligned. */ - blk_queue_dma_alignment(rq, 511); - - /* Make sure we don't use bounce buffers. */ - blk_queue_bounce_limit(rq, BLK_BOUNCE_ANY); - - gd->queue = rq; + info->rq = gd->queue = rq; + info->gd = gd; + info->sector_size = sector_size; + info->physical_sector_size = physical_sector_size; + blkif_set_queue_limits(info); return 0; } @@ -1136,16 +1149,11 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity, gd->private_data = info; set_capacity(gd, capacity); - if (xlvbd_init_blk_queue(gd, sector_size, physical_sector_size, - info->max_indirect_segments ? : - BLKIF_MAX_SEGMENTS_PER_REQUEST)) { + if (xlvbd_init_blk_queue(gd, sector_size, physical_sector_size)) { del_gendisk(gd); goto release; } - info->rq = gd->queue; - info->gd = gd; - xlvbd_flush(info); if (vdisk_info & VDISK_READONLY) @@ -2007,6 +2015,8 @@ static int blkif_recover(struct blkfront_info *info) struct split_bio *split_bio; blkfront_gather_backend_features(info); + /* Reset limits changed by blk_mq_update_nr_hw_queues(). */ + blkif_set_queue_limits(info); segs = info->max_indirect_segments ? : BLKIF_MAX_SEGMENTS_PER_REQUEST; blk_queue_max_segments(info->rq, segs / GRANTS_PER_PSEG); From 4e876c2bd37fbb5c37a4554a79cf979d486f0e82 Mon Sep 17 00:00:00 2001 From: Bob Liu Date: Wed, 27 Jul 2016 17:42:04 +0800 Subject: [PATCH 153/531] xen-blkfront: free resources if xlvbd_alloc_gendisk fails Current code forgets to free resources in the failure path of xlvbd_alloc_gendisk(), this patch fix it. Signed-off-by: Bob Liu Signed-off-by: Konrad Rzeszutek Wilk --- drivers/block/xen-blkfront.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index f84e220a26e6..88ef6d4729b4 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -2442,7 +2442,7 @@ static void blkfront_connect(struct blkfront_info *info) if (err) { xenbus_dev_fatal(info->xbdev, err, "xlvbd_add at %s", info->xbdev->otherend); - return; + goto fail; } xenbus_switch_state(info->xbdev, XenbusStateConnected); @@ -2455,6 +2455,11 @@ static void blkfront_connect(struct blkfront_info *info) device_add_disk(&info->xbdev->dev, info->gd); info->is_ready = 1; + return; + +fail: + blkif_free(info, 0); + return; } /** From 47af45d684b5f3ae000ad448db02ce4f13f73273 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Tue, 16 Aug 2016 17:38:54 -0700 Subject: [PATCH 154/531] Input: i8042 - set up shared ps2_cmd_mutex for AUX ports The commit 4097461897df ("Input: i8042 - break load dependency ...") correctly set up ps2_cmd_mutex pointer for the KBD port but forgot to do the same for AUX port(s), which results in communication on KBD and AUX ports to clash with each other. Fixes: 4097461897df ("Input: i8042 - break load dependency ...") Reported-by: Bruno Wolff III Tested-by: Bruno Wolff III Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov --- drivers/input/serio/i8042.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c index b4d34086e73f..405252a884dd 100644 --- a/drivers/input/serio/i8042.c +++ b/drivers/input/serio/i8042.c @@ -1305,6 +1305,7 @@ static int __init i8042_create_aux_port(int idx) serio->write = i8042_aux_write; serio->start = i8042_start; serio->stop = i8042_stop; + serio->ps2_cmd_mutex = &i8042_mutex; serio->port_data = port; serio->dev.parent = &i8042_platform_device->dev; if (idx < 0) { From 86147e3cfa5e118b61e78f4f0bf29e920dcbd477 Mon Sep 17 00:00:00 2001 From: Liav Rehana Date: Tue, 16 Aug 2016 10:55:35 +0300 Subject: [PATCH 155/531] ARC: use correct offset in pt_regs for saving/restoring user mode r25 User mode callee regs are explicitly collected before signal delivery or breakpoint trap. r25 is special for kernel as it serves as task pointer, so user mode value is clobbered very early. It is saved in pt_regs where generally only scratch (aka caller saved) regs are saved. The code to access the corresponding pt_regs location had a subtle bug as it was using load/store with scaling of offset, whereas the offset was already byte wise correct. So fix this by replacing LD.AS with a standard LD Cc: Signed-off-by: Liav Rehana Reviewed-by: Alexey Brodkin [vgupta: rewrote title and commit log] Signed-off-by: Vineet Gupta --- arch/arc/include/asm/entry.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h index ad7860c5ce15..51597f344a62 100644 --- a/arch/arc/include/asm/entry.h +++ b/arch/arc/include/asm/entry.h @@ -142,7 +142,7 @@ #ifdef CONFIG_ARC_CURR_IN_REG ; Retrieve orig r25 and save it with rest of callee_regs - ld.as r12, [r12, PT_user_r25] + ld r12, [r12, PT_user_r25] PUSH r12 #else PUSH r25 @@ -198,7 +198,7 @@ ; SP is back to start of pt_regs #ifdef CONFIG_ARC_CURR_IN_REG - st.as r12, [sp, PT_user_r25] + st r12, [sp, PT_user_r25] #endif .endm From 840c054fd0efb048df6fceb0c46385ec5b66dfe6 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Wed, 10 Aug 2016 14:10:57 -0700 Subject: [PATCH 156/531] ARC: Support syscall ABI v4 The syscall ABI includes the gcc functional calling ABI since a syscall implies userland caller and kernel callee. The current gcc ABI (v3) for ARCv2 ISA required 64-bit data be passed in even-odd register pairs, (potentially punching reg holes when passing such values as args). This was partly driven by the fact that the double-word LDD/STD instructions in ARCv2 expect the register alignment and thus gcc forcing this avoids extra MOV at the cost of a few unused register (which we have plenty anyways). This however was rejected as part of upstreaming gcc port to HS. So the new ABI v4 doesn't enforce the even-odd reg restriction. Do note that for ARCompact ISA builds v3 and v4 are practically the same in terms of gcc code generation. In terms of change management, we infer the new ABI if gcc 6.x onwards is used for building the kernel. This also needs a stable backport to enable older kernels to work with new tools/user-space Cc: Signed-off-by: Vineet Gupta --- arch/arc/include/uapi/asm/elf.h | 11 +++++++++-- arch/arc/kernel/process.c | 2 +- arch/arc/kernel/setup.c | 6 ++++-- 3 files changed, 14 insertions(+), 5 deletions(-) diff --git a/arch/arc/include/uapi/asm/elf.h b/arch/arc/include/uapi/asm/elf.h index 0f99ac8fcbb2..0037a587320d 100644 --- a/arch/arc/include/uapi/asm/elf.h +++ b/arch/arc/include/uapi/asm/elf.h @@ -13,8 +13,15 @@ /* Machine specific ELF Hdr flags */ #define EF_ARC_OSABI_MSK 0x00000f00 -#define EF_ARC_OSABI_ORIG 0x00000000 /* MUST be zero for back-compat */ -#define EF_ARC_OSABI_CURRENT 0x00000300 /* v3 (no legacy syscalls) */ + +#define EF_ARC_OSABI_V3 0x00000300 /* v3 (no legacy syscalls) */ +#define EF_ARC_OSABI_V4 0x00000400 /* v4 (64bit data any reg align) */ + +#if __GNUC__ < 6 +#define EF_ARC_OSABI_CURRENT EF_ARC_OSABI_V3 +#else +#define EF_ARC_OSABI_CURRENT EF_ARC_OSABI_V4 +#endif typedef unsigned long elf_greg_t; typedef unsigned long elf_fpregset_t; diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c index b5db9e7fd649..be1972bd2729 100644 --- a/arch/arc/kernel/process.c +++ b/arch/arc/kernel/process.c @@ -199,7 +199,7 @@ int elf_check_arch(const struct elf32_hdr *x) } eflags = x->e_flags; - if ((eflags & EF_ARC_OSABI_MSK) < EF_ARC_OSABI_CURRENT) { + if ((eflags & EF_ARC_OSABI_MSK) != EF_ARC_OSABI_CURRENT) { pr_err("ABI mismatch - you need newer toolchain\n"); force_sigsegv(SIGSEGV, current); return 0; diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index a946400a86d0..f52a0d0dc462 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -291,8 +291,10 @@ static char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len) cpu->dccm.base_addr, TO_KB(cpu->dccm.sz), cpu->iccm.base_addr, TO_KB(cpu->iccm.sz)); - n += scnprintf(buf + n, len - n, - "OS ABI [v3]\t: no-legacy-syscalls\n"); + n += scnprintf(buf + n, len - n, "OS ABI [v%d]\t: %s\n", + EF_ARC_OSABI_CURRENT >> 8, + EF_ARC_OSABI_CURRENT == EF_ARC_OSABI_V3 ? + "no-legacy-syscalls" : "64-bit data any register aligned"); return buf; } From d77976c414ed7f521b9c79b2a9dde0147a3cf754 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Wed, 17 Aug 2016 17:34:46 -0700 Subject: [PATCH 157/531] ARC: export kmap | MODPOST 7 modules | ERROR: "kmap" [fs/ext2/ext2.ko] undefined! | ../scripts/Makefile.modpost:91: recipe for target '__modpost' failed Cc: Signed-off-by: Vineet Gupta --- arch/arc/mm/highmem.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arc/mm/highmem.c b/arch/arc/mm/highmem.c index 04f83322c9fd..77ff64a874a1 100644 --- a/arch/arc/mm/highmem.c +++ b/arch/arc/mm/highmem.c @@ -61,6 +61,7 @@ void *kmap(struct page *page) return kmap_high(page); } +EXPORT_SYMBOL(kmap); void *kmap_atomic(struct page *page) { From 1c3c909303924d30145601f47b6c058fdd2cbc2e Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Tue, 16 Aug 2016 18:27:07 -0700 Subject: [PATCH 158/531] ARC: mm: fix build breakage with STRICT_MM_TYPECHECKS MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit | CC mm/memory.o | In file included from ../mm/memory.c:53:0: | ../include/linux/pfn_t.h: In function ‘pfn_t_pte’: | ../include/linux/pfn_t.h:78:2: error: conversion to non-scalar type requested | return pfn_pte(pfn_t_to_pfn(pfn), pgprot); With STRICT_MM_TYPECHECKS pte_t is a struct and the offending code forces a cast which ends up shifting a struct and hence the gcc warning. Note that in recent past some of the arches (aarch64, s390) made STRICT_MM_TYPECHECKS default, but we don't for ARC as this leads to slightly worse generated code, given ARC ABI definition of returning structs (which pte_t would become) Quoting from ARC ABI... "Results of type struct are returned in a caller-supplied temporary variable whose address is passed in r0. For such functions, the arguments are shifted so that they are passed in r1 and up." So - struct to be returned would be allocated on stack requiring extra code at call sites - callee updates stack memory to facilitate the return (vs. simple MOV into return reg r0) Hence STRICT_MM_TYPECHECKS is not enabled by default for ARC Cc: #4.4+ Signed-off-by: Vineet Gupta --- arch/arc/include/asm/pgtable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index 0f92d97432a2..89eeb3720051 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -280,7 +280,7 @@ static inline void pmd_set(pmd_t *pmdp, pte_t *ptep) #define pte_page(pte) pfn_to_page(pte_pfn(pte)) #define mk_pte(page, prot) pfn_pte(page_to_pfn(page), prot) -#define pfn_pte(pfn, prot) (__pte(((pte_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))) +#define pfn_pte(pfn, prot) __pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot)) /* Don't use virt_to_pfn for macros below: could cause truncations for PAE40*/ #define pte_pfn(pte) (pte_val(pte) >> PAGE_SHIFT) From 9a0fe86745b8e95f7ea39933a956f5771332c430 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 19 Aug 2016 15:33:12 -0400 Subject: [PATCH 159/531] pNFS: Handle NFS4ERR_OLD_STATEID correctly in LAYOUTSTAT calls We normally want to update the stateid and then retry, Signed-off-by: Trond Myklebust --- fs/nfs/nfs42proc.c | 34 +++++++++++++++++++++++++++++----- fs/nfs/pnfs.c | 1 - 2 files changed, 29 insertions(+), 6 deletions(-) diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 6f4752734804..64b43b4ad9dd 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -318,10 +318,22 @@ static void nfs42_layoutstat_prepare(struct rpc_task *task, void *calldata) { struct nfs42_layoutstat_data *data = calldata; - struct nfs_server *server = NFS_SERVER(data->args.inode); + struct inode *inode = data->inode; + struct nfs_server *server = NFS_SERVER(inode); + struct pnfs_layout_hdr *lo; + spin_lock(&inode->i_lock); + lo = NFS_I(inode)->layout; + if (!pnfs_layout_is_valid(lo)) { + spin_unlock(&inode->i_lock); + rpc_exit(task, 0); + return; + } + nfs4_stateid_copy(&data->args.stateid, &lo->plh_stateid); + spin_unlock(&inode->i_lock); nfs41_setup_sequence(nfs4_get_session(server), &data->args.seq_args, &data->res.seq_res, task); + } static void @@ -341,11 +353,11 @@ nfs42_layoutstat_done(struct rpc_task *task, void *calldata) case -NFS4ERR_ADMIN_REVOKED: case -NFS4ERR_DELEG_REVOKED: case -NFS4ERR_STALE_STATEID: - case -NFS4ERR_OLD_STATEID: case -NFS4ERR_BAD_STATEID: spin_lock(&inode->i_lock); lo = NFS_I(inode)->layout; - if (lo && nfs4_stateid_match(&data->args.stateid, + if (pnfs_layout_is_valid(lo) && + nfs4_stateid_match(&data->args.stateid, &lo->plh_stateid)) { LIST_HEAD(head); @@ -359,11 +371,23 @@ nfs42_layoutstat_done(struct rpc_task *task, void *calldata) } else spin_unlock(&inode->i_lock); break; + case -NFS4ERR_OLD_STATEID: + spin_lock(&inode->i_lock); + lo = NFS_I(inode)->layout; + if (pnfs_layout_is_valid(lo) && + nfs4_stateid_match_other(&data->args.stateid, + &lo->plh_stateid)) { + /* Do we need to delay before resending? */ + if (!nfs4_stateid_is_newer(&lo->plh_stateid, + &data->args.stateid)) + rpc_delay(task, HZ); + rpc_restart_call_prepare(task); + } + spin_unlock(&inode->i_lock); + break; case -ENOTSUPP: case -EOPNOTSUPP: NFS_SERVER(inode)->caps &= ~NFS_CAP_LAYOUTSTATS; - default: - break; } dprintk("%s server returns %d\n", __func__, task->tk_status); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 70806cae0d36..bf98f1b2595f 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -2510,7 +2510,6 @@ pnfs_report_layoutstat(struct inode *inode, gfp_t gfp_flags) data->args.fh = NFS_FH(inode); data->args.inode = inode; - nfs4_stateid_copy(&data->args.stateid, &hdr->plh_stateid); status = ld->prepare_layoutstats(&data->args); if (status) goto out_free; From c57653dc94d0db7bf63067433ceaa97bdcd0a312 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Fri, 19 Aug 2016 13:59:02 -0700 Subject: [PATCH 160/531] ARC: export __udivdi3 for modules Some module using div_u64() was failing to link because the libgcc 64-bit divide assist routine was not being exported for modules Reported-by: avinashp@quantenna.com Cc: stable@vger.kernel.org Signed-off-by: Vineet Gupta --- arch/arc/kernel/arcksyms.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arc/kernel/arcksyms.c b/arch/arc/kernel/arcksyms.c index 4d9e77724bed..000dd041ab42 100644 --- a/arch/arc/kernel/arcksyms.c +++ b/arch/arc/kernel/arcksyms.c @@ -28,6 +28,7 @@ extern void __muldf3(void); extern void __divdf3(void); extern void __floatunsidf(void); extern void __floatunsisf(void); +extern void __udivdi3(void); EXPORT_SYMBOL(__ashldi3); EXPORT_SYMBOL(__ashrdi3); @@ -45,6 +46,7 @@ EXPORT_SYMBOL(__muldf3); EXPORT_SYMBOL(__divdf3); EXPORT_SYMBOL(__floatunsidf); EXPORT_SYMBOL(__floatunsisf); +EXPORT_SYMBOL(__udivdi3); /* ARC optimised assembler routines */ EXPORT_SYMBOL(memset); From 13f9bba7cd4f1665e4091143950a54e3f2984b07 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Thu, 18 Aug 2016 21:09:02 +0300 Subject: [PATCH 161/531] net/mlx5e: Set port MTU on netdev creation rather on open Port mtu shouldn't be written to hardware on every single interface open. Here we set it only when needed, on change_mtu and netdevice creation. Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 870bea37c57c..0fc3a2b16a18 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1826,10 +1826,6 @@ int mlx5e_open_locked(struct net_device *netdev) netif_set_real_num_tx_queues(netdev, num_txqs); netif_set_real_num_rx_queues(netdev, priv->params.num_channels); - err = mlx5e_set_dev_port_mtu(netdev); - if (err) - goto err_clear_state_opened_flag; - err = mlx5e_open_channels(priv); if (err) { netdev_err(netdev, "%s: mlx5e_open_channels failed, %d\n", @@ -2593,6 +2589,7 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu) mlx5e_close_locked(netdev); netdev->mtu = new_mtu; + mlx5e_set_dev_port_mtu(netdev); if (was_opened) err = mlx5e_open_locked(netdev); @@ -3463,6 +3460,8 @@ void *mlx5e_create_netdev(struct mlx5_core_dev *mdev, mlx5e_init_l2_addr(priv); + mlx5e_set_dev_port_mtu(netdev); + err = register_netdev(netdev); if (err) { mlx5_core_err(mdev, "register_netdev failed, %d\n", err); From 506753b0b40997756d73f841c884a018f52401a0 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Thu, 18 Aug 2016 21:09:03 +0300 Subject: [PATCH 162/531] net/mlx5e: Optimization for MTU change Avoid unnecessary interface down/up operations upon an MTU change when it does not affect the rings configuration. Fixes: 461017cb006a ("net/mlx5e: Support RX multi-packet WQE (Striding RQ)") Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 0fc3a2b16a18..65258b259579 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2569,6 +2569,7 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu) u16 max_mtu; u16 min_mtu; int err = 0; + bool reset; mlx5_query_port_max_mtu(mdev, &max_mtu, 1); @@ -2584,14 +2585,18 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu) mutex_lock(&priv->state_lock); + reset = !priv->params.lro_en && + (priv->params.rq_wq_type != + MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ); + was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state); - if (was_opened) + if (was_opened && reset) mlx5e_close_locked(netdev); netdev->mtu = new_mtu; mlx5e_set_dev_port_mtu(netdev); - if (was_opened) + if (was_opened && reset) err = mlx5e_open_locked(netdev); mutex_unlock(&priv->state_lock); From 1061c90f524963a0a90e7d2f9a6bfa666458af51 Mon Sep 17 00:00:00 2001 From: Mohamad Haj Yahia Date: Thu, 18 Aug 2016 21:09:04 +0300 Subject: [PATCH 163/531] net/mlx5: Fix pci error recovery flow When PCI error is detected we should save the state of the pci prior to disabling it. Also when receiving pci slot reset call we need to verify that the device is responsive. Fixes: 89d44f0a6c73 ('net/mlx5_core: Add pci error handlers to mlx5_core driver') Signed-off-by: Mohamad Haj Yahia Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlx5/core/main.c | 63 +++++++++---------- 1 file changed, 31 insertions(+), 32 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 4f491d43e77d..2385bae92672 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1420,36 +1420,12 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev, dev_info(&pdev->dev, "%s was called\n", __func__); mlx5_enter_error_state(dev); mlx5_unload_one(dev, priv); + pci_save_state(pdev); mlx5_pci_disable_device(dev); return state == pci_channel_io_perm_failure ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET; } -static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev) -{ - struct mlx5_core_dev *dev = pci_get_drvdata(pdev); - int err = 0; - - dev_info(&pdev->dev, "%s was called\n", __func__); - - err = mlx5_pci_enable_device(dev); - if (err) { - dev_err(&pdev->dev, "%s: mlx5_pci_enable_device failed with error code: %d\n" - , __func__, err); - return PCI_ERS_RESULT_DISCONNECT; - } - pci_set_master(pdev); - pci_set_power_state(pdev, PCI_D0); - pci_restore_state(pdev); - - return err ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED; -} - -void mlx5_disable_device(struct mlx5_core_dev *dev) -{ - mlx5_pci_err_detected(dev->pdev, 0); -} - /* wait for the device to show vital signs by waiting * for the health counter to start counting. */ @@ -1477,6 +1453,36 @@ static int wait_vital(struct pci_dev *pdev) return -ETIMEDOUT; } +static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev) +{ + struct mlx5_core_dev *dev = pci_get_drvdata(pdev); + int err; + + dev_info(&pdev->dev, "%s was called\n", __func__); + + err = mlx5_pci_enable_device(dev); + if (err) { + dev_err(&pdev->dev, "%s: mlx5_pci_enable_device failed with error code: %d\n" + , __func__, err); + return PCI_ERS_RESULT_DISCONNECT; + } + + pci_set_master(pdev); + pci_restore_state(pdev); + + if (wait_vital(pdev)) { + dev_err(&pdev->dev, "%s: wait_vital timed out\n", __func__); + return PCI_ERS_RESULT_DISCONNECT; + } + + return PCI_ERS_RESULT_RECOVERED; +} + +void mlx5_disable_device(struct mlx5_core_dev *dev) +{ + mlx5_pci_err_detected(dev->pdev, 0); +} + static void mlx5_pci_resume(struct pci_dev *pdev) { struct mlx5_core_dev *dev = pci_get_drvdata(pdev); @@ -1485,13 +1491,6 @@ static void mlx5_pci_resume(struct pci_dev *pdev) dev_info(&pdev->dev, "%s was called\n", __func__); - pci_save_state(pdev); - err = wait_vital(pdev); - if (err) { - dev_err(&pdev->dev, "%s: wait_vital timed out\n", __func__); - return; - } - err = mlx5_load_one(dev, priv); if (err) dev_err(&pdev->dev, "%s: mlx5_load_one failed with error code: %d\n" From 2c0f8ce1b584a4d7b8ff53140d21dfed99834940 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Thu, 18 Aug 2016 21:09:05 +0300 Subject: [PATCH 164/531] net/mlx5: Added missing check of msg length in verifying its signature Set and verify signature calculates the signature for each of the mailbox nodes, even for those that are unused (from cache). Added a missing length check to set and verify only those which are used. While here, also moved the setting of msg's nodes token to where we already go over them. This saves a pass because checksum is disabled, and the only useful thing remaining that set signature does is setting the token. Fixes: e126ba97dba9 ('mlx5: Add driver for Mellanox Connect-IB adapters') Signed-off-by: Paul Blakey Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 83 ++++++++++++------- 1 file changed, 53 insertions(+), 30 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index d6e2a1cae19a..c2ec01a22d55 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -143,13 +143,14 @@ static struct mlx5_cmd_layout *get_inst(struct mlx5_cmd *cmd, int idx) return cmd->cmd_buf + (idx << cmd->log_stride); } -static u8 xor8_buf(void *buf, int len) +static u8 xor8_buf(void *buf, size_t offset, int len) { u8 *ptr = buf; u8 sum = 0; int i; + int end = len + offset; - for (i = 0; i < len; i++) + for (i = offset; i < end; i++) sum ^= ptr[i]; return sum; @@ -157,41 +158,49 @@ static u8 xor8_buf(void *buf, int len) static int verify_block_sig(struct mlx5_cmd_prot_block *block) { - if (xor8_buf(block->rsvd0, sizeof(*block) - sizeof(block->data) - 1) != 0xff) + size_t rsvd0_off = offsetof(struct mlx5_cmd_prot_block, rsvd0); + int xor_len = sizeof(*block) - sizeof(block->data) - 1; + + if (xor8_buf(block, rsvd0_off, xor_len) != 0xff) return -EINVAL; - if (xor8_buf(block, sizeof(*block)) != 0xff) + if (xor8_buf(block, 0, sizeof(*block)) != 0xff) return -EINVAL; return 0; } -static void calc_block_sig(struct mlx5_cmd_prot_block *block, u8 token, - int csum) +static void calc_block_sig(struct mlx5_cmd_prot_block *block) { - block->token = token; - if (csum) { - block->ctrl_sig = ~xor8_buf(block->rsvd0, sizeof(*block) - - sizeof(block->data) - 2); - block->sig = ~xor8_buf(block, sizeof(*block) - 1); - } + int ctrl_xor_len = sizeof(*block) - sizeof(block->data) - 2; + size_t rsvd0_off = offsetof(struct mlx5_cmd_prot_block, rsvd0); + + block->ctrl_sig = ~xor8_buf(block, rsvd0_off, ctrl_xor_len); + block->sig = ~xor8_buf(block, 0, sizeof(*block) - 1); } -static void calc_chain_sig(struct mlx5_cmd_msg *msg, u8 token, int csum) +static void calc_chain_sig(struct mlx5_cmd_msg *msg) { struct mlx5_cmd_mailbox *next = msg->next; + int size = msg->len; + int blen = size - min_t(int, sizeof(msg->first.data), size); + int n = (blen + MLX5_CMD_DATA_BLOCK_SIZE - 1) + / MLX5_CMD_DATA_BLOCK_SIZE; + int i = 0; - while (next) { - calc_block_sig(next->buf, token, csum); + for (i = 0; i < n && next; i++) { + calc_block_sig(next->buf); next = next->next; } } static void set_signature(struct mlx5_cmd_work_ent *ent, int csum) { - ent->lay->sig = ~xor8_buf(ent->lay, sizeof(*ent->lay)); - calc_chain_sig(ent->in, ent->token, csum); - calc_chain_sig(ent->out, ent->token, csum); + ent->lay->sig = ~xor8_buf(ent->lay, 0, sizeof(*ent->lay)); + if (csum) { + calc_chain_sig(ent->in); + calc_chain_sig(ent->out); + } } static void poll_timeout(struct mlx5_cmd_work_ent *ent) @@ -222,12 +231,17 @@ static int verify_signature(struct mlx5_cmd_work_ent *ent) struct mlx5_cmd_mailbox *next = ent->out->next; int err; u8 sig; + int size = ent->out->len; + int blen = size - min_t(int, sizeof(ent->out->first.data), size); + int n = (blen + MLX5_CMD_DATA_BLOCK_SIZE - 1) + / MLX5_CMD_DATA_BLOCK_SIZE; + int i = 0; - sig = xor8_buf(ent->lay, sizeof(*ent->lay)); + sig = xor8_buf(ent->lay, 0, sizeof(*ent->lay)); if (sig != 0xff) return -EINVAL; - while (next) { + for (i = 0; i < n && next; i++) { err = verify_block_sig(next->buf); if (err) return err; @@ -656,7 +670,6 @@ static void cmd_work_handler(struct work_struct *work) spin_unlock_irqrestore(&cmd->alloc_lock, flags); } - ent->token = alloc_token(cmd); cmd->ent_arr[ent->idx] = ent; lay = get_inst(cmd, ent->idx); ent->lay = lay; @@ -766,7 +779,8 @@ static u8 *get_status_ptr(struct mlx5_outbox_hdr *out) static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, struct mlx5_cmd_msg *out, void *uout, int uout_size, mlx5_cmd_cbk_t callback, - void *context, int page_queue, u8 *status) + void *context, int page_queue, u8 *status, + u8 token) { struct mlx5_cmd *cmd = &dev->cmd; struct mlx5_cmd_work_ent *ent; @@ -783,6 +797,8 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, if (IS_ERR(ent)) return PTR_ERR(ent); + ent->token = token; + if (!callback) init_completion(&ent->done); @@ -854,7 +870,8 @@ static const struct file_operations fops = { .write = dbg_write, }; -static int mlx5_copy_to_msg(struct mlx5_cmd_msg *to, void *from, int size) +static int mlx5_copy_to_msg(struct mlx5_cmd_msg *to, void *from, int size, + u8 token) { struct mlx5_cmd_prot_block *block; struct mlx5_cmd_mailbox *next; @@ -880,6 +897,7 @@ static int mlx5_copy_to_msg(struct mlx5_cmd_msg *to, void *from, int size) memcpy(block->data, from, copy); from += copy; size -= copy; + block->token = token; next = next->next; } @@ -949,7 +967,8 @@ static void free_cmd_box(struct mlx5_core_dev *dev, } static struct mlx5_cmd_msg *mlx5_alloc_cmd_msg(struct mlx5_core_dev *dev, - gfp_t flags, int size) + gfp_t flags, int size, + u8 token) { struct mlx5_cmd_mailbox *tmp, *head = NULL; struct mlx5_cmd_prot_block *block; @@ -978,6 +997,7 @@ static struct mlx5_cmd_msg *mlx5_alloc_cmd_msg(struct mlx5_core_dev *dev, tmp->next = head; block->next = cpu_to_be64(tmp->next ? tmp->next->dma : 0); block->block_num = cpu_to_be32(n - i - 1); + block->token = token; head = tmp; } msg->next = head; @@ -1352,7 +1372,7 @@ static struct mlx5_cmd_msg *alloc_msg(struct mlx5_core_dev *dev, int in_size, } if (IS_ERR(msg)) - msg = mlx5_alloc_cmd_msg(dev, gfp, in_size); + msg = mlx5_alloc_cmd_msg(dev, gfp, in_size, 0); return msg; } @@ -1377,6 +1397,7 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int err; u8 status = 0; u32 drv_synd; + u8 token; if (pci_channel_offline(dev->pdev) || dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) { @@ -1395,20 +1416,22 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, return err; } - err = mlx5_copy_to_msg(inb, in, in_size); + token = alloc_token(&dev->cmd); + + err = mlx5_copy_to_msg(inb, in, in_size, token); if (err) { mlx5_core_warn(dev, "err %d\n", err); goto out_in; } - outb = mlx5_alloc_cmd_msg(dev, gfp, out_size); + outb = mlx5_alloc_cmd_msg(dev, gfp, out_size, token); if (IS_ERR(outb)) { err = PTR_ERR(outb); goto out_in; } err = mlx5_cmd_invoke(dev, inb, outb, out, out_size, callback, context, - pages_queue, &status); + pages_queue, &status, token); if (err) goto out_out; @@ -1476,7 +1499,7 @@ static int create_msg_cache(struct mlx5_core_dev *dev) INIT_LIST_HEAD(&cmd->cache.med.head); for (i = 0; i < NUM_LONG_LISTS; i++) { - msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, LONG_LIST_SIZE); + msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, LONG_LIST_SIZE, 0); if (IS_ERR(msg)) { err = PTR_ERR(msg); goto ex_err; @@ -1486,7 +1509,7 @@ static int create_msg_cache(struct mlx5_core_dev *dev) } for (i = 0; i < NUM_MED_LISTS; i++) { - msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, MED_LIST_SIZE); + msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, MED_LIST_SIZE, 0); if (IS_ERR(msg)) { err = PTR_ERR(msg); goto ex_err; From 6c3b4f90861c7ed59d0287b0ff7f2623f9d93d73 Mon Sep 17 00:00:00 2001 From: Amir Vadai Date: Thu, 18 Aug 2016 21:09:06 +0300 Subject: [PATCH 165/531] net/mlx5: Update last-use statistics for flow rules Set lastuse statistic, when number of packets is changed compared to last query. This was wrongly dropped when bulk counter reading was added. Fixes: a351a1b03bf1 ('net/mlx5: Introduce bulk reading of flow counters') Signed-off-by: Amir Vadai Reported-by: Paul Blakey Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c index c2877e9de8a1..3a9195b4169d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c @@ -126,12 +126,21 @@ static struct rb_node *mlx5_fc_stats_query(struct mlx5_core_dev *dev, for (node = &first->node; node; node = rb_next(node)) { struct mlx5_fc *counter = rb_entry(node, struct mlx5_fc, node); struct mlx5_fc_cache *c = &counter->cache; + u64 packets; + u64 bytes; if (counter->id > last_id) break; mlx5_cmd_fc_bulk_get(dev, b, - counter->id, &c->packets, &c->bytes); + counter->id, &packets, &bytes); + + if (c->packets == packets) + continue; + + c->packets = packets; + c->bytes = bytes; + c->lastuse = jiffies; } out: From 1dbd0d373ac338903d27fab5204b13122cc5accd Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Thu, 18 Aug 2016 21:09:07 +0300 Subject: [PATCH 166/531] net/mlx5e: Use correct flow dissector key on flower offloading The wrong key is used when extracting the address type field set by the flower offload code. We have to use the control key and not the basic key, fix that. Fixes: e3a2b7ed018e ('net/mlx5e: Support offload cls_flower with drop action') Signed-off-by: Hadar Hen Zion Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index dc8b1cb0fdc8..22cfc4ac1837 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -170,7 +170,7 @@ static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) { struct flow_dissector_key_control *key = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, + FLOW_DISSECTOR_KEY_CONTROL, f->key); addr_type = key->addr_type; } From dbe413e3bb93e0634f6d8d00b01cda6f141e0acd Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Thu, 18 Aug 2016 21:09:08 +0300 Subject: [PATCH 167/531] net/mlx5e: Retrieve the switchdev id from the firmware only once Avoid firmware command execution each time the switchdev HW ID attr get call is made. We do that by reading the ID (PF NIC MAC) only once at load time and store it on the representor structure. Signed-off-by: Hadar Hen Zion Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 5 +++++ drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 5 ++--- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 1 + 3 files changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 65258b259579..03d944c0077e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3387,6 +3387,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv) queue_work(priv->wq, &priv->set_rx_mode_work); if (MLX5_CAP_GEN(mdev, vport_group_manager)) { + mlx5_query_nic_vport_mac_address(mdev, 0, rep.hw_id); rep.load = mlx5e_nic_rep_load; rep.unload = mlx5e_nic_rep_unload; rep.vport = 0; @@ -3505,16 +3506,20 @@ static void mlx5e_register_vport_rep(struct mlx5_core_dev *mdev) struct mlx5_eswitch *esw = mdev->priv.eswitch; int total_vfs = MLX5_TOTAL_VPORTS(mdev); int vport; + u8 mac[ETH_ALEN]; if (!MLX5_CAP_GEN(mdev, vport_group_manager)) return; + mlx5_query_nic_vport_mac_address(mdev, 0, mac); + for (vport = 1; vport < total_vfs; vport++) { struct mlx5_eswitch_rep rep; rep.load = mlx5e_vport_rep_load; rep.unload = mlx5e_vport_rep_unload; rep.vport = vport; + ether_addr_copy(rep.hw_id, mac); mlx5_eswitch_register_vport_rep(esw, &rep); } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 1c7d8b8314bf..134de4a11f1d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -135,17 +135,16 @@ static const struct ethtool_ops mlx5e_rep_ethtool_ops = { int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr) { struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5_eswitch_rep *rep = priv->ppriv; struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - u8 mac[ETH_ALEN]; if (esw->mode == SRIOV_NONE) return -EOPNOTSUPP; switch (attr->id) { case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: - mlx5_query_nic_vport_mac_address(priv->mdev, 0, mac); attr->u.ppid.id_len = ETH_ALEN; - memcpy(&attr->u.ppid.id, &mac, ETH_ALEN); + ether_addr_copy(attr->u.ppid.id, rep->hw_id); break; default: return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index c0b05603fc31..a96140971d77 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -174,6 +174,7 @@ struct mlx5_eswitch_rep { void *priv_data; struct list_head vport_sqs_list; bool valid; + u8 hw_id[ETH_ALEN]; }; struct mlx5_esw_offload { From ef78618b9d29d40c95ca7092493545b8487e226c Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Thu, 18 Aug 2016 21:09:09 +0300 Subject: [PATCH 168/531] net/mlx5: E-Switch, Return the correct devlink e-switch mode Since mlx5 has also the NONE e-switch mode, we must translate from mlx5 mode to devlink mode on the devlink eswitch mode get call, do that. While here, remove the mlx5_ prefix from the static function helpers that deal with the mode to comply with the rest of the code. Fixes: c930a3ad7453 ('net/mlx5e: Add devlink based SRIOV mode change') Signed-off-by: Or Gerlitz Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- .../mellanox/mlx5/core/eswitch_offloads.c | 24 +++++++++++++++---- 1 file changed, 19 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index a357e8eeeed8..1a3ccbf2dffd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -535,7 +535,7 @@ void esw_offloads_cleanup(struct mlx5_eswitch *esw, int nvports) esw_destroy_offloads_fdb_table(esw); } -static int mlx5_esw_mode_from_devlink(u16 mode, u16 *mlx5_mode) +static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode) { switch (mode) { case DEVLINK_ESWITCH_MODE_LEGACY: @@ -551,6 +551,22 @@ static int mlx5_esw_mode_from_devlink(u16 mode, u16 *mlx5_mode) return 0; } +static int esw_mode_to_devlink(u16 mlx5_mode, u16 *mode) +{ + switch (mlx5_mode) { + case SRIOV_LEGACY: + *mode = DEVLINK_ESWITCH_MODE_LEGACY; + break; + case SRIOV_OFFLOADS: + *mode = DEVLINK_ESWITCH_MODE_SWITCHDEV; + break; + default: + return -EINVAL; + } + + return 0; +} + int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode) { struct mlx5_core_dev *dev; @@ -566,7 +582,7 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode) if (cur_mlx5_mode == SRIOV_NONE) return -EOPNOTSUPP; - if (mlx5_esw_mode_from_devlink(mode, &mlx5_mode)) + if (esw_mode_from_devlink(mode, &mlx5_mode)) return -EINVAL; if (cur_mlx5_mode == mlx5_mode) @@ -592,9 +608,7 @@ int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode) if (dev->priv.eswitch->mode == SRIOV_NONE) return -EOPNOTSUPP; - *mode = dev->priv.eswitch->mode; - - return 0; + return esw_mode_to_devlink(dev->priv.eswitch->mode, mode); } void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw, From 1a8ee6f25b10da7e3de0899a184b221d793f2482 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Thu, 18 Aug 2016 21:09:10 +0300 Subject: [PATCH 169/531] net/mlx5: E-Switch, Set the send-to-vport rules in the correct table While adding actual offloading support to the new switchdev mode, we didn't change the setup of the send-to-vport rules to put them in the slow path table, fix that. Fixes: 1033665e63b6 ('net/mlx5: E-Switch, Use two priorities for SRIOV offloads mode') Signed-off-by: Or Gerlitz Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 1a3ccbf2dffd..3dc83a9459a4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -113,7 +113,7 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, int vport, u32 sqn dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT; dest.vport_num = vport; - flow_rule = mlx5_add_flow_rule(esw->fdb_table.fdb, spec, + flow_rule = mlx5_add_flow_rule(esw->fdb_table.offloads.fdb, spec, MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, 0, &dest); if (IS_ERR(flow_rule)) From f96750f8d6bd64bb6f5a7a1146121b96bc6115f0 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Thu, 18 Aug 2016 21:09:11 +0300 Subject: [PATCH 170/531] net/mlx5: E-Switch, Avoid ACLs in the offloads mode When we are in the switchdev/offloads mode, HW matching is done as dictated by the offloaded rules and hence we don't need to enable the ACLs mechanism used by the legacy mode. Signed-off-by: Or Gerlitz Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlx5/core/eswitch.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index f6d667797ee1..8b78f156214e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1451,7 +1451,8 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num, esw_debug(esw->dev, "Enabling VPORT(%d)\n", vport_num); - if (vport_num) { /* Only VFs need ACLs for VST and spoofchk filtering */ + /* Only VFs need ACLs for VST and spoofchk filtering */ + if (vport_num && esw->mode == SRIOV_LEGACY) { esw_vport_ingress_config(esw, vport); esw_vport_egress_config(esw, vport); } @@ -1502,7 +1503,7 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num) */ esw_vport_change_handle_locked(vport); vport->enabled_events = 0; - if (vport_num) { + if (vport_num && esw->mode == SRIOV_LEGACY) { esw_vport_disable_egress_acl(esw, vport); esw_vport_disable_ingress_acl(esw, vport); } @@ -1767,7 +1768,7 @@ int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw, vport, err); mutex_lock(&esw->state_lock); - if (evport->enabled) + if (evport->enabled && esw->mode == SRIOV_LEGACY) err = esw_vport_ingress_config(esw, evport); mutex_unlock(&esw->state_lock); return err; @@ -1839,7 +1840,7 @@ int mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw, mutex_lock(&esw->state_lock); evport->vlan = vlan; evport->qos = qos; - if (evport->enabled) { + if (evport->enabled && esw->mode == SRIOV_LEGACY) { err = esw_vport_ingress_config(esw, evport); if (err) goto out; @@ -1868,10 +1869,11 @@ int mlx5_eswitch_set_vport_spoofchk(struct mlx5_eswitch *esw, mutex_lock(&esw->state_lock); pschk = evport->spoofchk; evport->spoofchk = spoofchk; - if (evport->enabled) + if (evport->enabled && esw->mode == SRIOV_LEGACY) { err = esw_vport_ingress_config(esw, evport); - if (err) - evport->spoofchk = pschk; + if (err) + evport->spoofchk = pschk; + } mutex_unlock(&esw->state_lock); return err; From 4c2f2454964477c66ef57745daab203b71783f66 Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Thu, 18 Aug 2016 14:58:35 -0300 Subject: [PATCH 171/531] sctp: linearize early if it's not GSO Because otherwise when crc computation is still needed it's way more expensive than on a linear buffer to the point that it affects performance. It's so expensive that netperf test gives a perf output as below: Overhead Command Shared Object Symbol 18,62% netserver [kernel.vmlinux] [k] crc32_generic_shift 2,57% netserver [kernel.vmlinux] [k] __pskb_pull_tail 1,94% netserver [kernel.vmlinux] [k] fib_table_lookup 1,90% netserver [kernel.vmlinux] [k] copy_user_enhanced_fast_string 1,66% swapper [kernel.vmlinux] [k] intel_idle 1,63% netserver [kernel.vmlinux] [k] _raw_spin_lock 1,59% netserver [sctp] [k] sctp_packet_transmit 1,55% netserver [kernel.vmlinux] [k] memcpy_erms 1,42% netserver [sctp] [k] sctp_rcv # netperf -H 192.168.10.1 -l 10 -t SCTP_STREAM -cC -- -m 12000 SCTP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.10.1 () port 0 AF_INET Recv Send Send Utilization Service Demand Socket Socket Message Elapsed Send Recv Send Recv Size Size Size Time Throughput local remote local remote bytes bytes bytes secs. 10^6bits/s % S % S us/KB us/KB 212992 212992 12000 10.00 3016.42 2.88 3.78 1.874 2.462 After patch: Overhead Command Shared Object Symbol 2,75% netserver [kernel.vmlinux] [k] memcpy_erms 2,63% netserver [kernel.vmlinux] [k] copy_user_enhanced_fast_string 2,39% netserver [kernel.vmlinux] [k] fib_table_lookup 2,04% netserver [kernel.vmlinux] [k] __pskb_pull_tail 1,91% netserver [kernel.vmlinux] [k] _raw_spin_lock 1,91% netserver [sctp] [k] sctp_packet_transmit 1,72% netserver [mlx4_en] [k] mlx4_en_process_rx_cq 1,68% netserver [sctp] [k] sctp_rcv # netperf -H 192.168.10.1 -l 10 -t SCTP_STREAM -cC -- -m 12000 SCTP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.10.1 () port 0 AF_INET Recv Send Send Utilization Service Demand Socket Socket Message Elapsed Send Recv Send Recv Size Size Size Time Throughput local remote local remote bytes bytes bytes secs. 10^6bits/s % S % S us/KB us/KB 212992 212992 12000 10.00 3681.77 3.83 3.46 2.045 1.849 Fixes: 3acb50c18d8d ("sctp: delay as much as possible skb_linearize") Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- net/sctp/input.c | 11 +++++++---- net/sctp/inqueue.c | 13 ------------- 2 files changed, 7 insertions(+), 17 deletions(-) diff --git a/net/sctp/input.c b/net/sctp/input.c index c182db7d691f..69444d32ecda 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -119,7 +119,13 @@ int sctp_rcv(struct sk_buff *skb) skb_transport_offset(skb)) goto discard_it; - if (!pskb_may_pull(skb, sizeof(struct sctphdr))) + /* If the packet is fragmented and we need to do crc checking, + * it's better to just linearize it otherwise crc computing + * takes longer. + */ + if ((!(skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) && + skb_linearize(skb)) || + !pskb_may_pull(skb, sizeof(struct sctphdr))) goto discard_it; /* Pull up the IP header. */ @@ -1177,9 +1183,6 @@ static struct sctp_association *__sctp_rcv_lookup_harder(struct net *net, if ((skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP) return NULL; - if (skb_linearize(skb)) - return NULL; - ch = (sctp_chunkhdr_t *) skb->data; /* The code below will attempt to walk the chunk and extract diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index c30ddb0f3190..6437aa97cfd7 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -170,19 +170,6 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue) chunk = list_entry(entry, struct sctp_chunk, list); - /* Linearize if it's not GSO */ - if ((skb_shinfo(chunk->skb)->gso_type & SKB_GSO_SCTP) != SKB_GSO_SCTP && - skb_is_nonlinear(chunk->skb)) { - if (skb_linearize(chunk->skb)) { - __SCTP_INC_STATS(dev_net(chunk->skb->dev), SCTP_MIB_IN_PKT_DISCARDS); - sctp_chunk_free(chunk); - goto next_chunk; - } - - /* Update sctp_hdr as it probably changed */ - chunk->sctp_hdr = sctp_hdr(chunk->skb); - } - if ((skb_shinfo(chunk->skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP) { /* GSO-marked skbs but without frags, handle * them normally From 56cff471d0c62b721a298f806e7637501debb513 Mon Sep 17 00:00:00 2001 From: Gao Feng Date: Fri, 19 Aug 2016 13:36:23 +0800 Subject: [PATCH 172/531] l2tp: Fix the connect status check in pppol2tp_getname The sk->sk_state is bits flag, so need use bit operation check instead of value check. Signed-off-by: Gao Feng Tested-by: Guillaume Nault Signed-off-by: David S. Miller --- net/l2tp/l2tp_ppp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index d9560aa2dba3..232cb92033e8 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -856,7 +856,7 @@ static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr, error = -ENOTCONN; if (sk == NULL) goto end; - if (sk->sk_state != PPPOX_CONNECTED) + if (!(sk->sk_state & PPPOX_CONNECTED)) goto end; error = -EBADF; From 8912862f067276b480c4fed9da74c9c5601130a6 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 19 Aug 2016 14:43:48 +0200 Subject: [PATCH 173/531] mlxsw: spectrum_buffers: Fix pool value handling in mlxsw_sp_sb_tc_pool_bind_set Pool index has to be converted by get_pool helper to work correctly for egress pool. In mlxsw the egress pool index starts from 0. Fixes: 0f433fa0ecc ("mlxsw: spectrum_buffers: Implement shared buffer configuration") Signed-off-by: Jiri Pirko Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlxsw/spectrum_buffers.c | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c index 237418a0e6e0..953b214f38d0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -717,22 +717,18 @@ int mlxsw_sp_sb_tc_pool_bind_set(struct mlxsw_core_port *mlxsw_core_port, u8 local_port = mlxsw_sp_port->local_port; u8 pg_buff = tc_index; enum mlxsw_reg_sbxx_dir dir = pool_type; - u8 pool = pool_index; + u8 pool = pool_get(pool_index); u32 max_buff; int err; + if (dir != dir_get(pool_index)) + return -EINVAL; + err = mlxsw_sp_sb_threshold_in(mlxsw_sp, pool, dir, threshold, &max_buff); if (err) return err; - if (pool_type == DEVLINK_SB_POOL_TYPE_EGRESS) { - if (pool < MLXSW_SP_SB_POOL_COUNT) - return -EINVAL; - pool -= MLXSW_SP_SB_POOL_COUNT; - } else if (pool >= MLXSW_SP_SB_POOL_COUNT) { - return -EINVAL; - } return mlxsw_sp_sb_cm_write(mlxsw_sp, local_port, pg_buff, dir, 0, max_buff, pool); } From d5fb46e0e3b7e49ee83ba92efc3ab4e1a545ecc1 Mon Sep 17 00:00:00 2001 From: Eric Anholt Date: Tue, 26 Jul 2016 13:47:10 -0700 Subject: [PATCH 174/531] drm/vc4: Use drm_free_large() on handles to match its allocation. If you managed to exceed the limit to switch to vmalloc, we'd use the wrong free. Signed-off-by: Eric Anholt Fixes: d5b1a78a772f ("drm/vc4: Add support for drawing 3D frames.") Cc: stable@vger.kernel.org --- drivers/gpu/drm/vc4/vc4_gem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c index 6155e8aca1c6..62df61f9ac24 100644 --- a/drivers/gpu/drm/vc4/vc4_gem.c +++ b/drivers/gpu/drm/vc4/vc4_gem.c @@ -572,7 +572,7 @@ vc4_cl_lookup_bos(struct drm_device *dev, spin_unlock(&file_priv->table_lock); fail: - kfree(handles); + drm_free_large(handles); return 0; } From ece7267dccf0e9e08cb6e8dc6b7ad2be9c4eb444 Mon Sep 17 00:00:00 2001 From: Eric Anholt Date: Tue, 19 Jul 2016 11:32:44 -0700 Subject: [PATCH 175/531] drm/vc4: Use drm_malloc_ab to fix large rendering jobs. If you exceeded the size that kmalloc would return, you'd get a dmesg warning and a return from the job submit. We can handle much allocations with vmalloc, and drm_malloc_ab makes that decision. Fixes failure in piglit's scissor-many. Signed-off-by: Eric Anholt --- drivers/gpu/drm/vc4/vc4_gem.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c index 62df61f9ac24..bfd1b5280ff3 100644 --- a/drivers/gpu/drm/vc4/vc4_gem.c +++ b/drivers/gpu/drm/vc4/vc4_gem.c @@ -534,8 +534,8 @@ vc4_cl_lookup_bos(struct drm_device *dev, return -EINVAL; } - exec->bo = kcalloc(exec->bo_count, sizeof(struct drm_gem_cma_object *), - GFP_KERNEL); + exec->bo = drm_calloc_large(exec->bo_count, + sizeof(struct drm_gem_cma_object *)); if (!exec->bo) { DRM_ERROR("Failed to allocate validated BO pointers\n"); return -ENOMEM; @@ -608,7 +608,7 @@ vc4_get_bcl(struct drm_device *dev, struct vc4_exec_info *exec) * read the contents back for validation, and I think the * bo->vaddr is uncached access. */ - temp = kmalloc(temp_size, GFP_KERNEL); + temp = drm_malloc_ab(temp_size, 1); if (!temp) { DRM_ERROR("Failed to allocate storage for copying " "in bin/render CLs.\n"); @@ -675,7 +675,7 @@ vc4_get_bcl(struct drm_device *dev, struct vc4_exec_info *exec) ret = vc4_validate_shader_recs(dev, exec); fail: - kfree(temp); + drm_free_large(temp); return ret; } @@ -688,7 +688,7 @@ vc4_complete_exec(struct drm_device *dev, struct vc4_exec_info *exec) if (exec->bo) { for (i = 0; i < exec->bo_count; i++) drm_gem_object_unreference_unlocked(&exec->bo[i]->base); - kfree(exec->bo); + drm_free_large(exec->bo); } while (!list_empty(&exec->unref_list)) { From 163195fc12cae0c8b5c0d74d3ba8d2c5f81773bc Mon Sep 17 00:00:00 2001 From: Eric Anholt Date: Tue, 26 Jul 2016 13:47:12 -0700 Subject: [PATCH 176/531] drm/vc4: Fix handling of a pm_runtime_get_sync() success case. If the device was already up, a 1 is returned instead of 0. We were erroring out, leading the 3D driver to sometimes fail at screen initialization (generally with ENOENT returned to it). Signed-off-by: Eric Anholt Fixes: af713795c59f ("drm/vc4: Add a getparam ioctl for getting the V3D identity regs.") --- drivers/gpu/drm/vc4/vc4_drv.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c index 8b42d31a7f0e..9ecef9385491 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.c +++ b/drivers/gpu/drm/vc4/vc4_drv.c @@ -57,21 +57,21 @@ static int vc4_get_param_ioctl(struct drm_device *dev, void *data, switch (args->param) { case DRM_VC4_PARAM_V3D_IDENT0: ret = pm_runtime_get_sync(&vc4->v3d->pdev->dev); - if (ret) + if (ret < 0) return ret; args->value = V3D_READ(V3D_IDENT0); pm_runtime_put(&vc4->v3d->pdev->dev); break; case DRM_VC4_PARAM_V3D_IDENT1: ret = pm_runtime_get_sync(&vc4->v3d->pdev->dev); - if (ret) + if (ret < 0) return ret; args->value = V3D_READ(V3D_IDENT1); pm_runtime_put(&vc4->v3d->pdev->dev); break; case DRM_VC4_PARAM_V3D_IDENT2: ret = pm_runtime_get_sync(&vc4->v3d->pdev->dev); - if (ret) + if (ret < 0) return ret; args->value = V3D_READ(V3D_IDENT2); pm_runtime_put(&vc4->v3d->pdev->dev); From def96527707e1978a0c88e75d13b082f51460d5c Mon Sep 17 00:00:00 2001 From: Eric Anholt Date: Tue, 26 Jul 2016 13:47:13 -0700 Subject: [PATCH 177/531] drm/vc4: Free hang state before destroying BO cache. The BO cache will complain if BOs are still allocated when we try to destroy it (since freeing those BOs would try to hit the cache). You could hit this if you were to unload the module after a GPU hang. Signed-off-by: Eric Anholt Fixes: 214613656b51 ("drm/vc4: Add an interface for capturing the GPU state after a hang.") --- drivers/gpu/drm/vc4/vc4_gem.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c index bfd1b5280ff3..fba2c831afe6 100644 --- a/drivers/gpu/drm/vc4/vc4_gem.c +++ b/drivers/gpu/drm/vc4/vc4_gem.c @@ -942,8 +942,8 @@ vc4_gem_destroy(struct drm_device *dev) vc4->overflow_mem = NULL; } - vc4_bo_cache_destroy(dev); - if (vc4->hang_state) vc4_free_hang_state(dev, vc4->hang_state); + + vc4_bo_cache_destroy(dev); } From 9326e6f25574bbb8bd48206d245654780e3fd665 Mon Sep 17 00:00:00 2001 From: Eric Anholt Date: Tue, 26 Jul 2016 13:47:14 -0700 Subject: [PATCH 178/531] drm/vc4: Fix overflow mem unreferencing when the binner runs dry. Overflow memory handling is tricky: While it's still referenced by the BPO registers, we want to keep it from being freed. When we are putting a new set of overflow memory in the registers, we need to assign the old one to the last rendering job using it. We were looking at "what's currently running in the binner", but since the bin/render submission split, we may end up with the binner completing and having no new job while the renderer is still processing. So, if we don't find a bin job at all, look at the highest-seqno (last) render job to attach our overflow to. Signed-off-by: Eric Anholt Fixes: ca26d28bbaa3 ("drm/vc4: improve throughput by pipelining binning and rendering jobs") Cc: stable@vger.kernel.org --- drivers/gpu/drm/vc4/vc4_drv.h | 9 +++++++++ drivers/gpu/drm/vc4/vc4_irq.c | 4 +++- 2 files changed, 12 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h index 489e3de0c050..428e24919ef1 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.h +++ b/drivers/gpu/drm/vc4/vc4_drv.h @@ -321,6 +321,15 @@ vc4_first_render_job(struct vc4_dev *vc4) struct vc4_exec_info, head); } +static inline struct vc4_exec_info * +vc4_last_render_job(struct vc4_dev *vc4) +{ + if (list_empty(&vc4->render_job_list)) + return NULL; + return list_last_entry(&vc4->render_job_list, + struct vc4_exec_info, head); +} + /** * struct vc4_texture_sample_info - saves the offsets into the UBO for texture * setup parameters. diff --git a/drivers/gpu/drm/vc4/vc4_irq.c b/drivers/gpu/drm/vc4/vc4_irq.c index b0104a346a74..094bc6a475c1 100644 --- a/drivers/gpu/drm/vc4/vc4_irq.c +++ b/drivers/gpu/drm/vc4/vc4_irq.c @@ -83,8 +83,10 @@ vc4_overflow_mem_work(struct work_struct *work) spin_lock_irqsave(&vc4->job_lock, irqflags); current_exec = vc4_first_bin_job(vc4); + if (!current_exec) + current_exec = vc4_last_render_job(vc4); if (current_exec) { - vc4->overflow_mem->seqno = vc4->finished_seqno + 1; + vc4->overflow_mem->seqno = current_exec->seqno; list_add_tail(&vc4->overflow_mem->unref_head, ¤t_exec->unref_list); vc4->overflow_mem = NULL; From 552416c146fadc67cd9b53ef7adf88d3381c43a6 Mon Sep 17 00:00:00 2001 From: Eric Anholt Date: Tue, 26 Jul 2016 13:47:15 -0700 Subject: [PATCH 179/531] drm/vc4: Fix oops when userspace hands in a bad BO. We'd end up NULL pointer dereferencing because we didn't take the error path out in the parent. Fixes igt vc4_lookup_fail test. Signed-off-by: Eric Anholt Fixes: d5b1a78a772f ("drm/vc4: Add support for drawing 3D frames.") Cc: stable@vger.kernel.org --- drivers/gpu/drm/vc4/vc4_gem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c index fba2c831afe6..b262c5c26f10 100644 --- a/drivers/gpu/drm/vc4/vc4_gem.c +++ b/drivers/gpu/drm/vc4/vc4_gem.c @@ -573,7 +573,7 @@ vc4_cl_lookup_bos(struct drm_device *dev, fail: drm_free_large(handles); - return 0; + return ret; } static int From c10ac75aeed2d8486a73a316ac3a08f85d140894 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 19 Aug 2016 20:58:26 -0700 Subject: [PATCH 180/531] ixgbe: Do not clear RAR entry when clearing VMDq for SAN MAC The RAR entry for the SAN MAC address was being cleared when we were clearing the VMDq pool bits. In order to prevent this we need to add an extra check to protect the SAN MAC from being cleared. Fixes: 6e982aeae ("ixgbe: Clear stale pool mappings") Signed-off-by: Alexander Duyck Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/ixgbe/ixgbe_common.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index b4217f30e89c..c47b605e8651 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -2958,8 +2958,10 @@ s32 ixgbe_clear_vmdq_generic(struct ixgbe_hw *hw, u32 rar, u32 vmdq) } /* was that the last pool using this rar? */ - if (mpsar_lo == 0 && mpsar_hi == 0 && rar != 0) + if (mpsar_lo == 0 && mpsar_hi == 0 && + rar != 0 && rar != hw->mac.san_mac_rar_index) hw->mac.ops.clear_rar(hw, rar); + return 0; } From ff2e7d5d51469e98196f7933c83b781e96517e7c Mon Sep 17 00:00:00 2001 From: Shrikrishna Khare Date: Fri, 19 Aug 2016 10:33:42 -0700 Subject: [PATCH 181/531] vmxnet3: fix tx data ring copy for variable size 'Commit 3c8b3efc061a ("vmxnet3: allow variable length transmit data ring buffer")' changed the size of the buffers in the tx data ring from a fixed size of 128 bytes to a variable size. However, while copying data to the data ring, vmxnet3_copy_hdr continues to carry the old code that assumes fixed buffer size of 128. This patch fixes it by adding correct offset based on the actual data ring buffer size. Signed-off-by: Guolin Yang Signed-off-by: Shrikrishna Khare Signed-off-by: David S. Miller --- drivers/net/vmxnet3/vmxnet3_drv.c | 4 +++- drivers/net/vmxnet3/vmxnet3_int.h | 4 ++-- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index c68fe495d3f9..4244b9d4418e 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -914,7 +914,9 @@ vmxnet3_copy_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, { struct Vmxnet3_TxDataDesc *tdd; - tdd = tq->data_ring.base + tq->tx_ring.next2fill; + tdd = (struct Vmxnet3_TxDataDesc *)((u8 *)tq->data_ring.base + + tq->tx_ring.next2fill * + tq->txdata_desc_size); memcpy(tdd->data, skb->data, ctx->copy_size); netdev_dbg(adapter->netdev, diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h index 74fc03072b87..7dc37a090549 100644 --- a/drivers/net/vmxnet3/vmxnet3_int.h +++ b/drivers/net/vmxnet3/vmxnet3_int.h @@ -69,10 +69,10 @@ /* * Version numbers */ -#define VMXNET3_DRIVER_VERSION_STRING "1.4.9.0-k" +#define VMXNET3_DRIVER_VERSION_STRING "1.4.a.0-k" /* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */ -#define VMXNET3_DRIVER_VERSION_NUM 0x01040900 +#define VMXNET3_DRIVER_VERSION_NUM 0x01040a00 #if defined(CONFIG_PCI_MSI) /* RSS only makes sense if MSI-X is supported. */ From 6695593e4a7659db49ac6eca98c164f7b5589f72 Mon Sep 17 00:00:00 2001 From: Aleksandr Makarov Date: Sat, 20 Aug 2016 13:29:41 +0300 Subject: [PATCH 182/531] USB: serial: option: add WeTelecom WM-D200 Add support for WeTelecom WM-D200. T: Bus=03 Lev=01 Prnt=01 Port=01 Cnt=01 Dev#= 4 Spd=12 MxCh= 0 D: Ver= 1.10 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=22de ProdID=6801 Rev=00.00 S: Manufacturer=WeTelecom Incorporated S: Product=WeTelecom Mobile Products C: #Ifs= 4 Cfg#= 1 Atr=80 MxPwr=500mA I: If#= 0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) I: If#= 1 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) I: If#= 2 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) I: If#= 3 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=usb-storage Signed-off-by: Aleksandr Makarov Cc: stable Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index bc472584a229..bb6a71120c03 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -525,6 +525,10 @@ static void option_instat_callback(struct urb *urb); #define VIATELECOM_VENDOR_ID 0x15eb #define VIATELECOM_PRODUCT_CDS7 0x0001 +/* WeTelecom products */ +#define WETELECOM_VENDOR_ID 0x22de +#define WETELECOM_PRODUCT_WMD200 0x6801 + struct option_blacklist_info { /* bitmask of interface numbers blacklisted for send_setup */ const unsigned long sendsetup; @@ -1991,6 +1995,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_INTERFACE_CLASS(0x2020, 0x4000, 0xff) }, /* OLICARD300 - MT6225 */ { USB_DEVICE(INOVIA_VENDOR_ID, INOVIA_SEW858) }, { USB_DEVICE(VIATELECOM_VENDOR_ID, VIATELECOM_PRODUCT_CDS7) }, + { USB_DEVICE_AND_INTERFACE_INFO(WETELECOM_VENDOR_ID, WETELECOM_PRODUCT_WMD200, 0xff, 0xff, 0xff) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); From 5575cf133cf7f564da991595c6bc9344afa7d89a Mon Sep 17 00:00:00 2001 From: Daniel Romell Date: Fri, 19 Aug 2016 14:12:01 +0200 Subject: [PATCH 183/531] net: xilinx: emaclite: Fallback to random MAC address. If the address configured in the device tree is invalid, the driver will fallback to using a random address from the locally administered range. Signed-off-by: Daniel Romell Signed-off-by: David S. Miller --- drivers/net/ethernet/xilinx/xilinx_emaclite.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c index 3cee84a24815..93dc10b10c09 100644 --- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c +++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c @@ -1131,11 +1131,13 @@ static int xemaclite_of_probe(struct platform_device *ofdev) lp->rx_ping_pong = get_bool(ofdev, "xlnx,rx-ping-pong"); mac_address = of_get_mac_address(ofdev->dev.of_node); - if (mac_address) + if (mac_address) { /* Set the MAC address. */ memcpy(ndev->dev_addr, mac_address, ETH_ALEN); - else - dev_warn(dev, "No MAC address found\n"); + } else { + dev_warn(dev, "No MAC address found, using random\n"); + eth_hw_addr_random(ndev); + } /* Clear the Tx CSR's in case this is a restart */ __raw_writel(0, lp->base_addr + XEL_TSR_OFFSET); From 522caebb2c3684f4a1d154526fb5e33f1381e92a Mon Sep 17 00:00:00 2001 From: Giorgio Dal Molin Date: Tue, 16 Aug 2016 20:43:37 +0200 Subject: [PATCH 184/531] iio:ti-ads1015: fix a wrong pointer definition. The call to i2c_get_clientdata(client) returns a struct iio_dev*, not the needed struct ads1015_data*. We need here an intermediate step as in the function: void ads1015_get_channels_config(struct i2c_client *client). Signed-off-by: Giorgio Dal Molin Fixes: ecc24e72f437 ("iio: adc: Add TI ADS1015 ADC driver support") Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/adc/ti-ads1015.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/iio/adc/ti-ads1015.c b/drivers/iio/adc/ti-ads1015.c index 1ef398770a1f..066abaf80201 100644 --- a/drivers/iio/adc/ti-ads1015.c +++ b/drivers/iio/adc/ti-ads1015.c @@ -489,7 +489,8 @@ static struct iio_info ads1115_info = { #ifdef CONFIG_OF static int ads1015_get_channels_config_of(struct i2c_client *client) { - struct ads1015_data *data = i2c_get_clientdata(client); + struct iio_dev *indio_dev = i2c_get_clientdata(client); + struct ads1015_data *data = iio_priv(indio_dev); struct device_node *node; if (!client->dev.of_node || From 80e162ee9b31d77d851b10f8c5299132be1e120f Mon Sep 17 00:00:00 2001 From: Ian Abbott Date: Wed, 29 Jun 2016 20:27:44 +0100 Subject: [PATCH 185/531] staging: comedi: daqboard2000: bug fix board type matching code `daqboard2000_find_boardinfo()` is supposed to check if the DaqBoard/2000 series model is supported, based on the PCI subvendor and subdevice ID. The current code is wrong as it is comparing the PCI device's subdevice ID to an expected, fixed value for the subvendor ID. It should be comparing the PCI device's subvendor ID to this fixed value. Correct it. Fixes: 7e8401b23e7f ("staging: comedi: daqboard2000: add back subsystem_device check") Signed-off-by: Ian Abbott Cc: # 3.7+ Signed-off-by: Greg Kroah-Hartman --- drivers/staging/comedi/drivers/daqboard2000.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/staging/comedi/drivers/daqboard2000.c b/drivers/staging/comedi/drivers/daqboard2000.c index 65daef0c00d5..0f4eb954aa80 100644 --- a/drivers/staging/comedi/drivers/daqboard2000.c +++ b/drivers/staging/comedi/drivers/daqboard2000.c @@ -634,7 +634,7 @@ static const void *daqboard2000_find_boardinfo(struct comedi_device *dev, const struct daq200_boardtype *board; int i; - if (pcidev->subsystem_device != PCI_VENDOR_ID_IOTECH) + if (pcidev->subsystem_vendor != PCI_VENDOR_ID_IOTECH) return NULL; for (i = 0; i < ARRAY_SIZE(boardtypes); i++) { From 403fe7f34e3327ddac2e06a15e76a293d613381e Mon Sep 17 00:00:00 2001 From: Ian Abbott Date: Thu, 30 Jun 2016 19:58:32 +0100 Subject: [PATCH 186/531] staging: comedi: comedi_test: fix timer race conditions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 73e0e4dfed4c ("staging: comedi: comedi_test: fix timer lock-up") fixed a lock-up in the timer routine `waveform_ai_timer()` (which was called `waveform_ai_interrupt()` at the time) caused by commit 240512474424 ("staging: comedi: comedi_test: use comedi_handle_events()"). However, it introduced a race condition that can result in the timer routine misbehaving, such as accessing freed memory or dereferencing a NULL pointer. 73e0... changed the timer routine to do nothing unless a `WAVEFORM_AI_RUNNING` flag was set, and changed `waveform_ai_cancel()` to clear the flag and replace a call to `del_timer_sync()` with a call to `del_timer()`. `waveform_ai_cancel()` may be called from the timer routine itself (via `comedi_handle_events()`), or from `do_cancel()`. (`do_cancel()` is called as a result of a file operation (usually a `COMEDI_CANCEL` ioctl command, or a release), or during device removal.) When called from `do_cancel()`, the call to `waveform_ai_cancel()` is followed by a call to `do_become_nonbusy()`, which frees up stuff for the current asynchronous command under the assumption that it is now safe to do so. The race condition occurs when the timer routine `waveform_ai_timer()` checks the `WAVEFORM_AI_RUNNING` flag just before it is cleared by `waveform_ai_cancel()`, and is still running during the call to `do_become_nonbusy()`. In particular, it can lead to a NULL pointer dereference: BUG: unable to handle kernel NULL pointer dereference at (null) IP: [] waveform_ai_timer+0x17d/0x290 [comedi_test] That corresponds to this line in `waveform_ai_timer()`: unsigned int chanspec = cmd->chanlist[async->cur_chan]; but `do_become_nonbusy()` frees `cmd->chanlist` and sets it to `NULL`. Fix the race by calling `del_timer_sync()` instead of `del_timer()` in `waveform_ai_cancel()` when not in an interrupt context. The only time `waveform_ai_cancel()` is called in an interrupt context is when it is called from the timer routine itself, via `comedi_handle_events()`. There is no longer any need for the `WAVEFORM_AI_RUNNING` flag, so get rid of it. The bug was copied from the AI subdevice to the AO when support for commands on the AO subdevice was added by commit 0cf55bbef2f9 ("staging: comedi: comedi_test: implement commands on AO subdevice"). That involves the timer routine `waveform_ao_timer()`, the comedi "cancel" routine `waveform_ao_cancel()`, and the flag `WAVEFORM_AO_RUNNING`. Fix it in the same way as for the AI subdevice. Fixes: 73e0e4dfed4c ("staging: comedi: comedi_test: fix timer lock-up") Fixes: 0cf55bbef2f9 ("staging: comedi: comedi_test: implement commands on AO subdevice") Reported-by: Éric Piel Signed-off-by: Ian Abbott Cc: # 4.4+ Cc: Éric Piel Signed-off-by: Greg Kroah-Hartman --- drivers/staging/comedi/drivers/comedi_test.c | 46 +++++--------------- 1 file changed, 12 insertions(+), 34 deletions(-) diff --git a/drivers/staging/comedi/drivers/comedi_test.c b/drivers/staging/comedi/drivers/comedi_test.c index 4ab186669f0c..ec5b9a23494d 100644 --- a/drivers/staging/comedi/drivers/comedi_test.c +++ b/drivers/staging/comedi/drivers/comedi_test.c @@ -56,11 +56,6 @@ #define N_CHANS 8 -enum waveform_state_bits { - WAVEFORM_AI_RUNNING, - WAVEFORM_AO_RUNNING -}; - /* Data unique to this driver */ struct waveform_private { struct timer_list ai_timer; /* timer for AI commands */ @@ -68,7 +63,6 @@ struct waveform_private { unsigned int wf_amplitude; /* waveform amplitude in microvolts */ unsigned int wf_period; /* waveform period in microseconds */ unsigned int wf_current; /* current time in waveform period */ - unsigned long state_bits; unsigned int ai_scan_period; /* AI scan period in usec */ unsigned int ai_convert_period; /* AI conversion period in usec */ struct timer_list ao_timer; /* timer for AO commands */ @@ -191,10 +185,6 @@ static void waveform_ai_timer(unsigned long arg) unsigned int nsamples; unsigned int time_increment; - /* check command is still active */ - if (!test_bit(WAVEFORM_AI_RUNNING, &devpriv->state_bits)) - return; - now = ktime_to_us(ktime_get()); nsamples = comedi_nsamples_left(s, UINT_MAX); @@ -386,11 +376,6 @@ static int waveform_ai_cmd(struct comedi_device *dev, */ devpriv->ai_timer.expires = jiffies + usecs_to_jiffies(devpriv->ai_convert_period) + 1; - - /* mark command as active */ - smp_mb__before_atomic(); - set_bit(WAVEFORM_AI_RUNNING, &devpriv->state_bits); - smp_mb__after_atomic(); add_timer(&devpriv->ai_timer); return 0; } @@ -400,11 +385,12 @@ static int waveform_ai_cancel(struct comedi_device *dev, { struct waveform_private *devpriv = dev->private; - /* mark command as no longer active */ - clear_bit(WAVEFORM_AI_RUNNING, &devpriv->state_bits); - smp_mb__after_atomic(); - /* cannot call del_timer_sync() as may be called from timer routine */ - del_timer(&devpriv->ai_timer); + if (in_softirq()) { + /* Assume we were called from the timer routine itself. */ + del_timer(&devpriv->ai_timer); + } else { + del_timer_sync(&devpriv->ai_timer); + } return 0; } @@ -436,10 +422,6 @@ static void waveform_ao_timer(unsigned long arg) u64 scans_since; unsigned int scans_avail = 0; - /* check command is still active */ - if (!test_bit(WAVEFORM_AO_RUNNING, &devpriv->state_bits)) - return; - /* determine number of scan periods since last time */ now = ktime_to_us(ktime_get()); scans_since = now - devpriv->ao_last_scan_time; @@ -518,11 +500,6 @@ static int waveform_ao_inttrig_start(struct comedi_device *dev, devpriv->ao_last_scan_time = ktime_to_us(ktime_get()); devpriv->ao_timer.expires = jiffies + usecs_to_jiffies(devpriv->ao_scan_period); - - /* mark command as active */ - smp_mb__before_atomic(); - set_bit(WAVEFORM_AO_RUNNING, &devpriv->state_bits); - smp_mb__after_atomic(); add_timer(&devpriv->ao_timer); return 1; @@ -608,11 +585,12 @@ static int waveform_ao_cancel(struct comedi_device *dev, struct waveform_private *devpriv = dev->private; s->async->inttrig = NULL; - /* mark command as no longer active */ - clear_bit(WAVEFORM_AO_RUNNING, &devpriv->state_bits); - smp_mb__after_atomic(); - /* cannot call del_timer_sync() as may be called from timer routine */ - del_timer(&devpriv->ao_timer); + if (in_softirq()) { + /* Assume we were called from the timer routine itself. */ + del_timer(&devpriv->ao_timer); + } else { + del_timer_sync(&devpriv->ao_timer); + } return 0; } From 5ca05345c56cb979e1a25ab6146437002f95cac8 Mon Sep 17 00:00:00 2001 From: Ian Abbott Date: Wed, 20 Jul 2016 17:07:34 +0100 Subject: [PATCH 187/531] staging: comedi: ni_mio_common: fix wrong insn_write handler MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit For counter subdevices, the `s->insn_write` handler is being set to the wrong function, `ni_tio_insn_read()`. It should be `ni_tio_insn_write()`. Signed-off-by: Ian Abbott Reported-by: Éric Piel Fixes: 10f74377eec3 ("staging: comedi: ni_tio: make ni_tio_winsn() a proper comedi (*insn_write)" Cc: # 3.17+ Signed-off-by: Greg Kroah-Hartman --- drivers/staging/comedi/drivers/ni_mio_common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/staging/comedi/drivers/ni_mio_common.c b/drivers/staging/comedi/drivers/ni_mio_common.c index 8dabb19519a5..3cf3c05c5ef2 100644 --- a/drivers/staging/comedi/drivers/ni_mio_common.c +++ b/drivers/staging/comedi/drivers/ni_mio_common.c @@ -5480,7 +5480,7 @@ static int ni_E_init(struct comedi_device *dev, s->maxdata = (devpriv->is_m_series) ? 0xffffffff : 0x00ffffff; s->insn_read = ni_tio_insn_read; - s->insn_write = ni_tio_insn_read; + s->insn_write = ni_tio_insn_write; s->insn_config = ni_tio_insn_config; #ifdef PCIDMA if (dev->irq && devpriv->mite) { From c71f20ee76342376e3c4c67cdbe7421d8c4e886e Mon Sep 17 00:00:00 2001 From: Phil Turnbull Date: Fri, 29 Jul 2016 09:43:56 -0400 Subject: [PATCH 188/531] staging: comedi: adv_pci1760: Do not return EINVAL for CMDF_ROUND_DOWN. The CMDF_ROUND_DOWN case falls through and so always returns -EINVAL. Fixes: 14b93bb6bbf0 ("staging: comedi: adv_pci_dio: separate out PCI-1760 support") Signed-off-by: Phil Turnbull Reviewed-by: Ian Abbott Signed-off-by: Greg Kroah-Hartman --- drivers/staging/comedi/drivers/adv_pci1760.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/staging/comedi/drivers/adv_pci1760.c b/drivers/staging/comedi/drivers/adv_pci1760.c index d7dd1e55e347..9f525ff7290c 100644 --- a/drivers/staging/comedi/drivers/adv_pci1760.c +++ b/drivers/staging/comedi/drivers/adv_pci1760.c @@ -196,6 +196,7 @@ static int pci1760_pwm_ns_to_div(unsigned int flags, unsigned int ns) break; case CMDF_ROUND_DOWN: divisor = ns / PCI1760_PWM_TIMEBASE; + break; default: return -EINVAL; } From 5ac5c3bcf57419d0aa3f53b12b8c07599a13fdcc Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 21 Jun 2016 14:46:21 +0300 Subject: [PATCH 189/531] staging: comedi: dt2811: fix a precedence bug Bitwise | has higher precedence than ?: so we need to add some parenthesis for this to work as intended. Fixes: 7c9574090d30 ('staging: comedi: dt2811: simplify A/D reference configuration') Signed-off-by: Dan Carpenter Reviewed-by: Ian Abbott Signed-off-by: Greg Kroah-Hartman --- drivers/staging/comedi/drivers/dt2811.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/staging/comedi/drivers/dt2811.c b/drivers/staging/comedi/drivers/dt2811.c index 904f637797b6..8bbd93814340 100644 --- a/drivers/staging/comedi/drivers/dt2811.c +++ b/drivers/staging/comedi/drivers/dt2811.c @@ -588,8 +588,8 @@ static int dt2811_attach(struct comedi_device *dev, struct comedi_devconfig *it) s = &dev->subdevices[0]; s->type = COMEDI_SUBD_AI; s->subdev_flags = SDF_READABLE | - (it->options[2] == 1) ? SDF_DIFF : - (it->options[2] == 2) ? SDF_COMMON : SDF_GROUND; + ((it->options[2] == 1) ? SDF_DIFF : + (it->options[2] == 2) ? SDF_COMMON : SDF_GROUND); s->n_chan = (it->options[2] == 1) ? 8 : 16; s->maxdata = 0x0fff; s->range_table = board->is_pgh ? &dt2811_pgh_ai_ranges From f0f4b0cc3a8cffd983f5940d46cd0227f3f5710a Mon Sep 17 00:00:00 2001 From: Ian Abbott Date: Tue, 19 Jul 2016 12:17:39 +0100 Subject: [PATCH 190/531] staging: comedi: ni_mio_common: fix AO inttrig backwards compatibility Commit ebb657babfa9 ("staging: comedi: ni_mio_common: clarify the cmd->start_arg validation and use") introduced a backwards compatibility issue in the use of asynchronous commands on the AO subdevice when `start_src` is `TRIG_EXT`. Valid values for `start_src` are `TRIG_INT` (for internal, software trigger), and `TRIG_EXT` (for external trigger). When set to `TRIG_EXT`. In both cases, the driver relies on an internal, software trigger to set things up (allowing the user application to write sufficient samples to the data buffer before the trigger), so it acts as a software "pre-trigger" in the `TRIG_EXT` case. The software trigger is handled by `ni_ao_inttrig()`. Prior to the above change, when `start_src` was `TRIG_INT`, `start_arg` was required to be 0, and `ni_ao_inttrig()` checked that the software trigger number was also 0. After the above change, when `start_src` was `TRIG_INT`, any value was allowed for `start_arg`, and `ni_ao_inttrig()` checked that the software trigger number matched this `start_arg` value. The backwards compatibility issue is that the internal trigger number now has to match `start_arg` when `start_src` is `TRIG_EXT` when it previously had to be 0. Fix the backwards compatibility issue in `ni_ao_inttrig()` by always allowing software trigger number 0 when `start_src` is something other than `TRIG_INT`. Thanks to Spencer Olson for reporting the issue. Signed-off-by: Ian Abbott Reported-by: Spencer Olson Fixes: ebb657babfa9 ("staging: comedi: ni_mio_common: clarify the cmd->start_arg validation and use") Cc: stable Reviewed-by: H Hartley Sweeten Signed-off-by: Greg Kroah-Hartman --- drivers/staging/comedi/drivers/ni_mio_common.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/staging/comedi/drivers/ni_mio_common.c b/drivers/staging/comedi/drivers/ni_mio_common.c index 3cf3c05c5ef2..0f97d7b611d7 100644 --- a/drivers/staging/comedi/drivers/ni_mio_common.c +++ b/drivers/staging/comedi/drivers/ni_mio_common.c @@ -2772,7 +2772,15 @@ static int ni_ao_inttrig(struct comedi_device *dev, int i; static const int timeout = 1000; - if (trig_num != cmd->start_arg) + /* + * Require trig_num == cmd->start_arg when cmd->start_src == TRIG_INT. + * For backwards compatibility, also allow trig_num == 0 when + * cmd->start_src != TRIG_INT (i.e. when cmd->start_src == TRIG_EXT); + * in that case, the internal trigger is being used as a pre-trigger + * before the external trigger. + */ + if (!(trig_num == cmd->start_arg || + (trig_num == 0 && cmd->start_src != TRIG_INT))) return -EINVAL; /* From fcf68f3c0bb2a541aa47a2a38b8939edf84fd529 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Mon, 8 Aug 2016 17:19:38 -0700 Subject: [PATCH 191/531] iio: fix sched WARNING "do not call blocking ops when !TASK_RUNNING" When using CONFIG_DEBUG_ATOMIC_SLEEP, the scheduler nicely points out that we're calling sleeping primitives within the wait_event loop, which means we might clobber the task state: [ 10.831289] do not call blocking ops when !TASK_RUNNING; state=1 set at [] [ 10.845531] ------------[ cut here ]------------ [ 10.850161] WARNING: at kernel/sched/core.c:7630 ... [ 12.164333] ---[ end trace 45409966a9a76438 ]--- [ 12.168942] Call trace: [ 12.171391] [] __might_sleep+0x64/0x90 [ 12.176699] [] mutex_lock_nested+0x50/0x3fc [ 12.182440] [] iio_kfifo_buf_data_available+0x28/0x4c [ 12.189043] [] iio_buffer_ready+0x60/0xe0 [ 12.194608] [] iio_buffer_read_first_n_outer+0x108/0x1a8 [ 12.201474] [] __vfs_read+0x58/0x114 [ 12.206606] [] vfs_read+0x94/0x118 [ 12.211564] [] SyS_read+0x64/0xb4 [ 12.216436] [] el0_svc_naked+0x24/0x28 To avoid this, we should (a la https://lwn.net/Articles/628628/) use the wait_woken() function, which avoids the nested sleeping while still handling races between waiting / wake-events. Signed-off-by: Brian Norris Reviewed-by: Lars-Peter Clausen Cc: # 3.19+ for introduction of wake_woken Signed-off-by: Jonathan Cameron --- drivers/iio/industrialio-buffer.c | 23 +++++++++++++++++------ 1 file changed, 17 insertions(+), 6 deletions(-) diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c index 90462fcf5436..49bf9c59f117 100644 --- a/drivers/iio/industrialio-buffer.c +++ b/drivers/iio/industrialio-buffer.c @@ -107,6 +107,7 @@ ssize_t iio_buffer_read_first_n_outer(struct file *filp, char __user *buf, { struct iio_dev *indio_dev = filp->private_data; struct iio_buffer *rb = indio_dev->buffer; + DEFINE_WAIT_FUNC(wait, woken_wake_function); size_t datum_size; size_t to_wait; int ret; @@ -131,19 +132,29 @@ ssize_t iio_buffer_read_first_n_outer(struct file *filp, char __user *buf, else to_wait = min_t(size_t, n / datum_size, rb->watermark); + add_wait_queue(&rb->pollq, &wait); do { - ret = wait_event_interruptible(rb->pollq, - iio_buffer_ready(indio_dev, rb, to_wait, n / datum_size)); - if (ret) - return ret; + if (!indio_dev->info) { + ret = -ENODEV; + break; + } - if (!indio_dev->info) - return -ENODEV; + if (!iio_buffer_ready(indio_dev, rb, to_wait, n / datum_size)) { + if (signal_pending(current)) { + ret = -ERESTARTSYS; + break; + } + + wait_woken(&wait, TASK_INTERRUPTIBLE, + MAX_SCHEDULE_TIMEOUT); + continue; + } ret = rb->access->read_first_n(rb, n, buf); if (ret == 0 && (filp->f_flags & O_NONBLOCK)) ret = -EAGAIN; } while (ret == 0); + remove_wait_queue(&rb->pollq, &wait); return ret; } From ca64d4bc80a88845f7e1e266dbff798f928bcc06 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Mon, 25 Jul 2016 23:06:56 +0100 Subject: [PATCH 192/531] iio: chemical: atlas-ph-sensor: fix typo in val assignment Fix an incorrect assignment due to a typo on a variable name. The variable val2 should be assigned 100000 and not val. Signed-off-by: Colin Ian King Reviewed-By: Matt Ranostay Signed-off-by: Jonathan Cameron --- drivers/iio/chemical/atlas-ph-sensor.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/chemical/atlas-ph-sensor.c b/drivers/iio/chemical/atlas-ph-sensor.c index ae038a59d256..407f141a1eee 100644 --- a/drivers/iio/chemical/atlas-ph-sensor.c +++ b/drivers/iio/chemical/atlas-ph-sensor.c @@ -434,7 +434,7 @@ static int atlas_read_raw(struct iio_dev *indio_dev, break; case IIO_ELECTRICALCONDUCTIVITY: *val = 1; /* 0.00001 */ - *val = 100000; + *val2 = 100000; break; case IIO_CONCENTRATION: *val = 0; /* 0.000000001 */ From d9a8594011080def9202f2c258f755647fe66683 Mon Sep 17 00:00:00 2001 From: Aditya Shankar Date: Tue, 2 Aug 2016 11:49:00 +0200 Subject: [PATCH 193/531] MAINTAINERS: Update maintainer entry for wilc1000 Take the maintenance of the Atmel WIFI staging driver wilc1000. Former maintainers are no more with Atmel. Reported-by: Loic Lefort Signed-off-by: Aditya Shankar Signed-off-by: Ganesh Krishna Acked-by: Luis de Bethencourt Signed-off-by: Nicolas Ferre Signed-off-by: Greg Kroah-Hartman --- MAINTAINERS | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index a306795a7450..09c7066c82ed 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11217,12 +11217,8 @@ S: Odd Fixes F: drivers/staging/vt665?/ STAGING - WILC1000 WIFI DRIVER -M: Johnny Kim -M: Austin Shin -M: Chris Park -M: Tony Cho -M: Glen Lee -M: Leo Kim +M: Aditya Shankar +M: Ganesh Krishna L: linux-wireless@vger.kernel.org S: Supported F: drivers/staging/wilc1000/ From e9d766b965a15816cf9ec353d86c11f27b783d4d Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Sun, 22 May 2016 11:05:38 +0200 Subject: [PATCH 194/531] MAINTAINERS: Add file patterns for ion device tree bindings Submitters of device tree binding documentation may forget to CC the subsystem maintainer if this is missing. Signed-off-by: Geert Uytterhoeven Cc: Sumit Semwal Cc: devel@driverdev.osuosl.org Acked-by: Laura Abbott Signed-off-by: Greg Kroah-Hartman --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 09c7066c82ed..e614392ede4f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -798,6 +798,7 @@ M: Laura Abbott M: Sumit Semwal L: devel@driverdev.osuosl.org S: Supported +F: Documentation/devicetree/bindings/staging/ion/ F: drivers/staging/android/ion F: drivers/staging/android/uapi/ion.h F: drivers/staging/android/uapi/ion_test.h From 23535c1322e42e71f32bfbeae9970f4dba31e3bd Mon Sep 17 00:00:00 2001 From: Binoy Jayan Date: Thu, 21 Jul 2016 13:26:56 +0530 Subject: [PATCH 195/531] staging: wilc1000: txq_event: Fix coding error Fix incorrect usage of completion interface by replacing 'wait_for_completion' with 'complete'. This error was introduced accidentally while replacing semaphores with mutexes. Reported-by: Jiri Slaby Signed-off-by: Binoy Jayan Signed-off-by: Greg Kroah-Hartman --- drivers/staging/wilc1000/linux_wlan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/staging/wilc1000/linux_wlan.c b/drivers/staging/wilc1000/linux_wlan.c index 3a66255f14fc..32215110d597 100644 --- a/drivers/staging/wilc1000/linux_wlan.c +++ b/drivers/staging/wilc1000/linux_wlan.c @@ -648,7 +648,7 @@ void wilc1000_wlan_deinit(struct net_device *dev) mutex_unlock(&wl->hif_cs); } if (&wl->txq_event) - wait_for_completion(&wl->txq_event); + complete(&wl->txq_event); wlan_deinitialize_threads(dev); deinit_irq(dev); From 23436825e671cdd55c45d151ddc66fd3c47d10e9 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Sat, 16 Jul 2016 13:07:55 +0300 Subject: [PATCH 196/531] staging: wilc1000: NULL dereference on error We can't pass NULL pointers to destroy_workqueue(). Signed-off-by: Dan Carpenter Signed-off-by: Greg Kroah-Hartman --- drivers/staging/wilc1000/host_interface.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/staging/wilc1000/host_interface.c b/drivers/staging/wilc1000/host_interface.c index 0b1760cba6e3..78f524fcd214 100644 --- a/drivers/staging/wilc1000/host_interface.c +++ b/drivers/staging/wilc1000/host_interface.c @@ -3363,7 +3363,7 @@ int wilc_init(struct net_device *dev, struct host_if_drv **hif_drv_handler) if (!hif_workqueue) { netdev_err(vif->ndev, "Failed to create workqueue\n"); result = -ENOMEM; - goto _fail_mq_; + goto _fail_; } setup_timer(&periodic_rssi, GetPeriodicRSSI, @@ -3391,7 +3391,6 @@ int wilc_init(struct net_device *dev, struct host_if_drv **hif_drv_handler) clients_count++; -_fail_mq_: destroy_workqueue(hif_workqueue); _fail_: return result; From 6c08fda0306916135291103f23cc17248c422c49 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Mon, 15 Aug 2016 17:09:52 +0100 Subject: [PATCH 197/531] staging: wilc1000: correctly check if associatedsta has not been found The current check for associatedsta being set to -1 to indicate it has not been found is not working because associatedsta is initialized to zero and will never be -1. Fix this by initializing it to ~0 and checking for ~0 instead. Signed-off-by: Colin Ian King Signed-off-by: Greg Kroah-Hartman --- drivers/staging/wilc1000/wilc_wfi_cfgoperations.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/staging/wilc1000/wilc_wfi_cfgoperations.c b/drivers/staging/wilc1000/wilc_wfi_cfgoperations.c index 9092600a1794..2c2e8aca8305 100644 --- a/drivers/staging/wilc1000/wilc_wfi_cfgoperations.c +++ b/drivers/staging/wilc1000/wilc_wfi_cfgoperations.c @@ -1191,7 +1191,7 @@ static int get_station(struct wiphy *wiphy, struct net_device *dev, struct wilc_priv *priv; struct wilc_vif *vif; u32 i = 0; - u32 associatedsta = 0; + u32 associatedsta = ~0; u32 inactive_time = 0; priv = wiphy_priv(wiphy); vif = netdev_priv(dev); @@ -1204,7 +1204,7 @@ static int get_station(struct wiphy *wiphy, struct net_device *dev, } } - if (associatedsta == -1) { + if (associatedsta == ~0) { netdev_err(dev, "sta required is not associated\n"); return -ENOENT; } From c0678b2d6648ab65b68703044709e367799ba9f9 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 15 Aug 2016 15:52:23 -0700 Subject: [PATCH 198/531] include/linux: fix excess fence.h kernel-doc notation Fix excess fields in kernel-doc notation in after some struct fields were removed. Fixes these kernel-doc warnings: ..//include/linux/fence.h:85: warning: Excess struct/union/enum/typedef member 'child_list' description in 'fence' ..//include/linux/fence.h:85: warning: Excess struct/union/enum/typedef member 'active_list' description in 'fence' Fixes: 0431b9065f28 ("staging/android: bring struct sync_pt back") Cc: Daniel Vetter Cc: Sumit Semwal Cc: Luis de Bethencourt Signed-off-by: Randy Dunlap Reviewed-by: Gustavo Padovan Signed-off-by: Greg Kroah-Hartman --- include/linux/fence.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/include/linux/fence.h b/include/linux/fence.h index 8cc719a63728..2ac6fa5f4712 100644 --- a/include/linux/fence.h +++ b/include/linux/fence.h @@ -49,8 +49,6 @@ struct fence_cb; * @timestamp: Timestamp when the fence was signaled. * @status: Optional, only valid if < 0, must be set before calling * fence_signal, indicates that the fence has completed with an error. - * @child_list: list of children fences - * @active_list: list of active fences * * the flags member must be manipulated and read using the appropriate * atomic ops (bit_*), so taking the spinlock will not be needed most From 90c43ec6997a892448f1f86180a515f59cafd8a3 Mon Sep 17 00:00:00 2001 From: Vignesh R Date: Wed, 17 Aug 2016 17:43:00 +0530 Subject: [PATCH 199/531] iio: adc: ti_am335x_adc: Protect FIFO1 from concurrent access It is possible that two or more ADC channels can be simultaneously requested for raw samples, in which case there can be race in access to FIFO data resulting in loss of samples. If am335x_tsc_se_set_once() is called again from tiadc_read_raw(), when ADC is still acquired to sample one of the channels, the second process might be put into uninterruptible sleep state. Fix these issues, by protecting FIFO access and channel configurations with a mutex. Since tiadc_read_raw() might take anywhere between few microseconds to few milliseconds to finish execution (depending on averaging and delay values supplied via DT), its better to use mutex instead of spinlock. Fixes: 7ca6740cd1cd4 ("mfd: input: iio: ti_amm335x: Rework TSC/ADC synchronization") Signed-off-by: Vignesh R Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/adc/ti_am335x_adc.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c index 8a368756881b..bed9977a1863 100644 --- a/drivers/iio/adc/ti_am335x_adc.c +++ b/drivers/iio/adc/ti_am335x_adc.c @@ -32,6 +32,7 @@ struct tiadc_device { struct ti_tscadc_dev *mfd_tscadc; + struct mutex fifo1_lock; /* to protect fifo access */ int channels; u8 channel_line[8]; u8 channel_step[8]; @@ -359,6 +360,7 @@ static int tiadc_read_raw(struct iio_dev *indio_dev, int *val, int *val2, long mask) { struct tiadc_device *adc_dev = iio_priv(indio_dev); + int ret = IIO_VAL_INT; int i, map_val; unsigned int fifo1count, read, stepid; bool found = false; @@ -372,6 +374,7 @@ static int tiadc_read_raw(struct iio_dev *indio_dev, if (!step_en) return -EINVAL; + mutex_lock(&adc_dev->fifo1_lock); fifo1count = tiadc_readl(adc_dev, REG_FIFO1CNT); while (fifo1count--) tiadc_readl(adc_dev, REG_FIFO1); @@ -388,7 +391,8 @@ static int tiadc_read_raw(struct iio_dev *indio_dev, if (time_after(jiffies, timeout)) { am335x_tsc_se_adc_done(adc_dev->mfd_tscadc); - return -EAGAIN; + ret = -EAGAIN; + goto err_unlock; } } map_val = adc_dev->channel_step[chan->scan_index]; @@ -414,8 +418,11 @@ static int tiadc_read_raw(struct iio_dev *indio_dev, am335x_tsc_se_adc_done(adc_dev->mfd_tscadc); if (found == false) - return -EBUSY; - return IIO_VAL_INT; + ret = -EBUSY; + +err_unlock: + mutex_unlock(&adc_dev->fifo1_lock); + return ret; } static const struct iio_info tiadc_info = { @@ -483,6 +490,7 @@ static int tiadc_probe(struct platform_device *pdev) tiadc_step_config(indio_dev); tiadc_writel(adc_dev, REG_FIFO1THR, FIFO1_THRESHOLD); + mutex_init(&adc_dev->fifo1_lock); err = tiadc_channel_init(indio_dev, adc_dev->channels); if (err < 0) From 7175cce1c3f1d8c8840d2004f78f96a3904249b5 Mon Sep 17 00:00:00 2001 From: Vignesh R Date: Wed, 17 Aug 2016 17:43:01 +0530 Subject: [PATCH 200/531] iio: adc: ti_am335x_adc: Increase timeout value waiting for ADC sample Now that open delay and sample delay for each channel is configurable via DT, the default IDLE_TIMEOUT value is not enough as this is calculated based on hardcoded macros. This results in driver returning EBUSY sometimes. Fix this by increasing the timeout value based on maximum value possible to open delay and sample delays for each channel. Fixes: 5dc11e810676e ("iio: adc: ti_am335x_adc: make sample delay, open delay, averaging DT parameters") Signed-off-by: Vignesh R Acked-by: Lee Jones Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/adc/ti_am335x_adc.c | 2 +- include/linux/mfd/ti_am335x_tscadc.h | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c index bed9977a1863..c3cfacca2541 100644 --- a/drivers/iio/adc/ti_am335x_adc.c +++ b/drivers/iio/adc/ti_am335x_adc.c @@ -381,7 +381,7 @@ static int tiadc_read_raw(struct iio_dev *indio_dev, am335x_tsc_se_set_once(adc_dev->mfd_tscadc, step_en); - timeout = jiffies + usecs_to_jiffies + timeout = jiffies + msecs_to_jiffies (IDLE_TIMEOUT * adc_dev->channels); /* Wait for Fifo threshold interrupt */ while (1) { diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index 2567a87872b0..7f55b8b41032 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -138,16 +138,16 @@ /* * time in us for processing a single channel, calculated as follows: * - * num cycles = open delay + (sample delay + conv time) * averaging + * max num cycles = open delay + (sample delay + conv time) * averaging * - * num cycles: 152 + (1 + 13) * 16 = 376 + * max num cycles: 262143 + (255 + 13) * 16 = 266431 * * clock frequency: 26MHz / 8 = 3.25MHz * clock period: 1 / 3.25MHz = 308ns * - * processing time: 376 * 308ns = 116us + * max processing time: 266431 * 308ns = 83ms(approx) */ -#define IDLE_TIMEOUT 116 /* microsec */ +#define IDLE_TIMEOUT 83 /* milliseconds */ #define TSCADC_CELLS 2 From 7ac61a062f3147dc23e3f12b9dfe7c4dd35f9cb8 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 16 Aug 2016 15:33:28 +0200 Subject: [PATCH 201/531] iio: accel: kxsd9: Fix raw read return Any readings from the raw interface of the KXSD9 driver will return an empty string, because it does not return IIO_VAL_INT but rather some random value from the accelerometer to the caller. Cc: stable@vger.kernel.org Signed-off-by: Linus Walleij Signed-off-by: Jonathan Cameron --- drivers/iio/accel/kxsd9.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iio/accel/kxsd9.c b/drivers/iio/accel/kxsd9.c index 3a9f106787d2..da5fb67ecb34 100644 --- a/drivers/iio/accel/kxsd9.c +++ b/drivers/iio/accel/kxsd9.c @@ -160,6 +160,7 @@ static int kxsd9_read_raw(struct iio_dev *indio_dev, if (ret < 0) goto error_ret; *val = ret; + ret = IIO_VAL_INT; break; case IIO_CHAN_INFO_SCALE: ret = spi_w8r8(st->us, KXSD9_READ(KXSD9_REG_CTRL_C)); From d524d84b588e300418a99794eb5066683ec7c488 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Sun, 21 Aug 2016 15:24:33 +0100 Subject: [PATCH 202/531] net: tehuti: fix typo: "eneble" -> "enable" trivial typo fix in pr_err message Signed-off-by: Colin Ian King Signed-off-by: David S. Miller --- drivers/net/ethernet/tehuti/tehuti.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c index 7452b5f9d024..7108c68f16d3 100644 --- a/drivers/net/ethernet/tehuti/tehuti.c +++ b/drivers/net/ethernet/tehuti/tehuti.c @@ -1987,7 +1987,7 @@ bdx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if ((readl(nic->regs + FPGA_VER) & 0xFFF) >= 378) { err = pci_enable_msi(pdev); if (err) - pr_err("Can't eneble msi. error is %d\n", err); + pr_err("Can't enable msi. error is %d\n", err); else nic->irq_type = IRQ_MSI; } else From e340eca90ee18547027a6d5745ffabf7d173dfcc Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Sun, 14 Aug 2016 13:53:17 -0700 Subject: [PATCH 203/531] powerpc: cputhreads: Add missing include file Powerpc builds may fail with the following build error. Error log: In file included from ./arch/powerpc/include/asm/mmu_context.h:11:0, from ./include/linux/mmu_context.h:4, from mm/mmu_context.c:8: ./arch/powerpc/include/asm/cputhreads.h: In function 'get_tensr': ./arch/powerpc/include/asm/cputhreads.h:101:2: error: implicit declaration of function 'cpu_has_feature' The problem can be triggered by configuring ppc64e_defconfig and selecting CONFIG_TICK_CPU_ACCOUNTING instead of CONFIG_VIRT_CPU_ACCOUNTING_NATIVE. Fixes: b92a226e5284 ("powerpc: Move cpu_has_feature() to a separate file") Signed-off-by: Guenter Roeck Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/cputhreads.h | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h index 666bef4ebfae..9377bdf42eb8 100644 --- a/arch/powerpc/include/asm/cputhreads.h +++ b/arch/powerpc/include/asm/cputhreads.h @@ -3,6 +3,7 @@ #ifndef __ASSEMBLY__ #include +#include /* * Mapping of threads to cores From aded76bac54d1dd0a9c9203aa29a78423edc4cde Mon Sep 17 00:00:00 2001 From: Markus Elfring Date: Sun, 14 Aug 2016 21:42:17 +0200 Subject: [PATCH 204/531] drivers/macintosh: Delete owner assignment The field "owner" is set by core. Thus delete an extra initialisation. Generated by: scripts/coccinelle/api/platform_no_drv_owner.cocci Signed-off-by: Markus Elfring Signed-off-by: Benjamin Herrenschmidt --- drivers/macintosh/ams/ams-i2c.c | 1 - drivers/macintosh/windfarm_pm112.c | 1 - drivers/macintosh/windfarm_pm72.c | 1 - drivers/macintosh/windfarm_rm31.c | 1 - 4 files changed, 4 deletions(-) diff --git a/drivers/macintosh/ams/ams-i2c.c b/drivers/macintosh/ams/ams-i2c.c index 978eda8d6678..8a3ba565106f 100644 --- a/drivers/macintosh/ams/ams-i2c.c +++ b/drivers/macintosh/ams/ams-i2c.c @@ -73,7 +73,6 @@ MODULE_DEVICE_TABLE(i2c, ams_id); static struct i2c_driver ams_i2c_driver = { .driver = { .name = "ams", - .owner = THIS_MODULE, }, .probe = ams_i2c_probe, .remove = ams_i2c_remove, diff --git a/drivers/macintosh/windfarm_pm112.c b/drivers/macintosh/windfarm_pm112.c index 3024685e4cca..96d16fca68b2 100644 --- a/drivers/macintosh/windfarm_pm112.c +++ b/drivers/macintosh/windfarm_pm112.c @@ -668,7 +668,6 @@ static struct platform_driver wf_pm112_driver = { .remove = wf_pm112_remove, .driver = { .name = "windfarm", - .owner = THIS_MODULE, }, }; diff --git a/drivers/macintosh/windfarm_pm72.c b/drivers/macintosh/windfarm_pm72.c index 2f506b9d5a52..e88cfb36a74d 100644 --- a/drivers/macintosh/windfarm_pm72.c +++ b/drivers/macintosh/windfarm_pm72.c @@ -789,7 +789,6 @@ static struct platform_driver wf_pm72_driver = { .remove = wf_pm72_remove, .driver = { .name = "windfarm", - .owner = THIS_MODULE, }, }; diff --git a/drivers/macintosh/windfarm_rm31.c b/drivers/macintosh/windfarm_rm31.c index 82fc86a90c1a..bdfcb8a8bfbb 100644 --- a/drivers/macintosh/windfarm_rm31.c +++ b/drivers/macintosh/windfarm_rm31.c @@ -682,7 +682,6 @@ static struct platform_driver wf_rm31_driver = { .remove = wf_rm31_remove, .driver = { .name = "windfarm", - .owner = THIS_MODULE, }, }; From e72e799c0901b689c83468623cfcb85df431e882 Mon Sep 17 00:00:00 2001 From: Markus Elfring Date: Mon, 15 Aug 2016 22:07:54 +0200 Subject: [PATCH 205/531] powerpc/512x: Delete unnecessary assignment for the field "owner" The field "owner" is set by the core. Thus delete an unneeded initialisation. Generated by: scripts/coccinelle/api/platform_no_drv_owner.cocci Signed-off-by: Markus Elfring Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/512x/mpc512x_lpbfifo.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c b/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c index 8eb82b043dd8..d93dd4acf40b 100644 --- a/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c +++ b/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c @@ -528,7 +528,6 @@ static struct platform_driver mpc512x_lpbfifo_driver = { .remove = mpc512x_lpbfifo_remove, .driver = { .name = DRV_NAME, - .owner = THIS_MODULE, .of_match_table = mpc512x_lpbfifo_match, }, }; From f5ed841ce75ca33f413c394110d6dc002c097b01 Mon Sep 17 00:00:00 2001 From: Markus Elfring Date: Mon, 15 Aug 2016 22:36:05 +0200 Subject: [PATCH 206/531] powerpc: mpc8349emitx: Delete unnecessary assignment for the field "owner" The field "owner" is set by the core. Thus delete an unneeded initialisation. Generated by: scripts/coccinelle/api/platform_no_drv_owner.cocci Signed-off-by: Markus Elfring Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c index dbcd0303afed..63c5ab6489c9 100644 --- a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c +++ b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c @@ -222,7 +222,6 @@ static const struct of_device_id mcu_of_match_table[] = { static struct i2c_driver mcu_driver = { .driver = { .name = "mcu-mpc8349emitx", - .owner = THIS_MODULE, .of_match_table = mcu_of_match_table, }, .probe = mcu_probe, From 6f38a8b9a45833495dc878c335c5431cd98a16ed Mon Sep 17 00:00:00 2001 From: Andrew Donnellan Date: Thu, 18 Aug 2016 17:35:14 +1000 Subject: [PATCH 207/531] cxl: use pcibios_free_controller_deferred() when removing vPHBs When cxl removes a vPHB, it's possible that the pci_controller may be freed before all references to the devices on the vPHB have been released. This in turn causes an invalid memory access when the devices are eventually released, as pcibios_release_device() attempts to call the phb's release_device hook. In cxl_pci_vphb_remove(), remove the existing call to pcibios_free_controller(). Instead, use pcibios_free_controller_deferred() to free the pci_controller after all devices have been released. Export pci_set_host_bridge_release() so we can do this. Cc: stable@vger.kernel.org Signed-off-by: Andrew Donnellan Reviewed-by: Matthew R. Ochs Acked-by: Ian Munsie Signed-off-by: Benjamin Herrenschmidt --- drivers/misc/cxl/vphb.c | 10 +++++++++- drivers/pci/host-bridge.c | 1 + 2 files changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/misc/cxl/vphb.c b/drivers/misc/cxl/vphb.c index 7ada5f1b7bb6..3519acebfdab 100644 --- a/drivers/misc/cxl/vphb.c +++ b/drivers/misc/cxl/vphb.c @@ -230,6 +230,11 @@ int cxl_pci_vphb_add(struct cxl_afu *afu) if (phb->bus == NULL) return -ENXIO; + /* Set release hook on root bus */ + pci_set_host_bridge_release(to_pci_host_bridge(phb->bus->bridge), + pcibios_free_controller_deferred, + (void *) phb); + /* Claim resources. This might need some rework as well depending * whether we are doing probe-only or not, like assigning unassigned * resources etc... @@ -256,7 +261,10 @@ void cxl_pci_vphb_remove(struct cxl_afu *afu) afu->phb = NULL; pci_remove_root_bus(phb->bus); - pcibios_free_controller(phb); + /* + * We don't free phb here - that's handled by + * pcibios_free_controller_deferred() + */ } static bool _cxl_pci_is_vphb_device(struct pci_controller *phb) diff --git a/drivers/pci/host-bridge.c b/drivers/pci/host-bridge.c index 5f4a2e04c8d7..add66236215c 100644 --- a/drivers/pci/host-bridge.c +++ b/drivers/pci/host-bridge.c @@ -44,6 +44,7 @@ void pci_set_host_bridge_release(struct pci_host_bridge *bridge, bridge->release_fn = release_fn; bridge->release_data = release_data; } +EXPORT_SYMBOL_GPL(pci_set_host_bridge_release); void pcibios_resource_to_bus(struct pci_bus *bus, struct pci_bus_region *region, struct resource *res) From 2dd9c11b9d4dfbd6c070eab7b81197f65e82f1a0 Mon Sep 17 00:00:00 2001 From: Mauricio Faria de Oliveira Date: Thu, 11 Aug 2016 17:25:40 -0300 Subject: [PATCH 208/531] powerpc/pseries: use pci_host_bridge.release_fn() to kfree(phb) This patch leverages 'struct pci_host_bridge' from the PCI subsystem in order to free the pci_controller only after the last reference to its devices is dropped (avoiding an oops in pcibios_release_device() if the last reference is dropped after pcibios_free_controller()). The patch relies on pci_host_bridge.release_fn() (and .release_data), which is called automatically by the PCI subsystem when the root bus is released (i.e., the last reference is dropped). Those fields are set via pci_set_host_bridge_release() (e.g. in the platform-specific implementation of pcibios_root_bridge_prepare()). It introduces the 'pcibios_free_controller_deferred()' .release_fn() and it expects .release_data to hold a pointer to the pci_controller. The function implictly calls 'pcibios_free_controller()', so an user must *NOT* explicitly call it if using the new _deferred() callback. The functionality is enabled for pseries (although it isn't platform specific, and may be used by cxl). Details on not-so-elegant design choices: - Use 'pci_host_bridge.release_data' field as pointer to associated 'struct pci_controller' so *not* to 'pci_bus_to_host(bridge->bus)' in pcibios_free_controller_deferred(). That's because pci_remove_root_bus() sets 'host_bridge->bus = NULL' (so, if the last reference is released after pci_remove_root_bus() runs, which eventually reaches pcibios_free_controller_deferred(), that would hit a null pointer dereference). The cxl/vphb.c code calls pci_remove_root_bus(), and the cxl folks are interested in this fix. Test-case #1 (hold references) # ls -ld /sys/block/sd* | grep -m1 0021:01:00.0 <...> /sys/block/sdaa -> ../devices/pci0021:01/0021:01:00.0/<...> # ls -ld /sys/block/sd* | grep -m1 0021:01:00.1 <...> /sys/block/sdab -> ../devices/pci0021:01/0021:01:00.1/<...> # cat >/dev/sdaa & pid1=$! # cat >/dev/sdab & pid2=$! # drmgr -w 5 -d 1 -c phb -s 'PHB 33' -r Validating PHB DLPAR capability...yes. [ 594.306719] pci_hp_remove_devices: PCI: Removing devices on bus 0021:01 [ 594.306738] pci_hp_remove_devices: Removing 0021:01:00.0... ... [ 598.236381] pci_hp_remove_devices: Removing 0021:01:00.1... ... [ 611.972077] pci_bus 0021:01: busn_res: [bus 01-ff] is released [ 611.972140] rpadlpar_io: slot PHB 33 removed # kill -9 $pid1 # kill -9 $pid2 [ 632.918088] pcibios_free_controller_deferred: domain 33, dynamic 1 Test-case #2 (don't hold references) # drmgr -w 5 -d 1 -c phb -s 'PHB 33' -r Validating PHB DLPAR capability...yes. [ 916.357363] pci_hp_remove_devices: PCI: Removing devices on bus 0021:01 [ 916.357386] pci_hp_remove_devices: Removing 0021:01:00.0... ... [ 920.566527] pci_hp_remove_devices: Removing 0021:01:00.1... ... [ 933.955873] pci_bus 0021:01: busn_res: [bus 01-ff] is released [ 933.955977] pcibios_free_controller_deferred: domain 33, dynamic 1 [ 933.955999] rpadlpar_io: slot PHB 33 removed Suggested-By: Gavin Shan Signed-off-by: Mauricio Faria de Oliveira Reviewed-by: Gavin Shan Reviewed-by: Andrew Donnellan Tested-by: Andrew Donnellan # cxl Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/pci-bridge.h | 1 + arch/powerpc/kernel/pci-common.c | 36 ++++++++++++++++++++++ arch/powerpc/platforms/pseries/pci.c | 4 +++ arch/powerpc/platforms/pseries/pci_dlpar.c | 7 +++-- 4 files changed, 46 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index b5e88e4a171a..c0309c59bed8 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -301,6 +301,7 @@ extern void pci_process_bridge_OF_ranges(struct pci_controller *hose, /* Allocate & free a PCI host bridge structure */ extern struct pci_controller *pcibios_alloc_controller(struct device_node *dev); extern void pcibios_free_controller(struct pci_controller *phb); +extern void pcibios_free_controller_deferred(struct pci_host_bridge *bridge); #ifdef CONFIG_PCI extern int pcibios_vaddr_is_ioport(void __iomem *address); diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 7fdf324d5b51..e58908066b0e 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -153,6 +153,42 @@ void pcibios_free_controller(struct pci_controller *phb) } EXPORT_SYMBOL_GPL(pcibios_free_controller); +/* + * This function is used to call pcibios_free_controller() + * in a deferred manner: a callback from the PCI subsystem. + * + * _*DO NOT*_ call pcibios_free_controller() explicitly if + * this is used (or it may access an invalid *phb pointer). + * + * The callback occurs when all references to the root bus + * are dropped (e.g., child buses/devices and their users). + * + * It's called as .release_fn() of 'struct pci_host_bridge' + * which is associated with the 'struct pci_controller.bus' + * (root bus) - it expects .release_data to hold a pointer + * to 'struct pci_controller'. + * + * In order to use it, register .release_fn()/release_data + * like this: + * + * pci_set_host_bridge_release(bridge, + * pcibios_free_controller_deferred + * (void *) phb); + * + * e.g. in the pcibios_root_bridge_prepare() callback from + * pci_create_root_bus(). + */ +void pcibios_free_controller_deferred(struct pci_host_bridge *bridge) +{ + struct pci_controller *phb = (struct pci_controller *) + bridge->release_data; + + pr_debug("domain %d, dynamic %d\n", phb->global_number, phb->is_dynamic); + + pcibios_free_controller(phb); +} +EXPORT_SYMBOL_GPL(pcibios_free_controller_deferred); + /* * The function is used to return the minimal alignment * for memory or I/O windows of the associated P2P bridge. diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c index fe16a50700de..09eba5a9929a 100644 --- a/arch/powerpc/platforms/pseries/pci.c +++ b/arch/powerpc/platforms/pseries/pci.c @@ -119,6 +119,10 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge) bus = bridge->bus; + /* Rely on the pcibios_free_controller_deferred() callback. */ + pci_set_host_bridge_release(bridge, pcibios_free_controller_deferred, + (void *) pci_bus_to_host(bus)); + dn = pcibios_get_phb_of_node(bus); if (!dn) return 0; diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c index 906dbaa97fe2..547fd13e4f8e 100644 --- a/arch/powerpc/platforms/pseries/pci_dlpar.c +++ b/arch/powerpc/platforms/pseries/pci_dlpar.c @@ -106,8 +106,11 @@ int remove_phb_dynamic(struct pci_controller *phb) release_resource(res); } - /* Free pci_controller data structure */ - pcibios_free_controller(phb); + /* + * The pci_controller data structure is freed by + * the pcibios_free_controller_deferred() callback; + * see pseries_root_bridge_prepare(). + */ return 0; } From 6096481649ac27466cf2b453f185b43f680bf541 Mon Sep 17 00:00:00 2001 From: Andrzej Hajda Date: Wed, 17 Aug 2016 12:03:05 +0200 Subject: [PATCH 209/531] powerpc/powernv/pci: fix iterator signedness Unsigned type is always non-negative, so the loop could not end in case condition is never true. The problem has been detected using semantic patch scripts/coccinelle/tests/unsigned_lesser_than_zero.cocci Signed-off-by: Andrzej Hajda Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/powernv/pci-ioda.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index fd9444f9fb0c..13218263e66e 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -149,7 +149,7 @@ static void pnv_ioda_reserve_pe(struct pnv_phb *phb, int pe_no) static struct pnv_ioda_pe *pnv_ioda_alloc_pe(struct pnv_phb *phb) { - unsigned long pe = phb->ioda.total_pe_num - 1; + long pe; for (pe = phb->ioda.total_pe_num - 1; pe >= 0; pe--) { if (!test_and_set_bit(pe, phb->ioda.pe_alloc)) From 8a39b05f086904c3b2e04e4db3d81f30c0eae6ae Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Tue, 16 Aug 2016 10:57:34 -0400 Subject: [PATCH 210/531] powerpc: migrate exception table users off module.h and onto extable.h These files were only including module.h for exception table related functions. We've now separated that content out into its own file "extable.h" so now move over to that and avoid all the extra header content in module.h that we don't really need to compile these files. Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Paul Gortmaker Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/kprobes.c | 2 +- arch/powerpc/kernel/traps.c | 3 ++- arch/powerpc/mm/fault.c | 2 +- arch/powerpc/platforms/embedded6xx/holly.c | 2 +- arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c | 2 +- arch/powerpc/sysdev/fsl_rio.c | 2 +- 6 files changed, 7 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 3ed8ec09b5c9..e785cc9e1ecd 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -29,7 +29,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 2cb589264cb7..62859ebe0062 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -25,7 +25,8 @@ #include #include #include -#include +#include +#include /* print_modules */ #include #include #include diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index a4db22f65021..bb1ffc559f38 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -26,7 +26,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/powerpc/platforms/embedded6xx/holly.c b/arch/powerpc/platforms/embedded6xx/holly.c index dafba1057a47..dfd310031549 100644 --- a/arch/powerpc/platforms/embedded6xx/holly.c +++ b/arch/powerpc/platforms/embedded6xx/holly.c @@ -26,7 +26,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c index 80804f9916ee..f97bab8e37a2 100644 --- a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c +++ b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c @@ -23,7 +23,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c index 68e7c0dd2e45..3cc7cace194a 100644 --- a/arch/powerpc/sysdev/fsl_rio.c +++ b/arch/powerpc/sysdev/fsl_rio.c @@ -23,7 +23,7 @@ */ #include -#include +#include #include #include #include From 19ab58d19ef6291bab07c8e7110f3198c23432c1 Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Tue, 16 Aug 2016 19:50:12 +0800 Subject: [PATCH 211/531] powerpc, hotplug: Avoid to touch non-existent cpumasks. We observed a kernel oops when running a PPC guest with config NR_CPUS=4 and qemu option "-smp cores=1,threads=8": [ 30.634781] Unable to handle kernel paging request for data at address 0xc00000014192eb17 [ 30.636173] Faulting instruction address: 0xc00000000003e5cc [ 30.637069] Oops: Kernel access of bad area, sig: 11 [#1] [ 30.637877] SMP NR_CPUS=4 NUMA pSeries [ 30.638471] Modules linked in: [ 30.638949] CPU: 3 PID: 27 Comm: migration/3 Not tainted 4.7.0-07963-g9714b26 #1 [ 30.640059] task: c00000001e29c600 task.stack: c00000001e2a8000 [ 30.640956] NIP: c00000000003e5cc LR: c00000000003e550 CTR: 0000000000000000 [ 30.642001] REGS: c00000001e2ab8e0 TRAP: 0300 Not tainted (4.7.0-07963-g9714b26) [ 30.643139] MSR: 8000000102803033 CR: 22004084 XER: 00000000 [ 30.644583] CFAR: c000000000009e98 DAR: c00000014192eb17 DSISR: 40000000 SOFTE: 0 GPR00: c00000000140a6b8 c00000001e2abb60 c0000000016dd300 0000000000000003 GPR04: 0000000000000000 0000000000000004 c0000000016e5920 0000000000000008 GPR08: 0000000000000004 c00000014192eb17 0000000000000000 0000000000000020 GPR12: c00000000140a6c0 c00000000ffffc00 c0000000000d3ea8 c00000001e005680 GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 GPR20: 0000000000000000 c00000001e6b3a00 0000000000000000 0000000000000001 GPR24: c00000001ff85138 c00000001ff85130 000000001eb6f000 0000000000000001 GPR28: 0000000000000000 c0000000017014e0 0000000000000000 0000000000000018 [ 30.653882] NIP [c00000000003e5cc] __cpu_disable+0xcc/0x190 [ 30.654713] LR [c00000000003e550] __cpu_disable+0x50/0x190 [ 30.655528] Call Trace: [ 30.655893] [c00000001e2abb60] [c00000000003e550] __cpu_disable+0x50/0x190 (unreliable) [ 30.657280] [c00000001e2abbb0] [c0000000000aca0c] take_cpu_down+0x5c/0x100 [ 30.658365] [c00000001e2abc10] [c000000000163918] multi_cpu_stop+0x1a8/0x1e0 [ 30.659617] [c00000001e2abc60] [c000000000163cc0] cpu_stopper_thread+0xf0/0x1d0 [ 30.660737] [c00000001e2abd20] [c0000000000d8d70] smpboot_thread_fn+0x290/0x2a0 [ 30.661879] [c00000001e2abd80] [c0000000000d3fa8] kthread+0x108/0x130 [ 30.662876] [c00000001e2abe30] [c000000000009968] ret_from_kernel_thread+0x5c/0x74 [ 30.664017] Instruction dump: [ 30.664477] 7bde1f24 38a00000 787f1f24 3b600001 39890008 7d204b78 7d05e214 7d0b07b4 [ 30.665642] 796b1f24 7d26582a 7d204a14 7d29f214 <7d4048a8> 7d4a3878 7d4049ad 40c2fff4 [ 30.666854] ---[ end trace 32643b7195717741 ]--- The reason of this is that in __cpu_disable(), when we try to set the cpu_sibling_mask or cpu_core_mask of the sibling CPUs of the disabled one, we don't check whether the current configuration employs those sibling CPUs(hw threads). And if a CPU is not employed by a configuration, the percpu structures cpu_{sibling,core}_mask are not allocated, therefore accessing those cpumasks will result in problems as above. This patch fixes this problem by adding an addition check on whether the id is no less than nr_cpu_ids in the sibling CPU iteration code. Signed-off-by: Boqun Feng Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/smp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 25a39052bf6b..9c6f3fd58059 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -830,7 +830,7 @@ int __cpu_disable(void) /* Update sibling maps */ base = cpu_first_thread_sibling(cpu); - for (i = 0; i < threads_per_core; i++) { + for (i = 0; i < threads_per_core && base + i < nr_cpu_ids; i++) { cpumask_clear_cpu(cpu, cpu_sibling_mask(base + i)); cpumask_clear_cpu(base + i, cpu_sibling_mask(cpu)); cpumask_clear_cpu(cpu, cpu_core_mask(base + i)); From 66443efa83dc73775100b7442962ce2cb0d4472e Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 12 Aug 2016 21:45:52 +1000 Subject: [PATCH 212/531] powerpc/prom: Fix sub-processor option passed to ibm, client-architecture-support When booting from an OpenFirmware which supports it, we use the "ibm,client-architecture-support" firmware call to communicate our capabilities to firmware. The format of the structure we pass to firmware is specified in PAPR (Power Architecture Platform Requirements), or the public version LoPAPR (Linux on Power Architecture Platform Reference). Referring to table 244 in LoPAPR v1.1, option vector 5 contains a 4 byte field at bytes 17-20 for the "Platform Facilities Enable". This is followed by a 1 byte field at byte 21 for "Sub-Processor Represenation Level". Comparing to the code, there we have the Platform Facilities options (OV5_PFO_*) at byte 17, but we fail to pad that field out to its full width of 4 bytes. This means the OV5_SUB_PROCESSORS option is incorrectly placed at byte 18. Fix it by adding zero bytes for bytes 18, 19, 20, and comment the bytes to hopefully make it clearer in future. As far as I'm aware nothing actually consumes this value at this time, so the effect of this bug is nil in practice. It does mean we've been incorrectly setting bit 15 of the "Platform Facilities Enable" option for the past ~3 1/2 years, so we should avoid allocating that bit to anything else in future. Fixes: df77c7992029 ("powerpc/pseries: Update ibm,architecture.vec for PAPR 2.7/POWER8") Signed-off-by: Michael Ellerman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/prom_init.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 4e74fc588a3f..d3eff99e938c 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -695,7 +695,7 @@ unsigned char ibm_architecture_vec[] = { OV4_MIN_ENT_CAP, /* minimum VP entitled capacity */ /* option vector 5: PAPR/OF options */ - VECTOR_LENGTH(18), /* length */ + VECTOR_LENGTH(21), /* length */ 0, /* don't ignore, don't halt */ OV5_FEAT(OV5_LPAR) | OV5_FEAT(OV5_SPLPAR) | OV5_FEAT(OV5_LARGE_PAGES) | OV5_FEAT(OV5_DRCONF_MEMORY) | OV5_FEAT(OV5_DONATE_DEDICATE_CPU) | @@ -726,8 +726,11 @@ unsigned char ibm_architecture_vec[] = { 0, 0, OV5_FEAT(OV5_PFO_HW_RNG) | OV5_FEAT(OV5_PFO_HW_ENCR) | - OV5_FEAT(OV5_PFO_HW_842), - OV5_FEAT(OV5_SUB_PROCESSORS), + OV5_FEAT(OV5_PFO_HW_842), /* Byte 17 */ + 0, /* Byte 18 */ + 0, /* Byte 19 */ + 0, /* Byte 20 */ + OV5_FEAT(OV5_SUB_PROCESSORS), /* Byte 21 */ /* option vector 6: IBM PAPR hints */ VECTOR_LENGTH(3), /* length */ From 3f3b5dc14c25254d3fe98115c71b2a1f3ed97798 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Wed, 10 Aug 2016 20:48:42 +1000 Subject: [PATCH 213/531] powerpc/pseries: PACA save area fix for general exception vs MCE MCE must not use PACA_EXGEN. When a general exception enables MSR_RI, that means SPRN_SRR[01] and SPRN_SPRG are no longer used. However the PACA save area is still in use. Acked-by: Mahesh Salgaonkar Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/exceptions-64s.S | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index df6d45eb4115..034b7eaf68d2 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -969,14 +969,14 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) machine_check_common: mfspr r10,SPRN_DAR - std r10,PACA_EXGEN+EX_DAR(r13) + std r10,PACA_EXMC+EX_DAR(r13) mfspr r10,SPRN_DSISR - stw r10,PACA_EXGEN+EX_DSISR(r13) + stw r10,PACA_EXMC+EX_DSISR(r13) EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC) FINISH_NAP RECONCILE_IRQ_STATE(r10, r11) - ld r3,PACA_EXGEN+EX_DAR(r13) - lwz r4,PACA_EXGEN+EX_DSISR(r13) + ld r3,PACA_EXMC+EX_DAR(r13) + lwz r4,PACA_EXMC+EX_DSISR(r13) std r3,_DAR(r1) std r4,_DSISR(r1) bl save_nvgprs From a74599a5041979ae83aec7a6d5c8df9131db2ce6 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Wed, 10 Aug 2016 20:48:43 +1000 Subject: [PATCH 214/531] powerpc/pseries: PACA save area fix for MCE vs MCE MCE must not enable MSR_RI until PACA_EXMC is no longer being used. Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/exceptions-64s.S | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 034b7eaf68d2..bffec73dbffc 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -485,7 +485,23 @@ machine_check_fwnmi: EXCEPTION_PROLOG_0(PACA_EXMC) machine_check_pSeries_0: EXCEPTION_PROLOG_1(PACA_EXMC, KVMTEST, 0x200) - EXCEPTION_PROLOG_PSERIES_1(machine_check_common, EXC_STD) + /* + * The following is essentially EXCEPTION_PROLOG_PSERIES_1 with the + * difference that MSR_RI is not enabled, because PACA_EXMC is being + * used, so nested machine check corrupts it. machine_check_common + * enables MSR_RI. + */ + ld r12,PACAKBASE(r13) + ld r10,PACAKMSR(r13) + xori r10,r10,MSR_RI + mfspr r11,SPRN_SRR0 + LOAD_HANDLER(r12, machine_check_common) + mtspr SPRN_SRR0,r12 + mfspr r12,SPRN_SRR1 + mtspr SPRN_SRR1,r10 + rfid + b . /* prevent speculative execution */ + KVM_HANDLER_SKIP(PACA_EXMC, EXC_STD, 0x200) KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x300) KVM_HANDLER_SKIP(PACA_EXSLB, EXC_STD, 0x380) @@ -977,6 +993,9 @@ machine_check_common: RECONCILE_IRQ_STATE(r10, r11) ld r3,PACA_EXMC+EX_DAR(r13) lwz r4,PACA_EXMC+EX_DSISR(r13) + /* Enable MSR_RI when finished with PACA_EXMC */ + li r10,MSR_RI + mtmsrd r10,1 std r3,_DAR(r1) std r4,_DSISR(r1) bl save_nvgprs From 41017a7579cf49cb5513e17df1570dc918760079 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Thu, 11 Aug 2016 10:50:40 +0200 Subject: [PATCH 215/531] powerpc: sysdev: cpm: fix gpio save_regs functions of_mm_gpiochip_add_data() calls mm_gc->save_regs() before setting the data. Therefore ->save_regs() cannot use gpiochip_get_data() [ 0.275940] Unable to handle kernel paging request for data at address 0x00000130 [ 0.283120] Faulting instruction address: 0xc01b44cc [ 0.288175] Oops: Kernel access of bad area, sig: 11 [#1] [ 0.293343] PREEMPT CMPC885 [ 0.296141] CPU: 0 PID: 1 Comm: swapper Not tainted 4.7.0-g65124df-dirty #68 [ 0.304131] task: c6074000 ti: c6080000 task.ti: c6080000 [ 0.309459] NIP: c01b44cc LR: c0011720 CTR: c0011708 [ 0.314372] REGS: c6081d90 TRAP: 0300 Not tainted (4.7.0-g65124df-dirty) [ 0.322267] MSR: 00009032 CR: 24000028 XER: 20000000 [ 0.328813] DAR: 00000130 DSISR: c0000000 GPR00: c01b6d0c c6081e40 c6074000 c6017000 c9028000 c601d028 c6081dd8 00000000 GPR08: c601d028 00000000 ffffffff 00000001 24000044 00000000 c0002790 00000000 GPR16: 00000000 00000000 00000000 00000000 00000000 00000000 c05643b0 00000083 GPR24: c04a1a6c c0560000 c04a8308 c04c6480 c0012498 c6017000 c7ffcc78 c6017000 [ 0.360806] NIP [c01b44cc] gpiochip_get_data+0x4/0xc [ 0.365684] LR [c0011720] cpm1_gpio16_save_regs+0x18/0x44 [ 0.370972] Call Trace: [ 0.373451] [c6081e50] [c01b6d0c] of_mm_gpiochip_add_data+0x70/0xdc [ 0.379624] [c6081e70] [c00124c0] cpm_init_par_io+0x28/0x118 [ 0.385238] [c6081e80] [c04a8ac0] do_one_initcall+0xb0/0x17c [ 0.390819] [c6081ef0] [c04a8cbc] kernel_init_freeable+0x130/0x1dc [ 0.396924] [c6081f30] [c00027a4] kernel_init+0x14/0x110 [ 0.402177] [c6081f40] [c000b424] ret_from_kernel_thread+0x5c/0x64 [ 0.408233] Instruction dump: [ 0.411168] 4182fafc 3f80c040 48234c6d 3bc0fff0 3b9c5ed0 4bfffaf4 81290020 712a0004 [ 0.418825] 4182fb34 48234c51 4bfffb2c 81230004 <80690130> 4e800020 7c0802a6 9421ffe0 [ 0.426763] ---[ end trace fe4113ee21d72ffa ]--- fixes: e65078f1f3490 ("powerpc: sysdev: cpm1: use gpiochip data pointer") fixes: a14a2d484b386 ("powerpc: cpm_common: use gpiochip data pointer") Cc: stable@vger.kernel.org Signed-off-by: Christophe Leroy Reviewed-by: Linus Walleij Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/sysdev/cpm1.c | 6 ++++-- arch/powerpc/sysdev/cpm_common.c | 3 ++- 2 files changed, 6 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/sysdev/cpm1.c b/arch/powerpc/sysdev/cpm1.c index 6c110994d902..81d49476c47e 100644 --- a/arch/powerpc/sysdev/cpm1.c +++ b/arch/powerpc/sysdev/cpm1.c @@ -534,7 +534,8 @@ struct cpm1_gpio16_chip { static void cpm1_gpio16_save_regs(struct of_mm_gpio_chip *mm_gc) { - struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc); + struct cpm1_gpio16_chip *cpm1_gc = + container_of(mm_gc, struct cpm1_gpio16_chip, mm_gc); struct cpm_ioport16 __iomem *iop = mm_gc->regs; cpm1_gc->cpdata = in_be16(&iop->dat); @@ -649,7 +650,8 @@ struct cpm1_gpio32_chip { static void cpm1_gpio32_save_regs(struct of_mm_gpio_chip *mm_gc) { - struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc); + struct cpm1_gpio32_chip *cpm1_gc = + container_of(mm_gc, struct cpm1_gpio32_chip, mm_gc); struct cpm_ioport32b __iomem *iop = mm_gc->regs; cpm1_gc->cpdata = in_be32(&iop->dat); diff --git a/arch/powerpc/sysdev/cpm_common.c b/arch/powerpc/sysdev/cpm_common.c index 911456d17713..947f42007734 100644 --- a/arch/powerpc/sysdev/cpm_common.c +++ b/arch/powerpc/sysdev/cpm_common.c @@ -94,7 +94,8 @@ struct cpm2_gpio32_chip { static void cpm2_gpio32_save_regs(struct of_mm_gpio_chip *mm_gc) { - struct cpm2_gpio32_chip *cpm2_gc = gpiochip_get_data(&mm_gc->gc); + struct cpm2_gpio32_chip *cpm2_gc = + container_of(mm_gc, struct cpm2_gpio32_chip, mm_gc); struct cpm2_ioports __iomem *iop = mm_gc->regs; cpm2_gc->cpdata = in_be32(&iop->dat); From 7c379526d7e71d2041c8ca0bd9af4888916a14b9 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 11 Aug 2016 15:07:43 +0200 Subject: [PATCH 216/531] powerpc: move hmi.c to arch/powerpc/kvm/ hmi.c functions are unused unless sibling_subcore_state is nonzero, and that in turn happens only if KVM is in use. So move the code to arch/powerpc/kvm/, putting it under CONFIG_KVM_BOOK3S_HV_POSSIBLE rather than CONFIG_PPC_BOOK3S_64. The sibling_subcore_state is also included in struct paca_struct only if KVM is supported by the kernel. Cc: Daniel Axtens Cc: Michael Ellerman Cc: Mahesh Salgaonkar Cc: Paul Mackerras Cc: linuxppc-dev@lists.ozlabs.org Cc: kvm-ppc@vger.kernel.org Cc: kvm@vger.kernel.org Signed-off-by: Paolo Bonzini Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/hmi.h | 2 +- arch/powerpc/include/asm/paca.h | 12 +++++++----- arch/powerpc/kernel/Makefile | 2 +- arch/powerpc/kvm/Makefile | 1 + arch/powerpc/{kernel/hmi.c => kvm/book3s_hv_hmi.c} | 0 5 files changed, 10 insertions(+), 7 deletions(-) rename arch/powerpc/{kernel/hmi.c => kvm/book3s_hv_hmi.c} (100%) diff --git a/arch/powerpc/include/asm/hmi.h b/arch/powerpc/include/asm/hmi.h index 88b4901ac4ee..85b7a1a21e22 100644 --- a/arch/powerpc/include/asm/hmi.h +++ b/arch/powerpc/include/asm/hmi.h @@ -21,7 +21,7 @@ #ifndef __ASM_PPC64_HMI_H__ #define __ASM_PPC64_HMI_H__ -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE #define CORE_TB_RESYNC_REQ_BIT 63 #define MAX_SUBCORE_PER_CORE 4 diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 148303e7771f..6a6792bb39fb 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -183,11 +183,6 @@ struct paca_struct { */ u16 in_mce; u8 hmi_event_available; /* HMI event is available */ - /* - * Bitmap for sibling subcore status. See kvm/book3s_hv_ras.c for - * more details - */ - struct sibling_subcore_state *sibling_subcore_state; #endif /* Stuff for accurate time accounting */ @@ -202,6 +197,13 @@ struct paca_struct { struct kvmppc_book3s_shadow_vcpu shadow_vcpu; #endif struct kvmppc_host_state kvm_hstate; +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + /* + * Bitmap for sibling subcore status. See kvm/book3s_hv_ras.c for + * more details + */ + struct sibling_subcore_state *sibling_subcore_state; +#endif #endif }; diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index b2027a5cf508..fe4c075bcf50 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -41,7 +41,7 @@ obj-$(CONFIG_VDSO32) += vdso32/ obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o -obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o hmi.o +obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_book3e.o obj-$(CONFIG_PPC64) += vdso64/ obj-$(CONFIG_ALTIVEC) += vecemu.o diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index 1f9e5529e692..855d4b95d752 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -78,6 +78,7 @@ kvm-book3s_64-builtin-xics-objs-$(CONFIG_KVM_XICS) := \ ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \ + book3s_hv_hmi.o \ book3s_hv_rmhandlers.o \ book3s_hv_rm_mmu.o \ book3s_hv_ras.o \ diff --git a/arch/powerpc/kernel/hmi.c b/arch/powerpc/kvm/book3s_hv_hmi.c similarity index 100% rename from arch/powerpc/kernel/hmi.c rename to arch/powerpc/kvm/book3s_hv_hmi.c From 6f00975c619064a18c23fd3aced325ae165a73b9 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Sat, 20 Aug 2016 12:22:11 +0200 Subject: [PATCH 217/531] drm: Reject page_flip for !DRIVER_MODESET Somehow this one slipped through, which means drivers without modeset support can be oopsed (since those also don't call drm_mode_config_init, which means the crtc lookup will chase an uninitalized idr). Reported-by: Alexander Potapenko Cc: Alexander Potapenko Cc: stable@vger.kernel.org Signed-off-by: Daniel Vetter Reviewed-by: Chris Wilson Signed-off-by: Dave Airlie --- drivers/gpu/drm/drm_crtc.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index b1dbb60af99f..ddebe54cd5ca 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -5404,6 +5404,9 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev, struct drm_pending_vblank_event *e = NULL; int ret = -EINVAL; + if (!drm_core_check_feature(dev, DRIVER_MODESET)) + return -EINVAL; + if (page_flip->flags & ~DRM_MODE_PAGE_FLIP_FLAGS || page_flip->reserved != 0) return -EINVAL; From 93e11eb1b745ee8dbd4f98f24b542d496c8f1e03 Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Wed, 10 Aug 2016 13:44:56 +0000 Subject: [PATCH 218/531] dmaengine: fsl_raid: add missing of_node_put() in fsl_re_probe() When terminating for_each_compatible_node() iteration with break or return, of_node_put() should be used to prevent stale device node references from being left behind. Found by Coccinelle. Signed-off-by: Wei Yongjun Signed-off-by: Vinod Koul --- drivers/dma/fsl_raid.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/dma/fsl_raid.c b/drivers/dma/fsl_raid.c index aad167eaaee8..de2a2a2b1d75 100644 --- a/drivers/dma/fsl_raid.c +++ b/drivers/dma/fsl_raid.c @@ -836,6 +836,7 @@ static int fsl_re_probe(struct platform_device *ofdev) rc = of_property_read_u32(np, "reg", &off); if (rc) { dev_err(dev, "Reg property not found in JQ node\n"); + of_node_put(np); return -ENODEV; } /* Find out the Job Rings present under each JQ */ From 6a8b0c6b18f62a277ffb2139d0c0253fe35d7feb Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Wed, 10 Aug 2016 03:17:09 +0000 Subject: [PATCH 219/531] dmaengine: at_xdmac: fix to pass correct device identity to free_irq() free_irq() expects the same device identity that was passed to corresponding request_irq(), otherwise the IRQ is not freed. Fixes: e1f7c9eee707 ("dmaengine: at_xdmac: creation of the atmel eXtended DMA Controller driver") Signed-off-by: Wei Yongjun Acked-by: Ludovic Desroches Signed-off-by: Vinod Koul --- drivers/dma/at_xdmac.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index e434ffe7bc5c..832cbd647145 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -2067,7 +2067,7 @@ static int at_xdmac_probe(struct platform_device *pdev) err_clk_disable: clk_disable_unprepare(atxdmac->clk); err_free_irq: - free_irq(atxdmac->irq, atxdmac->dma.dev); + free_irq(atxdmac->irq, atxdmac); return ret; } @@ -2081,7 +2081,7 @@ static int at_xdmac_remove(struct platform_device *pdev) dma_async_device_unregister(&atxdmac->dma); clk_disable_unprepare(atxdmac->clk); - free_irq(atxdmac->irq, atxdmac->dma.dev); + free_irq(atxdmac->irq, atxdmac); for (i = 0; i < atxdmac->dma.chancnt; i++) { struct at_xdmac_chan *atchan = &atxdmac->chan[i]; From 32e80820de5d7eb778632af8f235727a32d3aeb2 Mon Sep 17 00:00:00 2001 From: LABBE Corentin Date: Tue, 16 Aug 2016 10:44:18 +0200 Subject: [PATCH 220/531] dmaengine: img-mdc: fix a possible NULL dereference of_match_device could return NULL, and so cause a NULL pointer dereference later at line 850: mdma->soc = match->data; For fixing this problem, we use of_device_get_match_data(), this will simplify the code a little by using a standard function for getting the match data. This was reported by coverity (CID 1324134) Signed-off-by: LABBE Corentin Signed-off-by: Vinod Koul --- drivers/dma/img-mdc-dma.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/dma/img-mdc-dma.c b/drivers/dma/img-mdc-dma.c index a4c53be482cf..624f1e1e9c55 100644 --- a/drivers/dma/img-mdc-dma.c +++ b/drivers/dma/img-mdc-dma.c @@ -861,7 +861,6 @@ static int mdc_dma_probe(struct platform_device *pdev) { struct mdc_dma *mdma; struct resource *res; - const struct of_device_id *match; unsigned int i; u32 val; int ret; @@ -871,8 +870,7 @@ static int mdc_dma_probe(struct platform_device *pdev) return -ENOMEM; platform_set_drvdata(pdev, mdma); - match = of_match_device(mdc_dma_of_match, &pdev->dev); - mdma->soc = match->data; + mdma->soc = of_device_get_match_data(&pdev->dev); res = platform_get_resource(pdev, IORESOURCE_MEM, 0); mdma->regs = devm_ioremap_resource(&pdev->dev, res); From f6c274e11e3b31a5f95c23962b1ba593bd6a4759 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Thu, 28 Jul 2016 10:16:12 +0300 Subject: [PATCH 221/531] usb: dwc3: pci: runtime_resume child device During runtime_resume of dwc3-pci.c, we need to runtime suspend our child device (which is dwc3 proper) otherwise nothing will happen. Signed-off-by: Felipe Balbi --- drivers/usb/dwc3/dwc3-pci.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index 2eb84d6c24a6..0a32430f4c41 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -243,6 +243,13 @@ static int dwc3_pci_runtime_suspend(struct device *dev) return -EBUSY; } +static int dwc3_pci_runtime_resume(struct device *dev) +{ + struct platform_device *dwc3 = dev_get_drvdata(dev); + + return pm_runtime_get(&dwc3->dev); +} + static int dwc3_pci_pm_dummy(struct device *dev) { /* @@ -259,7 +266,7 @@ static int dwc3_pci_pm_dummy(struct device *dev) static struct dev_pm_ops dwc3_pci_dev_pm_ops = { SET_SYSTEM_SLEEP_PM_OPS(dwc3_pci_pm_dummy, dwc3_pci_pm_dummy) - SET_RUNTIME_PM_OPS(dwc3_pci_runtime_suspend, dwc3_pci_pm_dummy, + SET_RUNTIME_PM_OPS(dwc3_pci_runtime_suspend, dwc3_pci_runtime_resume, NULL) }; From b74c2d875baaa07186f617c5617f4c5e3a8a41ad Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Thu, 28 Jul 2016 13:07:07 +0300 Subject: [PATCH 222/531] usb: dwc3: core: allow device to runtime_suspend several times After going through runtime_suspend/runtime_resume cycle once we would be left with an unbalanced pm_runtime_get() call. Fix that by making sure that we try to suspend right after resuming so things are balanced and device can runtime_suspend again. Signed-off-by: Felipe Balbi --- drivers/usb/dwc3/core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 946643157b78..35d092456bec 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1192,6 +1192,7 @@ static int dwc3_runtime_resume(struct device *dev) } pm_runtime_mark_last_busy(dev); + pm_runtime_put(dev); return 0; } From 83f8da562f8b5275fa1095b45762996971f7c607 Mon Sep 17 00:00:00 2001 From: Dinh Nguyen Date: Wed, 10 Aug 2016 08:53:34 -0500 Subject: [PATCH 223/531] usb: dwc2: Add reset control to dwc2 Allow for platforms that have a reset controller driver in place to bring the USB IP out of reset. Signed-off-by: Dinh Nguyen Acked-by: John Youn Tested-by: Stefan Wahren Signed-off-by: Felipe Balbi --- drivers/usb/dwc2/core.h | 1 + drivers/usb/dwc2/platform.c | 22 ++++++++++++++++++++++ 2 files changed, 23 insertions(+) diff --git a/drivers/usb/dwc2/core.h b/drivers/usb/dwc2/core.h index 9fae0291cd69..d64551243789 100644 --- a/drivers/usb/dwc2/core.h +++ b/drivers/usb/dwc2/core.h @@ -868,6 +868,7 @@ struct dwc2_hsotg { void *priv; int irq; struct clk *clk; + struct reset_control *reset; unsigned int queuing_high_bandwidth:1; unsigned int srp_success:1; diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c index fc6f5251de5d..530959a8a6d1 100644 --- a/drivers/usb/dwc2/platform.c +++ b/drivers/usb/dwc2/platform.c @@ -45,6 +45,7 @@ #include #include #include +#include #include @@ -337,6 +338,24 @@ static int dwc2_lowlevel_hw_init(struct dwc2_hsotg *hsotg) { int i, ret; + hsotg->reset = devm_reset_control_get_optional(hsotg->dev, "dwc2"); + if (IS_ERR(hsotg->reset)) { + ret = PTR_ERR(hsotg->reset); + switch (ret) { + case -ENOENT: + case -ENOTSUPP: + hsotg->reset = NULL; + break; + default: + dev_err(hsotg->dev, "error getting reset control %d\n", + ret); + return ret; + } + } + + if (hsotg->reset) + reset_control_deassert(hsotg->reset); + /* Set default UTMI width */ hsotg->phyif = GUSBCFG_PHYIF16; @@ -434,6 +453,9 @@ static int dwc2_driver_remove(struct platform_device *dev) if (hsotg->ll_hw_enabled) dwc2_lowlevel_hw_disable(hsotg); + if (hsotg->reset) + reset_control_assert(hsotg->reset); + return 0; } From 3295235fd70ed6d594aadee8c892a14f6a4b2d2e Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Sat, 13 Aug 2016 01:28:24 +0000 Subject: [PATCH 224/531] usb: renesas_usbhs: gadget: fix return value check in usbhs_mod_gadget_probe() In case of error, the function usb_get_phy() returns ERR_PTR() and never returns NULL. The NULL test in the return value check should be replaced with IS_ERR(). Fixes: b5a2875605ca ("usb: renesas_usbhs: Allow an OTG PHY driver to provide VBUS") Cc: # v4.3+ Acked-by: Yoshihiro Shimoda Signed-off-by: Wei Yongjun Signed-off-by: Felipe Balbi --- drivers/usb/renesas_usbhs/mod_gadget.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/renesas_usbhs/mod_gadget.c b/drivers/usb/renesas_usbhs/mod_gadget.c index 92bc83b92d10..c4c64740a3e7 100644 --- a/drivers/usb/renesas_usbhs/mod_gadget.c +++ b/drivers/usb/renesas_usbhs/mod_gadget.c @@ -1076,7 +1076,7 @@ int usbhs_mod_gadget_probe(struct usbhs_priv *priv) gpriv->transceiver = usb_get_phy(USB_PHY_TYPE_UNDEFINED); dev_info(dev, "%stransceiver found\n", - gpriv->transceiver ? "" : "no "); + !IS_ERR(gpriv->transceiver) ? "" : "no "); /* * CAUTION From 70237dc8efd092b93b40dc2eba812d66a5d65cb1 Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Thu, 11 Aug 2016 15:51:45 +0800 Subject: [PATCH 225/531] usb: gadget: function: f_eem: socket buffer may be NULL In eth_start_xmit, the socket buffer may be NULL. So, add NULL pointer check at .wrap API. Signed-off-by: Peter Chen Signed-off-by: Felipe Balbi --- drivers/usb/gadget/function/f_eem.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/usb/gadget/function/f_eem.c b/drivers/usb/gadget/function/f_eem.c index d58bfc32be9e..8741fd740174 100644 --- a/drivers/usb/gadget/function/f_eem.c +++ b/drivers/usb/gadget/function/f_eem.c @@ -341,11 +341,15 @@ static struct sk_buff *eem_wrap(struct gether *port, struct sk_buff *skb) { struct sk_buff *skb2 = NULL; struct usb_ep *in = port->in_ep; - int padlen = 0; + int headroom, tailroom, padlen = 0; u16 len = skb->len; - int headroom = skb_headroom(skb); - int tailroom = skb_tailroom(skb); + if (!skb) + return NULL; + + len = skb->len; + headroom = skb_headroom(skb); + tailroom = skb_tailroom(skb); /* When (len + EEM_HLEN + ETH_FCS_LEN) % in->maxpacket) is 0, * stick two bytes of zero-length EEM packet on the end. From 80d1642d7640ef00d8823f17a529785331aceb96 Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Thu, 11 Aug 2016 15:51:46 +0800 Subject: [PATCH 226/531] usb: gadget: function: f_rndis: socket buffer may be NULL In eth_start_xmit, the socket buffer may be NULL. So, add NULL pointer check at .wrap API. Signed-off-by: Peter Chen Signed-off-by: Felipe Balbi --- drivers/usb/gadget/function/f_rndis.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/gadget/function/f_rndis.c b/drivers/usb/gadget/function/f_rndis.c index c8005823b190..16562e461121 100644 --- a/drivers/usb/gadget/function/f_rndis.c +++ b/drivers/usb/gadget/function/f_rndis.c @@ -374,6 +374,9 @@ static struct sk_buff *rndis_add_header(struct gether *port, { struct sk_buff *skb2; + if (!skb) + return NULL; + skb2 = skb_realloc_headroom(skb, sizeof(struct rndis_packet_msg_type)); rndis_add_hdr(skb2); From f4693b08cc901912a87369c46537b94ed4084ea0 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 15 Jul 2016 14:15:47 +0300 Subject: [PATCH 227/531] usb: gadget: fsl_qe_udc: signedness bug in qe_get_frame() We can't assign -EINVAL to a u16. Fixes: 3948f0e0c999 ('usb: add Freescale QE/CPM USB peripheral controller driver') Acked-by: Peter Chen Signed-off-by: Dan Carpenter Signed-off-by: Felipe Balbi --- drivers/usb/gadget/udc/fsl_qe_udc.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/usb/gadget/udc/fsl_qe_udc.c b/drivers/usb/gadget/udc/fsl_qe_udc.c index cf8819a5c5b2..8bb011ea78f7 100644 --- a/drivers/usb/gadget/udc/fsl_qe_udc.c +++ b/drivers/usb/gadget/udc/fsl_qe_udc.c @@ -1878,11 +1878,8 @@ static int qe_get_frame(struct usb_gadget *gadget) tmp = in_be16(&udc->usb_param->frame_n); if (tmp & 0x8000) - tmp = tmp & 0x07ff; - else - tmp = -EINVAL; - - return (int)tmp; + return tmp & 0x07ff; + return -EINVAL; } static int fsl_qe_start(struct usb_gadget *gadget, From d6011f6fc21b4d4ab1586f01c4f62becaa0a28d7 Mon Sep 17 00:00:00 2001 From: Nicolas Saenz Julienne Date: Tue, 16 Aug 2016 10:22:38 +0100 Subject: [PATCH 228/531] usb: dwc3: gadget: don't rely on jiffies while holding spinlock __dwc3_gadget_wakeup() is called while holding a spinlock, then depends on jiffies in order to timeout while polling the USB core for a link state update. In the case the wakeup failed, the timeout will never happen and will also cause the cpu to stall until rcu_preempt kicks in. This switches to a "decrement variable and wait" timeout scheme. Signed-off-by: Nicolas Saenz Julienne Signed-off-by: Felipe Balbi --- drivers/usb/dwc3/gadget.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 1f5597ef945d..122e64df2f4d 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1433,7 +1433,7 @@ static int dwc3_gadget_get_frame(struct usb_gadget *g) static int __dwc3_gadget_wakeup(struct dwc3 *dwc) { - unsigned long timeout; + int retries; int ret; u32 reg; @@ -1484,9 +1484,9 @@ static int __dwc3_gadget_wakeup(struct dwc3 *dwc) } /* poll until Link State changes to ON */ - timeout = jiffies + msecs_to_jiffies(100); + retries = 20000; - while (!time_after(jiffies, timeout)) { + while (retries--) { reg = dwc3_readl(dwc->regs, DWC3_DSTS); /* in HS, means ON */ From 511a36d2f357724312bb3776d2f6eed3890928b2 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Thu, 30 Jun 2016 17:10:23 +0800 Subject: [PATCH 229/531] usb: gadget: Add the gserial port checking in gs_start_tx() When usb gadget is set gadget serial function, it will be crash in below situation. It will clean the 'port->port_usb' pointer in gserial_disconnect() function when usb link is inactive, but it will release lock for disabling the endpoints in this function. Druing the lock release period, it maybe complete one request to issue gs_write_complete()--->gs_start_tx() function, but the 'port->port_usb' pointer had been set NULL, thus it will be crash in gs_start_tx() function. This patch adds the 'port->port_usb' pointer checking in gs_start_tx() function to avoid this situation. Signed-off-by: Baolin Wang Signed-off-by: Felipe Balbi --- drivers/usb/gadget/function/u_serial.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c index 6ded6345cd09..e0cd1e4c8892 100644 --- a/drivers/usb/gadget/function/u_serial.c +++ b/drivers/usb/gadget/function/u_serial.c @@ -375,10 +375,15 @@ __acquires(&port->port_lock) */ { struct list_head *pool = &port->write_pool; - struct usb_ep *in = port->port_usb->in; + struct usb_ep *in; int status = 0; bool do_tty_wake = false; + if (!port->port_usb) + return status; + + in = port->port_usb->in; + while (!port->write_busy && !list_empty(pool)) { struct usb_request *req; int len; From 4396f46c8c628329bd35ee4b84140b8b001a11eb Mon Sep 17 00:00:00 2001 From: Shawn Lin Date: Mon, 22 Aug 2016 16:21:52 +0800 Subject: [PATCH 230/531] genirq: Fix potential memleak when failing to get irq pm Obviously we should free action here if irq_chip_pm_get failed. Fixes: be45beb2df69: "genirq: Add runtime power management support for IRQ chips" Signed-off-by: Shawn Lin Cc: Jon Hunter Cc: Marc Zyngier Link: http://lkml.kernel.org/r/1471854112-13006-1-git-send-email-shawn.lin@rock-chips.com Signed-off-by: Thomas Gleixner --- kernel/irq/manage.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 73a2b786b5e9..9530fcd27704 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1681,8 +1681,10 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler, action->dev_id = dev_id; retval = irq_chip_pm_get(&desc->irq_data); - if (retval < 0) + if (retval < 0) { + kfree(action); return retval; + } chip_bus_lock(desc); retval = __setup_irq(irq, desc, action); @@ -1985,8 +1987,10 @@ int request_percpu_irq(unsigned int irq, irq_handler_t handler, action->percpu_dev_id = dev_id; retval = irq_chip_pm_get(&desc->irq_data); - if (retval < 0) + if (retval < 0) { + kfree(action); return retval; + } chip_bus_lock(desc); retval = __setup_irq(irq, desc, action); From 3ee0ce2a54dff07d09440723594df89bc1a12e79 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 11 Aug 2016 07:06:45 -0700 Subject: [PATCH 231/531] genirq/affinity: Use get/put_online_cpus around cpumask operations Without locking out CPU mask operations we might end up with an inconsistent view of the cpumask in the function. Fixes: 5e385a6ef31f: "genirq: Add a helper to spread an affinity mask for MSI/MSI-X vectors" Signed-off-by: Christoph Hellwig Link: http://lkml.kernel.org/r/1470924405-25728-1-git-send-email-hch@lst.de Signed-off-by: Thomas Gleixner --- kernel/irq/affinity.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c index f68959341c0f..32f6cfcff212 100644 --- a/kernel/irq/affinity.c +++ b/kernel/irq/affinity.c @@ -39,6 +39,7 @@ struct cpumask *irq_create_affinity_mask(unsigned int *nr_vecs) return NULL; } + get_online_cpus(); if (max_vecs >= num_online_cpus()) { cpumask_copy(affinity_mask, cpu_online_mask); *nr_vecs = num_online_cpus(); @@ -56,6 +57,7 @@ struct cpumask *irq_create_affinity_mask(unsigned int *nr_vecs) } *nr_vecs = vecs; } + put_online_cpus(); return affinity_mask; } From 7e4379eae0e31994ea645db1d13006ea8e5ce539 Mon Sep 17 00:00:00 2001 From: Andrej Krutak Date: Thu, 18 Aug 2016 23:52:10 +0200 Subject: [PATCH 232/531] ALSA: line6: Remove double line6_pcm_release() after failed acquire. If there's an error, pcm is released in line6_pcm_acquire already. Fixes: 247d95ee6dd2 ('ALSA: line6: Handle error from line6_pcm_acquire()') Cc: # v4.0+ Reviewed-by: Stefan Hajnoczi Signed-off-by: Andrej Krutak Signed-off-by: Takashi Iwai --- sound/usb/line6/pcm.c | 1 - 1 file changed, 1 deletion(-) diff --git a/sound/usb/line6/pcm.c b/sound/usb/line6/pcm.c index 204cc074adb9..2bc8879757f9 100644 --- a/sound/usb/line6/pcm.c +++ b/sound/usb/line6/pcm.c @@ -55,7 +55,6 @@ static int snd_line6_impulse_volume_put(struct snd_kcontrol *kcontrol, err = line6_pcm_acquire(line6pcm, LINE6_STREAM_IMPULSE); if (err < 0) { line6pcm->impulse_volume = 0; - line6_pcm_release(line6pcm, LINE6_STREAM_IMPULSE); return err; } } else { From adc8a43a6d6688272ebffa81789fa857e603dec6 Mon Sep 17 00:00:00 2001 From: Andrej Krutak Date: Thu, 18 Aug 2016 23:52:11 +0200 Subject: [PATCH 233/531] ALSA: line6: Give up on the lock while URBs are released. Done, because line6_stream_stop() locks and calls line6_unlink_audio_urbs(), which in turn invokes audio_out_callback(), which tries to lock 2nd time. Fixes: ============================================= [ INFO: possible recursive locking detected ] 4.4.15+ #15 Not tainted --------------------------------------------- mplayer/3591 is trying to acquire lock: (&(&line6pcm->out.lock)->rlock){-.-...}, at: [] audio_out_callback+0x70/0x110 [snd_usb_line6] but task is already holding lock: (&(&line6pcm->out.lock)->rlock){-.-...}, at: [] line6_stream_stop+0x24/0x5c [snd_usb_line6] other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&(&line6pcm->out.lock)->rlock); lock(&(&line6pcm->out.lock)->rlock); *** DEADLOCK *** May be due to missing lock nesting notation 3 locks held by mplayer/3591: #0: (snd_pcm_link_rwlock){.-.-..}, at: [] snd_pcm_stream_lock+0x1e/0x40 [snd_pcm] #1: (&(&substream->self_group.lock)->rlock){-.-...}, at: [] snd_pcm_stream_lock+0x26/0x40 [snd_pcm] #2: (&(&line6pcm->out.lock)->rlock){-.-...}, at: [] line6_stream_stop+0x24/0x5c [snd_usb_line6] stack backtrace: CPU: 0 PID: 3591 Comm: mplayer Not tainted 4.4.15+ #15 Hardware name: Generic AM33XX (Flattened Device Tree) [] (unwind_backtrace) from [] (show_stack+0x11/0x14) [] (show_stack) from [] (dump_stack+0x8b/0xac) [] (dump_stack) from [] (__lock_acquire+0xc8b/0x1780) [] (__lock_acquire) from [] (lock_acquire+0x99/0x1c0) [] (lock_acquire) from [] (_raw_spin_lock_irqsave+0x3f/0x4c) [] (_raw_spin_lock_irqsave) from [] (audio_out_callback+0x70/0x110 [snd_usb_line6]) [] (audio_out_callback [snd_usb_line6]) from [] (__usb_hcd_giveback_urb+0x53/0xd0) [] (__usb_hcd_giveback_urb) from [] (musb_giveback+0x3d/0x98) [] (musb_giveback) from [] (musb_urb_dequeue+0x6d/0x114) [] (musb_urb_dequeue) from [] (usb_hcd_unlink_urb+0x39/0x98) [] (usb_hcd_unlink_urb) from [] (line6_unlink_audio_urbs+0x6a/0x6c [snd_usb_line6]) [] (line6_unlink_audio_urbs [snd_usb_line6]) from [] (line6_stream_stop+0x42/0x5c [snd_usb_line6]) [] (line6_stream_stop [snd_usb_line6]) from [] (snd_line6_trigger+0xb6/0xf4 [snd_usb_line6]) [] (snd_line6_trigger [snd_usb_line6]) from [] (snd_pcm_do_stop+0x36/0x38 [snd_pcm]) [] (snd_pcm_do_stop [snd_pcm]) from [] (snd_pcm_action_single+0x22/0x40 [snd_pcm]) [] (snd_pcm_action_single [snd_pcm]) from [] (snd_pcm_action+0xac/0xb0 [snd_pcm]) [] (snd_pcm_action [snd_pcm]) from [] (snd_pcm_drop+0x38/0x64 [snd_pcm]) [] (snd_pcm_drop [snd_pcm]) from [] (snd_pcm_common_ioctl1+0x7fe/0xbe8 [snd_pcm]) [] (snd_pcm_common_ioctl1 [snd_pcm]) from [] (snd_pcm_playback_ioctl1+0x15c/0x51c [snd_pcm]) [] (snd_pcm_playback_ioctl1 [snd_pcm]) from [] (snd_pcm_playback_ioctl+0x20/0x28 [snd_pcm]) [] (snd_pcm_playback_ioctl [snd_pcm]) from [] (do_vfs_ioctl+0x3af/0x5c8) Fixes: 63e20df1e5b2 ('ALSA: line6: Reorganize PCM stream handling') Cc: # v4.0+ Reviewed-by: Stefan Hajnoczi Signed-off-by: Andrej Krutak Signed-off-by: Takashi Iwai --- sound/usb/line6/pcm.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/usb/line6/pcm.c b/sound/usb/line6/pcm.c index 2bc8879757f9..41aa3355e920 100644 --- a/sound/usb/line6/pcm.c +++ b/sound/usb/line6/pcm.c @@ -210,7 +210,9 @@ static void line6_stream_stop(struct snd_line6_pcm *line6pcm, int direction, spin_lock_irqsave(&pstr->lock, flags); clear_bit(type, &pstr->running); if (!pstr->running) { + spin_unlock_irqrestore(&pstr->lock, flags); line6_unlink_audio_urbs(line6pcm, pstr); + spin_lock_irqsave(&pstr->lock, flags); if (direction == SNDRV_PCM_STREAM_CAPTURE) { line6pcm->prev_fbuf = NULL; line6pcm->prev_fsize = 0; From b027d11263836a0cd335520175257dcb99b43757 Mon Sep 17 00:00:00 2001 From: Andrej Krutak Date: Thu, 18 Aug 2016 23:52:12 +0200 Subject: [PATCH 234/531] ALSA: line6: Fix POD sysfs attributes segfault The commit 02fc76f6a changed base of the sysfs attributes from device to card. The "show" callbacks dereferenced wrong objects because of this. Fixes: 02fc76f6a7db ('ALSA: line6: Create sysfs via snd_card_add_dev_attr()') Cc: # v4.0+ Reviewed-by: Stefan Hajnoczi Signed-off-by: Andrej Krutak Signed-off-by: Takashi Iwai --- sound/usb/line6/pod.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/sound/usb/line6/pod.c b/sound/usb/line6/pod.c index daf81d169a42..45dd34874f43 100644 --- a/sound/usb/line6/pod.c +++ b/sound/usb/line6/pod.c @@ -244,8 +244,8 @@ static int pod_set_system_param_int(struct usb_line6_pod *pod, int value, static ssize_t serial_number_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct usb_interface *interface = to_usb_interface(dev); - struct usb_line6_pod *pod = usb_get_intfdata(interface); + struct snd_card *card = dev_to_snd_card(dev); + struct usb_line6_pod *pod = card->private_data; return sprintf(buf, "%u\n", pod->serial_number); } @@ -256,8 +256,8 @@ static ssize_t serial_number_show(struct device *dev, static ssize_t firmware_version_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct usb_interface *interface = to_usb_interface(dev); - struct usb_line6_pod *pod = usb_get_intfdata(interface); + struct snd_card *card = dev_to_snd_card(dev); + struct usb_line6_pod *pod = card->private_data; return sprintf(buf, "%d.%02d\n", pod->firmware_version / 100, pod->firmware_version % 100); @@ -269,8 +269,8 @@ static ssize_t firmware_version_show(struct device *dev, static ssize_t device_id_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct usb_interface *interface = to_usb_interface(dev); - struct usb_line6_pod *pod = usb_get_intfdata(interface); + struct snd_card *card = dev_to_snd_card(dev); + struct usb_line6_pod *pod = card->private_data; return sprintf(buf, "%d\n", pod->device_id); } From f4750a46a0dee58f7a65b438b28a092669b609aa Mon Sep 17 00:00:00 2001 From: Matt Roper Date: Fri, 17 Jun 2016 13:42:18 -0700 Subject: [PATCH 235/531] drm/i915/gen9: Initialize intel_state->active_crtcs during WM sanitization (v2) intel_state->active_crtcs is usually only initialized when doing a modeset. During our first atomic commit after boot, we're effectively faking a modeset to sanitize the DDB/wm setup, so ensure that this field gets initialized before use. v2: - Don't clobber active_crtcs if our first commit really is a modeset (Maarten) - Grab connection_mutex when faking a modeset during sanitization (Maarten) Reported-by: Tvrtko Ursulin Cc: Tvrtko Ursulin Cc: Maarten Lankhorst Signed-off-by: Matt Roper Tested-by: Tvrtko Ursulin Signed-off-by: Maarten Lankhorst Link: http://patchwork.freedesktop.org/patch/msgid/1466196140-16336-2-git-send-email-matthew.d.roper@intel.com Cc: stable@vger.kernel.org #v4.7+ (cherry picked from commit 1b54a880b250acc226b13cea221b90aa1b3e37dd) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_pm.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index d5deb58a2128..e9763a89f3d7 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -3912,9 +3912,24 @@ skl_compute_ddb(struct drm_atomic_state *state) * pretend that all pipes switched active status so that we'll * ensure a full DDB recompute. */ - if (dev_priv->wm.distrust_bios_wm) + if (dev_priv->wm.distrust_bios_wm) { + ret = drm_modeset_lock(&dev->mode_config.connection_mutex, + state->acquire_ctx); + if (ret) + return ret; + intel_state->active_pipe_changes = ~0; + /* + * We usually only initialize intel_state->active_crtcs if we + * we're doing a modeset; make sure this field is always + * initialized during the sanitization process that happens + * on the first commit too. + */ + if (!intel_state->modeset) + intel_state->active_crtcs = dev_priv->active_crtcs; + } + /* * If the modeset changes which CRTC's are active, we need to * recompute the DDB allocation for *all* active pipes, even From c7aca235aa60d1432c95b752812d359d0dbece4f Mon Sep 17 00:00:00 2001 From: Matt Roper Date: Fri, 17 Jun 2016 13:42:20 -0700 Subject: [PATCH 236/531] drm/i915/gen9: Drop invalid WARN() during data rate calculation It's possible to have a non-zero plane mask and still wind up with a total data rate of zero. There are two cases where this can happen: * planes are active (from the KMS point of view), but are all fully clipped (positioned offscreen) * the only active plane on a CRTC is the cursor (which is handled independently and not counted into the general data rate computations These are both valid display setups (although unusual), so we need to drop the WARN(). Signed-off-by: Matt Roper Reviewed-by: Maarten Lankhorst Testcase: kms_universal_planes.cursor-only-pipe-* Signed-off-by: Maarten Lankhorst Link: http://patchwork.freedesktop.org/patch/msgid/1466196140-16336-4-git-send-email-matthew.d.roper@intel.com Cc: stable@vger.kernel.org #v4.7+ (cherry picked from commit 43aa7e87507f519b0b2497b6fac1e894554eaef2) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_pm.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index e9763a89f3d7..421c5b72464a 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -3107,8 +3107,6 @@ skl_get_total_relative_data_rate(struct intel_crtc_state *intel_cstate) total_data_rate += intel_cstate->wm.skl.plane_y_data_rate[id]; } - WARN_ON(cstate->plane_mask && total_data_rate == 0); - return total_data_rate; } From dcd79934b0dd803fdb29216fbd6f4a899a66f466 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 18 Aug 2016 17:16:40 +0100 Subject: [PATCH 237/531] drm/i915: Unconditionally flush any chipset buffers before execbuf MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If userspace is asynchronously streaming into the batch or other execobjects, we may not flush those writes along with a change in cache domain (as there is no change). Therefore those writes may end up in internal chipset buffers and not visible to the GPU upon execution. We must issue a flush command or otherwise we encounter incoherency in the batchbuffers and the GPU executing invalid commands (i.e. hanging) quite regularly. v2: Throw a paranoid wmb() into the general flush so that we remain consistent with before. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=90841 Fixes: 1816f9236303 ("drm/i915: Support creation of unbound wc user...") Signed-off-by: Chris Wilson Cc: Akash Goel Cc: Daniel Vetter Cc: Tvrtko Ursulin Tested-by: Matti Hämäläinen Cc: stable@vger.kernel.org Reviewed-by: Mika Kuoppala Link: http://patchwork.freedesktop.org/patch/msgid/20160818161718.27187-1-chris@chris-wilson.co.uk (cherry picked from commit 600f436801deae65e48404847b61c89b4944e355) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_drv.h | 1 + drivers/gpu/drm/i915/i915_gem_execbuffer.c | 13 +++---------- 2 files changed, 4 insertions(+), 10 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 20fe9d52e256..3ca674e9c105 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -3591,6 +3591,7 @@ int i915_gem_evict_vm(struct i915_address_space *vm, bool do_idle); /* belongs in i915_gem_gtt.h */ static inline void i915_gem_chipset_flush(struct drm_i915_private *dev_priv) { + wmb(); if (INTEL_GEN(dev_priv) < 6) intel_gtt_chipset_flush(); } diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 1978633e7549..b35e5b6475b2 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -943,8 +943,6 @@ i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req, { const unsigned other_rings = ~intel_engine_flag(req->engine); struct i915_vma *vma; - uint32_t flush_domains = 0; - bool flush_chipset = false; int ret; list_for_each_entry(vma, vmas, exec_list) { @@ -957,16 +955,11 @@ i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req, } if (obj->base.write_domain & I915_GEM_DOMAIN_CPU) - flush_chipset |= i915_gem_clflush_object(obj, false); - - flush_domains |= obj->base.write_domain; + i915_gem_clflush_object(obj, false); } - if (flush_chipset) - i915_gem_chipset_flush(req->engine->i915); - - if (flush_domains & I915_GEM_DOMAIN_GTT) - wmb(); + /* Unconditionally flush any chipset caches (for streaming writes). */ + i915_gem_chipset_flush(req->engine->i915); /* Unconditionally invalidate gpu caches and ensure that we do flush * any residual writes from the previous batch. From 0184c2fff11705d0041c61356c57eac2e033c686 Mon Sep 17 00:00:00 2001 From: Dave Gordon Date: Fri, 19 Aug 2016 15:23:42 +0100 Subject: [PATCH 238/531] drm/i915: Reattach comment, complete type specification In the recent patch bc3d674 drm/i915: Allow userspace to request no-error-capture upon ... the final version moved the flags and the associated #defines around so they were adjacent; unfortunately, they ended up between a comment and the thing (hw_id) to which the comment applies :( So this patch reshuffles the comment and subject back together. Also, as we're touching 'hw_id', let's change it from just 'unsigned' to a fully-specified 'unsigned int', because some code checking tools (including checkpatch) object to plain 'unsigned'. Fixes: bc3d674462e5 ("drm/i915: Allow userspace to request no-error-capture...") Signed-off-by: Dave Gordon Cc: Chris Wilson Link: http://patchwork.freedesktop.org/patch/msgid/1471616622-6919-1-git-send-email-david.s.gordon@intel.com Reviewed-by: Chris Wilson Signed-off-by: Chris Wilson (cherry picked from commit 0be81156b3fb4d4e8e2c94177e5222dc21c3ff10) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_drv.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 3ca674e9c105..46e372ece6eb 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -882,11 +882,12 @@ struct i915_gem_context { struct i915_ctx_hang_stats hang_stats; - /* Unique identifier for this context, used by the hw for tracking */ unsigned long flags; #define CONTEXT_NO_ZEROMAP BIT(0) #define CONTEXT_NO_ERROR_CAPTURE BIT(1) - unsigned hw_id; + + /* Unique identifier for this context, used by the hw for tracking */ + unsigned int hw_id; u32 user_handle; u32 ggtt_alignment; From 5bc6abe7674d9cf41dbcdaaf98a19184da181439 Mon Sep 17 00:00:00 2001 From: Lyude Date: Wed, 17 Aug 2016 15:55:53 -0400 Subject: [PATCH 239/531] drm/i915/gen6+: Interpret mailbox error flags MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In order to add proper support for the SAGV, we need to be able to know what the cause of a failure to change the SAGV through the pcode mailbox was. The reasoning for this is that some very early pre-release Skylake machines don't actually allow you to control the SAGV on them, and indicate an invalid mailbox command was sent. This also might come in handy in the future for debugging. Changes since v1: - Add functions for interpreting gen6 mailbox error codes along with gen7+ error codes, and actually interpret those codes properly - Renamed patch to reflect new behavior Signed-off-by: Lyude Cc: Matt Roper Cc: Maarten Lankhorst Cc: Daniel Vetter Cc: Ville Syrjälä Cc: stable@vger.kernel.org Signed-off-by: Maarten Lankhorst Link: http://patchwork.freedesktop.org/patch/msgid/1471463761-26796-2-git-send-email-cpaul@redhat.com [mlankhorst: -ENOSYS -> -ENXIO for checkpatch] (cherry picked from commit 87660502f1a4d51fb043e89a45d30c9917787c22) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_reg.h | 9 +++++ drivers/gpu/drm/i915/intel_pm.c | 71 ++++++++++++++++++++++++++++++++- 2 files changed, 79 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 5c06413ae0e6..2b9508dda759 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -7145,6 +7145,15 @@ enum { #define GEN6_PCODE_MAILBOX _MMIO(0x138124) #define GEN6_PCODE_READY (1<<31) +#define GEN6_PCODE_ERROR_MASK 0xFF +#define GEN6_PCODE_SUCCESS 0x0 +#define GEN6_PCODE_ILLEGAL_CMD 0x1 +#define GEN6_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE 0x2 +#define GEN6_PCODE_TIMEOUT 0x3 +#define GEN6_PCODE_UNIMPLEMENTED_CMD 0xFF +#define GEN7_PCODE_TIMEOUT 0x2 +#define GEN7_PCODE_ILLEGAL_DATA 0x3 +#define GEN7_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE 0x10 #define GEN6_PCODE_WRITE_RC6VIDS 0x4 #define GEN6_PCODE_READ_RC6VIDS 0x5 #define GEN6_ENCODE_RC6_VID(mv) (((mv) - 245) / 5) diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 421c5b72464a..2c88c2f50d02 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -7671,8 +7671,53 @@ void intel_init_pm(struct drm_device *dev) } } +static inline int gen6_check_mailbox_status(struct drm_i915_private *dev_priv) +{ + uint32_t flags = + I915_READ_FW(GEN6_PCODE_MAILBOX) & GEN6_PCODE_ERROR_MASK; + + switch (flags) { + case GEN6_PCODE_SUCCESS: + return 0; + case GEN6_PCODE_UNIMPLEMENTED_CMD: + case GEN6_PCODE_ILLEGAL_CMD: + return -ENXIO; + case GEN6_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE: + return -EOVERFLOW; + case GEN6_PCODE_TIMEOUT: + return -ETIMEDOUT; + default: + MISSING_CASE(flags) + return 0; + } +} + +static inline int gen7_check_mailbox_status(struct drm_i915_private *dev_priv) +{ + uint32_t flags = + I915_READ_FW(GEN6_PCODE_MAILBOX) & GEN6_PCODE_ERROR_MASK; + + switch (flags) { + case GEN6_PCODE_SUCCESS: + return 0; + case GEN6_PCODE_ILLEGAL_CMD: + return -ENXIO; + case GEN7_PCODE_TIMEOUT: + return -ETIMEDOUT; + case GEN7_PCODE_ILLEGAL_DATA: + return -EINVAL; + case GEN7_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE: + return -EOVERFLOW; + default: + MISSING_CASE(flags); + return 0; + } +} + int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val) { + int status; + WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock)); /* GEN6_PCODE_* are outside of the forcewake domain, we can @@ -7699,12 +7744,25 @@ int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val *val = I915_READ_FW(GEN6_PCODE_DATA); I915_WRITE_FW(GEN6_PCODE_DATA, 0); + if (INTEL_GEN(dev_priv) > 6) + status = gen7_check_mailbox_status(dev_priv); + else + status = gen6_check_mailbox_status(dev_priv); + + if (status) { + DRM_DEBUG_DRIVER("warning: pcode (read) mailbox access failed: %d\n", + status); + return status; + } + return 0; } int sandybridge_pcode_write(struct drm_i915_private *dev_priv, - u32 mbox, u32 val) + u32 mbox, u32 val) { + int status; + WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock)); /* GEN6_PCODE_* are outside of the forcewake domain, we can @@ -7729,6 +7787,17 @@ int sandybridge_pcode_write(struct drm_i915_private *dev_priv, I915_WRITE_FW(GEN6_PCODE_DATA, 0); + if (INTEL_GEN(dev_priv) > 6) + status = gen7_check_mailbox_status(dev_priv); + else + status = gen6_check_mailbox_status(dev_priv); + + if (status) { + DRM_DEBUG_DRIVER("warning: pcode (write) mailbox access failed: %d\n", + status); + return status; + } + return 0; } From f403372658fc7b652a77885a4141e58e57d9c75a Mon Sep 17 00:00:00 2001 From: Lyude Date: Wed, 17 Aug 2016 15:55:54 -0400 Subject: [PATCH 240/531] drm/i915/skl: Add support for the SAGV, fix underrun hangs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since the watermark calculations for Skylake are still broken, we're apt to hitting underruns very easily under multi-monitor configurations. While it would be lovely if this was fixed, it's not. Another problem that's been coming from this however, is the mysterious issue of underruns causing full system hangs. An easy way to reproduce this with a skylake system: - Get a laptop with a skylake GPU, and hook up two external monitors to it - Move the cursor from the built-in LCD to one of the external displays as quickly as you can - You'll get a few pipe underruns, and eventually the entire system will just freeze. After doing a lot of investigation and reading through the bspec, I found the existence of the SAGV, which is responsible for adjusting the system agent voltage and clock frequencies depending on how much power we need. According to the bspec: "The display engine access to system memory is blocked during the adjustment time. SAGV defaults to enabled. Software must use the GT-driver pcode mailbox to disable SAGV when the display engine is not able to tolerate the blocking time." The rest of the bspec goes on to explain that software can simply leave the SAGV enabled, and disable it when we use interlaced pipes/have more then one pipe active. Sure enough, with this patchset the system hangs resulting from pipe underruns on Skylake have completely vanished on my T460s. Additionally, the bspec mentions turning off the SAGV with more then one pipe enabled as a workaround for display underruns. While this patch doesn't entirely fix that, it looks like it does improve the situation a little bit so it's likely this is going to be required to make watermarks on Skylake fully functional. This will still need additional work in the future: we shouldn't be enabling the SAGV if any of the currently enabled planes can't enable WM levels that introduce latencies >= 30 µs. Changes since v11: - Add skl_can_enable_sagv() - Make sure we don't enable SAGV when not all planes can enable watermarks >= the SAGV engine block time. I was originally going to save this for later, but I recently managed to run into a machine that was having problems with a single pipe configuration + SAGV. - Make comparisons to I915_SKL_SAGV_NOT_CONTROLLED explicit - Change I915_SAGV_DYNAMIC_FREQ to I915_SAGV_ENABLE - Move printks outside of mutexes - Don't print error messages twice Changes since v10: - Apparently sandybridge_pcode_read actually writes values and reads them back, despite it's misleading function name. This means we've been doing this mostly wrong and have been writing garbage to the SAGV control. Because of this, we no longer attempt to read the SAGV status during initialization (since there are no helpers for this). - mlankhorst noticed that this patch was breaking on some very early pre-release Skylake machines, which apparently don't allow you to disable the SAGV. To prevent machines from failing tests due to SAGV errors, if the first time we try to control the SAGV results in the mailbox indicating an invalid command, we just disable future attempts to control the SAGV state by setting dev_priv->skl_sagv_status to I915_SKL_SAGV_NOT_CONTROLLED and make a note of it in dmesg. - Move mutex_unlock() a little higher in skl_enable_sagv(). This doesn't actually fix anything, but lets us release the lock a little sooner since we're finished with it. Changes since v9: - Only enable/disable sagv on Skylake Changes since v8: - Add intel_state->modeset guard to the conditional for skl_enable_sagv() Changes since v7: - Remove GEN9_SAGV_LOW_FREQ, replace with GEN9_SAGV_IS_ENABLED (that's all we use it for anyway) - Use GEN9_SAGV_IS_ENABLED instead of 0x1 for clarification - Fix a styling error that snuck past me Changes since v6: - Protect skl_enable_sagv() with intel_state->modeset conditional in intel_atomic_commit_tail() Changes since v5: - Don't use is_power_of_2. Makes things confusing - Don't use the old state to figure out whether or not to enable/disable the sagv, use the new one - Split the loop in skl_disable_sagv into it's own function - Move skl_sagv_enable/disable() calls into intel_atomic_commit_tail() Changes since v4: - Use is_power_of_2 against active_crtcs to check whether we have > 1 pipe enabled - Fix skl_sagv_get_hw_state(): (temp & 0x1) indicates disabled, 0x0 enabled - Call skl_sagv_enable/disable() from pre/post-plane updates Changes since v3: - Use time_before() to compare timeout to jiffies Changes since v2: - Really apply minor style nitpicks to patch this time Changes since v1: - Added comments about this probably being one of the requirements to fixing Skylake's watermark issues - Minor style nitpicks from Matt Roper - Disable these functions on Broxton, since it doesn't have an SAGV Signed-off-by: Lyude Cc: Matt Roper Cc: Maarten Lankhorst Cc: Daniel Vetter Cc: Ville Syrjälä Cc: stable@vger.kernel.org Signed-off-by: Maarten Lankhorst Link: http://patchwork.freedesktop.org/patch/msgid/1471463761-26796-3-git-send-email-cpaul@redhat.com [mlankhorst: ENOSYS -> ENXIO, whitespace fixes] (cherry picked from commit 656d1b89e5ffb83036ab0e2a24be7558f34365c7) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_drv.h | 7 ++ drivers/gpu/drm/i915/i915_reg.h | 4 + drivers/gpu/drm/i915/intel_display.c | 11 ++ drivers/gpu/drm/i915/intel_drv.h | 3 + drivers/gpu/drm/i915/intel_pm.c | 148 +++++++++++++++++++++++++++ 5 files changed, 173 insertions(+) diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 46e372ece6eb..f68c78918d63 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1964,6 +1964,13 @@ struct drm_i915_private { struct i915_suspend_saved_registers regfile; struct vlv_s0ix_state vlv_s0ix_state; + enum { + I915_SKL_SAGV_UNKNOWN = 0, + I915_SKL_SAGV_DISABLED, + I915_SKL_SAGV_ENABLED, + I915_SKL_SAGV_NOT_CONTROLLED + } skl_sagv_status; + struct { /* * Raw watermark latency values: diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 2b9508dda759..bf2cad3f9e1f 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -7175,6 +7175,10 @@ enum { #define HSW_PCODE_DE_WRITE_FREQ_REQ 0x17 #define DISPLAY_IPS_CONTROL 0x19 #define HSW_PCODE_DYNAMIC_DUTY_CYCLE_CONTROL 0x1A +#define GEN9_PCODE_SAGV_CONTROL 0x21 +#define GEN9_SAGV_DISABLE 0x0 +#define GEN9_SAGV_IS_DISABLED 0x1 +#define GEN9_SAGV_ENABLE 0x3 #define GEN6_PCODE_DATA _MMIO(0x138128) #define GEN6_PCODE_FREQ_IA_RATIO_SHIFT 8 #define GEN6_PCODE_FREQ_RING_RATIO_SHIFT 16 diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 2a751b6e0253..175595fc3e45 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -13759,6 +13759,13 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state) intel_state->cdclk_pll_vco != dev_priv->cdclk_pll.vco)) dev_priv->display.modeset_commit_cdclk(state); + /* + * SKL workaround: bspec recommends we disable the SAGV when we + * have more then one pipe enabled + */ + if (IS_SKYLAKE(dev_priv) && !skl_can_enable_sagv(state)) + skl_disable_sagv(dev_priv); + intel_modeset_verify_disabled(dev); } @@ -13832,6 +13839,10 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state) intel_modeset_verify_crtc(crtc, old_crtc_state, crtc->state); } + if (IS_SKYLAKE(dev_priv) && intel_state->modeset && + skl_can_enable_sagv(state)) + skl_enable_sagv(dev_priv); + drm_atomic_helper_commit_hw_done(state); if (intel_state->modeset) diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index cc937a19b1ba..ff399b9a5c1f 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -1716,6 +1716,9 @@ void ilk_wm_get_hw_state(struct drm_device *dev); void skl_wm_get_hw_state(struct drm_device *dev); void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv, struct skl_ddb_allocation *ddb /* out */); +bool skl_can_enable_sagv(struct drm_atomic_state *state); +int skl_enable_sagv(struct drm_i915_private *dev_priv); +int skl_disable_sagv(struct drm_i915_private *dev_priv); uint32_t ilk_pipe_pixel_rate(const struct intel_crtc_state *pipe_config); bool ilk_disable_lp_wm(struct drm_device *dev); int sanitize_rc6_option(struct drm_i915_private *dev_priv, int enable_rc6); diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 2c88c2f50d02..496a911e5668 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -2852,6 +2852,7 @@ bool ilk_disable_lp_wm(struct drm_device *dev) #define SKL_DDB_SIZE 896 /* in blocks */ #define BXT_DDB_SIZE 512 +#define SKL_SAGV_BLOCK_TIME 30 /* µs */ /* * Return the index of a plane in the SKL DDB and wm result arrays. Primary @@ -2875,6 +2876,153 @@ skl_wm_plane_id(const struct intel_plane *plane) } } +/* + * SAGV dynamically adjusts the system agent voltage and clock frequencies + * depending on power and performance requirements. The display engine access + * to system memory is blocked during the adjustment time. Because of the + * blocking time, having this enabled can cause full system hangs and/or pipe + * underruns if we don't meet all of the following requirements: + * + * - <= 1 pipe enabled + * - All planes can enable watermarks for latencies >= SAGV engine block time + * - We're not using an interlaced display configuration + */ +int +skl_enable_sagv(struct drm_i915_private *dev_priv) +{ + int ret; + + if (dev_priv->skl_sagv_status == I915_SKL_SAGV_NOT_CONTROLLED || + dev_priv->skl_sagv_status == I915_SKL_SAGV_ENABLED) + return 0; + + DRM_DEBUG_KMS("Enabling the SAGV\n"); + mutex_lock(&dev_priv->rps.hw_lock); + + ret = sandybridge_pcode_write(dev_priv, GEN9_PCODE_SAGV_CONTROL, + GEN9_SAGV_ENABLE); + + /* We don't need to wait for the SAGV when enabling */ + mutex_unlock(&dev_priv->rps.hw_lock); + + /* + * Some skl systems, pre-release machines in particular, + * don't actually have an SAGV. + */ + if (ret == -ENXIO) { + DRM_DEBUG_DRIVER("No SAGV found on system, ignoring\n"); + dev_priv->skl_sagv_status = I915_SKL_SAGV_NOT_CONTROLLED; + return 0; + } else if (ret < 0) { + DRM_ERROR("Failed to enable the SAGV\n"); + return ret; + } + + dev_priv->skl_sagv_status = I915_SKL_SAGV_ENABLED; + return 0; +} + +static int +skl_do_sagv_disable(struct drm_i915_private *dev_priv) +{ + int ret; + uint32_t temp = GEN9_SAGV_DISABLE; + + ret = sandybridge_pcode_read(dev_priv, GEN9_PCODE_SAGV_CONTROL, + &temp); + if (ret) + return ret; + else + return temp & GEN9_SAGV_IS_DISABLED; +} + +int +skl_disable_sagv(struct drm_i915_private *dev_priv) +{ + int ret, result; + + if (dev_priv->skl_sagv_status == I915_SKL_SAGV_NOT_CONTROLLED || + dev_priv->skl_sagv_status == I915_SKL_SAGV_DISABLED) + return 0; + + DRM_DEBUG_KMS("Disabling the SAGV\n"); + mutex_lock(&dev_priv->rps.hw_lock); + + /* bspec says to keep retrying for at least 1 ms */ + ret = wait_for(result = skl_do_sagv_disable(dev_priv), 1); + mutex_unlock(&dev_priv->rps.hw_lock); + + if (ret == -ETIMEDOUT) { + DRM_ERROR("Request to disable SAGV timed out\n"); + return -ETIMEDOUT; + } + + /* + * Some skl systems, pre-release machines in particular, + * don't actually have an SAGV. + */ + if (result == -ENXIO) { + DRM_DEBUG_DRIVER("No SAGV found on system, ignoring\n"); + dev_priv->skl_sagv_status = I915_SKL_SAGV_NOT_CONTROLLED; + return 0; + } else if (result < 0) { + DRM_ERROR("Failed to disable the SAGV\n"); + return result; + } + + dev_priv->skl_sagv_status = I915_SKL_SAGV_DISABLED; + return 0; +} + +bool skl_can_enable_sagv(struct drm_atomic_state *state) +{ + struct drm_device *dev = state->dev; + struct drm_i915_private *dev_priv = to_i915(dev); + struct intel_atomic_state *intel_state = to_intel_atomic_state(state); + struct drm_crtc *crtc; + enum pipe pipe; + int level, plane; + + /* + * SKL workaround: bspec recommends we disable the SAGV when we have + * more then one pipe enabled + * + * If there are no active CRTCs, no additional checks need be performed + */ + if (hweight32(intel_state->active_crtcs) == 0) + return true; + else if (hweight32(intel_state->active_crtcs) > 1) + return false; + + /* Since we're now guaranteed to only have one active CRTC... */ + pipe = ffs(intel_state->active_crtcs) - 1; + crtc = dev_priv->pipe_to_crtc_mapping[pipe]; + + if (crtc->state->mode.flags & DRM_MODE_FLAG_INTERLACE) + return false; + + for_each_plane(dev_priv, pipe, plane) { + /* Skip this plane if it's not enabled */ + if (intel_state->wm_results.plane[pipe][plane][0] == 0) + continue; + + /* Find the highest enabled wm level for this plane */ + for (level = ilk_wm_max_level(dev); + intel_state->wm_results.plane[pipe][plane][level] == 0; --level) + { } + + /* + * If any of the planes on this pipe don't enable wm levels + * that incur memory latencies higher then 30µs we can't enable + * the SAGV + */ + if (dev_priv->wm.skl_latency[level] < SKL_SAGV_BLOCK_TIME) + return false; + } + + return true; +} + static void skl_ddb_get_pipe_allocation_limits(struct drm_device *dev, const struct intel_crtc_state *cstate, From 9909113cc48a7ce6e772573e3cc82a3f03ffa8ef Mon Sep 17 00:00:00 2001 From: Matt Roper Date: Wed, 17 Aug 2016 15:55:55 -0400 Subject: [PATCH 241/531] drm/i915/gen9: Only copy WM results for changed pipes to skl_hw MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When we write watermark values to the hardware, those values are stored in dev_priv->wm.skl_hw. However with recent watermark changes, the results structure we're copying from only contains valid watermark and DDB values for the pipes that are actually changing; the values for other pipes remain 0. Thus a blind copy of the entire skl_wm_values structure will clobber the values for unchanged pipes...we need to be more selective and only copy over the values for the changing pipes. This mistake was hidden until recently due to another bug that caused us to erroneously re-calculate watermarks for all active pipes rather than changing pipes. Only when that bug was fixed was the impact of this bug discovered (e.g., modesets failing with "Requested display configuration exceeds system watermark limitations" messages and leaving watermarks non-functional, even ones initiated by intel_fbdev_restore_mode). Changes since v1: - Add a function for copying a pipe's wm values (skl_copy_wm_for_pipe()) so we can reuse this later Fixes: 734fa01f3a17 ("drm/i915/gen9: Calculate watermarks during atomic 'check' (v2)") Fixes: 9b6130227495 ("drm/i915/gen9: Re-allocate DDB only for changed pipes") Signed-off-by: Matt Roper Signed-off-by: Lyude Reviewed-by: Matt Roper Cc: stable@vger.kernel.org Cc: Maarten Lankhorst Cc: Ville Syrjälä Cc: Daniel Vetter Cc: Radhakrishna Sripada Cc: Hans de Goede Signed-off-by: Maarten Lankhorst Link: http://patchwork.freedesktop.org/patch/msgid/1471463761-26796-4-git-send-email-cpaul@redhat.com (cherry picked from commit 2722efb90b3420dee54b4cb3cdc7917efacc2dce) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_pm.c | 28 ++++++++++++++++++++++++++-- 1 file changed, 26 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 496a911e5668..70dcf8d35568 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -4109,6 +4109,24 @@ skl_compute_ddb(struct drm_atomic_state *state) return 0; } +static void +skl_copy_wm_for_pipe(struct skl_wm_values *dst, + struct skl_wm_values *src, + enum pipe pipe) +{ + dst->wm_linetime[pipe] = src->wm_linetime[pipe]; + memcpy(dst->plane[pipe], src->plane[pipe], + sizeof(dst->plane[pipe])); + memcpy(dst->plane_trans[pipe], src->plane_trans[pipe], + sizeof(dst->plane_trans[pipe])); + + dst->ddb.pipe[pipe] = src->ddb.pipe[pipe]; + memcpy(dst->ddb.y_plane[pipe], src->ddb.y_plane[pipe], + sizeof(dst->ddb.y_plane[pipe])); + memcpy(dst->ddb.plane[pipe], src->ddb.plane[pipe], + sizeof(dst->ddb.plane[pipe])); +} + static int skl_compute_wm(struct drm_atomic_state *state) { @@ -4181,8 +4199,10 @@ static void skl_update_wm(struct drm_crtc *crtc) struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = to_i915(dev); struct skl_wm_values *results = &dev_priv->wm.skl_results; + struct skl_wm_values *hw_vals = &dev_priv->wm.skl_hw; struct intel_crtc_state *cstate = to_intel_crtc_state(crtc->state); struct skl_pipe_wm *pipe_wm = &cstate->wm.skl.optimal; + int pipe; if ((results->dirty_pipes & drm_crtc_mask(crtc)) == 0) return; @@ -4194,8 +4214,12 @@ static void skl_update_wm(struct drm_crtc *crtc) skl_write_wm_values(dev_priv, results); skl_flush_wm_values(dev_priv, results); - /* store the new configuration */ - dev_priv->wm.skl_hw = *results; + /* + * Store the new configuration (but only for the pipes that have + * changed; the other values weren't recomputed). + */ + for_each_pipe_masked(dev_priv, pipe, results->dirty_pipes) + skl_copy_wm_for_pipe(hw_vals, results, pipe); mutex_unlock(&dev_priv->wm.wm_mutex); } From 762c60ab0257d25eea8db3e3fec85ed53b5330fe Mon Sep 17 00:00:00 2001 From: Lyude Date: Wed, 17 Aug 2016 15:55:57 -0400 Subject: [PATCH 242/531] drm/i915/skl: Ensure pipes with changed wms get added to the state MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If we're enabling a pipe, we'll need to modify the watermarks on all active planes. Since those planes won't be added to the state on their own, we need to add them ourselves. Signed-off-by: Lyude Reviewed-by: Matt Roper Cc: stable@vger.kernel.org Cc: Ville Syrjälä Cc: Daniel Vetter Cc: Radhakrishna Sripada Cc: Hans de Goede Signed-off-by: Maarten Lankhorst Link: http://patchwork.freedesktop.org/patch/msgid/1471463761-26796-6-git-send-email-cpaul@redhat.com (cherry picked from commit 05a76d3d6ad1ee9f9814f88949cc9305fc165460) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_pm.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 70dcf8d35568..53e13c10e4ea 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -4104,6 +4104,10 @@ skl_compute_ddb(struct drm_atomic_state *state) ret = skl_allocate_pipe_ddb(cstate, ddb); if (ret) return ret; + + ret = drm_atomic_add_affected_planes(state, &intel_crtc->base); + if (ret) + return ret; } return 0; From 177d91aaea4bcafb29232336bafaa521b85286aa Mon Sep 17 00:00:00 2001 From: Maarten Lankhorst Date: Mon, 15 Aug 2016 15:09:27 +0200 Subject: [PATCH 243/531] drm/i915: Fix botched merge that downgrades CSR versions. Merge commit 5e580523d9128a4d8 reverts the version bumping parts of commit 4aa7fb9c3c4fa0. Bump the versions again and request the specific firmware version. The currently recommended versions are: SKL 1.26, KBL 1.01 and BXT 1.07. Cc: Patrik Jakobsson Cc: Imre Deak Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=97242 Cc: drm-intel-fixes@lists.freedesktop.org Fixes: 5e580523d912 ("Backmerge tag 'v4.7' into drm-next") Signed-off-by: Maarten Lankhorst Link: http://patchwork.freedesktop.org/patch/msgid/1471266567-22443-1-git-send-email-maarten.lankhorst@linux.intel.com Reviewed-by: Imre Deak (cherry picked from commit 536ab3ca19ef856e84389a155c5832c68559a28a) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_csr.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c index 3edb9580928e..c3b33a10c15c 100644 --- a/drivers/gpu/drm/i915/intel_csr.c +++ b/drivers/gpu/drm/i915/intel_csr.c @@ -41,15 +41,15 @@ * be moved to FW_FAILED. */ -#define I915_CSR_KBL "i915/kbl_dmc_ver1.bin" +#define I915_CSR_KBL "i915/kbl_dmc_ver1_01.bin" MODULE_FIRMWARE(I915_CSR_KBL); #define KBL_CSR_VERSION_REQUIRED CSR_VERSION(1, 1) -#define I915_CSR_SKL "i915/skl_dmc_ver1.bin" +#define I915_CSR_SKL "i915/skl_dmc_ver1_26.bin" MODULE_FIRMWARE(I915_CSR_SKL); -#define SKL_CSR_VERSION_REQUIRED CSR_VERSION(1, 23) +#define SKL_CSR_VERSION_REQUIRED CSR_VERSION(1, 26) -#define I915_CSR_BXT "i915/bxt_dmc_ver1.bin" +#define I915_CSR_BXT "i915/bxt_dmc_ver1_07.bin" MODULE_FIRMWARE(I915_CSR_BXT); #define BXT_CSR_VERSION_REQUIRED CSR_VERSION(1, 7) From e9e5e3fae8da7e237049e00e0bfc9e32fd808fe8 Mon Sep 17 00:00:00 2001 From: Vegard Nossum Date: Mon, 22 Aug 2016 12:47:43 +0200 Subject: [PATCH 244/531] bdev: fix NULL pointer dereference I got this: kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] PREEMPT SMP KASAN Dumping ftrace buffer: (ftrace buffer empty) CPU: 0 PID: 5505 Comm: syz-executor Not tainted 4.8.0-rc2+ #161 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org 04/01/2014 task: ffff880113415940 task.stack: ffff880118350000 RIP: 0010:[] [] bd_mount+0x52/0xa0 RSP: 0018:ffff880118357ca0 EFLAGS: 00010207 RAX: dffffc0000000000 RBX: ffffffffffffffff RCX: ffffc90000bb6000 RDX: 0000000000000018 RSI: ffffffff846d6b20 RDI: 00000000000000c7 RBP: ffff880118357cb0 R08: ffff880115967c68 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8801188211e8 R13: ffffffff847baa20 R14: ffff8801139cb000 R15: 0000000000000080 FS: 00007fa3ff6c0700(0000) GS:ffff88011aa00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fc1d8cc7e78 CR3: 0000000109f20000 CR4: 00000000000006f0 DR0: 000000000000001e DR1: 000000000000001e DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000600 Stack: ffff880112cfd6c0 ffff8801188211e8 ffff880118357cf0 ffffffff8167f207 ffffffff816d7a1e ffff880112a413c0 ffffffff847baa20 ffff8801188211e8 0000000000000080 ffff880112cfd6c0 ffff880118357d38 ffffffff816dce0a Call Trace: [] mount_fs+0x97/0x2e0 [] ? alloc_vfsmnt+0x55e/0x760 [] vfs_kern_mount+0x7a/0x300 [] ? _raw_read_unlock+0x2c/0x50 [] do_mount+0x3d7/0x2730 [] ? trace_do_page_fault+0x1f4/0x3a0 [] ? copy_mount_string+0x40/0x40 [] ? memset+0x31/0x40 [] ? copy_mount_options+0x1ee/0x320 [] SyS_mount+0xb2/0x120 [] ? copy_mnt_ns+0x970/0x970 [] do_syscall_64+0x1c4/0x4e0 [] entry_SYSCALL64_slow_path+0x25/0x25 Code: 83 e8 63 1b fc ff 48 85 c0 48 89 c3 74 4c e8 56 35 d1 ff 48 8d bb c8 00 00 00 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 <80> 3c 02 00 75 36 4c 8b a3 c8 00 00 00 48 b8 00 00 00 00 00 fc RIP [] bd_mount+0x52/0xa0 RSP ---[ end trace 13690ad962168b98 ]--- mount_pseudo() returns ERR_PTR(), not NULL, on error. Fixes: 3684aa7099e0 ("block-dev: enable writeback cgroup support") Cc: Shaohua Li Cc: Tejun Heo Cc: Jens Axboe Cc: stable@vger.kernel.org Signed-off-by: Vegard Nossum Signed-off-by: Jens Axboe --- fs/block_dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/block_dev.c b/fs/block_dev.c index c3cdde87cc8c..e17bdbdfe9b1 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -646,7 +646,7 @@ static struct dentry *bd_mount(struct file_system_type *fs_type, { struct dentry *dent; dent = mount_pseudo(fs_type, "bdev:", &bdev_sops, NULL, BDEVFS_MAGIC); - if (dent) + if (!IS_ERR(dent)) dent->d_sb->s_iflags |= SB_I_CGROUPWB; return dent; } From 209c721ce27022656a9d792b89572c4fdd7d31a7 Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Sun, 21 Aug 2016 15:37:16 +0000 Subject: [PATCH 245/531] ASoC: max98371: Add terminate entry for i2c_device_id tables Make sure i2c_device_id tables are NULL terminated. Signed-off-by: Wei Yongjun Signed-off-by: Mark Brown --- sound/soc/codecs/max98371.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/soc/codecs/max98371.c b/sound/soc/codecs/max98371.c index cf0a39bb631a..02352ed8961c 100644 --- a/sound/soc/codecs/max98371.c +++ b/sound/soc/codecs/max98371.c @@ -412,6 +412,7 @@ static int max98371_i2c_remove(struct i2c_client *client) static const struct i2c_device_id max98371_i2c_id[] = { { "max98371", 0 }, + { } }; MODULE_DEVICE_TABLE(i2c, max98371_i2c_id); From 6a33fa2b87513fee44cb8f0cd17b1acd6316bc6b Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 19 Aug 2016 18:07:14 +0100 Subject: [PATCH 246/531] irqchip/mips-gic: Cleanup chip and handler setup gic_shared_irq_domain_map() is called from gic_irq_domain_alloc() where the wrong chip has been set, and is then overwritten. Tidy this up by setting the correct chip the first time, and setting the handle_level_irq handler from gic_irq_domain_alloc() too. gic_shared_irq_domain_map() is also called from gic_irq_domain_map(), which now calls irq_set_chip_and_handler() to retain its previous behaviour. This patch prepares for a follow-on which will call gic_shared_irq_domain_map() from a callback where the lock on the struct irq_desc is held, which without this change would cause the call to irq_set_chip_and_handler() to lead to a deadlock. Fixes: c98c1822ee13 ("irqchip/mips-gic: Add device hierarchy domain") Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Cc: Jason Cooper Cc: Marc Zyngier Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/20160819170715.27820-1-paul.burton@imgtec.com Signed-off-by: Thomas Gleixner --- drivers/irqchip/irq-mips-gic.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index c5f33c3bd228..2e0f49992a98 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -713,9 +713,6 @@ static int gic_shared_irq_domain_map(struct irq_domain *d, unsigned int virq, unsigned long flags; int i; - irq_set_chip_and_handler(virq, &gic_level_irq_controller, - handle_level_irq); - spin_lock_irqsave(&gic_lock, flags); gic_map_to_pin(intr, gic_cpu_pin); gic_map_to_vpe(intr, mips_cm_vp_id(vpe)); @@ -732,6 +729,10 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int virq, { if (GIC_HWIRQ_TO_LOCAL(hw) < GIC_NUM_LOCAL_INTRS) return gic_local_irq_domain_map(d, virq, hw); + + irq_set_chip_and_handler(virq, &gic_level_irq_controller, + handle_level_irq); + return gic_shared_irq_domain_map(d, virq, hw, 0); } @@ -771,11 +772,13 @@ static int gic_irq_domain_alloc(struct irq_domain *d, unsigned int virq, hwirq = GIC_SHARED_TO_HWIRQ(base_hwirq + i); ret = irq_domain_set_hwirq_and_chip(d, virq + i, hwirq, - &gic_edge_irq_controller, + &gic_level_irq_controller, NULL); if (ret) goto error; + irq_set_handler(virq + i, handle_level_irq); + ret = gic_shared_irq_domain_map(d, virq + i, hwirq, cpu); if (ret) goto error; From 2564970a381651865364974ea414384b569cb9c0 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 19 Aug 2016 18:07:15 +0100 Subject: [PATCH 247/531] irqchip/mips-gic: Implement activate op for device domain If an IRQ is setup using __setup_irq(), which is used by the request_irq() family of functions, and we are using an SMP kernel then the affinity of the IRQ will be set via setup_affinity() immediately after the IRQ is enabled. This call to gic_set_affinity() will lead to the interrupt being mapped to a VPE. However there are other ways to use IRQs which don't cause affinity to be set, for example if it is used to chain to another IRQ controller with irq_set_chained_handler_and_data(). The irq_set_chained_handler_and_data() code path will enable the IRQ, but will not trigger a call to gic_set_affinity() and in this case nothing will map the interrupt to a VPE, meaning that the interrupt is never received. Fix this by implementing the activate operation for the GIC device IRQ domain, using gic_shared_irq_domain_map() to map the interrupt to the correct pin of cpu 0. Fixes: c98c1822ee13 ("irqchip/mips-gic: Add device hierarchy domain") Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Cc: Jason Cooper Cc: Marc Zyngier Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/20160819170715.27820-2-paul.burton@imgtec.com Signed-off-by: Thomas Gleixner --- drivers/irqchip/irq-mips-gic.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index 2e0f49992a98..83f498393a7f 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -893,10 +893,17 @@ void gic_dev_domain_free(struct irq_domain *d, unsigned int virq, return; } +static void gic_dev_domain_activate(struct irq_domain *domain, + struct irq_data *d) +{ + gic_shared_irq_domain_map(domain, d->irq, d->hwirq, 0); +} + static struct irq_domain_ops gic_dev_domain_ops = { .xlate = gic_dev_domain_xlate, .alloc = gic_dev_domain_alloc, .free = gic_dev_domain_free, + .activate = gic_dev_domain_activate, }; static int gic_ipi_domain_xlate(struct irq_domain *d, struct device_node *ctrlr, From e6a00f6684c9f348cd782922b4b277c68ab90b63 Mon Sep 17 00:00:00 2001 From: Yuval Shaia Date: Wed, 27 Jul 2016 01:24:52 -0700 Subject: [PATCH 248/531] IB/mlx4: Make function use_tunnel_data return void No need to return int if function always returns 0 Signed-off-by: Yuval Shaia Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx4/cq.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c index d6fc8a6e8c33..15b628996633 100644 --- a/drivers/infiniband/hw/mlx4/cq.c +++ b/drivers/infiniband/hw/mlx4/cq.c @@ -576,8 +576,8 @@ static int mlx4_ib_ipoib_csum_ok(__be16 status, __be16 checksum) checksum == cpu_to_be16(0xffff); } -static int use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct ib_wc *wc, - unsigned tail, struct mlx4_cqe *cqe, int is_eth) +static void use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct ib_wc *wc, + unsigned tail, struct mlx4_cqe *cqe, int is_eth) { struct mlx4_ib_proxy_sqp_hdr *hdr; @@ -600,8 +600,6 @@ static int use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct wc->slid = be16_to_cpu(hdr->tun.slid_mac_47_32); wc->sl = (u8) (be16_to_cpu(hdr->tun.sl_vid) >> 12); } - - return 0; } static void mlx4_ib_qp_sw_comp(struct mlx4_ib_qp *qp, int num_entries, @@ -852,9 +850,11 @@ static int mlx4_ib_poll_one(struct mlx4_ib_cq *cq, if (mlx4_is_mfunc(to_mdev(cq->ibcq.device)->dev)) { if ((*cur_qp)->mlx4_ib_qp_type & (MLX4_IB_QPT_PROXY_SMI_OWNER | - MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_GSI)) - return use_tunnel_data(*cur_qp, cq, wc, tail, - cqe, is_eth); + MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_GSI)) { + use_tunnel_data(*cur_qp, cq, wc, tail, cqe, + is_eth); + return 0; + } } wc->slid = be16_to_cpu(cqe->rlid); From 5412352fcd8fba7f278ae8c9ba36296716f17ae8 Mon Sep 17 00:00:00 2001 From: Yuval Shaia Date: Wed, 27 Jul 2016 01:24:53 -0700 Subject: [PATCH 249/531] IB/mlx4: Return EAGAIN for any error in mlx4_ib_poll_one Error code EAGAIN should be used when errors are temporary and next call might succeeds. When error code other than EAGAIN is returned, the caller (mlx4_ib_poll) will assume all CQE in the same bunch are error too and will drop them all. Signed-off-by: Yuval Shaia Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx4/cq.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c index 15b628996633..006db6436e3b 100644 --- a/drivers/infiniband/hw/mlx4/cq.c +++ b/drivers/infiniband/hw/mlx4/cq.c @@ -690,7 +690,7 @@ static int mlx4_ib_poll_one(struct mlx4_ib_cq *cq, if (unlikely((cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) == MLX4_OPCODE_NOP && is_send)) { pr_warn("Completion for NOP opcode detected!\n"); - return -EINVAL; + return -EAGAIN; } /* Resize CQ in progress */ @@ -721,7 +721,7 @@ static int mlx4_ib_poll_one(struct mlx4_ib_cq *cq, if (unlikely(!mqp)) { pr_warn("CQ %06x with entry for unknown QPN %06x\n", cq->mcq.cqn, be32_to_cpu(cqe->vlan_my_qpn) & MLX4_CQE_QPN_MASK); - return -EINVAL; + return -EAGAIN; } *cur_qp = to_mibqp(mqp); @@ -739,7 +739,7 @@ static int mlx4_ib_poll_one(struct mlx4_ib_cq *cq, if (unlikely(!msrq)) { pr_warn("CQ %06x with entry for unknown SRQN %06x\n", cq->mcq.cqn, srq_num); - return -EINVAL; + return -EAGAIN; } } From 8303f683b161467b6595c153c8751b80f9df3508 Mon Sep 17 00:00:00 2001 From: Tadeusz Struk Date: Wed, 3 Aug 2016 20:19:32 -0400 Subject: [PATCH 250/531] IB/hfi1: Allocate cpu mask on the heap to silence warning If CONFIG_FRAME_WARN is small (1K) and CONFIG_NR_CPUS big then a frame size warning is triggered during build. Allocate the cpu mask dynamically to silence the warning. Reviewed-by: Sebastian Sanchez Signed-off-by: Tadeusz Struk Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/affinity.c | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c index 79575ee873f2..9bbb21459166 100644 --- a/drivers/infiniband/hw/hfi1/affinity.c +++ b/drivers/infiniband/hw/hfi1/affinity.c @@ -682,7 +682,7 @@ int hfi1_set_sdma_affinity(struct hfi1_devdata *dd, const char *buf, size_t count) { struct hfi1_affinity_node *entry; - struct cpumask mask; + cpumask_var_t mask; int ret, i; spin_lock(&node_affinity.lock); @@ -692,19 +692,24 @@ int hfi1_set_sdma_affinity(struct hfi1_devdata *dd, const char *buf, if (!entry) return -EINVAL; - ret = cpulist_parse(buf, &mask); - if (ret) - return ret; + ret = zalloc_cpumask_var(&mask, GFP_KERNEL); + if (!ret) + return -ENOMEM; - if (!cpumask_subset(&mask, cpu_online_mask) || cpumask_empty(&mask)) { + ret = cpulist_parse(buf, mask); + if (ret) + goto out; + + if (!cpumask_subset(mask, cpu_online_mask) || cpumask_empty(mask)) { dd_dev_warn(dd, "Invalid CPU mask\n"); - return -EINVAL; + ret = -EINVAL; + goto out; } mutex_lock(&sdma_affinity_mutex); /* reset the SDMA interrupt affinity details */ init_cpu_mask_set(&entry->def_intr); - cpumask_copy(&entry->def_intr.mask, &mask); + cpumask_copy(&entry->def_intr.mask, mask); /* * Reassign the affinity for each SDMA interrupt. */ @@ -720,8 +725,9 @@ int hfi1_set_sdma_affinity(struct hfi1_devdata *dd, const char *buf, if (ret) break; } - mutex_unlock(&sdma_affinity_mutex); +out: + free_cpumask_var(mask); return ret ? ret : strnlen(buf, PAGE_SIZE); } From 23d70503ee187819a3775c7ac73f17c5bfe3fad0 Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Fri, 5 Aug 2016 13:46:49 +0000 Subject: [PATCH 251/531] IB/core: Fix possible memory leak in cma_resolve_iboe_route() 'work' and 'route->path_rec' are malloced in cma_resolve_iboe_route() and should be freed before leaving from the error handling cases, otherwise it will cause memory leak. Fixes: 200298326b27 ('IB/core: Validate route when we init ah') Signed-off-by: Wei Yongjun Reviewed-by: Haggai Eran Signed-off-by: Doug Ledford --- drivers/infiniband/core/cma.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index e6dfa1bd3def..5f65a78b27c9 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -2462,18 +2462,24 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv) if (addr->dev_addr.bound_dev_if) { ndev = dev_get_by_index(&init_net, addr->dev_addr.bound_dev_if); - if (!ndev) - return -ENODEV; + if (!ndev) { + ret = -ENODEV; + goto err2; + } if (ndev->flags & IFF_LOOPBACK) { dev_put(ndev); - if (!id_priv->id.device->get_netdev) - return -EOPNOTSUPP; + if (!id_priv->id.device->get_netdev) { + ret = -EOPNOTSUPP; + goto err2; + } ndev = id_priv->id.device->get_netdev(id_priv->id.device, id_priv->id.port_num); - if (!ndev) - return -ENODEV; + if (!ndev) { + ret = -ENODEV; + goto err2; + } } route->path_rec->net = &init_net; From 1d5840c971455ad4ecece3f72012961cac8d0f00 Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Sun, 7 Aug 2016 12:20:38 +0000 Subject: [PATCH 252/531] IB/isert: fix error return code in isert_alloc_login_buf() Fix to return error code -ENOMEM from the alloc error handling case instead of 0, as done elsewhere in this function. Signed-off-by: Wei Yongjun Acked-by: Sagi Grimberg Reviewed-by: Leon Romanovsky Signed-off-by: Doug Ledford --- drivers/infiniband/ulp/isert/ib_isert.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index ba6be060a476..7914c14478cd 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -448,7 +448,7 @@ isert_alloc_login_buf(struct isert_conn *isert_conn, isert_conn->login_rsp_buf = kzalloc(ISER_RX_PAYLOAD_SIZE, GFP_KERNEL); if (!isert_conn->login_rsp_buf) { - isert_err("Unable to allocate isert_conn->login_rspbuf\n"); + ret = -ENOMEM; goto out_unmap_login_req_buf; } From abb658ef0529488cfa75e79a2a9f894cb95eaec3 Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Mon, 8 Aug 2016 09:49:47 +0000 Subject: [PATCH 253/531] IB/hfi1: Remove duplicated include from affinity.c Remove duplicated include. Signed-off-by: Wei Yongjun Reviewed-by: Leon Romanovsky Reviewed-by: Ira Weiny Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/affinity.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c index 9bbb21459166..0566393e5aba 100644 --- a/drivers/infiniband/hw/hfi1/affinity.c +++ b/drivers/infiniband/hw/hfi1/affinity.c @@ -47,7 +47,6 @@ #include #include #include -#include #include "hfi.h" #include "affinity.h" From c62fb260a86dde3df5b2905432caa0e9f6898434 Mon Sep 17 00:00:00 2001 From: Mike Marciniszyn Date: Fri, 12 Aug 2016 11:17:37 -0400 Subject: [PATCH 254/531] IB/hfi1,IB/qib: Fix qp_stats sleep with rcu read lock held The qp init function does a kzalloc() while holding the RCU lock that encounters the following warning with a debug kernel when a cat of the qp_stats is done: [ 231.723948] rcu_scheduler_active = 1, debug_locks = 0 [ 231.731939] 3 locks held by cat/11355: [ 231.736492] #0: (debugfs_srcu){......}, at: [] debugfs_use_file_start+0x5/0x90 [ 231.746955] #1: (&p->lock){+.+.+.}, at: [] seq_read+0x4c/0x3c0 [ 231.755873] #2: (rcu_read_lock){......}, at: [] _qp_stats_seq_start+0x5/0xd0 [hfi1] [ 231.766862] The init functions do an implicit next which requires the rcu read lock before the kzalloc(). Fix for both drivers is to change the scope of the init function to only do the allocation and the initialization of the just allocated iter. The implict next is moved back into the respective start functions to fix the issue. Signed-off-by: Ira Weiny Signed-off-by: Mike Marciniszyn CC: # 4.6.x- Reviewed-by: Leon Romanovsky Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/debugfs.c | 14 +++++++++----- drivers/infiniband/hw/hfi1/qp.c | 4 ---- drivers/infiniband/hw/qib/qib_debugfs.c | 12 +++++++++--- drivers/infiniband/hw/qib/qib_qp.c | 4 ---- 4 files changed, 18 insertions(+), 16 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/debugfs.c b/drivers/infiniband/hw/hfi1/debugfs.c index dbab9d9cc288..a49cc88f08a2 100644 --- a/drivers/infiniband/hw/hfi1/debugfs.c +++ b/drivers/infiniband/hw/hfi1/debugfs.c @@ -223,28 +223,32 @@ DEBUGFS_SEQ_FILE_OPEN(ctx_stats) DEBUGFS_FILE_OPS(ctx_stats); static void *_qp_stats_seq_start(struct seq_file *s, loff_t *pos) -__acquires(RCU) + __acquires(RCU) { struct qp_iter *iter; loff_t n = *pos; - rcu_read_lock(); iter = qp_iter_init(s->private); + + /* stop calls rcu_read_unlock */ + rcu_read_lock(); + if (!iter) return NULL; - while (n--) { + do { if (qp_iter_next(iter)) { kfree(iter); return NULL; } - } + } while (n--); return iter; } static void *_qp_stats_seq_next(struct seq_file *s, void *iter_ptr, loff_t *pos) + __must_hold(RCU) { struct qp_iter *iter = iter_ptr; @@ -259,7 +263,7 @@ static void *_qp_stats_seq_next(struct seq_file *s, void *iter_ptr, } static void _qp_stats_seq_stop(struct seq_file *s, void *iter_ptr) -__releases(RCU) + __releases(RCU) { rcu_read_unlock(); } diff --git a/drivers/infiniband/hw/hfi1/qp.c b/drivers/infiniband/hw/hfi1/qp.c index a5aa3517e7d5..4e4d8317c281 100644 --- a/drivers/infiniband/hw/hfi1/qp.c +++ b/drivers/infiniband/hw/hfi1/qp.c @@ -656,10 +656,6 @@ struct qp_iter *qp_iter_init(struct hfi1_ibdev *dev) iter->dev = dev; iter->specials = dev->rdi.ibdev.phys_port_cnt * 2; - if (qp_iter_next(iter)) { - kfree(iter); - return NULL; - } return iter; } diff --git a/drivers/infiniband/hw/qib/qib_debugfs.c b/drivers/infiniband/hw/qib/qib_debugfs.c index 5e75b43c596b..5bad8e3b40bb 100644 --- a/drivers/infiniband/hw/qib/qib_debugfs.c +++ b/drivers/infiniband/hw/qib/qib_debugfs.c @@ -189,27 +189,32 @@ static int _ctx_stats_seq_show(struct seq_file *s, void *v) DEBUGFS_FILE(ctx_stats) static void *_qp_stats_seq_start(struct seq_file *s, loff_t *pos) + __acquires(RCU) { struct qib_qp_iter *iter; loff_t n = *pos; - rcu_read_lock(); iter = qib_qp_iter_init(s->private); + + /* stop calls rcu_read_unlock */ + rcu_read_lock(); + if (!iter) return NULL; - while (n--) { + do { if (qib_qp_iter_next(iter)) { kfree(iter); return NULL; } - } + } while (n--); return iter; } static void *_qp_stats_seq_next(struct seq_file *s, void *iter_ptr, loff_t *pos) + __must_hold(RCU) { struct qib_qp_iter *iter = iter_ptr; @@ -224,6 +229,7 @@ static void *_qp_stats_seq_next(struct seq_file *s, void *iter_ptr, } static void _qp_stats_seq_stop(struct seq_file *s, void *iter_ptr) + __releases(RCU) { rcu_read_unlock(); } diff --git a/drivers/infiniband/hw/qib/qib_qp.c b/drivers/infiniband/hw/qib/qib_qp.c index 9cc0aae1d781..f9b8cd2354d1 100644 --- a/drivers/infiniband/hw/qib/qib_qp.c +++ b/drivers/infiniband/hw/qib/qib_qp.c @@ -573,10 +573,6 @@ struct qib_qp_iter *qib_qp_iter_init(struct qib_ibdev *dev) return NULL; iter->dev = dev; - if (qib_qp_iter_next(iter)) { - kfree(iter); - return NULL; - } return iter; } From 140690eae7626a820ea135f33ff9fe11c1bcee6d Mon Sep 17 00:00:00 2001 From: Easwar Hariharan Date: Tue, 9 Aug 2016 11:17:18 -0400 Subject: [PATCH 255/531] IB/hfi1: Fetch monitor values on-demand for CableInfo query The monitor values from bytes 22 through 81 of the QSFP memory space (SFF 8636) are dynamic and serving them out of the QSFP memory cache maintained by the driver provides stale data to the CableInfo SMA query. This patch refreshes the dynamic values from the QSFP memory on request and overwrites the stale data from the cache for the overlap between the requested range and the monitor range. Reviewed-by: Jubin John Reviewed-by: Ira Weiny Signed-off-by: Easwar Hariharan Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/qsfp.c | 32 +++++++++++++++++++++++++++++-- drivers/infiniband/hw/hfi1/qsfp.h | 3 +++ 2 files changed, 33 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/qsfp.c b/drivers/infiniband/hw/hfi1/qsfp.c index a207717ade2a..4e95ad810847 100644 --- a/drivers/infiniband/hw/hfi1/qsfp.c +++ b/drivers/infiniband/hw/hfi1/qsfp.c @@ -706,8 +706,8 @@ int get_cable_info(struct hfi1_devdata *dd, u32 port_num, u32 addr, u32 len, u8 *data) { struct hfi1_pportdata *ppd; - u32 excess_len = 0; - int ret = 0; + u32 excess_len = len; + int ret = 0, offset = 0; if (port_num > dd->num_pports || port_num < 1) { dd_dev_info(dd, "%s: Invalid port number %d\n", @@ -740,6 +740,34 @@ int get_cable_info(struct hfi1_devdata *dd, u32 port_num, u32 addr, u32 len, } memcpy(data, &ppd->qsfp_info.cache[addr], len); + + if (addr <= QSFP_MONITOR_VAL_END && + (addr + len) >= QSFP_MONITOR_VAL_START) { + /* Overlap with the dynamic channel monitor range */ + if (addr < QSFP_MONITOR_VAL_START) { + if (addr + len <= QSFP_MONITOR_VAL_END) + len = addr + len - QSFP_MONITOR_VAL_START; + else + len = QSFP_MONITOR_RANGE; + offset = QSFP_MONITOR_VAL_START - addr; + addr = QSFP_MONITOR_VAL_START; + } else if (addr == QSFP_MONITOR_VAL_START) { + offset = 0; + if (addr + len > QSFP_MONITOR_VAL_END) + len = QSFP_MONITOR_RANGE; + } else { + offset = 0; + if (addr + len > QSFP_MONITOR_VAL_END) + len = QSFP_MONITOR_VAL_END - addr + 1; + } + /* Refresh the values of the dynamic monitors from the cable */ + ret = one_qsfp_read(ppd, dd->hfi1_id, addr, data + offset, len); + if (ret != len) { + ret = -EAGAIN; + goto set_zeroes; + } + } + return 0; set_zeroes: diff --git a/drivers/infiniband/hw/hfi1/qsfp.h b/drivers/infiniband/hw/hfi1/qsfp.h index 69275ebd9597..36cf52359848 100644 --- a/drivers/infiniband/hw/hfi1/qsfp.h +++ b/drivers/infiniband/hw/hfi1/qsfp.h @@ -74,6 +74,9 @@ /* Defined fields that Intel requires of qualified cables */ /* Byte 0 is Identifier, not checked */ /* Byte 1 is reserved "status MSB" */ +#define QSFP_MONITOR_VAL_START 22 +#define QSFP_MONITOR_VAL_END 81 +#define QSFP_MONITOR_RANGE (QSFP_MONITOR_VAL_END - QSFP_MONITOR_VAL_START + 1) #define QSFP_TX_CTRL_BYTE_OFFS 86 #define QSFP_PWR_CTRL_BYTE_OFFS 93 #define QSFP_CDR_CTRL_BYTE_OFFS 98 From c867caaf8ecd5498d399558d0f11825f175c6cdd Mon Sep 17 00:00:00 2001 From: Mike Marciniszyn Date: Tue, 9 Aug 2016 11:19:55 -0400 Subject: [PATCH 256/531] IB/hfi1: Pass packet ptr to set_armed_active The "packet" parameter was being passed on the stack, change it to a pointer. Reviewed-by: Don Hiatt Signed-off-by: Mike Marciniszyn Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/driver.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/driver.c b/drivers/infiniband/hw/hfi1/driver.c index 8246dc7d0573..c4156870a8bb 100644 --- a/drivers/infiniband/hw/hfi1/driver.c +++ b/drivers/infiniband/hw/hfi1/driver.c @@ -888,14 +888,14 @@ void set_all_slowpath(struct hfi1_devdata *dd) } static inline int set_armed_to_active(struct hfi1_ctxtdata *rcd, - struct hfi1_packet packet, + struct hfi1_packet *packet, struct hfi1_devdata *dd) { struct work_struct *lsaw = &rcd->ppd->linkstate_active_work; - struct hfi1_message_header *hdr = hfi1_get_msgheader(packet.rcd->dd, - packet.rhf_addr); + struct hfi1_message_header *hdr = hfi1_get_msgheader(packet->rcd->dd, + packet->rhf_addr); - if (hdr2sc(hdr, packet.rhf) != 0xf) { + if (hdr2sc(hdr, packet->rhf) != 0xf) { int hwstate = read_logical_state(dd); if (hwstate != LSTATE_ACTIVE) { @@ -979,7 +979,7 @@ int handle_receive_interrupt(struct hfi1_ctxtdata *rcd, int thread) /* Auto activate link on non-SC15 packet receive */ if (unlikely(rcd->ppd->host_link_state == HLS_UP_ARMED) && - set_armed_to_active(rcd, packet, dd)) + set_armed_to_active(rcd, &packet, dd)) goto bail; last = process_rcv_packet(&packet, thread); } From 69b9f4a4233b6f9ea168c25123b9eb629739d8e5 Mon Sep 17 00:00:00 2001 From: Mike Marciniszyn Date: Tue, 9 Aug 2016 11:19:56 -0400 Subject: [PATCH 257/531] IB/hfi1: Validate header in set_armed_active Validate the etype to insure that the header is correct. Reviewed-by: Don Hiatt Signed-off-by: Mike Marciniszyn Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/driver.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/hfi1/driver.c b/drivers/infiniband/hw/hfi1/driver.c index c4156870a8bb..303f10555729 100644 --- a/drivers/infiniband/hw/hfi1/driver.c +++ b/drivers/infiniband/hw/hfi1/driver.c @@ -894,8 +894,9 @@ static inline int set_armed_to_active(struct hfi1_ctxtdata *rcd, struct work_struct *lsaw = &rcd->ppd->linkstate_active_work; struct hfi1_message_header *hdr = hfi1_get_msgheader(packet->rcd->dd, packet->rhf_addr); + u8 etype = rhf_rcv_type(packet->rhf); - if (hdr2sc(hdr, packet->rhf) != 0xf) { + if (etype == RHF_RCV_TYPE_IB && hdr2sc(hdr, packet->rhf) != 0xf) { int hwstate = read_logical_state(dd); if (hwstate != LSTATE_ACTIVE) { From 476d95bd02240894806ebe64f1c4dcf6dbba87f4 Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Wed, 10 Aug 2016 03:14:04 +0000 Subject: [PATCH 258/531] IB/hfi1: Using kfree_rcu() to simplify the code The callback function of call_rcu() just calls a kfree(), so we can use kfree_rcu() instead of call_rcu() + callback function. Signed-off-by: Wei Yongjun Tested-by: Mike Marciniszyn Acked-by: Mike Marciniszyn Tested-by: Mike Marciniszyn Acked-by: Mike Marciniszyn Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/hfi.h | 1 - drivers/infiniband/hw/hfi1/init.c | 2 +- drivers/infiniband/hw/hfi1/mad.c | 9 +-------- 3 files changed, 2 insertions(+), 10 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h index 1000e0fd96d9..f41414ef0cbc 100644 --- a/drivers/infiniband/hw/hfi1/hfi.h +++ b/drivers/infiniband/hw/hfi1/hfi.h @@ -1656,7 +1656,6 @@ struct cc_state *get_cc_state_protected(struct hfi1_pportdata *ppd) struct hfi1_devdata *hfi1_init_dd(struct pci_dev *, const struct pci_device_id *); void hfi1_free_devdata(struct hfi1_devdata *); -void cc_state_reclaim(struct rcu_head *rcu); struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev, size_t extra); /* LED beaconing functions */ diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c index a358d23ecd54..b7935451093c 100644 --- a/drivers/infiniband/hw/hfi1/init.c +++ b/drivers/infiniband/hw/hfi1/init.c @@ -1333,7 +1333,7 @@ static void cleanup_device_data(struct hfi1_devdata *dd) spin_unlock(&ppd->cc_state_lock); if (cc_state) - call_rcu(&cc_state->rcu, cc_state_reclaim); + kfree_rcu(cc_state, rcu); } free_credit_return(dd); diff --git a/drivers/infiniband/hw/hfi1/mad.c b/drivers/infiniband/hw/hfi1/mad.c index 1263abe01999..95c43e1e0ce5 100644 --- a/drivers/infiniband/hw/hfi1/mad.c +++ b/drivers/infiniband/hw/hfi1/mad.c @@ -3398,7 +3398,7 @@ static void apply_cc_state(struct hfi1_pportdata *ppd) spin_unlock(&ppd->cc_state_lock); - call_rcu(&old_cc_state->rcu, cc_state_reclaim); + kfree_rcu(old_cc_state, rcu); } static int __subn_set_opa_cong_setting(struct opa_smp *smp, u32 am, u8 *data, @@ -3553,13 +3553,6 @@ static int __subn_get_opa_cc_table(struct opa_smp *smp, u32 am, u8 *data, return reply((struct ib_mad_hdr *)smp); } -void cc_state_reclaim(struct rcu_head *rcu) -{ - struct cc_state *cc_state = container_of(rcu, struct cc_state, rcu); - - kfree(cc_state); -} - static int __subn_set_opa_cc_table(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, u32 *resp_len) From 57bb562ad4651453c9f20d506a65e46e4d11042f Mon Sep 17 00:00:00 2001 From: Christophe Jaillet Date: Wed, 10 Aug 2016 07:34:27 +0200 Subject: [PATCH 259/531] IB/hfi1: Add missing error code assignment before test It is likely that checking the result of 'setup_ctxt' is expected here. Signed-off-by: Christophe JAILLET Acked-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/file_ops.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index 1ecbec192358..ed76be39b20b 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -222,7 +222,7 @@ static long hfi1_file_ioctl(struct file *fp, unsigned int cmd, ret = assign_ctxt(fp, &uinfo); if (ret < 0) return ret; - setup_ctxt(fp); + ret = setup_ctxt(fp); if (ret) return ret; ret = user_init(fp); From 86cd747c6dd6cdbc825e36ad5f0029f3c5a37776 Mon Sep 17 00:00:00 2001 From: Christophe Jaillet Date: Wed, 10 Aug 2016 17:45:01 +0200 Subject: [PATCH 260/531] IB/usnic: Fix error return code If 'pci_register_driver' fails, we return 'err' which is known to be 0. Return the error instead. Signed-off-by: Christophe JAILLET Signed-off-by: Doug Ledford --- drivers/infiniband/hw/usnic/usnic_ib_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/usnic/usnic_ib_main.c b/drivers/infiniband/hw/usnic/usnic_ib_main.c index c229b9f4a52d..0a89a955550b 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_main.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_main.c @@ -664,7 +664,8 @@ static int __init usnic_ib_init(void) return err; } - if (pci_register_driver(&usnic_ib_pci_driver)) { + err = pci_register_driver(&usnic_ib_pci_driver); + if (err) { usnic_err("Unable to register with PCI\n"); goto out_umem_fini; } From 701b4bf6e3eeff1a856d6889e1ebb35edd6c019a Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 16 Aug 2016 12:29:46 +0300 Subject: [PATCH 261/531] MAINTAINERS: Fix Soft RoCE location The Soft RoCE (rxe) is located in drivers/inifiniband/sw and not in drivers/infiniband/hw/. This patch fixes it. Fixes: 8700e3e7c485 ("Soft RoCE driver") Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 0bbe4b105c34..fc2613d45504 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7661,7 +7661,7 @@ L: linux-rdma@vger.kernel.org S: Supported W: https://github.com/SoftRoCE/rxe-dev/wiki/rxe-dev:-Home Q: http://patchwork.kernel.org/project/linux-rdma/list/ -F: drivers/infiniband/hw/rxe/ +F: drivers/infiniband/sw/rxe/ F: include/uapi/rdma/rdma_user_rxe.h MEMBARRIER SUPPORT From f29a08dc145e05de6a57f0aeaba6020464f80e15 Mon Sep 17 00:00:00 2001 From: Easwar Hariharan Date: Tue, 16 Aug 2016 13:25:34 -0700 Subject: [PATCH 262/531] IB/hfi1: Return invalid field for non-QSFP CableInfo queries The driver does not check if the CableInfo query is supported for the port type. Return early if CableInfo is not supported for the port type, making compliance with the specification explicit and preventing lower level code from potentially doing the wrong thing if the query is not supported for the hardware implementation. Reviewed-by: Ira Weiny Signed-off-by: Easwar Hariharan Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/mad.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/infiniband/hw/hfi1/mad.c b/drivers/infiniband/hw/hfi1/mad.c index 95c43e1e0ce5..39e42c373a01 100644 --- a/drivers/infiniband/hw/hfi1/mad.c +++ b/drivers/infiniband/hw/hfi1/mad.c @@ -1819,6 +1819,11 @@ static int __subn_get_opa_cable_info(struct opa_smp *smp, u32 am, u8 *data, u32 len = OPA_AM_CI_LEN(am) + 1; int ret; + if (dd->pport->port_type != PORT_TYPE_QSFP) { + smp->status |= IB_SMP_INVALID_FIELD; + return reply((struct ib_mad_hdr *)smp); + } + #define __CI_PAGE_SIZE BIT(7) /* 128 bytes */ #define __CI_PAGE_MASK ~(__CI_PAGE_SIZE - 1) #define __CI_PAGE_NUM(a) ((a) & __CI_PAGE_MASK) From 08fe16f6192bccd5798e9b60461f7aa151b34cd4 Mon Sep 17 00:00:00 2001 From: Mitko Haralanov Date: Tue, 16 Aug 2016 13:26:12 -0700 Subject: [PATCH 263/531] IB/hfi1: Improve J_KEY generation Previously, J_KEY generation was based on the lower 16 bits of the user's UID. While this works, it was not good enough as a non-root user could collide with a root user given a sufficiently large UID. This patch attempt to improve the J_KEY generation by using the following algorithm: The 16 bit J_KEY space is partitioned into 3 separate spaces reserved for different user classes: * all users with administtor privileges (including 'root') will use J_KEYs in the range of 0 to 31, * all kernel protocols, which use KDETH packets will use J_KEYs in the range of 32 to 63, and * all other users will use J_KEYs in the range of 64 to 65535. The above separation is aimed at preventing different user levels from sending packets to each other and, additionally, separate kernel protocols from all other types of users. The later is meant to prevent the potential corruption of kernel memory by any other type of user. Reviewed-by: Ira Weiny Signed-off-by: Mitko Haralanov Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/hfi.h | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h index f41414ef0cbc..a021e660d482 100644 --- a/drivers/infiniband/hw/hfi1/hfi.h +++ b/drivers/infiniband/hw/hfi1/hfi.h @@ -1272,9 +1272,26 @@ static inline int hdr2sc(struct hfi1_message_header *hdr, u64 rhf) ((!!(rhf_dc_info(rhf))) << 4); } +#define HFI1_JKEY_WIDTH 16 +#define HFI1_JKEY_MASK (BIT(16) - 1) +#define HFI1_ADMIN_JKEY_RANGE 32 + +/* + * J_KEYs are split and allocated in the following groups: + * 0 - 31 - users with administrator privileges + * 32 - 63 - kernel protocols using KDETH packets + * 64 - 65535 - all other users using KDETH packets + */ static inline u16 generate_jkey(kuid_t uid) { - return from_kuid(current_user_ns(), uid) & 0xffff; + u16 jkey = from_kuid(current_user_ns(), uid) & HFI1_JKEY_MASK; + + if (capable(CAP_SYS_ADMIN)) + jkey &= HFI1_ADMIN_JKEY_RANGE - 1; + else if (jkey < 64) + jkey |= BIT(HFI1_JKEY_WIDTH - 1); + + return jkey; } /* From 56c8ca510de2884b2f741e5fd8d3df6161378de6 Mon Sep 17 00:00:00 2001 From: Mike Marciniszyn Date: Tue, 16 Aug 2016 13:26:29 -0700 Subject: [PATCH 264/531] IB/rdmvat: Fix double vfree() in rvt_create_qp() error path The unwind logic for creating a user QP has a double vfree of the non-shared receive queue when handling a "too many qps" failure. The code unwinds the mmmap info by decrementing a reference count which will call rvt_release_mmap_info() which in turn does the vfree() of the r_rq.wq. The unwind code then does the same free. Fix by guarding the vfree() with the same test that is done in close and only do the vfree() if qp->ip is NULL. Reviewed-by: Dennis Dalessandro Signed-off-by: Mike Marciniszyn Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- drivers/infiniband/sw/rdmavt/qp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index bdb540f25a88..870b4f212fbc 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -873,7 +873,8 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd, free_qpn(&rdi->qp_dev->qpn_table, qp->ibqp.qp_num); bail_rq_wq: - vfree(qp->r_rq.wq); + if (!qp->ip) + vfree(qp->r_rq.wq); bail_driver_priv: rdi->driver_f.qp_priv_free(rdi, qp); From e0cf75deab8155334c8228eb7f097b15127d0a49 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Tue, 16 Aug 2016 13:27:03 -0700 Subject: [PATCH 265/531] IB/hfi1: Fix mm_struct use after free Testing with CONFIG_SLUB_DEBUG_ON=y resulted in the kernel panic below. This is the result of the mm_struct sometimes being free'd prior to hfi1_file_close being called. This was due to the combination of 2 reasons: 1) hfi1_file_close is deferred in process exit and it therefore may not be called synchronously with process exit. 2) exit_mm is called prior to exit_files in do_exit. Normally this is ok however, our kernel bypass code requires us to have access to the mm_struct for house keeping both at "normal" close time as well as at process exit. Therefore, the fix is to simply keep a reference to the mm_struct until we are done with it. [ 3006.340150] general protection fault: 0000 [#1] SMP [ 3006.346469] Modules linked in: hfi1 rdmavt rpcrdma ib_isert iscsi_target_mod ib_iser libiscsi scsi_transport_iscsi ib_srpt target_core_mod ib_srp scsi_transport_srp ib_ipoib rdma_ucm ib_ucm ib_uverbs ib_umad rdma_cm ib_cm iw_cm dm_mirror dm_region_hash dm_log dm_mod snd_hda_code c_realtek iTCO_wdt snd_hda_codec_generic iTCO_vendor_support sb_edac edac_core x86_pkg_temp_thermal intel_powerclamp coretemp kvm irqbypass c rct10dif_pclmul crc32_pclmul ghash_clmulni_intel aesni_intel lrw snd_hda_intel gf128mul snd_hda_codec glue_helper snd_hda_core ablk_helper sn d_hwdep cryptd snd_seq snd_seq_device snd_pcm snd_timer snd soundcore pcspkr shpchp mei_me sg lpc_ich mei i2c_i801 mfd_core ioatdma ipmi_devi ntf wmi ipmi_si ipmi_msghandler acpi_cpufreq nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables ext4 jbd2 mbcache mlx4_en ib_core sr_mod s d_mod cdrom crc32c_intel mgag200 drm_kms_helper syscopyarea sysfillrect igb sysimgblt fb_sys_fops ptp mlx4_core ttm isci pps_core ahci drm li bsas libahci dca firewire_ohci i2c_algo_bit scsi_transport_sas firewire_core crc_itu_t i2c_core libata [last unloaded: mlx4_ib] [ 3006.461759] CPU: 16 PID: 11624 Comm: mpi_stress Not tainted 4.7.0-rc5+ #1 [ 3006.469915] Hardware name: Intel Corporation W2600CR ........../W2600CR, BIOS SE5C600.86B.01.08.0003.022620131521 02/26/2013 [ 3006.483027] task: ffff8804102f0040 ti: ffff8804102f8000 task.ti: ffff8804102f8000 [ 3006.491971] RIP: 0010:[] [] __lock_acquire+0xb3/0x19e0 [ 3006.501905] RSP: 0018:ffff8804102fb908 EFLAGS: 00010002 [ 3006.508447] RAX: 6b6b6b6b6b6b6b6b RBX: 0000000000000001 RCX: 0000000000000000 [ 3006.517012] RDX: 0000000000000001 RSI: 0000000000000000 RDI: ffff880410b56a40 [ 3006.525569] RBP: ffff8804102fb9b0 R08: 0000000000000001 R09: 0000000000000000 [ 3006.534119] R10: ffff8804102f0040 R11: 0000000000000000 R12: 0000000000000000 [ 3006.542664] R13: ffff880410b56a40 R14: 0000000000000000 R15: 0000000000000000 [ 3006.551203] FS: 00007ff478c08700(0000) GS:ffff88042e200000(0000) knlGS:0000000000000000 [ 3006.560814] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 3006.567806] CR2: 00007f667f5109e0 CR3: 0000000001c06000 CR4: 00000000000406e0 [ 3006.576352] Stack: [ 3006.579157] ffffffff8124b819 ffffffffffffffff 0000000000000000 ffff8804102fb940 [ 3006.588072] 0000000000000002 0000000000000000 ffff8804102f0040 0000000000000007 [ 3006.596971] 0000000000000006 ffff8803cad6f000 0000000000000000 ffff8804102f0040 [ 3006.605878] Call Trace: [ 3006.609220] [] ? uncharge_batch+0x109/0x250 [ 3006.616382] [] lock_acquire+0xd3/0x220 [ 3006.623056] [] ? hfi1_release_user_pages+0x7c/0xa0 [hfi1] [ 3006.631593] [] down_write+0x49/0x80 [ 3006.638022] [] ? hfi1_release_user_pages+0x7c/0xa0 [hfi1] [ 3006.646569] [] hfi1_release_user_pages+0x7c/0xa0 [hfi1] [ 3006.654898] [] cacheless_tid_rb_remove+0x106/0x330 [hfi1] [ 3006.663417] [] ? mark_held_locks+0x66/0x90 [ 3006.670498] [] ? _raw_spin_unlock_irqrestore+0x36/0x60 [ 3006.678741] [] tid_rb_remove+0xe/0x10 [hfi1] [ 3006.686010] [] hfi1_mmu_rb_unregister+0xc5/0x100 [hfi1] [ 3006.694387] [] hfi1_user_exp_rcv_free+0x39/0x120 [hfi1] [ 3006.702732] [] hfi1_file_close+0x17a/0x330 [hfi1] [ 3006.710489] [] __fput+0xfa/0x230 [ 3006.716595] [] ____fput+0xe/0x10 [ 3006.722696] [] task_work_run+0x86/0xc0 [ 3006.729379] [] do_exit+0x323/0xc40 [ 3006.735672] [] do_group_exit+0x4c/0xc0 [ 3006.742371] [] get_signal+0x345/0x940 [ 3006.748958] [] do_signal+0x37/0x700 [ 3006.755328] [] ? poll_select_set_timeout+0x5a/0x90 [ 3006.763146] [] ? __audit_syscall_exit+0x1db/0x260 [ 3006.770853] [] ? rcu_read_lock_sched_held+0x93/0xa0 [ 3006.778765] [] ? kfree+0x1e4/0x2a0 [ 3006.784986] [] ? exit_to_usermode_loop+0x33/0xac [ 3006.792551] [] exit_to_usermode_loop+0x5e/0xac [ 3006.799907] [] do_syscall_64+0x12a/0x190 [ 3006.806664] [] entry_SYSCALL64_slow_path+0x25/0x25 [ 3006.814396] Code: 24 08 44 89 44 24 10 89 4c 24 18 e8 a8 d8 ff ff 48 85 c0 8b 4c 24 18 44 8b 44 24 10 44 8b 4c 24 08 4c 8b 14 24 0f 84 30 08 00 00 ff 80 98 01 00 00 8b 3d 48 ad be 01 45 8b a2 90 0b 00 00 85 [ 3006.837158] RIP [] __lock_acquire+0xb3/0x19e0 [ 3006.844401] RSP [ 3006.851170] ---[ end trace b7b9f21cf06c27df ]--- [ 3006.927420] Kernel panic - not syncing: Fatal exception [ 3006.933954] Kernel Offset: disabled [ 3006.940961] ---[ end Kernel panic - not syncing: Fatal exception [ 3006.948249] ------------[ cut here ]------------ Fixes: 3faa3d9a308e ("IB/hfi1: Make use of mm consistent") Reviewed-by: Dean Luick Signed-off-by: Ira Weiny Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/file_ops.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index ed76be39b20b..7e03ccd2554d 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -183,6 +183,7 @@ static int hfi1_file_open(struct inode *inode, struct file *fp) if (fd) { fd->rec_cpu_num = -1; /* no cpu affinity by default */ fd->mm = current->mm; + atomic_inc(&fd->mm->mm_count); } fp->private_data = fd; @@ -779,6 +780,7 @@ static int hfi1_file_close(struct inode *inode, struct file *fp) mutex_unlock(&hfi1_mutex); hfi1_free_ctxtdata(dd, uctxt); done: + mmdrop(fdata->mm); kobject_put(&dd->kobj); kfree(fdata); return 0; From 7f446abf12d741f4e29f00c633cb5fa67c2eee71 Mon Sep 17 00:00:00 2001 From: Steve Wise Date: Fri, 19 Aug 2016 07:29:07 -0700 Subject: [PATCH 266/531] iw_cxgb4: limit IRD/ORD advertised to ULP by device max. The i40iw initiator sends an MPA-request with ird = 63, ord = 63. The cxgb4 responder sends a RST. Since the inbound ord=63 and it exceeds the max_ird/c4iw_max_read_depth (=32 default), chelsio decides to abort. Instead, cxgb4 should adjust the ord/ird down before presenting it to the ULP. Reported-by: Shiraz Saleem Signed-off-by: Steve Wise Signed-off-by: Doug Ledford --- drivers/infiniband/hw/cxgb4/cm.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index 3aca7f6171b4..a698efc69257 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -1827,8 +1827,12 @@ static int process_mpa_request(struct c4iw_ep *ep, struct sk_buff *skb) (ep->mpa_pkt + sizeof(*mpa)); ep->ird = ntohs(mpa_v2_params->ird) & MPA_V2_IRD_ORD_MASK; + ep->ird = min_t(u32, ep->ird, + cur_max_read_depth(ep->com.dev)); ep->ord = ntohs(mpa_v2_params->ord) & MPA_V2_IRD_ORD_MASK; + ep->ord = min_t(u32, ep->ord, + cur_max_read_depth(ep->com.dev)); PDBG("%s initiator ird %u ord %u\n", __func__, ep->ird, ep->ord); if (ntohs(mpa_v2_params->ird) & MPA_V2_PEER2PEER_MODEL) From 30b03b1528b60623986ee0b50ec0e5dab9094be8 Mon Sep 17 00:00:00 2001 From: Steve Wise Date: Fri, 19 Aug 2016 07:29:08 -0700 Subject: [PATCH 267/531] iw_cxgb4: use the MPA initiator's IRD if < our ORD The i40iw initiator sends an MPA-request with ird=16 and ord=16. The cxgb4 responder sends an MPA-reply with ord = 32 causing i40iw to terminate due to insufficient resources. The logic to reduce the ORD to <= peer's IRD was wrong. Reported-by: Shiraz Saleem Signed-off-by: Steve Wise Signed-off-by: Doug Ledford --- drivers/infiniband/hw/cxgb4/cm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index a698efc69257..b6a953aed7e8 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -3140,7 +3140,7 @@ int c4iw_accept_cr(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) if (ep->mpa_attr.version == 2 && ep->mpa_attr.enhanced_rdma_conn) { if (conn_param->ord > ep->ird) { if (RELAXED_IRD_NEGOTIATION) { - ep->ord = ep->ird; + conn_param->ord = ep->ird; } else { ep->ird = conn_param->ird; ep->ord = conn_param->ord; From 5cab4d84780573afbf5077ae9c3f919b4f305f20 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Mon, 22 Aug 2016 13:49:59 -0700 Subject: [PATCH 268/531] Input: silead - use devm_gpiod_get The silead code is using devm_foo for everything (and does not free any resources). Except that it is using gpiod_get instead of devm_gpiod_get (but is not freeing the gpio_desc), change this to use devm_gpiod_get so that the gpio will be properly released. Signed-off-by: Hans de Goede Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/silead.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/input/touchscreen/silead.c b/drivers/input/touchscreen/silead.c index 7379fe153cf9..b2744a64e933 100644 --- a/drivers/input/touchscreen/silead.c +++ b/drivers/input/touchscreen/silead.c @@ -464,7 +464,7 @@ static int silead_ts_probe(struct i2c_client *client, return -ENODEV; /* Power GPIO pin */ - data->gpio_power = gpiod_get_optional(dev, "power", GPIOD_OUT_LOW); + data->gpio_power = devm_gpiod_get_optional(dev, "power", GPIOD_OUT_LOW); if (IS_ERR(data->gpio_power)) { if (PTR_ERR(data->gpio_power) != -EPROBE_DEFER) dev_err(dev, "Shutdown GPIO request failed\n"); From fae16989be77b09bab86c79233e4b511ea769cea Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 22 Aug 2016 13:25:56 -0700 Subject: [PATCH 269/531] Input: tegra-kbc - fix inverted reset logic Commit fe6b0dfaba68 ("Input: tegra-kbc - use reset framework") accidentally converted _deassert to _assert, so there is no code to wake up this hardware. Fixes: fe6b0dfaba68 ("Input: tegra-kbc - use reset framework") Signed-off-by: Masahiro Yamada Acked-by: Thierry Reding Acked-by: Laxman Dewangan Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov --- drivers/input/keyboard/tegra-kbc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/input/keyboard/tegra-kbc.c b/drivers/input/keyboard/tegra-kbc.c index 7d61439be5f2..0c07e1023a46 100644 --- a/drivers/input/keyboard/tegra-kbc.c +++ b/drivers/input/keyboard/tegra-kbc.c @@ -376,7 +376,7 @@ static int tegra_kbc_start(struct tegra_kbc *kbc) /* Reset the KBC controller to clear all previous status.*/ reset_control_assert(kbc->rst); udelay(100); - reset_control_assert(kbc->rst); + reset_control_deassert(kbc->rst); udelay(100); tegra_kbc_config_pins(kbc); From 3e29d6bb6433ebfa4e187b1164b80baf720d58c3 Mon Sep 17 00:00:00 2001 From: Andrew Duggan Date: Mon, 22 Aug 2016 11:28:11 -0700 Subject: [PATCH 270/531] Input: synaptics-rmi4 - fix register descriptor subpacket map construction The map_offset variable is specific to the register and needs to be reset in the loop. Otherwise, subsequent register's subpacket maps will have their bits set at the wrong index. Signed-off-by: Andrew Duggan Tested-by: Nitin Chaudhary Reviewed-by: Benjamin Tissoires Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov --- drivers/input/rmi4/rmi_driver.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c index faa295ec4f31..c83bce89028b 100644 --- a/drivers/input/rmi4/rmi_driver.c +++ b/drivers/input/rmi4/rmi_driver.c @@ -553,7 +553,6 @@ int rmi_read_register_desc(struct rmi_device *d, u16 addr, goto free_struct_buff; reg = find_first_bit(rdesc->presense_map, RMI_REG_DESC_PRESENSE_BITS); - map_offset = 0; for (i = 0; i < rdesc->num_registers; i++) { struct rmi_register_desc_item *item = &rdesc->registers[i]; int reg_size = struct_buf[offset]; @@ -576,6 +575,8 @@ int rmi_read_register_desc(struct rmi_device *d, u16 addr, item->reg = reg; item->reg_size = reg_size; + map_offset = 0; + do { for (b = 0; b < 7; b++) { if (struct_buf[offset] & (0x1 << b)) From e3a888a4bff0bef0b256d55c58bc32c99fb44ece Mon Sep 17 00:00:00 2001 From: Petr Cvek Date: Fri, 19 Aug 2016 10:14:29 -0700 Subject: [PATCH 271/531] Input: ads7846 - remove redundant regulator_disable call ADS7846 regulator is disabled twice in a row in ads7846_remove(). Valid one is in ads7846_disable(). Removing the ads7846 module causes warning about unbalanced disables. ... WARNING: CPU: 0 PID: 29269 at drivers/regulator/core.c:2251 _regulator_disable+0xf8/0x130 unbalanced disables for vads7846 CPU: 0 PID: 29269 Comm: rmmod Tainted: G D W 4.7.0+ #3 Hardware name: HTC Magician ... show_stack+0x10/0x14 __warn+0xd8/0x100 warn_slowpath_fmt+0x38/0x48 _regulator_disable+0xf8/0x130 regulator_disable+0x34/0x60 ads7846_remove+0x58/0xd4 [ads7846] spi_drv_remove+0x1c/0x34 __device_release_driver+0x84/0x114 driver_detach+0x8c/0x90 bus_remove_driver+0x5c/0xc8 SyS_delete_module+0x1a0/0x238 ret_fast_syscall+0x0/0x38 Signed-off-by: Petr Cvek Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/ads7846.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c index a61b2153ab8c..1ce3ecbe37f8 100644 --- a/drivers/input/touchscreen/ads7846.c +++ b/drivers/input/touchscreen/ads7846.c @@ -1473,7 +1473,6 @@ static int ads7846_remove(struct spi_device *spi) ads784x_hwmon_unregister(spi, ts); - regulator_disable(ts->reg); regulator_put(ts->reg); if (!ts->get_pendown_state) { From b47b0cc73032d3c8225b5ea9a077941632f16d91 Mon Sep 17 00:00:00 2001 From: Mikko Rapeli Date: Mon, 22 Aug 2016 20:32:38 +0200 Subject: [PATCH 272/531] include/uapi/linux/if_pppox.h: include linux/if.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes userspace compilation error: error: ‘IFNAMSIZ’ undeclared here (not in a function) Signed-off-by: Mikko Rapeli Signed-off-by: David S. Miller --- include/uapi/linux/if_pppox.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/uapi/linux/if_pppox.h b/include/uapi/linux/if_pppox.h index e128769331b5..473c3c45e3d8 100644 --- a/include/uapi/linux/if_pppox.h +++ b/include/uapi/linux/if_pppox.h @@ -21,6 +21,7 @@ #include #include +#include #include #include From 1fe8e0f074c77aa41aaa579345a9e675acbebfa9 Mon Sep 17 00:00:00 2001 From: Mikko Rapeli Date: Mon, 22 Aug 2016 20:32:39 +0200 Subject: [PATCH 273/531] include/uapi/linux/if_tunnel.h: include linux/if.h, linux/ip.h and linux/in6.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes userspace compilation errors like: error: field ‘iph’ has incomplete type error: field ‘prefix’ has incomplete type Signed-off-by: Mikko Rapeli Signed-off-by: David S. Miller --- include/uapi/linux/if_tunnel.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h index 1046f5515174..777b6cdb1b7b 100644 --- a/include/uapi/linux/if_tunnel.h +++ b/include/uapi/linux/if_tunnel.h @@ -2,6 +2,9 @@ #define _UAPI_IF_TUNNEL_H_ #include +#include +#include +#include #include From 05ee5de7451796cf9a8aeb2f05a57790d4fd2336 Mon Sep 17 00:00:00 2001 From: Mikko Rapeli Date: Mon, 22 Aug 2016 20:32:42 +0200 Subject: [PATCH 274/531] include/uapi/linux/if_pppol2tp.h: include linux/in.h and linux/in6.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes userspace compilation errors like: error: field ‘addr’ has incomplete type struct sockaddr_in addr; /* IP address and port to send to */ ^ error: field ‘addr’ has incomplete type struct sockaddr_in6 addr; /* IP address and port to send to */ Signed-off-by: Mikko Rapeli Signed-off-by: David S. Miller --- include/uapi/linux/if_pppol2tp.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/include/uapi/linux/if_pppol2tp.h b/include/uapi/linux/if_pppol2tp.h index 163e8adac2d6..4bd1f55d6377 100644 --- a/include/uapi/linux/if_pppol2tp.h +++ b/include/uapi/linux/if_pppol2tp.h @@ -16,7 +16,8 @@ #define _UAPI__LINUX_IF_PPPOL2TP_H #include - +#include +#include /* Structure used to connect() the socket to a particular tunnel UDP * socket over IPv4. From eafe92114308acf14e45c6c3d154a5dad5523d1a Mon Sep 17 00:00:00 2001 From: Mikko Rapeli Date: Mon, 22 Aug 2016 20:32:43 +0200 Subject: [PATCH 275/531] include/uapi/linux/if_pppox.h: include linux/in.h and linux/in6.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes userspace compilation errors: error: field ‘addr’ has incomplete type struct sockaddr_in addr; /* IP address and port to send to */ error: field ‘addr’ has incomplete type struct sockaddr_in6 addr; /* IP address and port to send to */ Signed-off-by: Mikko Rapeli Signed-off-by: David S. Miller --- include/uapi/linux/if_pppox.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/include/uapi/linux/if_pppox.h b/include/uapi/linux/if_pppox.h index 473c3c45e3d8..d37bbb17a007 100644 --- a/include/uapi/linux/if_pppox.h +++ b/include/uapi/linux/if_pppox.h @@ -24,6 +24,8 @@ #include #include #include +#include +#include /* For user-space programs to pick up these definitions * which they wouldn't get otherwise without defining __KERNEL__ From e6571aa5cb65ff52a87843652d0d8120a48aae7c Mon Sep 17 00:00:00 2001 From: Mikko Rapeli Date: Mon, 22 Aug 2016 20:32:55 +0200 Subject: [PATCH 276/531] include/uapi/linux/openvswitch.h: use __u32 from linux/types.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes userspace compiler error: error: unknown type name ‘uint32_t’ Signed-off-by: Mikko Rapeli Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index d95a3018f6a1..645499a634f7 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -632,8 +632,8 @@ enum ovs_hash_alg { * @hash_basis: basis used for computing hash. */ struct ovs_action_hash { - uint32_t hash_alg; /* One of ovs_hash_alg. */ - uint32_t hash_basis; + __u32 hash_alg; /* One of ovs_hash_alg. */ + __u32 hash_basis; }; /** From cf00713a655d3019be7faa184402f16c43a0fed3 Mon Sep 17 00:00:00 2001 From: Mikko Rapeli Date: Mon, 22 Aug 2016 20:32:58 +0200 Subject: [PATCH 277/531] include/uapi/linux/atm_zatm.h: include linux/time.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes userspace compile error: error: field ‘real’ has incomplete type struct timeval real; /* real (wall-clock) time */ Signed-off-by: Mikko Rapeli Signed-off-by: David S. Miller --- include/uapi/linux/atm_zatm.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/uapi/linux/atm_zatm.h b/include/uapi/linux/atm_zatm.h index 9c9c6ad55f14..5cd4d4d2dd1d 100644 --- a/include/uapi/linux/atm_zatm.h +++ b/include/uapi/linux/atm_zatm.h @@ -14,6 +14,7 @@ #include #include +#include #define ZATM_GETPOOL _IOW('a',ATMIOC_SARPRV+1,struct atmif_sioc) /* get pool statistics */ From a1d1f65ff5ac27276a585b41a619d30995bb92fe Mon Sep 17 00:00:00 2001 From: Mikko Rapeli Date: Mon, 22 Aug 2016 20:33:19 +0200 Subject: [PATCH 278/531] include/uapi/linux/openvswitch.h: use __u32 from linux/types.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Kernel uapi header are supposed to use them. Fixes userspace compile error: linux/openvswitch.h:583:2: error: unknown type name ‘uint32_t’ Signed-off-by: Mikko Rapeli Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 645499a634f7..54c3b4f4aceb 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -583,7 +583,7 @@ enum ovs_userspace_attr { #define OVS_USERSPACE_ATTR_MAX (__OVS_USERSPACE_ATTR_MAX - 1) struct ovs_action_trunc { - uint32_t max_len; /* Max packet size in bytes. */ + __u32 max_len; /* Max packet size in bytes. */ }; /** From 53dc65d4d33c422d086c9d9ad8c03ab400ffc0a1 Mon Sep 17 00:00:00 2001 From: Mikko Rapeli Date: Mon, 22 Aug 2016 20:33:21 +0200 Subject: [PATCH 279/531] include/uapi/linux/ipx.h: fix conflicting defitions with glibc netipx/ipx.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes these compiler warnings via libc-compat.h when glibc netipx/ipx.h is included before linux/ipx.h: ./linux/ipx.h:9:8: error: redefinition of ‘struct sockaddr_ipx’ ./linux/ipx.h:26:8: error: redefinition of ‘struct ipx_route_definition’ ./linux/ipx.h:32:8: error: redefinition of ‘struct ipx_interface_definition’ ./linux/ipx.h:49:8: error: redefinition of ‘struct ipx_config_data’ ./linux/ipx.h:58:8: error: redefinition of ‘struct ipx_route_def’ Signed-off-by: Mikko Rapeli Signed-off-by: David S. Miller --- include/uapi/linux/ipx.h | 13 ++++++++++++- include/uapi/linux/libc-compat.h | 26 ++++++++++++++++++++++++++ 2 files changed, 38 insertions(+), 1 deletion(-) diff --git a/include/uapi/linux/ipx.h b/include/uapi/linux/ipx.h index 3d48014cdd71..30f031db12f6 100644 --- a/include/uapi/linux/ipx.h +++ b/include/uapi/linux/ipx.h @@ -1,11 +1,13 @@ #ifndef _IPX_H_ #define _IPX_H_ +#include /* for compatibility with glibc netipx/ipx.h */ #include #include #include #define IPX_NODE_LEN 6 #define IPX_MTU 576 +#if __UAPI_DEF_SOCKADDR_IPX struct sockaddr_ipx { __kernel_sa_family_t sipx_family; __be16 sipx_port; @@ -14,6 +16,7 @@ struct sockaddr_ipx { __u8 sipx_type; unsigned char sipx_zero; /* 16 byte fill */ }; +#endif /* __UAPI_DEF_SOCKADDR_IPX */ /* * So we can fit the extra info for SIOCSIFADDR into the address nicely @@ -23,12 +26,15 @@ struct sockaddr_ipx { #define IPX_DLTITF 0 #define IPX_CRTITF 1 +#if __UAPI_DEF_IPX_ROUTE_DEFINITION struct ipx_route_definition { __be32 ipx_network; __be32 ipx_router_network; unsigned char ipx_router_node[IPX_NODE_LEN]; }; +#endif /* __UAPI_DEF_IPX_ROUTE_DEFINITION */ +#if __UAPI_DEF_IPX_INTERFACE_DEFINITION struct ipx_interface_definition { __be32 ipx_network; unsigned char ipx_device[16]; @@ -45,16 +51,20 @@ struct ipx_interface_definition { #define IPX_INTERNAL 2 unsigned char ipx_node[IPX_NODE_LEN]; }; - +#endif /* __UAPI_DEF_IPX_INTERFACE_DEFINITION */ + +#if __UAPI_DEF_IPX_CONFIG_DATA struct ipx_config_data { unsigned char ipxcfg_auto_select_primary; unsigned char ipxcfg_auto_create_interfaces; }; +#endif /* __UAPI_DEF_IPX_CONFIG_DATA */ /* * OLD Route Definition for backward compatibility. */ +#if __UAPI_DEF_IPX_ROUTE_DEF struct ipx_route_def { __be32 ipx_network; __be32 ipx_router_network; @@ -67,6 +77,7 @@ struct ipx_route_def { #define IPX_RT_BLUEBOOK 2 #define IPX_RT_ROUTED 1 }; +#endif /* __UAPI_DEF_IPX_ROUTE_DEF */ #define SIOCAIPXITFCRT (SIOCPROTOPRIVATE) #define SIOCAIPXPRISLT (SIOCPROTOPRIVATE + 1) diff --git a/include/uapi/linux/libc-compat.h b/include/uapi/linux/libc-compat.h index e4f048ee7043..44b8a6bd5fe1 100644 --- a/include/uapi/linux/libc-compat.h +++ b/include/uapi/linux/libc-compat.h @@ -139,6 +139,25 @@ #endif /* _NETINET_IN_H */ +/* Coordinate with glibc netipx/ipx.h header. */ +#if defined(__NETIPX_IPX_H) + +#define __UAPI_DEF_SOCKADDR_IPX 0 +#define __UAPI_DEF_IPX_ROUTE_DEFINITION 0 +#define __UAPI_DEF_IPX_INTERFACE_DEFINITION 0 +#define __UAPI_DEF_IPX_CONFIG_DATA 0 +#define __UAPI_DEF_IPX_ROUTE_DEF 0 + +#else /* defined(__NETIPX_IPX_H) */ + +#define __UAPI_DEF_SOCKADDR_IPX 1 +#define __UAPI_DEF_IPX_ROUTE_DEFINITION 1 +#define __UAPI_DEF_IPX_INTERFACE_DEFINITION 1 +#define __UAPI_DEF_IPX_CONFIG_DATA 1 +#define __UAPI_DEF_IPX_ROUTE_DEF 1 + +#endif /* defined(__NETIPX_IPX_H) */ + /* Definitions for xattr.h */ #if defined(_SYS_XATTR_H) #define __UAPI_DEF_XATTR 0 @@ -179,6 +198,13 @@ #define __UAPI_DEF_IN6_PKTINFO 1 #define __UAPI_DEF_IP6_MTUINFO 1 +/* Definitions for ipx.h */ +#define __UAPI_DEF_SOCKADDR_IPX 1 +#define __UAPI_DEF_IPX_ROUTE_DEFINITION 1 +#define __UAPI_DEF_IPX_INTERFACE_DEFINITION 1 +#define __UAPI_DEF_IPX_CONFIG_DATA 1 +#define __UAPI_DEF_IPX_ROUTE_DEF 1 + /* Definitions for xattr.h */ #define __UAPI_DEF_XATTR 1 From 85b51b12115c79cce7ea1ced6c0bd0339a165d3f Mon Sep 17 00:00:00 2001 From: Mike Manning Date: Thu, 18 Aug 2016 14:39:40 +0100 Subject: [PATCH 280/531] net: ipv6: Remove addresses for failures with strict DAD If DAD fails with accept_dad set to 2, global addresses and host routes are incorrectly left in place. Even though disable_ipv6 is set, contrary to documentation, the addresses are not dynamically deleted from the interface. It is only on a subsequent link down/up that these are removed. The fix is not only to set the disable_ipv6 flag, but also to call addrconf_ifdown(), which is the action to carry out when disabling IPv6. This results in the addresses and routes being deleted immediately. The DAD failure for the LL addr is determined as before via netlink, or by the absence of the LL addr (which also previously would have had to be checked for in case of an intervening link down and up). As the call to addrconf_ifdown() requires an rtnl lock, the logic to disable IPv6 when DAD fails is moved to addrconf_dad_work(). Previous behavior: root@vm1:/# sysctl net.ipv6.conf.eth3.accept_dad=2 net.ipv6.conf.eth3.accept_dad = 2 root@vm1:/# ip -6 addr add 2000::10/64 dev eth3 root@vm1:/# ip link set up eth3 root@vm1:/# ip -6 addr show dev eth3 5: eth3: mtu 1500 qlen 1000 inet6 2000::10/64 scope global valid_lft forever preferred_lft forever inet6 fe80::5054:ff:fe43:dd5a/64 scope link tentative dadfailed valid_lft forever preferred_lft forever root@vm1:/# ip -6 route show dev eth3 2000::/64 proto kernel metric 256 fe80::/64 proto kernel metric 256 root@vm1:/# ip link set down eth3 root@vm1:/# ip link set up eth3 root@vm1:/# ip -6 addr show dev eth3 root@vm1:/# ip -6 route show dev eth3 root@vm1:/# New behavior: root@vm1:/# sysctl net.ipv6.conf.eth3.accept_dad=2 net.ipv6.conf.eth3.accept_dad = 2 root@vm1:/# ip -6 addr add 2000::10/64 dev eth3 root@vm1:/# ip link set up eth3 root@vm1:/# ip -6 addr show dev eth3 root@vm1:/# ip -6 route show dev eth3 root@vm1:/# Signed-off-by: Mike Manning Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 34 +++++++++++++++++++++------------- 1 file changed, 21 insertions(+), 13 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index df8425fcbc2c..f418d2eaeddd 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1872,7 +1872,6 @@ static int addrconf_dad_end(struct inet6_ifaddr *ifp) void addrconf_dad_failure(struct inet6_ifaddr *ifp) { - struct in6_addr addr; struct inet6_dev *idev = ifp->idev; struct net *net = dev_net(ifp->idev->dev); @@ -1934,18 +1933,6 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) in6_ifa_put(ifp2); lock_errdad: spin_lock_bh(&ifp->lock); - } else if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6) { - addr.s6_addr32[0] = htonl(0xfe800000); - addr.s6_addr32[1] = 0; - - if (!ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) && - ipv6_addr_equal(&ifp->addr, &addr)) { - /* DAD failed for link-local based on MAC address */ - idev->cnf.disable_ipv6 = 1; - - pr_info("%s: IPv6 being disabled!\n", - ifp->idev->dev->name); - } } errdad: @@ -3821,6 +3808,7 @@ static void addrconf_dad_work(struct work_struct *w) dad_work); struct inet6_dev *idev = ifp->idev; struct in6_addr mcaddr; + bool disable_ipv6 = false; enum { DAD_PROCESS, @@ -3837,6 +3825,24 @@ static void addrconf_dad_work(struct work_struct *w) } else if (ifp->state == INET6_IFADDR_STATE_ERRDAD) { action = DAD_ABORT; ifp->state = INET6_IFADDR_STATE_POSTDAD; + + if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6 && + !(ifp->flags & IFA_F_STABLE_PRIVACY)) { + struct in6_addr addr; + + addr.s6_addr32[0] = htonl(0xfe800000); + addr.s6_addr32[1] = 0; + + if (!ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) && + ipv6_addr_equal(&ifp->addr, &addr)) { + /* DAD failed for link-local based on MAC */ + idev->cnf.disable_ipv6 = 1; + + pr_info("%s: IPv6 being disabled!\n", + ifp->idev->dev->name); + disable_ipv6 = true; + } + } } spin_unlock_bh(&ifp->lock); @@ -3845,6 +3851,8 @@ static void addrconf_dad_work(struct work_struct *w) goto out; } else if (action == DAD_ABORT) { addrconf_dad_stop(ifp, 1); + if (disable_ipv6) + addrconf_ifdown(idev->dev, 0); goto out; } From c0451fe1f27b815b3f400df2a63b9aecf589b7b0 Mon Sep 17 00:00:00 2001 From: Shmulik Ladkani Date: Sun, 21 Aug 2016 11:22:32 +0300 Subject: [PATCH 281/531] net: ip_finish_output_gso: Allow fragmenting segments of tunneled skbs if their DF is unset In b8247f095e, "net: ip_finish_output_gso: If skb_gso_network_seglen exceeds MTU, allow segmentation for local udp tunneled skbs" gso skbs arriving from an ingress interface that go through UDP tunneling, are allowed to be fragmented if the resulting encapulated segments exceed the dst mtu of the egress interface. This aligned the behavior of gso skbs to non-gso skbs going through udp encapsulation path. However the non-gso vs gso anomaly is present also in the following cases of a GRE tunnel: - ip_gre in collect_md mode, where TUNNEL_DONT_FRAGMENT is not set (e.g. OvS vport-gre with df_default=false) - ip_gre in nopmtudisc mode, where IFLA_GRE_IGNORE_DF is set In both of the above cases, the non-gso skbs get fragmented, whereas the gso skbs (having skb_gso_network_seglen that exceeds dst mtu) get dropped, as they don't go through the segment+fragment code path. Fix: Setting IPSKB_FRAG_SEGS if the tunnel specified IP_DF bit is NOT set. Tunnels that do set IP_DF, will not go to fragmentation of segments. This preserves behavior of ip_gre in (the default) pmtudisc mode. Fixes: b8247f095e ("net: ip_finish_output_gso: If skb_gso_network_seglen exceeds MTU, allow segmentation for local udp tunneled skbs") Reported-by: wenxu Cc: Hannes Frederic Sowa Signed-off-by: Shmulik Ladkani Tested-by: wenxu Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/ipv4/ip_tunnel_core.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 9d847c302551..0f227db0e9ac 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -73,9 +73,11 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, skb_dst_set(skb, &rt->dst); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); - if (skb_iif && proto == IPPROTO_UDP) { - /* Arrived from an ingress interface and got udp encapuslated. - * The encapsulated network segment length may exceed dst mtu. + if (skb_iif && !(df & htons(IP_DF))) { + /* Arrived from an ingress interface, got encapsulated, with + * fragmentation of encapulating frames allowed. + * If skb is gso, the resulting encapsulated network segments + * may exceed dst mtu. * Allow IP Fragmentation of segments. */ IPCB(skb)->flags |= IPSKB_FRAG_SEGS; From 4870e704d901602e4ae5de462c4e65732cf2ed6c Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Mon, 22 Aug 2016 12:03:29 +0300 Subject: [PATCH 282/531] qed: FLR of active VFs might lead to FW assert Driver never bothered marking the VF's vport with the VF's sw_fid. As a result, FLR flows are not going to clean those vports. If the vport was active when FLRed, re-activating it would lead to a FW assertion. Fixes: dacd88d6f6851 ("qed: IOV l2 functionality") Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index 35e53771533f..45ab74676573 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -561,9 +561,18 @@ struct qed_dev { static inline u8 qed_concrete_to_sw_fid(struct qed_dev *cdev, u32 concrete_fid) { + u8 vfid = GET_FIELD(concrete_fid, PXP_CONCRETE_FID_VFID); u8 pfid = GET_FIELD(concrete_fid, PXP_CONCRETE_FID_PFID); + u8 vf_valid = GET_FIELD(concrete_fid, + PXP_CONCRETE_FID_VFVALID); + u8 sw_fid; - return pfid; + if (vf_valid) + sw_fid = vfid + MAX_NUM_PFS; + else + sw_fid = pfid; + + return sw_fid; } #define PURE_LB_TC 8 From 7329a655875a2f4bd6984fe8a7e00a6981e802f3 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Fri, 19 Aug 2016 12:15:22 -0700 Subject: [PATCH 283/531] usercopy: avoid potentially undefined behavior in pointer math check_bogus_address() checked for pointer overflow using this expression, where 'ptr' has type 'const void *': ptr + n < ptr Since pointer wraparound is undefined behavior, gcc at -O2 by default treats it like the following, which would not behave as intended: (long)n < 0 Fortunately, this doesn't currently happen for kernel code because kernel code is compiled with -fno-strict-overflow. But the expression should be fixed anyway to use well-defined integer arithmetic, since it could be treated differently by different compilers in the future or could be reported by tools checking for undefined behavior. Signed-off-by: Eric Biggers Signed-off-by: Kees Cook --- mm/usercopy.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/usercopy.c b/mm/usercopy.c index 8ebae91a6b55..82f81df2edcf 100644 --- a/mm/usercopy.c +++ b/mm/usercopy.c @@ -124,7 +124,7 @@ static inline const char *check_kernel_text_object(const void *ptr, static inline const char *check_bogus_address(const void *ptr, unsigned long n) { /* Reject if object wraps past end of memory. */ - if (ptr + n < ptr) + if ((unsigned long)ptr + n < (unsigned long)ptr) return ""; /* Reject if NULL or ZERO-allocation. */ From 94cd97af690dd9537818dc9841d0ec68bb1dd877 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 22 Aug 2016 11:53:59 -0500 Subject: [PATCH 284/531] usercopy: fix overlap check for kernel text When running with a local patch which moves the '_stext' symbol to the very beginning of the kernel text area, I got the following panic with CONFIG_HARDENED_USERCOPY: usercopy: kernel memory exposure attempt detected from ffff88103dfff000 () (4096 bytes) ------------[ cut here ]------------ kernel BUG at mm/usercopy.c:79! invalid opcode: 0000 [#1] SMP ... CPU: 0 PID: 4800 Comm: cp Not tainted 4.8.0-rc3.after+ #1 Hardware name: Dell Inc. PowerEdge R720/0X3D66, BIOS 2.5.4 01/22/2016 task: ffff880817444140 task.stack: ffff880816274000 RIP: 0010:[] __check_object_size+0x76/0x413 RSP: 0018:ffff880816277c40 EFLAGS: 00010246 RAX: 000000000000006b RBX: ffff88103dfff000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff88081f80dfa8 RDI: ffff88081f80dfa8 RBP: ffff880816277c90 R08: 000000000000054c R09: 0000000000000000 R10: 0000000000000005 R11: 0000000000000006 R12: 0000000000001000 R13: ffff88103e000000 R14: ffff88103dffffff R15: 0000000000000001 FS: 00007fb9d1750800(0000) GS:ffff88081f800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000021d2000 CR3: 000000081a08f000 CR4: 00000000001406f0 Stack: ffff880816277cc8 0000000000010000 000000043de07000 0000000000000000 0000000000001000 ffff880816277e60 0000000000001000 ffff880816277e28 000000000000c000 0000000000001000 ffff880816277ce8 ffffffff8136c3a6 Call Trace: [] copy_page_to_iter_iovec+0xa6/0x1c0 [] copy_page_to_iter+0x16/0x90 [] generic_file_read_iter+0x3e3/0x7c0 [] ? xfs_file_buffered_aio_write+0xad/0x260 [xfs] [] ? down_read+0x12/0x40 [] xfs_file_buffered_aio_read+0x51/0xc0 [xfs] [] xfs_file_read_iter+0x62/0xb0 [xfs] [] __vfs_read+0xdf/0x130 [] vfs_read+0x8e/0x140 [] SyS_read+0x55/0xc0 [] do_syscall_64+0x67/0x160 [] entry_SYSCALL64_slow_path+0x25/0x25 RIP: 0033:[<00007fb9d0c33c00>] 0x7fb9d0c33c00 RSP: 002b:00007ffc9c262f28 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 RAX: ffffffffffffffda RBX: fffffffffff8ffff RCX: 00007fb9d0c33c00 RDX: 0000000000010000 RSI: 00000000021c3000 RDI: 0000000000000004 RBP: 00000000021c3000 R08: 0000000000000000 R09: 00007ffc9c264d6c R10: 00007ffc9c262c50 R11: 0000000000000246 R12: 0000000000010000 R13: 00007ffc9c2630b0 R14: 0000000000000004 R15: 0000000000010000 Code: 81 48 0f 44 d0 48 c7 c6 90 4d a3 81 48 c7 c0 bb b3 a2 81 48 0f 44 f0 4d 89 e1 48 89 d9 48 c7 c7 68 16 a3 81 31 c0 e8 f4 57 f7 ff <0f> 0b 48 8d 90 00 40 00 00 48 39 d3 0f 83 22 01 00 00 48 39 c3 RIP [] __check_object_size+0x76/0x413 RSP The checked object's range [ffff88103dfff000, ffff88103e000000) is valid, so there shouldn't have been a BUG. The hardened usercopy code got confused because the range's ending address is the same as the kernel's text starting address at 0xffff88103e000000. The overlap check is slightly off. Fixes: f5509cc18daa ("mm: Hardened usercopy") Signed-off-by: Josh Poimboeuf Signed-off-by: Kees Cook --- mm/usercopy.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/usercopy.c b/mm/usercopy.c index 82f81df2edcf..a3cc3052f830 100644 --- a/mm/usercopy.c +++ b/mm/usercopy.c @@ -83,7 +83,7 @@ static bool overlaps(const void *ptr, unsigned long n, unsigned long low, unsigned long check_high = check_low + n; /* Does not overlap if entirely above or entirely below. */ - if (check_low >= high || check_high < low) + if (check_low >= high || check_high <= low) return false; return true; From 28a10c426e81afc88514bca8e73affccf850fdf6 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Mon, 22 Aug 2016 07:10:20 -0400 Subject: [PATCH 285/531] net sched: fix encoding to use real length Encoding of the metadata was using the padded length as opposed to the real length of the data which is a bug per specification. This has not been an issue todate because all metadatum specified so far has been 32 bit where aligned and data length are the same width. This also includes a bug fix for validating the length of a u16 field. But since there is no metadata of size u16 yes we are fine to include it here. While at it get rid of magic numbers. Fixes: ef6980b6becb ("net sched: introduce IFE action") Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- net/sched/act_ife.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 141a06eeb1e5..e87cd81315e1 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -53,7 +53,7 @@ int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen, const void *dval) u32 *tlv = (u32 *)(skbdata); u16 totlen = nla_total_size(dlen); /*alignment + hdr */ char *dptr = (char *)tlv + NLA_HDRLEN; - u32 htlv = attrtype << 16 | totlen; + u32 htlv = attrtype << 16 | dlen; *tlv = htonl(htlv); memset(dptr, 0, totlen - NLA_HDRLEN); @@ -135,7 +135,7 @@ EXPORT_SYMBOL_GPL(ife_release_meta_gen); int ife_validate_meta_u32(void *val, int len) { - if (len == 4) + if (len == sizeof(u32)) return 0; return -EINVAL; @@ -144,8 +144,8 @@ EXPORT_SYMBOL_GPL(ife_validate_meta_u32); int ife_validate_meta_u16(void *val, int len) { - /* length will include padding */ - if (len == NLA_ALIGN(2)) + /* length will not include padding */ + if (len == sizeof(u16)) return 0; return -EINVAL; @@ -652,12 +652,14 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, u8 *tlvdata = (u8 *)tlv; u16 mtype = tlv->type; u16 mlen = tlv->len; + u16 alen; mtype = ntohs(mtype); mlen = ntohs(mlen); + alen = NLA_ALIGN(mlen); - if (find_decode_metaid(skb, ife, mtype, (mlen - 4), - (void *)(tlvdata + 4))) { + if (find_decode_metaid(skb, ife, mtype, (mlen - NLA_HDRLEN), + (void *)(tlvdata + NLA_HDRLEN))) { /* abuse overlimits to count when we receive metadata * but dont have an ops for it */ @@ -666,8 +668,8 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, ife->tcf_qstats.overlimits++; } - tlvdata += mlen; - ifehdrln -= mlen; + tlvdata += alen; + ifehdrln -= alen; tlv = (struct meta_tlvhdr *)tlvdata; } From 6c73358c83ce870c0cf32413e5cadb3b9a39c606 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Mon, 22 Aug 2016 16:58:53 -0400 Subject: [PATCH 286/531] USB: fix typo in wMaxPacketSize validation The maximum value allowed for wMaxPacketSize of a high-speed interrupt endpoint is 1024 bytes, not 1023. Signed-off-by: Alan Stern Fixes: aed9d65ac327 ("USB: validate wMaxPacketValue entries in endpoint descriptors") CC: Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/config.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index 051163189810..15ce4ab11688 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -187,7 +187,7 @@ static const unsigned short high_speed_maxpacket_maxes[4] = { [USB_ENDPOINT_XFER_CONTROL] = 64, [USB_ENDPOINT_XFER_ISOC] = 1024, [USB_ENDPOINT_XFER_BULK] = 512, - [USB_ENDPOINT_XFER_INT] = 1023, + [USB_ENDPOINT_XFER_INT] = 1024, }; static const unsigned short super_speed_maxpacket_maxes[4] = { [USB_ENDPOINT_XFER_CONTROL] = 512, From a8719670687c46ed2e904c0d05fa4cd7e4950cd1 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Tue, 23 Aug 2016 10:27:19 +0300 Subject: [PATCH 287/531] ASoC: omap-mcpdm: Fix irq resource handling Fixes: ddd17531ad908 ("ASoC: omap-mcpdm: Clean up with devm_* function") Managed irq request will not doing any good in ASoC probe level as it is not going to free up the irq when the driver is unbound from the sound card. Signed-off-by: Peter Ujfalusi Reported-by: Russell King Signed-off-by: Mark Brown --- sound/soc/omap/omap-mcpdm.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/sound/soc/omap/omap-mcpdm.c b/sound/soc/omap/omap-mcpdm.c index 74d6e6fdcfd0..64609c77a79d 100644 --- a/sound/soc/omap/omap-mcpdm.c +++ b/sound/soc/omap/omap-mcpdm.c @@ -394,8 +394,8 @@ static int omap_mcpdm_probe(struct snd_soc_dai *dai) pm_runtime_get_sync(mcpdm->dev); omap_mcpdm_write(mcpdm, MCPDM_REG_CTRL, 0x00); - ret = devm_request_irq(mcpdm->dev, mcpdm->irq, omap_mcpdm_irq_handler, - 0, "McPDM", (void *)mcpdm); + ret = request_irq(mcpdm->irq, omap_mcpdm_irq_handler, 0, "McPDM", + (void *)mcpdm); pm_runtime_put_sync(mcpdm->dev); @@ -420,6 +420,7 @@ static int omap_mcpdm_remove(struct snd_soc_dai *dai) { struct omap_mcpdm *mcpdm = snd_soc_dai_get_drvdata(dai); + free_irq(mcpdm->irq, (void *)mcpdm); pm_runtime_disable(mcpdm->dev); return 0; From a77ec83a57890240c546df00ca5df1cdeedb1cc3 Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Mon, 6 Jun 2016 18:07:59 -0400 Subject: [PATCH 288/531] vhost/scsi: fix reuse of &vq->iov[out] in response The address of the iovec &vq->iov[out] is not guaranteed to contain the scsi command's response iovec throughout the lifetime of the command. Rather, it is more likely to contain an iovec from an immediately following command after looping back around to vhost_get_vq_desc(). Pass along the iovec entirely instead. Fixes: 79c14141a487 ("vhost/scsi: Convert completion path to use copy_to_iter") Cc: stable@vger.kernel.org Signed-off-by: Benjamin Coddington Signed-off-by: Michael S. Tsirkin --- drivers/vhost/scsi.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 9d6320e8ff3e..6e29d053843d 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -88,7 +88,7 @@ struct vhost_scsi_cmd { struct scatterlist *tvc_prot_sgl; struct page **tvc_upages; /* Pointer to response header iovec */ - struct iovec *tvc_resp_iov; + struct iovec tvc_resp_iov; /* Pointer to vhost_scsi for our device */ struct vhost_scsi *tvc_vhost; /* Pointer to vhost_virtqueue for the cmd */ @@ -547,7 +547,7 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work) memcpy(v_rsp.sense, cmd->tvc_sense_buf, se_cmd->scsi_sense_length); - iov_iter_init(&iov_iter, READ, cmd->tvc_resp_iov, + iov_iter_init(&iov_iter, READ, &cmd->tvc_resp_iov, cmd->tvc_in_iovs, sizeof(v_rsp)); ret = copy_to_iter(&v_rsp, sizeof(v_rsp), &iov_iter); if (likely(ret == sizeof(v_rsp))) { @@ -1044,7 +1044,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) } cmd->tvc_vhost = vs; cmd->tvc_vq = vq; - cmd->tvc_resp_iov = &vq->iov[out]; + cmd->tvc_resp_iov = vq->iov[out]; cmd->tvc_in_iovs = in; pr_debug("vhost_scsi got command opcode: %#02x, lun: %d\n", From b88fa69eaa8649f11828158c7b65c4bcd886ebd5 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 23 Aug 2016 11:19:33 -0400 Subject: [PATCH 289/531] pNFS: The client must not do I/O to the DS if it's lease has expired Ensure that the client conforms to the normative behaviour described in RFC5661 Section 12.7.2: "If a client believes its lease has expired, it MUST NOT send I/O to the storage device until it has validated its lease." So ensure that we wait for the lease to be validated before using the layout. Signed-off-by: Trond Myklebust Cc: stable@vger.kernel.org # v3.20+ --- fs/nfs/pnfs.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index bf98f1b2595f..6daf034645c8 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1555,6 +1555,7 @@ pnfs_update_layout(struct inode *ino, } lookup_again: + nfs4_client_recover_expired_lease(clp); first = false; spin_lock(&ino->i_lock); lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags); From 41963c10c47a35185e68cb9049f7a3493c94d2d7 Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Mon, 22 Aug 2016 14:11:16 -0400 Subject: [PATCH 290/531] pnfs/blocklayout: update last_write_offset atomically with extents Block/SCSI layout write completion may add committable extents to the extent tree before updating the layout's last-written byte under the inode lock. If a sync happens before this value is updated, then prepare_layoutcommit may find and encode these extents which would produce a LAYOUTCOMMIT request whose encoded extents are larger than the request's loca_length. Fix this by using a last-written byte value that is updated atomically with the extent tree so that commitable extents always match. Signed-off-by: Benjamin Coddington Signed-off-by: Trond Myklebust --- fs/nfs/blocklayout/blocklayout.c | 2 +- fs/nfs/blocklayout/blocklayout.h | 3 ++- fs/nfs/blocklayout/extent_tree.c | 10 +++++++--- 3 files changed, 10 insertions(+), 5 deletions(-) diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index f55a4e756047..217847679f0e 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -346,7 +346,7 @@ static void bl_write_cleanup(struct work_struct *work) PAGE_SIZE - 1) & (loff_t)PAGE_MASK; ext_tree_mark_written(bl, start >> SECTOR_SHIFT, - (end - start) >> SECTOR_SHIFT); + (end - start) >> SECTOR_SHIFT, end); } pnfs_ld_write_done(hdr); diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h index 18e6fd0b9506..efc007f00742 100644 --- a/fs/nfs/blocklayout/blocklayout.h +++ b/fs/nfs/blocklayout/blocklayout.h @@ -141,6 +141,7 @@ struct pnfs_block_layout { struct rb_root bl_ext_ro; spinlock_t bl_ext_lock; /* Protects list manipulation */ bool bl_scsi_layout; + u64 bl_lwb; }; static inline struct pnfs_block_layout * @@ -182,7 +183,7 @@ int ext_tree_insert(struct pnfs_block_layout *bl, int ext_tree_remove(struct pnfs_block_layout *bl, bool rw, sector_t start, sector_t end); int ext_tree_mark_written(struct pnfs_block_layout *bl, sector_t start, - sector_t len); + sector_t len, u64 lwb); bool ext_tree_lookup(struct pnfs_block_layout *bl, sector_t isect, struct pnfs_block_extent *ret, bool rw); int ext_tree_prepare_commit(struct nfs4_layoutcommit_args *arg); diff --git a/fs/nfs/blocklayout/extent_tree.c b/fs/nfs/blocklayout/extent_tree.c index 992bcb19c11e..c85fbfd2d0d9 100644 --- a/fs/nfs/blocklayout/extent_tree.c +++ b/fs/nfs/blocklayout/extent_tree.c @@ -402,7 +402,7 @@ ext_tree_split(struct rb_root *root, struct pnfs_block_extent *be, int ext_tree_mark_written(struct pnfs_block_layout *bl, sector_t start, - sector_t len) + sector_t len, u64 lwb) { struct rb_root *root = &bl->bl_ext_rw; sector_t end = start + len; @@ -471,6 +471,8 @@ ext_tree_mark_written(struct pnfs_block_layout *bl, sector_t start, } } out: + if (bl->bl_lwb < lwb) + bl->bl_lwb = lwb; spin_unlock(&bl->bl_ext_lock); __ext_put_deviceids(&tmp); @@ -518,7 +520,7 @@ static __be32 *encode_scsi_range(struct pnfs_block_extent *be, __be32 *p) } static int ext_tree_encode_commit(struct pnfs_block_layout *bl, __be32 *p, - size_t buffer_size, size_t *count) + size_t buffer_size, size_t *count, __u64 *lastbyte) { struct pnfs_block_extent *be; int ret = 0; @@ -542,6 +544,8 @@ static int ext_tree_encode_commit(struct pnfs_block_layout *bl, __be32 *p, p = encode_block_extent(be, p); be->be_tag = EXTENT_COMMITTING; } + *lastbyte = bl->bl_lwb - 1; + bl->bl_lwb = 0; spin_unlock(&bl->bl_ext_lock); return ret; @@ -564,7 +568,7 @@ ext_tree_prepare_commit(struct nfs4_layoutcommit_args *arg) arg->layoutupdate_pages = &arg->layoutupdate_page; retry: - ret = ext_tree_encode_commit(bl, start_p + 1, buffer_size, &count); + ret = ext_tree_encode_commit(bl, start_p + 1, buffer_size, &count, &arg->lastbytewritten); if (unlikely(ret)) { ext_tree_free_commitdata(arg, buffer_size); From 48ef5865d08fa0a36d786f2f8e12c6194d27538b Mon Sep 17 00:00:00 2001 From: Markus Elfring Date: Fri, 19 Aug 2016 08:50:23 +0200 Subject: [PATCH 291/531] IB/qib: Use memdup_user() rather than duplicating its implementation Reuse existing functionality from memdup_user() instead of keeping duplicate source code. This issue was detected by using the Coccinelle software. Signed-off-by: Markus Elfring Reviewed-by: Leon Romanovsky Signed-off-by: Doug Ledford --- drivers/infiniband/hw/qib/qib_fs.c | 26 +++++--------------------- 1 file changed, 5 insertions(+), 21 deletions(-) diff --git a/drivers/infiniband/hw/qib/qib_fs.c b/drivers/infiniband/hw/qib/qib_fs.c index fcdf37913a26..c3edc033f7c4 100644 --- a/drivers/infiniband/hw/qib/qib_fs.c +++ b/drivers/infiniband/hw/qib/qib_fs.c @@ -328,26 +328,12 @@ static ssize_t flash_write(struct file *file, const char __user *buf, pos = *ppos; - if (pos != 0) { - ret = -EINVAL; - goto bail; - } + if (pos != 0 || count != sizeof(struct qib_flash)) + return -EINVAL; - if (count != sizeof(struct qib_flash)) { - ret = -EINVAL; - goto bail; - } - - tmp = kmalloc(count, GFP_KERNEL); - if (!tmp) { - ret = -ENOMEM; - goto bail; - } - - if (copy_from_user(tmp, buf, count)) { - ret = -EFAULT; - goto bail_tmp; - } + tmp = memdup_user(buf, count); + if (IS_ERR(tmp)) + return PTR_ERR(tmp); dd = private2dd(file); if (qib_eeprom_write(dd, pos, tmp, count)) { @@ -361,8 +347,6 @@ static ssize_t flash_write(struct file *file, const char __user *buf, bail_tmp: kfree(tmp); - -bail: return ret; } From 92d27ae6b3bb3491c1685fb3ca7ae1b26d81bdf4 Mon Sep 17 00:00:00 2001 From: Markus Elfring Date: Mon, 22 Aug 2016 18:23:24 +0200 Subject: [PATCH 292/531] IB/core: Use memdup_user() rather than duplicating its implementation * Reuse existing functionality from memdup_user() instead of keeping duplicate source code. This issue was detected by using the Coccinelle software. * The local variable "ret" will be set to an appropriate value a bit later. Thus omit the explicit initialisation at the beginning. Signed-off-by: Markus Elfring Signed-off-by: Doug Ledford --- include/rdma/ib_verbs.h | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 8e90dd28bb75..e1f96737c2a1 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2115,22 +2115,17 @@ static inline bool ib_is_udata_cleared(struct ib_udata *udata, size_t len) { const void __user *p = udata->inbuf + offset; - bool ret = false; + bool ret; u8 *buf; if (len > USHRT_MAX) return false; - buf = kmalloc(len, GFP_KERNEL); - if (!buf) + buf = memdup_user(p, len); + if (IS_ERR(buf)) return false; - if (copy_from_user(buf, p, len)) - goto free; - ret = !memchr_inv(buf, 0, len); - -free: kfree(buf); return ret; } From 6c7d46fdb8165ece4b0a17fb8f0b9320dbfeffc2 Mon Sep 17 00:00:00 2001 From: Shiraz Saleem Date: Mon, 22 Aug 2016 18:09:14 -0500 Subject: [PATCH 293/531] i40iw: Change mem_resources pointer to a u8 iwdev->mem_resources is incorrectly defined as an unsigned long instead of u8. As a result, the offset into the dynamic allocated structures in i40iw_initialize_hw_resources() is incorrectly calculated and would lead to writing of memory regions outside of the allocated buffer. Fixes: 8e06af711bf2 ("i40iw: add main, hdr, status") Reported-by: Stefan Assmann Signed-off-by: Mustafa Ismail Signed-off-by: Shiraz Saleem Signed-off-by: Doug Ledford --- drivers/infiniband/hw/i40iw/i40iw.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/i40iw/i40iw.h b/drivers/infiniband/hw/i40iw/i40iw.h index b738acdb9b02..882f3ef2e4c7 100644 --- a/drivers/infiniband/hw/i40iw/i40iw.h +++ b/drivers/infiniband/hw/i40iw/i40iw.h @@ -232,7 +232,7 @@ struct i40iw_device { struct i40e_client *client; struct i40iw_hw hw; struct i40iw_cm_core cm_core; - unsigned long *mem_resources; + u8 *mem_resources; unsigned long *allocated_qps; unsigned long *allocated_cqs; unsigned long *allocated_mrs; From 44856be3e95c87f03e850ef4fdf8c0503c2dde18 Mon Sep 17 00:00:00 2001 From: Mustafa Ismail Date: Mon, 22 Aug 2016 18:15:58 -0500 Subject: [PATCH 294/531] i40iw: Protect req_resource_num update In i40iw_alloc_resource(), ensure that the update to req_resource_num is protected by the lock. Fixes: 8e06af711bf2 ("i40iw: add main, hdr, status") Reported-by: Stefan Assmann Signed-off-by: Mustafa Ismail Signed-off-by: Shiraz Saleem Signed-off-by: Doug Ledford --- drivers/infiniband/hw/i40iw/i40iw.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/i40iw/i40iw.h b/drivers/infiniband/hw/i40iw/i40iw.h index 882f3ef2e4c7..8ec09e470f84 100644 --- a/drivers/infiniband/hw/i40iw/i40iw.h +++ b/drivers/infiniband/hw/i40iw/i40iw.h @@ -435,8 +435,8 @@ static inline int i40iw_alloc_resource(struct i40iw_device *iwdev, *next = resource_num + 1; if (*next == max_resources) *next = 0; - spin_unlock_irqrestore(&iwdev->resource_lock, flags); *req_resource_num = resource_num; + spin_unlock_irqrestore(&iwdev->resource_lock, flags); return 0; } From faa739fb5df56aadab96bcd2f6eb3486cc3a3aec Mon Sep 17 00:00:00 2001 From: Mustafa Ismail Date: Mon, 22 Aug 2016 18:17:12 -0500 Subject: [PATCH 295/531] i40iw: Add missing check for interface already open In i40iw_open(), check if interface is already open and return success if it is. Fixes: 8e06af711bf2 ("i40iw: add main, hdr, status") Reported-by: Stefan Assmann Signed-off-by: Mustafa Ismail Signed-off-by: Shiraz Saleem Signed-off-by: Doug Ledford --- drivers/infiniband/hw/i40iw/i40iw_main.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/infiniband/hw/i40iw/i40iw_main.c b/drivers/infiniband/hw/i40iw/i40iw_main.c index 6e9081380a27..0cbbe4038298 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_main.c +++ b/drivers/infiniband/hw/i40iw/i40iw_main.c @@ -1558,6 +1558,10 @@ static int i40iw_open(struct i40e_info *ldev, struct i40e_client *client) enum i40iw_status_code status; struct i40iw_handler *hdl; + hdl = i40iw_find_netdev(ldev->netdev); + if (hdl) + return 0; + hdl = kzalloc(sizeof(*hdl), GFP_KERNEL); if (!hdl) return -ENOMEM; From cff069b78c21559f427c3fefe9ef3294e3dec094 Mon Sep 17 00:00:00 2001 From: Bharat Potnuri Date: Tue, 23 Aug 2016 20:27:33 +0530 Subject: [PATCH 296/531] iw_cxgb4: Fix cxgb4 arm CQ logic w/IB_CQ_REPORT_MISSED_EVENTS Current cxgb4 arm CQ logic ignores IB_CQ_REPORT_MISSED_EVENTS for request completion notification on a CQ. Due to this ib_poll_handler() assumes all events polled and avoids further iopoll scheduling. This patch adds logic to cxgb4 ib_req_notify_cq() handler to check if CQ is not empty and return accordingly. Based on the return value of ib_req_notify_cq() handler, ib_poll_handler() will schedule a run of iopoll handler. Signed-off-by: Potnuri Bharat Teja Reviewed-by: Steve Wise Signed-off-by: Doug Ledford --- drivers/infiniband/hw/cxgb4/cq.c | 10 +++++----- drivers/infiniband/hw/cxgb4/t4.h | 5 +++++ 2 files changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c index 812ab7278b8e..ac926c942fee 100644 --- a/drivers/infiniband/hw/cxgb4/cq.c +++ b/drivers/infiniband/hw/cxgb4/cq.c @@ -1016,15 +1016,15 @@ int c4iw_resize_cq(struct ib_cq *cq, int cqe, struct ib_udata *udata) int c4iw_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags) { struct c4iw_cq *chp; - int ret; + int ret = 0; unsigned long flag; chp = to_c4iw_cq(ibcq); spin_lock_irqsave(&chp->lock, flag); - ret = t4_arm_cq(&chp->cq, - (flags & IB_CQ_SOLICITED_MASK) == IB_CQ_SOLICITED); + t4_arm_cq(&chp->cq, + (flags & IB_CQ_SOLICITED_MASK) == IB_CQ_SOLICITED); + if (flags & IB_CQ_REPORT_MISSED_EVENTS) + ret = t4_cq_notempty(&chp->cq); spin_unlock_irqrestore(&chp->lock, flag); - if (ret && !(flags & IB_CQ_REPORT_MISSED_EVENTS)) - ret = 0; return ret; } diff --git a/drivers/infiniband/hw/cxgb4/t4.h b/drivers/infiniband/hw/cxgb4/t4.h index 6126bbe36095..02173f4315fa 100644 --- a/drivers/infiniband/hw/cxgb4/t4.h +++ b/drivers/infiniband/hw/cxgb4/t4.h @@ -634,6 +634,11 @@ static inline int t4_valid_cqe(struct t4_cq *cq, struct t4_cqe *cqe) return (CQE_GENBIT(cqe) == cq->gen); } +static inline int t4_cq_notempty(struct t4_cq *cq) +{ + return cq->sw_in_use || t4_valid_cqe(cq, &cq->queue[cq->cidx]); +} + static inline int t4_next_hw_cqe(struct t4_cq *cq, struct t4_cqe **cqe) { int ret; From 543852af8e5902aee8f7c72c89e1513663e0f696 Mon Sep 17 00:00:00 2001 From: Caesar Wang Date: Wed, 27 Jul 2016 22:24:04 +0800 Subject: [PATCH 297/531] iio: adc: rockchip_saradc: reset saradc controller before programming it SARADC controller needs to be reset before programming it, otherwise it will not function properly. Signed-off-by: Caesar Wang Cc: Jonathan Cameron Cc: Heiko Stuebner Cc: Rob Herring Cc: linux-iio@vger.kernel.org Cc: linux-rockchip@lists.infradead.org Tested-by: Guenter Roeck Cc: Signed-off-by: Jonathan Cameron --- .../bindings/iio/adc/rockchip-saradc.txt | 7 +++++ drivers/iio/adc/Kconfig | 1 + drivers/iio/adc/rockchip_saradc.c | 30 +++++++++++++++++++ 3 files changed, 38 insertions(+) diff --git a/Documentation/devicetree/bindings/iio/adc/rockchip-saradc.txt b/Documentation/devicetree/bindings/iio/adc/rockchip-saradc.txt index bf99e2f24788..205593f56fe7 100644 --- a/Documentation/devicetree/bindings/iio/adc/rockchip-saradc.txt +++ b/Documentation/devicetree/bindings/iio/adc/rockchip-saradc.txt @@ -16,6 +16,11 @@ Required properties: - vref-supply: The regulator supply ADC reference voltage. - #io-channel-cells: Should be 1, see ../iio-bindings.txt +Optional properties: +- resets: Must contain an entry for each entry in reset-names if need support + this option. See ../reset/reset.txt for details. +- reset-names: Must include the name "saradc-apb". + Example: saradc: saradc@2006c000 { compatible = "rockchip,saradc"; @@ -23,6 +28,8 @@ Example: interrupts = ; clocks = <&cru SCLK_SARADC>, <&cru PCLK_SARADC>; clock-names = "saradc", "apb_pclk"; + resets = <&cru SRST_SARADC>; + reset-names = "saradc-apb"; #io-channel-cells = <1>; vref-supply = <&vcc18>; }; diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig index 1de31bdd4ce4..767577298ee3 100644 --- a/drivers/iio/adc/Kconfig +++ b/drivers/iio/adc/Kconfig @@ -389,6 +389,7 @@ config QCOM_SPMI_VADC config ROCKCHIP_SARADC tristate "Rockchip SARADC driver" depends on ARCH_ROCKCHIP || (ARM && COMPILE_TEST) + depends on RESET_CONTROLLER help Say yes here to build support for the SARADC found in SoCs from Rockchip. diff --git a/drivers/iio/adc/rockchip_saradc.c b/drivers/iio/adc/rockchip_saradc.c index f9ad6c2d6821..85d701291654 100644 --- a/drivers/iio/adc/rockchip_saradc.c +++ b/drivers/iio/adc/rockchip_saradc.c @@ -21,6 +21,8 @@ #include #include #include +#include +#include #include #include @@ -53,6 +55,7 @@ struct rockchip_saradc { struct clk *clk; struct completion completion; struct regulator *vref; + struct reset_control *reset; const struct rockchip_saradc_data *data; u16 last_val; }; @@ -190,6 +193,16 @@ static const struct of_device_id rockchip_saradc_match[] = { }; MODULE_DEVICE_TABLE(of, rockchip_saradc_match); +/** + * Reset SARADC Controller. + */ +static void rockchip_saradc_reset_controller(struct reset_control *reset) +{ + reset_control_assert(reset); + usleep_range(10, 20); + reset_control_deassert(reset); +} + static int rockchip_saradc_probe(struct platform_device *pdev) { struct rockchip_saradc *info = NULL; @@ -218,6 +231,20 @@ static int rockchip_saradc_probe(struct platform_device *pdev) if (IS_ERR(info->regs)) return PTR_ERR(info->regs); + /* + * The reset should be an optional property, as it should work + * with old devicetrees as well + */ + info->reset = devm_reset_control_get(&pdev->dev, "saradc-apb"); + if (IS_ERR(info->reset)) { + ret = PTR_ERR(info->reset); + if (ret != -ENOENT) + return ret; + + dev_dbg(&pdev->dev, "no reset control found\n"); + info->reset = NULL; + } + init_completion(&info->completion); irq = platform_get_irq(pdev, 0); @@ -252,6 +279,9 @@ static int rockchip_saradc_probe(struct platform_device *pdev) return PTR_ERR(info->vref); } + if (info->reset) + rockchip_saradc_reset_controller(info->reset); + /* * Use a default value for the converter clock. * This may become user-configurable in the future. From 78ec79bfd59e126e1cb394302bfa531a420b3ecd Mon Sep 17 00:00:00 2001 From: Caesar Wang Date: Wed, 27 Jul 2016 22:24:06 +0800 Subject: [PATCH 298/531] arm64: dts: rockchip: add reset saradc node for rk3368 SoCs SARADC controller needs to be reset before programming it, otherwise it will not function properly. Signed-off-by: Caesar Wang Acked-by: Heiko Stuebner Cc: Signed-off-by: Jonathan Cameron --- arch/arm64/boot/dts/rockchip/rk3368.dtsi | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/arch/arm64/boot/dts/rockchip/rk3368.dtsi index d02a900378e1..4f44d1191bfd 100644 --- a/arch/arm64/boot/dts/rockchip/rk3368.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3368.dtsi @@ -270,6 +270,8 @@ saradc: saradc@ff100000 { #io-channel-cells = <1>; clocks = <&cru SCLK_SARADC>, <&cru PCLK_SARADC>; clock-names = "saradc", "apb_pclk"; + resets = <&cru SRST_SARADC>; + reset-names = "saradc-apb"; status = "disabled"; }; From 3d4267a5a3a4b7619b80ad1839d8b3bedd8b7a8d Mon Sep 17 00:00:00 2001 From: Caesar Wang Date: Wed, 27 Jul 2016 22:24:07 +0800 Subject: [PATCH 299/531] arm: dts: rockchip: add reset node for the exist saradc SoCs SARADC controller needs to be reset before programming it, otherwise it will not function properly. Signed-off-by: Caesar Wang Acked-by: Heiko Stuebner Cc: Signed-off-by: Jonathan Cameron --- arch/arm/boot/dts/rk3066a.dtsi | 2 ++ arch/arm/boot/dts/rk3288.dtsi | 2 ++ arch/arm/boot/dts/rk3xxx.dtsi | 2 ++ 3 files changed, 6 insertions(+) diff --git a/arch/arm/boot/dts/rk3066a.dtsi b/arch/arm/boot/dts/rk3066a.dtsi index c0ba86c3a2ab..0d0dae3a1694 100644 --- a/arch/arm/boot/dts/rk3066a.dtsi +++ b/arch/arm/boot/dts/rk3066a.dtsi @@ -197,6 +197,8 @@ tsadc: tsadc@20060000 { clock-names = "saradc", "apb_pclk"; interrupts = ; #io-channel-cells = <1>; + resets = <&cru SRST_SARADC>; + reset-names = "saradc-apb"; status = "disabled"; }; diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi index cd33f0170890..91c4b3c7a8d5 100644 --- a/arch/arm/boot/dts/rk3288.dtsi +++ b/arch/arm/boot/dts/rk3288.dtsi @@ -279,6 +279,8 @@ saradc: saradc@ff100000 { #io-channel-cells = <1>; clocks = <&cru SCLK_SARADC>, <&cru PCLK_SARADC>; clock-names = "saradc", "apb_pclk"; + resets = <&cru SRST_SARADC>; + reset-names = "saradc-apb"; status = "disabled"; }; diff --git a/arch/arm/boot/dts/rk3xxx.dtsi b/arch/arm/boot/dts/rk3xxx.dtsi index 99bbcc2c9b89..e2cd683b4e4b 100644 --- a/arch/arm/boot/dts/rk3xxx.dtsi +++ b/arch/arm/boot/dts/rk3xxx.dtsi @@ -399,6 +399,8 @@ saradc: saradc@2006c000 { #io-channel-cells = <1>; clocks = <&cru SCLK_SARADC>, <&cru PCLK_SARADC>; clock-names = "saradc", "apb_pclk"; + resets = <&cru SRST_SARADC>; + reset-names = "saradc-apb"; status = "disabled"; }; From 53e5f36fbd2453ad69a3369a1db62dc06c30a4aa Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Tue, 23 Aug 2016 15:32:51 -0400 Subject: [PATCH 300/531] USB: avoid left shift by -1 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit UBSAN complains about a left shift by -1 in proc_do_submiturb(). This can occur when an URB is submitted for a bulk or control endpoint on a high-speed device, since the code doesn't bother to check the endpoint type; normally only interrupt or isochronous endpoints have a nonzero bInterval value. Aside from the fact that the operation is illegal, it shouldn't matter because the result isn't used. Still, in theory it could cause a hardware exception or other problem, so we should work around it. This patch avoids doing the left shift unless the shift amount is >= 0. The same piece of code has another problem. When checking the device speed (the exponential encoding for interrupt endpoints is used only by high-speed or faster devices), we need to look for speed >= USB_SPEED_SUPER as well as speed == USB_SPEED HIGH. The patch adds this check. Signed-off-by: Alan Stern Reported-by: Vittorio Zecca Tested-by: Vittorio Zecca Suggested-by: Bjørn Mork CC: Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/devio.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index e6a6d67c8705..09c8d9ca61ae 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -1709,11 +1709,17 @@ static int proc_do_submiturb(struct usb_dev_state *ps, struct usbdevfs_urb *uurb as->urb->start_frame = uurb->start_frame; as->urb->number_of_packets = number_of_packets; as->urb->stream_id = stream_id; - if (uurb->type == USBDEVFS_URB_TYPE_ISO || - ps->dev->speed == USB_SPEED_HIGH) - as->urb->interval = 1 << min(15, ep->desc.bInterval - 1); - else - as->urb->interval = ep->desc.bInterval; + + if (ep->desc.bInterval) { + if (uurb->type == USBDEVFS_URB_TYPE_ISO || + ps->dev->speed == USB_SPEED_HIGH || + ps->dev->speed >= USB_SPEED_SUPER) + as->urb->interval = 1 << + min(15, ep->desc.bInterval - 1); + else + as->urb->interval = ep->desc.bInterval; + } + as->urb->context = as; as->urb->complete = async_completed; for (totlen = u = 0; u < number_of_packets; u++) { From c0082e985fdf77b02fc9e0dac3b58504dcf11b7a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Vincent=20Stehl=C3=A9?= Date: Fri, 12 Aug 2016 15:26:30 +0200 Subject: [PATCH 301/531] ubifs: Fix assertion in layout_in_gaps() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit An assertion in layout_in_gaps() verifies that the gap_lebs pointer is below the maximum bound. When computing this maximum bound the idx_lebs count is multiplied by sizeof(int), while C pointers arithmetic does take into account the size of the pointed elements implicitly already. Remove the multiplication to fix the assertion. Fixes: 1e51764a3c2ac05a ("UBIFS: add new flash file system") Cc: Signed-off-by: Vincent Stehlé Cc: Artem Bityutskiy Signed-off-by: Artem Bityutskiy Signed-off-by: Richard Weinberger --- fs/ubifs/tnc_commit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ubifs/tnc_commit.c b/fs/ubifs/tnc_commit.c index b45345d701e7..51157da3f76e 100644 --- a/fs/ubifs/tnc_commit.c +++ b/fs/ubifs/tnc_commit.c @@ -370,7 +370,7 @@ static int layout_in_gaps(struct ubifs_info *c, int cnt) p = c->gap_lebs; do { - ubifs_assert(p < c->gap_lebs + sizeof(int) * c->lst.idx_lebs); + ubifs_assert(p < c->gap_lebs + c->lst.idx_lebs); written = layout_leb_in_gaps(c, p); if (written < 0) { err = written; From 17ce1eb0b64eb27d4f9180daae7495fa022c7b0d Mon Sep 17 00:00:00 2001 From: Richard Weinberger Date: Sun, 31 Jul 2016 21:42:23 +0200 Subject: [PATCH 302/531] ubifs: Fix xattr generic handler usage UBIFS uses full names to work with xattrs, therefore we have to use xattr_full_name() to obtain the xattr prefix as string. Cc: Cc: Andreas Gruenbacher Fixes: 2b88fc21ca ("ubifs: Switch to generic xattr handlers") Signed-off-by: Richard Weinberger Reviewed-by: Andreas Gruenbacher Tested-by: Dongsheng Yang --- fs/ubifs/xattr.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index e237811f09ce..11a004114eba 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -575,7 +575,8 @@ static int ubifs_xattr_get(const struct xattr_handler *handler, dbg_gen("xattr '%s', ino %lu ('%pd'), buf size %zd", name, inode->i_ino, dentry, size); - return __ubifs_getxattr(inode, name, buffer, size); + name = xattr_full_name(handler, name); + return __ubifs_getxattr(inode, name, buffer, size); } static int ubifs_xattr_set(const struct xattr_handler *handler, @@ -586,6 +587,8 @@ static int ubifs_xattr_set(const struct xattr_handler *handler, dbg_gen("xattr '%s', host ino %lu ('%pd'), size %zd", name, inode->i_ino, dentry, size); + name = xattr_full_name(handler, name); + if (value) return __ubifs_setxattr(inode, name, value, size, flags); else From dad2232844073295c64e9cc2d734a0ade043e0f6 Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Wed, 17 Aug 2016 18:10:11 +0300 Subject: [PATCH 303/531] um: Don't discard .text.exit section Commit e41f501d3912 ("vmlinux.lds: account for destructor sections") added '.text.exit' to EXIT_TEXT which is discarded at link time by default. This breaks compilation of UML: `.text.exit' referenced in section `.fini_array' of /usr/lib/gcc/x86_64-linux-gnu/6/../../../x86_64-linux-gnu/libc.a(sdlerror.o): defined in discarded section `.text.exit' of /usr/lib/gcc/x86_64-linux-gnu/6/../../../x86_64-linux-gnu/libc.a(sdlerror.o) Apparently UML doesn't want to discard exit text, so let's place all EXIT_TEXT sections in .exit.text. Fixes: e41f501d3912 ("vmlinux.lds: account for destructor sections") Reported-by: Stefan Traby Signed-off-by: Andrey Ryabinin Cc: Acked-by: Dmitry Vyukov Signed-off-by: Richard Weinberger --- arch/um/include/asm/common.lds.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/um/include/asm/common.lds.S b/arch/um/include/asm/common.lds.S index 1dd5bd8a8c59..133055311dce 100644 --- a/arch/um/include/asm/common.lds.S +++ b/arch/um/include/asm/common.lds.S @@ -81,7 +81,7 @@ .altinstr_replacement : { *(.altinstr_replacement) } /* .exit.text is discard at runtime, not link time, to deal with references from .altinstructions and .eh_frame */ - .exit.text : { *(.exit.text) } + .exit.text : { EXIT_TEXT } .exit.data : { *(.exit.data) } .preinit_array : { From 21c80c9fefc3db10b530a96eb0478c29eb28bf77 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Tue, 23 Aug 2016 16:36:42 -0500 Subject: [PATCH 304/531] x86/PCI: VMD: Fix infinite loop executing irq's We can't initialize the list head on deletion as this causes the node to point to itself, which causes an infinite loop if vmd_irq() happens to be servicing that node. The list initialization was trying to fix a bug from multiple calls to disable the same IRQ. Fix this instead by having the VMD driver track if the interrupt is enabled. [bhelgaas: changelog, add "Fixes"] Fixes: 97e923063575 ("x86/PCI: VMD: Initialize list item in IRQ disable") Reported-by: Grzegorz Koczot Tested-by: Miroslaw Drost Signed-off-by: Keith Busch Signed-off-by: Bjorn Helgaas Acked-by Jon Derrick: --- arch/x86/pci/vmd.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/arch/x86/pci/vmd.c b/arch/x86/pci/vmd.c index b814ca675131..7948be342ee9 100644 --- a/arch/x86/pci/vmd.c +++ b/arch/x86/pci/vmd.c @@ -41,6 +41,7 @@ static DEFINE_RAW_SPINLOCK(list_lock); * @node: list item for parent traversal. * @rcu: RCU callback item for freeing. * @irq: back pointer to parent. + * @enabled: true if driver enabled IRQ * @virq: the virtual IRQ value provided to the requesting driver. * * Every MSI/MSI-X IRQ requested for a device in a VMD domain will be mapped to @@ -50,6 +51,7 @@ struct vmd_irq { struct list_head node; struct rcu_head rcu; struct vmd_irq_list *irq; + bool enabled; unsigned int virq; }; @@ -122,7 +124,9 @@ static void vmd_irq_enable(struct irq_data *data) unsigned long flags; raw_spin_lock_irqsave(&list_lock, flags); + WARN_ON(vmdirq->enabled); list_add_tail_rcu(&vmdirq->node, &vmdirq->irq->irq_list); + vmdirq->enabled = true; raw_spin_unlock_irqrestore(&list_lock, flags); data->chip->irq_unmask(data); @@ -136,8 +140,10 @@ static void vmd_irq_disable(struct irq_data *data) data->chip->irq_mask(data); raw_spin_lock_irqsave(&list_lock, flags); - list_del_rcu(&vmdirq->node); - INIT_LIST_HEAD_RCU(&vmdirq->node); + if (vmdirq->enabled) { + list_del_rcu(&vmdirq->node); + vmdirq->enabled = false; + } raw_spin_unlock_irqrestore(&list_lock, flags); } From e83c6744e81abc93a20d0eb3b7f504a176a6126a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 23 Aug 2016 13:59:33 -0700 Subject: [PATCH 305/531] udp: fix poll() issue with zero sized packets Laura tracked poll() [and friends] regression caused by commit e6afc8ace6dd ("udp: remove headers from UDP packets before queueing") udp_poll() needs to know if there is a valid packet in receive queue, even if its payload length is 0. Change first_packet_length() to return an signed int, and use -1 as the indication of an empty queue. Fixes: e6afc8ace6dd ("udp: remove headers from UDP packets before queueing") Reported-by: Laura Abbott Signed-off-by: Eric Dumazet Tested-by: Laura Abbott Signed-off-by: David S. Miller --- net/ipv4/udp.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index e61f7cd65d08..00d18c57c83c 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1182,13 +1182,13 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset, * @sk: socket * * Drops all bad checksum frames, until a valid one is found. - * Returns the length of found skb, or 0 if none is found. + * Returns the length of found skb, or -1 if none is found. */ -static unsigned int first_packet_length(struct sock *sk) +static int first_packet_length(struct sock *sk) { struct sk_buff_head list_kill, *rcvq = &sk->sk_receive_queue; struct sk_buff *skb; - unsigned int res; + int res; __skb_queue_head_init(&list_kill); @@ -1203,7 +1203,7 @@ static unsigned int first_packet_length(struct sock *sk) __skb_unlink(skb, rcvq); __skb_queue_tail(&list_kill, skb); } - res = skb ? skb->len : 0; + res = skb ? skb->len : -1; spin_unlock_bh(&rcvq->lock); if (!skb_queue_empty(&list_kill)) { @@ -1232,7 +1232,7 @@ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg) case SIOCINQ: { - unsigned int amount = first_packet_length(sk); + int amount = max_t(int, 0, first_packet_length(sk)); return put_user(amount, (int __user *)arg); } @@ -2184,7 +2184,7 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait) /* Check for false positives due to checksum errors */ if ((mask & POLLRDNORM) && !(file->f_flags & O_NONBLOCK) && - !(sk->sk_shutdown & RCV_SHUTDOWN) && !first_packet_length(sk)) + !(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1) mask &= ~(POLLIN | POLLRDNORM); return mask; From b323431bc017e9862870cbbac004774c769ee112 Mon Sep 17 00:00:00 2001 From: Zefir Kurtisi Date: Mon, 22 Aug 2016 15:56:38 +0200 Subject: [PATCH 306/531] gianfar: prevent fragmentation in DSA environments The eTSEC register MRBLR defines the maximum space in the RX buffers and is set to 1536 by gianfar. This reasonably covers the common use case where the MTU is kept at default 1500. In that case, the largest Ethernet frame size of 1518 plus an optional GMAC_FCB_LEN of 8, and an additional padding of 8 to handle FSL_GIANFAR_DEV_HAS_TIMER totals to 1534 and nicely fit within the chosen MRBLR. Alas, if the eTSEC is attached to a DSA enabled switch, the (E)DSA header extension (4 or 8 bytes) causes every maximum sized frame to be fragmented by the hardware. This patch increases the maximum RX buffer size by 8 and rounds up to the next multiple of 64, which the hardware's defines as RX buffer granularity. Signed-off-by: Zefir Kurtisi Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/gianfar.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/freescale/gianfar.h b/drivers/net/ethernet/freescale/gianfar.h index 373fd094f2f3..6e8a9c8467b9 100644 --- a/drivers/net/ethernet/freescale/gianfar.h +++ b/drivers/net/ethernet/freescale/gianfar.h @@ -100,7 +100,8 @@ extern const char gfar_driver_version[]; #define DEFAULT_RX_LFC_THR 16 #define DEFAULT_LFC_PTVVAL 4 -#define GFAR_RXB_SIZE 1536 +/* prevent fragmenation by HW in DSA environments */ +#define GFAR_RXB_SIZE roundup(1536 + 8, 64) #define GFAR_SKBFRAG_SIZE (RXBUF_ALIGNMENT + GFAR_RXB_SIZE \ + SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) #define GFAR_RXB_TRUESIZE 2048 From 6c389fc931bcda88940c809f752ada6d7799482c Mon Sep 17 00:00:00 2001 From: Zefir Kurtisi Date: Mon, 22 Aug 2016 15:58:12 +0200 Subject: [PATCH 307/531] gianfar: fix size of scatter-gathered frames The current scatter-gather logic in gianfar is flawed, since it does not consider the eTSEC's RxBD 'Data Length' field is context depening: for the last fragment it contains the full frame size, while fragments contain the fragment size, which equals the value written to register MRBLR. This causes data corruption as soon as the hardware starts to fragment receiving frames. As a result, the size of fragmented frames is increased by (nr_frags - 1) * MRBLR We first noticed this issue working with DSA, where an ICMP request sized 1472 bytes causes the scatter-gather logic to kick in. The full Ethernet frame (1518) gets increased by DSA (4), GMAC_FCB_LEN (8), and FSL_GIANFAR_DEV_HAS_TIMER (priv->padding=8) to a total of 1538 octets, which is fragmented by the hardware and reconstructed by the driver to a 3074 octet frame. This patch fixes the problem by adjusting the size of the last fragment. It was tested by setting MRBLR to different multiples of 64, proving correct scatter-gather operation on frames with up to 9000 octets in size. Signed-off-by: Zefir Kurtisi Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/gianfar.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index d20935dc8399..4b4f5bc0e279 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -2922,17 +2922,25 @@ static bool gfar_add_rx_frag(struct gfar_rx_buff *rxb, u32 lstatus, { unsigned int size = lstatus & BD_LENGTH_MASK; struct page *page = rxb->page; + bool last = !!(lstatus & BD_LFLAG(RXBD_LAST)); /* Remove the FCS from the packet length */ - if (likely(lstatus & BD_LFLAG(RXBD_LAST))) + if (last) size -= ETH_FCS_LEN; - if (likely(first)) + if (likely(first)) { skb_put(skb, size); - else - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, - rxb->page_offset + RXBUF_ALIGNMENT, - size, GFAR_RXB_TRUESIZE); + } else { + /* the last fragments' length contains the full frame length */ + if (last) + size -= skb->len; + + /* in case the last fragment consisted only of the FCS */ + if (size > 0) + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, + rxb->page_offset + RXBUF_ALIGNMENT, + size, GFAR_RXB_TRUESIZE); + } /* try reuse page */ if (unlikely(page_count(page) != 1)) From 20a2b49fc538540819a0c552877086548cff8d8d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 22 Aug 2016 11:31:10 -0700 Subject: [PATCH 308/531] tcp: properly scale window in tcp_v[46]_reqsk_send_ack() When sending an ack in SYN_RECV state, we must scale the offered window if wscale option was negotiated and accepted. Tested: Following packetdrill test demonstrates the issue : 0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 +0 bind(3, ..., ...) = 0 +0 listen(3, 1) = 0 // Establish a connection. +0 < S 0:0(0) win 20000 +0 > S. 0:0(0) ack 1 win 28960 +0 < . 1:11(10) ack 1 win 156 // check that window is properly scaled ! +0 > . 1:1(0) ack 1 win 226 Signed-off-by: Eric Dumazet Cc: Yuchung Cheng Cc: Neal Cardwell Acked-by: Yuchung Cheng Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 8 +++++++- net/ipv6/tcp_ipv6.c | 8 +++++++- 2 files changed, 14 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 32b048e524d6..7158d4f8dae4 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -814,8 +814,14 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt; + /* RFC 7323 2.3 + * The window field (SEG.WND) of every outgoing segment, with the + * exception of segments, MUST be right-shifted by + * Rcv.Wind.Shift bits: + */ tcp_v4_send_ack(sock_net(sk), skb, seq, - tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd, + tcp_rsk(req)->rcv_nxt, + req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp, req->ts_recent, 0, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 33df8b8575cc..94f4f89d73e7 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -944,9 +944,15 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV * sk->sk_state == TCP_SYN_RECV -> for Fast Open. */ + /* RFC 7323 2.3 + * The window field (SEG.WND) of every outgoing segment, with the + * exception of segments, MUST be right-shifted by + * Rcv.Wind.Shift bits: + */ tcp_v6_send_ack(sk, skb, (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, - tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd, + tcp_rsk(req)->rcv_nxt, + req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr), 0, 0); From f64f14820e2deb5db056a05d7672ee2b1c6290e5 Mon Sep 17 00:00:00 2001 From: Xander Huff Date: Mon, 22 Aug 2016 15:57:16 -0500 Subject: [PATCH 309/531] phy: micrel: Reenable interrupts during resume for ksz9031 Like the ksz8081, the ksz9031 has the behavior where it will clear the interrupt enable bits when leaving power down. This takes advantage of the solution provided by f5aba91. Signed-off-by: Xander Huff Signed-off-by: Nathan Sullivan Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/micrel.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 053e87905b94..885ac9cbab5a 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -964,7 +964,7 @@ static struct phy_driver ksphy_driver[] = { .get_strings = kszphy_get_strings, .get_stats = kszphy_get_stats, .suspend = genphy_suspend, - .resume = genphy_resume, + .resume = kszphy_resume, }, { .phy_id = PHY_ID_KSZ8873MLL, .phy_id_mask = MICREL_PHY_ID_MASK, From 1bc261fabe866c4cdc97f52319eaa0c7ee31026e Mon Sep 17 00:00:00 2001 From: Jamie Lentin Date: Mon, 22 Aug 2016 22:47:08 +0100 Subject: [PATCH 310/531] net: mv88e6xxx: Fix ingress rate removal for mv6131 chips The PORT_RATE_CONTROL register works differently on 88e6095/6095f/6131 in comparison to 6123/61/65, and 0x0 disables. The distinction was lost Linux 4.1 --> 4.2 Signed-off-by: Jamie Lentin Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index d1d9d3cf9139..710679067594 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2656,15 +2656,19 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) return ret; } + /* Rate Control: disable ingress rate limiting. */ if (mv88e6xxx_6352_family(chip) || mv88e6xxx_6351_family(chip) || mv88e6xxx_6165_family(chip) || mv88e6xxx_6097_family(chip) || - mv88e6xxx_6185_family(chip) || mv88e6xxx_6095_family(chip) || mv88e6xxx_6320_family(chip)) { - /* Rate Control: disable ingress rate limiting. */ ret = _mv88e6xxx_reg_write(chip, REG_PORT(port), PORT_RATE_CONTROL, 0x0001); if (ret) return ret; + } else if (mv88e6xxx_6185_family(chip) || mv88e6xxx_6095_family(chip)) { + ret = _mv88e6xxx_reg_write(chip, REG_PORT(port), + PORT_RATE_CONTROL, 0x0000); + if (ret) + return ret; } /* Port Control 1: disable trunking, disable sending From 53080fe9c451e7625e71b91c384e7bef1be72b00 Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Tue, 23 Aug 2016 09:48:20 -0300 Subject: [PATCH 311/531] net: lpc_eth: Check clk_prepare_enable() error clk_prepare_enable() may fail, so we should better check its return value and propagate it in the case of failure While at it, replace __lpc_eth_clock_enable() with a plain clk_prepare_enable/clk_disable_unprepare() call in order to simplify the code. Signed-off-by: Fabio Estevam Acked-by: Vladimir Zapolskiy Signed-off-by: David S. Miller --- drivers/net/ethernet/nxp/lpc_eth.c | 20 +++++++++----------- 1 file changed, 9 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c index 4d4ecba0aad9..8e13ec84c538 100644 --- a/drivers/net/ethernet/nxp/lpc_eth.c +++ b/drivers/net/ethernet/nxp/lpc_eth.c @@ -475,14 +475,6 @@ static void __lpc_get_mac(struct netdata_local *pldat, u8 *mac) mac[5] = tmp >> 8; } -static void __lpc_eth_clock_enable(struct netdata_local *pldat, bool enable) -{ - if (enable) - clk_prepare_enable(pldat->clk); - else - clk_disable_unprepare(pldat->clk); -} - static void __lpc_params_setup(struct netdata_local *pldat) { u32 tmp; @@ -1056,7 +1048,7 @@ static int lpc_eth_close(struct net_device *ndev) writel(0, LPC_ENET_MAC2(pldat->net_base)); spin_unlock_irqrestore(&pldat->lock, flags); - __lpc_eth_clock_enable(pldat, false); + clk_disable_unprepare(pldat->clk); return 0; } @@ -1197,11 +1189,14 @@ static int lpc_eth_ioctl(struct net_device *ndev, struct ifreq *req, int cmd) static int lpc_eth_open(struct net_device *ndev) { struct netdata_local *pldat = netdev_priv(ndev); + int ret; if (netif_msg_ifup(pldat)) dev_dbg(&pldat->pdev->dev, "enabling %s\n", ndev->name); - __lpc_eth_clock_enable(pldat, true); + ret = clk_prepare_enable(pldat->clk); + if (ret) + return ret; /* Suspended PHY makes LPC ethernet core block, so resume now */ phy_resume(ndev->phydev); @@ -1320,7 +1315,9 @@ static int lpc_eth_drv_probe(struct platform_device *pdev) } /* Enable network clock */ - __lpc_eth_clock_enable(pldat, true); + ret = clk_prepare_enable(pldat->clk); + if (ret) + goto err_out_clk_put; /* Map IO space */ pldat->net_base = ioremap(res->start, resource_size(res)); @@ -1454,6 +1451,7 @@ static int lpc_eth_drv_probe(struct platform_device *pdev) iounmap(pldat->net_base); err_out_disable_clocks: clk_disable_unprepare(pldat->clk); +err_out_clk_put: clk_put(pldat->clk); err_out_free_dev: free_netdev(ndev); From a8184003c0bb1d6362c2af76c560b3caae6832cb Mon Sep 17 00:00:00 2001 From: Rabin Vincent Date: Tue, 23 Aug 2016 16:31:28 +0200 Subject: [PATCH 312/531] dwc_eth_qos: fix interrupt enable race We currently enable interrupts before we enable NAPI. If an RX interrupt hits before we enabled NAPI then the NAPI callback is never called and we leave the hardware with RX interrupts disabled, which of course leads us to never handling received packets. Fix this by moving the interrupt enable to after we've enable NAPI and the reclaim tasklet. Fixes: cd5e41234729 ("dwc_eth_qos: do phy_start before resetting hardware") Signed-off-by: Rabin Vincent Signed-off-by: Lars Persson Signed-off-by: David S. Miller --- drivers/net/ethernet/synopsys/dwc_eth_qos.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/synopsys/dwc_eth_qos.c b/drivers/net/ethernet/synopsys/dwc_eth_qos.c index 9f159a775af3..5a3941bf250f 100644 --- a/drivers/net/ethernet/synopsys/dwc_eth_qos.c +++ b/drivers/net/ethernet/synopsys/dwc_eth_qos.c @@ -1622,13 +1622,7 @@ static void dwceqos_init_hw(struct net_local *lp) DWCEQOS_MMC_CTRL_RSTONRD); dwceqos_enable_mmc_interrupt(lp); - /* Enable Interrupts */ - dwceqos_write(lp, REG_DWCEQOS_DMA_CH0_IE, - DWCEQOS_DMA_CH0_IE_NIE | - DWCEQOS_DMA_CH0_IE_RIE | DWCEQOS_DMA_CH0_IE_TIE | - DWCEQOS_DMA_CH0_IE_AIE | - DWCEQOS_DMA_CH0_IE_FBEE); - + dwceqos_write(lp, REG_DWCEQOS_DMA_CH0_IE, 0); dwceqos_write(lp, REG_DWCEQOS_MAC_IE, 0); dwceqos_write(lp, REG_DWCEQOS_MAC_CFG, DWCEQOS_MAC_CFG_IPC | @@ -1905,6 +1899,15 @@ static int dwceqos_open(struct net_device *ndev) netif_start_queue(ndev); tasklet_enable(&lp->tx_bdreclaim_tasklet); + /* Enable Interrupts -- do this only after we enable NAPI and the + * tasklet. + */ + dwceqos_write(lp, REG_DWCEQOS_DMA_CH0_IE, + DWCEQOS_DMA_CH0_IE_NIE | + DWCEQOS_DMA_CH0_IE_RIE | DWCEQOS_DMA_CH0_IE_TIE | + DWCEQOS_DMA_CH0_IE_AIE | + DWCEQOS_DMA_CH0_IE_FBEE); + return 0; } From 232cb53a45965f8789fbf0a9a1962f8c67ab1a3c Mon Sep 17 00:00:00 2001 From: Lance Richardson Date: Tue, 23 Aug 2016 11:40:52 -0400 Subject: [PATCH 313/531] sctp: fix overrun in sctp_diag_dump_one() The function sctp_diag_dump_one() currently performs a memcpy() of 64 bytes from a 16 byte field into another 16 byte field. Fix by using correct size, use sizeof to obtain correct size instead of using a hard-coded constant. Fixes: 8f840e47f190 ("sctp: add the sctp_diag.c file") Signed-off-by: Lance Richardson Reviewed-by: Xin Long Acked-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- net/sctp/sctp_diag.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/sctp/sctp_diag.c b/net/sctp/sctp_diag.c index bb691538adc8..f3508aa75815 100644 --- a/net/sctp/sctp_diag.c +++ b/net/sctp/sctp_diag.c @@ -424,11 +424,13 @@ static int sctp_diag_dump_one(struct sk_buff *in_skb, paddr.v4.sin_family = AF_INET; } else { laddr.v6.sin6_port = req->id.idiag_sport; - memcpy(&laddr.v6.sin6_addr, req->id.idiag_src, 64); + memcpy(&laddr.v6.sin6_addr, req->id.idiag_src, + sizeof(laddr.v6.sin6_addr)); laddr.v6.sin6_family = AF_INET6; paddr.v6.sin6_port = req->id.idiag_dport; - memcpy(&paddr.v6.sin6_addr, req->id.idiag_dst, 64); + memcpy(&paddr.v6.sin6_addr, req->id.idiag_dst, + sizeof(paddr.v6.sin6_addr)); paddr.v6.sin6_family = AF_INET6; } From 75d855a5e93e6f3d9b37a8719d69a5318f051453 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 23 Aug 2016 09:57:51 -0700 Subject: [PATCH 314/531] udp: get rid of SLAB_DESTROY_BY_RCU allocations After commit ca065d0cf80f ("udp: no longer use SLAB_DESTROY_BY_RCU") we do not need this special allocation mode anymore, even if it is harmless. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/udp.c | 1 - net/ipv4/udplite.c | 1 - net/ipv6/udp.c | 1 - net/ipv6/udplite.c | 1 - 4 files changed, 4 deletions(-) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 00d18c57c83c..5fdcb8d108d4 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2216,7 +2216,6 @@ struct proto udp_prot = { .sysctl_wmem = &sysctl_udp_wmem_min, .sysctl_rmem = &sysctl_udp_rmem_min, .obj_size = sizeof(struct udp_sock), - .slab_flags = SLAB_DESTROY_BY_RCU, .h.udp_table = &udp_table, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_udp_setsockopt, diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index 3b3efbda48e1..2eea073e27ef 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -55,7 +55,6 @@ struct proto udplite_prot = { .unhash = udp_lib_unhash, .get_port = udp_v4_get_port, .obj_size = sizeof(struct udp_sock), - .slab_flags = SLAB_DESTROY_BY_RCU, .h.udp_table = &udplite_table, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_udp_setsockopt, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 81e2f98b958d..19ac3a1c308d 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1460,7 +1460,6 @@ struct proto udpv6_prot = { .sysctl_wmem = &sysctl_udp_wmem_min, .sysctl_rmem = &sysctl_udp_rmem_min, .obj_size = sizeof(struct udp6_sock), - .slab_flags = SLAB_DESTROY_BY_RCU, .h.udp_table = &udp_table, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_udpv6_setsockopt, diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index 9cf097e206e9..fd6ef414899b 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -50,7 +50,6 @@ struct proto udplitev6_prot = { .unhash = udp_lib_unhash, .get_port = udp_v6_get_port, .obj_size = sizeof(struct udp6_sock), - .slab_flags = SLAB_DESTROY_BY_RCU, .h.udp_table = &udplite_table, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_udpv6_setsockopt, From 7b996243fab46092fb3a29c773c54be8152366e4 Mon Sep 17 00:00:00 2001 From: Soheil Hassas Yeganeh Date: Tue, 23 Aug 2016 18:22:33 -0400 Subject: [PATCH 315/531] tun: fix transmit timestamp support Instead of using sock_tx_timestamp, use skb_tx_timestamp to record software transmit timestamp of a packet. sock_tx_timestamp resets and overrides the tx_flags of the skb. The function is intended to be called from within the protocol layer when creating the skb, not from a device driver. This is inconsistent with other drivers and will cause issues for TCP. In TCP, we intend to sample the timestamps for the last byte for each sendmsg/sendpage. For that reason, tcp_sendmsg calls tcp_tx_timestamp only with the last skb that it generates. For example, if a 128KB message is split into two 64KB packets we want to sample the SND timestamp of the last packet. The current code in the tun driver, however, will result in sampling the SND timestamp for both packets. Also, when the last packet is split into smaller packets for retranmission (see tcp_fragment), the tun driver will record timestamps for all of the retransmitted packets and not only the last packet. Fixes: eda297729171 (tun: Support software transmit time stamping.) Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: Francis Yan Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/tun.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 9c8b5bc2b9d8..6f9df375c5d4 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -894,11 +894,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC))) goto drop; - if (skb->sk && sk_fullsock(skb->sk)) { - sock_tx_timestamp(skb->sk, skb->sk->sk_tsflags, - &skb_shinfo(skb)->tx_flags); - sw_tx_timestamp(skb); - } + skb_tx_timestamp(skb); /* Orphan the skb - required as we might hang on to it * for indefinite time. From d7226c7a4dd19929d6df4ae04698da2fcf6f875a Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 23 Aug 2016 21:05:27 -0700 Subject: [PATCH 316/531] net: diag: Fix refcnt leak in error path destroying socket inet_diag_find_one_icsk takes a reference to a socket that is not released if sock_diag_destroy returns an error. Fix by changing tcp_diag_destroy to manage the refcnt for all cases and remove the sock_put calls from tcp_abort. Fixes: c1e64e298b8ca ("net: diag: Support destroying TCP sockets") Reported-by: Lorenzo Colitti Signed-off-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 2 -- net/ipv4/tcp_diag.c | 7 ++++++- 2 files changed, 6 insertions(+), 3 deletions(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 032a96d78c99..ffbb218de520 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3193,7 +3193,6 @@ int tcp_abort(struct sock *sk, int err) local_bh_enable(); return 0; } - sock_gen_put(sk); return -EOPNOTSUPP; } @@ -3222,7 +3221,6 @@ int tcp_abort(struct sock *sk, int err) bh_unlock_sock(sk); local_bh_enable(); release_sock(sk); - sock_put(sk); return 0; } EXPORT_SYMBOL_GPL(tcp_abort); diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index 4d610934fb39..a748c74aa8b7 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -54,11 +54,16 @@ static int tcp_diag_destroy(struct sk_buff *in_skb, { struct net *net = sock_net(in_skb->sk); struct sock *sk = inet_diag_find_one_icsk(net, &tcp_hashinfo, req); + int err; if (IS_ERR(sk)) return PTR_ERR(sk); - return sock_diag_destroy(sk, ECONNABORTED); + err = sock_diag_destroy(sk, ECONNABORTED); + + sock_gen_put(sk); + + return err; } #endif From 27727df240c7cc84f2ba6047c6f18d5addfd25ef Mon Sep 17 00:00:00 2001 From: John Stultz Date: Tue, 23 Aug 2016 16:08:21 -0700 Subject: [PATCH 317/531] timekeeping: Avoid taking lock in NMI path with CONFIG_DEBUG_TIMEKEEPING When I added some extra sanity checking in timekeeping_get_ns() under CONFIG_DEBUG_TIMEKEEPING, I missed that the NMI safe __ktime_get_fast_ns() method was using timekeeping_get_ns(). Thus the locking added to the debug checks broke the NMI-safety of __ktime_get_fast_ns(). This patch open-codes the timekeeping_get_ns() logic for __ktime_get_fast_ns(), so can avoid any deadlocks in NMI. Fixes: 4ca22c2648f9 "timekeeping: Add warnings when overflows or underflows are observed" Reported-by: Steven Rostedt Reported-by: Peter Zijlstra Signed-off-by: John Stultz Cc: stable Link: http://lkml.kernel.org/r/1471993702-29148-2-git-send-email-john.stultz@linaro.org Signed-off-by: Thomas Gleixner --- kernel/time/timekeeping.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 3b65746c7f15..e07fb093f819 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -401,7 +401,10 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) do { seq = raw_read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); - now = ktime_to_ns(tkr->base) + timekeeping_get_ns(tkr); + now = ktime_to_ns(tkr->base); + + now += clocksource_delta(tkr->read(tkr->clock), + tkr->cycle_last, tkr->mask); } while (read_seqcount_retry(&tkf->seq, seq)); return now; From a4f8f6667f099036c88f231dcad4cf233652c824 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Tue, 23 Aug 2016 16:08:22 -0700 Subject: [PATCH 318/531] timekeeping: Cap array access in timekeeping_debug It was reported that hibernation could fail on the 2nd attempt, where the system hangs at hibernate() -> syscore_resume() -> i8237A_resume() -> claim_dma_lock(), because the lock has already been taken. However there is actually no other process would like to grab this lock on that problematic platform. Further investigation showed that the problem is triggered by setting /sys/power/pm_trace to 1 before the 1st hibernation. Since once pm_trace is enabled, the rtc becomes unmeaningful after suspend, and meanwhile some BIOSes would like to adjust the 'invalid' RTC (e.g, smaller than 1970) to the release date of that motherboard during POST stage, thus after resumed, it may seem that the system had a significant long sleep time which is a completely meaningless value. Then in timekeeping_resume -> tk_debug_account_sleep_time, if the bit31 of the sleep time happened to be set to 1, fls() returns 32 and we add 1 to sleep_time_bin[32], which causes an out of bounds array access and therefor memory being overwritten. As depicted by System.map: 0xffffffff81c9d080 b sleep_time_bin 0xffffffff81c9d100 B dma_spin_lock the dma_spin_lock.val is set to 1, which caused this problem. This patch adds a sanity check in tk_debug_account_sleep_time() to ensure we don't index past the sleep_time_bin array. [jstultz: Problem diagnosed and original patch by Chen Yu, I've solved the issue slightly differently, but borrowed his excelent explanation of the issue here.] Fixes: 5c83545f24ab "power: Add option to log time spent in suspend" Reported-by: Janek Kozicki Reported-by: Chen Yu Signed-off-by: John Stultz Cc: linux-pm@vger.kernel.org Cc: Peter Zijlstra Cc: Xunlei Pang Cc: "Rafael J. Wysocki" Cc: stable Cc: Zhang Rui Link: http://lkml.kernel.org/r/1471993702-29148-3-git-send-email-john.stultz@linaro.org Signed-off-by: Thomas Gleixner --- kernel/time/timekeeping_debug.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c index f6bd65236712..107310a6f36f 100644 --- a/kernel/time/timekeeping_debug.c +++ b/kernel/time/timekeeping_debug.c @@ -23,7 +23,9 @@ #include "timekeeping_internal.h" -static unsigned int sleep_time_bin[32] = {0}; +#define NUM_BINS 32 + +static unsigned int sleep_time_bin[NUM_BINS] = {0}; static int tk_debug_show_sleep_time(struct seq_file *s, void *data) { @@ -69,6 +71,9 @@ late_initcall(tk_debug_sleep_time_init); void tk_debug_account_sleep_time(struct timespec64 *t) { - sleep_time_bin[fls(t->tv_sec)]++; + /* Cap bin index so we don't overflow the array */ + int bin = min(fls(t->tv_sec), NUM_BINS-1); + + sleep_time_bin[bin]++; } From 2e63ad4bd5dd583871e6602f9d398b9322d358d9 Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Tue, 23 Aug 2016 20:07:19 +0800 Subject: [PATCH 319/531] x86/apic: Do not init irq remapping if ioapic is disabled native_smp_prepare_cpus -> default_setup_apic_routing -> enable_IR_x2apic -> irq_remapping_prepare -> intel_prepare_irq_remapping -> intel_setup_irq_remapping So IR table is setup even if "noapic" boot parameter is added. As a result we crash later when the interrupt affinity is set due to a half initialized remapping infrastructure. Prevent remap initialization when IOAPIC is disabled. Signed-off-by: Wanpeng Li Cc: Peter Zijlstra Cc: Joerg Roedel Link: http://lkml.kernel.org/r/1471954039-3942-1-git-send-email-wanpeng.li@hotmail.com Cc: stable@vger.kernel.org Signed-off-by: Thomas Gleixner --- arch/x86/kernel/apic/apic.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index cea4fc19e844..50c95af0f017 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1623,6 +1623,9 @@ void __init enable_IR_x2apic(void) unsigned long flags; int ret, ir_stat; + if (skip_ioapic_setup) + return; + ir_stat = irq_remapping_prepare(); if (ir_stat < 0 && !x2apic_supported()) return; From abaa2274811d607679e8687b4118c4922a3517ac Mon Sep 17 00:00:00 2001 From: Anisse Astier Date: Wed, 24 Aug 2016 09:14:13 +0200 Subject: [PATCH 320/531] ALSA: hda/realtek - fix headset mic detection for MSI MS-B120 MSI Cubi MS-B120 needs the same fixup as the Gigabyte BXBT-2807 for its mic to work. They both use a single 3-way jack for both mic and headset with an ALC283 codec, with the same pins used. Cc: Daniel Drake Signed-off-by: Anisse Astier Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 574b1b48996f..7100f05e651a 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -4828,7 +4828,7 @@ enum { ALC293_FIXUP_DELL1_MIC_NO_PRESENCE, ALC292_FIXUP_TPT440_DOCK, ALC292_FIXUP_TPT440, - ALC283_FIXUP_BXBT2807_MIC, + ALC283_FIXUP_HEADSET_MIC, ALC255_FIXUP_DELL_WMI_MIC_MUTE_LED, ALC282_FIXUP_ASPIRE_V5_PINS, ALC280_FIXUP_HP_GPIO4, @@ -5321,7 +5321,7 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC292_FIXUP_TPT440_DOCK, }, - [ALC283_FIXUP_BXBT2807_MIC] = { + [ALC283_FIXUP_HEADSET_MIC] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { { 0x19, 0x04a110f0 }, @@ -5651,7 +5651,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x10cf, 0x1757, "Lifebook E752", ALC269_FIXUP_LIFEBOOK_HP_PIN), SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC), SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC), - SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_BXBT2807_MIC), + SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x21b8, "Thinkpad Edge 14", ALC269_FIXUP_SKU_IGNORE), From 588deb614a0d3caa596dd8eba8c4d31eaaeb89b9 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Tue, 9 Aug 2016 11:03:56 +0100 Subject: [PATCH 321/531] MAINTAINERS: Add ARM ARCHITECTED TIMER entry The ARM architected timer driver falls under the drivers/clocksource/ catch-all in MAINTAINERS, and get_maintainers.pl doesn't suggest a number of people who should be Cc'd. The ARM architected timer is a core component of ARMv7+VE and ARMv8, and is critical to the correct operation of both architecture ports (and their respective KVM code), and patches to it should have review by knowledgeable interested parties. This patch adds a MAINTAINERS entry for the driver and its low-level arch components, such that get_maintainer.pl will always include relevant interested parties for modifications to the driver. For the timebeing, this means myself and Marc Zyngier. Signed-off-by: Mark Rutland Acked-by: Marc Zyngier Cc: Catalin Marinas Cc: Daniel Lezcano Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/1470737036-2082-1-git-send-email-mark.rutland@arm.com Signed-off-by: Thomas Gleixner --- MAINTAINERS | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 0bbe4b105c34..4705c94f6a37 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -881,6 +881,15 @@ S: Supported F: drivers/gpu/drm/arc/ F: Documentation/devicetree/bindings/display/snps,arcpgu.txt +ARM ARCHITECTED TIMER DRIVER +M: Mark Rutland +M: Marc Zyngier +L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +S: Maintained +F: arch/arm/include/asm/arch_timer.h +F: arch/arm64/include/asm/arch_timer.h +F: drivers/clocksource/arm_arch_timer.c + ARM HDLCD DRM DRIVER M: Liviu Dudau S: Supported From aa8c0f1ad7e862147f4efb32bbb71ff66eb38caa Mon Sep 17 00:00:00 2001 From: Baoyou Xie Date: Tue, 23 Aug 2016 23:19:29 +0800 Subject: [PATCH 322/531] clocksource/drivers/pxa: Fix include files for compilation We get 1 warning about global functions without a declaration in the clocksource/drivers/pxa driver when building with W=1: drivers/clocksource/pxa_timer.c:221:13: warning: no previous prototype for 'pxa_timer_nodt_init' [-Wmissing-prototypes] void __init pxa_timer_nodt_init(int irq, void __iomem *base, In fact, this function is declared in pxa.h, so this patch add missing header dependencies. Signed-off-by: Baoyou Xie Reviewed-by: Arnd Bergmann Cc: daniel.lezcano@linaro.org Cc: xie.baoyou@zte.com.cn Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/1471965569-4104-1-git-send-email-baoyou.xie@linaro.org Signed-off-by: Thomas Gleixner --- drivers/clocksource/pxa_timer.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/clocksource/pxa_timer.c b/drivers/clocksource/pxa_timer.c index 937e10b84d58..3e1cb512f3ce 100644 --- a/drivers/clocksource/pxa_timer.c +++ b/drivers/clocksource/pxa_timer.c @@ -21,6 +21,8 @@ #include #include +#include + #include #define OSMR0 0x00 /* OS Timer 0 Match Register */ From 40d9c32525cba79130612650b1abc47c0c0f19a8 Mon Sep 17 00:00:00 2001 From: Aleksandr Makarov Date: Wed, 24 Aug 2016 13:06:22 +0300 Subject: [PATCH 323/531] USB: serial: option: add WeTelecom 0x6802 and 0x6803 products These product IDs are listed in Windows driver. 0x6803 corresponds to WeTelecom WM-D300. 0x6802 name is unknown. Signed-off-by: Aleksandr Makarov Cc: stable Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index bb6a71120c03..9894e341c6ac 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -528,6 +528,8 @@ static void option_instat_callback(struct urb *urb); /* WeTelecom products */ #define WETELECOM_VENDOR_ID 0x22de #define WETELECOM_PRODUCT_WMD200 0x6801 +#define WETELECOM_PRODUCT_6802 0x6802 +#define WETELECOM_PRODUCT_WMD300 0x6803 struct option_blacklist_info { /* bitmask of interface numbers blacklisted for send_setup */ @@ -1996,6 +1998,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(INOVIA_VENDOR_ID, INOVIA_SEW858) }, { USB_DEVICE(VIATELECOM_VENDOR_ID, VIATELECOM_PRODUCT_CDS7) }, { USB_DEVICE_AND_INTERFACE_INFO(WETELECOM_VENDOR_ID, WETELECOM_PRODUCT_WMD200, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(WETELECOM_VENDOR_ID, WETELECOM_PRODUCT_6802, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(WETELECOM_VENDOR_ID, WETELECOM_PRODUCT_WMD300, 0xff, 0xff, 0xff) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); From f74bdd4cb5d0d4c3e89919e850e0bbb8789f32f9 Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Tue, 16 Aug 2016 21:49:45 +0200 Subject: [PATCH 324/531] hwrng: mxc-rnga - Fix Kconfig dependency We can directly depend on SOC_IMX31 since commit c9ee94965dce ("ARM: imx: deconstruct mxc_rnga initialization") Since that commit, CONFIG_HW_RANDOM_MXC_RNGA could not be switched on with unknown symbol ARCH_HAS_RNGA and mxc-rnga.o can't be generated with ARCH=arm make M=drivers/char/hw_random Previously, HW_RANDOM_MXC_RNGA required ARCH_HAS_RNGA which was based on IMX_HAVE_PLATFORM_MXC_RNGA && ARCH_MXC. IMX_HAVE_PLATFORM_MXC_RNGA was based on SOC_IMX31. Fixes: c9ee94965dce ("ARM: imx: deconstruct mxc_rnga initialization") Signed-off-by: Fabian Frederick Acked-by: Arnd Bergmann Signed-off-by: Herbert Xu --- drivers/char/hw_random/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/char/hw_random/Kconfig b/drivers/char/hw_random/Kconfig index 56ad5a5936a9..8c0770bf8881 100644 --- a/drivers/char/hw_random/Kconfig +++ b/drivers/char/hw_random/Kconfig @@ -244,7 +244,7 @@ config HW_RANDOM_TX4939 config HW_RANDOM_MXC_RNGA tristate "Freescale i.MX RNGA Random Number Generator" - depends on ARCH_HAS_RNGA + depends on SOC_IMX31 default HW_RANDOM ---help--- This driver provides kernel-side support for the Random Number From 10bb087ce381c812cd81a65ffd5e6f83e6399291 Mon Sep 17 00:00:00 2001 From: Giovanni Cabiddu Date: Thu, 18 Aug 2016 19:53:36 +0100 Subject: [PATCH 325/531] crypto: qat - fix aes-xts key sizes Increase value of supported key sizes for qat_aes_xts. aes-xts keys consists of keys of equal size concatenated. Fixes: def14bfaf30d ("crypto: qat - add support for ctr(aes) and xts(aes)") Cc: stable@vger.kernel.org Reported-by: Wenqian Yu Signed-off-by: Giovanni Cabiddu Signed-off-by: Herbert Xu --- drivers/crypto/qat/qat_common/qat_algs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/crypto/qat/qat_common/qat_algs.c b/drivers/crypto/qat/qat_common/qat_algs.c index 769148dbaeb3..20f35df8a01f 100644 --- a/drivers/crypto/qat/qat_common/qat_algs.c +++ b/drivers/crypto/qat/qat_common/qat_algs.c @@ -1260,8 +1260,8 @@ static struct crypto_alg qat_algs[] = { { .setkey = qat_alg_ablkcipher_xts_setkey, .decrypt = qat_alg_ablkcipher_decrypt, .encrypt = qat_alg_ablkcipher_encrypt, - .min_keysize = AES_MIN_KEY_SIZE, - .max_keysize = AES_MAX_KEY_SIZE, + .min_keysize = 2 * AES_MIN_KEY_SIZE, + .max_keysize = 2 * AES_MAX_KEY_SIZE, .ivsize = AES_BLOCK_SIZE, }, }, From 901d3d4fee83e9407d91e7178048e2fed6c91f6b Mon Sep 17 00:00:00 2001 From: Li Zhong Date: Wed, 24 Aug 2016 15:34:40 +0800 Subject: [PATCH 326/531] crypto: vmx - fix null dereference in p8_aes_xts_crypt walk.iv is not assigned a value in blkcipher_walk_init. It makes iv uninitialized. It is possibly a null value(as shown below), which is then used by aes_p8_encrypt. This patch moves iv = walk.iv after blkcipher_walk_virt, in which walk.iv is set. [17856.268050] Unable to handle kernel paging request for data at address 0x00000000 [17856.268212] Faulting instruction address: 0xd000000002ff04bc 7:mon> t [link register ] d000000002ff47b8 p8_aes_xts_crypt+0x168/0x2a0 [vmx_crypto] (938) [c000000013b77960] d000000002ff4794 p8_aes_xts_crypt+0x144/0x2a0 [vmx_crypto] (unreliable) [c000000013b77a70] c000000000544d64 skcipher_decrypt_blkcipher+0x64/0x80 [c000000013b77ac0] d000000003c0175c crypt_convert+0x53c/0x620 [dm_crypt] [c000000013b77ba0] d000000003c043fc kcryptd_crypt+0x3cc/0x440 [dm_crypt] [c000000013b77c50] c0000000000f3070 process_one_work+0x1e0/0x590 [c000000013b77ce0] c0000000000f34c8 worker_thread+0xa8/0x660 [c000000013b77d80] c0000000000fc0b0 kthread+0x110/0x130 [c000000013b77e30] c0000000000098f0 ret_from_kernel_thread+0x5c/0x6c Signed-off-by: Li Zhong Signed-off-by: Herbert Xu --- drivers/crypto/vmx/aes_xts.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/crypto/vmx/aes_xts.c b/drivers/crypto/vmx/aes_xts.c index cfb25413917c..24353ec336c5 100644 --- a/drivers/crypto/vmx/aes_xts.c +++ b/drivers/crypto/vmx/aes_xts.c @@ -129,8 +129,8 @@ static int p8_aes_xts_crypt(struct blkcipher_desc *desc, blkcipher_walk_init(&walk, dst, src, nbytes); - iv = (u8 *)walk.iv; ret = blkcipher_walk_virt(desc, &walk); + iv = walk.iv; memset(tweak, 0, AES_BLOCK_SIZE); aes_p8_encrypt(iv, tweak, &ctx->tweak_key); From 8b6a3fe8fab97716990a3abde1a01fb5a34552a3 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Wed, 24 Aug 2016 10:07:14 +0100 Subject: [PATCH 327/531] perf/core: Use this_cpu_ptr() when stopping AUX events When tearing down an AUX buf for an event via perf_mmap_close(), __perf_event_output_stop() is called on the event's CPU to ensure that trace generation is halted before the process of unmapping and freeing the buffer pages begins. The callback is performed via cpu_function_call(), which ensures that it runs with interrupts disabled and is therefore not preemptible. Unfortunately, the current code grabs the per-cpu context pointer using get_cpu_ptr(), which unnecessarily disables preemption and doesn't pair the call with put_cpu_ptr(), leading to a preempt_count() imbalance and a BUG when freeing the AUX buffer later on: WARNING: CPU: 1 PID: 2249 at kernel/events/ring_buffer.c:539 __rb_free_aux+0x10c/0x120 Modules linked in: [...] Call Trace: [] dump_stack+0x4f/0x72 [] __warn+0xc6/0xe0 [] warn_slowpath_null+0x18/0x20 [] __rb_free_aux+0x10c/0x120 [] rb_free_aux+0x13/0x20 [] perf_mmap_close+0x29e/0x2f0 [] ? perf_iterate_ctx+0xe0/0xe0 [] remove_vma+0x25/0x60 [] exit_mmap+0x106/0x140 [] mmput+0x1c/0xd0 [] do_exit+0x253/0xbf0 [] do_group_exit+0x3e/0xb0 [] get_signal+0x249/0x640 [] do_signal+0x23/0x640 [] ? _raw_write_unlock_irq+0x12/0x30 [] ? _raw_spin_unlock_irq+0x9/0x10 [] ? __schedule+0x2c6/0x710 [] exit_to_usermode_loop+0x74/0x90 [] prepare_exit_to_usermode+0x26/0x30 [] retint_user+0x8/0x10 This patch uses this_cpu_ptr() instead of get_cpu_ptr(), since preemption is already disabled by the caller. Signed-off-by: Will Deacon Reviewed-by: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Vince Weaver Fixes: 95ff4ca26c49 ("perf/core: Free AUX pages in unmap path") Link: http://lkml.kernel.org/r/20160824091905.GA16944@arm.com Signed-off-by: Ingo Molnar --- kernel/events/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 5650f5317e0c..3cfabdf7b942 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6166,7 +6166,7 @@ static int __perf_pmu_output_stop(void *info) { struct perf_event *event = info; struct pmu *pmu = event->pmu; - struct perf_cpu_context *cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); + struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); struct remote_output ro = { .rb = event->rb, }; From 87904c3e82319cf2bad8d656d79c5030dab9490e Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 12 Aug 2016 16:00:53 +0200 Subject: [PATCH 328/531] drm/tegra: dsi: Enhance runtime power management The MIPI DSI output on Tegra SoCs requires some external logic to calibrate the MIPI pads before a video signal can be transmitted. This MIPI calibration logic requires to be powered on while the MIPI pads are being used, which is currently done as part of the DSI driver's probe implementation. This is suboptimal because it will leave the MIPI calibration logic powered up even if the DSI output is never used. On Tegra114 and earlier this behaviour also causes the driver to hang while trying to power up the MIPI calibration logic because the power partition that contains the MIPI calibration logic will be powered on by the display controller at output pipeline configuration time. Thus the power up sequence for the MIPI calibration logic happens before it's power partition is guaranteed to be enabled. Fix this by splitting up the API into a request/free pair of functions that manage the runtime dependency between the DSI and the calibration modules (no registers are accessed) and a set of enable, calibrate and disable functions that program the MIPI calibration logic at points in time where the power partition is really enabled. While at it, make sure that the runtime power management also works in ganged mode, which is currently also broken. Reported-by: Jonathan Hunter Tested-by: Jonathan Hunter Signed-off-by: Thierry Reding --- drivers/gpu/drm/tegra/dsi.c | 43 ++++++++++++++++++++---- drivers/gpu/host1x/mipi.c | 65 ++++++++++++++++++------------------- include/linux/host1x.h | 2 ++ 3 files changed, 70 insertions(+), 40 deletions(-) diff --git a/drivers/gpu/drm/tegra/dsi.c b/drivers/gpu/drm/tegra/dsi.c index 3d228ad90e0f..3dea1216bafd 100644 --- a/drivers/gpu/drm/tegra/dsi.c +++ b/drivers/gpu/drm/tegra/dsi.c @@ -840,6 +840,21 @@ static const struct drm_encoder_funcs tegra_dsi_encoder_funcs = { .destroy = tegra_output_encoder_destroy, }; +static void tegra_dsi_unprepare(struct tegra_dsi *dsi) +{ + int err; + + if (dsi->slave) + tegra_dsi_unprepare(dsi->slave); + + err = tegra_mipi_disable(dsi->mipi); + if (err < 0) + dev_err(dsi->dev, "failed to disable MIPI calibration: %d\n", + err); + + pm_runtime_put(dsi->dev); +} + static void tegra_dsi_encoder_disable(struct drm_encoder *encoder) { struct tegra_output *output = encoder_to_output(encoder); @@ -876,7 +891,26 @@ static void tegra_dsi_encoder_disable(struct drm_encoder *encoder) tegra_dsi_disable(dsi); - pm_runtime_put(dsi->dev); + tegra_dsi_unprepare(dsi); +} + +static void tegra_dsi_prepare(struct tegra_dsi *dsi) +{ + int err; + + pm_runtime_get_sync(dsi->dev); + + err = tegra_mipi_enable(dsi->mipi); + if (err < 0) + dev_err(dsi->dev, "failed to enable MIPI calibration: %d\n", + err); + + err = tegra_dsi_pad_calibrate(dsi); + if (err < 0) + dev_err(dsi->dev, "MIPI calibration failed: %d\n", err); + + if (dsi->slave) + tegra_dsi_prepare(dsi->slave); } static void tegra_dsi_encoder_enable(struct drm_encoder *encoder) @@ -887,13 +921,8 @@ static void tegra_dsi_encoder_enable(struct drm_encoder *encoder) struct tegra_dsi *dsi = to_dsi(output); struct tegra_dsi_state *state; u32 value; - int err; - pm_runtime_get_sync(dsi->dev); - - err = tegra_dsi_pad_calibrate(dsi); - if (err < 0) - dev_err(dsi->dev, "MIPI calibration failed: %d\n", err); + tegra_dsi_prepare(dsi); state = tegra_dsi_get_state(dsi); diff --git a/drivers/gpu/host1x/mipi.c b/drivers/gpu/host1x/mipi.c index 52a6fd224127..e00809d996a2 100644 --- a/drivers/gpu/host1x/mipi.c +++ b/drivers/gpu/host1x/mipi.c @@ -242,20 +242,6 @@ struct tegra_mipi_device *tegra_mipi_request(struct device *device) dev->pads = args.args[0]; dev->device = device; - mutex_lock(&dev->mipi->lock); - - if (dev->mipi->usage_count++ == 0) { - err = tegra_mipi_power_up(dev->mipi); - if (err < 0) { - dev_err(dev->mipi->dev, - "failed to power up MIPI bricks: %d\n", - err); - return ERR_PTR(err); - } - } - - mutex_unlock(&dev->mipi->lock); - return dev; put: @@ -270,30 +256,43 @@ EXPORT_SYMBOL(tegra_mipi_request); void tegra_mipi_free(struct tegra_mipi_device *device) { - int err; - - mutex_lock(&device->mipi->lock); - - if (--device->mipi->usage_count == 0) { - err = tegra_mipi_power_down(device->mipi); - if (err < 0) { - /* - * Not much that can be done here, so an error message - * will have to do. - */ - dev_err(device->mipi->dev, - "failed to power down MIPI bricks: %d\n", - err); - } - } - - mutex_unlock(&device->mipi->lock); - platform_device_put(device->pdev); kfree(device); } EXPORT_SYMBOL(tegra_mipi_free); +int tegra_mipi_enable(struct tegra_mipi_device *dev) +{ + int err = 0; + + mutex_lock(&dev->mipi->lock); + + if (dev->mipi->usage_count++ == 0) + err = tegra_mipi_power_up(dev->mipi); + + mutex_unlock(&dev->mipi->lock); + + return err; + +} +EXPORT_SYMBOL(tegra_mipi_enable); + +int tegra_mipi_disable(struct tegra_mipi_device *dev) +{ + int err = 0; + + mutex_lock(&dev->mipi->lock); + + if (--dev->mipi->usage_count == 0) + err = tegra_mipi_power_down(dev->mipi); + + mutex_unlock(&dev->mipi->lock); + + return err; + +} +EXPORT_SYMBOL(tegra_mipi_disable); + static int tegra_mipi_wait(struct tegra_mipi *mipi) { unsigned long timeout = jiffies + msecs_to_jiffies(250); diff --git a/include/linux/host1x.h b/include/linux/host1x.h index d2ba7d334039..1ffbf2a8cb99 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -304,6 +304,8 @@ struct tegra_mipi_device; struct tegra_mipi_device *tegra_mipi_request(struct device *device); void tegra_mipi_free(struct tegra_mipi_device *device); +int tegra_mipi_enable(struct tegra_mipi_device *device); +int tegra_mipi_disable(struct tegra_mipi_device *device); int tegra_mipi_calibrate(struct tegra_mipi_device *device); #endif From 9b47f77a680447e0132b2cf7fb82374e014bec1c Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Wed, 24 Aug 2016 03:52:12 -0700 Subject: [PATCH 329/531] nvme: Fix nvme_get/set_features() with a NULL result pointer nvme_set_features() callers seem to expect that passing NULL as the result pointer is acceptable. Teach nvme_set_features() not to try to write to the NULL address. For symmetry, make the same change to nvme_get_features(), despite the fact that all current callers pass a valid result pointer. I assume that this bug hasn't been reported in practice because the callers that pass NULL are all in the SCSI translation layer and no one uses the relevant operations. Cc: stable@vger.kernel.org Signed-off-by: Andy Lutomirski Reviewed-by: Sagi Grimberg Signed-off-by: Jens Axboe --- drivers/nvme/host/core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 7f75d661237f..2feacc70bf61 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -611,7 +611,7 @@ int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid, ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0, NVME_QID_ANY, 0, 0); - if (ret >= 0) + if (ret >= 0 && result) *result = le32_to_cpu(cqe.result); return ret; } @@ -631,7 +631,7 @@ int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11, ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0, NVME_QID_ANY, 0, 0); - if (ret >= 0) + if (ret >= 0 && result) *result = le32_to_cpu(cqe.result); return ret; } From 4d70dca4eadf2f95abe389116ac02b8439c2d16c Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Tue, 23 Aug 2016 21:49:45 +0800 Subject: [PATCH 330/531] block: make sure a big bio is split into at most 256 bvecs After arbitrary bio size was introduced, the incoming bio may be very big. We have to split the bio into small bios so that each holds at most BIO_MAX_PAGES bvecs for safety reason, such as bio_clone(). This patch fixes the following kernel crash: > [ 172.660142] BUG: unable to handle kernel NULL pointer dereference at 0000000000000028 > [ 172.660229] IP: [] bio_trim+0xf/0x2a > [ 172.660289] PGD 7faf3e067 PUD 7f9279067 PMD 0 > [ 172.660399] Oops: 0000 [#1] SMP > [...] > [ 172.664780] Call Trace: > [ 172.664813] [] ? raid1_make_request+0x2e8/0xad7 [raid1] > [ 172.664846] [] ? blk_queue_split+0x377/0x3d4 > [ 172.664880] [] ? md_make_request+0xf6/0x1e9 [md_mod] > [ 172.664912] [] ? generic_make_request+0xb5/0x155 > [ 172.664947] [] ? prio_io+0x85/0x95 [bcache] > [ 172.664981] [] ? register_cache_set+0x355/0x8d0 [bcache] > [ 172.665016] [] ? register_bcache+0x1006/0x1174 [bcache] The issue can be reproduced by the following steps: - create one raid1 over two virtio-blk - build bcache device over the above raid1 and another cache device and bucket size is set as 2Mbytes - set cache mode as writeback - run random write over ext4 on the bcache device Fixes: 54efd50(block: make generic_make_request handle arbitrarily sized bios) Reported-by: Sebastian Roesner Reported-by: Eric Wheeler Cc: stable@vger.kernel.org (4.3+) Cc: Shaohua Li Acked-by: Kent Overstreet Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-merge.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/block/blk-merge.c b/block/blk-merge.c index 72627e3cf91e..2642e5fc8b69 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -94,8 +94,30 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, bool do_split = true; struct bio *new = NULL; const unsigned max_sectors = get_max_io_size(q, bio); + unsigned bvecs = 0; bio_for_each_segment(bv, bio, iter) { + /* + * With arbitrary bio size, the incoming bio may be very + * big. We have to split the bio into small bios so that + * each holds at most BIO_MAX_PAGES bvecs because + * bio_clone() can fail to allocate big bvecs. + * + * It should have been better to apply the limit per + * request queue in which bio_clone() is involved, + * instead of globally. The biggest blocker is the + * bio_clone() in bio bounce. + * + * If bio is splitted by this reason, we should have + * allowed to continue bios merging, but don't do + * that now for making the change simple. + * + * TODO: deal with bio bounce's bio_clone() gracefully + * and convert the global limit into per-queue limit. + */ + if (bvecs++ >= BIO_MAX_PAGES) + goto split; + /* * If the queue doesn't support SG gaps and adding this * offset would create a gap, disallow it. From 5661538749511d4c2f7d33e1e179f10c545b24d5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Wed, 17 Aug 2016 13:44:20 +0200 Subject: [PATCH 331/531] drm/amdgpu: fix lru size grouping v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Adding a BO can make it the insertion point for larger sizes as well. v2: add a comment about the guard structure. Signed-off-by: Christian König Reviewed-by: Alex Deucher Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 2 ++ drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 8 ++++++++ 2 files changed, 10 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 8c704c86597b..700c56baf2de 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -426,6 +426,8 @@ struct amdgpu_mman { /* custom LRU management */ struct amdgpu_mman_lru log2_size[AMDGPU_TTM_LRU_SIZE]; + /* guard for log2_size array, don't add anything in between */ + struct amdgpu_mman_lru guard; }; int amdgpu_copy_buffer(struct amdgpu_ring *ring, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 141bfcabd19c..716f2afeb6a9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -950,6 +950,8 @@ static struct list_head *amdgpu_ttm_lru_tail(struct ttm_buffer_object *tbo) struct list_head *res = lru->lru[tbo->mem.mem_type]; lru->lru[tbo->mem.mem_type] = &tbo->lru; + while ((++lru)->lru[tbo->mem.mem_type] == res) + lru->lru[tbo->mem.mem_type] = &tbo->lru; return res; } @@ -960,6 +962,8 @@ static struct list_head *amdgpu_ttm_swap_lru_tail(struct ttm_buffer_object *tbo) struct list_head *res = lru->swap_lru; lru->swap_lru = &tbo->swap; + while ((++lru)->swap_lru == res) + lru->swap_lru = &tbo->swap; return res; } @@ -1011,6 +1015,10 @@ int amdgpu_ttm_init(struct amdgpu_device *adev) lru->swap_lru = &adev->mman.bdev.glob->swap_lru; } + for (j = 0; j < TTM_NUM_MEM_TYPES; ++j) + adev->mman.guard.lru[j] = NULL; + adev->mman.guard.swap_lru = NULL; + adev->mman.initialized = true; r = ttm_bo_init_mm(&adev->mman.bdev, TTM_PL_VRAM, adev->mc.real_vram_size >> PAGE_SHIFT); From 9afee94939e3eda4c8bf239f7727cb56e158c976 Mon Sep 17 00:00:00 2001 From: Frederic Dalleau Date: Tue, 23 Aug 2016 07:59:19 +0200 Subject: [PATCH 332/531] Bluetooth: Fix memory leak at end of hci requests MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In hci_req_sync_complete the event skb is referenced in hdev->req_skb. It is used (via hci_req_run_skb) from either __hci_cmd_sync_ev which will pass the skb to the caller, or __hci_req_sync which leaks. unreferenced object 0xffff880005339a00 (size 256): comm "kworker/u3:1", pid 1011, jiffies 4294671976 (age 107.389s) backtrace: [] kmemleak_alloc+0x49/0xa0 [] kmem_cache_alloc+0x128/0x180 [] skb_clone+0x4f/0xa0 [] hci_event_packet+0xc1/0x3290 [] hci_rx_work+0x18b/0x360 [] process_one_work+0x14a/0x440 [] worker_thread+0x43/0x4d0 [] kthread+0xc4/0xe0 [] ret_from_fork+0x1f/0x40 [] 0xffffffffffffffff Signed-off-by: Frédéric Dalleau Signed-off-by: Marcel Holtmann --- net/bluetooth/hci_request.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index c045b3c54768..b0e23dfc5c34 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -262,6 +262,8 @@ int __hci_req_sync(struct hci_dev *hdev, int (*func)(struct hci_request *req, break; } + kfree_skb(hdev->req_skb); + hdev->req_skb = NULL; hdev->req_status = hdev->req_result = 0; BT_DBG("%s end: err %d", hdev->name, err); From dbb50887c8f619fc5c3489783ebc3122bc134a31 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 27 Jul 2016 11:40:14 -0700 Subject: [PATCH 333/531] Bluetooth: split sk_filter in l2cap_sock_recv_cb During an audit for sk_filter(), we found that rx_busy_skb handling in l2cap_sock_recv_cb() and l2cap_sock_recvmsg() looks not quite as intended. The assumption from commit e328140fdacb ("Bluetooth: Use event-driven approach for handling ERTM receive buffer") is that errors returned from sock_queue_rcv_skb() are due to receive buffer shortage. However, nothing should prevent doing a setsockopt() with SO_ATTACH_FILTER on the socket, that could drop some of the incoming skbs when handled in sock_queue_rcv_skb(). In that case sock_queue_rcv_skb() will return with -EPERM, propagated from sk_filter() and if in L2CAP_MODE_ERTM mode, wrong assumption was that we failed due to receive buffer being full. From that point onwards, due to the to-be-dropped skb being held in rx_busy_skb, we cannot make any forward progress as rx_busy_skb is never cleared from l2cap_sock_recvmsg(), due to the filter drop verdict over and over coming from sk_filter(). Meanwhile, in l2cap_sock_recv_cb() all new incoming skbs are being dropped due to rx_busy_skb being occupied. Instead, just use __sock_queue_rcv_skb() where an error really tells that there's a receive buffer issue. Split the sk_filter() and enable it for non-segmented modes at queuing time since at this point in time the skb has already been through the ERTM state machine and it has been acked, so dropping is not allowed. Instead, for ERTM and streaming mode, call sk_filter() in l2cap_data_rcv() so the packet can be dropped before the state machine sees it. Fixes: e328140fdacb ("Bluetooth: Use event-driven approach for handling ERTM receive buffer") Signed-off-by: Daniel Borkmann Signed-off-by: Mat Martineau Acked-by: Willem de Bruijn Signed-off-by: Marcel Holtmann --- net/bluetooth/l2cap_core.c | 8 ++++++++ net/bluetooth/l2cap_sock.c | 14 ++++++++++++-- 2 files changed, 20 insertions(+), 2 deletions(-) diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 54ceb1f2cc9a..d4cad29b033f 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -32,6 +32,7 @@ #include #include +#include #include #include @@ -5835,6 +5836,9 @@ static int l2cap_reassemble_sdu(struct l2cap_chan *chan, struct sk_buff *skb, if (chan->sdu) break; + if (!pskb_may_pull(skb, L2CAP_SDULEN_SIZE)) + break; + chan->sdu_len = get_unaligned_le16(skb->data); skb_pull(skb, L2CAP_SDULEN_SIZE); @@ -6610,6 +6614,10 @@ static int l2cap_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb) goto drop; } + if ((chan->mode == L2CAP_MODE_ERTM || + chan->mode == L2CAP_MODE_STREAMING) && sk_filter(chan->data, skb)) + goto drop; + if (!control->sframe) { int err; diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 1842141baedb..a8ba752732c9 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1019,7 +1019,7 @@ static int l2cap_sock_recvmsg(struct socket *sock, struct msghdr *msg, goto done; if (pi->rx_busy_skb) { - if (!sock_queue_rcv_skb(sk, pi->rx_busy_skb)) + if (!__sock_queue_rcv_skb(sk, pi->rx_busy_skb)) pi->rx_busy_skb = NULL; else goto done; @@ -1270,7 +1270,17 @@ static int l2cap_sock_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb) goto done; } - err = sock_queue_rcv_skb(sk, skb); + if (chan->mode != L2CAP_MODE_ERTM && + chan->mode != L2CAP_MODE_STREAMING) { + /* Even if no filter is attached, we could potentially + * get errors from security modules, etc. + */ + err = sk_filter(sk, skb); + if (err) + goto done; + } + + err = __sock_queue_rcv_skb(sk, skb); /* For ERTM, handle one skb that doesn't fit into the recv * buffer. This is important to do because the data frames From 5dfd5e5e3bc68ab3912acc712c8180942094fc69 Mon Sep 17 00:00:00 2001 From: Shiraz Saleem Date: Mon, 22 Aug 2016 18:16:37 -0500 Subject: [PATCH 334/531] i40iw: Add missing NULL check for MPA private data Add NULL check for pdata and pdata->addr before the memcpy in i40iw_form_cm_frame(). This fixes a NULL pointer de-reference which occurs when the MPA private data pointer is NULL. Also only copy pdata->size bytes in the memcpy to prevent reading past the length of the private data buffer provided by upper layer. Fixes: f27b4746f378 ("i40iw: add connection management code") Reported-by: Stefan Assmann Signed-off-by: Mustafa Ismail Signed-off-by: Shiraz Saleem Signed-off-by: Doug Ledford --- drivers/infiniband/hw/i40iw/i40iw_cm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.c b/drivers/infiniband/hw/i40iw/i40iw_cm.c index 5026dc79978a..64343985e0b7 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_cm.c +++ b/drivers/infiniband/hw/i40iw/i40iw_cm.c @@ -535,8 +535,8 @@ static struct i40iw_puda_buf *i40iw_form_cm_frame(struct i40iw_cm_node *cm_node, buf += hdr_len; } - if (pd_len) - memcpy(buf, pdata->addr, pd_len); + if (pdata && pdata->addr) + memcpy(buf, pdata->addr, pdata->size); atomic_set(&sqbuf->refcount, 1); From 7eaf8313b1cfe93417a22bdc3f7380cac2a3dc6d Mon Sep 17 00:00:00 2001 From: Mustafa Ismail Date: Mon, 22 Aug 2016 19:01:47 -0500 Subject: [PATCH 335/531] i40iw: Do not set self-referencing pointer to NULL after kfree In i40iw_free_virt_mem(), do not set mem->va to NULL after freeing it as mem->va is a self-referencing pointer to mem. Fixes: 4e9042e647ff ("i40iw: add hw and utils files") Reported-by: Stefan Assmann Signed-off-by: Mustafa Ismail Signed-off-by: Shiraz Saleem Signed-off-by: Doug Ledford --- drivers/infiniband/hw/i40iw/i40iw_utils.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/i40iw/i40iw_utils.c b/drivers/infiniband/hw/i40iw/i40iw_utils.c index 0e8db0a35141..6fd043b1d714 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_utils.c +++ b/drivers/infiniband/hw/i40iw/i40iw_utils.c @@ -673,8 +673,11 @@ enum i40iw_status_code i40iw_free_virt_mem(struct i40iw_hw *hw, { if (!mem) return I40IW_ERR_PARAM; + /* + * mem->va points to the parent of mem, so both mem and mem->va + * can not be touched once mem->va is freed + */ kfree(mem->va); - mem->va = NULL; return 0; } From 82d200cc6fc817dbf049b67e5e3215eab427e846 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Tue, 23 Aug 2016 21:16:26 +0100 Subject: [PATCH 336/531] IB/mlx5: Remove superfluous include of io-mapping.h This file does not use any structs or functions defined by io-mapping.h (nor does it directly use iomap, ioremap, iounamp or friends). Remove it to simplify verification of changes to io-mapping.h The include existed since its inception in commit e126ba97dba9edeb6fafa3665b5f8497fc9cdf8c Author: Eli Cohen Date: Sun Jul 7 17:25:49 2013 +0300 mlx5: Add driver for Mellanox Connect-IB adapters which looks like a copy across from the Mellanox ethernet driver. Signed-off-by: Chris Wilson Cc: Eli Cohen Cc: Jack Morgenstein Cc: Or Gerlitz Cc: Matan Barak Cc: Leon Romanovsky Cc: Doug Ledford Cc: Sean Hefty Cc: Hal Rosenstock Cc: linux-rdma@vger.kernel.org Reviewed-by: Leon Romanovsky Reviewed-by: Laurence Oberman Tested-by: Laurence Oberman Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/main.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index a84bb766fc62..1b4094baa2de 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -37,7 +37,6 @@ #include #include #include -#include #if defined(CONFIG_X86) #include #endif From d41d0910d97f05be987d2d60de7e8685c108963b Mon Sep 17 00:00:00 2001 From: Mustafa Ismail Date: Tue, 23 Aug 2016 16:50:13 -0500 Subject: [PATCH 337/531] i40iw: Fix double free of allocated_buffer Memory allocated for iwqp; iwqp->allocated_buffer is freed twice in the create_qp error path. Correct this by having it freed only once in i40iw_free_qp_resources(). Fixes: d37498417947 ("i40iw: add files for iwarp interface") Signed-off-by: Mustafa Ismail Signed-off-by: Shiraz Saleem Signed-off-by: Doug Ledford --- drivers/infiniband/hw/i40iw/i40iw_verbs.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c index 2360338877bf..722e5af1e3d8 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c @@ -794,7 +794,6 @@ static struct ib_qp *i40iw_create_qp(struct ib_pd *ibpd, return &iwqp->ibqp; error: i40iw_free_qp_resources(iwdev, iwqp, qp_num); - kfree(mem); return ERR_PTR(err_code); } From 433c58139f6a7d59824aadd23d6c9cac1d4e6100 Mon Sep 17 00:00:00 2001 From: Mustafa Ismail Date: Tue, 23 Aug 2016 17:24:56 -0500 Subject: [PATCH 338/531] i40iw: Avoid writing to freed memory iwpbl->iwmr points to the structure that contains iwpbl, which is iwmr. Setting this to NULL would result in writing to freed memory. So just free iwmr, and return. Fixes: d37498417947 ("i40iw: add files for iwarp interface") Reported-by: Stefan Assmann Signed-off-by: Mustafa Ismail Signed-off-by: Shiraz Saleem Signed-off-by: Doug Ledford --- drivers/infiniband/hw/i40iw/i40iw_verbs.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c index 722e5af1e3d8..6329c971c22f 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c @@ -1925,8 +1925,7 @@ static int i40iw_dereg_mr(struct ib_mr *ib_mr) } if (iwpbl->pbl_allocated) i40iw_free_pble(iwdev->pble_rsrc, palloc); - kfree(iwpbl->iwmr); - iwpbl->iwmr = NULL; + kfree(iwmr); return 0; } From 3c199b4523c92dc5df027eeeffa657e2ccf453ab Mon Sep 17 00:00:00 2001 From: Selvin Xavier Date: Wed, 24 Aug 2016 01:17:41 -0400 Subject: [PATCH 339/531] RDMA/ocrdma: Fix the max_sge reported from FW Current driver is reporting wrong values for max_sge and max_sge_rd in query_device. This breaks the nfs rdma and iser in some device profiles. Fixing the driver to report correct values from FW. Signed-off-by: Selvin Xavier Signed-off-by: Devesh Sharma Signed-off-by: Doug Ledford --- drivers/infiniband/hw/ocrdma/ocrdma_hw.c | 14 +++++++------- drivers/infiniband/hw/ocrdma/ocrdma_sli.h | 12 ++++++++---- drivers/infiniband/hw/ocrdma/ocrdma_verbs.c | 4 ++-- 3 files changed, 17 insertions(+), 13 deletions(-) diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c index 16740dcb876b..67fc0b6857e1 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c @@ -1156,18 +1156,18 @@ static void ocrdma_get_attr(struct ocrdma_dev *dev, attr->max_srq = (rsp->max_srq_rpir_qps & OCRDMA_MBX_QUERY_CFG_MAX_SRQ_MASK) >> OCRDMA_MBX_QUERY_CFG_MAX_SRQ_OFFSET; - attr->max_send_sge = ((rsp->max_write_send_sge & + attr->max_send_sge = ((rsp->max_recv_send_sge & OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_MASK) >> OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_SHIFT); - attr->max_recv_sge = (rsp->max_write_send_sge & - OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_MASK) >> - OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_SHIFT; + attr->max_recv_sge = (rsp->max_recv_send_sge & + OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_MASK) >> + OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_SHIFT; attr->max_srq_sge = (rsp->max_srq_rqe_sge & OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_MASK) >> OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_OFFSET; - attr->max_rdma_sge = (rsp->max_write_send_sge & - OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_MASK) >> - OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_SHIFT; + attr->max_rdma_sge = (rsp->max_wr_rd_sge & + OCRDMA_MBX_QUERY_CFG_MAX_RD_SGE_MASK) >> + OCRDMA_MBX_QUERY_CFG_MAX_RD_SGE_SHIFT; attr->max_ord_per_qp = (rsp->max_ird_ord_per_qp & OCRDMA_MBX_QUERY_CFG_MAX_ORD_PER_QP_MASK) >> OCRDMA_MBX_QUERY_CFG_MAX_ORD_PER_QP_SHIFT; diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h index 0efc9662c6d8..37df4481bb8f 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h +++ b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h @@ -554,9 +554,9 @@ enum { OCRDMA_MBX_QUERY_CFG_L3_TYPE_MASK = 0x18, OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_SHIFT = 0, OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_MASK = 0xFFFF, - OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_SHIFT = 16, - OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_MASK = 0xFFFF << - OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_SHIFT, + OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_SHIFT = 16, + OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_MASK = 0xFFFF << + OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_SHIFT, OCRDMA_MBX_QUERY_CFG_MAX_ORD_PER_QP_SHIFT = 0, OCRDMA_MBX_QUERY_CFG_MAX_ORD_PER_QP_MASK = 0xFFFF, @@ -612,6 +612,8 @@ enum { OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_OFFSET = 0, OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_MASK = 0xFFFF << OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_OFFSET, + OCRDMA_MBX_QUERY_CFG_MAX_RD_SGE_SHIFT = 0, + OCRDMA_MBX_QUERY_CFG_MAX_RD_SGE_MASK = 0xFFFF, }; struct ocrdma_mbx_query_config { @@ -619,7 +621,7 @@ struct ocrdma_mbx_query_config { struct ocrdma_mbx_rsp rsp; u32 qp_srq_cq_ird_ord; u32 max_pd_ca_ack_delay; - u32 max_write_send_sge; + u32 max_recv_send_sge; u32 max_ird_ord_per_qp; u32 max_shared_ird_ord; u32 max_mr; @@ -639,6 +641,8 @@ struct ocrdma_mbx_query_config { u32 max_wqes_rqes_per_q; u32 max_cq_cqes_per_cq; u32 max_srq_rqe_sge; + u32 max_wr_rd_sge; + u32 ird_pgsz_num_pages; }; struct ocrdma_fw_ver_rsp { diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c index b1a3d91fe8b9..0aa854737e74 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c @@ -125,8 +125,8 @@ int ocrdma_query_device(struct ib_device *ibdev, struct ib_device_attr *attr, IB_DEVICE_SYS_IMAGE_GUID | IB_DEVICE_LOCAL_DMA_LKEY | IB_DEVICE_MEM_MGT_EXTENSIONS; - attr->max_sge = dev->attr.max_send_sge; - attr->max_sge_rd = attr->max_sge; + attr->max_sge = min(dev->attr.max_send_sge, dev->attr.max_recv_sge); + attr->max_sge_rd = dev->attr.max_rdma_sge; attr->max_cq = dev->attr.max_cq; attr->max_cqe = dev->attr.max_cqe; attr->max_mr = dev->attr.max_mr; From f888f58795b640442165e60a6fa93e8e623d01a5 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 24 Aug 2016 11:18:51 +0200 Subject: [PATCH 340/531] mlxsw: spectrum: Add missing flood to router port In case we have a layer 3 interface on top of a bridge (VLAN / FID RIF), then we should flood the following packet types to the router: * Broadcast: If DIP is the broadcast address of the interface, then we need to be able to get it to CPU by trapping it following route lookup. * Reserved IP multicast (224.0.0.X): Some control packets (e.g. OSPF) use this range and are trapped in the router block. Fixes: 99f44bb3527b ("mlxsw: spectrum: Enable L3 interfaces on top of bridge devices") Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/port.h | 1 + .../net/ethernet/mellanox/mlxsw/spectrum.c | 43 ++++++++++++++++++- 2 files changed, 43 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/port.h b/drivers/net/ethernet/mellanox/mlxsw/port.h index f33b997f2b61..af371a82c35b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/port.h +++ b/drivers/net/ethernet/mellanox/mlxsw/port.h @@ -56,6 +56,7 @@ #define MLXSW_PORT_PHY_BITS_MASK (MLXSW_PORT_MAX_PHY_PORTS - 1) #define MLXSW_PORT_CPU_PORT 0x0 +#define MLXSW_PORT_ROUTER_PORT (MLXSW_PORT_MAX_PHY_PORTS + 2) #define MLXSW_PORT_DONT_CARE (MLXSW_PORT_MAX_PORTS) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 1f8168906811..7291f2c4b0c7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -3324,6 +3324,39 @@ static struct mlxsw_sp_fid *mlxsw_sp_bridge_fid_get(struct mlxsw_sp *mlxsw_sp, return mlxsw_sp_fid_find(mlxsw_sp, fid); } +static enum mlxsw_flood_table_type mlxsw_sp_flood_table_type_get(u16 fid) +{ + return mlxsw_sp_fid_is_vfid(fid) ? MLXSW_REG_SFGC_TABLE_TYPE_FID : + MLXSW_REG_SFGC_TABLE_TYPE_FID_OFFEST; +} + +static u16 mlxsw_sp_flood_table_index_get(u16 fid) +{ + return mlxsw_sp_fid_is_vfid(fid) ? mlxsw_sp_fid_to_vfid(fid) : fid; +} + +static int mlxsw_sp_router_port_flood_set(struct mlxsw_sp *mlxsw_sp, u16 fid, + bool set) +{ + enum mlxsw_flood_table_type table_type; + char *sftr_pl; + u16 index; + int err; + + sftr_pl = kmalloc(MLXSW_REG_SFTR_LEN, GFP_KERNEL); + if (!sftr_pl) + return -ENOMEM; + + table_type = mlxsw_sp_flood_table_type_get(fid); + index = mlxsw_sp_flood_table_index_get(fid); + mlxsw_reg_sftr_pack(sftr_pl, MLXSW_SP_FLOOD_TABLE_BM, index, table_type, + 1, MLXSW_PORT_ROUTER_PORT, set); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sftr), sftr_pl); + + kfree(sftr_pl); + return err; +} + static enum mlxsw_reg_ritr_if_type mlxsw_sp_rif_type_get(u16 fid) { if (mlxsw_sp_fid_is_vfid(fid)) @@ -3360,10 +3393,14 @@ static int mlxsw_sp_rif_bridge_create(struct mlxsw_sp *mlxsw_sp, if (rif == MLXSW_SP_RIF_MAX) return -ERANGE; - err = mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, true); + err = mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, true); if (err) return err; + err = mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, true); + if (err) + goto err_rif_bridge_op; + err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, true); if (err) goto err_rif_fdb_op; @@ -3385,6 +3422,8 @@ static int mlxsw_sp_rif_bridge_create(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false); err_rif_fdb_op: mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, false); +err_rif_bridge_op: + mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false); return err; } @@ -3404,6 +3443,8 @@ void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, false); + mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false); + netdev_dbg(l3_dev, "RIF=%d destroyed\n", rif); } From 51af96b53469f3b8cfcfe0504d0ff87239175b78 Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Wed, 24 Aug 2016 11:18:52 +0200 Subject: [PATCH 341/531] mlxsw: router: Enable neighbors to be created on stacked devices Make the function mlxsw_router_neigh_construct search the rif according to the neighbour dev other than the dev that was passed to the ndo, thus allowing creating neigbhours upon stacked devices. Fixes: 6cf3c971dc84 ("mlxsw: spectrum_router: Add private neigh table") Signed-off-by: Yotam Gigi Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 90bb93b037ec..917ddd1e422f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -657,7 +657,7 @@ int mlxsw_sp_router_neigh_construct(struct net_device *dev, return 0; } - r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); + r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, n->dev); if (WARN_ON(!r)) return -EINVAL; From 9a035a40f7f3f6708b79224b86c5777a3334f7ea Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Mon, 15 Aug 2016 09:02:38 -0600 Subject: [PATCH 342/531] xenbus: don't look up transaction IDs for ordinary writes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This should really only be done for XS_TRANSACTION_END messages, or else at least some of the xenstore-* tools don't work anymore. Fixes: 0beef634b8 ("xenbus: don't BUG() on user mode induced condition") Reported-by: Richard Schütz Cc: Signed-off-by: Jan Beulich Tested-by: Richard Schütz Signed-off-by: David Vrabel --- drivers/xen/xenbus/xenbus_dev_frontend.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index 7487971f9f78..c1010f018bd8 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -316,7 +316,7 @@ static int xenbus_write_transaction(unsigned msg_type, rc = -ENOMEM; goto out; } - } else { + } else if (msg_type == XS_TRANSACTION_END) { list_for_each_entry(trans, &u->transactions, list) if (trans->handle.id == u->u.msg.tx_id) break; From 55467dea2967259f21f4f854fc99d39cc5fea60e Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Fri, 29 Jul 2016 11:06:48 +0200 Subject: [PATCH 343/531] xen: change the type of xen_vcpu_id to uint32_t We pass xen_vcpu_id mapping information to hypercalls which require uint32_t type so it would be cleaner to have it as uint32_t. The initializer to -1 can be dropped as we always do the mapping before using it and we never check the 'not set' value anyway. Signed-off-by: Vitaly Kuznetsov Signed-off-by: David Vrabel --- arch/arm/xen/enlighten.c | 2 +- arch/x86/xen/enlighten.c | 2 +- include/xen/xen-ops.h | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index b0b82f5ea338..3d2cef6488ea 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -50,7 +50,7 @@ DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu); static struct vcpu_info __percpu *xen_vcpu_info; /* Linux <-> Xen vCPU id mapping */ -DEFINE_PER_CPU(int, xen_vcpu_id) = -1; +DEFINE_PER_CPU(uint32_t, xen_vcpu_id); EXPORT_PER_CPU_SYMBOL(xen_vcpu_id); /* These are unused until we support booting "pre-ballooned" */ diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 8ffb089b19a5..b86ebb1a9a7f 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -118,7 +118,7 @@ DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu); DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info); /* Linux <-> Xen vCPU id mapping */ -DEFINE_PER_CPU(int, xen_vcpu_id) = -1; +DEFINE_PER_CPU(uint32_t, xen_vcpu_id); EXPORT_PER_CPU_SYMBOL(xen_vcpu_id); enum xen_domain_type xen_domain_type = XEN_NATIVE; diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index 9a37c541822f..b5486e648607 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -9,8 +9,8 @@ DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu); -DECLARE_PER_CPU(int, xen_vcpu_id); -static inline int xen_vcpu_nr(int cpu) +DECLARE_PER_CPU(uint32_t, xen_vcpu_id); +static inline uint32_t xen_vcpu_nr(int cpu) { return per_cpu(xen_vcpu_id, cpu); } From 486b0f7bcd64be027535811ef44195bc1027fbd3 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Fri, 19 Aug 2016 15:34:01 -0700 Subject: [PATCH 344/531] r5cache: set MD_JOURNAL_CLEAN correctly Currently, the code sets MD_JOURNAL_CLEAN when the array has MD_FEATURE_JOURNAL and the recovery_cp is MaxSector. The array will be MD_JOURNAL_CLEAN even if the journal device is missing. With this patch, the MD_JOURNAL_CLEAN is only set when the journal device presents. Signed-off-by: Song Liu Signed-off-by: Shaohua Li --- drivers/md/md.c | 5 +---- drivers/md/raid5.c | 13 ++++++++----- 2 files changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index cc25cbcf10b2..4f6cf3b849e3 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -1604,11 +1604,8 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev) mddev->new_chunk_sectors = mddev->chunk_sectors; } - if (le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL) { + if (le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL) set_bit(MD_HAS_JOURNAL, &mddev->flags); - if (mddev->recovery_cp == MaxSector) - set_bit(MD_JOURNAL_CLEAN, &mddev->flags); - } } else if (mddev->pers == NULL) { /* Insist of good event counter while assembling, except for * spares (which don't need an event count) */ diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 4f8f5242ea3b..2119e094dfb3 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -6840,11 +6840,14 @@ static int raid5_run(struct mddev *mddev) if (IS_ERR(conf)) return PTR_ERR(conf); - if (test_bit(MD_HAS_JOURNAL, &mddev->flags) && !journal_dev) { - printk(KERN_ERR "md/raid:%s: journal disk is missing, force array readonly\n", - mdname(mddev)); - mddev->ro = 1; - set_disk_ro(mddev->gendisk, 1); + if (test_bit(MD_HAS_JOURNAL, &mddev->flags)) { + if (!journal_dev) { + pr_err("md/raid:%s: journal disk is missing, force array readonly\n", + mdname(mddev)); + mddev->ro = 1; + set_disk_ro(mddev->gendisk, 1); + } else if (mddev->recovery_cp == MaxSector) + set_bit(MD_JOURNAL_CLEAN, &mddev->flags); } conf->min_offset_diff = min_offset_diff; From 0f6187dbe542d71ace8ba0908954b0f4f8a30a1e Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Sun, 21 Aug 2016 14:42:25 +0000 Subject: [PATCH 345/531] md-cluster: fix error return code in join() Fix to return error code -ENOMEM from the lockres_init() error handling case instead of 0, as done elsewhere in this function. Signed-off-by: Wei Yongjun Signed-off-by: Shaohua Li --- drivers/md/md-cluster.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c index 41573f1f626f..34a840d9df76 100644 --- a/drivers/md/md-cluster.c +++ b/drivers/md/md-cluster.c @@ -834,8 +834,10 @@ static int join(struct mddev *mddev, int nodes) goto err; } cinfo->ack_lockres = lockres_init(mddev, "ack", ack_bast, 0); - if (!cinfo->ack_lockres) + if (!cinfo->ack_lockres) { + ret = -ENOMEM; goto err; + } /* get sync CR lock on ACK. */ if (dlm_lock_sync(cinfo->ack_lockres, DLM_LOCK_CR)) pr_err("md-cluster: failed to get a sync CR lock on ACK!(%d)\n", @@ -849,8 +851,10 @@ static int join(struct mddev *mddev, int nodes) pr_info("md-cluster: Joined cluster %s slot %d\n", str, cinfo->slot_number); snprintf(str, 64, "bitmap%04d", cinfo->slot_number - 1); cinfo->bitmap_lockres = lockres_init(mddev, str, NULL, 1); - if (!cinfo->bitmap_lockres) + if (!cinfo->bitmap_lockres) { + ret = -ENOMEM; goto err; + } if (dlm_lock_sync(cinfo->bitmap_lockres, DLM_LOCK_PW)) { pr_err("Failed to get bitmap lock\n"); ret = -EINVAL; @@ -858,8 +862,10 @@ static int join(struct mddev *mddev, int nodes) } cinfo->resync_lockres = lockres_init(mddev, "resync", NULL, 0); - if (!cinfo->resync_lockres) + if (!cinfo->resync_lockres) { + ret = -ENOMEM; goto err; + } return 0; err: From 27028626b4b9022dcac23688e09ea43b36e1183c Mon Sep 17 00:00:00 2001 From: Tomasz Majchrzak Date: Tue, 23 Aug 2016 10:53:57 +0200 Subject: [PATCH 346/531] raid10: record correct address of bad block For failed write request record block address on a device, not block address in an array. Signed-off-by: Tomasz Majchrzak Signed-off-by: Shaohua Li --- drivers/md/raid10.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 1a632a8c8005..4589866257d5 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -2465,20 +2465,21 @@ static int narrow_write_error(struct r10bio *r10_bio, int i) while (sect_to_write) { struct bio *wbio; + sector_t wsector; if (sectors > sect_to_write) sectors = sect_to_write; /* Write at 'sector' for 'sectors' */ wbio = bio_clone_mddev(bio, GFP_NOIO, mddev); bio_trim(wbio, sector - bio->bi_iter.bi_sector, sectors); - wbio->bi_iter.bi_sector = (r10_bio->devs[i].addr+ - choose_data_offset(r10_bio, rdev) + - (sector - r10_bio->sector)); + wsector = r10_bio->devs[i].addr + (sector - r10_bio->sector); + wbio->bi_iter.bi_sector = wsector + + choose_data_offset(r10_bio, rdev); wbio->bi_bdev = rdev->bdev; bio_set_op_attrs(wbio, REQ_OP_WRITE, 0); if (submit_bio_wait(wbio) < 0) /* Failure! */ - ok = rdev_set_badblocks(rdev, sector, + ok = rdev_set_badblocks(rdev, wsector, sectors, 0) && ok; From 5f9d1fde7d54a5d5fd8cccbee9c9c31474fcdcf2 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Mon, 22 Aug 2016 21:14:01 -0700 Subject: [PATCH 347/531] raid5: fix memory leak of bio integrity data Yi reported a memory leak of raid5 with DIF/DIX enabled disks. raid5 doesn't alloc/free bio, instead it reuses bios. There are two issues in current code: 1. the code calls bio_init (from init_stripe->raid5_build_block->bio_init) then bio_reset (ops_run_io). The bio is reused, so likely there is integrity data attached. bio_init will clear a pointer to integrity data and makes bio_reset can't release the data 2. bio_reset is called before dispatching bio. After bio is finished, it's possible we don't free bio's integrity data (eg, we don't call bio_reset again) Both issues will cause memory leak. The patch moves bio_init to stripe creation and bio_reset to bio end io. This will fix the two issues. Reported-by: Yi Zhang Signed-off-by: Shaohua Li --- drivers/md/raid5.c | 22 +++++++++++++++------- 1 file changed, 15 insertions(+), 7 deletions(-) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 2119e094dfb3..d1a279b1916b 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -1005,7 +1005,6 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) set_bit(STRIPE_IO_STARTED, &sh->state); - bio_reset(bi); bi->bi_bdev = rdev->bdev; bio_set_op_attrs(bi, op, op_flags); bi->bi_end_io = op_is_write(op) @@ -1057,7 +1056,6 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) set_bit(STRIPE_IO_STARTED, &sh->state); - bio_reset(rbi); rbi->bi_bdev = rrdev->bdev; bio_set_op_attrs(rbi, op, op_flags); BUG_ON(!op_is_write(op)); @@ -1990,9 +1988,11 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request) put_cpu(); } -static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp) +static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp, + int disks) { struct stripe_head *sh; + int i; sh = kmem_cache_zalloc(sc, gfp); if (sh) { @@ -2001,6 +2001,12 @@ static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp) INIT_LIST_HEAD(&sh->batch_list); INIT_LIST_HEAD(&sh->lru); atomic_set(&sh->count, 1); + for (i = 0; i < disks; i++) { + struct r5dev *dev = &sh->dev[i]; + + bio_init(&dev->req); + bio_init(&dev->rreq); + } } return sh; } @@ -2008,7 +2014,7 @@ static int grow_one_stripe(struct r5conf *conf, gfp_t gfp) { struct stripe_head *sh; - sh = alloc_stripe(conf->slab_cache, gfp); + sh = alloc_stripe(conf->slab_cache, gfp, conf->pool_size); if (!sh) return 0; @@ -2179,7 +2185,7 @@ static int resize_stripes(struct r5conf *conf, int newsize) mutex_lock(&conf->cache_size_mutex); for (i = conf->max_nr_stripes; i; i--) { - nsh = alloc_stripe(sc, GFP_KERNEL); + nsh = alloc_stripe(sc, GFP_KERNEL, newsize); if (!nsh) break; @@ -2311,6 +2317,7 @@ static void raid5_end_read_request(struct bio * bi) (unsigned long long)sh->sector, i, atomic_read(&sh->count), bi->bi_error); if (i == disks) { + bio_reset(bi); BUG(); return; } @@ -2414,6 +2421,7 @@ static void raid5_end_read_request(struct bio * bi) clear_bit(R5_LOCKED, &sh->dev[i].flags); set_bit(STRIPE_HANDLE, &sh->state); raid5_release_stripe(sh); + bio_reset(bi); } static void raid5_end_write_request(struct bio *bi) @@ -2448,6 +2456,7 @@ static void raid5_end_write_request(struct bio *bi) (unsigned long long)sh->sector, i, atomic_read(&sh->count), bi->bi_error); if (i == disks) { + bio_reset(bi); BUG(); return; } @@ -2491,18 +2500,17 @@ static void raid5_end_write_request(struct bio *bi) if (sh->batch_head && sh != sh->batch_head) raid5_release_stripe(sh->batch_head); + bio_reset(bi); } static void raid5_build_block(struct stripe_head *sh, int i, int previous) { struct r5dev *dev = &sh->dev[i]; - bio_init(&dev->req); dev->req.bi_io_vec = &dev->vec; dev->req.bi_max_vecs = 1; dev->req.bi_private = sh; - bio_init(&dev->rreq); dev->rreq.bi_io_vec = &dev->rvec; dev->rreq.bi_max_vecs = 1; dev->rreq.bi_private = sh; From 45c91d808ff989d950e260dab9f89e8f4a3c9c2c Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Mon, 22 Aug 2016 21:14:02 -0700 Subject: [PATCH 348/531] raid5: avoid unnecessary bio data set bio_reset doesn't change bi_io_vec and bi_max_vecs, so we don't need to set them every time. bi_private will be set before the bio is dispatched. Signed-off-by: Shaohua Li --- drivers/md/raid5.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index d1a279b1916b..62febe8d4919 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -2005,7 +2005,12 @@ static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp, struct r5dev *dev = &sh->dev[i]; bio_init(&dev->req); + dev->req.bi_io_vec = &dev->vec; + dev->req.bi_max_vecs = 1; + bio_init(&dev->rreq); + dev->rreq.bi_io_vec = &dev->rvec; + dev->rreq.bi_max_vecs = 1; } } return sh; @@ -2507,14 +2512,6 @@ static void raid5_build_block(struct stripe_head *sh, int i, int previous) { struct r5dev *dev = &sh->dev[i]; - dev->req.bi_io_vec = &dev->vec; - dev->req.bi_max_vecs = 1; - dev->req.bi_private = sh; - - dev->rreq.bi_io_vec = &dev->rvec; - dev->rreq.bi_max_vecs = 1; - dev->rreq.bi_private = sh; - dev->flags = 0; dev->sector = raid5_compute_blocknr(sh, i, previous); } From af7c388a9c2e5fdd36da6eaaa35fb86fb8aefd0b Mon Sep 17 00:00:00 2001 From: Vince Hsu Date: Wed, 24 Aug 2016 15:56:56 +0200 Subject: [PATCH 349/531] clk: tegra: remove TEGRA_PLL_USE_LOCK for PLLD/PLLD2 Tegra114 has a HW bug that the PLLD/PLLD2 lock bit cannot be asserted when the DIS power domain is during up-powergating process but the clamp to this domain is not removed yet. That causes a timeout and aborts the power sequence, although the PLLD/PLLD2 has already locked. To remove the false alarm, we don't use the lock for PLLD/PLLD2. Just wait 1ms and treat the clocks as locked. Signed-off-by: Vince Hsu Tested-by: Jonathan Hunter Signed-off-by: Thierry Reding Signed-off-by: Stephen Boyd --- drivers/clk/tegra/clk-tegra114.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/clk/tegra/clk-tegra114.c b/drivers/clk/tegra/clk-tegra114.c index 64da7b79a6e4..933b5dd698b8 100644 --- a/drivers/clk/tegra/clk-tegra114.c +++ b/drivers/clk/tegra/clk-tegra114.c @@ -428,7 +428,7 @@ static struct tegra_clk_pll_params pll_d_params = { .div_nmp = &pllp_nmp, .freq_table = pll_d_freq_table, .flags = TEGRA_PLL_HAS_CPCON | TEGRA_PLL_SET_LFCON | - TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE, + TEGRA_PLL_HAS_LOCK_ENABLE, }; static struct tegra_clk_pll_params pll_d2_params = { @@ -446,7 +446,7 @@ static struct tegra_clk_pll_params pll_d2_params = { .div_nmp = &pllp_nmp, .freq_table = pll_d_freq_table, .flags = TEGRA_PLL_HAS_CPCON | TEGRA_PLL_SET_LFCON | - TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE, + TEGRA_PLL_HAS_LOCK_ENABLE, }; static const struct pdiv_map pllu_p[] = { From e1718d97aa88ea44a6a8f50ff464253dd0dacf01 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 24 Aug 2016 12:31:36 -0400 Subject: [PATCH 350/531] drm/amdgpu: avoid a possible array overflow MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When looking up the connector type make sure the index is valid. Avoids a later crash if we read past the end of the array. Workaround for bug: https://bugs.freedesktop.org/show_bug.cgi?id=97460 Reviewed-by: Christian König Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c index 983175363b06..151422307d31 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c @@ -321,6 +321,12 @@ bool amdgpu_atombios_get_connector_info_from_object_table(struct amdgpu_device * (le16_to_cpu(path->usConnObjectId) & OBJECT_TYPE_MASK) >> OBJECT_TYPE_SHIFT; + if (con_obj_id >= ARRAY_SIZE(object_connector_convert)) { + DRM_ERROR("invalid con_obj_id %d for device tag 0x%04x\n", + con_obj_id, le16_to_cpu(path->usDeviceTag)); + continue; + } + connector_type = object_connector_convert[con_obj_id]; connector_object_id = con_obj_id; From 611a1507fe8569ce1adab3abc982ea58ab559fb9 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 24 Aug 2016 13:04:15 -0400 Subject: [PATCH 351/531] drm/amdgpu: skip TV/CV in display parsing MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit No asics supported by amdgpu support analog TV. Workaround for bug: https://bugs.freedesktop.org/show_bug.cgi?id=97460 Reviewed-by: Christian König Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c index 151422307d31..fe872b82e619 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c @@ -321,6 +321,13 @@ bool amdgpu_atombios_get_connector_info_from_object_table(struct amdgpu_device * (le16_to_cpu(path->usConnObjectId) & OBJECT_TYPE_MASK) >> OBJECT_TYPE_SHIFT; + /* Skip TV/CV support */ + if ((le16_to_cpu(path->usDeviceTag) == + ATOM_DEVICE_TV1_SUPPORT) || + (le16_to_cpu(path->usDeviceTag) == + ATOM_DEVICE_CV_SUPPORT)) + continue; + if (con_obj_id >= ARRAY_SIZE(object_connector_convert)) { DRM_ERROR("invalid con_obj_id %d for device tag 0x%04x\n", con_obj_id, le16_to_cpu(path->usDeviceTag)); From 716b076ba4b273f5f85c97448c5110c6d21e73e6 Mon Sep 17 00:00:00 2001 From: Doug Ledford Date: Wed, 24 Aug 2016 12:14:19 -0400 Subject: [PATCH 352/531] IB/srpt: Update sport->port_guid with each port refresh If port_guid is set with the default subnet_prefix, then we get a change event and run a port refresh, we don't update the port_guid. As a result, attempts to create a target device that uses the new subnet_prefix in the wwn will fail to find a match and be rejected by the ib_srpt driver. This makes it impossible to configure a port if it was initialized with a default subnet_prefix and later changed to any non-default subnet-prefix. Updating the port refresh task to always update the wwn based upon the current subnext_prefix solves this problem. Cc: Bart Van Assche Cc: nab@linux-iscsi.org Signed-off-by: Doug Ledford --- drivers/infiniband/ulp/srpt/ib_srpt.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index dfa23b075a88..883bbfe08e0e 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -522,6 +522,11 @@ static int srpt_refresh_port(struct srpt_port *sport) if (ret) goto err_query_port; + snprintf(sport->port_guid, sizeof(sport->port_guid), + "0x%016llx%016llx", + be64_to_cpu(sport->gid.global.subnet_prefix), + be64_to_cpu(sport->gid.global.interface_id)); + if (!sport->mad_agent) { memset(®_req, 0, sizeof(reg_req)); reg_req.mgmt_class = IB_MGMT_CLASS_DEVICE_MGMT; @@ -2548,10 +2553,6 @@ static void srpt_add_one(struct ib_device *device) sdev->device->name, i); goto err_ring; } - snprintf(sport->port_guid, sizeof(sport->port_guid), - "0x%016llx%016llx", - be64_to_cpu(sport->gid.global.subnet_prefix), - be64_to_cpu(sport->gid.global.interface_id)); } spin_lock(&srpt_dev_lock); From e57690fe009b2ab0cee8a57f53be634540e49c9d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 24 Aug 2016 15:34:35 -0600 Subject: [PATCH 353/531] blk-mq: don't overwrite rq->mq_ctx We do this in a few places, if the CPU is offline. This isn't allowed, though, since on multi queue hardware, we can't just move a request from one software queue to another, if they map to different hardware queues. The request and tag isn't valid on another hardware queue. This can happen if plugging races with CPU offlining. But it does no harm, since it can only happen in the window where we are currently busy freezing the queue and flushing IO, in preparation for redoing the software <-> hardware queue mappings. Signed-off-by: Jens Axboe --- block/blk-mq.c | 55 +++++++++++++++----------------------------------- 1 file changed, 16 insertions(+), 39 deletions(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index e931a0e8e73d..729169d022fc 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1036,10 +1036,11 @@ void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs) EXPORT_SYMBOL(blk_mq_delay_queue); static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx, - struct blk_mq_ctx *ctx, struct request *rq, bool at_head) { + struct blk_mq_ctx *ctx = rq->mq_ctx; + trace_block_rq_insert(hctx->queue, rq); if (at_head) @@ -1053,20 +1054,16 @@ static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, { struct blk_mq_ctx *ctx = rq->mq_ctx; - __blk_mq_insert_req_list(hctx, ctx, rq, at_head); + __blk_mq_insert_req_list(hctx, rq, at_head); blk_mq_hctx_mark_pending(hctx, ctx); } void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue, - bool async) + bool async) { + struct blk_mq_ctx *ctx = rq->mq_ctx; struct request_queue *q = rq->q; struct blk_mq_hw_ctx *hctx; - struct blk_mq_ctx *ctx = rq->mq_ctx, *current_ctx; - - current_ctx = blk_mq_get_ctx(q); - if (!cpu_online(ctx->cpu)) - rq->mq_ctx = ctx = current_ctx; hctx = q->mq_ops->map_queue(q, ctx->cpu); @@ -1076,8 +1073,6 @@ void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue, if (run_queue) blk_mq_run_hw_queue(hctx, async); - - blk_mq_put_ctx(current_ctx); } static void blk_mq_insert_requests(struct request_queue *q, @@ -1088,14 +1083,9 @@ static void blk_mq_insert_requests(struct request_queue *q, { struct blk_mq_hw_ctx *hctx; - struct blk_mq_ctx *current_ctx; trace_block_unplug(q, depth, !from_schedule); - current_ctx = blk_mq_get_ctx(q); - - if (!cpu_online(ctx->cpu)) - ctx = current_ctx; hctx = q->mq_ops->map_queue(q, ctx->cpu); /* @@ -1107,15 +1097,14 @@ static void blk_mq_insert_requests(struct request_queue *q, struct request *rq; rq = list_first_entry(list, struct request, queuelist); + BUG_ON(rq->mq_ctx != ctx); list_del_init(&rq->queuelist); - rq->mq_ctx = ctx; - __blk_mq_insert_req_list(hctx, ctx, rq, false); + __blk_mq_insert_req_list(hctx, rq, false); } blk_mq_hctx_mark_pending(hctx, ctx); spin_unlock(&ctx->lock); blk_mq_run_hw_queue(hctx, from_schedule); - blk_mq_put_ctx(current_ctx); } static int plug_ctx_cmp(void *priv, struct list_head *a, struct list_head *b) @@ -1630,16 +1619,17 @@ static int blk_mq_alloc_bitmap(struct blk_mq_ctxmap *bitmap, int node) return 0; } +/* + * 'cpu' is going away. splice any existing rq_list entries from this + * software queue to the hw queue dispatch list, and ensure that it + * gets run. + */ static int blk_mq_hctx_cpu_offline(struct blk_mq_hw_ctx *hctx, int cpu) { - struct request_queue *q = hctx->queue; struct blk_mq_ctx *ctx; LIST_HEAD(tmp); - /* - * Move ctx entries to new CPU, if this one is going away. - */ - ctx = __blk_mq_get_ctx(q, cpu); + ctx = __blk_mq_get_ctx(hctx->queue, cpu); spin_lock(&ctx->lock); if (!list_empty(&ctx->rq_list)) { @@ -1651,24 +1641,11 @@ static int blk_mq_hctx_cpu_offline(struct blk_mq_hw_ctx *hctx, int cpu) if (list_empty(&tmp)) return NOTIFY_OK; - ctx = blk_mq_get_ctx(q); - spin_lock(&ctx->lock); - - while (!list_empty(&tmp)) { - struct request *rq; - - rq = list_first_entry(&tmp, struct request, queuelist); - rq->mq_ctx = ctx; - list_move_tail(&rq->queuelist, &ctx->rq_list); - } - - hctx = q->mq_ops->map_queue(q, ctx->cpu); - blk_mq_hctx_mark_pending(hctx, ctx); - - spin_unlock(&ctx->lock); + spin_lock(&hctx->lock); + list_splice_tail_init(&tmp, &hctx->dispatch); + spin_unlock(&hctx->lock); blk_mq_run_hw_queue(hctx, true); - blk_mq_put_ctx(ctx); return NOTIFY_OK; } From 0e87e58bf60edb6bb28e493c7a143f41b091a5e5 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 24 Aug 2016 15:38:01 -0600 Subject: [PATCH 354/531] blk-mq: improve warning for running a queue on the wrong CPU __blk_mq_run_hw_queue() currently warns if we are running the queue on a CPU that isn't set in its mask. However, this can happen if a CPU is being offlined, and the workqueue handling will place the work on CPU0 instead. Improve the warning so that it only triggers if the batch cpu in the hardware queue is currently online. If it triggers for that case, then it's indicative of a flow problem in blk-mq, so we want to retain it for that case. Signed-off-by: Jens Axboe --- block/blk-mq.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index 729169d022fc..13f5a6c1de76 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -793,11 +793,12 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx) struct list_head *dptr; int queued; - WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask)); - if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state))) return; + WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) && + cpu_online(hctx->next_cpu)); + hctx->run++; /* From a45f9d41c9dd2c28e38b9b88f69c39bc63807de9 Mon Sep 17 00:00:00 2001 From: Xing Zheng Date: Wed, 24 Aug 2016 11:29:39 -0700 Subject: [PATCH 355/531] clk: rockchip: mark aclk_emmc_noc as a critical clock on rk3399 We don't have code to handle any of the noc clocks in rk3399 and they're all just listed as critical clocks. Let's do the same for aclk_emmc_noc. Without this clock being marked as critical we have problems around suspend/resume after commit 20c389e656a8 ("clk: rockchip: fix incorrect aclk_emmc source gate bits on rk3399"). Before that change we were presumably not actually gating any of these clocks because we were setting the wrong gate. Fixes: 20c389e656a8 ("clk: rockchip: fix incorrect aclk_emmc source gate bits on rk3399") Signed-off-by: Xing Zheng Signed-off-by: Douglas Anderson Signed-off-by: Heiko Stuebner --- drivers/clk/rockchip/clk-rk3399.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/clk/rockchip/clk-rk3399.c b/drivers/clk/rockchip/clk-rk3399.c index ec5b2fd77c50..cdfabeb9a034 100644 --- a/drivers/clk/rockchip/clk-rk3399.c +++ b/drivers/clk/rockchip/clk-rk3399.c @@ -1484,6 +1484,7 @@ static const char *const rk3399_cru_critical_clocks[] __initconst = { "hclk_perilp1", "hclk_perilp1_noc", "aclk_dmac0_perilp", + "aclk_emmc_noc", "gpll_hclk_perilp1_src", "gpll_aclk_perilp0_src", "gpll_aclk_perihp_src", From 299f6230bc6d0ccd5f95bb0fb865d80a9c7d5ccc Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Wed, 24 Aug 2016 21:12:58 -0400 Subject: [PATCH 356/531] dm flakey: fix reads to be issued if drop_writes configured v4.8-rc3 commit 99f3c90d0d ("dm flakey: error READ bios during the down_interval") overlooked the 'drop_writes' feature, which is meant to allow reads to be issued rather than errored, during the down_interval. Fixes: 99f3c90d0d ("dm flakey: error READ bios during the down_interval") Reported-by: Qu Wenruo Signed-off-by: Mike Snitzer Cc: stable@vger.kernel.org --- drivers/md/dm-flakey.c | 27 ++++++++++++++++----------- 1 file changed, 16 insertions(+), 11 deletions(-) diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index 97e446d54a15..6a2e8dd44a1b 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -289,15 +289,13 @@ static int flakey_map(struct dm_target *ti, struct bio *bio) pb->bio_submitted = true; /* - * Map reads as normal only if corrupt_bio_byte set. + * Error reads if neither corrupt_bio_byte or drop_writes are set. + * Otherwise, flakey_end_io() will decide if the reads should be modified. */ if (bio_data_dir(bio) == READ) { - /* If flags were specified, only corrupt those that match. */ - if (fc->corrupt_bio_byte && (fc->corrupt_bio_rw == READ) && - all_corrupt_bio_flags_match(bio, fc)) - goto map_bio; - else + if (!fc->corrupt_bio_byte && !test_bit(DROP_WRITES, &fc->flags)) return -EIO; + goto map_bio; } /* @@ -334,14 +332,21 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio, int error) struct flakey_c *fc = ti->private; struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data)); - /* - * Corrupt successful READs while in down state. - */ if (!error && pb->bio_submitted && (bio_data_dir(bio) == READ)) { - if (fc->corrupt_bio_byte) + if (fc->corrupt_bio_byte && (fc->corrupt_bio_rw == READ) && + all_corrupt_bio_flags_match(bio, fc)) { + /* + * Corrupt successful matching READs while in down state. + */ corrupt_bio_data(bio, fc); - else + + } else if (!test_bit(DROP_WRITES, &fc->flags)) { + /* + * Error read during the down_interval if drop_writes + * wasn't configured. + */ return -EIO; + } } return error; From 9c5a559d9495bba6e5b6c5ee4e8e2f2b71088684 Mon Sep 17 00:00:00 2001 From: Heinz Mauelshagen Date: Tue, 23 Aug 2016 21:17:48 +0200 Subject: [PATCH 357/531] dm log: fix unitialized bio operation flags Commit e6047149db ("dm: use bio op accessors") switched DM over to using bio_set_op_attrs() but didn't take care to initialize lc->io_req.bi_op_flags in dm-log.c:rw_header(). This caused rw_header()'s call to dm_io() to make bio->bi_op_flags be uninitialized in dm-io.c:do_region(), which ultimately resulted in a SCSI BUG() in sd_init_command(). Also, adjust rw_header() and its callers to use REQ_OP_{READ|WRITE}. Fixes: e6047149db ("dm: use bio op accessors") Signed-off-by: Heinz Mauelshagen Reviewed-by: Shaun Tancheff Signed-off-by: Mike Snitzer --- drivers/md/dm-log.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c index 4ca2d1df5b44..07fc1ad42ec5 100644 --- a/drivers/md/dm-log.c +++ b/drivers/md/dm-log.c @@ -291,9 +291,10 @@ static void header_from_disk(struct log_header_core *core, struct log_header_dis core->nr_regions = le64_to_cpu(disk->nr_regions); } -static int rw_header(struct log_c *lc, int rw) +static int rw_header(struct log_c *lc, int op) { - lc->io_req.bi_op = rw; + lc->io_req.bi_op = op; + lc->io_req.bi_op_flags = 0; return dm_io(&lc->io_req, 1, &lc->header_location, NULL); } @@ -316,7 +317,7 @@ static int read_header(struct log_c *log) { int r; - r = rw_header(log, READ); + r = rw_header(log, REQ_OP_READ); if (r) return r; @@ -630,7 +631,7 @@ static int disk_resume(struct dm_dirty_log *log) header_to_disk(&lc->header, lc->disk_header); /* write the new header */ - r = rw_header(lc, WRITE); + r = rw_header(lc, REQ_OP_WRITE); if (!r) { r = flush_header(lc); if (r) @@ -698,7 +699,7 @@ static int disk_flush(struct dm_dirty_log *log) log_clear_bit(lc, lc->clean_bits, i); } - r = rw_header(lc, WRITE); + r = rw_header(lc, REQ_OP_WRITE); if (r) fail_log_device(lc); else { From 16590a228109e2f318d2cc6466221134cfab723a Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 22 Aug 2016 14:57:42 -0400 Subject: [PATCH 358/531] SUNRPC: Silence WARN_ON when NFSv4.1 over RDMA is in use Using NFSv4.1 on RDMA should be safe, so broaden the new checks in rpc_create(). WARN_ON_ONCE is used, matching most other WARN call sites in clnt.c. Fixes: 39a9beab5acb ("rpc: share one xps between all backchannels") Fixes: d50039ea5ee6 ("nfsd4/rpc: move backchannel create logic...") Signed-off-by: Chuck Lever Reviewed-by: J. Bruce Fields Signed-off-by: Trond Myklebust --- net/sunrpc/clnt.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 7f79fb7dc6a0..66f23b376fa0 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -453,7 +453,7 @@ static struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args, struct rpc_xprt_switch *xps; if (args->bc_xprt && args->bc_xprt->xpt_bc_xps) { - WARN_ON(args->protocol != XPRT_TRANSPORT_BC_TCP); + WARN_ON_ONCE(!(args->protocol & XPRT_TRANSPORT_BC)); xps = args->bc_xprt->xpt_bc_xps; xprt_switch_get(xps); } else { @@ -520,7 +520,7 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args) char servername[48]; if (args->bc_xprt) { - WARN_ON(args->protocol != XPRT_TRANSPORT_BC_TCP); + WARN_ON_ONCE(!(args->protocol & XPRT_TRANSPORT_BC)); xprt = args->bc_xprt->xpt_bc_xprt; if (xprt) { xprt_get(xprt); From 23fd537c9508fb6e3b93ddf23982f51afc087781 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Wed, 24 Aug 2016 14:33:27 +0300 Subject: [PATCH 359/531] usb: gadget: udc: core: don't starve DMA resources Always unmap all SG entries as required by DMA API Fixes: a698908d3b3b ("usb: gadget: add generic map/unmap request utilities") Cc: # v3.4+ Signed-off-by: Felipe Balbi --- drivers/usb/gadget/udc/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index 934f83881c30..40c04bb25f2f 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -827,7 +827,7 @@ void usb_gadget_unmap_request_by_dev(struct device *dev, return; if (req->num_mapped_sgs) { - dma_unmap_sg(dev, req->sg, req->num_mapped_sgs, + dma_unmap_sg(dev, req->sg, req->num_sgs, is_in ? DMA_TO_DEVICE : DMA_FROM_DEVICE); req->num_mapped_sgs = 0; From 696fe69d7e631f00f23b0ef1694d9b90058dca54 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Wed, 24 Aug 2016 14:32:39 +0300 Subject: [PATCH 360/531] usb: dwc3: debug: fix ep name on trace output There was a typo when generating endpoint name which would be very confusing when debugging. Fix it. Signed-off-by: Felipe Balbi --- drivers/usb/dwc3/debug.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/dwc3/debug.h b/drivers/usb/dwc3/debug.h index 22dfc3dd6a13..33ab2a203c1b 100644 --- a/drivers/usb/dwc3/debug.h +++ b/drivers/usb/dwc3/debug.h @@ -192,7 +192,7 @@ dwc3_ep_event_string(const struct dwc3_event_depevt *event) int ret; ret = sprintf(str, "ep%d%s: ", epnum >> 1, - (epnum & 1) ? "in" : "in"); + (epnum & 1) ? "in" : "out"); if (ret < 0) return "UNKNOWN"; From 6f8245b4e37c2072d3daea24e19dbc0162ffd22c Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Wed, 24 Aug 2016 14:40:13 +0300 Subject: [PATCH 361/531] usb: dwc3: gadget: always decrement by 1 We need to decrement in both cases (enq > deq and enq < deq) Signed-off-by: Felipe Balbi --- drivers/usb/dwc3/gadget.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 122e64df2f4d..7a8d3d822b54 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -884,12 +884,9 @@ static u32 dwc3_calc_trbs_left(struct dwc3_ep *dep) return DWC3_TRB_NUM - 1; } - trbs_left = dep->trb_dequeue - dep->trb_enqueue; + trbs_left = dep->trb_dequeue - dep->trb_enqueue - 1; trbs_left &= (DWC3_TRB_NUM - 1); - if (dep->trb_dequeue < dep->trb_enqueue) - trbs_left--; - return trbs_left; } From fd363bd417ddb6103564c69cfcbd92d9a7877431 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 24 Aug 2016 18:02:08 +0100 Subject: [PATCH 362/531] arm64: avoid TLB conflict with CONFIG_RANDOMIZE_BASE When CONFIG_RANDOMIZE_BASE is selected, we modify the page tables to remap the kernel at a newly-chosen VA range. We do this with the MMU disabled, but do not invalidate TLBs prior to re-enabling the MMU with the new tables. Thus the old mappings entries may still live in TLBs, and we risk violating Break-Before-Make requirements, leading to TLB conflicts and/or other issues. We invalidate TLBs when we uninsall the idmap in early setup code, but prior to this we are subject to issues relating to the Break-Before-Make violation. Avoid these issues by invalidating the TLBs before the new mappings can be used by the hardware. Fixes: f80fb3a3d508 ("arm64: add support for kernel ASLR") Cc: # 4.6+ Acked-by: Ard Biesheuvel Acked-by: Will Deacon Signed-off-by: Mark Rutland Signed-off-by: Catalin Marinas --- arch/arm64/kernel/head.S | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index b77f58355da1..3e7b050e99dc 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -757,6 +757,9 @@ ENTRY(__enable_mmu) isb bl __create_page_tables // recreate kernel mapping + tlbi vmalle1 // Remove any stale TLB entries + dsb nsh + msr sctlr_el1, x19 // re-enable the MMU isb ic iallu // flush instructions fetched From 1c1ea4f781db9f754842b9c31d1eff400d17cddc Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Tue, 19 Jul 2016 15:36:05 -0700 Subject: [PATCH 363/531] Btrfs: fix memory leak of reloc_root When some critical errors occur and FS would be flipped into RO, if we have an on-going balance, we can end up with a memory leak of root->reloc_root since btrfs_drop_snapshots() bails out without freeing reloc_root at the very early start. However, we're not able to free reloc_root in btrfs_drop_snapshots() because its caller, merge_reloc_roots(), still needs to access it to cleanup reloc_root's rbtree. This makes us free reloc_root when we're going to free fs/file roots. Signed-off-by: Liu Bo Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index ff2362dca91a..4a34c9fcc1a7 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3744,8 +3744,15 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info, if (btrfs_root_refs(&root->root_item) == 0) synchronize_srcu(&fs_info->subvol_srcu); - if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) + if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) { btrfs_free_log(NULL, root); + if (root->reloc_root) { + free_extent_buffer(root->reloc_root->node); + free_extent_buffer(root->reloc_root->commit_root); + btrfs_put_fs_root(root->reloc_root); + root->reloc_root = NULL; + } + } if (root->free_ino_pinned) __btrfs_remove_free_space_cache(root->free_ino_pinned); From d8422ba334f9df16e071bc77707e55fd7f8446ae Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Wed, 20 Jul 2016 15:04:18 +0800 Subject: [PATCH 364/531] btrfs: backref: Fix soft lockup in __merge_refs function When over 1000 file extents refers to one extent, find_parent_nodes() will be obviously slow, due to the O(n^2)~O(n^3) loops inside __merge_refs(). The following ftrace shows the cubic growth of execution time: 256 refs 5) + 91.768 us | __add_keyed_refs.isra.12 [btrfs](); 5) 1.447 us | __add_missing_keys.isra.13 [btrfs](); 5) ! 114.544 us | __merge_refs [btrfs](); 5) ! 136.399 us | __merge_refs [btrfs](); 512 refs 6) ! 279.859 us | __add_keyed_refs.isra.12 [btrfs](); 6) 3.164 us | __add_missing_keys.isra.13 [btrfs](); 6) ! 442.498 us | __merge_refs [btrfs](); 6) # 2091.073 us | __merge_refs [btrfs](); and 1024 refs 7) ! 368.683 us | __add_keyed_refs.isra.12 [btrfs](); 7) 4.810 us | __add_missing_keys.isra.13 [btrfs](); 7) # 2043.428 us | __merge_refs [btrfs](); 7) * 18964.23 us | __merge_refs [btrfs](); And sort them into the following char: (Unit: us) ------------------------------------------------------------------------ Trace function | 256 ref | 512 refs | 1024 refs | ------------------------------------------------------------------------ __add_keyed_refs | 91 | 249 | 368 | __add_missing_keys | 1 | 3 | 4 | __merge_refs 1st call | 114 | 442 | 2043 | __merge_refs 2nd call | 136 | 2091 | 18964 | ------------------------------------------------------------------------ We can see the that __add_keyed_refs() grows almost in linear behavior. And __add_missing_keys() in this case doesn't change much or takes much time. While for the 1st __merge_refs() it's square growth for the 2nd __merge_refs() call it's cubic growth. It's no doubt that merge_refs() will take a long long time to execute if the number of refs continues its grows. So add a cond_resced() into the loop of __merge_refs(). Although this will solve the problem of soft lockup, we need to use the new rb_tree based structure introduced by Lu Fengqi to really solve the long execution time. Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/backref.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 2b88439c2ee8..455a6b2fd539 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -589,6 +589,7 @@ static void __merge_refs(struct list_head *head, int mode) list_del(&ref2->list); kmem_cache_free(btrfs_prelim_ref_cache, ref2); + cond_resched(); } } From f3bca8028bd934e96257b8bd1143e6474fe98465 Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Wed, 20 Jul 2016 17:33:44 -0700 Subject: [PATCH 365/531] Btrfs: add ASSERT for block group's memory leak This adds several ASSERT()' s to report memory leak of block group cache. Signed-off-by: Liu Bo Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/extent-tree.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index c2b81b0d3fe0..e962b0e25324 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -9942,6 +9942,7 @@ void btrfs_put_block_group_cache(struct btrfs_fs_info *info) block_group->iref = 0; block_group->inode = NULL; spin_unlock(&block_group->lock); + ASSERT(block_group->io_ctl.inode == NULL); iput(inode); last = block_group->key.objectid + block_group->key.offset; btrfs_put_block_group(block_group); @@ -9999,6 +10000,10 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info) free_excluded_extents(info->extent_root, block_group); btrfs_remove_free_space_cache(block_group); + ASSERT(list_empty(&block_group->dirty_list)); + ASSERT(list_empty(&block_group->io_list)); + ASSERT(list_empty(&block_group->bg_list)); + ASSERT(atomic_read(&block_group->count) == 1); btrfs_put_block_group(block_group); spin_lock(&info->block_group_cache_lock); From eecba891d38051ebf7f4af6394d188a5fd151a6a Mon Sep 17 00:00:00 2001 From: Alex Lyakas Date: Sun, 6 Dec 2015 12:32:31 +0200 Subject: [PATCH 366/531] btrfs: flush_space: treat return value of do_chunk_alloc properly do_chunk_alloc returns 1 when it succeeds to allocate a new chunk. But flush_space will not convert this to 0, and will also return 1. As a result, reserve_metadata_bytes will think that flush_space failed, and may potentially return this value "1" to the caller (depends how reserve_metadata_bytes was called). The caller will also treat this as an error. For example, btrfs_block_rsv_refill does: int ret = -ENOSPC; ... ret = reserve_metadata_bytes(root, block_rsv, num_bytes, flush); if (!ret) { block_rsv_add_bytes(block_rsv, num_bytes, 0); return 0; } return ret; So it will return -ENOSPC. Signed-off-by: Alex Lyakas Reviewed-by: Josef Bacik Reviewed-by: Liu Bo Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/extent-tree.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index e962b0e25324..d2cc16ff3e21 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4882,7 +4882,7 @@ static int flush_space(struct btrfs_root *root, btrfs_get_alloc_profile(root, 0), CHUNK_ALLOC_NO_FORCE); btrfs_end_transaction(trans, root); - if (ret == -ENOSPC) + if (ret > 0 || ret == -ENOSPC) ret = 0; break; case COMMIT_TRANS: From d2c609b834d62f1e91f1635a27dca29f7806d3d6 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Mon, 15 Aug 2016 12:10:33 -0400 Subject: [PATCH 367/531] btrfs: properly track when rescan worker is running The qgroup_flags field is overloaded such that it reflects the on-disk status of qgroups and the runtime state. The BTRFS_QGROUP_STATUS_FLAG_RESCAN flag is used to indicate that a rescan operation is in progress, but if the file system is unmounted while a rescan is running, the rescan operation is paused. If the file system is then mounted read-only, the flag will still be present but the rescan operation will not have been resumed. When we go to umount, btrfs_qgroup_wait_for_completion will see the flag and interpret it to mean that the rescan worker is still running and will wait for a completion that will never come. This patch uses a separate flag to indicate when the worker is running. The locking and state surrounding the qgroup rescan worker needs a lot of attention beyond this patch but this is enough to avoid a hung umount. Cc: # v4.4+ Signed-off-by; Jeff Mahoney Reviewed-by: Qu Wenruo Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/ctree.h | 1 + fs/btrfs/disk-io.c | 1 + fs/btrfs/qgroup.c | 9 ++++++++- 3 files changed, 10 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index f66a0ba9a2a9..acc6850a118f 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1028,6 +1028,7 @@ struct btrfs_fs_info { struct btrfs_workqueue *qgroup_rescan_workers; struct completion qgroup_rescan_completion; struct btrfs_work qgroup_rescan_work; + bool qgroup_rescan_running; /* protected by qgroup_rescan_lock */ /* filesystem state */ unsigned long fs_state; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 4a34c9fcc1a7..f5b2a7fb4575 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2304,6 +2304,7 @@ static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info) fs_info->quota_enabled = 0; fs_info->pending_quota_state = 0; fs_info->qgroup_ulist = NULL; + fs_info->qgroup_rescan_running = false; mutex_init(&fs_info->qgroup_rescan_lock); } diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 93ee1c18ef9d..3fe295e2c84a 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -2303,6 +2303,10 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) int err = -ENOMEM; int ret = 0; + mutex_lock(&fs_info->qgroup_rescan_lock); + fs_info->qgroup_rescan_running = true; + mutex_unlock(&fs_info->qgroup_rescan_lock); + path = btrfs_alloc_path(); if (!path) goto out; @@ -2369,6 +2373,9 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) } done: + mutex_lock(&fs_info->qgroup_rescan_lock); + fs_info->qgroup_rescan_running = false; + mutex_unlock(&fs_info->qgroup_rescan_lock); complete_all(&fs_info->qgroup_rescan_completion); } @@ -2494,7 +2501,7 @@ int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info) mutex_lock(&fs_info->qgroup_rescan_lock); spin_lock(&fs_info->qgroup_lock); - running = fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN; + running = fs_info->qgroup_rescan_running; spin_unlock(&fs_info->qgroup_lock); mutex_unlock(&fs_info->qgroup_rescan_lock); From d06f23d6a947c9abae41dc46be69a56baf36f436 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Mon, 8 Aug 2016 22:08:06 -0400 Subject: [PATCH 368/531] btrfs: waiting on qgroup rescan should not always be interruptible We wait on qgroup rescan completion in three places: file system shutdown, the quota disable ioctl, and the rescan wait ioctl. If the user sends a signal while we're waiting, we continue happily along. This is expected behavior for the rescan wait ioctl. It's racy in the shutdown path but mostly works due to other unrelated synchronization points. In the quota disable path, it Oopses the kernel pretty much immediately. Cc: # v4.4+ Signed-off-by: Jeff Mahoney Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 2 +- fs/btrfs/ioctl.c | 2 +- fs/btrfs/qgroup.c | 12 +++++++++--- fs/btrfs/qgroup.h | 3 ++- 4 files changed, 13 insertions(+), 6 deletions(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index f5b2a7fb4575..7857f64e1cae 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3864,7 +3864,7 @@ void close_ctree(struct btrfs_root *root) smp_mb(); /* wait for the qgroup rescan worker to stop */ - btrfs_qgroup_wait_for_completion(fs_info); + btrfs_qgroup_wait_for_completion(fs_info, false); /* wait for the uuid_scan task to finish */ down(&fs_info->uuid_tree_rescan_sem); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 14ed1e9e6bc8..b2a2da5893af 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -5084,7 +5084,7 @@ static long btrfs_ioctl_quota_rescan_wait(struct file *file, void __user *arg) if (!capable(CAP_SYS_ADMIN)) return -EPERM; - return btrfs_qgroup_wait_for_completion(root->fs_info); + return btrfs_qgroup_wait_for_completion(root->fs_info, true); } static long _btrfs_ioctl_set_received_subvol(struct file *file, diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 3fe295e2c84a..13eb6a7a4db1 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -995,7 +995,7 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans, goto out; fs_info->quota_enabled = 0; fs_info->pending_quota_state = 0; - btrfs_qgroup_wait_for_completion(fs_info); + btrfs_qgroup_wait_for_completion(fs_info, false); spin_lock(&fs_info->qgroup_lock); quota_root = fs_info->quota_root; fs_info->quota_root = NULL; @@ -2494,7 +2494,8 @@ btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info) return 0; } -int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info) +int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info, + bool interruptible) { int running; int ret = 0; @@ -2505,9 +2506,14 @@ int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info) spin_unlock(&fs_info->qgroup_lock); mutex_unlock(&fs_info->qgroup_rescan_lock); - if (running) + if (!running) + return 0; + + if (interruptible) ret = wait_for_completion_interruptible( &fs_info->qgroup_rescan_completion); + else + wait_for_completion(&fs_info->qgroup_rescan_completion); return ret; } diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index 710887c06aaf..af3e5578cad7 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -46,7 +46,8 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); int btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info); void btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info); -int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info); +int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info, + bool interruptible); int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 src, u64 dst); int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans, From cb93b52cc005ba0e470845b519c662e661d5113c Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Mon, 15 Aug 2016 10:36:50 +0800 Subject: [PATCH 369/531] btrfs: qgroup: Refactor btrfs_qgroup_insert_dirty_extent() Refactor btrfs_qgroup_insert_dirty_extent() function, to two functions: 1. btrfs_qgroup_insert_dirty_extent_nolock() Almost the same with original code. For delayed_ref usage, which has delayed refs locked. Change the return value type to int, since caller never needs the pointer, but only needs to know if they need to free the allocated memory. 2. btrfs_qgroup_insert_dirty_extent() The more encapsulated version. Will do the delayed_refs lock, memory allocation, quota enabled check and other things. The original design is to keep exported functions to minimal, but since more btrfs hacks exposed, like replacing path in balance, we need to record dirty extents manually, so we have to add such functions. Also, add comment for both functions, to info developers how to keep qgroup correct when doing hacks. Cc: Mark Fasheh Signed-off-by: Qu Wenruo Reviewed-and-Tested-by: Goldwyn Rodrigues Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/delayed-ref.c | 7 ++----- fs/btrfs/extent-tree.c | 37 +++++-------------------------------- fs/btrfs/qgroup.c | 41 +++++++++++++++++++++++++++++++++++------ fs/btrfs/qgroup.h | 33 +++++++++++++++++++++++++++++---- 4 files changed, 71 insertions(+), 47 deletions(-) diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index d9ddcfc18c91..ac02e041464b 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -541,7 +541,6 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_head *existing; struct btrfs_delayed_ref_head *head_ref = NULL; struct btrfs_delayed_ref_root *delayed_refs; - struct btrfs_qgroup_extent_record *qexisting; int count_mod = 1; int must_insert_reserved = 0; @@ -606,10 +605,8 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info, qrecord->num_bytes = num_bytes; qrecord->old_roots = NULL; - qexisting = btrfs_qgroup_insert_dirty_extent(fs_info, - delayed_refs, - qrecord); - if (qexisting) + if(btrfs_qgroup_insert_dirty_extent_nolock(fs_info, + delayed_refs, qrecord)) kfree(qrecord); } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index d2cc16ff3e21..d10872748c43 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -8521,35 +8521,6 @@ static noinline void reada_walk_down(struct btrfs_trans_handle *trans, wc->reada_slot = slot; } -/* - * These may not be seen by the usual inc/dec ref code so we have to - * add them here. - */ -static int record_one_subtree_extent(struct btrfs_trans_handle *trans, - struct btrfs_root *root, u64 bytenr, - u64 num_bytes) -{ - struct btrfs_qgroup_extent_record *qrecord; - struct btrfs_delayed_ref_root *delayed_refs; - - qrecord = kmalloc(sizeof(*qrecord), GFP_NOFS); - if (!qrecord) - return -ENOMEM; - - qrecord->bytenr = bytenr; - qrecord->num_bytes = num_bytes; - qrecord->old_roots = NULL; - - delayed_refs = &trans->transaction->delayed_refs; - spin_lock(&delayed_refs->lock); - if (btrfs_qgroup_insert_dirty_extent(trans->fs_info, - delayed_refs, qrecord)) - kfree(qrecord); - spin_unlock(&delayed_refs->lock); - - return 0; -} - static int account_leaf_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *eb) @@ -8583,7 +8554,8 @@ static int account_leaf_items(struct btrfs_trans_handle *trans, num_bytes = btrfs_file_extent_disk_num_bytes(eb, fi); - ret = record_one_subtree_extent(trans, root, bytenr, num_bytes); + ret = btrfs_qgroup_insert_dirty_extent(trans, root->fs_info, + bytenr, num_bytes, GFP_NOFS); if (ret) return ret; } @@ -8732,8 +8704,9 @@ static int account_shared_subtree(struct btrfs_trans_handle *trans, btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); path->locks[level] = BTRFS_READ_LOCK_BLOCKING; - ret = record_one_subtree_extent(trans, root, child_bytenr, - root->nodesize); + ret = btrfs_qgroup_insert_dirty_extent(trans, + root->fs_info, child_bytenr, + root->nodesize, GFP_NOFS); if (ret) goto out; } diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 13eb6a7a4db1..8db2e29fdcf4 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1453,10 +1453,9 @@ int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans, return ret; } -struct btrfs_qgroup_extent_record * -btrfs_qgroup_insert_dirty_extent(struct btrfs_fs_info *fs_info, - struct btrfs_delayed_ref_root *delayed_refs, - struct btrfs_qgroup_extent_record *record) +int btrfs_qgroup_insert_dirty_extent_nolock(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_root *delayed_refs, + struct btrfs_qgroup_extent_record *record) { struct rb_node **p = &delayed_refs->dirty_extent_root.rb_node; struct rb_node *parent_node = NULL; @@ -1475,12 +1474,42 @@ btrfs_qgroup_insert_dirty_extent(struct btrfs_fs_info *fs_info, else if (bytenr > entry->bytenr) p = &(*p)->rb_right; else - return entry; + return 1; } rb_link_node(&record->node, parent_node, p); rb_insert_color(&record->node, &delayed_refs->dirty_extent_root); - return NULL; + return 0; +} + +int btrfs_qgroup_insert_dirty_extent(struct btrfs_trans_handle *trans, + struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes, + gfp_t gfp_flag) +{ + struct btrfs_qgroup_extent_record *record; + struct btrfs_delayed_ref_root *delayed_refs; + int ret; + + if (!fs_info->quota_enabled || bytenr == 0 || num_bytes == 0) + return 0; + if (WARN_ON(trans == NULL)) + return -EINVAL; + record = kmalloc(sizeof(*record), gfp_flag); + if (!record) + return -ENOMEM; + + delayed_refs = &trans->transaction->delayed_refs; + record->bytenr = bytenr; + record->num_bytes = num_bytes; + record->old_roots = NULL; + + spin_lock(&delayed_refs->lock); + ret = btrfs_qgroup_insert_dirty_extent_nolock(fs_info, delayed_refs, + record); + spin_unlock(&delayed_refs->lock); + if (ret > 0) + kfree(record); + return 0; } #define UPDATE_NEW 0 diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index af3e5578cad7..1bc64c864b62 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -64,10 +64,35 @@ void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info); struct btrfs_delayed_extent_op; int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); -struct btrfs_qgroup_extent_record * -btrfs_qgroup_insert_dirty_extent(struct btrfs_fs_info *fs_info, - struct btrfs_delayed_ref_root *delayed_refs, - struct btrfs_qgroup_extent_record *record); +/* + * Insert one dirty extent record into @delayed_refs, informing qgroup to + * account that extent at commit trans time. + * + * No lock version, caller must acquire delayed ref lock and allocate memory. + * + * Return 0 for success insert + * Return >0 for existing record, caller can free @record safely. + * Error is not possible + */ +int btrfs_qgroup_insert_dirty_extent_nolock( + struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_root *delayed_refs, + struct btrfs_qgroup_extent_record *record); + +/* + * Insert one dirty extent record into @delayed_refs, informing qgroup to + * account that extent at commit trans time. + * + * Better encapsulated version. + * + * Return 0 if the operation is done. + * Return <0 for error, like memory allocation failure or invalid parameter + * (NULL trans) + */ +int btrfs_qgroup_insert_dirty_extent(struct btrfs_trans_handle *trans, + struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes, + gfp_t gfp_flag); + int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, From 62b99540a1d91e46422f0e04de50fc723812c421 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Mon, 15 Aug 2016 10:36:51 +0800 Subject: [PATCH 370/531] btrfs: relocation: Fix leaking qgroups numbers on data extents This patch fixes a REGRESSION introduced in 4.2, caused by the big quota rework. When balancing data extents, qgroup will leak all its numbers for relocated data extents. The relocation is done in the following steps for data extents: 1) Create data reloc tree and inode 2) Copy all data extents to data reloc tree And commit transaction 3) Create tree reloc tree(special snapshot) for any related subvolumes 4) Replace file extent in tree reloc tree with new extents in data reloc tree And commit transaction 5) Merge tree reloc tree with original fs, by swapping tree blocks For 1)~4), since tree reloc tree and data reloc tree doesn't count to qgroup, everything is OK. But for 5), the swapping of tree blocks will only info qgroup to track metadata extents. If metadata extents contain file extents, qgroup number for file extents will get lost, leading to corrupted qgroup accounting. The fix is, before commit transaction of step 5), manually info qgroup to track all file extents in data reloc tree. Since at commit transaction time, the tree swapping is done, and qgroup will account these data extents correctly. Cc: Mark Fasheh Reported-by: Mark Fasheh Reported-by: Filipe Manana Signed-off-by: Qu Wenruo Tested-by: Goldwyn Rodrigues Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/relocation.c | 109 +++++++++++++++++++++++++++++++++++++++--- 1 file changed, 103 insertions(+), 6 deletions(-) diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index b26a5aea41b4..27480ef9813c 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -31,6 +31,7 @@ #include "async-thread.h" #include "free-space-cache.h" #include "inode-map.h" +#include "qgroup.h" /* * backref_node, mapping_node and tree_block start with this @@ -3916,6 +3917,90 @@ int prepare_to_relocate(struct reloc_control *rc) return 0; } +/* + * Qgroup fixer for data chunk relocation. + * The data relocation is done in the following steps + * 1) Copy data extents into data reloc tree + * 2) Create tree reloc tree(special snapshot) for related subvolumes + * 3) Modify file extents in tree reloc tree + * 4) Merge tree reloc tree with original fs tree, by swapping tree blocks + * + * The problem is, data and tree reloc tree are not accounted to qgroup, + * and 4) will only info qgroup to track tree blocks change, not file extents + * in the tree blocks. + * + * The good news is, related data extents are all in data reloc tree, so we + * only need to info qgroup to track all file extents in data reloc tree + * before commit trans. + */ +static int qgroup_fix_relocated_data_extents(struct btrfs_trans_handle *trans, + struct reloc_control *rc) +{ + struct btrfs_fs_info *fs_info = rc->extent_root->fs_info; + struct inode *inode = rc->data_inode; + struct btrfs_root *data_reloc_root = BTRFS_I(inode)->root; + struct btrfs_path *path; + struct btrfs_key key; + int ret = 0; + + if (!fs_info->quota_enabled) + return 0; + + /* + * Only for stage where we update data pointers the qgroup fix is + * valid. + * For MOVING_DATA stage, we will miss the timing of swapping tree + * blocks, and won't fix it. + */ + if (!(rc->stage == UPDATE_DATA_PTRS && rc->extents_found)) + return 0; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + key.objectid = btrfs_ino(inode); + key.type = BTRFS_EXTENT_DATA_KEY; + key.offset = 0; + + ret = btrfs_search_slot(NULL, data_reloc_root, &key, path, 0, 0); + if (ret < 0) + goto out; + + lock_extent(&BTRFS_I(inode)->io_tree, 0, (u64)-1); + while (1) { + struct btrfs_file_extent_item *fi; + + btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); + if (key.objectid > btrfs_ino(inode)) + break; + if (key.type != BTRFS_EXTENT_DATA_KEY) + goto next; + fi = btrfs_item_ptr(path->nodes[0], path->slots[0], + struct btrfs_file_extent_item); + if (btrfs_file_extent_type(path->nodes[0], fi) != + BTRFS_FILE_EXTENT_REG) + goto next; + ret = btrfs_qgroup_insert_dirty_extent(trans, fs_info, + btrfs_file_extent_disk_bytenr(path->nodes[0], fi), + btrfs_file_extent_disk_num_bytes(path->nodes[0], fi), + GFP_NOFS); + if (ret < 0) + break; +next: + ret = btrfs_next_item(data_reloc_root, path); + if (ret < 0) + break; + if (ret > 0) { + ret = 0; + break; + } + } + unlock_extent(&BTRFS_I(inode)->io_tree, 0 , (u64)-1); +out: + btrfs_free_path(path); + return ret; +} + static noinline_for_stack int relocate_block_group(struct reloc_control *rc) { struct rb_root blocks = RB_ROOT; @@ -4102,10 +4187,16 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc) /* get rid of pinned extents */ trans = btrfs_join_transaction(rc->extent_root); - if (IS_ERR(trans)) + if (IS_ERR(trans)) { err = PTR_ERR(trans); - else - btrfs_commit_transaction(trans, rc->extent_root); + goto out_free; + } + err = qgroup_fix_relocated_data_extents(trans, rc); + if (err < 0) { + btrfs_abort_transaction(trans, err); + goto out_free; + } + btrfs_commit_transaction(trans, rc->extent_root); out_free: btrfs_free_block_rsv(rc->extent_root, rc->block_rsv); btrfs_free_path(path); @@ -4468,10 +4559,16 @@ int btrfs_recover_relocation(struct btrfs_root *root) unset_reloc_control(rc); trans = btrfs_join_transaction(rc->extent_root); - if (IS_ERR(trans)) + if (IS_ERR(trans)) { err = PTR_ERR(trans); - else - err = btrfs_commit_transaction(trans, rc->extent_root); + goto out_free; + } + err = qgroup_fix_relocated_data_extents(trans, rc); + if (err < 0) { + btrfs_abort_transaction(trans, err); + goto out_free; + } + err = btrfs_commit_transaction(trans, rc->extent_root); out_free: kfree(rc); out: From df2c95f33e0a28b22509e4ee85365eedf32a1056 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Mon, 15 Aug 2016 10:36:52 +0800 Subject: [PATCH 371/531] btrfs: qgroup: Fix qgroup incorrectness caused by log replay When doing log replay at mount time(after power loss), qgroup will leak numbers of replayed data extents. The cause is almost the same of balance. So fix it by manually informing qgroup for owner changed extents. The bug can be detected by btrfs/119 test case. Cc: Mark Fasheh Signed-off-by: Qu Wenruo Reviewed-and-Tested-by: Goldwyn Rodrigues Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/tree-log.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index fff3f3efa436..ffe92da81b8a 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -27,6 +27,7 @@ #include "backref.h" #include "hash.h" #include "compression.h" +#include "qgroup.h" /* magic values for the inode_only field in btrfs_log_inode: * @@ -680,6 +681,21 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, ins.type = BTRFS_EXTENT_ITEM_KEY; offset = key->offset - btrfs_file_extent_offset(eb, item); + /* + * Manually record dirty extent, as here we did a shallow + * file extent item copy and skip normal backref update, + * but modifying extent tree all by ourselves. + * So need to manually record dirty extent for qgroup, + * as the owner of the file extent changed from log tree + * (doesn't affect qgroup) to fs/file tree(affects qgroup) + */ + ret = btrfs_qgroup_insert_dirty_extent(trans, root->fs_info, + btrfs_file_extent_disk_bytenr(eb, item), + btrfs_file_extent_disk_num_bytes(eb, item), + GFP_NOFS); + if (ret < 0) + goto out; + if (ins.objectid > 0) { u64 csum_start; u64 csum_end; From dcb40c196fc85c6dfb28456480e5a882e26f567d Mon Sep 17 00:00:00 2001 From: Wang Xiaoguang Date: Mon, 25 Jul 2016 15:51:38 +0800 Subject: [PATCH 372/531] btrfs: use correct offset for reloc_inode in prealloc_file_extent_cluster() In prealloc_file_extent_cluster(), btrfs_check_data_free_space() uses wrong file offset for reloc_inode, it uses cluster->start and cluster->end, which indeed are extent's bytenr. The correct value should be cluster->[start|end] minus block group's start bytenr. start bytenr cluster->start | | extent | extent | ...| extent | |----------------------------------------------------------------| | block group reloc_inode | Signed-off-by: Wang Xiaoguang Reviewed-by: Josef Bacik Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/relocation.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 27480ef9813c..71b4b70f56b9 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -3038,12 +3038,14 @@ int prealloc_file_extent_cluster(struct inode *inode, u64 num_bytes; int nr = 0; int ret = 0; + u64 prealloc_start = cluster->start - offset; + u64 prealloc_end = cluster->end - offset; BUG_ON(cluster->start != cluster->boundary[0]); inode_lock(inode); - ret = btrfs_check_data_free_space(inode, cluster->start, - cluster->end + 1 - cluster->start); + ret = btrfs_check_data_free_space(inode, prealloc_start, + prealloc_end + 1 - prealloc_start); if (ret) goto out; @@ -3064,8 +3066,8 @@ int prealloc_file_extent_cluster(struct inode *inode, break; nr++; } - btrfs_free_reserved_data_space(inode, cluster->start, - cluster->end + 1 - cluster->start); + btrfs_free_reserved_data_space(inode, prealloc_start, + prealloc_end + 1 - prealloc_start); out: inode_unlock(inode); return ret; From 4824f1f412f75e9f84b9cecbde828e8f4699f82d Mon Sep 17 00:00:00 2001 From: Wang Xiaoguang Date: Mon, 25 Jul 2016 15:51:39 +0800 Subject: [PATCH 373/531] btrfs: divide btrfs_update_reserved_bytes() into two functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch divides btrfs_update_reserved_bytes() into btrfs_add_reserved_bytes() and btrfs_free_reserved_bytes(), and next patch will extend btrfs_add_reserved_bytes（）to fix some false ENOSPC error, please see later patch for detailed info. Signed-off-by: Wang Xiaoguang Reviewed-by: Josef Bacik Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/extent-tree.c | 97 +++++++++++++++++++++++++----------------- 1 file changed, 57 insertions(+), 40 deletions(-) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index d10872748c43..f1121db65878 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -104,9 +104,10 @@ static int find_next_key(struct btrfs_path *path, int level, struct btrfs_key *key); static void dump_space_info(struct btrfs_space_info *info, u64 bytes, int dump_block_groups); -static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache, - u64 num_bytes, int reserve, - int delalloc); +static int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache, + u64 num_bytes, int reserve, int delalloc); +static int btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache, + u64 num_bytes, int delalloc); static int block_rsv_use_bytes(struct btrfs_block_rsv *block_rsv, u64 num_bytes); int btrfs_pin_extent(struct btrfs_root *root, @@ -6497,19 +6498,14 @@ void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg) } /** - * btrfs_update_reserved_bytes - update the block_group and space info counters + * btrfs_add_reserved_bytes - update the block_group and space info counters * @cache: The cache we are manipulating * @num_bytes: The number of bytes in question * @reserve: One of the reservation enums * @delalloc: The blocks are allocated for the delalloc write * - * This is called by the allocator when it reserves space, or by somebody who is - * freeing space that was never actually used on disk. For example if you - * reserve some space for a new leaf in transaction A and before transaction A - * commits you free that leaf, you call this with reserve set to 0 in order to - * clear the reservation. - * - * Metadata reservations should be called with RESERVE_ALLOC so we do the proper + * This is called by the allocator when it reserves space. Metadata + * reservations should be called with RESERVE_ALLOC so we do the proper * ENOSPC accounting. For data we handle the reservation through clearing the * delalloc bits in the io_tree. We have to do this since we could end up * allocating less disk space for the amount of data we have reserved in the @@ -6519,44 +6515,65 @@ void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg) * make the reservation and return -EAGAIN, otherwise this function always * succeeds. */ -static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache, - u64 num_bytes, int reserve, int delalloc) +static int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache, + u64 num_bytes, int reserve, int delalloc) { struct btrfs_space_info *space_info = cache->space_info; int ret = 0; spin_lock(&space_info->lock); spin_lock(&cache->lock); - if (reserve != RESERVE_FREE) { - if (cache->ro) { - ret = -EAGAIN; - } else { - cache->reserved += num_bytes; - space_info->bytes_reserved += num_bytes; - if (reserve == RESERVE_ALLOC) { - trace_btrfs_space_reservation(cache->fs_info, - "space_info", space_info->flags, - num_bytes, 0); - space_info->bytes_may_use -= num_bytes; - } - - if (delalloc) - cache->delalloc_bytes += num_bytes; - } + if (cache->ro) { + ret = -EAGAIN; } else { - if (cache->ro) - space_info->bytes_readonly += num_bytes; - cache->reserved -= num_bytes; - space_info->bytes_reserved -= num_bytes; + cache->reserved += num_bytes; + space_info->bytes_reserved += num_bytes; + if (reserve == RESERVE_ALLOC) { + trace_btrfs_space_reservation(cache->fs_info, + "space_info", space_info->flags, + num_bytes, 0); + space_info->bytes_may_use -= num_bytes; + } if (delalloc) - cache->delalloc_bytes -= num_bytes; + cache->delalloc_bytes += num_bytes; } spin_unlock(&cache->lock); spin_unlock(&space_info->lock); return ret; } +/** + * btrfs_free_reserved_bytes - update the block_group and space info counters + * @cache: The cache we are manipulating + * @num_bytes: The number of bytes in question + * @delalloc: The blocks are allocated for the delalloc write + * + * This is called by somebody who is freeing space that was never actually used + * on disk. For example if you reserve some space for a new leaf in transaction + * A and before transaction A commits you free that leaf, you call this with + * reserve set to 0 in order to clear the reservation. + */ + +static int btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache, + u64 num_bytes, int delalloc) +{ + struct btrfs_space_info *space_info = cache->space_info; + int ret = 0; + + spin_lock(&space_info->lock); + spin_lock(&cache->lock); + if (cache->ro) + space_info->bytes_readonly += num_bytes; + cache->reserved -= num_bytes; + space_info->bytes_reserved -= num_bytes; + + if (delalloc) + cache->delalloc_bytes -= num_bytes; + spin_unlock(&cache->lock); + spin_unlock(&space_info->lock); + return ret; +} void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans, struct btrfs_root *root) { @@ -7191,7 +7208,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags)); btrfs_add_free_space(cache, buf->start, buf->len); - btrfs_update_reserved_bytes(cache, buf->len, RESERVE_FREE, 0); + btrfs_free_reserved_bytes(cache, buf->len, 0); btrfs_put_block_group(cache); trace_btrfs_reserved_extent_free(root, buf->start, buf->len); pin = 0; @@ -7763,8 +7780,8 @@ static noinline int find_free_extent(struct btrfs_root *orig_root, search_start - offset); BUG_ON(offset > search_start); - ret = btrfs_update_reserved_bytes(block_group, num_bytes, - alloc_type, delalloc); + ret = btrfs_add_reserved_bytes(block_group, num_bytes, + alloc_type, delalloc); if (ret == -EAGAIN) { btrfs_add_free_space(block_group, offset, num_bytes); goto loop; @@ -7995,7 +8012,7 @@ static int __btrfs_free_reserved_extent(struct btrfs_root *root, if (btrfs_test_opt(root->fs_info, DISCARD)) ret = btrfs_discard_extent(root, start, len, NULL); btrfs_add_free_space(cache, start, len); - btrfs_update_reserved_bytes(cache, len, RESERVE_FREE, delalloc); + btrfs_free_reserved_bytes(cache, len, delalloc); trace_btrfs_reserved_extent_free(root, start, len); } @@ -8223,8 +8240,8 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans, if (!block_group) return -EINVAL; - ret = btrfs_update_reserved_bytes(block_group, ins->offset, - RESERVE_ALLOC_NO_ACCOUNT, 0); + ret = btrfs_add_reserved_bytes(block_group, ins->offset, + RESERVE_ALLOC_NO_ACCOUNT, 0); BUG_ON(ret); /* logic error */ ret = alloc_reserved_file_extent(trans, root, 0, root_objectid, 0, owner, offset, ins, 1); From 18513091af9483ba84328d42092bd4d42a3c958f Mon Sep 17 00:00:00 2001 From: Wang Xiaoguang Date: Mon, 25 Jul 2016 15:51:40 +0800 Subject: [PATCH 374/531] btrfs: update btrfs_space_info's bytes_may_use timely This patch can fix some false ENOSPC errors, below test script can reproduce one false ENOSPC error: #!/bin/bash dd if=/dev/zero of=fs.img bs=$((1024*1024)) count=128 dev=$(losetup --show -f fs.img) mkfs.btrfs -f -M $dev mkdir /tmp/mntpoint mount $dev /tmp/mntpoint cd /tmp/mntpoint xfs_io -f -c "falloc 0 $((64*1024*1024))" testfile Above script will fail for ENOSPC reason, but indeed fs still has free space to satisfy this request. Please see call graph: btrfs_fallocate() |-> btrfs_alloc_data_chunk_ondemand() | bytes_may_use += 64M |-> btrfs_prealloc_file_range() |-> btrfs_reserve_extent() |-> btrfs_add_reserved_bytes() | alloc_type is RESERVE_ALLOC_NO_ACCOUNT, so it does not | change bytes_may_use, and bytes_reserved += 64M. Now | bytes_may_use + bytes_reserved == 128M, which is greater | than btrfs_space_info's total_bytes, false enospc occurs. | Note, the bytes_may_use decrease operation will be done in | end of btrfs_fallocate(), which is too late. Here is another simple case for buffered write: CPU 1 | CPU 2 | |-> cow_file_range() |-> __btrfs_buffered_write() |-> btrfs_reserve_extent() | | | | | | | | | ..... | |-> btrfs_check_data_free_space() | | | | |-> extent_clear_unlock_delalloc() | In CPU 1, btrfs_reserve_extent()->find_free_extent()-> btrfs_add_reserved_bytes() do not decrease bytes_may_use, the decrease operation will be delayed to be done in extent_clear_unlock_delalloc(). Assume in this case, btrfs_reserve_extent() reserved 128MB data, CPU2's btrfs_check_data_free_space() tries to reserve 100MB data space. If 100MB > data_sinfo->total_bytes - data_sinfo->bytes_used - data_sinfo->bytes_reserved - data_sinfo->bytes_pinned - data_sinfo->bytes_readonly - data_sinfo->bytes_may_use btrfs_check_data_free_space() will try to allcate new data chunk or call btrfs_start_delalloc_roots(), or commit current transaction in order to reserve some free space, obviously a lot of work. But indeed it's not necessary as long as decreasing bytes_may_use timely, we still have free space, decreasing 128M from bytes_may_use. To fix this issue, this patch chooses to update bytes_may_use for both data and metadata in btrfs_add_reserved_bytes(). For compress path, real extent length may not be equal to file content length, so introduce a ram_bytes argument for btrfs_reserve_extent(), find_free_extent() and btrfs_add_reserved_bytes(), it's becasue bytes_may_use is increased by file content length. Then compress path can update bytes_may_use correctly. Also now we can discard RESERVE_ALLOC_NO_ACCOUNT, RESERVE_ALLOC and RESERVE_FREE. As we know, usually EXTENT_DO_ACCOUNTING is used for error path. In run_delalloc_nocow(), for inode marked as NODATACOW or extent marked as PREALLOC, we also need to update bytes_may_use, but can not pass EXTENT_DO_ACCOUNTING, because it also clears metadata reservation, so here we introduce EXTENT_CLEAR_DATA_RESV flag to indicate btrfs_clear_bit_hook() to update btrfs_space_info's bytes_may_use. Meanwhile __btrfs_prealloc_file_range() will call btrfs_free_reserved_data_space() internally for both sucessful and failed path, btrfs_prealloc_file_range()'s callers does not need to call btrfs_free_reserved_data_space() any more. Signed-off-by: Wang Xiaoguang Reviewed-by: Josef Bacik Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/ctree.h | 2 +- fs/btrfs/extent-tree.c | 56 ++++++++++++++---------------------------- fs/btrfs/extent_io.h | 1 + fs/btrfs/file.c | 26 +++++++++++--------- fs/btrfs/inode-map.c | 3 +-- fs/btrfs/inode.c | 37 ++++++++++++++++++++-------- fs/btrfs/relocation.c | 11 +++++++-- 7 files changed, 73 insertions(+), 63 deletions(-) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index acc6850a118f..09cdff0d58e8 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2579,7 +2579,7 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 root_objectid, u64 owner, u64 offset, struct btrfs_key *ins); -int btrfs_reserve_extent(struct btrfs_root *root, u64 num_bytes, +int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes, u64 num_bytes, u64 min_alloc_size, u64 empty_size, u64 hint_byte, struct btrfs_key *ins, int is_data, int delalloc); int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index f1121db65878..133c93b0a0f1 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -60,21 +60,6 @@ enum { CHUNK_ALLOC_FORCE = 2, }; -/* - * Control how reservations are dealt with. - * - * RESERVE_FREE - freeing a reservation. - * RESERVE_ALLOC - allocating space and we need to update bytes_may_use for - * ENOSPC accounting - * RESERVE_ALLOC_NO_ACCOUNT - allocating space and we should not update - * bytes_may_use as the ENOSPC accounting is done elsewhere - */ -enum { - RESERVE_FREE = 0, - RESERVE_ALLOC = 1, - RESERVE_ALLOC_NO_ACCOUNT = 2, -}; - static int update_block_group(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 num_bytes, int alloc); @@ -105,7 +90,7 @@ static int find_next_key(struct btrfs_path *path, int level, static void dump_space_info(struct btrfs_space_info *info, u64 bytes, int dump_block_groups); static int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache, - u64 num_bytes, int reserve, int delalloc); + u64 ram_bytes, u64 num_bytes, int delalloc); static int btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache, u64 num_bytes, int delalloc); static int block_rsv_use_bytes(struct btrfs_block_rsv *block_rsv, @@ -3502,7 +3487,6 @@ static int cache_save_setup(struct btrfs_block_group_cache *block_group, dcs = BTRFS_DC_SETUP; else if (ret == -ENOSPC) set_bit(BTRFS_TRANS_CACHE_ENOSPC, &trans->transaction->flags); - btrfs_free_reserved_data_space(inode, 0, num_pages); out_put: iput(inode); @@ -6500,8 +6484,9 @@ void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg) /** * btrfs_add_reserved_bytes - update the block_group and space info counters * @cache: The cache we are manipulating + * @ram_bytes: The number of bytes of file content, and will be same to + * @num_bytes except for the compress path. * @num_bytes: The number of bytes in question - * @reserve: One of the reservation enums * @delalloc: The blocks are allocated for the delalloc write * * This is called by the allocator when it reserves space. Metadata @@ -6516,7 +6501,7 @@ void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg) * succeeds. */ static int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache, - u64 num_bytes, int reserve, int delalloc) + u64 ram_bytes, u64 num_bytes, int delalloc) { struct btrfs_space_info *space_info = cache->space_info; int ret = 0; @@ -6528,13 +6513,11 @@ static int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache, } else { cache->reserved += num_bytes; space_info->bytes_reserved += num_bytes; - if (reserve == RESERVE_ALLOC) { - trace_btrfs_space_reservation(cache->fs_info, - "space_info", space_info->flags, - num_bytes, 0); - space_info->bytes_may_use -= num_bytes; - } + trace_btrfs_space_reservation(cache->fs_info, + "space_info", space_info->flags, + ram_bytes, 0); + space_info->bytes_may_use -= ram_bytes; if (delalloc) cache->delalloc_bytes += num_bytes; } @@ -7433,9 +7416,9 @@ btrfs_release_block_group(struct btrfs_block_group_cache *cache, * the free space extent currently. */ static noinline int find_free_extent(struct btrfs_root *orig_root, - u64 num_bytes, u64 empty_size, - u64 hint_byte, struct btrfs_key *ins, - u64 flags, int delalloc) + u64 ram_bytes, u64 num_bytes, u64 empty_size, + u64 hint_byte, struct btrfs_key *ins, + u64 flags, int delalloc) { int ret = 0; struct btrfs_root *root = orig_root->fs_info->extent_root; @@ -7447,8 +7430,6 @@ static noinline int find_free_extent(struct btrfs_root *orig_root, struct btrfs_space_info *space_info; int loop = 0; int index = __get_raid_index(flags); - int alloc_type = (flags & BTRFS_BLOCK_GROUP_DATA) ? - RESERVE_ALLOC_NO_ACCOUNT : RESERVE_ALLOC; bool failed_cluster_refill = false; bool failed_alloc = false; bool use_cluster = true; @@ -7780,8 +7761,8 @@ static noinline int find_free_extent(struct btrfs_root *orig_root, search_start - offset); BUG_ON(offset > search_start); - ret = btrfs_add_reserved_bytes(block_group, num_bytes, - alloc_type, delalloc); + ret = btrfs_add_reserved_bytes(block_group, ram_bytes, + num_bytes, delalloc); if (ret == -EAGAIN) { btrfs_add_free_space(block_group, offset, num_bytes); goto loop; @@ -7953,7 +7934,7 @@ static void dump_space_info(struct btrfs_space_info *info, u64 bytes, up_read(&info->groups_sem); } -int btrfs_reserve_extent(struct btrfs_root *root, +int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes, u64 num_bytes, u64 min_alloc_size, u64 empty_size, u64 hint_byte, struct btrfs_key *ins, int is_data, int delalloc) @@ -7965,8 +7946,8 @@ int btrfs_reserve_extent(struct btrfs_root *root, flags = btrfs_get_alloc_profile(root, is_data); again: WARN_ON(num_bytes < root->sectorsize); - ret = find_free_extent(root, num_bytes, empty_size, hint_byte, ins, - flags, delalloc); + ret = find_free_extent(root, ram_bytes, num_bytes, empty_size, + hint_byte, ins, flags, delalloc); if (!ret && !is_data) { btrfs_dec_block_group_reservations(root->fs_info, ins->objectid); @@ -7975,6 +7956,7 @@ int btrfs_reserve_extent(struct btrfs_root *root, num_bytes = min(num_bytes >> 1, ins->offset); num_bytes = round_down(num_bytes, root->sectorsize); num_bytes = max(num_bytes, min_alloc_size); + ram_bytes = num_bytes; if (num_bytes == min_alloc_size) final_tried = true; goto again; @@ -8241,7 +8223,7 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans, return -EINVAL; ret = btrfs_add_reserved_bytes(block_group, ins->offset, - RESERVE_ALLOC_NO_ACCOUNT, 0); + ins->offset, 0); BUG_ON(ret); /* logic error */ ret = alloc_reserved_file_extent(trans, root, 0, root_objectid, 0, owner, offset, ins, 1); @@ -8385,7 +8367,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, if (IS_ERR(block_rsv)) return ERR_CAST(block_rsv); - ret = btrfs_reserve_extent(root, blocksize, blocksize, + ret = btrfs_reserve_extent(root, blocksize, blocksize, blocksize, empty_size, hint, &ins, 0, 0); if (ret) goto out_unuse; diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index c0c1c4fef6ce..b52ca5db01cb 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -20,6 +20,7 @@ #define EXTENT_DAMAGED (1U << 14) #define EXTENT_NORESERVE (1U << 15) #define EXTENT_QGROUP_RESERVED (1U << 16) +#define EXTENT_CLEAR_DATA_RESV (1U << 17) #define EXTENT_IOBITS (EXTENT_LOCKED | EXTENT_WRITEBACK) #define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING | EXTENT_FIRST_DELALLOC) diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 5842423f8f47..3391f2adf0c8 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2675,6 +2675,7 @@ static long btrfs_fallocate(struct file *file, int mode, alloc_start = round_down(offset, blocksize); alloc_end = round_up(offset + len, blocksize); + cur_offset = alloc_start; /* Make sure we aren't being give some crap mode */ if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) @@ -2767,7 +2768,6 @@ static long btrfs_fallocate(struct file *file, int mode, /* First, check if we exceed the qgroup limit */ INIT_LIST_HEAD(&reserve_list); - cur_offset = alloc_start; while (1) { em = btrfs_get_extent(inode, NULL, 0, cur_offset, alloc_end - cur_offset, 0); @@ -2794,6 +2794,14 @@ static long btrfs_fallocate(struct file *file, int mode, last_byte - cur_offset); if (ret < 0) break; + } else { + /* + * Do not need to reserve unwritten extent for this + * range, free reserved data space first, otherwise + * it'll result in false ENOSPC error. + */ + btrfs_free_reserved_data_space(inode, cur_offset, + last_byte - cur_offset); } free_extent_map(em); cur_offset = last_byte; @@ -2811,6 +2819,9 @@ static long btrfs_fallocate(struct file *file, int mode, range->start, range->len, 1 << inode->i_blkbits, offset + len, &alloc_hint); + else + btrfs_free_reserved_data_space(inode, range->start, + range->len); list_del(&range->list); kfree(range); } @@ -2845,18 +2856,11 @@ static long btrfs_fallocate(struct file *file, int mode, unlock_extent_cached(&BTRFS_I(inode)->io_tree, alloc_start, locked_end, &cached_state, GFP_KERNEL); out: - /* - * As we waited the extent range, the data_rsv_map must be empty - * in the range, as written data range will be released from it. - * And for prealloacted extent, it will also be released when - * its metadata is written. - * So this is completely used as cleanup. - */ - btrfs_qgroup_free_data(inode, alloc_start, alloc_end - alloc_start); inode_unlock(inode); /* Let go of our reservation. */ - btrfs_free_reserved_data_space(inode, alloc_start, - alloc_end - alloc_start); + if (ret != 0) + btrfs_free_reserved_data_space(inode, alloc_start, + alloc_end - cur_offset); return ret; } diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index aa6fabaee72e..359ee861b5a4 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -495,10 +495,9 @@ int btrfs_save_ino_cache(struct btrfs_root *root, ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, prealloc, prealloc, prealloc, &alloc_hint); if (ret) { - btrfs_delalloc_release_space(inode, 0, prealloc); + btrfs_delalloc_release_metadata(inode, prealloc); goto out_put; } - btrfs_free_reserved_data_space(inode, 0, prealloc); ret = btrfs_write_out_ino_cache(root, trans, path, inode); out_put: diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 29636624a427..bcea20015d9a 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -566,6 +566,8 @@ static noinline void compress_file_range(struct inode *inode, PAGE_SET_WRITEBACK | page_error_op | PAGE_END_WRITEBACK); + btrfs_free_reserved_data_space_noquota(inode, start, + end - start + 1); goto free_pages_out; } } @@ -742,7 +744,7 @@ static noinline void submit_compressed_extents(struct inode *inode, lock_extent(io_tree, async_extent->start, async_extent->start + async_extent->ram_size - 1); - ret = btrfs_reserve_extent(root, + ret = btrfs_reserve_extent(root, async_extent->ram_size, async_extent->compressed_size, async_extent->compressed_size, 0, alloc_hint, &ins, 1, 1); @@ -969,7 +971,8 @@ static noinline int cow_file_range(struct inode *inode, EXTENT_DEFRAG, PAGE_UNLOCK | PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK); - + btrfs_free_reserved_data_space_noquota(inode, start, + end - start + 1); *nr_written = *nr_written + (end - start + PAGE_SIZE) / PAGE_SIZE; *page_started = 1; @@ -989,7 +992,7 @@ static noinline int cow_file_range(struct inode *inode, unsigned long op; cur_alloc_size = disk_num_bytes; - ret = btrfs_reserve_extent(root, cur_alloc_size, + ret = btrfs_reserve_extent(root, cur_alloc_size, cur_alloc_size, root->sectorsize, 0, alloc_hint, &ins, 1, 1); if (ret < 0) @@ -1489,8 +1492,10 @@ static noinline int run_delalloc_nocow(struct inode *inode, extent_clear_unlock_delalloc(inode, cur_offset, cur_offset + num_bytes - 1, locked_page, EXTENT_LOCKED | - EXTENT_DELALLOC, PAGE_UNLOCK | - PAGE_SET_PRIVATE2); + EXTENT_DELALLOC | + EXTENT_CLEAR_DATA_RESV, + PAGE_UNLOCK | PAGE_SET_PRIVATE2); + if (!nolock && nocow) btrfs_end_write_no_snapshoting(root); cur_offset = extent_end; @@ -1807,7 +1812,9 @@ static void btrfs_clear_bit_hook(struct inode *inode, return; if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID - && do_list && !(state->state & EXTENT_NORESERVE)) + && do_list && !(state->state & EXTENT_NORESERVE) + && (*bits & (EXTENT_DO_ACCOUNTING | + EXTENT_CLEAR_DATA_RESV))) btrfs_free_reserved_data_space_noquota(inode, state->start, len); @@ -7252,7 +7259,7 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode, int ret; alloc_hint = get_extent_allocation_hint(inode, start, len); - ret = btrfs_reserve_extent(root, len, root->sectorsize, 0, + ret = btrfs_reserve_extent(root, len, len, root->sectorsize, 0, alloc_hint, &ins, 1, 1); if (ret) return ERR_PTR(ret); @@ -7752,6 +7759,13 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, ret = PTR_ERR(em2); goto unlock_err; } + /* + * For inode marked NODATACOW or extent marked PREALLOC, + * use the existing or preallocated extent, so does not + * need to adjust btrfs_space_info's bytes_may_use. + */ + btrfs_free_reserved_data_space_noquota(inode, + start, len); goto unlock; } } @@ -7786,7 +7800,6 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, i_size_write(inode, start + len); adjust_dio_outstanding_extents(inode, dio_data, len); - btrfs_free_reserved_data_space(inode, start, len); WARN_ON(dio_data->reserve < len); dio_data->reserve -= len; dio_data->unsubmitted_oe_range_end = start + len; @@ -10306,6 +10319,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, u64 last_alloc = (u64)-1; int ret = 0; bool own_trans = true; + u64 end = start + num_bytes - 1; if (trans) own_trans = false; @@ -10327,8 +10341,8 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, * sized chunks. */ cur_bytes = min(cur_bytes, last_alloc); - ret = btrfs_reserve_extent(root, cur_bytes, min_size, 0, - *alloc_hint, &ins, 1, 0); + ret = btrfs_reserve_extent(root, cur_bytes, cur_bytes, + min_size, 0, *alloc_hint, &ins, 1, 0); if (ret) { if (own_trans) btrfs_end_transaction(trans, root); @@ -10414,6 +10428,9 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, if (own_trans) btrfs_end_transaction(trans, root); } + if (cur_offset < end) + btrfs_free_reserved_data_space(inode, cur_offset, + end - cur_offset + 1); return ret; } diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 71b4b70f56b9..8a2c2a07987b 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -3040,6 +3040,7 @@ int prealloc_file_extent_cluster(struct inode *inode, int ret = 0; u64 prealloc_start = cluster->start - offset; u64 prealloc_end = cluster->end - offset; + u64 cur_offset; BUG_ON(cluster->start != cluster->boundary[0]); inode_lock(inode); @@ -3049,6 +3050,7 @@ int prealloc_file_extent_cluster(struct inode *inode, if (ret) goto out; + cur_offset = prealloc_start; while (nr < cluster->nr) { start = cluster->boundary[nr] - offset; if (nr + 1 < cluster->nr) @@ -3058,16 +3060,21 @@ int prealloc_file_extent_cluster(struct inode *inode, lock_extent(&BTRFS_I(inode)->io_tree, start, end); num_bytes = end + 1 - start; + if (cur_offset < start) + btrfs_free_reserved_data_space(inode, cur_offset, + start - cur_offset); ret = btrfs_prealloc_file_range(inode, 0, start, num_bytes, num_bytes, end + 1, &alloc_hint); + cur_offset = end + 1; unlock_extent(&BTRFS_I(inode)->io_tree, start, end); if (ret) break; nr++; } - btrfs_free_reserved_data_space(inode, prealloc_start, - prealloc_end + 1 - prealloc_start); + if (cur_offset < prealloc_end) + btrfs_free_reserved_data_space(inode, cur_offset, + prealloc_end + 1 - cur_offset); out: inode_unlock(inode); return ret; From 9e7cc91a6d18a4973c6d2cc104871439c9e94f3d Mon Sep 17 00:00:00 2001 From: Wang Xiaoguang Date: Mon, 1 Aug 2016 13:28:08 +0800 Subject: [PATCH 375/531] btrfs: fix fsfreeze hang caused by delayed iputs deal When running fstests generic/068, sometimes we got below deadlock: xfs_io D ffff8800331dbb20 0 6697 6693 0x00000080 ffff8800331dbb20 ffff88007acfc140 ffff880034d895c0 ffff8800331dc000 ffff880032d243e8 fffffffeffffffff ffff880032d24400 0000000000000001 ffff8800331dbb38 ffffffff816a9045 ffff880034d895c0 ffff8800331dbba8 Call Trace: [] schedule+0x35/0x80 [] rwsem_down_read_failed+0xf2/0x140 [] ? __filemap_fdatawrite_range+0xd1/0x100 [] call_rwsem_down_read_failed+0x18/0x30 [] ? btrfs_alloc_block_rsv+0x2c/0xb0 [btrfs] [] percpu_down_read+0x35/0x50 [] __sb_start_write+0x2c/0x40 [] start_transaction+0x2a5/0x4d0 [btrfs] [] btrfs_join_transaction+0x17/0x20 [btrfs] [] btrfs_evict_inode+0x3c4/0x5d0 [btrfs] [] evict+0xba/0x1a0 [] iput+0x196/0x200 [] btrfs_run_delayed_iputs+0x70/0xc0 [btrfs] [] btrfs_commit_transaction+0x928/0xa80 [btrfs] [] btrfs_freeze+0x30/0x40 [btrfs] [] freeze_super+0xf0/0x190 [] do_vfs_ioctl+0x4a5/0x5c0 [] ? do_audit_syscall_entry+0x66/0x70 [] ? syscall_trace_enter_phase1+0x11f/0x140 [] SyS_ioctl+0x79/0x90 [] do_syscall_64+0x62/0x110 [] entry_SYSCALL64_slow_path+0x25/0x25 >From this warning, freeze_super() already holds SB_FREEZE_FS, but btrfs_freeze() will call btrfs_commit_transaction() again, if btrfs_commit_transaction() finds that it has delayed iputs to handle, it'll start_transaction(), which will try to get SB_FREEZE_FS lock again, then deadlock occurs. The root cause is that in btrfs, sync_filesystem(sb) does not make sure all metadata is updated. There still maybe some codes adding delayed iputs, see below sample race window: CPU1 | CPU2 |-> freeze_super() | |-> sync_filesystem(sb); | | |-> cleaner_kthread() | | |-> btrfs_delete_unused_bgs() | | |-> btrfs_remove_chunk() | | |-> btrfs_remove_block_group() | | |-> btrfs_add_delayed_iput() | | |-> sb->s_writers.frozen = SB_FREEZE_FS; | |-> sb_wait_write(sb, SB_FREEZE_FS); | | acquire SB_FREEZE_FS lock. | | | |-> btrfs_freeze() | |-> btrfs_commit_transaction() | |-> btrfs_run_delayed_iputs() | | will handle delayed iputs, | | that means start_transaction() | | will be called, which will try | | to get SB_FREEZE_FS lock. | To fix this issue, introduce a "int fs_frozen" to record internally whether fs has been frozen. If fs has been frozen, we can not handle delayed iputs. Signed-off-by: Wang Xiaoguang Reviewed-by: David Sterba [ add comment to btrfs_freeze ] Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/ctree.h | 2 ++ fs/btrfs/disk-io.c | 1 + fs/btrfs/super.c | 16 ++++++++++++++++ fs/btrfs/transaction.c | 7 ++++++- 4 files changed, 25 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 09cdff0d58e8..ec4154faab61 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1080,6 +1080,8 @@ struct btrfs_fs_info { struct list_head pinned_chunks; int creating_free_space_tree; + /* Used to record internally whether fs has been frozen */ + int fs_frozen; }; struct btrfs_subvolume_writers { diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 7857f64e1cae..17062223fac3 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2631,6 +2631,7 @@ int open_ctree(struct super_block *sb, atomic_set(&fs_info->qgroup_op_seq, 0); atomic_set(&fs_info->reada_works_cnt, 0); atomic64_set(&fs_info->tree_mod_seq, 0); + fs_info->fs_frozen = 0; fs_info->sb = sb; fs_info->max_inline = BTRFS_DEFAULT_MAX_INLINE; fs_info->metadata_ratio = 0; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 864ce334f696..4071fe2bd098 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -2241,6 +2241,13 @@ static int btrfs_freeze(struct super_block *sb) struct btrfs_trans_handle *trans; struct btrfs_root *root = btrfs_sb(sb)->tree_root; + root->fs_info->fs_frozen = 1; + /* + * We don't need a barrier here, we'll wait for any transaction that + * could be in progress on other threads (and do delayed iputs that + * we want to avoid on a frozen filesystem), or do the commit + * ourselves. + */ trans = btrfs_attach_transaction_barrier(root); if (IS_ERR(trans)) { /* no transaction, don't bother */ @@ -2251,6 +2258,14 @@ static int btrfs_freeze(struct super_block *sb) return btrfs_commit_transaction(trans, root); } +static int btrfs_unfreeze(struct super_block *sb) +{ + struct btrfs_root *root = btrfs_sb(sb)->tree_root; + + root->fs_info->fs_frozen = 0; + return 0; +} + static int btrfs_show_devname(struct seq_file *m, struct dentry *root) { struct btrfs_fs_info *fs_info = btrfs_sb(root->d_sb); @@ -2299,6 +2314,7 @@ static const struct super_operations btrfs_super_ops = { .statfs = btrfs_statfs, .remount_fs = btrfs_remount, .freeze_fs = btrfs_freeze, + .unfreeze_fs = btrfs_unfreeze, }; static const struct file_operations btrfs_ctl_fops = { diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 9cca0a721961..95d41919d034 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -2278,8 +2278,13 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, kmem_cache_free(btrfs_trans_handle_cachep, trans); + /* + * If fs has been frozen, we can not handle delayed iputs, otherwise + * it'll result in deadlock about SB_FREEZE_FS. + */ if (current != root->fs_info->transaction_kthread && - current != root->fs_info->cleaner_kthread) + current != root->fs_info->cleaner_kthread && + !root->fs_info->fs_frozen) btrfs_run_delayed_iputs(root); return ret; From 28b737f6ede3661fe610937706c4a6f50e9ab769 Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Fri, 29 Jul 2016 11:09:50 -0700 Subject: [PATCH 376/531] Btrfs: clarify do_chunk_alloc()'s return value Function start_transaction() can return ERR_PTR(1) when flush is BTRFS_RESERVE_FLUSH_LIMIT, so the call graph is start_transaction (return ERR_PTR(1)) -> btrfs_block_rsv_add (return 1) -> reserve_metadata_bytes (return 1) -> flush_space (return 1) -> do_chunk_alloc (return 1) With BTRFS_RESERVE_FLUSH_LIMIT, if flush_space is already on the flush_state of ALLOC_CHUNK and it successfully allocates a new chunk, then instead of trying to reserve space again, reserve_metadata_bytes returns 1 immediately. Eventually the callers who call start_transaction() usually just do the IS_ERR() check which ERR_PTR(1) can pass, then it'll get a panic when dereferencing a pointer which is ERR_PTR(1). The following patch fixes the above problem. "btrfs: flush_space: treat return value of do_chunk_alloc properly" https://patchwork.kernel.org/patch/7778651/ This add comments to clarify do_chunk_alloc()'s return value. Signed-off-by: Liu Bo Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/extent-tree.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 133c93b0a0f1..d5d3cfb1f66f 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4457,6 +4457,15 @@ void check_system_chunk(struct btrfs_trans_handle *trans, } } +/* + * If force is CHUNK_ALLOC_FORCE: + * - return 1 if it successfully allocates a chunk, + * - return errors including -ENOSPC otherwise. + * If force is NOT CHUNK_ALLOC_FORCE: + * - return 0 if it doesn't need to allocate a new chunk, + * - return 1 if it successfully allocates a chunk, + * - return errors including -ENOSPC otherwise. + */ static int do_chunk_alloc(struct btrfs_trans_handle *trans, struct btrfs_root *extent_root, u64 flags, int force) { From 142388194191a3edc9ba01cfcfd8b691e0971fb2 Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Fri, 22 Jul 2016 06:04:53 +0800 Subject: [PATCH 377/531] btrfs: do not background blkdev_put() At the end of unmount/dev-delete, if the device exclusive open is not actually closed, then there might be a race with another program in the userland who is trying to open the device in exclusive mode and it may fail for eg: unmount /btrfs; fsck /dev/x btrfs dev del /dev/x /btrfs; fsck /dev/x so here background blkdev_put() is not a choice Signed-off-by: Anand Jain Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/volumes.c | 27 +++++++++++++++++++-------- 1 file changed, 19 insertions(+), 8 deletions(-) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index e217035d63df..9a6f0dcb3e9c 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -834,10 +834,6 @@ static void __free_device(struct work_struct *work) struct btrfs_device *device; device = container_of(work, struct btrfs_device, rcu_work); - - if (device->bdev) - blkdev_put(device->bdev, device->mode); - rcu_string_free(device->name); kfree(device); } @@ -852,6 +848,17 @@ static void free_device(struct rcu_head *head) schedule_work(&device->rcu_work); } +static void btrfs_close_bdev(struct btrfs_device *device) +{ + if (device->bdev && device->writeable) { + sync_blockdev(device->bdev); + invalidate_bdev(device->bdev); + } + + if (device->bdev) + blkdev_put(device->bdev, device->mode); +} + static void btrfs_close_one_device(struct btrfs_device *device) { struct btrfs_fs_devices *fs_devices = device->fs_devices; @@ -870,10 +877,7 @@ static void btrfs_close_one_device(struct btrfs_device *device) if (device->missing) fs_devices->missing_devices--; - if (device->bdev && device->writeable) { - sync_blockdev(device->bdev); - invalidate_bdev(device->bdev); - } + btrfs_close_bdev(device); new_device = btrfs_alloc_device(NULL, &device->devid, device->uuid); @@ -1932,6 +1936,8 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path, u64 devid) btrfs_sysfs_rm_device_link(root->fs_info->fs_devices, device); } + btrfs_close_bdev(device); + call_rcu(&device->rcu, free_device); num_devices = btrfs_super_num_devices(root->fs_info->super_copy) - 1; @@ -2025,6 +2031,9 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info, /* zero out the old super if it is writable */ btrfs_scratch_superblocks(srcdev->bdev, srcdev->name->str); } + + btrfs_close_bdev(srcdev); + call_rcu(&srcdev->rcu, free_device); /* @@ -2080,6 +2089,8 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, * the device_list_mutex lock. */ btrfs_scratch_superblocks(tgtdev->bdev, tgtdev->name->str); + + btrfs_close_bdev(tgtdev); call_rcu(&tgtdev->rcu, free_device); } From 187ee58c62c1d0d238d3dc4835869d33e1869906 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Thu, 18 Aug 2016 15:30:06 -0400 Subject: [PATCH 378/531] Btrfs: fix em leak in find_first_block_group We need to call free_extent_map() on the em we look up. Signed-off-by: Josef Bacik Reviewed-by: Omar Sandoval Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/extent-tree.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index d5d3cfb1f66f..60d4ae7ce974 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -9887,6 +9887,7 @@ static int find_first_block_group(struct btrfs_root *root, } else { ret = 0; } + free_extent_map(em); goto out; } path->slots[0]++; From 35bbb97fc898aeb874cb7c8b746f091caa359994 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Wed, 17 Aug 2016 21:58:33 -0400 Subject: [PATCH 379/531] btrfs: don't create or leak aliased root while cleaning up orphans commit 909c3a22da3 (Btrfs: fix loading of orphan roots leading to BUG_ON) avoids the BUG_ON but can add an aliased root to the dead_roots list or leak the root. Since we've already been loading roots into the radix tree, we should use it before looking the root up on disk. Cc: # 4.5 Signed-off-by: Jeff Mahoney Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 4 ++-- fs/btrfs/disk-io.h | 2 ++ fs/btrfs/root-tree.c | 27 ++++++++++++++++++--------- 3 files changed, 22 insertions(+), 11 deletions(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 17062223fac3..edda47162752 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1624,8 +1624,8 @@ int btrfs_init_fs_root(struct btrfs_root *root) return ret; } -static struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info, - u64 root_id) +struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info, + u64 root_id) { struct btrfs_root *root; diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index c9d42c92da2b..e0efe45e5282 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -68,6 +68,8 @@ struct extent_buffer *btrfs_find_tree_block(struct btrfs_fs_info *fs_info, struct btrfs_root *btrfs_read_fs_root(struct btrfs_root *tree_root, struct btrfs_key *location); int btrfs_init_fs_root(struct btrfs_root *root); +struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info, + u64 root_id); int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root); void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info); diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 7fd7e1830cfe..091296062456 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -272,6 +272,23 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root) root_key.objectid = key.offset; key.offset++; + /* + * The root might have been inserted already, as before we look + * for orphan roots, log replay might have happened, which + * triggers a transaction commit and qgroup accounting, which + * in turn reads and inserts fs roots while doing backref + * walking. + */ + root = btrfs_lookup_fs_root(tree_root->fs_info, + root_key.objectid); + if (root) { + WARN_ON(!test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, + &root->state)); + if (btrfs_root_refs(&root->root_item) == 0) + btrfs_add_dead_root(root); + continue; + } + root = btrfs_read_fs_root(tree_root, &root_key); err = PTR_ERR_OR_ZERO(root); if (err && err != -ENOENT) { @@ -310,16 +327,8 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root) set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state); err = btrfs_insert_fs_root(root->fs_info, root); - /* - * The root might have been inserted already, as before we look - * for orphan roots, log replay might have happened, which - * triggers a transaction commit and qgroup accounting, which - * in turn reads and inserts fs roots while doing backref - * walking. - */ - if (err == -EEXIST) - err = 0; if (err) { + BUG_ON(err == -EEXIST); btrfs_free_fs_root(root); break; } From 053ab70f0604224c7893b43f9d9d5efa283580d6 Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Tue, 23 Aug 2016 17:37:45 -0700 Subject: [PATCH 380/531] Btrfs: check btree node's nritems When btree node (level = 1) has nritems which equals to zero, we can end up with panic due to insert_ptr()'s BUG_ON(slot > nritems); where slot is 1 and nritems is 0, as copy_for_split() calls insert_ptr(.., path->slots[1] + 1, ...); A invalid value results in the whole mess, this adds the check for btree's node nritems so that we stop reading block when when something is wrong. Signed-off-by: Liu Bo Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index edda47162752..474209f50844 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -613,6 +613,19 @@ static noinline int check_leaf(struct btrfs_root *root, return 0; } +static int check_node(struct btrfs_root *root, struct extent_buffer *node) +{ + unsigned long nr = btrfs_header_nritems(node); + + if (nr == 0 || nr > BTRFS_NODEPTRS_PER_BLOCK(root)) { + btrfs_crit(root->fs_info, + "corrupt node: block %llu root %llu nritems %lu", + node->start, root->objectid, nr); + return -EIO; + } + return 0; +} + static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, u64 phy_offset, struct page *page, u64 start, u64 end, int mirror) @@ -683,6 +696,9 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, ret = -EIO; } + if (found_level > 0 && check_node(root, eb)) + ret = -EIO; + if (!ret) set_extent_buffer_uptodate(eb); err: From 1ba98d086fe3a14d6a31f2f66dbab70c45d00f63 Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Tue, 23 Aug 2016 15:22:58 -0700 Subject: [PATCH 381/531] Btrfs: detect corruption when non-root leaf has zero item Right now we treat leaf which has zero item as a valid one because we could have an empty tree, that is, a root that is also a leaf without any item, however, in the same case but when the leaf is not a root, we can end up with hitting the BUG_ON(1) in btrfs_extend_item() called by setup_inline_extent_backref(). This makes us check the situation as a corruption if leaf is not its own root. Signed-off-by: Liu Bo Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 474209f50844..70e76ad11fbf 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -560,8 +560,29 @@ static noinline int check_leaf(struct btrfs_root *root, u32 nritems = btrfs_header_nritems(leaf); int slot; - if (nritems == 0) + if (nritems == 0) { + struct btrfs_root *check_root; + + key.objectid = btrfs_header_owner(leaf); + key.type = BTRFS_ROOT_ITEM_KEY; + key.offset = (u64)-1; + + check_root = btrfs_get_fs_root(root->fs_info, &key, false); + /* + * The only reason we also check NULL here is that during + * open_ctree() some roots has not yet been set up. + */ + if (!IS_ERR_OR_NULL(check_root)) { + /* if leaf is the root, then it's fine */ + if (leaf->start != + btrfs_root_bytenr(&check_root->root_item)) { + CORRUPT("non-root leaf's nritems is 0", + leaf, root, 0); + return -EIO; + } + } return 0; + } /* Check the 0 item */ if (btrfs_item_offset_nr(leaf, 0) + btrfs_item_size_nr(leaf, 0) != From 28a235931b56d4e7bdd51f6733daf95f2b269da8 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 23 Aug 2016 21:13:51 +0100 Subject: [PATCH 382/531] Btrfs: fix lockdep warning on deadlock against an inode's log mutex Commit 44f714dae50a ("Btrfs: improve performance on fsync against new inode after rename/unlink"), which landed in 4.8-rc2, introduced a possibility for a deadlock due to double locking of an inode's log mutex by the same task, which lockdep reports with: [23045.433975] ============================================= [23045.434748] [ INFO: possible recursive locking detected ] [23045.435426] 4.7.0-rc6-btrfs-next-34+ #1 Not tainted [23045.436044] --------------------------------------------- [23045.436044] xfs_io/3688 is trying to acquire lock: [23045.436044] (&ei->log_mutex){+.+...}, at: [] btrfs_log_inode+0x13a/0xc95 [btrfs] [23045.436044] but task is already holding lock: [23045.436044] (&ei->log_mutex){+.+...}, at: [] btrfs_log_inode+0x13a/0xc95 [btrfs] [23045.436044] other info that might help us debug this: [23045.436044] Possible unsafe locking scenario: [23045.436044] CPU0 [23045.436044] ---- [23045.436044] lock(&ei->log_mutex); [23045.436044] lock(&ei->log_mutex); [23045.436044] *** DEADLOCK *** [23045.436044] May be due to missing lock nesting notation [23045.436044] 3 locks held by xfs_io/3688: [23045.436044] #0: (&sb->s_type->i_mutex_key#15){+.+...}, at: [] btrfs_sync_file+0x14e/0x425 [btrfs] [23045.436044] #1: (sb_internal#2){.+.+.+}, at: [] __sb_start_write+0x5f/0xb0 [23045.436044] #2: (&ei->log_mutex){+.+...}, at: [] btrfs_log_inode+0x13a/0xc95 [btrfs] [23045.436044] stack backtrace: [23045.436044] CPU: 4 PID: 3688 Comm: xfs_io Not tainted 4.7.0-rc6-btrfs-next-34+ #1 [23045.436044] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.1-0-gb3ef39f-prebuilt.qemu-project.org 04/01/2014 [23045.436044] 0000000000000000 ffff88022f5f7860 ffffffff8127074d ffffffff82a54b70 [23045.436044] ffffffff82a54b70 ffff88022f5f7920 ffffffff81092897 ffff880228015d68 [23045.436044] 0000000000000000 ffffffff82a54b70 ffffffff829c3f00 ffff880228015d68 [23045.436044] Call Trace: [23045.436044] [] dump_stack+0x67/0x90 [23045.436044] [] __lock_acquire+0xcbb/0xe4e [23045.436044] [] ? mark_lock+0x24/0x201 [23045.436044] [] ? mark_held_locks+0x5e/0x74 [23045.436044] [] lock_acquire+0x12f/0x1c3 [23045.436044] [] ? lock_acquire+0x12f/0x1c3 [23045.436044] [] ? btrfs_log_inode+0x13a/0xc95 [btrfs] [23045.436044] [] ? btrfs_log_inode+0x13a/0xc95 [btrfs] [23045.436044] [] mutex_lock_nested+0x77/0x3a7 [23045.436044] [] ? btrfs_log_inode+0x13a/0xc95 [btrfs] [23045.436044] [] ? btrfs_release_delayed_node+0xb/0xd [btrfs] [23045.436044] [] btrfs_log_inode+0x13a/0xc95 [btrfs] [23045.436044] [] ? btrfs_log_inode+0x13a/0xc95 [btrfs] [23045.436044] [] ? vprintk_emit+0x453/0x465 [23045.436044] [] btrfs_log_inode+0x66e/0xc95 [btrfs] [23045.436044] [] log_new_dir_dentries+0x26c/0x359 [btrfs] [23045.436044] [] btrfs_log_inode_parent+0x4a6/0x628 [btrfs] [23045.436044] [] btrfs_log_dentry_safe+0x5a/0x75 [btrfs] [23045.436044] [] btrfs_sync_file+0x304/0x425 [btrfs] [23045.436044] [] vfs_fsync_range+0x8c/0x9e [23045.436044] [] vfs_fsync+0x1c/0x1e [23045.436044] [] do_fsync+0x31/0x4a [23045.436044] [] SyS_fsync+0x10/0x14 [23045.436044] [] entry_SYSCALL_64_fastpath+0x18/0xa8 [23045.436044] [] ? trace_hardirqs_off_caller+0x3f/0xaa An example reproducer for this is: $ mkfs.btrfs -f /dev/sdb $ mount /dev/sdb /mnt $ mkdir /mnt/dir $ touch /mnt/dir/foo $ sync $ mv /mnt/dir/foo /mnt/dir/bar $ touch /mnt/dir/foo $ xfs_io -c "fsync" /mnt/dir/bar This is because while logging the inode of file bar we end up logging its parent directory (since its inode has an unlink_trans field matching the current transaction id due to the rename operation), which in turn logs the inodes for all its new dentries, so that the new inode for the new file named foo gets logged which in turn triggered another logging attempt for the inode we are fsync'ing, since that inode had an old name that corresponds to the name of the new inode. So fix this by ensuring that when logging the inode for a new dentry that has a name matching an old name of some other inode, we don't log again the original inode that we are fsync'ing. Fixes: 44f714dae50a ("Btrfs: improve performance on fsync against new inode after rename/unlink") Signed-off-by: Filipe Manana Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/file.c | 2 +- fs/btrfs/tree-log.c | 5 +++-- fs/btrfs/tree-log.h | 5 ++++- 3 files changed, 8 insertions(+), 4 deletions(-) diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 3391f2adf0c8..fea31a4a6e36 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2070,7 +2070,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) } trans->sync = true; - btrfs_init_log_ctx(&ctx); + btrfs_init_log_ctx(&ctx, inode); ret = btrfs_log_dentry_safe(trans, root, dentry, start, end, &ctx); if (ret < 0) { diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index ffe92da81b8a..e935035ac034 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2823,7 +2823,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, */ mutex_unlock(&root->log_mutex); - btrfs_init_log_ctx(&root_log_ctx); + btrfs_init_log_ctx(&root_log_ctx, NULL); mutex_lock(&log_root_tree->log_mutex); atomic_inc(&log_root_tree->log_batch); @@ -4757,7 +4757,8 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, if (ret < 0) { err = ret; goto out_unlock; - } else if (ret > 0) { + } else if (ret > 0 && ctx && + other_ino != btrfs_ino(ctx->inode)) { struct btrfs_key inode_key; struct inode *other_inode; diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h index a9f1b75d080d..ab858e31ccbc 100644 --- a/fs/btrfs/tree-log.h +++ b/fs/btrfs/tree-log.h @@ -30,15 +30,18 @@ struct btrfs_log_ctx { int log_transid; int io_err; bool log_new_dentries; + struct inode *inode; struct list_head list; }; -static inline void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx) +static inline void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx, + struct inode *inode) { ctx->log_ret = 0; ctx->log_transid = 0; ctx->io_err = 0; ctx->log_new_dentries = false; + ctx->inode = inode; INIT_LIST_HEAD(&ctx->list); } From 5bb53c0fb8e0fc2e34287d5d0fcadc784de913e1 Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Tue, 23 Aug 2016 18:55:31 +0300 Subject: [PATCH 383/531] fs/block_dev: fix potential NULL ptr deref in freeze_bdev() Calling freeze_bdev() twice on the same block device without mounted filesystem get_super() will return NULL, which will lead to NULL-ptr dereference later in drop_super(). Check get_super() result to fix that. Note, that this is a purely theoretical issue. We have only 3 freeze_bdev() callers. 2 of them are in filesystem code and used on a device with mounted fs. The third one in lock_fs() has protection in upper-layer code against freezing block device the second time without thawing it first. Signed-off-by: Andrey Ryabinin Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/block_dev.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/block_dev.c b/fs/block_dev.c index e17bdbdfe9b1..08ae99343d92 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -249,7 +249,8 @@ struct super_block *freeze_bdev(struct block_device *bdev) * thaw_bdev drops it. */ sb = get_super(bdev); - drop_super(sb); + if (sb) + drop_super(sb); mutex_unlock(&bdev->bd_fsfreeze_mutex); return sb; } From 468c298ad3ed3f0d94a65f8ca00f6bfc6c2b4e33 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 25 Aug 2016 08:56:44 -0600 Subject: [PATCH 384/531] Revert "floppy: fix open(O_ACCMODE) for ioctl-only open" This reverts commit ff06db1efb2ad6db06eb5b99b88a0c15a9cc9b0e. --- drivers/block/floppy.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index b71a9c767009..c557057fe8ae 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -3663,6 +3663,11 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) opened_bdev[drive] = bdev; + if (!(mode & (FMODE_READ|FMODE_WRITE))) { + res = -EINVAL; + goto out; + } + res = -ENXIO; if (!floppy_track_buffer) { @@ -3706,15 +3711,13 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) if (UFDCS->rawcmd == 1) UFDCS->rawcmd = 2; - if (mode & (FMODE_READ|FMODE_WRITE)) { - UDRS->last_checked = 0; - clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags); - check_disk_change(bdev); - if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags)) - goto out; - if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags)) - goto out; - } + UDRS->last_checked = 0; + clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags); + check_disk_change(bdev); + if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags)) + goto out; + if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags)) + goto out; res = -EROFS; From f2791e7eadf437633f30faa51b30878cf15650be Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 25 Aug 2016 08:56:51 -0600 Subject: [PATCH 385/531] Revert "floppy: refactor open() flags handling" This reverts commit 09954bad448791ef01202351d437abdd9497a804. --- drivers/block/floppy.c | 34 +++++++++++++++------------------- 1 file changed, 15 insertions(+), 19 deletions(-) diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index c557057fe8ae..e3d8e4ced4a2 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -3663,11 +3663,6 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) opened_bdev[drive] = bdev; - if (!(mode & (FMODE_READ|FMODE_WRITE))) { - res = -EINVAL; - goto out; - } - res = -ENXIO; if (!floppy_track_buffer) { @@ -3711,20 +3706,21 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) if (UFDCS->rawcmd == 1) UFDCS->rawcmd = 2; - UDRS->last_checked = 0; - clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags); - check_disk_change(bdev); - if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags)) - goto out; - if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags)) - goto out; - - res = -EROFS; - - if ((mode & FMODE_WRITE) && - !test_bit(FD_DISK_WRITABLE_BIT, &UDRS->flags)) - goto out; - + if (!(mode & FMODE_NDELAY)) { + if (mode & (FMODE_READ|FMODE_WRITE)) { + UDRS->last_checked = 0; + clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags); + check_disk_change(bdev); + if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags)) + goto out; + if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags)) + goto out; + } + res = -EROFS; + if ((mode & FMODE_WRITE) && + !test_bit(FD_DISK_WRITABLE_BIT, &UDRS->flags)) + goto out; + } mutex_unlock(&open_lock); mutex_unlock(&floppy_mutex); return 0; From 07c72d7d54d138eb2ca37709a5a3d55fbcc01536 Mon Sep 17 00:00:00 2001 From: Tatyana Nikolova Date: Wed, 24 Aug 2016 13:59:17 -0500 Subject: [PATCH 386/531] i40iw: Send last streaming mode message for loopback connections Send a zero length last streaming mode message for loopback connections to synchronize between accepting QP and connecting QP. This avoids data transfer to start on the accepting QP before the connecting QP is in RTS. Also remove function i40iw_loopback_nop() as it is no longer used. Fixes: f27b4746f378 ("i40iw: add connection management code") Signed-off-by: Tatyana Nikolova Signed-off-by: Shiraz Saleem Signed-off-by: Doug Ledford --- drivers/infiniband/hw/i40iw/i40iw_cm.c | 22 +--------------------- 1 file changed, 1 insertion(+), 21 deletions(-) diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.c b/drivers/infiniband/hw/i40iw/i40iw_cm.c index 64343985e0b7..7ca0638579c0 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_cm.c +++ b/drivers/infiniband/hw/i40iw/i40iw_cm.c @@ -3346,26 +3346,6 @@ int i40iw_cm_disconn(struct i40iw_qp *iwqp) return 0; } -/** - * i40iw_loopback_nop - Send a nop - * @qp: associated hw qp - */ -static void i40iw_loopback_nop(struct i40iw_sc_qp *qp) -{ - u64 *wqe; - u64 header; - - wqe = qp->qp_uk.sq_base->elem; - set_64bit_val(wqe, 0, 0); - set_64bit_val(wqe, 8, 0); - set_64bit_val(wqe, 16, 0); - - header = LS_64(I40IWQP_OP_NOP, I40IWQPSQ_OPCODE) | - LS_64(0, I40IWQPSQ_SIGCOMPL) | - LS_64(qp->qp_uk.swqe_polarity, I40IWQPSQ_VALID); - set_64bit_val(wqe, 24, header); -} - /** * i40iw_qp_disconnect - free qp and close cm * @iwqp: associate qp for the connection @@ -3638,7 +3618,7 @@ int i40iw_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) } else { if (iwqp->page) iwqp->sc_qp.qp_uk.sq_base = kmap(iwqp->page); - i40iw_loopback_nop(&iwqp->sc_qp); + dev->iw_priv_qp_ops->qp_send_lsmm(&iwqp->sc_qp, NULL, 0, 0); } if (iwqp->page) From 90a56f72edb088c678083c32d05936c7c8d9a948 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Fri, 12 Aug 2016 15:11:28 +0300 Subject: [PATCH 387/531] Bluetooth: Fix bt_sock_recvmsg when MSG_TRUNC is not set Commit b5f34f9420b50c9b5876b9a2b68e96be6d629054 attempt to introduce proper handling for MSG_TRUNC but recv and variants should still work as read if no flag is passed, but because the code may set MSG_TRUNC to msg->msg_flags that shall not be used as it may cause it to be behave as if MSG_TRUNC is always, so instead of using it this changes the code to use the flags parameter which shall contain the original flags. Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Marcel Holtmann --- net/bluetooth/af_bluetooth.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index ece45e0683fd..0b5f729d08d2 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -250,7 +250,7 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, skb_free_datagram(sk, skb); - if (msg->msg_flags & MSG_TRUNC) + if (flags & MSG_TRUNC) copied = skblen; return err ? : copied; From 4f34228b67246ae3b3ab1dc33b980c77c0650ef4 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Mon, 15 Aug 2016 16:02:20 +0300 Subject: [PATCH 388/531] Bluetooth: Fix hci_sock_recvmsg when MSG_TRUNC is not set Similar to bt_sock_recvmsg MSG_TRUNC shall be checked using the original flags not msg_flags. Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Marcel Holtmann --- net/bluetooth/hci_sock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 6ef8a01a9ad4..96f04b7b9556 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -1091,7 +1091,7 @@ static int hci_sock_recvmsg(struct socket *sock, struct msghdr *msg, skb_free_datagram(sk, skb); - if (msg->msg_flags & MSG_TRUNC) + if (flags & MSG_TRUNC) copied = skblen; return err ? : copied; From 2b721f20770ccbca4d3dad58e1bd44aa570efb3f Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 10 Aug 2016 18:52:38 +0200 Subject: [PATCH 389/531] drm: Protect fb_defio in drivers with CONFIG_KMS_FBDEV_EMULATION For reasons that entirely elude me fb.h exposes all the structures, even when it is not enabled. Except for special stuff like fb_defio. Which means all the drivers which haven't yet switched over to the defio support in the helpers and still roll their own, will fail to compile when fbdev emulation is disabled. Protect just those bits, as a gnarly reminder that conversion to the core defio helpers would be good. Reviewed-by: Alex Deucher Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1470847958-28465-6-git-send-email-daniel.vetter@ffwll.ch Signed-off-by: Dave Airlie --- drivers/gpu/drm/qxl/qxl_fb.c | 4 ++++ drivers/gpu/drm/udl/udl_fb.c | 4 ++++ 2 files changed, 8 insertions(+) diff --git a/drivers/gpu/drm/qxl/qxl_fb.c b/drivers/gpu/drm/qxl/qxl_fb.c index df2657051afd..28c1423049c5 100644 --- a/drivers/gpu/drm/qxl/qxl_fb.c +++ b/drivers/gpu/drm/qxl/qxl_fb.c @@ -73,10 +73,12 @@ static void qxl_fb_image_init(struct qxl_fb_image *qxl_fb_image, } } +#ifdef CONFIG_DRM_FBDEV_EMULATION static struct fb_deferred_io qxl_defio = { .delay = QXL_DIRTY_DELAY, .deferred_io = drm_fb_helper_deferred_io, }; +#endif static struct fb_ops qxlfb_ops = { .owner = THIS_MODULE, @@ -313,8 +315,10 @@ static int qxlfb_create(struct qxl_fbdev *qfbdev, goto out_destroy_fbi; } +#ifdef CONFIG_DRM_FBDEV_EMULATION info->fbdefio = &qxl_defio; fb_deferred_io_init(info); +#endif qdev->fbdev_info = info; qdev->fbdev_qfb = &qfbdev->qfb; diff --git a/drivers/gpu/drm/udl/udl_fb.c b/drivers/gpu/drm/udl/udl_fb.c index d5df555aeba0..9688bfa92ccd 100644 --- a/drivers/gpu/drm/udl/udl_fb.c +++ b/drivers/gpu/drm/udl/udl_fb.c @@ -203,6 +203,7 @@ static int udl_fb_open(struct fb_info *info, int user) ufbdev->fb_count++; +#ifdef CONFIG_DRM_FBDEV_EMULATION if (fb_defio && (info->fbdefio == NULL)) { /* enable defio at last moment if not disabled by client */ @@ -218,6 +219,7 @@ static int udl_fb_open(struct fb_info *info, int user) info->fbdefio = fbdefio; fb_deferred_io_init(info); } +#endif pr_notice("open /dev/fb%d user=%d fb_info=%p count=%d\n", info->node, user, info, ufbdev->fb_count); @@ -235,12 +237,14 @@ static int udl_fb_release(struct fb_info *info, int user) ufbdev->fb_count--; +#ifdef CONFIG_DRM_FBDEV_EMULATION if ((ufbdev->fb_count == 0) && (info->fbdefio)) { fb_deferred_io_cleanup(info); kfree(info->fbdefio); info->fbdefio = NULL; info->fbops->fb_mmap = udl_fb_mmap; } +#endif pr_warn("released /dev/fb%d user=%d count=%d\n", info->node, user, ufbdev->fb_count); From 869c554808ccf7ddd25be5317073b88ceddb8507 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Thu, 25 Aug 2016 14:11:43 -0600 Subject: [PATCH 390/531] mmc: fix use-after-free of struct request We call mmc_req_is_special() after having processed a request, but it could be freed after that. Check that ahead of time, and use the cached value. Reported-by: Hans de Goede Tested-by: Hans de Goede Fixes: c2df40dfb8c0 ("drivers: use req op accessor") Signed-off-by: Jens Axboe --- drivers/mmc/card/block.c | 4 ++-- drivers/mmc/card/queue.c | 4 +++- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index 82503e6f04b3..2206d4477dbb 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -2151,6 +2151,7 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req) struct mmc_card *card = md->queue.card; struct mmc_host *host = card->host; unsigned long flags; + bool req_is_special = mmc_req_is_special(req); if (req && !mq->mqrq_prev->req) /* claim host only for the first request */ @@ -2191,8 +2192,7 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req) } out: - if ((!req && !(mq->flags & MMC_QUEUE_NEW_REQUEST)) || - mmc_req_is_special(req)) + if ((!req && !(mq->flags & MMC_QUEUE_NEW_REQUEST)) || req_is_special) /* * Release host when there are no more requests * and after special request(discard, flush) is done. diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c index 29578e98603d..708057261b38 100644 --- a/drivers/mmc/card/queue.c +++ b/drivers/mmc/card/queue.c @@ -65,6 +65,8 @@ static int mmc_queue_thread(void *d) spin_unlock_irq(q->queue_lock); if (req || mq->mqrq_prev->req) { + bool req_is_special = mmc_req_is_special(req); + set_current_state(TASK_RUNNING); mq->issue_fn(mq, req); cond_resched(); @@ -80,7 +82,7 @@ static int mmc_queue_thread(void *d) * has been finished. Do not assign it to previous * request. */ - if (mmc_req_is_special(req)) + if (req_is_special) mq->mqrq_cur->req = NULL; mq->mqrq_prev->brq.mrq.data = NULL; From a5de125dd46c851fc962806135953c1bd0a0f0df Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Wed, 24 Aug 2016 13:32:19 +0000 Subject: [PATCH 391/531] tipc: fix the error handling in tipc_udp_enable() Fix to return a negative error code in enable_mcast() error handling case, and release udp socket when necessary. Fixes: d0f91938bede ("tipc: add ip/udp media type") Signed-off-by: Wei Yongjun Signed-off-by: David S. Miller --- net/tipc/udp_media.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index b016c011970b..ae7e14cae085 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -396,10 +396,13 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, tuncfg.encap_destroy = NULL; setup_udp_tunnel_sock(net, ub->ubsock, &tuncfg); - if (enable_mcast(ub, remote)) + err = enable_mcast(ub, remote); + if (err) goto err; return 0; err: + if (ub->ubsock) + udp_tunnel_sock_release(ub->ubsock); kfree(ub); return err; } From 166ee5b87866de07a3e56c1b757f2b5cabba72a5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 24 Aug 2016 09:39:02 -0700 Subject: [PATCH 392/531] qdisc: fix a module refcount leak in qdisc_create_dflt() Should qdisc_alloc() fail, we must release the module refcount we got right before. Fixes: 6da7c8fcbcbd ("qdisc: allow setting default queuing discipline") Signed-off-by: Eric Dumazet Acked-by: John Fastabend Acked-by: John Fastabend Signed-off-by: David S. Miller --- net/sched/sch_generic.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index e95b67cd5718..657c13362b19 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -643,18 +643,19 @@ struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, struct Qdisc *sch; if (!try_module_get(ops->owner)) - goto errout; + return NULL; sch = qdisc_alloc(dev_queue, ops); - if (IS_ERR(sch)) - goto errout; + if (IS_ERR(sch)) { + module_put(ops->owner); + return NULL; + } sch->parent = parentid; if (!ops->init || ops->init(sch, NULL) == 0) return sch; qdisc_destroy(sch); -errout: return NULL; } EXPORT_SYMBOL(qdisc_create_dflt); From 4f101c47791cdcb831b3ef1f831b1cc51e4fe03c Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 24 Aug 2016 11:01:20 -0700 Subject: [PATCH 393/531] net: dsa: bcm_sf2: Fix race condition while unmasking interrupts We kept shadow copies of which interrupt sources we have enabled and disabled, but due to an order bug in how intrl2_mask_clear was defined, we could run into the following scenario: CPU0 CPU1 intrl2_1_mask_clear(..) sets INTRL2_CPU_MASK_CLEAR bcm_sf2_switch_1_isr read INTRL2_CPU_STATUS and masks with stale irq1_mask value updates irq1_mask value Which would make us loop again and again trying to process and interrupt we are not clearing since our copy of whether it was enabled before still indicates it was not. Fix this by updating the shadow copy first, and then unasking at the HW level. Fixes: 246d7f773c13 ("net: dsa: add Broadcom SF2 switch driver") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/dsa/bcm_sf2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/dsa/bcm_sf2.h b/drivers/net/dsa/bcm_sf2.h index 463bed8cbe4c..dd446e466699 100644 --- a/drivers/net/dsa/bcm_sf2.h +++ b/drivers/net/dsa/bcm_sf2.h @@ -205,8 +205,8 @@ static inline void name##_writeq(struct bcm_sf2_priv *priv, u64 val, \ static inline void intrl2_##which##_mask_clear(struct bcm_sf2_priv *priv, \ u32 mask) \ { \ - intrl2_##which##_writel(priv, mask, INTRL2_CPU_MASK_CLEAR); \ priv->irq##which##_mask &= ~(mask); \ + intrl2_##which##_writel(priv, mask, INTRL2_CPU_MASK_CLEAR); \ } \ static inline void intrl2_##which##_mask_set(struct bcm_sf2_priv *priv, \ u32 mask) \ From c3e70edd7c2eed6acd234627a6007627f5c76e8e Mon Sep 17 00:00:00 2001 From: Xander Huff Date: Wed, 24 Aug 2016 16:47:53 -0500 Subject: [PATCH 394/531] Revert "phy: IRQ cannot be shared" This reverts: commit 33c133cc7598 ("phy: IRQ cannot be shared") On hardware with multiple PHY devices hooked up to the same IRQ line, allow them to share it. Sergei Shtylyov says: "I'm not sure now what was the reason I concluded that the IRQ sharing was impossible... most probably I thought that the kernel IRQ handling code exited the loop over the IRQ actions once IRQ_HANDLED was returned -- which is obviously not so in reality..." Signed-off-by: Xander Huff Signed-off-by: Nathan Sullivan Signed-off-by: David S. Miller --- drivers/net/phy/phy.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index c5dc2c363f96..c6f66832a1a6 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -722,8 +722,10 @@ static int phy_disable_interrupts(struct phy_device *phydev) int phy_start_interrupts(struct phy_device *phydev) { atomic_set(&phydev->irq_disable, 0); - if (request_irq(phydev->irq, phy_interrupt, 0, "phy_interrupt", - phydev) < 0) { + if (request_irq(phydev->irq, phy_interrupt, + IRQF_SHARED, + "phy_interrupt", + phydev) < 0) { pr_warn("%s: Can't get IRQ %d (PHY)\n", phydev->mdio.bus->name, phydev->irq); phydev->irq = PHY_POLL; From f38ff2ee7727994685494bcc4d7c274b35b5418a Mon Sep 17 00:00:00 2001 From: Anjali Singhai Jain Date: Wed, 24 Aug 2016 17:51:53 -0700 Subject: [PATCH 395/531] i40e: Change some init flow for the client This change makes a common flow for Client instance open during init and reset path. The Client subtask can handle both the cases instead of making a separate notify_client_of_open call. Also it may fix a bug during reset where the service task was leaking some memory and causing issues. Change-Id: I7232a32fd52b82e863abb54266fa83122f80a0cd Signed-off-by: Anjali Singhai Jain Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/i40e/i40e_client.c | 41 ++++++++++++++----- drivers/net/ethernet/intel/i40e/i40e_main.c | 1 - 2 files changed, 30 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c index e1370c556a3c..618f18436618 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_client.c +++ b/drivers/net/ethernet/intel/i40e/i40e_client.c @@ -199,6 +199,7 @@ void i40e_notify_client_of_l2_param_changes(struct i40e_vsi *vsi) void i40e_notify_client_of_netdev_open(struct i40e_vsi *vsi) { struct i40e_client_instance *cdev; + int ret = 0; if (!vsi) return; @@ -211,7 +212,14 @@ void i40e_notify_client_of_netdev_open(struct i40e_vsi *vsi) "Cannot locate client instance open routine\n"); continue; } - cdev->client->ops->open(&cdev->lan_info, cdev->client); + if (!(test_bit(__I40E_CLIENT_INSTANCE_OPENED, + &cdev->state))) { + ret = cdev->client->ops->open(&cdev->lan_info, + cdev->client); + if (!ret) + set_bit(__I40E_CLIENT_INSTANCE_OPENED, + &cdev->state); + } } } mutex_unlock(&i40e_client_instance_mutex); @@ -407,12 +415,14 @@ struct i40e_vsi *i40e_vsi_lookup(struct i40e_pf *pf, * i40e_client_add_instance - add a client instance struct to the instance list * @pf: pointer to the board struct * @client: pointer to a client struct in the client list. + * @existing: if there was already an existing instance * - * Returns cdev ptr on success, NULL on failure + * Returns cdev ptr on success or if already exists, NULL on failure **/ static struct i40e_client_instance *i40e_client_add_instance(struct i40e_pf *pf, - struct i40e_client *client) + struct i40e_client *client, + bool *existing) { struct i40e_client_instance *cdev; struct netdev_hw_addr *mac = NULL; @@ -421,7 +431,7 @@ struct i40e_client_instance *i40e_client_add_instance(struct i40e_pf *pf, mutex_lock(&i40e_client_instance_mutex); list_for_each_entry(cdev, &i40e_client_instances, list) { if ((cdev->lan_info.pf == pf) && (cdev->client == client)) { - cdev = NULL; + *existing = true; goto out; } } @@ -505,6 +515,7 @@ void i40e_client_subtask(struct i40e_pf *pf) { struct i40e_client_instance *cdev; struct i40e_client *client; + bool existing = false; int ret = 0; if (!(pf->flags & I40E_FLAG_SERVICE_CLIENT_REQUESTED)) @@ -528,18 +539,25 @@ void i40e_client_subtask(struct i40e_pf *pf) /* check if L2 VSI is up, if not we are not ready */ if (test_bit(__I40E_DOWN, &pf->vsi[pf->lan_vsi]->state)) continue; + } else { + dev_warn(&pf->pdev->dev, "This client %s is being instanciated at probe\n", + client->name); } /* Add the client instance to the instance list */ - cdev = i40e_client_add_instance(pf, client); + cdev = i40e_client_add_instance(pf, client, &existing); if (!cdev) continue; - /* Also up the ref_cnt of no. of instances of this client */ - atomic_inc(&client->ref_cnt); - dev_info(&pf->pdev->dev, "Added instance of Client %s to PF%d bus=0x%02x func=0x%02x\n", - client->name, pf->hw.pf_id, - pf->hw.bus.device, pf->hw.bus.func); + if (!existing) { + /* Also up the ref_cnt for no. of instances of this + * client. + */ + atomic_inc(&client->ref_cnt); + dev_info(&pf->pdev->dev, "Added instance of Client %s to PF%d bus=0x%02x func=0x%02x\n", + client->name, pf->hw.pf_id, + pf->hw.bus.device, pf->hw.bus.func); + } /* Send an Open request to the client */ atomic_inc(&cdev->ref_cnt); @@ -588,7 +606,8 @@ int i40e_lan_add_device(struct i40e_pf *pf) pf->hw.pf_id, pf->hw.bus.device, pf->hw.bus.func); /* Since in some cases register may have happened before a device gets - * added, we can schedule a subtask to go initiate the clients. + * added, we can schedule a subtask to go initiate the clients if + * they can be launched at probe time. */ pf->flags |= I40E_FLAG_SERVICE_CLIENT_REQUESTED; i40e_service_event_schedule(pf); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index c6ac7a61812f..828ed28c3c14 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -5431,7 +5431,6 @@ int i40e_open(struct net_device *netdev) wr32(&pf->hw, I40E_GLLAN_TSOMSK_L, be32_to_cpu(TCP_FLAG_CWR) >> 16); udp_tunnel_get_rx_info(netdev); - i40e_notify_client_of_netdev_open(vsi); return 0; } From b628d611a2a53858263fc419dba552f32431dba4 Mon Sep 17 00:00:00 2001 From: Gao Feng Date: Thu, 25 Aug 2016 09:45:39 +0800 Subject: [PATCH 396/531] 8139cp: Fix one possible deadloop in cp_rx_poll When cp_rx_poll does not get enough packet, it will check the rx interrupt status again. If so, it will jumpt to rx_status_loop again. But the goto jump resets the rx variable as zero too. As a result, it causes one possible deadloop. Assume this case, rx_status_loop only gets the packet count which is less than budget, and (cpr16(IntrStatus) & cp_rx_intr_mask) condition is always true. It causes the deadloop happens and system is blocked. Signed-off-by: Gao Feng Signed-off-by: David S. Miller --- drivers/net/ethernet/realtek/8139cp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c index deae10d7426d..5297bf77211c 100644 --- a/drivers/net/ethernet/realtek/8139cp.c +++ b/drivers/net/ethernet/realtek/8139cp.c @@ -467,8 +467,8 @@ static int cp_rx_poll(struct napi_struct *napi, int budget) unsigned int rx_tail = cp->rx_tail; int rx; -rx_status_loop: rx = 0; +rx_status_loop: cpw16(IntrStatus, cp_rx_intr_mask); while (rx < budget) { From ed150e1a5cf20c04cf0b2d2c34e498fc1d6519be Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Fri, 26 Aug 2016 15:58:40 +1000 Subject: [PATCH 397/531] xfs: don't perform lookups on zero-height btrees If the caller passes in a cursor to a zero-height btree (which is impossible), we never set block to anything but NULL, which causes the later dereference of it to crash. Instead, just return -EFSCORRUPTED. Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_btree.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index b5c213a051cd..33f14067c320 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -1814,6 +1814,10 @@ xfs_btree_lookup( XFS_BTREE_STATS_INC(cur, lookup); + /* No such thing as a zero-level tree. */ + if (cur->bc_nlevels == 0) + return -EFSCORRUPTED; + block = NULL; keyno = 0; From 738f57c16a2bb527c705641f0fc1c68ff8cba72a Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Fri, 26 Aug 2016 15:59:19 +1000 Subject: [PATCH 398/531] xfs: disallow mounting of realtime + rmap filesystems Since the kernel doesn't currently support the realtime rmapbt, don't allow such filesystems to be mounted. Support will appear in a future release. Signed-off-by: Darrick J. Wong Reviewed-by: Carlos Maiolino Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- fs/xfs/xfs_super.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 24ef83ef04de..fd6be45b3a1e 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1574,9 +1574,16 @@ xfs_fs_fill_super( } } - if (xfs_sb_version_hasrmapbt(&mp->m_sb)) + if (xfs_sb_version_hasrmapbt(&mp->m_sb)) { + if (mp->m_sb.sb_rblocks) { + xfs_alert(mp, + "EXPERIMENTAL reverse mapping btree not compatible with realtime device!"); + error = -EINVAL; + goto out_filestream_unmount; + } xfs_alert(mp, "EXPERIMENTAL reverse mapping btree feature enabled. Use at your own risk!"); + } error = xfs_mountfs(mp); if (error) From da1f039d6947b1a49f13b39a6de0df2a3e9e1ed1 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Fri, 26 Aug 2016 15:59:31 +1000 Subject: [PATCH 399/531] xfs: don't log the entire end of the AGF When we're logging the last non-spare field in the AGF, we don't need to log the spare fields, so plumb in a new AGF logging flag to help us avoid that. Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_alloc.c | 2 ++ fs/xfs/libxfs/xfs_format.h | 6 ++++-- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 3dd8f1d54498..05b5243d89f6 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -2278,6 +2278,8 @@ xfs_alloc_log_agf( offsetof(xfs_agf_t, agf_btreeblks), offsetof(xfs_agf_t, agf_uuid), offsetof(xfs_agf_t, agf_rmap_blocks), + /* needed so that we don't log the whole rest of the structure: */ + offsetof(xfs_agf_t, agf_spare64), sizeof(xfs_agf_t) }; diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index e6a8bea0f7ba..270fb5cf4fa1 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -674,7 +674,8 @@ typedef struct xfs_agf { #define XFS_AGF_BTREEBLKS 0x00000800 #define XFS_AGF_UUID 0x00001000 #define XFS_AGF_RMAP_BLOCKS 0x00002000 -#define XFS_AGF_NUM_BITS 14 +#define XFS_AGF_SPARE64 0x00004000 +#define XFS_AGF_NUM_BITS 15 #define XFS_AGF_ALL_BITS ((1 << XFS_AGF_NUM_BITS) - 1) #define XFS_AGF_FLAGS \ @@ -691,7 +692,8 @@ typedef struct xfs_agf { { XFS_AGF_LONGEST, "LONGEST" }, \ { XFS_AGF_BTREEBLKS, "BTREEBLKS" }, \ { XFS_AGF_UUID, "UUID" }, \ - { XFS_AGF_RMAP_BLOCKS, "RMAP_BLOCKS" } + { XFS_AGF_RMAP_BLOCKS, "RMAP_BLOCKS" }, \ + { XFS_AGF_SPARE64, "SPARE64" } /* disk block (xfs_daddr_t) in the AG */ #define XFS_AGF_DADDR(mp) ((xfs_daddr_t)(1 << (mp)->m_sectbb_log)) From 722278997bc964349e23e7061d541f8df3133a04 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Fri, 26 Aug 2016 15:59:50 +1000 Subject: [PATCH 400/531] xfs: fix some key handling problems in _btree_simple_query_range We only need the record's high key for the first record that we look at; for all records, we /definitely/ need the regular record key. Therefore, fix how the simple range query function gets its keys. Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_btree.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 33f14067c320..b70d9f918156 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -4563,10 +4563,10 @@ xfs_btree_simple_query_range( error = xfs_btree_get_rec(cur, &recp, &stat); if (error || !stat) break; - cur->bc_ops->init_high_key_from_rec(&rec_key, recp); /* Skip if high_key(rec) < low_key. */ if (firstrec) { + cur->bc_ops->init_high_key_from_rec(&rec_key, recp); firstrec = false; diff = cur->bc_ops->diff_two_keys(cur, low_key, &rec_key); @@ -4575,6 +4575,7 @@ xfs_btree_simple_query_range( } /* Stop if high_key < low_key(rec). */ + cur->bc_ops->init_key_from_rec(&rec_key, recp); diff = cur->bc_ops->diff_two_keys(cur, &rec_key, high_key); if (diff > 0) break; From 5b5c2dbd3c9bcfa89fba9709c12ecc0a445c6e40 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Fri, 26 Aug 2016 16:00:10 +1000 Subject: [PATCH 401/531] xfs: simple btree query range should look right if LE lookup fails If the initial LOOKUP_LE in the simple query range fails to find anything, we should attempt to increment the btree cursor to see if there actually /are/ records for what we're trying to find. Without this patch, a bnobt range query of (0, $agsize) returns no results because the leftmost record never has a startblock of zero. Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_btree.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index b70d9f918156..08569792fe20 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -4558,6 +4558,13 @@ xfs_btree_simple_query_range( if (error) goto out; + /* Nothing? See if there's anything to the right. */ + if (!stat) { + error = xfs_btree_increment(cur, 0, &stat); + if (error) + goto out; + } + while (stat) { /* Find the record. */ error = xfs_btree_get_rec(cur, &recp, &stat); From f3d7ebdeb2c297bd26272384e955033493ca291c Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Fri, 26 Aug 2016 16:01:30 +1000 Subject: [PATCH 402/531] xfs: fix superblock inprogress check From inspection, the superblock sb_inprogress check is done in the verifier and triggered only for the primary superblock via a "bp->b_bn == XFS_SB_DADDR" check. Unfortunately, the primary superblock is an uncached buffer, and hence it is configured by xfs_buf_read_uncached() with: bp->b_bn = XFS_BUF_DADDR_NULL; /* always null for uncached buffers */ And so this check never triggers. Fix it. cc: Signed-off-by: Dave Chinner Reviewed-by: Brian Foster Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_sb.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 0e3d4f5ec33c..4aecc5fefe96 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -583,7 +583,8 @@ xfs_sb_verify( * Only check the in progress field for the primary superblock as * mkfs.xfs doesn't clear it from secondary superblocks. */ - return xfs_mount_validate_sb(mp, &sb, bp->b_bn == XFS_SB_DADDR, + return xfs_mount_validate_sb(mp, &sb, + bp->b_maps[0].bm_bn == XFS_SB_DADDR, check_version); } From 800b2694f890cc35a1bda63501fc71c94389d517 Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Fri, 26 Aug 2016 16:01:59 +1000 Subject: [PATCH 403/531] xfs: prevent dropping ioend completions during buftarg wait xfs_wait_buftarg() waits for all pending I/O, drains the ioend completion workqueue and walks the LRU until all buffers in the cache have been released. This is traditionally an unmount operation` but the mechanism is also reused during filesystem freeze. xfs_wait_buftarg() invokes drain_workqueue() as part of the quiesce, which is intended more for a shutdown sequence in that it indicates to the queue that new operations are not expected once the drain has begun. New work jobs after this point result in a WARN_ON_ONCE() and are otherwise dropped. With filesystem freeze, however, read operations are allowed and can proceed during or after the workqueue drain. If such a read occurs during the drain sequence, the workqueue infrastructure complains about the queued ioend completion work item and drops it on the floor. As a result, the buffer remains on the LRU and the freeze never completes. Despite the fact that the overall buffer cache cleanup is not necessary during freeze, fix up this operation such that it is safe to invoke during non-unmount quiesce operations. Replace the drain_workqueue() call with flush_workqueue(), which runs a similar serialization on pending workqueue jobs without causing new jobs to be dropped. This is safe for unmount as unmount independently locks out new operations by the time xfs_wait_buftarg() is invoked. cc: Signed-off-by: Brian Foster Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- fs/xfs/xfs_buf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 607cc29bba21..b5b9bffe3520 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1611,7 +1611,7 @@ xfs_wait_buftarg( */ while (percpu_counter_sum(&btp->bt_io_count)) delay(100); - drain_workqueue(btp->bt_mount->m_buf_workqueue); + flush_workqueue(btp->bt_mount->m_buf_workqueue); /* loop until there is nothing left on the lru list. */ while (list_lru_count(&btp->bt_lru)) { From 699e36e5b8e9f77b2be4c23f0b309e53be4b2880 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Tue, 23 Aug 2016 10:44:02 +0200 Subject: [PATCH 404/531] clocksource/drivers/timer-atmel-pit: Enable mck clock mck is needed to get the PIT working. Explicitly prepare_enable it instead of assuming it is enabled. This solves an issue where the system is freezing when the ETM/ETB drivers are enabled. Reported-by: Olivier Schonken Reviewed-by: Boris Brezillon Acked-by: Nicolas Ferre Signed-off-by: Alexandre Belloni Signed-off-by: Daniel Lezcano --- drivers/clocksource/timer-atmel-pit.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/clocksource/timer-atmel-pit.c b/drivers/clocksource/timer-atmel-pit.c index 1ffac0cb0cb7..3494bc5a21d5 100644 --- a/drivers/clocksource/timer-atmel-pit.c +++ b/drivers/clocksource/timer-atmel-pit.c @@ -261,6 +261,12 @@ static int __init at91sam926x_pit_dt_init(struct device_node *node) return PTR_ERR(data->mck); } + ret = clk_prepare_enable(data->mck); + if (ret) { + pr_err("Unable to enable mck\n"); + return ret; + } + /* Get the interrupts property */ data->irq = irq_of_parse_and_map(node, 0); if (!data->irq) { From 4d0e701659aa869a445823149e172e23faa6edac Mon Sep 17 00:00:00 2001 From: Marcin Nowakowski Date: Wed, 17 Aug 2016 12:22:33 +0200 Subject: [PATCH 405/531] drivers/clocksource/pistachio: Fix memory corruption in init Driver init code incorrectly uses the block base address and as a result clears clocksource structure's fields instead of the hardware registers. Commit 09a998201649 ("timekeeping: Lift clocksource cacheline restriction") has changed the offsets within pistachio_clocksource structure and what has previously gone unnoticed now leads to a kernel panic during boot. Signed-off-by: Marcin Nowakowski Signed-off-by: Daniel Lezcano --- drivers/clocksource/time-pistachio.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/clocksource/time-pistachio.c b/drivers/clocksource/time-pistachio.c index a7d9a08e4b0e..a8e6c7df853d 100644 --- a/drivers/clocksource/time-pistachio.c +++ b/drivers/clocksource/time-pistachio.c @@ -202,10 +202,10 @@ static int __init pistachio_clksrc_of_init(struct device_node *node) rate = clk_get_rate(fast_clk); /* Disable irq's for clocksource usage */ - gpt_writel(&pcs_gpt.base, 0, TIMER_IRQ_MASK, 0); - gpt_writel(&pcs_gpt.base, 0, TIMER_IRQ_MASK, 1); - gpt_writel(&pcs_gpt.base, 0, TIMER_IRQ_MASK, 2); - gpt_writel(&pcs_gpt.base, 0, TIMER_IRQ_MASK, 3); + gpt_writel(pcs_gpt.base, 0, TIMER_IRQ_MASK, 0); + gpt_writel(pcs_gpt.base, 0, TIMER_IRQ_MASK, 1); + gpt_writel(pcs_gpt.base, 0, TIMER_IRQ_MASK, 2); + gpt_writel(pcs_gpt.base, 0, TIMER_IRQ_MASK, 3); /* Enable timer block */ writel(TIMER_ME_GLOBAL, pcs_gpt.base); From b53e7d000d9e6e9fd2c6eb6b82d2783c67fd599e Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Thu, 25 Aug 2016 14:26:59 +0800 Subject: [PATCH 406/531] clocksource/drivers/sun4i: Clear interrupts after stopping timer in probe function The bootloader (U-boot) sometimes uses this timer for various delays. It uses it as a ongoing counter, and does comparisons on the current counter value. The timer counter is never stopped. In some cases when the user interacts with the bootloader, or lets it idle for some time before loading Linux, the timer may expire, and an interrupt will be pending. This results in an unexpected interrupt when the timer interrupt is enabled by the kernel, at which point the event_handler isn't set yet. This results in a NULL pointer dereference exception, panic, and no way to reboot. Clear any pending interrupts after we stop the timer in the probe function to avoid this. Cc: stable@vger.kernel.org Signed-off-by: Chen-Yu Tsai Signed-off-by: Daniel Lezcano Acked-by: Maxime Ripard --- drivers/clocksource/sun4i_timer.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/clocksource/sun4i_timer.c b/drivers/clocksource/sun4i_timer.c index 97669ee4df2a..c83452cacb41 100644 --- a/drivers/clocksource/sun4i_timer.c +++ b/drivers/clocksource/sun4i_timer.c @@ -123,12 +123,16 @@ static struct clock_event_device sun4i_clockevent = { .set_next_event = sun4i_clkevt_next_event, }; +static void sun4i_timer_clear_interrupt(void) +{ + writel(TIMER_IRQ_EN(0), timer_base + TIMER_IRQ_ST_REG); +} static irqreturn_t sun4i_timer_interrupt(int irq, void *dev_id) { struct clock_event_device *evt = (struct clock_event_device *)dev_id; - writel(0x1, timer_base + TIMER_IRQ_ST_REG); + sun4i_timer_clear_interrupt(); evt->event_handler(evt); return IRQ_HANDLED; @@ -208,6 +212,9 @@ static int __init sun4i_timer_init(struct device_node *node) /* Make sure timer is stopped before playing with interrupts */ sun4i_clkevt_time_stop(0); + /* clear timer0 interrupt */ + sun4i_timer_clear_interrupt(); + sun4i_clockevent.cpumask = cpu_possible_mask; sun4i_clockevent.irq = irq; From 079d37df3397d48aab0f014986c1b0a1ca6256aa Mon Sep 17 00:00:00 2001 From: Eric Ren Date: Thu, 25 Aug 2016 17:20:59 +0800 Subject: [PATCH 407/531] dlm: fix malfunction of dlm_tool caused by debugfs changes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With the current kernel, `dlm_tool lockdebug` fails as below: "dlm_tool lockdebug ED0BD86DCE724393918A1AE8FDBF1EE3 can't open /sys/kernel/debug/dlm/ED0BD86DCE724393918A1AE8FDBF1EE3: Operation not permitted" This is because table_open() depends on file->f_op to tell which seq_file ops should be passed down. But, the original file ops in file->f_op is replaced by "debugfs_full_proxy_file_operations" with commit 49d200deaa68 ("debugfs: prevent access to removed files' private data"). Currently, I can think up 2 solutions: 1st, replace debugfs_create_file() with debugfs_create_file_unsafe(); 2nd, make different table_open#() accordingly. The 1st one is neat, but I don't thoroughly understand its risk. Maybe someone has a better one. Signed-off-by: Eric Ren Signed-off-by: David Teigland --- fs/dlm/debug_fs.c | 62 ++++++++++++++++++++++++++++++++++++----------- 1 file changed, 48 insertions(+), 14 deletions(-) diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c index eea64912c9c0..466f7d60edc2 100644 --- a/fs/dlm/debug_fs.c +++ b/fs/dlm/debug_fs.c @@ -607,20 +607,54 @@ static const struct file_operations format2_fops; static const struct file_operations format3_fops; static const struct file_operations format4_fops; -static int table_open(struct inode *inode, struct file *file) +static int table_open1(struct inode *inode, struct file *file) { struct seq_file *seq; - int ret = -1; + int ret; - if (file->f_op == &format1_fops) - ret = seq_open(file, &format1_seq_ops); - else if (file->f_op == &format2_fops) - ret = seq_open(file, &format2_seq_ops); - else if (file->f_op == &format3_fops) - ret = seq_open(file, &format3_seq_ops); - else if (file->f_op == &format4_fops) - ret = seq_open(file, &format4_seq_ops); + ret = seq_open(file, &format1_seq_ops); + if (ret) + return ret; + seq = file->private_data; + seq->private = inode->i_private; /* the dlm_ls */ + return 0; +} + +static int table_open2(struct inode *inode, struct file *file) +{ + struct seq_file *seq; + int ret; + + ret = seq_open(file, &format2_seq_ops); + if (ret) + return ret; + + seq = file->private_data; + seq->private = inode->i_private; /* the dlm_ls */ + return 0; +} + +static int table_open3(struct inode *inode, struct file *file) +{ + struct seq_file *seq; + int ret; + + ret = seq_open(file, &format3_seq_ops); + if (ret) + return ret; + + seq = file->private_data; + seq->private = inode->i_private; /* the dlm_ls */ + return 0; +} + +static int table_open4(struct inode *inode, struct file *file) +{ + struct seq_file *seq; + int ret; + + ret = seq_open(file, &format4_seq_ops); if (ret) return ret; @@ -631,7 +665,7 @@ static int table_open(struct inode *inode, struct file *file) static const struct file_operations format1_fops = { .owner = THIS_MODULE, - .open = table_open, + .open = table_open1, .read = seq_read, .llseek = seq_lseek, .release = seq_release @@ -639,7 +673,7 @@ static const struct file_operations format1_fops = { static const struct file_operations format2_fops = { .owner = THIS_MODULE, - .open = table_open, + .open = table_open2, .read = seq_read, .llseek = seq_lseek, .release = seq_release @@ -647,7 +681,7 @@ static const struct file_operations format2_fops = { static const struct file_operations format3_fops = { .owner = THIS_MODULE, - .open = table_open, + .open = table_open3, .read = seq_read, .llseek = seq_lseek, .release = seq_release @@ -655,7 +689,7 @@ static const struct file_operations format3_fops = { static const struct file_operations format4_fops = { .owner = THIS_MODULE, - .open = table_open, + .open = table_open4, .read = seq_read, .llseek = seq_lseek, .release = seq_release From c234af5875ffeab39d5a2c4230a477a35987a484 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 25 Aug 2016 07:51:10 +0100 Subject: [PATCH 408/531] net: hns: dereference ppe_cb->ppe_common_cb if it is non-null ppe_cb->ppe_common_cb is being dereferenced before a null check is being made on it. If ppe_cb->ppe_common_cb is null then we end up with a null pointer dereference when assigning dsaf_dev. Fix this by moving the initialisation of dsaf_dev once we know ppe_cb->ppe_common_cb is OK to dereference. Signed-off-by: Colin Ian King Acked-by: Yisen Zhuang Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c index ff8b6a468b24..6ea872287307 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c @@ -328,9 +328,10 @@ static void hns_ppe_init_hw(struct hns_ppe_cb *ppe_cb) static void hns_ppe_uninit_hw(struct hns_ppe_cb *ppe_cb) { u32 port; - struct dsaf_device *dsaf_dev = ppe_cb->ppe_common_cb->dsaf_dev; if (ppe_cb->ppe_common_cb) { + struct dsaf_device *dsaf_dev = ppe_cb->ppe_common_cb->dsaf_dev; + port = ppe_cb->index; dsaf_dev->misc_op->ppe_srst(dsaf_dev, port, 0); } From c15e07b02bf0450bc8e60f2cc51cb42daa371417 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 25 Aug 2016 18:30:52 +0200 Subject: [PATCH 409/531] team: loadbalance: push lacpdus to exact delivery When team is in bridge and LACP is utilized, LACPDU packets are pushed to userspace using raw socket and there they are processed. However, since 8626c56c8279b, LACPDU skbs are dropped by bridge rx_handler so they never reach packet handlers in rx path. Fix this by explicity treat LACPDUs to be pushed to exact delivery in team rx_handler. Reported-by: Ido Schimmel Fixes: 8626c56c8279b ("bridge: fix potential use-after-free when hook returns QUEUE or STOLEN verdict") Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/team/team_mode_loadbalance.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/net/team/team_mode_loadbalance.c b/drivers/net/team/team_mode_loadbalance.c index cdb19b385d42..b228bea7931f 100644 --- a/drivers/net/team/team_mode_loadbalance.c +++ b/drivers/net/team/team_mode_loadbalance.c @@ -14,9 +14,23 @@ #include #include #include +#include #include #include +static rx_handler_result_t lb_receive(struct team *team, struct team_port *port, + struct sk_buff *skb) +{ + if (unlikely(skb->protocol == htons(ETH_P_SLOW))) { + /* LACPDU packets should go to exact delivery */ + const unsigned char *dest = eth_hdr(skb)->h_dest; + + if (is_link_local_ether_addr(dest) && dest[5] == 0x02) + return RX_HANDLER_EXACT; + } + return RX_HANDLER_ANOTHER; +} + struct lb_priv; typedef struct team_port *lb_select_tx_port_func_t(struct team *, @@ -652,6 +666,7 @@ static const struct team_mode_ops lb_mode_ops = { .port_enter = lb_port_enter, .port_leave = lb_port_leave, .port_disabled = lb_port_disabled, + .receive = lb_receive, .transmit = lb_transmit, }; From 101b29a204f87c99377faa53bd378f101ebb1824 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 25 Aug 2016 15:16:45 -0700 Subject: [PATCH 410/531] byteswap: don't use __builtin_bswap*() with sparse Although sparse declares __builtin_bswap*(), it can't actually do constant folding inside them (yet). As such, things like switch (protocol) { case htons(ETH_P_IP): break; } which we do all over the place cause sparse to warn that it expects a constant instead of a function call. Disable __HAVE_BUILTIN_BSWAP*__ if __CHECKER__ is defined to avoid this. Fixes: 7322dd755e7d ("byteswap: try to avoid __builtin_constant_p gcc bug") Link: http://lkml.kernel.org/r/1470914102-26389-1-git-send-email-johannes@sipsolutions.net Signed-off-by: Johannes Berg Acked-by: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compiler-gcc.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index e2949397c19b..8dbc8929a6a0 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -242,7 +242,11 @@ */ #define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0) -#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP +/* + * sparse (__CHECKER__) pretends to be gcc, but can't do constant + * folding in __builtin_bswap*() (yet), so don't set these for it. + */ +#if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP) && !defined(__CHECKER__) #if GCC_VERSION >= 40400 #define __HAVE_BUILTIN_BSWAP32__ #define __HAVE_BUILTIN_BSWAP64__ @@ -250,7 +254,7 @@ #if GCC_VERSION >= 40800 #define __HAVE_BUILTIN_BSWAP16__ #endif -#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */ +#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP && !__CHECKER__ */ #if GCC_VERSION >= 50000 #define KASAN_ABI_VERSION 4 From 8582fb59f7ee012f2b8118c2bb95168c1622a4c5 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Thu, 25 Aug 2016 15:16:48 -0700 Subject: [PATCH 411/531] get_maintainer: quiet noisy implicit -f vcs_file_exists checking Checking command line filenames that are outside the git tree can emit a noisy and confusing message. Quiet that message by redirecting stderr. Verify that the command was executed successfully. Fixes: 4cad35a7ca69 ("get_maintainer.pl: reduce need for command-line option -f") Link: http://lkml.kernel.org/r/1970a1d2fecb258e384e2e4fdaacdc9ccf3e30a4.1470955439.git.joe@perches.com Signed-off-by: Joe Perches Reported-by: Wolfram Sang Tested-by: Wolfram Sang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/get_maintainer.pl | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index 49a00d54b835..aed4511f0304 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -2136,9 +2136,11 @@ sub vcs_file_exists { my $cmd = $VCS_cmds{"file_exists_cmd"}; $cmd =~ s/(\$\w+)/$1/eeg; # interpolate $cmd - + $cmd .= " 2>&1"; $exists = &{$VCS_cmds{"execute_cmd"}}($cmd); + return 0 if ($? != 0); + return $exists; } From e7d316a02f683864a12389f8808570e37fb90aa3 Mon Sep 17 00:00:00 2001 From: Subash Abhinov Kasiviswanathan Date: Thu, 25 Aug 2016 15:16:51 -0700 Subject: [PATCH 412/531] sysctl: handle error writing UINT_MAX to u32 fields We have scripts which write to certain fields on 3.18 kernels but this seems to be failing on 4.4 kernels. An entry which we write to here is xfrm_aevent_rseqth which is u32. echo 4294967295 > /proc/sys/net/core/xfrm_aevent_rseqth Commit 230633d109e3 ("kernel/sysctl.c: detect overflows when converting to int") prevented writing to sysctl entries when integer overflow occurs. However, this does not apply to unsigned integers. Heinrich suggested that we introduce a new option to handle 64 bit limits and set min as 0 and max as UINT_MAX. This might not work as it leads to issues similar to __do_proc_doulongvec_minmax. Alternatively, we would need to change the datatype of the entry to 64 bit. static int __do_proc_doulongvec_minmax(void *data, struct ctl_table { i = (unsigned long *) data; //This cast is causing to read beyond the size of data (u32) vleft = table->maxlen / sizeof(unsigned long); //vleft is 0 because maxlen is sizeof(u32) which is lesser than sizeof(unsigned long) on x86_64. Introduce a new proc handler proc_douintvec. Individual proc entries will need to be updated to use the new handler. [akpm@linux-foundation.org: coding-style fixes] Fixes: 230633d109e3 ("kernel/sysctl.c:detect overflows when converting to int") Link: http://lkml.kernel.org/r/1471479806-5252-1-git-send-email-subashab@codeaurora.org Signed-off-by: Subash Abhinov Kasiviswanathan Cc: Heinrich Schuchardt Cc: Kees Cook Cc: "David S. Miller" Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sysctl.h | 2 ++ kernel/sysctl.c | 45 ++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 45 insertions(+), 2 deletions(-) diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 697e160c78d0..a4f7203a9017 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -42,6 +42,8 @@ extern int proc_dostring(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int proc_dointvec(struct ctl_table *, int, void __user *, size_t *, loff_t *); +extern int proc_douintvec(struct ctl_table *, int, + void __user *, size_t *, loff_t *); extern int proc_dointvec_minmax(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int proc_dointvec_jiffies(struct ctl_table *, int, diff --git a/kernel/sysctl.c b/kernel/sysctl.c index b43d0b27c1fe..a13bbdaab47d 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2140,6 +2140,21 @@ static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp, return 0; } +static int do_proc_douintvec_conv(bool *negp, unsigned long *lvalp, + int *valp, + int write, void *data) +{ + if (write) { + if (*negp) + return -EINVAL; + *valp = *lvalp; + } else { + unsigned int val = *valp; + *lvalp = (unsigned long)val; + } + return 0; +} + static const char proc_wspace_sep[] = { ' ', '\t', '\n' }; static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table, @@ -2259,8 +2274,27 @@ static int do_proc_dointvec(struct ctl_table *table, int write, int proc_dointvec(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - return do_proc_dointvec(table,write,buffer,lenp,ppos, - NULL,NULL); + return do_proc_dointvec(table, write, buffer, lenp, ppos, NULL, NULL); +} + +/** + * proc_douintvec - read a vector of unsigned integers + * @table: the sysctl table + * @write: %TRUE if this is a write to the sysctl file + * @buffer: the user buffer + * @lenp: the size of the user buffer + * @ppos: file position + * + * Reads/writes up to table->maxlen/sizeof(unsigned int) unsigned integer + * values from/to the user buffer, treated as an ASCII string. + * + * Returns 0 on success. + */ +int proc_douintvec(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return do_proc_dointvec(table, write, buffer, lenp, ppos, + do_proc_douintvec_conv, NULL); } /* @@ -2858,6 +2892,12 @@ int proc_dointvec(struct ctl_table *table, int write, return -ENOSYS; } +int proc_douintvec(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return -ENOSYS; +} + int proc_dointvec_minmax(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -2903,6 +2943,7 @@ int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write, * exception granted :-) */ EXPORT_SYMBOL(proc_dointvec); +EXPORT_SYMBOL(proc_douintvec); EXPORT_SYMBOL(proc_dointvec_jiffies); EXPORT_SYMBOL(proc_dointvec_minmax); EXPORT_SYMBOL(proc_dointvec_userhz_jiffies); From 804dd150468cfd920d92d4b3cf00536fedef3902 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 25 Aug 2016 15:16:57 -0700 Subject: [PATCH 413/531] soft_dirty: fix soft_dirty during THP split While adding proper userfaultfd_wp support with bits in pagetable and swap entry to avoid false positives WP userfaults through swap/fork/ KSM/etc, I've been adding a framework that mostly mirrors soft dirty. So I noticed in one place I had to add uffd_wp support to the pagetables that wasn't covered by soft_dirty and I think it should have. Example: in the THP migration code migrate_misplaced_transhuge_page() pmd_mkdirty is called unconditionally after mk_huge_pmd. entry = mk_huge_pmd(new_page, vma->vm_page_prot); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); That sets soft dirty too (it's a false positive for soft dirty, the soft dirty bit could be more finegrained and transfer the bit like uffd_wp will do.. pmd/pte_uffd_wp() enforces the invariant that when it's set pmd/pte_write is not set). However in the THP split there's no unconditional pmd_mkdirty after mk_huge_pmd and pte_swp_mksoft_dirty isn't called after the migration entry is created. The code sets the dirty bit in the struct page instead of setting it in the pagetable (which is fully equivalent as far as the real dirty bit is concerned, as the whole point of pagetable bits is to be eventually flushed out of to the page, but that is not equivalent for the soft-dirty bit that gets lost in translation). This was found by code review only and totally untested as I'm working to actually replace soft dirty and I don't have time to test potential soft dirty bugfixes as well :). Transfer the soft_dirty from pmd to pte during THP splits. This fix avoids losing the soft_dirty bit and avoids userland memory corruption in the checkpoint. Fixes: eef1b3ba053aa6 ("thp: implement split_huge_pmd()") Link: http://lkml.kernel.org/r/1471610515-30229-2-git-send-email-aarcange@redhat.com Signed-off-by: Andrea Arcangeli Acked-by: Pavel Emelyanov Cc: "Kirill A. Shutemov" Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/huge_memory.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 2373f0a7d340..2db2112aa31e 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1512,7 +1512,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, struct page *page; pgtable_t pgtable; pmd_t _pmd; - bool young, write, dirty; + bool young, write, dirty, soft_dirty; unsigned long addr; int i; @@ -1546,6 +1546,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, write = pmd_write(*pmd); young = pmd_young(*pmd); dirty = pmd_dirty(*pmd); + soft_dirty = pmd_soft_dirty(*pmd); pmdp_huge_split_prepare(vma, haddr, pmd); pgtable = pgtable_trans_huge_withdraw(mm, pmd); @@ -1562,6 +1563,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, swp_entry_t swp_entry; swp_entry = make_migration_entry(page + i, write); entry = swp_entry_to_pte(swp_entry); + if (soft_dirty) + entry = pte_swp_mksoft_dirty(entry); } else { entry = mk_pte(page + i, vma->vm_page_prot); entry = maybe_mkwrite(entry, vma); @@ -1569,6 +1572,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, entry = pte_wrprotect(entry); if (!young) entry = pte_mkold(entry); + if (soft_dirty) + entry = pte_mksoft_dirty(entry); } if (dirty) SetPageDirty(page + i); From ae6c33ba6e37eea3012fe2640b22400ef3f2d0f3 Mon Sep 17 00:00:00 2001 From: Nicolas Iooss Date: Thu, 25 Aug 2016 15:17:00 -0700 Subject: [PATCH 414/531] printk: fix parsing of "brl=" option Commit bbeddf52adc1 ("printk: move braille console support into separate braille.[ch] files") moved the parsing of braille-related options into _braille_console_setup(), changing the type of variable str from char* to char**. In this commit, memcmp(str, "brl,", 4) was correctly updated to memcmp(*str, "brl,", 4) but not memcmp(str, "brl=", 4). Update the code to make "brl=" option work again and replace memcmp() with strncmp() to make the compiler able to detect such an issue. Fixes: bbeddf52adc1 ("printk: move braille console support into separate braille.[ch] files") Link: http://lkml.kernel.org/r/20160823165700.28952-1-nicolas.iooss_linux@m4x.org Signed-off-by: Nicolas Iooss Cc: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/printk/braille.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/printk/braille.c b/kernel/printk/braille.c index 276762f3a460..d5760c42f042 100644 --- a/kernel/printk/braille.c +++ b/kernel/printk/braille.c @@ -9,10 +9,10 @@ char *_braille_console_setup(char **str, char **brl_options) { - if (!memcmp(*str, "brl,", 4)) { + if (!strncmp(*str, "brl,", 4)) { *brl_options = ""; *str += 4; - } else if (!memcmp(str, "brl=", 4)) { + } else if (!strncmp(*str, "brl=", 4)) { *brl_options = *str + 4; *str = strchr(*brl_options, ','); if (!*str) From a5ff1b34e16c203397542d98c49c5c7783193946 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 25 Aug 2016 15:17:02 -0700 Subject: [PATCH 415/531] treewide: replace config_enabled() with IS_ENABLED() (2nd round) Commit 97f2645f358b ("tree-wide: replace config_enabled() with IS_ENABLED()") mostly killed config_enabled(), but some new users have appeared for v4.8-rc1. They are all used for a boolean option, so can be replaced with IS_ENABLED() safely. Link: http://lkml.kernel.org/r/1471970749-24867-1-git-send-email-yamada.masahiro@socionext.com Signed-off-by: Masahiro Yamada Acked-by: Kees Cook Acked-by: Peter Oberparleiter Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Ralf Baechle Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/mips/include/asm/page.h | 4 ++-- arch/s390/kernel/setup.c | 6 ++---- arch/x86/mm/kaslr.c | 2 +- 3 files changed, 5 insertions(+), 7 deletions(-) diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h index ea0cd9773914..5f987598054f 100644 --- a/arch/mips/include/asm/page.h +++ b/arch/mips/include/asm/page.h @@ -164,7 +164,7 @@ typedef struct { unsigned long pgprot; } pgprot_t; */ static inline unsigned long ___pa(unsigned long x) { - if (config_enabled(CONFIG_64BIT)) { + if (IS_ENABLED(CONFIG_64BIT)) { /* * For MIPS64 the virtual address may either be in one of * the compatibility segements ckseg0 or ckseg1, or it may @@ -173,7 +173,7 @@ static inline unsigned long ___pa(unsigned long x) return x < CKSEG0 ? XPHYSADDR(x) : CPHYSADDR(x); } - if (!config_enabled(CONFIG_EVA)) { + if (!IS_ENABLED(CONFIG_EVA)) { /* * We're using the standard MIPS32 legacy memory map, ie. * the address x is going to be in kseg0 or kseg1. We can diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index ba5f456edaa9..7f7ba5f23f13 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -204,11 +204,9 @@ static void __init conmode_default(void) #endif } } else if (MACHINE_IS_KVM) { - if (sclp.has_vt220 && - config_enabled(CONFIG_SCLP_VT220_CONSOLE)) + if (sclp.has_vt220 && IS_ENABLED(CONFIG_SCLP_VT220_CONSOLE)) SET_CONSOLE_VT220; - else if (sclp.has_linemode && - config_enabled(CONFIG_SCLP_CONSOLE)) + else if (sclp.has_linemode && IS_ENABLED(CONFIG_SCLP_CONSOLE)) SET_CONSOLE_SCLP; else SET_CONSOLE_HVC; diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index ec8654f117d8..bda8d5eef04d 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -77,7 +77,7 @@ static inline unsigned long get_padding(struct kaslr_memory_region *region) */ static inline bool kaslr_memory_enabled(void) { - return kaslr_enabled() && !config_enabled(CONFIG_KASAN); + return kaslr_enabled() && !IS_ENABLED(CONFIG_KASAN); } /* Initialize base and padding for each memory region randomized with KASLR */ From b32eaf71db6085f2ba54cf3ddf688bfc858219d0 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Thu, 25 Aug 2016 15:17:05 -0700 Subject: [PATCH 416/531] mm: clarify COMPACTION Kconfig text The current wording of the COMPACTION Kconfig help text doesn't emphasise that disabling COMPACTION might cripple the page allocator which relies on the compaction quite heavily for high order requests and an unexpected OOM can happen with the lack of compaction. Make sure we are vocal about that. Link: http://lkml.kernel.org/r/20160823091726.GK23577@dhcp22.suse.cz Signed-off-by: Michal Hocko Cc: Markus Trippelsdorf Cc: Mel Gorman Cc: Joonsoo Kim Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/Kconfig | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/mm/Kconfig b/mm/Kconfig index 78a23c5c302d..be0ee11fa0d9 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -262,7 +262,14 @@ config COMPACTION select MIGRATION depends on MMU help - Allows the compaction of memory for the allocation of huge pages. + Compaction is the only memory management component to form + high order (larger physically contiguous) memory blocks + reliably. The page allocator relies on compaction heavily and + the lack of the feature can lead to unexpected OOM killer + invocations for high order memory requests. You shouldn't + disable this option unless there really is a strong reason for + it and then we would be really interested to hear about that at + linux-mm@kvack.org. # # support for page migration From 358c07fcc3b60ab08d77f1684de8bd81bcf49a1a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 25 Aug 2016 15:17:08 -0700 Subject: [PATCH 417/531] mm: memcontrol: avoid unused function warning A bugfix in v4.8-rc2 introduced a harmless warning when CONFIG_MEMCG_SWAP is disabled but CONFIG_MEMCG is enabled: mm/memcontrol.c:4085:27: error: 'mem_cgroup_id_get_online' defined but not used [-Werror=unused-function] static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg) This moves the function inside of the #ifdef block that hides the calling function, to avoid the warning. Fixes: 1f47b61fb407 ("mm: memcontrol: fix swap counter leak on swapout from offline cgroup") Link: http://lkml.kernel.org/r/20160824113733.2776701-1-arnd@arndb.de Signed-off-by: Arnd Bergmann Acked-by: Michal Hocko Acked-by: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 36 ++++++++++++++++++------------------ 1 file changed, 18 insertions(+), 18 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2ff0289ad061..9a6a51a7c416 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4082,24 +4082,6 @@ static void mem_cgroup_id_get_many(struct mem_cgroup *memcg, unsigned int n) atomic_add(n, &memcg->id.ref); } -static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg) -{ - while (!atomic_inc_not_zero(&memcg->id.ref)) { - /* - * The root cgroup cannot be destroyed, so it's refcount must - * always be >= 1. - */ - if (WARN_ON_ONCE(memcg == root_mem_cgroup)) { - VM_BUG_ON(1); - break; - } - memcg = parent_mem_cgroup(memcg); - if (!memcg) - memcg = root_mem_cgroup; - } - return memcg; -} - static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n) { if (atomic_sub_and_test(n, &memcg->id.ref)) { @@ -5821,6 +5803,24 @@ static int __init mem_cgroup_init(void) subsys_initcall(mem_cgroup_init); #ifdef CONFIG_MEMCG_SWAP +static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg) +{ + while (!atomic_inc_not_zero(&memcg->id.ref)) { + /* + * The root cgroup cannot be destroyed, so it's refcount must + * always be >= 1. + */ + if (WARN_ON_ONCE(memcg == root_mem_cgroup)) { + VM_BUG_ON(1); + break; + } + memcg = parent_mem_cgroup(memcg); + if (!memcg) + memcg = root_mem_cgroup; + } + return memcg; +} + /** * mem_cgroup_swapout - transfer a memsw charge to swap * @page: page whose memsw charge to transfer From 088bf2ff5d12e2e32ee52a4024fec26e582f44d3 Mon Sep 17 00:00:00 2001 From: Vegard Nossum Date: Thu, 25 Aug 2016 15:17:11 -0700 Subject: [PATCH 418/531] fs/seq_file: fix out-of-bounds read seq_read() is a nasty piece of work, not to mention buggy. It has (I think) an old bug which allows unprivileged userspace to read beyond the end of m->buf. I was getting these: BUG: KASAN: slab-out-of-bounds in seq_read+0xcd2/0x1480 at addr ffff880116889880 Read of size 2713 by task trinity-c2/1329 CPU: 2 PID: 1329 Comm: trinity-c2 Not tainted 4.8.0-rc1+ #96 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org 04/01/2014 Call Trace: kasan_object_err+0x1c/0x80 kasan_report_error+0x2cb/0x7e0 kasan_report+0x4e/0x80 check_memory_region+0x13e/0x1a0 kasan_check_read+0x11/0x20 seq_read+0xcd2/0x1480 proc_reg_read+0x10b/0x260 do_loop_readv_writev.part.5+0x140/0x2c0 do_readv_writev+0x589/0x860 vfs_readv+0x7b/0xd0 do_readv+0xd8/0x2c0 SyS_readv+0xb/0x10 do_syscall_64+0x1b3/0x4b0 entry_SYSCALL64_slow_path+0x25/0x25 Object at ffff880116889100, in cache kmalloc-4096 size: 4096 Allocated: PID = 1329 save_stack_trace+0x26/0x80 save_stack+0x46/0xd0 kasan_kmalloc+0xad/0xe0 __kmalloc+0x1aa/0x4a0 seq_buf_alloc+0x35/0x40 seq_read+0x7d8/0x1480 proc_reg_read+0x10b/0x260 do_loop_readv_writev.part.5+0x140/0x2c0 do_readv_writev+0x589/0x860 vfs_readv+0x7b/0xd0 do_readv+0xd8/0x2c0 SyS_readv+0xb/0x10 do_syscall_64+0x1b3/0x4b0 return_from_SYSCALL_64+0x0/0x6a Freed: PID = 0 (stack is not available) Memory state around the buggy address: ffff88011688a000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff88011688a080: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 >ffff88011688a100: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ^ ffff88011688a180: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff88011688a200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ================================================================== Disabling lock debugging due to kernel taint This seems to be the same thing that Dave Jones was seeing here: https://lkml.org/lkml/2016/8/12/334 There are multiple issues here: 1) If we enter the function with a non-empty buffer, there is an attempt to flush it. But it was not clearing m->from after doing so, which means that if we try to do this flush twice in a row without any call to traverse() in between, we are going to be reading from the wrong place -- the splat above, fixed by this patch. 2) If there's a short write to userspace because of page faults, the buffer may already contain multiple lines (i.e. pos has advanced by more than 1), but we don't save the progress that was made so the next call will output what we've already returned previously. Since that is a much less serious issue (and I have a headache after staring at seq_read() for the past 8 hours), I'll leave that for now. Link: http://lkml.kernel.org/r/1471447270-32093-1-git-send-email-vegard.nossum@oracle.com Signed-off-by: Vegard Nossum Reported-by: Dave Jones Cc: Al Viro Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/seq_file.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/seq_file.c b/fs/seq_file.c index 19f532e7d35e..6dc4296eed62 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -223,8 +223,10 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos) size -= n; buf += n; copied += n; - if (!m->count) + if (!m->count) { + m->from = 0; m->index++; + } if (!size) goto Done; } From d0e5845561c238619de9f5b77e0d763f4c331ca5 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 25 Aug 2016 15:17:14 -0700 Subject: [PATCH 419/531] dax: fix device-dax region base The data offset for a dax region needs to account for a reservation in the resource range. Otherwise, device-dax is allowing mappings directly into the memmap or device-info-block area with crash signatures like the following: BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 IP: get_zone_device_page+0x11/0x30 Call Trace: follow_devmap_pmd+0x298/0x2c0 follow_page_mask+0x275/0x530 __get_user_pages+0xe3/0x750 __gfn_to_pfn_memslot+0x1b2/0x450 [kvm] tdp_page_fault+0x130/0x280 [kvm] kvm_mmu_page_fault+0x5f/0xf0 [kvm] handle_ept_violation+0x94/0x180 [kvm_intel] vmx_handle_exit+0x1d3/0x1440 [kvm_intel] kvm_arch_vcpu_ioctl_run+0x81d/0x16a0 [kvm] kvm_vcpu_ioctl+0x33c/0x620 [kvm] do_vfs_ioctl+0xa2/0x5d0 SyS_ioctl+0x79/0x90 entry_SYSCALL_64_fastpath+0x1a/0xa4 Fixes: ab68f2622136 ("/dev/dax, pmem: direct access to persistent memory") Link: http://lkml.kernel.org/r/147205536732.1606.8994275381938837346.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams Reported-by: Abhilash Kumar Mulumudi Reported-by: Toshi Kani Tested-by: Toshi Kani Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/dax/pmem.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c index dfb168568af1..1f01e98c83c7 100644 --- a/drivers/dax/pmem.c +++ b/drivers/dax/pmem.c @@ -116,6 +116,9 @@ static int dax_pmem_probe(struct device *dev) if (rc) return rc; + /* adjust the dax_region resource to the start of data */ + res.start += le64_to_cpu(pfn_sb->dataoff); + nd_region = to_nd_region(dev->parent); dax_region = alloc_dax_region(dev, nd_region->id, &res, le32_to_cpu(pfn_sb->align), addr, PFN_DEV|PFN_MAP); From 11bd969fdefea3ac0cb9791224f1e09784e21e58 Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Thu, 25 Aug 2016 15:17:17 -0700 Subject: [PATCH 420/531] mm: silently skip readahead for DAX inodes For DAX inodes we need to be careful to never have page cache pages in the mapping->page_tree. This radix tree should be composed only of DAX exceptional entries and zero pages. ltp's readahead02 test was triggering a warning because we were trying to insert a DAX exceptional entry but found that a page cache page had already been inserted into the tree. This page was being inserted into the radix tree in response to a readahead(2) call. Readahead doesn't make sense for DAX inodes, but we don't want it to report a failure either. Instead, we just return success and don't do any work. Link: http://lkml.kernel.org/r/20160824221429.21158-1-ross.zwisler@linux.intel.com Signed-off-by: Ross Zwisler Reported-by: Jeff Moyer Cc: Dan Williams Cc: Dave Chinner Cc: Dave Hansen Cc: Jan Kara Cc: [4.5+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/readahead.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/mm/readahead.c b/mm/readahead.c index 65ec288dc057..c8a955b1297e 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -8,6 +8,7 @@ */ #include +#include #include #include #include @@ -544,6 +545,14 @@ do_readahead(struct address_space *mapping, struct file *filp, if (!mapping || !mapping->a_ops) return -EINVAL; + /* + * Readahead doesn't make sense for DAX inodes, but we don't want it + * to report a failure either. Instead, we just return success and + * don't do any work. + */ + if (dax_mapping(mapping)) + return 0; + return force_page_cache_readahead(mapping, filp, index, nr); } From e70c70c38d7a5ced76fc8b1c4a7ccee76e9c2911 Mon Sep 17 00:00:00 2001 From: Andrew Rybchenko Date: Fri, 26 Aug 2016 11:19:34 +0100 Subject: [PATCH 421/531] sfc: fix potential stack corruption from running past stat bitmask On 32-bit systems, mask is only an array of 3 longs, not 4, so don't try to write to mask[3]. Also include build-time checks in case the size of the bitmask changes. Fixes: 3c36a2aded8c ("sfc: display vadaptor statistics for all interfaces") Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- drivers/net/ethernet/sfc/ef10.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index f658fee74f18..e00a669e9e09 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -1517,13 +1517,14 @@ static void efx_ef10_get_stat_mask(struct efx_nic *efx, unsigned long *mask) } #if BITS_PER_LONG == 64 + BUILD_BUG_ON(BITS_TO_LONGS(EF10_STAT_COUNT) != 2); mask[0] = raw_mask[0]; mask[1] = raw_mask[1]; #else + BUILD_BUG_ON(BITS_TO_LONGS(EF10_STAT_COUNT) != 3); mask[0] = raw_mask[0] & 0xffffffff; mask[1] = raw_mask[0] >> 32; mask[2] = raw_mask[1] & 0xffffffff; - mask[3] = raw_mask[1] >> 32; #endif } From 9dbeea7f08f3784b152d9fb3b86beb34aad77c72 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 26 Aug 2016 08:51:39 -0700 Subject: [PATCH 422/531] rhashtable: fix a memory leak in alloc_bucket_locks() If vmalloc() was successful, do not attempt a kmalloc_array() Fixes: 4cf0b354d92e ("rhashtable: avoid large lock-array allocations") Reported-by: CAI Qian Signed-off-by: Eric Dumazet Cc: Florian Westphal Acked-by: Herbert Xu Tested-by: CAI Qian Signed-off-by: David S. Miller --- lib/rhashtable.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 5ba520b544d7..56054e541a0f 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -77,17 +77,18 @@ static int alloc_bucket_locks(struct rhashtable *ht, struct bucket_table *tbl, size = min_t(unsigned int, size, tbl->size >> 1); if (sizeof(spinlock_t) != 0) { + tbl->locks = NULL; #ifdef CONFIG_NUMA if (size * sizeof(spinlock_t) > PAGE_SIZE && gfp == GFP_KERNEL) tbl->locks = vmalloc(size * sizeof(spinlock_t)); - else #endif if (gfp != GFP_KERNEL) gfp |= __GFP_NOWARN | __GFP_NORETRY; - tbl->locks = kmalloc_array(size, sizeof(spinlock_t), - gfp); + if (!tbl->locks) + tbl->locks = kmalloc_array(size, sizeof(spinlock_t), + gfp); if (!tbl->locks) return -ENOMEM; for (i = 0; i < size; i++) From f5b7b559e14881b27d76f9c97817ec82bfc48827 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Wed, 24 Aug 2016 12:25:56 +0300 Subject: [PATCH 423/531] nvme-rdma: Get rid of duplicate variable We already have need_inval in ib_mr, lets use that instead. Signed-off-by: Sagi Grimberg Reviewed-by: Christoph Hellwig --- drivers/nvme/host/rdma.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index c133256fd745..881ac28575ef 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -77,7 +77,6 @@ struct nvme_rdma_request { u32 num_sge; int nents; bool inline_data; - bool need_inval; struct ib_reg_wr reg_wr; struct ib_cqe reg_cqe; struct nvme_rdma_queue *queue; @@ -286,7 +285,7 @@ static int nvme_rdma_reinit_request(void *data, struct request *rq) struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq); int ret = 0; - if (!req->need_inval) + if (!req->mr->need_inval) goto out; ib_dereg_mr(req->mr); @@ -298,7 +297,7 @@ static int nvme_rdma_reinit_request(void *data, struct request *rq) req->mr = NULL; } - req->need_inval = false; + req->mr->need_inval = false; out: return ret; @@ -850,7 +849,7 @@ static void nvme_rdma_unmap_data(struct nvme_rdma_queue *queue, if (!blk_rq_bytes(rq)) return; - if (req->need_inval) { + if (req->mr->need_inval) { res = nvme_rdma_inv_rkey(queue, req); if (res < 0) { dev_err(ctrl->ctrl.device, @@ -936,7 +935,7 @@ static int nvme_rdma_map_sg_fr(struct nvme_rdma_queue *queue, IB_ACCESS_REMOTE_READ | IB_ACCESS_REMOTE_WRITE; - req->need_inval = true; + req->mr->need_inval = true; sg->addr = cpu_to_le64(req->mr->iova); put_unaligned_le24(req->mr->length, sg->length); @@ -959,7 +958,7 @@ static int nvme_rdma_map_data(struct nvme_rdma_queue *queue, req->num_sge = 1; req->inline_data = false; - req->need_inval = false; + req->mr->need_inval = false; c->common.flags |= NVME_CMD_SGL_METABUF; @@ -1146,7 +1145,7 @@ static int nvme_rdma_process_nvme_rsp(struct nvme_rdma_queue *queue, if ((wc->wc_flags & IB_WC_WITH_INVALIDATE) && wc->ex.invalidate_rkey == req->mr->rkey) - req->need_inval = false; + req->mr->need_inval = false; blk_mq_complete_request(rq, status); @@ -1476,7 +1475,7 @@ static int nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, if (rq->cmd_type == REQ_TYPE_FS && req_op(rq) == REQ_OP_FLUSH) flush = true; ret = nvme_rdma_post_send(queue, sqe, req->sge, req->num_sge, - req->need_inval ? &req->reg_wr.wr : NULL, flush); + req->mr->need_inval ? &req->reg_wr.wr : NULL, flush); if (ret) { nvme_rdma_unmap_data(queue, rq); goto err; From 4d8c6a7946d53648d9ed0e3852a1c81ce07d40db Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Fri, 26 Aug 2016 00:37:52 +0300 Subject: [PATCH 424/531] nvme-rdma: Get rid of redundant defines Signed-off-by: Sagi Grimberg Reviewed-by: Christoph Hellwig --- drivers/nvme/host/rdma.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 881ac28575ef..ab545fb347a0 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -43,10 +43,6 @@ #define NVME_RDMA_MAX_INLINE_SEGMENTS 1 -#define NVME_RDMA_MAX_PAGES_PER_MR 512 - -#define NVME_RDMA_DEF_RECONNECT_DELAY 20 - /* * We handle AEN commands ourselves and don't even let the * block layer know about them. From 89f82cbb0d5c0ab768c8d02914188aa2211cd2e3 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Mon, 22 Aug 2016 15:15:23 -0400 Subject: [PATCH 425/531] drm/msm: fix use of copy_from_user() while holding spinlock Use instead __copy_from_user_inatomic() and fallback to slow-path where we drop and re-aquire the lock in case of fault. Cc: stable@vger.kernel.org Reported-by: Vaishali Thakkar Signed-off-by: Rob Clark --- drivers/gpu/drm/msm/msm_gem_submit.c | 27 ++++++++++++++++++++++----- 1 file changed, 22 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index 9766f9ae4b7d..408da409a216 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -64,6 +64,14 @@ void msm_gem_submit_free(struct msm_gem_submit *submit) kfree(submit); } +static inline unsigned long __must_check +copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) +{ + if (access_ok(VERIFY_READ, from, n)) + return __copy_from_user_inatomic(to, from, n); + return -EFAULT; +} + static int submit_lookup_objects(struct msm_gem_submit *submit, struct drm_msm_gem_submit *args, struct drm_file *file) { @@ -71,6 +79,7 @@ static int submit_lookup_objects(struct msm_gem_submit *submit, int ret = 0; spin_lock(&file->table_lock); + pagefault_disable(); for (i = 0; i < args->nr_bos; i++) { struct drm_msm_gem_submit_bo submit_bo; @@ -84,10 +93,15 @@ static int submit_lookup_objects(struct msm_gem_submit *submit, */ submit->bos[i].flags = 0; - ret = copy_from_user(&submit_bo, userptr, sizeof(submit_bo)); - if (ret) { - ret = -EFAULT; - goto out_unlock; + ret = copy_from_user_inatomic(&submit_bo, userptr, sizeof(submit_bo)); + if (unlikely(ret)) { + pagefault_enable(); + spin_unlock(&file->table_lock); + ret = copy_from_user(&submit_bo, userptr, sizeof(submit_bo)); + if (ret) + goto out; + spin_lock(&file->table_lock); + pagefault_disable(); } if (submit_bo.flags & ~MSM_SUBMIT_BO_FLAGS) { @@ -127,9 +141,12 @@ static int submit_lookup_objects(struct msm_gem_submit *submit, } out_unlock: - submit->nr_bos = i; + pagefault_enable(); spin_unlock(&file->table_lock); +out: + submit->nr_bos = i; + return ret; } From d78d383ab354b0b9e1d23404ae0d9fbdeb9aa035 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Mon, 22 Aug 2016 15:28:38 -0400 Subject: [PATCH 426/531] drm/msm: protect against faults from copy_from_user() in submit ioctl An evil userspace could try to cause deadlock by passing an unfaulted-in GEM bo as submit->bos (or submit->cmds) table. Which will trigger msm_gem_fault() while we already hold struct_mutex. See: https://github.com/freedreno/msmtest/blob/master/evilsubmittest.c Cc: stable@vger.kernel.org Signed-off-by: Rob Clark --- drivers/gpu/drm/msm/msm_drv.h | 6 ++++++ drivers/gpu/drm/msm/msm_gem.c | 9 +++++++++ drivers/gpu/drm/msm/msm_gem_submit.c | 3 +++ 3 files changed, 18 insertions(+) diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h index b4bc7f1ef717..d0da52f2a806 100644 --- a/drivers/gpu/drm/msm/msm_drv.h +++ b/drivers/gpu/drm/msm/msm_drv.h @@ -157,6 +157,12 @@ struct msm_drm_private { struct shrinker shrinker; struct msm_vblank_ctrl vblank_ctrl; + + /* task holding struct_mutex.. currently only used in submit path + * to detect and reject faults from copy_from_user() for submit + * ioctl. + */ + struct task_struct *struct_mutex_task; }; struct msm_format { diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 6cd4af443139..85f3047e05ae 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -196,11 +196,20 @@ int msm_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { struct drm_gem_object *obj = vma->vm_private_data; struct drm_device *dev = obj->dev; + struct msm_drm_private *priv = dev->dev_private; struct page **pages; unsigned long pfn; pgoff_t pgoff; int ret; + /* This should only happen if userspace tries to pass a mmap'd + * but unfaulted gem bo vaddr into submit ioctl, triggering + * a page fault while struct_mutex is already held. This is + * not a valid use-case so just bail. + */ + if (priv->struct_mutex_task == current) + return VM_FAULT_SIGBUS; + /* Make sure we don't parallel update on a fault, nor move or remove * something from beneath our feet */ diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index 408da409a216..880d6a9af7c8 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -394,6 +394,8 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, if (ret) return ret; + priv->struct_mutex_task = current; + submit = submit_create(dev, gpu, args->nr_bos, args->nr_cmds); if (!submit) { ret = -ENOMEM; @@ -485,6 +487,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, if (ret) msm_gem_submit_free(submit); out_unlock: + priv->struct_mutex_task = NULL; mutex_unlock(&dev->struct_mutex); return ret; } From e09c978aae5bedfdb379be80363b024b7d82638b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 27 Aug 2016 23:44:04 -0400 Subject: [PATCH 427/531] NFSv4.1: Fix Oopsable condition in server callback races The slot table hasn't been an array since v3.7. Ensure that we use nfs4_lookup_slot() to access the slot correctly. Fixes: 87dda67e7386 ("NFSv4.1: Allow SEQUENCE to resize the slot table...") Signed-off-by: Trond Myklebust Cc: stable@vger.kernel.org # v3.8+ --- fs/nfs/callback_proc.c | 5 +---- fs/nfs/nfs4session.c | 33 +++++++++++++++++++++++++++++++++ fs/nfs/nfs4session.h | 1 + 3 files changed, 35 insertions(+), 4 deletions(-) diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index c92a75e066a6..a4cf6d2c14a4 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -454,11 +454,8 @@ static bool referring_call_exists(struct nfs_client *clp, ((u32 *)&rclist->rcl_sessionid.data)[3], ref->rc_sequenceid, ref->rc_slotid); - spin_lock(&tbl->slot_tbl_lock); - status = (test_bit(ref->rc_slotid, tbl->used_slots) && - tbl->slots[ref->rc_slotid].seq_nr == + status = nfs4_slot_seqid_in_use(tbl, ref->rc_slotid, ref->rc_sequenceid); - spin_unlock(&tbl->slot_tbl_lock); if (status) goto out; } diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c index 332d06e64fa9..c1f4c208f38a 100644 --- a/fs/nfs/nfs4session.c +++ b/fs/nfs/nfs4session.c @@ -172,6 +172,39 @@ struct nfs4_slot *nfs4_lookup_slot(struct nfs4_slot_table *tbl, u32 slotid) return ERR_PTR(-E2BIG); } +static int nfs4_slot_get_seqid(struct nfs4_slot_table *tbl, u32 slotid, + u32 *seq_nr) + __must_hold(&tbl->slot_tbl_lock) +{ + struct nfs4_slot *slot; + + slot = nfs4_lookup_slot(tbl, slotid); + if (IS_ERR(slot)) + return PTR_ERR(slot); + *seq_nr = slot->seq_nr; + return 0; +} + +/* + * nfs4_slot_seqid_in_use - test if a slot sequence id is still in use + * + * Given a slot table, slot id and sequence number, determine if the + * RPC call in question is still in flight. This function is mainly + * intended for use by the callback channel. + */ +bool nfs4_slot_seqid_in_use(struct nfs4_slot_table *tbl, u32 slotid, u32 seq_nr) +{ + u32 cur_seq; + bool ret = false; + + spin_lock(&tbl->slot_tbl_lock); + if (nfs4_slot_get_seqid(tbl, slotid, &cur_seq) == 0 && + cur_seq == seq_nr && test_bit(slotid, tbl->used_slots)) + ret = true; + spin_unlock(&tbl->slot_tbl_lock); + return ret; +} + /* * nfs4_alloc_slot - efficiently look for a free slot * diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h index 5b51298d1d03..33cace62b50b 100644 --- a/fs/nfs/nfs4session.h +++ b/fs/nfs/nfs4session.h @@ -78,6 +78,7 @@ extern int nfs4_setup_slot_table(struct nfs4_slot_table *tbl, extern void nfs4_shutdown_slot_table(struct nfs4_slot_table *tbl); extern struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl); extern struct nfs4_slot *nfs4_lookup_slot(struct nfs4_slot_table *tbl, u32 slotid); +extern bool nfs4_slot_seqid_in_use(struct nfs4_slot_table *tbl, u32 slotid, u32 seq_nr); extern bool nfs4_try_to_lock_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot); extern void nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot); extern void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl); From 045d2a6d076a2ecd7043ea543ea198af943f8b16 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 28 Aug 2016 13:25:43 -0400 Subject: [PATCH 428/531] NFSv4.1: Delay callback processing when there are referring triples If CB_SEQUENCE tells us that the processing of this request depends on the completion of one or more referring triples (see RFC 5661 Section 2.10.6.3), delay the callback processing until after the RPC requests being referred to have completed. If we end up delaying for more than 1/2 second, then fall back to returning NFS4ERR_DELAY in reply to the callback. Signed-off-by: Trond Myklebust --- fs/nfs/callback_proc.c | 4 ++-- fs/nfs/nfs4proc.c | 2 ++ fs/nfs/nfs4session.c | 22 +++++++++++++++++++++- fs/nfs/nfs4session.h | 5 ++++- 4 files changed, 29 insertions(+), 4 deletions(-) diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index a4cf6d2c14a4..c35932967722 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -454,8 +454,8 @@ static bool referring_call_exists(struct nfs_client *clp, ((u32 *)&rclist->rcl_sessionid.data)[3], ref->rc_sequenceid, ref->rc_slotid); - status = nfs4_slot_seqid_in_use(tbl, ref->rc_slotid, - ref->rc_sequenceid); + status = nfs4_slot_wait_on_seqid(tbl, ref->rc_slotid, + ref->rc_sequenceid, HZ >> 1) < 0; if (status) goto out; } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 1949bbd806eb..0cc0c319cfdd 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -686,6 +686,8 @@ static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res) res->sr_slot = NULL; if (send_new_highest_used_slotid) nfs41_notify_server(session->clp); + if (waitqueue_active(&tbl->slot_waitq)) + wake_up_all(&tbl->slot_waitq); } int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res) diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c index c1f4c208f38a..b62973045a3e 100644 --- a/fs/nfs/nfs4session.c +++ b/fs/nfs/nfs4session.c @@ -28,6 +28,7 @@ static void nfs4_init_slot_table(struct nfs4_slot_table *tbl, const char *queue) tbl->highest_used_slotid = NFS4_NO_SLOT; spin_lock_init(&tbl->slot_tbl_lock); rpc_init_priority_wait_queue(&tbl->slot_tbl_waitq, queue); + init_waitqueue_head(&tbl->slot_waitq); init_completion(&tbl->complete); } @@ -192,7 +193,8 @@ static int nfs4_slot_get_seqid(struct nfs4_slot_table *tbl, u32 slotid, * RPC call in question is still in flight. This function is mainly * intended for use by the callback channel. */ -bool nfs4_slot_seqid_in_use(struct nfs4_slot_table *tbl, u32 slotid, u32 seq_nr) +static bool nfs4_slot_seqid_in_use(struct nfs4_slot_table *tbl, + u32 slotid, u32 seq_nr) { u32 cur_seq; bool ret = false; @@ -205,6 +207,24 @@ bool nfs4_slot_seqid_in_use(struct nfs4_slot_table *tbl, u32 slotid, u32 seq_nr) return ret; } +/* + * nfs4_slot_wait_on_seqid - wait until a slot sequence id is complete + * + * Given a slot table, slot id and sequence number, wait until the + * corresponding RPC call completes. This function is mainly + * intended for use by the callback channel. + */ +int nfs4_slot_wait_on_seqid(struct nfs4_slot_table *tbl, + u32 slotid, u32 seq_nr, + unsigned long timeout) +{ + if (wait_event_timeout(tbl->slot_waitq, + !nfs4_slot_seqid_in_use(tbl, slotid, seq_nr), + timeout) == 0) + return -ETIMEDOUT; + return 0; +} + /* * nfs4_alloc_slot - efficiently look for a free slot * diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h index 33cace62b50b..fa75d7db3db3 100644 --- a/fs/nfs/nfs4session.h +++ b/fs/nfs/nfs4session.h @@ -36,6 +36,7 @@ struct nfs4_slot_table { unsigned long used_slots[SLOT_TABLE_SZ]; /* used/unused bitmap */ spinlock_t slot_tbl_lock; struct rpc_wait_queue slot_tbl_waitq; /* allocators may wait here */ + wait_queue_head_t slot_waitq; /* Completion wait on slot */ u32 max_slots; /* # slots in table */ u32 max_slotid; /* Max allowed slotid value */ u32 highest_used_slotid; /* sent to server on each SEQ. @@ -78,7 +79,9 @@ extern int nfs4_setup_slot_table(struct nfs4_slot_table *tbl, extern void nfs4_shutdown_slot_table(struct nfs4_slot_table *tbl); extern struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl); extern struct nfs4_slot *nfs4_lookup_slot(struct nfs4_slot_table *tbl, u32 slotid); -extern bool nfs4_slot_seqid_in_use(struct nfs4_slot_table *tbl, u32 slotid, u32 seq_nr); +extern int nfs4_slot_wait_on_seqid(struct nfs4_slot_table *tbl, + u32 slotid, u32 seq_nr, + unsigned long timeout); extern bool nfs4_try_to_lock_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot); extern void nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot); extern void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl); From 07e8dcbda71ef87e9cbdc42b5bb16a44c1ab839b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 28 Aug 2016 10:28:25 -0400 Subject: [PATCH 429/531] NFSv4.1: Defer bumping the slot sequence number until we free the slot For operations like OPEN or LAYOUTGET, which return recallable state (i.e. delegations and layouts) we want to enable the mechanism for resolving recall races in RFC5661 Section 2.10.6.3. To do so, we will want to defer bumping the slot's sequence number until we have finished processing the RPC results. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 9 +++++++-- fs/nfs/nfs4session.h | 3 ++- 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 0cc0c319cfdd..de4a89d3d740 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -666,6 +666,11 @@ static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res) tbl = slot->table; session = tbl->session; + /* Bump the slot sequence number */ + if (slot->seq_done) + slot->seq_nr++; + slot->seq_done = 0; + spin_lock(&tbl->slot_tbl_lock); /* Be nice to the server: try to ensure that the last transmitted * value for highest_user_slotid <= target_highest_slotid @@ -716,7 +721,7 @@ int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res) switch (res->sr_status) { case 0: /* Update the slot's sequence and clientid lease timer */ - ++slot->seq_nr; + slot->seq_done = 1; clp = session->clp; do_renew_lease(clp, res->sr_timestamp); /* Check sequence flags */ @@ -771,7 +776,7 @@ int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res) goto retry_nowait; default: /* Just update the slot sequence no. */ - ++slot->seq_nr; + slot->seq_done = 1; } out: /* The session may be reset by one of the error handlers. */ diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h index fa75d7db3db3..f703b755351b 100644 --- a/fs/nfs/nfs4session.h +++ b/fs/nfs/nfs4session.h @@ -21,7 +21,8 @@ struct nfs4_slot { unsigned long generation; u32 slot_nr; u32 seq_nr; - unsigned int interrupted : 1; + unsigned int interrupted : 1, + seq_done : 1; }; /* Sessions */ From 2e80dbe7ac51a911e8a828407b1a48c5ba938cd2 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 28 Aug 2016 11:50:26 -0400 Subject: [PATCH 430/531] NFSv4.1: Close callback races for OPEN, LAYOUTGET and LAYOUTRETURN Defer freeing the slot until after we have processed the results from OPEN and LAYOUTGET. This means that the server can rely on the mechanism in RFC5661 Section 2.10.6.3 to ensure that replies to an OPEN or LAYOUTGET/RETURN RPC call don't race with the callbacks that apply to them. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 78 +++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 65 insertions(+), 13 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index de4a89d3d740..f5aecaabcb7c 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -634,15 +634,11 @@ int nfs40_setup_sequence(struct nfs4_slot_table *tbl, } EXPORT_SYMBOL_GPL(nfs40_setup_sequence); -static int nfs40_sequence_done(struct rpc_task *task, - struct nfs4_sequence_res *res) +static void nfs40_sequence_free_slot(struct nfs4_sequence_res *res) { struct nfs4_slot *slot = res->sr_slot; struct nfs4_slot_table *tbl; - if (slot == NULL) - goto out; - tbl = slot->table; spin_lock(&tbl->slot_tbl_lock); if (!nfs41_wake_and_assign_slot(tbl, slot)) @@ -650,7 +646,13 @@ static int nfs40_sequence_done(struct rpc_task *task, spin_unlock(&tbl->slot_tbl_lock); res->sr_slot = NULL; -out: +} + +static int nfs40_sequence_done(struct rpc_task *task, + struct nfs4_sequence_res *res) +{ + if (res->sr_slot != NULL) + nfs40_sequence_free_slot(res); return 1; } @@ -695,7 +697,8 @@ static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res) wake_up_all(&tbl->slot_waitq); } -int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res) +static int nfs41_sequence_process(struct rpc_task *task, + struct nfs4_sequence_res *res) { struct nfs4_session *session; struct nfs4_slot *slot = res->sr_slot; @@ -781,11 +784,11 @@ int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res) out: /* The session may be reset by one of the error handlers. */ dprintk("%s: Error %d free the slot \n", __func__, res->sr_status); - nfs41_sequence_free_slot(res); out_noaction: return ret; retry_nowait: if (rpc_restart_call_prepare(task)) { + nfs41_sequence_free_slot(res); task->tk_status = 0; ret = 0; } @@ -796,8 +799,37 @@ int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res) rpc_delay(task, NFS4_POLL_RETRY_MAX); return 0; } + +int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res) +{ + if (!nfs41_sequence_process(task, res)) + return 0; + if (res->sr_slot != NULL) + nfs41_sequence_free_slot(res); + return 1; + +} EXPORT_SYMBOL_GPL(nfs41_sequence_done); +static int nfs4_sequence_process(struct rpc_task *task, struct nfs4_sequence_res *res) +{ + if (res->sr_slot == NULL) + return 1; + if (res->sr_slot->table->session != NULL) + return nfs41_sequence_process(task, res); + return nfs40_sequence_done(task, res); +} + +static void nfs4_sequence_free_slot(struct nfs4_sequence_res *res) +{ + if (res->sr_slot != NULL) { + if (res->sr_slot->table->session != NULL) + nfs41_sequence_free_slot(res); + else + nfs40_sequence_free_slot(res); + } +} + int nfs4_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res) { if (res->sr_slot == NULL) @@ -927,6 +959,17 @@ static int nfs4_setup_sequence(const struct nfs_server *server, args, res, task); } +static int nfs4_sequence_process(struct rpc_task *task, struct nfs4_sequence_res *res) +{ + return nfs40_sequence_done(task, res); +} + +static void nfs4_sequence_free_slot(struct nfs4_sequence_res *res) +{ + if (res->sr_slot != NULL) + nfs40_sequence_free_slot(res); +} + int nfs4_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res) { @@ -1204,6 +1247,7 @@ static void nfs4_opendata_free(struct kref *kref) struct super_block *sb = p->dentry->d_sb; nfs_free_seqid(p->o_arg.seqid); + nfs4_sequence_free_slot(&p->o_res.seq_res); if (p->state != NULL) nfs4_put_open_state(p->state); nfs4_put_state_owner(p->owner); @@ -1663,9 +1707,14 @@ _nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data) static struct nfs4_state * nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data) { + struct nfs4_state *ret; + if (data->o_arg.claim == NFS4_OPEN_CLAIM_PREVIOUS) - return _nfs4_opendata_reclaim_to_nfs4_state(data); - return _nfs4_opendata_to_nfs4_state(data); + ret =_nfs4_opendata_reclaim_to_nfs4_state(data); + else + ret = _nfs4_opendata_to_nfs4_state(data); + nfs4_sequence_free_slot(&data->o_res.seq_res); + return ret; } static struct nfs_open_context *nfs4_state_find_open_context(struct nfs4_state *state) @@ -2063,7 +2112,7 @@ static void nfs4_open_done(struct rpc_task *task, void *calldata) data->rpc_status = task->tk_status; - if (!nfs4_sequence_done(task, &data->o_res.seq_res)) + if (!nfs4_sequence_process(task, &data->o_res.seq_res)) return; if (task->tk_status == 0) { @@ -7871,7 +7920,7 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata) struct nfs4_layoutget *lgp = calldata; dprintk("--> %s\n", __func__); - nfs41_sequence_done(task, &lgp->res.seq_res); + nfs41_sequence_process(task, &lgp->res.seq_res); dprintk("<-- %s\n", __func__); } @@ -8087,6 +8136,7 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout, gfp_t gfp_flags) /* if layoutp->len is 0, nfs4_layoutget_prepare called rpc_exit */ if (status == 0 && lgp->res.layoutp->len) lseg = pnfs_layout_process(lgp); + nfs4_sequence_free_slot(&lgp->res.seq_res); rpc_put_task(task); dprintk("<-- %s status=%d\n", __func__, status); if (status) @@ -8113,7 +8163,7 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata) dprintk("--> %s\n", __func__); - if (!nfs41_sequence_done(task, &lrp->res.seq_res)) + if (!nfs41_sequence_process(task, &lrp->res.seq_res)) return; server = NFS_SERVER(lrp->args.inode); @@ -8125,6 +8175,7 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata) case -NFS4ERR_DELAY: if (nfs4_async_handle_error(task, server, NULL, NULL) != -EAGAIN) break; + nfs4_sequence_free_slot(&lrp->res.seq_res); rpc_restart_call_prepare(task); return; } @@ -8145,6 +8196,7 @@ static void nfs4_layoutreturn_release(void *calldata) pnfs_set_layout_stateid(lo, &lrp->res.stateid, true); pnfs_clear_layoutreturn_waitbit(lo); spin_unlock(&lo->plh_inode->i_lock); + nfs4_sequence_free_slot(&lrp->res.seq_res); pnfs_free_lseg_list(&freeme); pnfs_put_layout_hdr(lrp->args.layout); nfs_iput_and_deactive(lrp->inode); From d138027a8256a3e9d7657c8d0dae84c08ef2cfe1 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 28 Aug 2016 12:19:04 -0400 Subject: [PATCH 431/531] NFSv4.1: Remove obsolete and incorrrect assignment in nfs4_callback_sequence Signed-off-by: Trond Myklebust --- fs/nfs/callback_proc.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index c35932967722..f953ef6b2f2e 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -484,7 +484,6 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args, goto out; tbl = &clp->cl_session->bc_slot_table; - slot = tbl->slots + args->csa_slotid; /* Set up res before grabbing the spinlock */ memcpy(&res->csr_sessionid, &args->csa_sessionid, From add1fa75101263ab4d74240f93000998d4325624 Mon Sep 17 00:00:00 2001 From: Mario Kleiner Date: Sat, 27 Aug 2016 01:02:28 +0200 Subject: [PATCH 432/531] drm/atomic: Don't potentially reset color_mgmt_changed on successive property updates. Due to assigning the 'replaced' value instead of or'ing it, if drm_atomic_crtc_set_property() gets called multiple times, the last call will define the color_mgmt_changed flag, so a non-updating call to a property can reset the flag and prevent actual hw state updates required by preceding property updates. Signed-off-by: Mario Kleiner Cc: Daniel Vetter Cc: # v4.6+ Reviewed-by: Daniel Vetter Signed-off-by: Dave Airlie --- drivers/gpu/drm/drm_atomic.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index fa3930757972..2a3ded44cf2a 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -475,7 +475,7 @@ int drm_atomic_crtc_set_property(struct drm_crtc *crtc, val, -1, &replaced); - state->color_mgmt_changed = replaced; + state->color_mgmt_changed |= replaced; return ret; } else if (property == config->ctm_property) { ret = drm_atomic_replace_property_blob_from_id(crtc, @@ -483,7 +483,7 @@ int drm_atomic_crtc_set_property(struct drm_crtc *crtc, val, sizeof(struct drm_color_ctm), &replaced); - state->color_mgmt_changed = replaced; + state->color_mgmt_changed |= replaced; return ret; } else if (property == config->gamma_lut_property) { ret = drm_atomic_replace_property_blob_from_id(crtc, @@ -491,7 +491,7 @@ int drm_atomic_crtc_set_property(struct drm_crtc *crtc, val, -1, &replaced); - state->color_mgmt_changed = replaced; + state->color_mgmt_changed |= replaced; return ret; } else if (crtc->funcs->atomic_set_property) return crtc->funcs->atomic_set_property(crtc, state, property, val); From 3eab887a55424fc2c27553b7bfe32330df83f7b8 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 28 Aug 2016 15:04:33 -0700 Subject: [PATCH 433/531] Linux 4.8-rc4 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 3537aa23905f..67f42d57e6e7 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 8 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Psychotic Stoned Sheep # *DOCUMENTATION* From 17de0a9ff3df8f54f2f47746d118112d4e61d973 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Aug 2016 11:33:58 +1000 Subject: [PATCH 434/531] iomap: don't set FIEMAP_EXTENT_MERGED for extent based filesystems Filesystems like XFS that use extents should not set the FIEMAP_EXTENT_MERGED flag in the fiemap extent structures. To allow for both behaviors for the upcoming gfs2 usage split the iomap type field into type and flags, and only set FIEMAP_EXTENT_MERGED if the IOMAP_F_MERGED flag is set. The flags field will also come in handy for future features such as shared extents on reflink-enabled file systems. Reported-by: Andreas Gruenbacher Signed-off-by: Christoph Hellwig Acked-by: Darrick J. Wong Signed-off-by: Dave Chinner --- fs/iomap.c | 5 ++++- include/linux/iomap.h | 8 +++++++- 2 files changed, 11 insertions(+), 2 deletions(-) diff --git a/fs/iomap.c b/fs/iomap.c index 0342254646e3..706270f21b35 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -428,9 +428,12 @@ static int iomap_to_fiemap(struct fiemap_extent_info *fi, break; } + if (iomap->flags & IOMAP_F_MERGED) + flags |= FIEMAP_EXTENT_MERGED; + return fiemap_fill_next_extent(fi, iomap->offset, iomap->blkno != IOMAP_NULL_BLOCK ? iomap->blkno << 9: 0, - iomap->length, flags | FIEMAP_EXTENT_MERGED); + iomap->length, flags); } diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 3267df461012..3d70ece10313 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -18,6 +18,11 @@ struct vm_fault; #define IOMAP_MAPPED 0x03 /* blocks allocated @blkno */ #define IOMAP_UNWRITTEN 0x04 /* blocks allocated @blkno in unwritten state */ +/* + * Flags for iomap mappings: + */ +#define IOMAP_F_MERGED 0x01 /* contains multiple blocks/extents */ + /* * Magic value for blkno: */ @@ -27,7 +32,8 @@ struct iomap { sector_t blkno; /* 1st sector of mapping, 512b units */ loff_t offset; /* file offset of mapping, bytes */ u64 length; /* length of mapping, bytes */ - int type; /* type of mapping */ + u16 type; /* type of mapping */ + u16 flags; /* flags for mapping */ struct block_device *bdev; /* block device for I/O */ }; From cc7786d3ee7e3c979799db834b528db2c0834c2e Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Mon, 25 Jul 2016 14:26:51 +1000 Subject: [PATCH 435/531] powerpc/tm: do not use r13 for tabort_syscall tabort_syscall runs with RI=1, so a nested recoverable machine check will load the paca into r13 and overwrite what we loaded it with, because exceptions returning to privileged mode do not restore r13. Fixes: b4b56f9ecab4 (powerpc/tm: Abort syscalls in active transactions) Cc: stable@vger.kernel.org Signed-off-by: Nick Piggin Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/entry_64.S | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 6b8bc0dd09d4..5afd03e5e8b8 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -368,13 +368,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) tabort_syscall: /* Firstly we need to enable TM in the kernel */ mfmsr r10 - li r13, 1 - rldimi r10, r13, MSR_TM_LG, 63-MSR_TM_LG + li r9, 1 + rldimi r10, r9, MSR_TM_LG, 63-MSR_TM_LG mtmsrd r10, 0 /* tabort, this dooms the transaction, nothing else */ - li r13, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT) - TABORT(R13) + li r9, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT) + TABORT(R9) /* * Return directly to userspace. We have corrupted user register state, @@ -382,8 +382,8 @@ tabort_syscall: * resume after the tbegin of the aborted transaction with the * checkpointed register state. */ - li r13, MSR_RI - andc r10, r10, r13 + li r9, MSR_RI + andc r10, r10, r9 mtmsrd r10, 1 mtspr SPRN_SRR0, r11 mtspr SPRN_SRR1, r12 From a9cbf0b2195b695cbeeeecaa4e2770948c212e9a Mon Sep 17 00:00:00 2001 From: Mukesh Ojha Date: Mon, 22 Aug 2016 12:17:44 +0530 Subject: [PATCH 436/531] powerpc/powernv : Drop reference added by kset_find_obj() In a situation, where Linux kernel gets notified about duplicate error log from OPAL, it is been observed that kernel fails to remove sysfs entries (/sys/firmware/opal/elog/0xXXXXXXXX) of such error logs. This is because, we currently search the error log/dump kobject in the kset list via 'kset_find_obj()' routine. Which eventually increment the reference count by one, once it founds the kobject. So, unless we decrement the reference count by one after it found the kobject, we would not be able to release the kobject properly later. This patch adds the 'kobject_put()' which was missing earlier. Signed-off-by: Mukesh Ojha Cc: stable@vger.kernel.org Reviewed-by: Vasant Hegde Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/powernv/opal-dump.c | 7 ++++++- arch/powerpc/platforms/powernv/opal-elog.c | 7 ++++++- 2 files changed, 12 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c index 2ee96431f736..4c827826c05e 100644 --- a/arch/powerpc/platforms/powernv/opal-dump.c +++ b/arch/powerpc/platforms/powernv/opal-dump.c @@ -370,6 +370,7 @@ static irqreturn_t process_dump(int irq, void *data) uint32_t dump_id, dump_size, dump_type; struct dump_obj *dump; char name[22]; + struct kobject *kobj; rc = dump_read_info(&dump_id, &dump_size, &dump_type); if (rc != OPAL_SUCCESS) @@ -381,8 +382,12 @@ static irqreturn_t process_dump(int irq, void *data) * that gracefully and not create two conflicting * entries. */ - if (kset_find_obj(dump_kset, name)) + kobj = kset_find_obj(dump_kset, name); + if (kobj) { + /* Drop reference added by kset_find_obj() */ + kobject_put(kobj); return 0; + } dump = create_dump_obj(dump_id, dump_size, dump_type); if (!dump) diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c index 37f959bf392e..f2344cbd2f46 100644 --- a/arch/powerpc/platforms/powernv/opal-elog.c +++ b/arch/powerpc/platforms/powernv/opal-elog.c @@ -247,6 +247,7 @@ static irqreturn_t elog_event(int irq, void *data) uint64_t elog_type; int rc; char name[2+16+1]; + struct kobject *kobj; rc = opal_get_elog_size(&id, &size, &type); if (rc != OPAL_SUCCESS) { @@ -269,8 +270,12 @@ static irqreturn_t elog_event(int irq, void *data) * that gracefully and not create two conflicting * entries. */ - if (kset_find_obj(elog_kset, name)) + kobj = kset_find_obj(elog_kset, name); + if (kobj) { + /* Drop reference added by kset_find_obj() */ + kobject_put(kobj); return IRQ_HANDLED; + } create_elog_obj(log_id, elog_size, elog_type); From 78a3e8889b4b6b99775ed954696ff3e017f5d19b Mon Sep 17 00:00:00 2001 From: Cyril Bur Date: Tue, 23 Aug 2016 10:46:17 +1000 Subject: [PATCH 437/531] powerpc: signals: Discard transaction state from signal frames Userspace can begin and suspend a transaction within the signal handler which means they might enter sys_rt_sigreturn() with the processor in suspended state. sys_rt_sigreturn() wants to restore process context (which may have been in a transaction before signal delivery). To do this it must restore TM SPRS. To achieve this, any transaction initiated within the signal frame must be discarded in order to be able to restore TM SPRs as TM SPRs can only be manipulated non-transactionally.. >From the PowerPC ISA: TM Bad Thing Exception [Category: Transactional Memory] An attempt is made to execute a mtspr targeting a TM register in other than Non-transactional state. Not doing so results in a TM Bad Thing: [12045.221359] Kernel BUG at c000000000050a40 [verbose debug info unavailable] [12045.221470] Unexpected TM Bad Thing exception at c000000000050a40 (msr 0x201033) [12045.221540] Oops: Unrecoverable exception, sig: 6 [#1] [12045.221586] SMP NR_CPUS=2048 NUMA PowerNV [12045.221634] Modules linked in: xt_CHECKSUM iptable_mangle ipt_MASQUERADE nf_nat_masquerade_ipv4 iptable_nat nf_nat_ipv4 nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_conntrack ipt_REJECT nf_reject_ipv4 xt_tcpudp bridge stp llc ebtable_filter ebtables ip6table_filter ip6_tables iptable_filter ip_tables x_tables kvm_hv kvm uio_pdrv_genirq ipmi_powernv uio powernv_rng ipmi_msghandler autofs4 ses enclosure scsi_transport_sas bnx2x ipr mdio libcrc32c [12045.222167] CPU: 68 PID: 6178 Comm: sigreturnpanic Not tainted 4.7.0 #34 [12045.222224] task: c0000000fce38600 ti: c0000000fceb4000 task.ti: c0000000fceb4000 [12045.222293] NIP: c000000000050a40 LR: c0000000000163bc CTR: 0000000000000000 [12045.222361] REGS: c0000000fceb7ac0 TRAP: 0700 Not tainted (4.7.0) [12045.222418] MSR: 9000000300201033 CR: 28444280 XER: 20000000 [12045.222625] CFAR: c0000000000163b8 SOFTE: 0 PACATMSCRATCH: 900000014280f033 GPR00: 01100000b8000001 c0000000fceb7d40 c00000000139c100 c0000000fce390d0 GPR04: 900000034280f033 0000000000000000 0000000000000000 0000000000000000 GPR08: 0000000000000000 b000000000001033 0000000000000001 0000000000000000 GPR12: 0000000000000000 c000000002926400 0000000000000000 0000000000000000 GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 GPR20: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 GPR24: 0000000000000000 00003ffff98cadd0 00003ffff98cb470 0000000000000000 GPR28: 900000034280f033 c0000000fceb7ea0 0000000000000001 c0000000fce390d0 [12045.223535] NIP [c000000000050a40] tm_restore_sprs+0xc/0x1c [12045.223584] LR [c0000000000163bc] tm_recheckpoint+0x5c/0xa0 [12045.223630] Call Trace: [12045.223655] [c0000000fceb7d80] [c000000000026e74] sys_rt_sigreturn+0x494/0x6c0 [12045.223738] [c0000000fceb7e30] [c0000000000092e0] system_call+0x38/0x108 [12045.223806] Instruction dump: [12045.223841] 7c800164 4e800020 7c0022a6 f80304a8 7c0222a6 f80304b0 7c0122a6 f80304b8 [12045.223955] 4e800020 e80304a8 7c0023a6 e80304b0 <7c0223a6> e80304b8 7c0123a6 4e800020 [12045.224074] ---[ end trace cb8002ee240bae76 ]--- It isn't clear exactly if there is really a use case for userspace returning with a suspended transaction, however, doing so doesn't (on its own) constitute a bad frame. As such, this patch simply discards the transactional state of the context calling the sigreturn and continues. Reported-by: Laurent Dufour Signed-off-by: Cyril Bur Tested-by: Laurent Dufour Reviewed-by: Laurent Dufour Acked-by: Simon Guo Signed-off-by: Benjamin Herrenschmidt --- Documentation/powerpc/transactional_memory.txt | 2 ++ arch/powerpc/kernel/signal_32.c | 14 ++++++++++++++ arch/powerpc/kernel/signal_64.c | 14 ++++++++++++++ 3 files changed, 30 insertions(+) diff --git a/Documentation/powerpc/transactional_memory.txt b/Documentation/powerpc/transactional_memory.txt index ba0a2a4a54ba..e32fdbb4c9a7 100644 --- a/Documentation/powerpc/transactional_memory.txt +++ b/Documentation/powerpc/transactional_memory.txt @@ -167,6 +167,8 @@ signal will be rolled back anyway. For signals taken in non-TM or suspended mode, we use the normal/non-checkpointed stack pointer. +Any transaction initiated inside a sighandler and suspended on return +from the sighandler to the kernel will get reclaimed and discarded. Failure cause codes used by kernel ================================== diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index b6aa378aff63..a7daf749b97f 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -1226,7 +1226,21 @@ long sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, (regs->gpr[1] + __SIGNAL_FRAMESIZE + 16); if (!access_ok(VERIFY_READ, rt_sf, sizeof(*rt_sf))) goto bad; + #ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* + * If there is a transactional state then throw it away. + * The purpose of a sigreturn is to destroy all traces of the + * signal frame, this includes any transactional state created + * within in. We only check for suspended as we can never be + * active in the kernel, we are active, there is nothing better to + * do than go ahead and Bad Thing later. + * The cause is not important as there will never be a + * recheckpoint so it's not user visible. + */ + if (MSR_TM_SUSPENDED(mfmsr())) + tm_reclaim_current(0); + if (__get_user(tmp, &rt_sf->uc.uc_link)) goto bad; uc_transact = (struct ucontext __user *)(uintptr_t)tmp; diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 7e49984d4331..70409bb90a95 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -676,7 +676,21 @@ int sys_rt_sigreturn(unsigned long r3, unsigned long r4, unsigned long r5, if (__copy_from_user(&set, &uc->uc_sigmask, sizeof(set))) goto badframe; set_current_blocked(&set); + #ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* + * If there is a transactional state then throw it away. + * The purpose of a sigreturn is to destroy all traces of the + * signal frame, this includes any transactional state created + * within in. We only check for suspended as we can never be + * active in the kernel, we are active, there is nothing better to + * do than go ahead and Bad Thing later. + * The cause is not important as there will never be a + * recheckpoint so it's not user visible. + */ + if (MSR_TM_SUSPENDED(mfmsr())) + tm_reclaim_current(0); + if (__get_user(msr, &uc->uc_mcontext.gp_regs[PT_MSR])) goto badframe; if (MSR_TM_ACTIVE(msr)) { From fe4c988bdd1cc60402a4e3ca3976a686ea991b5a Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Mon, 29 Aug 2016 01:13:42 +0300 Subject: [PATCH 438/531] net/mlx5e: Limit UMR length to the device's limitation ConnectX-4 UMR (User Memory Region) MTT translation table offset in WQE is limited to U16_MAX, before this patch we ignored that limitation and requested the maximum possible UMR translation length that the netdev might need (MAX channels * MAX pages per channel). In case of a system with #cores > 32 and when linear WQE allocation fails, falling back to using UMR WQEs will cause the RQ (Receive Queue) to get stuck. Here we limit UMR length to min(U16_MAX, max required pages) (while considering the required alignments) on driver load, by default U16_MAX is sufficient since the default RX rings value guarantees that we are in range, dynamically (on set_ringparam/set_channels) we will check if the new required UMR length (num mtts) is still in range, if not, fail the request. Fixes: bc77b240b3c5 ('net/mlx5e: Add fragmented memory support for RX multi packet WQE') Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 14 +++++++------- .../ethernet/mellanox/mlx5/core/en_ethtool.c | 19 +++++++++++++++++++ .../net/ethernet/mellanox/mlx5/core/en_main.c | 11 ++++++++--- .../net/ethernet/mellanox/mlx5/core/en_rx.c | 12 ++++++------ 4 files changed, 40 insertions(+), 16 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 1b495efa7490..d63a1b8f9c13 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -73,8 +73,12 @@ #define MLX5_MPWRQ_PAGES_PER_WQE BIT(MLX5_MPWRQ_WQE_PAGE_ORDER) #define MLX5_MPWRQ_STRIDES_PER_PAGE (MLX5_MPWRQ_NUM_STRIDES >> \ MLX5_MPWRQ_WQE_PAGE_ORDER) -#define MLX5_CHANNEL_MAX_NUM_MTTS (ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8) * \ - BIT(MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE_MPW)) + +#define MLX5_MTT_OCTW(npages) (ALIGN(npages, 8) / 2) +#define MLX5E_REQUIRED_MTTS(rqs, wqes)\ + (rqs * wqes * ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8)) +#define MLX5E_VALID_NUM_MTTS(num_mtts) (MLX5_MTT_OCTW(num_mtts) <= U16_MAX) + #define MLX5_UMR_ALIGN (2048) #define MLX5_MPWRQ_SMALL_PACKET_THRESHOLD (128) @@ -304,6 +308,7 @@ struct mlx5e_rq { unsigned long state; int ix; + u32 mpwqe_mtt_offset; struct mlx5e_rx_am am; /* Adaptive Moderation */ @@ -814,11 +819,6 @@ static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev) MLX5E_MAX_NUM_CHANNELS); } -static inline int mlx5e_get_mtt_octw(int npages) -{ - return ALIGN(npages, 8) / 2; -} - extern const struct ethtool_ops mlx5e_ethtool_ops; #ifdef CONFIG_MLX5_CORE_EN_DCB extern const struct dcbnl_rtnl_ops mlx5e_dcbnl_ops; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 4a3757e60441..9cfe4088d008 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -373,6 +373,7 @@ static int mlx5e_set_ringparam(struct net_device *dev, u16 min_rx_wqes; u8 log_rq_size; u8 log_sq_size; + u32 num_mtts; int err = 0; if (param->rx_jumbo_pending) { @@ -397,6 +398,15 @@ static int mlx5e_set_ringparam(struct net_device *dev, 1 << mlx5_max_log_rq_size(rq_wq_type)); return -EINVAL; } + + num_mtts = MLX5E_REQUIRED_MTTS(priv->params.num_channels, param->rx_pending); + if (priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ && + !MLX5E_VALID_NUM_MTTS(num_mtts)) { + netdev_info(dev, "%s: rx_pending (%d) request can't be satisfied, try to reduce.\n", + __func__, param->rx_pending); + return -EINVAL; + } + if (param->tx_pending < (1 << MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE)) { netdev_info(dev, "%s: tx_pending (%d) < min (%d)\n", __func__, param->tx_pending, @@ -454,6 +464,7 @@ static int mlx5e_set_channels(struct net_device *dev, unsigned int count = ch->combined_count; bool arfs_enabled; bool was_opened; + u32 num_mtts; int err = 0; if (!count) { @@ -472,6 +483,14 @@ static int mlx5e_set_channels(struct net_device *dev, return -EINVAL; } + num_mtts = MLX5E_REQUIRED_MTTS(count, BIT(priv->params.log_rq_size)); + if (priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ && + !MLX5E_VALID_NUM_MTTS(num_mtts)) { + netdev_info(dev, "%s: rx count (%d) request can't be satisfied, try to reduce.\n", + __func__, count); + return -EINVAL; + } + if (priv->params.num_channels == count) return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 03d944c0077e..65360b1f6ee3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -340,6 +340,9 @@ static int mlx5e_create_rq(struct mlx5e_channel *c, rq->alloc_wqe = mlx5e_alloc_rx_mpwqe; rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe; + rq->mpwqe_mtt_offset = c->ix * + MLX5E_REQUIRED_MTTS(1, BIT(priv->params.log_rq_size)); + rq->mpwqe_stride_sz = BIT(priv->params.mpwqe_log_stride_sz); rq->mpwqe_num_strides = BIT(priv->params.mpwqe_log_num_strides); rq->wqe_sz = rq->mpwqe_stride_sz * rq->mpwqe_num_strides; @@ -3233,8 +3236,8 @@ static int mlx5e_create_umr_mkey(struct mlx5e_priv *priv) struct mlx5_create_mkey_mbox_in *in; struct mlx5_mkey_seg *mkc; int inlen = sizeof(*in); - u64 npages = - priv->profile->max_nch(mdev) * MLX5_CHANNEL_MAX_NUM_MTTS; + u64 npages = MLX5E_REQUIRED_MTTS(priv->profile->max_nch(mdev), + BIT(MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE_MPW)); int err; in = mlx5_vzalloc(inlen); @@ -3248,10 +3251,12 @@ static int mlx5e_create_umr_mkey(struct mlx5e_priv *priv) MLX5_PERM_LOCAL_WRITE | MLX5_ACCESS_MODE_MTT; + npages = min_t(u32, ALIGN(U16_MAX, 4) * 2, npages); + mkc->qpn_mkey7_0 = cpu_to_be32(0xffffff << 8); mkc->flags_pd = cpu_to_be32(mdev->mlx5e_res.pdn); mkc->len = cpu_to_be64(npages << PAGE_SHIFT); - mkc->xlt_oct_size = cpu_to_be32(mlx5e_get_mtt_octw(npages)); + mkc->xlt_oct_size = cpu_to_be32(MLX5_MTT_OCTW(npages)); mkc->log2_page_size = PAGE_SHIFT; err = mlx5_core_create_mkey(mdev, &priv->umr_mkey, in, inlen, NULL, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 9f2a16a507e0..bdc9e33a06e4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -324,9 +324,9 @@ mlx5e_copy_skb_header_fragmented_mpwqe(struct device *pdev, } } -static u16 mlx5e_get_wqe_mtt_offset(u16 rq_ix, u16 wqe_ix) +static u32 mlx5e_get_wqe_mtt_offset(struct mlx5e_rq *rq, u16 wqe_ix) { - return rq_ix * MLX5_CHANNEL_MAX_NUM_MTTS + + return rq->mpwqe_mtt_offset + wqe_ix * ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8); } @@ -340,7 +340,7 @@ static void mlx5e_build_umr_wqe(struct mlx5e_rq *rq, struct mlx5_wqe_data_seg *dseg = &wqe->data; struct mlx5e_mpw_info *wi = &rq->wqe_info[ix]; u8 ds_cnt = DIV_ROUND_UP(sizeof(*wqe), MLX5_SEND_WQE_DS); - u16 umr_wqe_mtt_offset = mlx5e_get_wqe_mtt_offset(rq->ix, ix); + u32 umr_wqe_mtt_offset = mlx5e_get_wqe_mtt_offset(rq, ix); memset(wqe, 0, sizeof(*wqe)); cseg->opmod_idx_opcode = @@ -353,9 +353,9 @@ static void mlx5e_build_umr_wqe(struct mlx5e_rq *rq, ucseg->flags = MLX5_UMR_TRANSLATION_OFFSET_EN; ucseg->klm_octowords = - cpu_to_be16(mlx5e_get_mtt_octw(MLX5_MPWRQ_PAGES_PER_WQE)); + cpu_to_be16(MLX5_MTT_OCTW(MLX5_MPWRQ_PAGES_PER_WQE)); ucseg->bsf_octowords = - cpu_to_be16(mlx5e_get_mtt_octw(umr_wqe_mtt_offset)); + cpu_to_be16(MLX5_MTT_OCTW(umr_wqe_mtt_offset)); ucseg->mkey_mask = cpu_to_be64(MLX5_MKEY_MASK_FREE); dseg->lkey = sq->mkey_be; @@ -423,7 +423,7 @@ static int mlx5e_alloc_rx_fragmented_mpwqe(struct mlx5e_rq *rq, { struct mlx5e_mpw_info *wi = &rq->wqe_info[ix]; int mtt_sz = mlx5e_get_wqe_mtt_sz(); - u32 dma_offset = mlx5e_get_wqe_mtt_offset(rq->ix, ix) << PAGE_SHIFT; + u64 dma_offset = (u64)mlx5e_get_wqe_mtt_offset(rq, ix) << PAGE_SHIFT; int i; wi->umr.dma_info = kmalloc(sizeof(*wi->umr.dma_info) * From f2fde18c52a7367a8f6cf6855e2a7174e601c8ee Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Mon, 29 Aug 2016 01:13:43 +0300 Subject: [PATCH 439/531] net/mlx5e: Don't wait for RQ completions on close This will significantly reduce receive queue flush time on interface down. Instead of asking the firmware to flush the RQ (Receive Queue) via asynchronous completions when moved to error, we handle RQ flush manually (mlx5e_free_rx_descs) same as we did when RQ flush got timed out. This will reduce RQs flush time and speedup interface down procedure (ifconfig down) from 6 sec to 0.3 sec on a 48 cores system. Moved mlx5e_free_rx_descs en_main.c where it is needed, to keep en_rx.c free form non critical data path code for better code locality. Fixes: 6cd392a082de ('net/mlx5e: Handle RQ flush in error cases') Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 4 +- .../net/ethernet/mellanox/mlx5/core/en_main.c | 37 +++++++++---------- .../net/ethernet/mellanox/mlx5/core/en_rx.c | 23 ++---------- 3 files changed, 22 insertions(+), 42 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index d63a1b8f9c13..26a7ec7073f2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -223,9 +223,8 @@ struct mlx5e_tstamp { }; enum { - MLX5E_RQ_STATE_POST_WQES_ENABLE, + MLX5E_RQ_STATE_FLUSH, MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, - MLX5E_RQ_STATE_FLUSH_TIMEOUT, MLX5E_RQ_STATE_AM, }; @@ -703,7 +702,6 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget); bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget); int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget); void mlx5e_free_tx_descs(struct mlx5e_sq *sq); -void mlx5e_free_rx_descs(struct mlx5e_rq *rq); void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 65360b1f6ee3..2463eba75125 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -431,7 +431,6 @@ static int mlx5e_enable_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param) MLX5_SET(rqc, rqc, cqn, rq->cq.mcq.cqn); MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RST); - MLX5_SET(rqc, rqc, flush_in_error_en, 1); MLX5_SET(rqc, rqc, vsd, priv->params.vlan_strip_disable); MLX5_SET(wq, wq, log_wq_pg_sz, rq->wq_ctrl.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); @@ -528,6 +527,23 @@ static int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq) return -ETIMEDOUT; } +static void mlx5e_free_rx_descs(struct mlx5e_rq *rq) +{ + struct mlx5_wq_ll *wq = &rq->wq; + struct mlx5e_rx_wqe *wqe; + __be16 wqe_ix_be; + u16 wqe_ix; + + while (!mlx5_wq_ll_is_empty(wq)) { + wqe_ix_be = *wq->tail_next; + wqe_ix = be16_to_cpu(wqe_ix_be); + wqe = mlx5_wq_ll_get_wqe(&rq->wq, wqe_ix); + rq->dealloc_wqe(rq, wqe_ix); + mlx5_wq_ll_pop(&rq->wq, wqe_ix_be, + &wqe->next.next_wqe_index); + } +} + static int mlx5e_open_rq(struct mlx5e_channel *c, struct mlx5e_rq_param *param, struct mlx5e_rq *rq) @@ -551,8 +567,6 @@ static int mlx5e_open_rq(struct mlx5e_channel *c, if (param->am_enabled) set_bit(MLX5E_RQ_STATE_AM, &c->rq.state); - set_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state); - sq->ico_wqe_info[pi].opcode = MLX5_OPCODE_NOP; sq->ico_wqe_info[pi].num_wqebbs = 1; mlx5e_send_nop(sq, true); /* trigger mlx5e_post_rx_wqes() */ @@ -569,23 +583,8 @@ static int mlx5e_open_rq(struct mlx5e_channel *c, static void mlx5e_close_rq(struct mlx5e_rq *rq) { - int tout = 0; - int err; - - clear_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state); + set_bit(MLX5E_RQ_STATE_FLUSH, &rq->state); napi_synchronize(&rq->channel->napi); /* prevent mlx5e_post_rx_wqes */ - - err = mlx5e_modify_rq_state(rq, MLX5_RQC_STATE_RDY, MLX5_RQC_STATE_ERR); - while (!mlx5_wq_ll_is_empty(&rq->wq) && !err && - tout++ < MLX5_EN_QP_FLUSH_MAX_ITER) - msleep(MLX5_EN_QP_FLUSH_MSLEEP_QUANT); - - if (err || tout == MLX5_EN_QP_FLUSH_MAX_ITER) - set_bit(MLX5E_RQ_STATE_FLUSH_TIMEOUT, &rq->state); - - /* avoid destroying rq before mlx5e_poll_rx_cq() is done with it */ - napi_synchronize(&rq->channel->napi); - cancel_work_sync(&rq->am.work); mlx5e_disable_rq(rq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index bdc9e33a06e4..fee1e47769a8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -595,26 +595,9 @@ void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) wi->free_wqe(rq, wi); } -void mlx5e_free_rx_descs(struct mlx5e_rq *rq) -{ - struct mlx5_wq_ll *wq = &rq->wq; - struct mlx5e_rx_wqe *wqe; - __be16 wqe_ix_be; - u16 wqe_ix; - - while (!mlx5_wq_ll_is_empty(wq)) { - wqe_ix_be = *wq->tail_next; - wqe_ix = be16_to_cpu(wqe_ix_be); - wqe = mlx5_wq_ll_get_wqe(&rq->wq, wqe_ix); - rq->dealloc_wqe(rq, wqe_ix); - mlx5_wq_ll_pop(&rq->wq, wqe_ix_be, - &wqe->next.next_wqe_index); - } -} - #define RQ_CANNOT_POST(rq) \ - (!test_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state) || \ - test_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state)) + (test_bit(MLX5E_RQ_STATE_FLUSH, &rq->state) || \ + test_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state)) bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq) { @@ -916,7 +899,7 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq); int work_done = 0; - if (unlikely(test_bit(MLX5E_RQ_STATE_FLUSH_TIMEOUT, &rq->state))) + if (unlikely(test_bit(MLX5E_RQ_STATE_FLUSH, &rq->state))) return 0; if (cq->decmprs_left) From 8484f9ed13b26043be80ff5774506024956eae8f Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Mon, 29 Aug 2016 01:13:44 +0300 Subject: [PATCH 440/531] net/mlx5e: Don't post fragmented MPWQE when RQ is disabled ICO (Internal control operations) SQ (Send Queue) is closed/disabled after RQ (Receive Queue). After RQ is closed an ICO SQ completion might post a fragmented MPWQE (Multi Packet Work Queue Element) into that RQ. As on regular RQ post, check if we are allowed to post to that RQ (RQ is enabled). Cleanup in-progress UMR MPWQE on mlx5e_free_rx_descs if needed. Fixes: bc77b240b3c5 ('net/mlx5e: Add fragmented memory support for RX multi packet WQE') Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 4 ++++ drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 6 ++++++ 2 files changed, 10 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 2463eba75125..e259eaa18f55 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -534,6 +534,10 @@ static void mlx5e_free_rx_descs(struct mlx5e_rq *rq) __be16 wqe_ix_be; u16 wqe_ix; + /* UMR WQE (if in progress) is always at wq->head */ + if (test_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state)) + mlx5e_free_rx_fragmented_mpwqe(rq, &rq->wqe_info[wq->head]); + while (!mlx5_wq_ll_is_empty(wq)) { wqe_ix_be = *wq->tail_next; wqe_ix = be16_to_cpu(wqe_ix_be); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index fee1e47769a8..b6f8ebbdb487 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -506,6 +506,12 @@ void mlx5e_post_rx_fragmented_mpwqe(struct mlx5e_rq *rq) struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(wq, wq->head); clear_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state); + + if (unlikely(test_bit(MLX5E_RQ_STATE_FLUSH, &rq->state))) { + mlx5e_free_rx_fragmented_mpwqe(rq, &rq->wqe_info[wq->head]); + return; + } + mlx5_wq_ll_push(wq, be16_to_cpu(wqe->next.next_wqe_index)); rq->stats.mpwqe_frag++; From 6e8dd6d6f4bd2fd6fefdbf2e73bf251e36db59af Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Mon, 29 Aug 2016 01:13:45 +0300 Subject: [PATCH 441/531] net/mlx5e: Don't wait for SQ completions on close Instead of asking the firmware to flush the SQ (Send Queue) via asynchronous completions when moved to error, we handle SQ flush manually (mlx5e_free_tx_descs) same as we did when SQ flush got timed out or on tx_timeout. This will reduce SQs flush time and speedup interface down procedure. Moved mlx5e_free_tx_descs to the end of en_tx.c for tx critical code locality. Fixes: 29429f3300a3 ('net/mlx5e: Timeout if SQ doesn't flush during close') Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 3 +- .../net/ethernet/mellanox/mlx5/core/en_main.c | 50 ++++---------- .../net/ethernet/mellanox/mlx5/core/en_tx.c | 67 +++++++++---------- .../net/ethernet/mellanox/mlx5/core/en_txrx.c | 6 +- 4 files changed, 50 insertions(+), 76 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 26a7ec7073f2..bf722aa88cf0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -369,9 +369,8 @@ struct mlx5e_sq_dma { }; enum { - MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, + MLX5E_SQ_STATE_FLUSH, MLX5E_SQ_STATE_BF_ENABLE, - MLX5E_SQ_STATE_TX_TIMEOUT, }; struct mlx5e_ico_wqe_info { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index e259eaa18f55..297781af53c7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -39,13 +39,6 @@ #include "eswitch.h" #include "vxlan.h" -enum { - MLX5_EN_QP_FLUSH_TIMEOUT_MS = 5000, - MLX5_EN_QP_FLUSH_MSLEEP_QUANT = 20, - MLX5_EN_QP_FLUSH_MAX_ITER = MLX5_EN_QP_FLUSH_TIMEOUT_MS / - MLX5_EN_QP_FLUSH_MSLEEP_QUANT, -}; - struct mlx5e_rq_param { u32 rqc[MLX5_ST_SZ_DW(rqc)]; struct mlx5_wq_param wq; @@ -827,7 +820,6 @@ static int mlx5e_open_sq(struct mlx5e_channel *c, goto err_disable_sq; if (sq->txq) { - set_bit(MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, &sq->state); netdev_tx_reset_queue(sq->txq); netif_tx_start_queue(sq->txq); } @@ -851,38 +843,20 @@ static inline void netif_tx_disable_queue(struct netdev_queue *txq) static void mlx5e_close_sq(struct mlx5e_sq *sq) { - int tout = 0; - int err; - - if (sq->txq) { - clear_bit(MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, &sq->state); - /* prevent netif_tx_wake_queue */ - napi_synchronize(&sq->channel->napi); - netif_tx_disable_queue(sq->txq); - - /* ensure hw is notified of all pending wqes */ - if (mlx5e_sq_has_room_for(sq, 1)) - mlx5e_send_nop(sq, true); - - err = mlx5e_modify_sq(sq, MLX5_SQC_STATE_RDY, - MLX5_SQC_STATE_ERR, false, 0); - if (err) - set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state); - } - - /* wait till sq is empty, unless a TX timeout occurred on this SQ */ - while (sq->cc != sq->pc && - !test_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state)) { - msleep(MLX5_EN_QP_FLUSH_MSLEEP_QUANT); - if (tout++ > MLX5_EN_QP_FLUSH_MAX_ITER) - set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state); - } - - /* avoid destroying sq before mlx5e_poll_tx_cq() is done with it */ + set_bit(MLX5E_SQ_STATE_FLUSH, &sq->state); + /* prevent netif_tx_wake_queue */ napi_synchronize(&sq->channel->napi); - mlx5e_free_tx_descs(sq); + if (sq->txq) { + netif_tx_disable_queue(sq->txq); + + /* last doorbell out, godspeed .. */ + if (mlx5e_sq_has_room_for(sq, 1)) + mlx5e_send_nop(sq, true); + } + mlx5e_disable_sq(sq); + mlx5e_free_tx_descs(sq); mlx5e_destroy_sq(sq); } @@ -2802,7 +2776,7 @@ static void mlx5e_tx_timeout(struct net_device *dev) if (!netif_xmit_stopped(netdev_get_tx_queue(dev, i))) continue; sched_work = true; - set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state); + set_bit(MLX5E_SQ_STATE_FLUSH, &sq->state); netdev_err(dev, "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x\n", i, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index e073bf59890d..5f209ade17bf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -394,35 +394,6 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev) return mlx5e_sq_xmit(sq, skb); } -void mlx5e_free_tx_descs(struct mlx5e_sq *sq) -{ - struct mlx5e_tx_wqe_info *wi; - struct sk_buff *skb; - u16 ci; - int i; - - while (sq->cc != sq->pc) { - ci = sq->cc & sq->wq.sz_m1; - skb = sq->skb[ci]; - wi = &sq->wqe_info[ci]; - - if (!skb) { /* nop */ - sq->cc++; - continue; - } - - for (i = 0; i < wi->num_dma; i++) { - struct mlx5e_sq_dma *dma = - mlx5e_dma_get(sq, sq->dma_fifo_cc++); - - mlx5e_tx_dma_unmap(sq->pdev, dma); - } - - dev_kfree_skb_any(skb); - sq->cc += wi->num_wqebbs; - } -} - bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) { struct mlx5e_sq *sq; @@ -434,7 +405,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) sq = container_of(cq, struct mlx5e_sq, cq); - if (unlikely(test_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state))) + if (unlikely(test_bit(MLX5E_SQ_STATE_FLUSH, &sq->state))) return false; npkts = 0; @@ -512,11 +483,39 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) netdev_tx_completed_queue(sq->txq, npkts, nbytes); if (netif_tx_queue_stopped(sq->txq) && - mlx5e_sq_has_room_for(sq, MLX5E_SQ_STOP_ROOM) && - likely(test_bit(MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, &sq->state))) { - netif_tx_wake_queue(sq->txq); - sq->stats.wake++; + mlx5e_sq_has_room_for(sq, MLX5E_SQ_STOP_ROOM)) { + netif_tx_wake_queue(sq->txq); + sq->stats.wake++; } return (i == MLX5E_TX_CQ_POLL_BUDGET); } + +void mlx5e_free_tx_descs(struct mlx5e_sq *sq) +{ + struct mlx5e_tx_wqe_info *wi; + struct sk_buff *skb; + u16 ci; + int i; + + while (sq->cc != sq->pc) { + ci = sq->cc & sq->wq.sz_m1; + skb = sq->skb[ci]; + wi = &sq->wqe_info[ci]; + + if (!skb) { /* nop */ + sq->cc++; + continue; + } + + for (i = 0; i < wi->num_dma; i++) { + struct mlx5e_sq_dma *dma = + mlx5e_dma_get(sq, sq->dma_fifo_cc++); + + mlx5e_tx_dma_unmap(sq->pdev, dma); + } + + dev_kfree_skb_any(skb); + sq->cc += wi->num_wqebbs; + } +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index 64ae2e800daa..9bf33bb69210 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -51,16 +51,18 @@ struct mlx5_cqe64 *mlx5e_get_cqe(struct mlx5e_cq *cq) static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq) { + struct mlx5e_sq *sq = container_of(cq, struct mlx5e_sq, cq); struct mlx5_wq_cyc *wq; struct mlx5_cqe64 *cqe; - struct mlx5e_sq *sq; u16 sqcc; + if (unlikely(test_bit(MLX5E_SQ_STATE_FLUSH, &sq->state))) + return; + cqe = mlx5e_get_cqe(cq); if (likely(!cqe)) return; - sq = container_of(cq, struct mlx5e_sq, cq); wq = &sq->wq; /* sq->cc must be updated only after mlx5_cqwq_update_db_record(), From cc8e9ebf952699cb6870f1366a4920d05b036e31 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Mon, 29 Aug 2016 01:13:46 +0300 Subject: [PATCH 442/531] net/mlx5e: Fix ethtool -g/G rx ring parameter report with striding RQ The driver RQ has two possible configurations: striding RQ and non-striding RQ. Until this patch, the driver always reported the number of hardware WQEs (ring descriptors). For non striding RQ configuration, this was OK since we have one WQE per pending packet For striding RQ, multiple packets can fit into one WQE. For better user experience we normalize the rx_pending parameter (size of wqe/mtu) as the average ring size in case of striding RQ. Fixes: 461017cb006a ('net/mlx5e: Support RX multi-packet WQE ...') Signed-off-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- .../ethernet/mellanox/mlx5/core/en_ethtool.c | 76 ++++++++++++++++--- 1 file changed, 67 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 9cfe4088d008..d0cf8fa22659 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -352,15 +352,61 @@ static void mlx5e_get_ethtool_stats(struct net_device *dev, sq_stats_desc, j); } +static u32 mlx5e_rx_wqes_to_packets(struct mlx5e_priv *priv, int rq_wq_type, + int num_wqe) +{ + int packets_per_wqe; + int stride_size; + int num_strides; + int wqe_size; + + if (rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) + return num_wqe; + + stride_size = 1 << priv->params.mpwqe_log_stride_sz; + num_strides = 1 << priv->params.mpwqe_log_num_strides; + wqe_size = stride_size * num_strides; + + packets_per_wqe = wqe_size / + ALIGN(ETH_DATA_LEN, stride_size); + return (1 << (order_base_2(num_wqe * packets_per_wqe) - 1)); +} + +static u32 mlx5e_packets_to_rx_wqes(struct mlx5e_priv *priv, int rq_wq_type, + int num_packets) +{ + int packets_per_wqe; + int stride_size; + int num_strides; + int wqe_size; + int num_wqes; + + if (rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) + return num_packets; + + stride_size = 1 << priv->params.mpwqe_log_stride_sz; + num_strides = 1 << priv->params.mpwqe_log_num_strides; + wqe_size = stride_size * num_strides; + + num_packets = (1 << order_base_2(num_packets)); + + packets_per_wqe = wqe_size / + ALIGN(ETH_DATA_LEN, stride_size); + num_wqes = DIV_ROUND_UP(num_packets, packets_per_wqe); + return 1 << (order_base_2(num_wqes)); +} + static void mlx5e_get_ringparam(struct net_device *dev, struct ethtool_ringparam *param) { struct mlx5e_priv *priv = netdev_priv(dev); int rq_wq_type = priv->params.rq_wq_type; - param->rx_max_pending = 1 << mlx5_max_log_rq_size(rq_wq_type); + param->rx_max_pending = mlx5e_rx_wqes_to_packets(priv, rq_wq_type, + 1 << mlx5_max_log_rq_size(rq_wq_type)); param->tx_max_pending = 1 << MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE; - param->rx_pending = 1 << priv->params.log_rq_size; + param->rx_pending = mlx5e_rx_wqes_to_packets(priv, rq_wq_type, + 1 << priv->params.log_rq_size); param->tx_pending = 1 << priv->params.log_sq_size; } @@ -370,6 +416,9 @@ static int mlx5e_set_ringparam(struct net_device *dev, struct mlx5e_priv *priv = netdev_priv(dev); bool was_opened; int rq_wq_type = priv->params.rq_wq_type; + u32 rx_pending_wqes; + u32 min_rq_size; + u32 max_rq_size; u16 min_rx_wqes; u8 log_rq_size; u8 log_sq_size; @@ -386,20 +435,29 @@ static int mlx5e_set_ringparam(struct net_device *dev, __func__); return -EINVAL; } - if (param->rx_pending < (1 << mlx5_min_log_rq_size(rq_wq_type))) { + + min_rq_size = mlx5e_rx_wqes_to_packets(priv, rq_wq_type, + 1 << mlx5_min_log_rq_size(rq_wq_type)); + max_rq_size = mlx5e_rx_wqes_to_packets(priv, rq_wq_type, + 1 << mlx5_max_log_rq_size(rq_wq_type)); + rx_pending_wqes = mlx5e_packets_to_rx_wqes(priv, rq_wq_type, + param->rx_pending); + + if (param->rx_pending < min_rq_size) { netdev_info(dev, "%s: rx_pending (%d) < min (%d)\n", __func__, param->rx_pending, - 1 << mlx5_min_log_rq_size(rq_wq_type)); + min_rq_size); return -EINVAL; } - if (param->rx_pending > (1 << mlx5_max_log_rq_size(rq_wq_type))) { + if (param->rx_pending > max_rq_size) { netdev_info(dev, "%s: rx_pending (%d) > max (%d)\n", __func__, param->rx_pending, - 1 << mlx5_max_log_rq_size(rq_wq_type)); + max_rq_size); return -EINVAL; } - num_mtts = MLX5E_REQUIRED_MTTS(priv->params.num_channels, param->rx_pending); + num_mtts = MLX5E_REQUIRED_MTTS(priv->params.num_channels, + rx_pending_wqes); if (priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ && !MLX5E_VALID_NUM_MTTS(num_mtts)) { netdev_info(dev, "%s: rx_pending (%d) request can't be satisfied, try to reduce.\n", @@ -420,9 +478,9 @@ static int mlx5e_set_ringparam(struct net_device *dev, return -EINVAL; } - log_rq_size = order_base_2(param->rx_pending); + log_rq_size = order_base_2(rx_pending_wqes); log_sq_size = order_base_2(param->tx_pending); - min_rx_wqes = mlx5_min_rx_wqes(rq_wq_type, param->rx_pending); + min_rx_wqes = mlx5_min_rx_wqes(rq_wq_type, rx_pending_wqes); if (log_rq_size == priv->params.log_rq_size && log_sq_size == priv->params.log_sq_size && From c8cf78fe100b0d152a1932327c24cefc0ba4bdbe Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Mon, 29 Aug 2016 01:13:47 +0300 Subject: [PATCH 443/531] net/mlx5e: Add ethtool counter for TX xmit_more Add a counter in ethtool for the number of times that TX xmit_more was used. Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 1 + drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | 4 ++++ drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 1 + 3 files changed, 6 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 297781af53c7..2459c7f3db8d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -155,6 +155,7 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv) s->tx_queue_stopped += sq_stats->stopped; s->tx_queue_wake += sq_stats->wake; s->tx_queue_dropped += sq_stats->dropped; + s->tx_xmit_more += sq_stats->xmit_more; s->tx_csum_partial_inner += sq_stats->csum_partial_inner; tx_offload_none += sq_stats->csum_none; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 7b9d8a989b52..499487ce3b53 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -70,6 +70,7 @@ struct mlx5e_sw_stats { u64 tx_queue_stopped; u64 tx_queue_wake; u64 tx_queue_dropped; + u64 tx_xmit_more; u64 rx_wqe_err; u64 rx_mpwqe_filler; u64 rx_mpwqe_frag; @@ -101,6 +102,7 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_stopped) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_wake) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_dropped) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xmit_more) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_wqe_err) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_frag) }, @@ -298,6 +300,7 @@ struct mlx5e_sq_stats { /* commonly accessed in data path */ u64 packets; u64 bytes; + u64 xmit_more; u64 tso_packets; u64 tso_bytes; u64 tso_inner_packets; @@ -324,6 +327,7 @@ static const struct counter_desc sq_stats_desc[] = { { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, stopped) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, wake) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, dropped) }, + { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, xmit_more) }, }; #define NUM_SW_COUNTERS ARRAY_SIZE(sw_stats_desc) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 5f209ade17bf..988eca99ee0f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -375,6 +375,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) sq->stats.packets++; sq->stats.bytes += num_bytes; + sq->stats.xmit_more += skb->xmit_more; return NETDEV_TX_OK; dma_unmap_wqe_err: From bf50082c15eb2bc47d1922e70f424c57f36646d5 Mon Sep 17 00:00:00 2001 From: Kamal Heib Date: Mon, 29 Aug 2016 01:13:48 +0300 Subject: [PATCH 444/531] net/mlx5e: Fix memory leak if refreshing TIRs fails Free 'in' command object also when mlx5_core_modify_tir fails. Fixes: 724b2aa15126 ("net/mlx5e: TIRs management refactoring") Signed-off-by: Kamal Heib Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en_common.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index 673043ccd76c..9cce153e1035 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -139,7 +139,7 @@ int mlx5e_refresh_tirs_self_loopback_enable(struct mlx5_core_dev *mdev) struct mlx5e_tir *tir; void *in; int inlen; - int err; + int err = 0; inlen = MLX5_ST_SZ_BYTES(modify_tir_in); in = mlx5_vzalloc(inlen); @@ -151,10 +151,11 @@ int mlx5e_refresh_tirs_self_loopback_enable(struct mlx5_core_dev *mdev) list_for_each_entry(tir, &mdev->mlx5e_res.td.tirs_list, list) { err = mlx5_core_modify_tir(mdev, tir->tirn, in, inlen); if (err) - return err; + goto out; } +out: kvfree(in); - return 0; + return err; } From 1722b9694ecfbc602865017c3fa6da0e3ec234d8 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Mon, 29 Aug 2016 01:13:49 +0300 Subject: [PATCH 445/531] net/mlx5: Add error prints when validate ETS failed Upon set ETS failure due to user invalid input, add error prints to specify the exact error to the user. Fixes: cdcf11212b22 ('net/mlx5e: Validate BW weight values of ETS') Signed-off-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- .../ethernet/mellanox/mlx5/core/en_dcbnl.c | 21 ++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index caa9a3ccc3f3..762af16ed021 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -127,29 +127,40 @@ int mlx5e_dcbnl_ieee_setets_core(struct mlx5e_priv *priv, struct ieee_ets *ets) return mlx5_set_port_tc_bw_alloc(mdev, tc_tx_bw); } -static int mlx5e_dbcnl_validate_ets(struct ieee_ets *ets) +static int mlx5e_dbcnl_validate_ets(struct net_device *netdev, + struct ieee_ets *ets) { int bw_sum = 0; int i; /* Validate Priority */ for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { - if (ets->prio_tc[i] >= MLX5E_MAX_PRIORITY) + if (ets->prio_tc[i] >= MLX5E_MAX_PRIORITY) { + netdev_err(netdev, + "Failed to validate ETS: priority value greater than max(%d)\n", + MLX5E_MAX_PRIORITY); return -EINVAL; + } } /* Validate Bandwidth Sum */ for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) { - if (!ets->tc_tx_bw[i]) + if (!ets->tc_tx_bw[i]) { + netdev_err(netdev, + "Failed to validate ETS: BW 0 is illegal\n"); return -EINVAL; + } bw_sum += ets->tc_tx_bw[i]; } } - if (bw_sum != 0 && bw_sum != 100) + if (bw_sum != 0 && bw_sum != 100) { + netdev_err(netdev, + "Failed to validate ETS: BW sum is illegal\n"); return -EINVAL; + } return 0; } @@ -159,7 +170,7 @@ static int mlx5e_dcbnl_ieee_setets(struct net_device *netdev, struct mlx5e_priv *priv = netdev_priv(netdev); int err; - err = mlx5e_dbcnl_validate_ets(ets); + err = mlx5e_dbcnl_validate_ets(netdev, ets); if (err) return err; From e5835f2833b12808c53aa621d1d3aa085706b5b3 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Mon, 29 Aug 2016 01:13:50 +0300 Subject: [PATCH 446/531] net/mlx5: Increase number of ethtool steering priorities Ethtool has 11 flow tables, each flow table has its own priority. Increase the number of priorities to be aligned with the number of flow tables. Fixes: 1174fce8d141 ('net/mlx5e: Support l3/l4 flow type specs in ethtool flow steering') Signed-off-by: Maor Gottlieb Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 75bb8c864557..3d6c1f65e586 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -80,7 +80,7 @@ LEFTOVERS_NUM_PRIOS) #define ETHTOOL_PRIO_NUM_LEVELS 1 -#define ETHTOOL_NUM_PRIOS 10 +#define ETHTOOL_NUM_PRIOS 11 #define ETHTOOL_MIN_LEVEL (KERNEL_MIN_LEVEL + ETHTOOL_NUM_PRIOS) /* Vlan, mac, ttc, aRFS */ #define KERNEL_NIC_PRIO_NUM_LEVELS 4 From 7d13eca09ed5e477f6ecfd97a35058762228b5e4 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Sat, 27 Aug 2016 15:34:20 -0700 Subject: [PATCH 447/531] Documentation: networking: dsa: Remove platform device TODO Since commit 83c0afaec7b7 ("net: dsa: Add new binding implementation"), the shortcomings of the dsa platform device have been addressed, remove that TODO item. Signed-off-by: Florian Fainelli Acked-by: Andrew Lunn Signed-off-by: David S. Miller --- Documentation/networking/dsa/dsa.txt | 20 -------------------- 1 file changed, 20 deletions(-) diff --git a/Documentation/networking/dsa/dsa.txt b/Documentation/networking/dsa/dsa.txt index 9d05ed7f7da5..f20c884c048a 100644 --- a/Documentation/networking/dsa/dsa.txt +++ b/Documentation/networking/dsa/dsa.txt @@ -587,26 +587,6 @@ of DSA, would be the its port-based VLAN, used by the associated bridge device. TODO ==== -The platform device problem ---------------------------- -DSA is currently implemented as a platform device driver which is far from ideal -as was discussed in this thread: - -http://permalink.gmane.org/gmane.linux.network/329848 - -This basically prevents the device driver model to be properly used and applied, -and support non-MDIO, non-MMIO Ethernet connected switches. - -Another problem with the platform device driver approach is that it prevents the -use of a modular switch drivers build due to a circular dependency, illustrated -here: - -http://comments.gmane.org/gmane.linux.network/345803 - -Attempts of reworking this has been done here: - -https://lwn.net/Articles/643149/ - Making SWITCHDEV and DSA converge towards an unified codebase ------------------------------------------------------------- From 2fb04fdf30192ff1e2b5834e9b7745889ea8bbcb Mon Sep 17 00:00:00 2001 From: Russell King Date: Sat, 27 Aug 2016 17:33:03 +0100 Subject: [PATCH 448/531] net: smc91x: fix SMC accesses Commit b70661c70830 ("net: smc91x: use run-time configuration on all ARM machines") broke some ARM platforms through several mistakes. Firstly, the access size must correspond to the following rule: (a) at least one of 16-bit or 8-bit access size must be supported (b) 32-bit accesses are optional, and may be enabled in addition to the above. Secondly, it provides no emulation of 16-bit accesses, instead blindly making 16-bit accesses even when the platform specifies that only 8-bit is supported. Reorganise smc91x.h so we can make use of the existing 16-bit access emulation already provided - if 16-bit accesses are supported, use 16-bit accesses directly, otherwise if 8-bit accesses are supported, use the provided 16-bit access emulation. If neither, BUG(). This exactly reflects the driver behaviour prior to the commit being fixed. Since the conversion incorrectly cut down the available access sizes on several platforms, we also need to go through every platform and fix up the overly-restrictive access size: Arnd assumed that if a platform can perform 32-bit, 16-bit and 8-bit accesses, then only a 32-bit access size needed to be specified - not so, all available access sizes must be specified. This likely fixes some performance regressions in doing this: if a platform does not support 8-bit accesses, 8-bit accesses have been emulated by performing a 16-bit read-modify-write access. Tested on the Intel Assabet/Neponset platform, which supports only 8-bit accesses, which was broken by the original commit. Fixes: b70661c70830 ("net: smc91x: use run-time configuration on all ARM machines") Signed-off-by: Russell King Tested-by: Robert Jarzmik Signed-off-by: David S. Miller --- arch/arm/mach-pxa/idp.c | 3 +- arch/arm/mach-pxa/xcep.c | 3 +- arch/arm/mach-realview/core.c | 3 +- arch/arm/mach-sa1100/pleb.c | 2 +- arch/blackfin/mach-bf561/boards/cm_bf561.c | 3 +- arch/blackfin/mach-bf561/boards/ezkit.c | 3 +- drivers/net/ethernet/smsc/smc91x.c | 7 +++ drivers/net/ethernet/smsc/smc91x.h | 65 +++++++++++++++------- include/linux/smc91x.h | 10 ++++ 9 files changed, 73 insertions(+), 26 deletions(-) diff --git a/arch/arm/mach-pxa/idp.c b/arch/arm/mach-pxa/idp.c index c410d84b243d..66070acaa888 100644 --- a/arch/arm/mach-pxa/idp.c +++ b/arch/arm/mach-pxa/idp.c @@ -83,7 +83,8 @@ static struct resource smc91x_resources[] = { }; static struct smc91x_platdata smc91x_platdata = { - .flags = SMC91X_USE_32BIT | SMC91X_USE_DMA | SMC91X_NOWAIT, + .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT | + SMC91X_USE_DMA | SMC91X_NOWAIT, }; static struct platform_device smc91x_device = { diff --git a/arch/arm/mach-pxa/xcep.c b/arch/arm/mach-pxa/xcep.c index 3f06cd90567a..056369ef250e 100644 --- a/arch/arm/mach-pxa/xcep.c +++ b/arch/arm/mach-pxa/xcep.c @@ -120,7 +120,8 @@ static struct resource smc91x_resources[] = { }; static struct smc91x_platdata xcep_smc91x_info = { - .flags = SMC91X_USE_32BIT | SMC91X_NOWAIT | SMC91X_USE_DMA, + .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT | + SMC91X_NOWAIT | SMC91X_USE_DMA, }; static struct platform_device smc91x_device = { diff --git a/arch/arm/mach-realview/core.c b/arch/arm/mach-realview/core.c index baf174542e36..a0ead0ae23d6 100644 --- a/arch/arm/mach-realview/core.c +++ b/arch/arm/mach-realview/core.c @@ -93,7 +93,8 @@ static struct smsc911x_platform_config smsc911x_config = { }; static struct smc91x_platdata smc91x_platdata = { - .flags = SMC91X_USE_32BIT | SMC91X_NOWAIT, + .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT | + SMC91X_NOWAIT, }; static struct platform_device realview_eth_device = { diff --git a/arch/arm/mach-sa1100/pleb.c b/arch/arm/mach-sa1100/pleb.c index 1525d7b5f1b7..88149f85bc49 100644 --- a/arch/arm/mach-sa1100/pleb.c +++ b/arch/arm/mach-sa1100/pleb.c @@ -45,7 +45,7 @@ static struct resource smc91x_resources[] = { }; static struct smc91x_platdata smc91x_platdata = { - .flags = SMC91X_USE_16BIT | SMC91X_NOWAIT, + .flags = SMC91X_USE_16BIT | SMC91X_USE_8BIT | SMC91X_NOWAIT, }; static struct platform_device smc91x_device = { diff --git a/arch/blackfin/mach-bf561/boards/cm_bf561.c b/arch/blackfin/mach-bf561/boards/cm_bf561.c index c6db52ba3a06..10c57771822d 100644 --- a/arch/blackfin/mach-bf561/boards/cm_bf561.c +++ b/arch/blackfin/mach-bf561/boards/cm_bf561.c @@ -146,7 +146,8 @@ static struct platform_device hitachi_fb_device = { #include static struct smc91x_platdata smc91x_info = { - .flags = SMC91X_USE_32BIT | SMC91X_NOWAIT, + .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT | + SMC91X_NOWAIT, .leda = RPC_LED_100_10, .ledb = RPC_LED_TX_RX, }; diff --git a/arch/blackfin/mach-bf561/boards/ezkit.c b/arch/blackfin/mach-bf561/boards/ezkit.c index f35525b55819..57d1c43726d9 100644 --- a/arch/blackfin/mach-bf561/boards/ezkit.c +++ b/arch/blackfin/mach-bf561/boards/ezkit.c @@ -134,7 +134,8 @@ static struct platform_device net2272_bfin_device = { #include static struct smc91x_platdata smc91x_info = { - .flags = SMC91X_USE_32BIT | SMC91X_NOWAIT, + .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT | + SMC91X_NOWAIT, .leda = RPC_LED_100_10, .ledb = RPC_LED_TX_RX, }; diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c index 726b80f45906..503a3b6dce91 100644 --- a/drivers/net/ethernet/smsc/smc91x.c +++ b/drivers/net/ethernet/smsc/smc91x.c @@ -2275,6 +2275,13 @@ static int smc_drv_probe(struct platform_device *pdev) if (pd) { memcpy(&lp->cfg, pd, sizeof(lp->cfg)); lp->io_shift = SMC91X_IO_SHIFT(lp->cfg.flags); + + if (!SMC_8BIT(lp) && !SMC_16BIT(lp)) { + dev_err(&pdev->dev, + "at least one of 8-bit or 16-bit access support is required.\n"); + ret = -ENXIO; + goto out_free_netdev; + } } #if IS_BUILTIN(CONFIG_OF) diff --git a/drivers/net/ethernet/smsc/smc91x.h b/drivers/net/ethernet/smsc/smc91x.h index 1a55c7976df0..e17671c9d1b0 100644 --- a/drivers/net/ethernet/smsc/smc91x.h +++ b/drivers/net/ethernet/smsc/smc91x.h @@ -36,6 +36,27 @@ #include #include +/* + * Any 16-bit access is performed with two 8-bit accesses if the hardware + * can't do it directly. Most registers are 16-bit so those are mandatory. + */ +#define SMC_outw_b(x, a, r) \ + do { \ + unsigned int __val16 = (x); \ + unsigned int __reg = (r); \ + SMC_outb(__val16, a, __reg); \ + SMC_outb(__val16 >> 8, a, __reg + (1 << SMC_IO_SHIFT)); \ + } while (0) + +#define SMC_inw_b(a, r) \ + ({ \ + unsigned int __val16; \ + unsigned int __reg = r; \ + __val16 = SMC_inb(a, __reg); \ + __val16 |= SMC_inb(a, __reg + (1 << SMC_IO_SHIFT)) << 8; \ + __val16; \ + }) + /* * Define your architecture specific bus configuration parameters here. */ @@ -55,10 +76,30 @@ #define SMC_IO_SHIFT (lp->io_shift) #define SMC_inb(a, r) readb((a) + (r)) -#define SMC_inw(a, r) readw((a) + (r)) +#define SMC_inw(a, r) \ + ({ \ + unsigned int __smc_r = r; \ + SMC_16BIT(lp) ? readw((a) + __smc_r) : \ + SMC_8BIT(lp) ? SMC_inw_b(a, __smc_r) : \ + ({ BUG(); 0; }); \ + }) + #define SMC_inl(a, r) readl((a) + (r)) #define SMC_outb(v, a, r) writeb(v, (a) + (r)) +#define SMC_outw(v, a, r) \ + do { \ + unsigned int __v = v, __smc_r = r; \ + if (SMC_16BIT(lp)) \ + __SMC_outw(__v, a, __smc_r); \ + else if (SMC_8BIT(lp)) \ + SMC_outw_b(__v, a, __smc_r); \ + else \ + BUG(); \ + } while (0) + #define SMC_outl(v, a, r) writel(v, (a) + (r)) +#define SMC_insb(a, r, p, l) readsb((a) + (r), p, l) +#define SMC_outsb(a, r, p, l) writesb((a) + (r), p, l) #define SMC_insw(a, r, p, l) readsw((a) + (r), p, l) #define SMC_outsw(a, r, p, l) writesw((a) + (r), p, l) #define SMC_insl(a, r, p, l) readsl((a) + (r), p, l) @@ -66,7 +107,7 @@ #define SMC_IRQ_FLAGS (-1) /* from resource */ /* We actually can't write halfwords properly if not word aligned */ -static inline void SMC_outw(u16 val, void __iomem *ioaddr, int reg) +static inline void __SMC_outw(u16 val, void __iomem *ioaddr, int reg) { if ((machine_is_mainstone() || machine_is_stargate2() || machine_is_pxa_idp()) && reg & 2) { @@ -416,24 +457,8 @@ smc_pxa_dma_insw(void __iomem *ioaddr, struct smc_local *lp, int reg, int dma, #if ! SMC_CAN_USE_16BIT -/* - * Any 16-bit access is performed with two 8-bit accesses if the hardware - * can't do it directly. Most registers are 16-bit so those are mandatory. - */ -#define SMC_outw(x, ioaddr, reg) \ - do { \ - unsigned int __val16 = (x); \ - SMC_outb( __val16, ioaddr, reg ); \ - SMC_outb( __val16 >> 8, ioaddr, reg + (1 << SMC_IO_SHIFT));\ - } while (0) -#define SMC_inw(ioaddr, reg) \ - ({ \ - unsigned int __val16; \ - __val16 = SMC_inb( ioaddr, reg ); \ - __val16 |= SMC_inb( ioaddr, reg + (1 << SMC_IO_SHIFT)) << 8; \ - __val16; \ - }) - +#define SMC_outw(x, ioaddr, reg) SMC_outw_b(x, ioaddr, reg) +#define SMC_inw(ioaddr, reg) SMC_inw_b(ioaddr, reg) #define SMC_insw(a, r, p, l) BUG() #define SMC_outsw(a, r, p, l) BUG() diff --git a/include/linux/smc91x.h b/include/linux/smc91x.h index 76199b75d584..e302c447e057 100644 --- a/include/linux/smc91x.h +++ b/include/linux/smc91x.h @@ -1,6 +1,16 @@ #ifndef __SMC91X_H__ #define __SMC91X_H__ +/* + * These bits define which access sizes a platform can support, rather + * than the maximal access size. So, if your platform can do 16-bit + * and 32-bit accesses to the SMC91x device, but not 8-bit, set both + * SMC91X_USE_16BIT and SMC91X_USE_32BIT. + * + * The SMC91x driver requires at least one of SMC91X_USE_8BIT or + * SMC91X_USE_16BIT to be supported - just setting SMC91X_USE_32BIT is + * an invalid configuration. + */ #define SMC91X_USE_8BIT (1 << 0) #define SMC91X_USE_16BIT (1 << 1) #define SMC91X_USE_32BIT (1 << 2) From b99b43bb4bdf1d361f7487cf03d803082bbf9101 Mon Sep 17 00:00:00 2001 From: Owen Lin Date: Fri, 26 Aug 2016 13:49:09 +0800 Subject: [PATCH 449/531] Add Killer E2500 device ID in alx driver. Signed-off-by: David S. Miller --- drivers/net/ethernet/atheros/alx/main.c | 2 ++ drivers/net/ethernet/atheros/alx/reg.h | 1 + 2 files changed, 3 insertions(+) diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index 6453148d066a..4eb17daefc4f 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -1545,6 +1545,8 @@ static const struct pci_device_id alx_pci_tbl[] = { .driver_data = ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG }, { PCI_VDEVICE(ATTANSIC, ALX_DEV_ID_E2400), .driver_data = ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG }, + { PCI_VDEVICE(ATTANSIC, ALX_DEV_ID_E2500), + .driver_data = ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG }, { PCI_VDEVICE(ATTANSIC, ALX_DEV_ID_AR8162), .driver_data = ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG }, { PCI_VDEVICE(ATTANSIC, ALX_DEV_ID_AR8171) }, diff --git a/drivers/net/ethernet/atheros/alx/reg.h b/drivers/net/ethernet/atheros/alx/reg.h index 0959e6824cb6..1fc2d852249f 100644 --- a/drivers/net/ethernet/atheros/alx/reg.h +++ b/drivers/net/ethernet/atheros/alx/reg.h @@ -38,6 +38,7 @@ #define ALX_DEV_ID_AR8161 0x1091 #define ALX_DEV_ID_E2200 0xe091 #define ALX_DEV_ID_E2400 0xe0a1 +#define ALX_DEV_ID_E2500 0xe0b1 #define ALX_DEV_ID_AR8162 0x1090 #define ALX_DEV_ID_AR8171 0x10A1 #define ALX_DEV_ID_AR8172 0x10A0 From f48d1496b8537d75776478c6942dd87f34d7f270 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Mon, 15 Aug 2016 18:25:17 -0400 Subject: [PATCH 450/531] platform/olpc: Make ec explicitly non-modular The Kconfig entry controlling compilation of this code is: arch/x86/Kconfig:config OLPC arch/x86/Kconfig: bool "One Laptop Per Child support" ...meaning that it currently is not being built as a module by anyone. Lets remove the couple traces of modular infrastructure use, so that when reading the driver there is no doubt it is builtin-only. We delete the MODULE_LICENSE tag etc. since all that information was (or is now) contained at the top of the file in the comments. Cc: platform-driver-x86@vger.kernel.org Signed-off-by: Paul Gortmaker Acked-by: Andres Salomon Signed-off-by: Darren Hart --- drivers/platform/olpc/olpc-ec.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/platform/olpc/olpc-ec.c b/drivers/platform/olpc/olpc-ec.c index f99b183d5296..374a8028fec7 100644 --- a/drivers/platform/olpc/olpc-ec.c +++ b/drivers/platform/olpc/olpc-ec.c @@ -1,6 +1,8 @@ /* * Generic driver for the OLPC Embedded Controller. * + * Author: Andres Salomon + * * Copyright (C) 2011-2012 One Laptop per Child Foundation. * * Licensed under the GPL v2 or later. @@ -12,7 +14,7 @@ #include #include #include -#include +#include #include #include #include @@ -326,8 +328,4 @@ static int __init olpc_ec_init_module(void) { return platform_driver_register(&olpc_ec_plat_driver); } - arch_initcall(olpc_ec_init_module); - -MODULE_AUTHOR("Andres Salomon "); -MODULE_LICENSE("GPL"); From da43bf0c21e57fff0221da5de0a9a388ec0d27cd Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Mon, 15 Aug 2016 18:24:59 -0400 Subject: [PATCH 451/531] intel_pmic_gpio: Make explicitly non-modular The Kconfig entry controlling compilation of this code is: drivers/platform/x86/Kconfig:config GPIO_INTEL_PMIC drivers/platform/x86/Kconfig: bool "Intel PMIC GPIO support" ...meaning that it currently is not being built as a module by anyone. Lets remove the couple traces of modular infrastructure use, so that when reading the driver there is no doubt it is builtin-only. We delete the MODULE_LICENSE tag etc. since all that information was (or is now) contained at the top of the file in the comments. We don't replace module.h with init.h since the file already has that. Cc: Alek Du Cc: platform-driver-x86@vger.kernel.org Signed-off-by: Paul Gortmaker Signed-off-by: Darren Hart --- drivers/platform/x86/intel_pmic_gpio.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/platform/x86/intel_pmic_gpio.c b/drivers/platform/x86/intel_pmic_gpio.c index 63b371d6ee55..91ae58510d92 100644 --- a/drivers/platform/x86/intel_pmic_gpio.c +++ b/drivers/platform/x86/intel_pmic_gpio.c @@ -1,6 +1,8 @@ /* Moorestown PMIC GPIO (access through IPC) driver * Copyright (c) 2008 - 2009, Intel Corporation. * + * Author: Alek Du + * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. @@ -21,7 +23,6 @@ #define pr_fmt(fmt) "%s: " fmt, __func__ -#include #include #include #include @@ -322,9 +323,4 @@ static int __init platform_pmic_gpio_init(void) { return platform_driver_register(&platform_pmic_gpio_driver); } - subsys_initcall(platform_pmic_gpio_init); - -MODULE_AUTHOR("Alek Du "); -MODULE_DESCRIPTION("Intel Moorestown PMIC GPIO driver"); -MODULE_LICENSE("GPL v2"); From 98744b408c757901df57fa50cbd5826245dc3a1f Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Mon, 29 Aug 2016 08:44:03 +0200 Subject: [PATCH 452/531] clocksource/drivers/atmel-pit: Fix compilation error MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The previous fix introduced a check against the ret variable which is not defined, hence producing a compilation error: linux/drivers/clocksource/timer-atmel-pit.c: In function ‘at91sam926x_pit_dt_init’: linux/drivers/clocksource/timer-atmel-pit.c:264:2: error: ‘ret’ undeclared (first use in this function) ret = clk_prepare_enable(data->mck); ^ linux/drivers/clocksource/timer-atmel-pit.c:264:2: note: each undeclared identifier is reported only once for each function it appears in Add the missing the variable 'ret'. Fixes: 504f34c9e45c "clocksource/drivers/atmel-pit: Convert init function to return error" Signed-off-by: Daniel Lezcano Cc: alexandre.belloni@free-electrons.com Cc: motobud@gmail.com Cc: realbright@lgcns.com Link: http://lkml.kernel.org/r/1472453043-24287-1-git-send-email-daniel.lezcano@linaro.org Signed-off-by: Thomas Gleixner --- drivers/clocksource/timer-atmel-pit.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/clocksource/timer-atmel-pit.c b/drivers/clocksource/timer-atmel-pit.c index 3494bc5a21d5..7f0f5b26d8c5 100644 --- a/drivers/clocksource/timer-atmel-pit.c +++ b/drivers/clocksource/timer-atmel-pit.c @@ -240,6 +240,7 @@ static int __init at91sam926x_pit_common_init(struct pit_data *data) static int __init at91sam926x_pit_dt_init(struct device_node *node) { struct pit_data *data; + int ret; data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) From 3c3292634fc2de1ab97b6aa3222fee647f737adb Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Mon, 29 Aug 2016 13:18:23 +0200 Subject: [PATCH 453/531] hwmon: (it87) Add missing sysfs attribute group terminator Attribute array it87_attributes_in lacks its NULL terminator, causing random behavior when operating on the attribute group. Fixes: 52929715634a ("hwmon: (it87) Use is_visible for voltage sensors") Signed-off-by: Jean Delvare Cc: Martin Blumenstingl Cc: Guenter Roeck Cc: stable@vger.kernel.org Signed-off-by: Guenter Roeck --- drivers/hwmon/it87.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/hwmon/it87.c b/drivers/hwmon/it87.c index d0203a115eff..4667012b46b7 100644 --- a/drivers/hwmon/it87.c +++ b/drivers/hwmon/it87.c @@ -2015,6 +2015,7 @@ static struct attribute *it87_attributes_in[] = { &sensor_dev_attr_in10_input.dev_attr.attr, /* 41 */ &sensor_dev_attr_in11_input.dev_attr.attr, /* 41 */ &sensor_dev_attr_in12_input.dev_attr.attr, /* 41 */ + NULL }; static const struct attribute_group it87_group_in = { From c6c1f9bc798bee7cfc2e172cd2c9b48187d801a7 Mon Sep 17 00:00:00 2001 From: Liu Ying Date: Mon, 15 Aug 2016 16:41:13 +0800 Subject: [PATCH 454/531] drm/imx: Add active plane reconfiguration support We don't support configuring active plane on-the-fly for imx-drm. The relevant CRTC should be disabled before the plane configuration. Of course, the plane itself should be disabled as well. This patch adds active plane reconfiguration support by forcing CRTC mode change and disabling-enabling plane in plane's ->atomic_update callback. Suggested-by: Daniel Vetter Cc: Philipp Zabel Cc: David Airlie Cc: Russell King Cc: Daniel Vetter Cc: Peter Senna Tschudin Signed-off-by: Liu Ying Tested-by: Peter Senna Tschudin Tested-by: Lucas Stach Signed-off-by: Philipp Zabel --- drivers/gpu/drm/imx/imx-drm-core.c | 26 +++++++++++++++++++++++++- drivers/gpu/drm/imx/ipuv3-plane.c | 21 ++++++++++++++------- 2 files changed, 39 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c index 9f7dafce3a4c..7bf90e9e6139 100644 --- a/drivers/gpu/drm/imx/imx-drm-core.c +++ b/drivers/gpu/drm/imx/imx-drm-core.c @@ -171,10 +171,34 @@ static void imx_drm_output_poll_changed(struct drm_device *drm) drm_fbdev_cma_hotplug_event(imxdrm->fbhelper); } +static int imx_drm_atomic_check(struct drm_device *dev, + struct drm_atomic_state *state) +{ + int ret; + + ret = drm_atomic_helper_check_modeset(dev, state); + if (ret) + return ret; + + ret = drm_atomic_helper_check_planes(dev, state); + if (ret) + return ret; + + /* + * Check modeset again in case crtc_state->mode_changed is + * updated in plane's ->atomic_check callback. + */ + ret = drm_atomic_helper_check_modeset(dev, state); + if (ret) + return ret; + + return ret; +} + static const struct drm_mode_config_funcs imx_drm_mode_config_funcs = { .fb_create = drm_fb_cma_create, .output_poll_changed = imx_drm_output_poll_changed, - .atomic_check = drm_atomic_helper_check, + .atomic_check = imx_drm_atomic_check, .atomic_commit = drm_atomic_helper_commit, }; diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c index 4ad67d015ec7..29423e757d36 100644 --- a/drivers/gpu/drm/imx/ipuv3-plane.c +++ b/drivers/gpu/drm/imx/ipuv3-plane.c @@ -319,13 +319,14 @@ static int ipu_plane_atomic_check(struct drm_plane *plane, return -EINVAL; /* - * since we cannot touch active IDMAC channels, we do not support - * resizing the enabled plane or changing its format + * We support resizing active plane or changing its format by + * forcing CRTC mode change and disabling-enabling plane in plane's + * ->atomic_update callback. */ if (old_fb && (state->src_w != old_state->src_w || state->src_h != old_state->src_h || fb->pixel_format != old_fb->pixel_format)) - return -EINVAL; + crtc_state->mode_changed = true; eba = drm_plane_state_to_eba(state); @@ -336,7 +337,7 @@ static int ipu_plane_atomic_check(struct drm_plane *plane, return -EINVAL; if (old_fb && fb->pitches[0] != old_fb->pitches[0]) - return -EINVAL; + crtc_state->mode_changed = true; switch (fb->pixel_format) { case DRM_FORMAT_YUV420: @@ -372,7 +373,7 @@ static int ipu_plane_atomic_check(struct drm_plane *plane, return -EINVAL; if (old_fb && old_fb->pitches[1] != fb->pitches[1]) - return -EINVAL; + crtc_state->mode_changed = true; } return 0; @@ -392,8 +393,14 @@ static void ipu_plane_atomic_update(struct drm_plane *plane, enum ipu_color_space ics; if (old_state->fb) { - ipu_plane_atomic_set_base(ipu_plane, old_state); - return; + struct drm_crtc_state *crtc_state = state->crtc->state; + + if (!crtc_state->mode_changed) { + ipu_plane_atomic_set_base(ipu_plane, old_state); + return; + } + + ipu_disable_plane(plane); } switch (ipu_plane->dp_flow) { From 3dc147359e3dcdf0648f1e2c11f62cfae3160df0 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 29 Aug 2016 15:12:54 -0400 Subject: [PATCH 455/531] pNFS/flexfiles: Fix an Oopsable condition when connection to the DS fails If the attempt to connect to a DS fails inside ff_layout_pg_init_read or ff_layout_pg_init_write, then we currently end up clearing the layout segment carried by the struct nfs_pageio_descriptor, causing an Oops when we later call into ff_layout_read_pagelist/ff_layout_write_pagelist. The fix is to ensure we return the layout and then retry. Fixes: 446ca2195303 ("pNFS/flexfiles: When initing reads or writes, we...") Cc: stable@vger.kernel.org # v4.7+ Signed-off-by: Trond Myklebust --- fs/nfs/flexfilelayout/flexfilelayout.c | 37 +++++++++++------------ fs/nfs/flexfilelayout/flexfilelayoutdev.c | 19 ++++++------ 2 files changed, 28 insertions(+), 28 deletions(-) diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index ee1c94c7614c..51b51369704c 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -806,11 +806,14 @@ ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg, { struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg); struct nfs4_pnfs_ds *ds; + bool fail_return = false; int idx; /* mirrors are sorted by efficiency */ for (idx = start_idx; idx < fls->mirror_array_cnt; idx++) { - ds = nfs4_ff_layout_prepare_ds(lseg, idx, false); + if (idx+1 == fls->mirror_array_cnt) + fail_return = true; + ds = nfs4_ff_layout_prepare_ds(lseg, idx, fail_return); if (ds) { *best_idx = idx; return ds; @@ -859,6 +862,7 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs4_pnfs_ds *ds; int ds_idx; +retry: /* Use full layout for now */ if (!pgio->pg_lseg) ff_layout_pg_get_read(pgio, req, false); @@ -871,10 +875,13 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio, ds = ff_layout_choose_best_ds_for_read(pgio->pg_lseg, 0, &ds_idx); if (!ds) { - if (ff_layout_no_fallback_to_mds(pgio->pg_lseg)) - goto out_pnfs; - else + if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg)) goto out_mds; + pnfs_put_lseg(pgio->pg_lseg); + pgio->pg_lseg = NULL; + /* Sleep for 1 second before retrying */ + ssleep(1); + goto retry; } mirror = FF_LAYOUT_COMP(pgio->pg_lseg, ds_idx); @@ -890,12 +897,6 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio, pnfs_put_lseg(pgio->pg_lseg); pgio->pg_lseg = NULL; nfs_pageio_reset_read_mds(pgio); - return; - -out_pnfs: - pnfs_set_lo_fail(pgio->pg_lseg); - pnfs_put_lseg(pgio->pg_lseg); - pgio->pg_lseg = NULL; } static void @@ -909,6 +910,7 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio, int i; int status; +retry: if (!pgio->pg_lseg) { pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, req->wb_context, @@ -940,10 +942,13 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio, for (i = 0; i < pgio->pg_mirror_count; i++) { ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, i, true); if (!ds) { - if (ff_layout_no_fallback_to_mds(pgio->pg_lseg)) - goto out_pnfs; - else + if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg)) goto out_mds; + pnfs_put_lseg(pgio->pg_lseg); + pgio->pg_lseg = NULL; + /* Sleep for 1 second before retrying */ + ssleep(1); + goto retry; } pgm = &pgio->pg_mirrors[i]; mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i); @@ -956,12 +961,6 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio, pnfs_put_lseg(pgio->pg_lseg); pgio->pg_lseg = NULL; nfs_pageio_reset_write_mds(pgio); - return; - -out_pnfs: - pnfs_set_lo_fail(pgio->pg_lseg); - pnfs_put_lseg(pgio->pg_lseg); - pgio->pg_lseg = NULL; } static unsigned int diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index 970efba05ae1..f7a3f6b05369 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -379,7 +379,7 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx, devid = &mirror->mirror_ds->id_node; if (ff_layout_test_devid_unavailable(devid)) - goto out; + goto out_fail; ds = mirror->mirror_ds->ds; /* matching smp_wmb() in _nfs4_pnfs_v3/4_ds_connect */ @@ -405,15 +405,16 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx, mirror->mirror_ds->ds_versions[0].rsize = max_payload; if (mirror->mirror_ds->ds_versions[0].wsize > max_payload) mirror->mirror_ds->ds_versions[0].wsize = max_payload; - } else { - ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout), - mirror, lseg->pls_range.offset, - lseg->pls_range.length, NFS4ERR_NXIO, - OP_ILLEGAL, GFP_NOIO); - if (fail_return || !ff_layout_has_available_ds(lseg)) - pnfs_error_mark_layout_for_return(ino, lseg); - ds = NULL; + goto out; } + ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout), + mirror, lseg->pls_range.offset, + lseg->pls_range.length, NFS4ERR_NXIO, + OP_ILLEGAL, GFP_NOIO); +out_fail: + if (fail_return || !ff_layout_has_available_ds(lseg)) + pnfs_error_mark_layout_for_return(ino, lseg); + ds = NULL; out: return ds; } From ea78d80866ce375defb2fdd1c8a3aafec95e0f85 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Aug 2016 13:51:39 +1000 Subject: [PATCH 456/531] xfs: track log done items directly in the deferred pending work item Christoph reports slab corruption when a deferred refcount update aborts during _defer_finish(). The cause of this was broken log item state tracking in xfs_defer_pending -- upon an abort, _defer_trans_abort() will call abort_intent on all intent items, including the ones that have already had a done item attached. This is incorrect because each intent item has 2 refcount: the first is released when the intent item is committed to the log; and the second is released when the _done_ item is committed to the log, or by the intent creator if there is no done item. In other words, once we log the done item, responsibility for releasing the intent item's second refcount is transferred to the done item and /must not/ be performed by anything else. The dfp_committed flag should have been tracking whether or not we had a done item so that _defer_trans_abort could decide if it needs to abort the intent item, but due to a thinko this was not the case. Rip it out and track the done item directly so that we do the right thing w.r.t. intent item freeing. Signed-off-by: Darrick J. Wong Reported-by: Christoph Hellwig Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_defer.c | 17 ++++------------- fs/xfs/libxfs/xfs_defer.h | 2 +- fs/xfs/xfs_trace.h | 2 +- 3 files changed, 6 insertions(+), 15 deletions(-) diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c index 054a2032fdb3..c221d0ecd52e 100644 --- a/fs/xfs/libxfs/xfs_defer.c +++ b/fs/xfs/libxfs/xfs_defer.c @@ -194,7 +194,7 @@ xfs_defer_trans_abort( /* Abort intent items. */ list_for_each_entry(dfp, &dop->dop_pending, dfp_list) { trace_xfs_defer_pending_abort(tp->t_mountp, dfp); - if (dfp->dfp_committed) + if (!dfp->dfp_done) dfp->dfp_type->abort_intent(dfp->dfp_intent); } @@ -290,7 +290,6 @@ xfs_defer_finish( struct xfs_defer_pending *dfp; struct list_head *li; struct list_head *n; - void *done_item = NULL; void *state; int error = 0; void (*cleanup_fn)(struct xfs_trans *, void *, int); @@ -309,19 +308,11 @@ xfs_defer_finish( if (error) goto out; - /* Mark all pending intents as committed. */ - list_for_each_entry_reverse(dfp, &dop->dop_pending, dfp_list) { - if (dfp->dfp_committed) - break; - trace_xfs_defer_pending_commit((*tp)->t_mountp, dfp); - dfp->dfp_committed = true; - } - /* Log an intent-done item for the first pending item. */ dfp = list_first_entry(&dop->dop_pending, struct xfs_defer_pending, dfp_list); trace_xfs_defer_pending_finish((*tp)->t_mountp, dfp); - done_item = dfp->dfp_type->create_done(*tp, dfp->dfp_intent, + dfp->dfp_done = dfp->dfp_type->create_done(*tp, dfp->dfp_intent, dfp->dfp_count); cleanup_fn = dfp->dfp_type->finish_cleanup; @@ -331,7 +322,7 @@ xfs_defer_finish( list_del(li); dfp->dfp_count--; error = dfp->dfp_type->finish_item(*tp, dop, li, - done_item, &state); + dfp->dfp_done, &state); if (error) { /* * Clean up after ourselves and jump out. @@ -428,8 +419,8 @@ xfs_defer_add( dfp = kmem_alloc(sizeof(struct xfs_defer_pending), KM_SLEEP | KM_NOFS); dfp->dfp_type = defer_op_types[type]; - dfp->dfp_committed = false; dfp->dfp_intent = NULL; + dfp->dfp_done = NULL; dfp->dfp_count = 0; INIT_LIST_HEAD(&dfp->dfp_work); list_add_tail(&dfp->dfp_list, &dop->dop_intake); diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h index cc3981c48296..e96533d178cf 100644 --- a/fs/xfs/libxfs/xfs_defer.h +++ b/fs/xfs/libxfs/xfs_defer.h @@ -30,8 +30,8 @@ struct xfs_defer_op_type; struct xfs_defer_pending { const struct xfs_defer_op_type *dfp_type; /* function pointers */ struct list_head dfp_list; /* pending items */ - bool dfp_committed; /* committed trans? */ void *dfp_intent; /* log intent item */ + void *dfp_done; /* log done item */ struct list_head dfp_work; /* work items */ unsigned int dfp_count; /* # extent items */ }; diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 7e88bec3f359..d303a665dba9 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -2295,7 +2295,7 @@ DECLARE_EVENT_CLASS(xfs_defer_pending_class, __entry->dev = mp ? mp->m_super->s_dev : 0; __entry->type = dfp->dfp_type->type; __entry->intent = dfp->dfp_intent; - __entry->committed = dfp->dfp_committed; + __entry->committed = dfp->dfp_done != NULL; __entry->nr = dfp->dfp_count; ), TP_printk("dev %d:%d optype %d intent %p committed %d nr %d\n", From a474478642d57641ea06645104a15acc0420f01a Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Mon, 29 Aug 2016 17:51:24 +0200 Subject: [PATCH 457/531] drm/imx: fix crtc vblank state regression The atomic conversion lost the notification to let the DRM core know about the current state of the CRTC vblank interrupts. This regressed the ability of the core to reject page flip attempts on currently disabled CRTCs. Add back the notifications. Signed-off-by: Lucas Stach Signed-off-by: Philipp Zabel --- drivers/gpu/drm/imx/ipuv3-crtc.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c index 08e188bc10fc..462056e4b9e4 100644 --- a/drivers/gpu/drm/imx/ipuv3-crtc.c +++ b/drivers/gpu/drm/imx/ipuv3-crtc.c @@ -76,6 +76,8 @@ static void ipu_crtc_disable(struct drm_crtc *crtc) crtc->state->event = NULL; } spin_unlock_irq(&crtc->dev->event_lock); + + drm_crtc_vblank_off(crtc); } static void imx_drm_crtc_reset(struct drm_crtc *crtc) @@ -175,6 +177,8 @@ static int ipu_crtc_atomic_check(struct drm_crtc *crtc, static void ipu_crtc_atomic_begin(struct drm_crtc *crtc, struct drm_crtc_state *old_crtc_state) { + drm_crtc_vblank_on(crtc); + spin_lock_irq(&crtc->dev->event_lock); if (crtc->state->event) { WARN_ON(drm_crtc_vblank_get(crtc)); From 2c5575401e34de3d2fc90af1c95bc73435784093 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Fri, 26 Aug 2016 16:28:39 -0500 Subject: [PATCH 458/531] usb: musb: Fix locking errors for host only mode If we have USB gadgets disabled and USB_MUSB_HOST set, we get errors "possible irq lock inverssion dependency detected" errors during boot. Let's fix the issue by adding start_musb flag and start the controller after we're out of the spinlock protected section. Reported-by: Ladislav Michl Tested-by: Ladislav Michl Signed-off-by: Tony Lindgren Signed-off-by: Bin Liu Signed-off-by: Greg Kroah-Hartman --- drivers/usb/musb/musb_virthub.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/usb/musb/musb_virthub.c b/drivers/usb/musb/musb_virthub.c index 192248f974ec..fe08e776fec3 100644 --- a/drivers/usb/musb/musb_virthub.c +++ b/drivers/usb/musb/musb_virthub.c @@ -290,6 +290,7 @@ int musb_hub_control( u32 temp; int retval = 0; unsigned long flags; + bool start_musb = false; spin_lock_irqsave(&musb->lock, flags); @@ -390,7 +391,7 @@ int musb_hub_control( * logic relating to VBUS power-up. */ if (!hcd->self.is_b_host && musb_has_gadget(musb)) - musb_start(musb); + start_musb = true; break; case USB_PORT_FEAT_RESET: musb_port_reset(musb, true); @@ -451,5 +452,9 @@ int musb_hub_control( retval = -EPIPE; } spin_unlock_irqrestore(&musb->lock, flags); + + if (start_musb) + musb_start(musb); + return retval; } From 8c57cac1457f3125a5d13dc03635c0708c61bff0 Mon Sep 17 00:00:00 2001 From: Tomas Winkler Date: Wed, 20 Jul 2016 10:24:02 +0300 Subject: [PATCH 459/531] mei: me: disable driver on SPT SPS firmware Sunrise Point PCH with SPS Firmware doesn't expose working MEI interface, we need to quirk it out. The SPS Firmware is identifiable only on the first PCI function of the device. Cc: #4.6+ Tested-by: Sujith Pandel Signed-off-by: Tomas Winkler Signed-off-by: Greg Kroah-Hartman --- drivers/misc/mei/hw-me.c | 10 ++++++++-- drivers/misc/mei/pci-me.c | 4 ++-- 2 files changed, 10 insertions(+), 4 deletions(-) diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c index e2fb44cc5c37..dc3a854e02d3 100644 --- a/drivers/misc/mei/hw-me.c +++ b/drivers/misc/mei/hw-me.c @@ -1263,8 +1263,14 @@ static bool mei_me_fw_type_nm(struct pci_dev *pdev) static bool mei_me_fw_type_sps(struct pci_dev *pdev) { u32 reg; - /* Read ME FW Status check for SPS Firmware */ - pci_read_config_dword(pdev, PCI_CFG_HFS_1, ®); + unsigned int devfn; + + /* + * Read ME FW Status register to check for SPS Firmware + * The SPS FW is only signaled in pci function 0 + */ + devfn = PCI_DEVFN(PCI_SLOT(pdev->devfn), 0); + pci_bus_read_config_dword(pdev->bus, devfn, PCI_CFG_HFS_1, ®); trace_mei_pci_cfg_read(&pdev->dev, "PCI_CFG_HFS_1", PCI_CFG_HFS_1, reg); /* if bits [19:16] = 15, running SPS Firmware */ return (reg & 0xf0000) == 0xf0000; diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index 64e64da6da44..71cea9b296b2 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -85,8 +85,8 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_SPT, mei_me_pch8_cfg)}, {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_2, mei_me_pch8_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H, mei_me_pch8_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H_2, mei_me_pch8_cfg)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H, mei_me_pch8_sps_cfg)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H_2, mei_me_pch8_sps_cfg)}, {MEI_PCI_DEVICE(MEI_DEV_ID_BXT_M, mei_me_pch8_cfg)}, {MEI_PCI_DEVICE(MEI_DEV_ID_APL_I, mei_me_pch8_cfg)}, From 52442f9b11b7e5d4a38d99143011831fd171f8d9 Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Tue, 30 Aug 2016 09:20:32 -0400 Subject: [PATCH 460/531] NFS4: Avoid migration loops If a server returns itself as a location while migrating, the client may end up getting stuck attempting to migrate twice to the same server. Catch this by checking if the nfs_client found is the same as the existing client. For the other two callers to nfs4_set_client, the nfs_client will always be ERR_PTR(-EINVAL). Signed-off-by: Benjamin Coddington Signed-off-by: Trond Myklebust --- fs/nfs/nfs4client.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 8d7d08d4f95f..cd3b7cfdde16 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -817,6 +817,11 @@ static int nfs4_set_client(struct nfs_server *server, goto error; } + if (server->nfs_client == clp) { + error = -ELOOP; + goto error; + } + /* * Query for the lease time on clientid setup or renewal * From 98b0f80c2396224bbbed81792b526e6c72ba9efa Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 29 Aug 2016 11:15:36 -0400 Subject: [PATCH 461/531] NFSv4.x: Fix a refcount leak in nfs_callback_up_net On error, the callers expect us to return without bumping nn->cb_users[]. Signed-off-by: Trond Myklebust Cc: stable@vger.kernel.org # v3.7+ --- fs/nfs/callback.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index a7f2e6e33305..52a28311e2a4 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -275,6 +275,7 @@ static int nfs_callback_up_net(int minorversion, struct svc_serv *serv, err_socks: svc_rpcb_cleanup(serv, net); err_bind: + nn->cb_users[minorversion]--; dprintk("NFS: Couldn't create callback socket: err = %d; " "net = %p\n", ret, net); return ret; From 9ebae9e4bcd7dff22536af8a969d8f66e6f23900 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Tue, 30 Aug 2016 16:47:02 +0100 Subject: [PATCH 462/531] pata_ninja32: Avoid corrupting status flags Ninja32 needs to set some flags to indicate it does 32bit IO. However it currently assigns this which loses the initializing flag and causes a warning spew. Fix it to use a logical or as is intended. Signed-off-by: Alan Cox Tested-by: Ellmar Stelnberger Signed-off-by: Tejun Heo --- drivers/ata/pata_ninja32.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ata/pata_ninja32.c b/drivers/ata/pata_ninja32.c index 633aa2934a18..44f97ad3c88d 100644 --- a/drivers/ata/pata_ninja32.c +++ b/drivers/ata/pata_ninja32.c @@ -144,7 +144,7 @@ static int ninja32_init_one(struct pci_dev *dev, const struct pci_device_id *id) ap->ioaddr.altstatus_addr = base + 0x1E; ap->ioaddr.bmdma_addr = base; ata_sff_std_ports(&ap->ioaddr); - ap->pflags = ATA_PFLAG_PIO32 | ATA_PFLAG_PIO32CHANGE; + ap->pflags |= ATA_PFLAG_PIO32 | ATA_PFLAG_PIO32CHANGE; ninja32_program(base); /* FIXME: Should we disable them at remove ? */ From 0d025d271e55f3de21f0aaaf54b42d20404d2b23 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 30 Aug 2016 08:04:16 -0500 Subject: [PATCH 463/531] mm/usercopy: get rid of CONFIG_DEBUG_STRICT_USER_COPY_CHECKS There are three usercopy warnings which are currently being silenced for gcc 4.6 and newer: 1) "copy_from_user() buffer size is too small" compile warning/error This is a static warning which happens when object size and copy size are both const, and copy size > object size. I didn't see any false positives for this one. So the function warning attribute seems to be working fine here. Note this scenario is always a bug and so I think it should be changed to *always* be an error, regardless of CONFIG_DEBUG_STRICT_USER_COPY_CHECKS. 2) "copy_from_user() buffer size is not provably correct" compile warning This is another static warning which happens when I enable __compiletime_object_size() for new compilers (and CONFIG_DEBUG_STRICT_USER_COPY_CHECKS). It happens when object size is const, but copy size is *not*. In this case there's no way to compare the two at build time, so it gives the warning. (Note the warning is a byproduct of the fact that gcc has no way of knowing whether the overflow function will be called, so the call isn't dead code and the warning attribute is activated.) So this warning seems to only indicate "this is an unusual pattern, maybe you should check it out" rather than "this is a bug". I get 102(!) of these warnings with allyesconfig and the __compiletime_object_size() gcc check removed. I don't know if there are any real bugs hiding in there, but from looking at a small sample, I didn't see any. According to Kees, it does sometimes find real bugs. But the false positive rate seems high. 3) "Buffer overflow detected" runtime warning This is a runtime warning where object size is const, and copy size > object size. All three warnings (both static and runtime) were completely disabled for gcc 4.6 with the following commit: 2fb0815c9ee6 ("gcc4: disable __compiletime_object_size for GCC 4.6+") That commit mistakenly assumed that the false positives were caused by a gcc bug in __compiletime_object_size(). But in fact, __compiletime_object_size() seems to be working fine. The false positives were instead triggered by #2 above. (Though I don't have an explanation for why the warnings supposedly only started showing up in gcc 4.6.) So remove warning #2 to get rid of all the false positives, and re-enable warnings #1 and #3 by reverting the above commit. Furthermore, since #1 is a real bug which is detected at compile time, upgrade it to always be an error. Having done all that, CONFIG_DEBUG_STRICT_USER_COPY_CHECKS is no longer needed. Signed-off-by: Josh Poimboeuf Cc: Kees Cook Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H . Peter Anvin" Cc: Andy Lutomirski Cc: Steven Rostedt Cc: Brian Gerst Cc: Peter Zijlstra Cc: Frederic Weisbecker Cc: Byungchul Park Cc: Nilay Vaish Signed-off-by: Linus Torvalds --- arch/parisc/Kconfig | 1 - arch/parisc/configs/c8000_defconfig | 1 - arch/parisc/configs/generic-64bit_defconfig | 1 - arch/parisc/include/asm/uaccess.h | 22 ++++--- arch/s390/Kconfig | 1 - arch/s390/configs/default_defconfig | 1 - arch/s390/configs/gcov_defconfig | 1 - arch/s390/configs/performance_defconfig | 1 - arch/s390/defconfig | 1 - arch/s390/include/asm/uaccess.h | 19 +++--- arch/tile/Kconfig | 1 - arch/tile/include/asm/uaccess.h | 22 +++---- arch/x86/Kconfig | 1 - arch/x86/include/asm/uaccess.h | 69 +++------------------ include/asm-generic/uaccess.h | 1 + include/linux/compiler-gcc.h | 2 +- lib/Kconfig.debug | 18 ------ lib/Makefile | 1 - lib/usercopy.c | 9 --- 19 files changed, 45 insertions(+), 128 deletions(-) delete mode 100644 lib/usercopy.c diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index cd8778103165..af12c2db9bb8 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -1,6 +1,5 @@ config PARISC def_bool y - select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select ARCH_MIGHT_HAVE_PC_PARPORT select HAVE_IDE select HAVE_OPROFILE diff --git a/arch/parisc/configs/c8000_defconfig b/arch/parisc/configs/c8000_defconfig index 1a8f6f95689e..f6a4c016304b 100644 --- a/arch/parisc/configs/c8000_defconfig +++ b/arch/parisc/configs/c8000_defconfig @@ -245,7 +245,6 @@ CONFIG_DEBUG_RT_MUTEXES=y CONFIG_PROVE_RCU_DELAY=y CONFIG_DEBUG_BLOCK_EXT_DEVT=y CONFIG_LATENCYTOP=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_KEYS=y # CONFIG_CRYPTO_HW is not set CONFIG_FONTS=y diff --git a/arch/parisc/configs/generic-64bit_defconfig b/arch/parisc/configs/generic-64bit_defconfig index 7e0792658952..c564e6e1fa23 100644 --- a/arch/parisc/configs/generic-64bit_defconfig +++ b/arch/parisc/configs/generic-64bit_defconfig @@ -291,7 +291,6 @@ CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y CONFIG_BOOTPARAM_HUNG_TASK_PANIC=y # CONFIG_SCHED_DEBUG is not set CONFIG_TIMER_STATS=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_ECB=m CONFIG_CRYPTO_PCBC=m diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h index 0f59fd9ca205..e9150487e20d 100644 --- a/arch/parisc/include/asm/uaccess.h +++ b/arch/parisc/include/asm/uaccess.h @@ -208,13 +208,13 @@ unsigned long copy_in_user(void __user *dst, const void __user *src, unsigned lo #define __copy_to_user_inatomic __copy_to_user #define __copy_from_user_inatomic __copy_from_user -extern void copy_from_user_overflow(void) -#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS - __compiletime_error("copy_from_user() buffer size is not provably correct") -#else - __compiletime_warning("copy_from_user() buffer size is not provably correct") -#endif -; +extern void __compiletime_error("usercopy buffer size is too small") +__bad_copy_user(void); + +static inline void copy_user_overflow(int size, unsigned long count) +{ + WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); +} static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, @@ -223,10 +223,12 @@ static inline unsigned long __must_check copy_from_user(void *to, int sz = __compiletime_object_size(to); int ret = -EFAULT; - if (likely(sz == -1 || !__builtin_constant_p(n) || sz >= n)) + if (likely(sz == -1 || sz >= n)) ret = __copy_from_user(to, from, n); - else - copy_from_user_overflow(); + else if (!__builtin_constant_p(n)) + copy_user_overflow(sz, n); + else + __bad_copy_user(); return ret; } diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index e751fe25d6ab..c109f073d454 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -68,7 +68,6 @@ config DEBUG_RODATA config S390 def_bool y select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE - select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_GCOV_PROFILE_ALL diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig index 26e0c7f08814..412b1bd21029 100644 --- a/arch/s390/configs/default_defconfig +++ b/arch/s390/configs/default_defconfig @@ -602,7 +602,6 @@ CONFIG_FAIL_FUTEX=y CONFIG_FAULT_INJECTION_DEBUG_FS=y CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y CONFIG_LATENCYTOP=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_IRQSOFF_TRACER=y CONFIG_PREEMPT_TRACER=y CONFIG_SCHED_TRACER=y diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig index 24879dab47bc..bec279eb4b93 100644 --- a/arch/s390/configs/gcov_defconfig +++ b/arch/s390/configs/gcov_defconfig @@ -552,7 +552,6 @@ CONFIG_NOTIFIER_ERROR_INJECTION=m CONFIG_CPU_NOTIFIER_ERROR_INJECT=m CONFIG_PM_NOTIFIER_ERROR_INJECT=m CONFIG_LATENCYTOP=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_BLK_DEV_IO_TRACE=y # CONFIG_KPROBE_EVENT is not set CONFIG_TRACE_ENUM_MAP_FILE=y diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig index a5c1e5f2a0ca..1751446a5bbb 100644 --- a/arch/s390/configs/performance_defconfig +++ b/arch/s390/configs/performance_defconfig @@ -549,7 +549,6 @@ CONFIG_TIMER_STATS=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=60 CONFIG_LATENCYTOP=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_STACK_TRACER=y diff --git a/arch/s390/defconfig b/arch/s390/defconfig index 73610f2e3b4f..2d40ef0a6295 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -172,7 +172,6 @@ CONFIG_DEBUG_NOTIFIERS=y CONFIG_RCU_CPU_STALL_TIMEOUT=60 CONFIG_RCU_TRACE=y CONFIG_LATENCYTOP=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index 9b49cf1daa8f..95aefdba4be2 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -311,6 +311,14 @@ int __get_user_bad(void) __attribute__((noreturn)); #define __put_user_unaligned __put_user #define __get_user_unaligned __get_user +extern void __compiletime_error("usercopy buffer size is too small") +__bad_copy_user(void); + +static inline void copy_user_overflow(int size, unsigned long count) +{ + WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); +} + /** * copy_to_user: - Copy a block of data into user space. * @to: Destination address, in user space. @@ -332,12 +340,6 @@ copy_to_user(void __user *to, const void *from, unsigned long n) return __copy_to_user(to, from, n); } -void copy_from_user_overflow(void) -#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS -__compiletime_warning("copy_from_user() buffer size is not provably correct") -#endif -; - /** * copy_from_user: - Copy a block of data from user space. * @to: Destination address, in kernel space. @@ -362,7 +364,10 @@ copy_from_user(void *to, const void __user *from, unsigned long n) might_fault(); if (unlikely(sz != -1 && sz < n)) { - copy_from_user_overflow(); + if (!__builtin_constant_p(n)) + copy_user_overflow(sz, n); + else + __bad_copy_user(); return n; } return __copy_from_user(to, from, n); diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig index 4820a02838ac..78da75b670bc 100644 --- a/arch/tile/Kconfig +++ b/arch/tile/Kconfig @@ -4,7 +4,6 @@ config TILE def_bool y select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE - select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_WANT_FRAME_POINTERS diff --git a/arch/tile/include/asm/uaccess.h b/arch/tile/include/asm/uaccess.h index 0a9c4265763b..a77369e91e54 100644 --- a/arch/tile/include/asm/uaccess.h +++ b/arch/tile/include/asm/uaccess.h @@ -416,14 +416,13 @@ _copy_from_user(void *to, const void __user *from, unsigned long n) return n; } -#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS -/* - * There are still unprovable places in the generic code as of 2.6.34, so this - * option is not really compatible with -Werror, which is more useful in - * general. - */ -extern void copy_from_user_overflow(void) - __compiletime_warning("copy_from_user() size is not provably correct"); +extern void __compiletime_error("usercopy buffer size is too small") +__bad_copy_user(void); + +static inline void copy_user_overflow(int size, unsigned long count) +{ + WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); +} static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, @@ -433,14 +432,13 @@ static inline unsigned long __must_check copy_from_user(void *to, if (likely(sz == -1 || sz >= n)) n = _copy_from_user(to, from, n); + else if (!__builtin_constant_p(n)) + copy_user_overflow(sz, n); else - copy_from_user_overflow(); + __bad_copy_user(); return n; } -#else -#define copy_from_user _copy_from_user -#endif #ifdef __tilegx__ /** diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index c580d8c33562..2a1f0ce7c59a 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -24,7 +24,6 @@ config X86 select ARCH_DISCARD_MEMBLOCK select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE - select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FAST_MULTIPLIER diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index a0ae610b9280..c3f291195294 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -697,43 +697,14 @@ unsigned long __must_check _copy_from_user(void *to, const void __user *from, unsigned long __must_check _copy_to_user(void __user *to, const void *from, unsigned n); -#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS -# define copy_user_diag __compiletime_error -#else -# define copy_user_diag __compiletime_warning -#endif +extern void __compiletime_error("usercopy buffer size is too small") +__bad_copy_user(void); -extern void copy_user_diag("copy_from_user() buffer size is too small") -copy_from_user_overflow(void); -extern void copy_user_diag("copy_to_user() buffer size is too small") -copy_to_user_overflow(void) __asm__("copy_from_user_overflow"); - -#undef copy_user_diag - -#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS - -extern void -__compiletime_warning("copy_from_user() buffer size is not provably correct") -__copy_from_user_overflow(void) __asm__("copy_from_user_overflow"); -#define __copy_from_user_overflow(size, count) __copy_from_user_overflow() - -extern void -__compiletime_warning("copy_to_user() buffer size is not provably correct") -__copy_to_user_overflow(void) __asm__("copy_from_user_overflow"); -#define __copy_to_user_overflow(size, count) __copy_to_user_overflow() - -#else - -static inline void -__copy_from_user_overflow(int size, unsigned long count) +static inline void copy_user_overflow(int size, unsigned long count) { WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); } -#define __copy_to_user_overflow __copy_from_user_overflow - -#endif - static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { @@ -743,31 +714,13 @@ copy_from_user(void *to, const void __user *from, unsigned long n) kasan_check_write(to, n); - /* - * While we would like to have the compiler do the checking for us - * even in the non-constant size case, any false positives there are - * a problem (especially when DEBUG_STRICT_USER_COPY_CHECKS, but even - * without - the [hopefully] dangerous looking nature of the warning - * would make people go look at the respecitive call sites over and - * over again just to find that there's no problem). - * - * And there are cases where it's just not realistic for the compiler - * to prove the count to be in range. For example when multiple call - * sites of a helper function - perhaps in different source files - - * all doing proper range checking, yet the helper function not doing - * so again. - * - * Therefore limit the compile time checking to the constant size - * case, and do only runtime checking for non-constant sizes. - */ - if (likely(sz < 0 || sz >= n)) { check_object_size(to, n, false); n = _copy_from_user(to, from, n); - } else if (__builtin_constant_p(n)) - copy_from_user_overflow(); + } else if (!__builtin_constant_p(n)) + copy_user_overflow(sz, n); else - __copy_from_user_overflow(sz, n); + __bad_copy_user(); return n; } @@ -781,21 +734,17 @@ copy_to_user(void __user *to, const void *from, unsigned long n) might_fault(); - /* See the comment in copy_from_user() above. */ if (likely(sz < 0 || sz >= n)) { check_object_size(from, n, true); n = _copy_to_user(to, from, n); - } else if (__builtin_constant_p(n)) - copy_to_user_overflow(); + } else if (!__builtin_constant_p(n)) + copy_user_overflow(sz, n); else - __copy_to_user_overflow(sz, n); + __bad_copy_user(); return n; } -#undef __copy_from_user_overflow -#undef __copy_to_user_overflow - /* * We rely on the nested NMI work to allow atomic faults from the NMI path; the * nested NMI paths are careful to preserve CR2. diff --git a/include/asm-generic/uaccess.h b/include/asm-generic/uaccess.h index 1bfa602958f2..5dea1fb6979c 100644 --- a/include/asm-generic/uaccess.h +++ b/include/asm-generic/uaccess.h @@ -72,6 +72,7 @@ struct exception_table_entry /* Returns 0 if exception not found and fixup otherwise. */ extern unsigned long search_exception_table(unsigned long); + /* * architectures with an MMU should override these two */ diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 8dbc8929a6a0..573c5a18908f 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -158,7 +158,7 @@ #define __compiler_offsetof(a, b) \ __builtin_offsetof(a, b) -#if GCC_VERSION >= 40100 && GCC_VERSION < 40600 +#if GCC_VERSION >= 40100 # define __compiletime_object_size(obj) __builtin_object_size(obj, 0) #endif diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 2307d7c89dac..2e2cca509231 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1686,24 +1686,6 @@ config LATENCYTOP Enable this option if you want to use the LatencyTOP tool to find out which userspace is blocking on what kernel operations. -config ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS - bool - -config DEBUG_STRICT_USER_COPY_CHECKS - bool "Strict user copy size checks" - depends on ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS - depends on DEBUG_KERNEL && !TRACE_BRANCH_PROFILING - help - Enabling this option turns a certain set of sanity checks for user - copy operations into compile time failures. - - The copy_from_user() etc checks are there to help test if there - are sufficient security checks on the length argument of - the copy operation, by having gcc prove that the argument is - within bounds. - - If unsure, say N. - source kernel/trace/Kconfig menu "Runtime Testing" diff --git a/lib/Makefile b/lib/Makefile index cfa68eb269e4..5dc77a8ec297 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -24,7 +24,6 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \ is_single_threaded.o plist.o decompress.o kobject_uevent.o \ earlycpio.o seq_buf.o nmi_backtrace.o nodemask.o -obj-$(CONFIG_ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS) += usercopy.o lib-$(CONFIG_MMU) += ioremap.o lib-$(CONFIG_SMP) += cpumask.o lib-$(CONFIG_HAS_DMA) += dma-noop.o diff --git a/lib/usercopy.c b/lib/usercopy.c deleted file mode 100644 index 4f5b1ddbcd25..000000000000 --- a/lib/usercopy.c +++ /dev/null @@ -1,9 +0,0 @@ -#include -#include -#include - -void copy_from_user_overflow(void) -{ - WARN(1, "Buffer overflow detected!\n"); -} -EXPORT_SYMBOL(copy_from_user_overflow); From a5d60783df61fbb67b7596b8a0f6b4b2e05251d5 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Tue, 30 Aug 2016 16:11:53 -0400 Subject: [PATCH 464/531] dm log writes: move IO accounting earlier to fix error path Move log_one_block()'s atomic_inc(&lc->io_blocks) before bio_alloc() to fix a bug that the target hangs if bio_alloc() fails. The error path does put_io_block(lc), so atomic_inc(&lc->io_blocks) must occur before invoking the error path to avoid underflow of lc->io_blocks. Signed-off-by: Mikulas Patocka Reviewed-by: Josef Bacik Signed-off-by: Mike Snitzer Cc: stable@vger.kernel.org --- drivers/md/dm-log-writes.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index 4ab68033f9d1..4cc78aef9007 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -259,12 +259,12 @@ static int log_one_block(struct log_writes_c *lc, goto out; sector++; + atomic_inc(&lc->io_blocks); bio = bio_alloc(GFP_KERNEL, block->vec_cnt); if (!bio) { DMERR("Couldn't alloc log bio"); goto error; } - atomic_inc(&lc->io_blocks); bio->bi_iter.bi_size = 0; bio->bi_iter.bi_sector = sector; bio->bi_bdev = lc->logdev->bdev; From 7efb367320f56fc4d549875b6f3a6940018ef2e5 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Tue, 30 Aug 2016 16:20:55 -0400 Subject: [PATCH 465/531] dm log writes: fix bug with too large bios bio_alloc() can allocate a bio with at most BIO_MAX_PAGES (256) vector entries. However, the incoming bio may have more vector entries if it was allocated by other means. For example, bcache submits bios with more than BIO_MAX_PAGES entries. This results in bio_alloc() failure. To avoid the failure, change the code so that it allocates bio with at most BIO_MAX_PAGES entries. If the incoming bio has more entries, bio_add_page() will fail and a new bio will be allocated - the code that handles bio_add_page() failure already exists in the dm-log-writes target. Signed-off-by: Mikulas Patocka Reviewed-by: Josef Bacik Signed-off-by: Mike Snitzer Cc: stable@vger.kernel.org # v4.1+ --- drivers/md/dm-log-writes.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index 4cc78aef9007..ba24f4f37efc 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -260,7 +260,7 @@ static int log_one_block(struct log_writes_c *lc, sector++; atomic_inc(&lc->io_blocks); - bio = bio_alloc(GFP_KERNEL, block->vec_cnt); + bio = bio_alloc(GFP_KERNEL, min(block->vec_cnt, BIO_MAX_PAGES)); if (!bio) { DMERR("Couldn't alloc log bio"); goto error; @@ -282,7 +282,7 @@ static int log_one_block(struct log_writes_c *lc, if (ret != block->vecs[i].bv_len) { atomic_inc(&lc->io_blocks); submit_bio(bio); - bio = bio_alloc(GFP_KERNEL, block->vec_cnt - i); + bio = bio_alloc(GFP_KERNEL, min(block->vec_cnt - i, BIO_MAX_PAGES)); if (!bio) { DMERR("Couldn't alloc log bio"); goto error; From 485a252a5559b45d7df04c819ec91177c62c270b Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 10 Aug 2016 16:28:09 -0700 Subject: [PATCH 466/531] seccomp: Fix tracer exit notifications during fatal signals This fixes a ptrace vs fatal pending signals bug as manifested in seccomp now that seccomp was reordered to happen after ptrace. The short version is that seccomp should not attempt to call do_exit() while fatal signals are pending under a tracer. The existing code was trying to be as defensively paranoid as possible, but it now ends up confusing ptrace. Instead, the syscall can just be skipped (which solves the original concern that the do_exit() was addressing) and normal signal handling, tracer notification, and process death can happen. Paraphrasing from the original bug report: If a tracee task is in a PTRACE_EVENT_SECCOMP trap, or has been resumed after such a trap but not yet been scheduled, and another task in the thread-group calls exit_group(), then the tracee task exits without the ptracer receiving a PTRACE_EVENT_EXIT notification. Test case here: https://gist.github.com/khuey/3c43ac247c72cef8c956ca73281c9be7 The bug happens because when __seccomp_filter() detects fatal_signal_pending(), it calls do_exit() without dequeuing the fatal signal. When do_exit() sends the PTRACE_EVENT_EXIT notification and that task is descheduled, __schedule() notices that there is a fatal signal pending and changes its state from TASK_TRACED to TASK_RUNNING. That prevents the ptracer's waitpid() from returning the ptrace event. A more detailed analysis is here: https://github.com/mozilla/rr/issues/1762#issuecomment-237396255. Reported-by: Robert O'Callahan Reported-by: Kyle Huey Tested-by: Kyle Huey Fixes: 93e35efb8de4 ("x86/ptrace: run seccomp after ptrace") Signed-off-by: Kees Cook Acked-by: Oleg Nesterov Acked-by: James Morris --- kernel/seccomp.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/kernel/seccomp.c b/kernel/seccomp.c index ef6c6c3f9d8a..0db7c8a2afe2 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -605,12 +605,16 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, ptrace_event(PTRACE_EVENT_SECCOMP, data); /* * The delivery of a fatal signal during event - * notification may silently skip tracer notification. - * Terminating the task now avoids executing a system - * call that may not be intended. + * notification may silently skip tracer notification, + * which could leave us with a potentially unmodified + * syscall that the tracer would have liked to have + * changed. Since the process is about to die, we just + * force the syscall to be skipped and let the signal + * kill the process and correctly handle any tracer exit + * notifications. */ if (fatal_signal_pending(current)) - do_exit(SIGSYS); + goto skip; /* Check if the tracer forced the syscall to be skipped. */ this_syscall = syscall_get_nr(current, task_pt_regs(current)); if (this_syscall < 0) From 91e630d9ae6de6f740ef7c8176736eb55366833e Mon Sep 17 00:00:00 2001 From: Vladimir Zapolskiy Date: Thu, 10 Mar 2016 01:22:19 +0200 Subject: [PATCH 467/531] dm log writes: fix check of kthread_run() return value The kthread_run() function returns either a valid task_struct or ERR_PTR() value, check for NULL is invalid. This change fixes potential for oops, e.g. in OOM situation. Signed-off-by: Vladimir Zapolskiy Signed-off-by: Mike Snitzer Cc: stable@vger.kernel.org --- drivers/md/dm-log-writes.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index ba24f4f37efc..49e4d8d4558f 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -459,9 +459,9 @@ static int log_writes_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad; } - ret = -EINVAL; lc->log_kthread = kthread_run(log_writes_kthread, lc, "log-write"); - if (!lc->log_kthread) { + if (IS_ERR(lc->log_kthread)) { + ret = PTR_ERR(lc->log_kthread); ti->error = "Couldn't alloc kthread"; dm_put_device(ti, lc->dev); dm_put_device(ti, lc->logdev); From 4e870e948fbabf62b78e8410f04c67703e7c816b Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Tue, 30 Aug 2016 16:38:42 -0400 Subject: [PATCH 468/531] dm crypt: fix error with too large bios When dm-crypt processes writes, it allocates a new bio in crypt_alloc_buffer(). The bio is allocated from a bio set and it can have at most BIO_MAX_PAGES vector entries, however the incoming bio can be larger (e.g. if it was allocated by bcache). If the incoming bio is larger, bio_alloc_bioset() fails and an error is returned. To avoid the error, we test for a too large bio in the function crypt_map() and use dm_accept_partial_bio() to split the bio. dm_accept_partial_bio() trims the current bio to the desired size and asks DM core to send another bio with the rest of the data. Signed-off-by: Mikulas Patocka Signed-off-by: Mike Snitzer Cc: stable@vger.kernel.org # v3.16+ --- drivers/md/dm-crypt.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index eedba67b0e3e..d609566c19b0 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1924,6 +1924,13 @@ static int crypt_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_REMAPPED; } + /* + * Check if bio is too large, split as needed. + */ + if (unlikely(bio->bi_iter.bi_size > (BIO_MAX_PAGES << PAGE_SHIFT)) && + bio_data_dir(bio) == WRITE) + dm_accept_partial_bio(bio, ((BIO_MAX_PAGES << PAGE_SHIFT) >> SECTOR_SHIFT)); + io = dm_per_bio_data(bio, cc->per_bio_data_size); crypt_io_init(io, cc, bio, dm_target_offset(ti, bio->bi_iter.bi_sector)); io->ctx.req = (struct skcipher_request *)(io + 1); From 5d0be84ec0cacfc7a6d6ea548afdd07d481324cd Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 30 Aug 2016 09:51:44 -0700 Subject: [PATCH 469/531] dm crypt: fix free of bad values after tfm allocation failure If crypt_alloc_tfms() had to allocate multiple tfms and it failed before the last allocation, then it would call crypt_free_tfms() and could free pointers from uninitialized memory -- due to the crypt_free_tfms() check for non-zero cc->tfms[i]. Fix by allocating zeroed memory. Signed-off-by: Eric Biggers Signed-off-by: Mike Snitzer Cc: stable@vger.kernel.org --- drivers/md/dm-crypt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index d609566c19b0..874295757caa 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1453,7 +1453,7 @@ static int crypt_alloc_tfms(struct crypt_config *cc, char *ciphermode) unsigned i; int err; - cc->tfms = kmalloc(cc->tfms_count * sizeof(struct crypto_skcipher *), + cc->tfms = kzalloc(cc->tfms_count * sizeof(struct crypto_skcipher *), GFP_KERNEL); if (!cc->tfms) return -ENOMEM; From edd1ea2a8a2549e4fe58e817d539445729491ecf Mon Sep 17 00:00:00 2001 From: Bhaktipriya Shridhar Date: Tue, 30 Aug 2016 22:19:11 +0530 Subject: [PATCH 470/531] dm bufio: remove use of deprecated create_singlethread_workqueue() The workqueue "dm_bufio_wq" queues a single work item &dm_bufio_work so it doesn't require execution ordering. Hence, alloc_workqueue() has been used to replace the deprecated create_singlethread_workqueue(). The WQ_MEM_RECLAIM flag has been set since DM requires forward progress under memory pressure. Since there are fixed number of work items, explicit concurrency limit is unnecessary here. Signed-off-by: Bhaktipriya Shridhar Signed-off-by: Mike Snitzer --- drivers/md/dm-bufio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 6571c81465e1..8625040bae92 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -1879,7 +1879,7 @@ static int __init dm_bufio_init(void) __cache_size_refresh(); mutex_unlock(&dm_bufio_clients_lock); - dm_bufio_wq = create_singlethread_workqueue("dm_bufio_cache"); + dm_bufio_wq = alloc_workqueue("dm_bufio_cache", WQ_MEM_RECLAIM, 0); if (!dm_bufio_wq) return -ENOMEM; From bd37e022e334757a5dc1dae41baa29e16befe4ec Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Sun, 21 Aug 2016 15:41:44 +0000 Subject: [PATCH 471/531] cpufreq: dt: Add terminate entry for of_device_id tables Make sure of_device_id tables are NULL terminated. Signed-off-by: Wei Yongjun Acked-by: Viresh Kumar Fixes: f56aad1d98f1 (cpufreq: dt: Add generic platform-device creation support) CC: 4.7+ # 4.7+ Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/cpufreq-dt-platdev.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c index 0bb44d5b5df4..2ee40fd360ca 100644 --- a/drivers/cpufreq/cpufreq-dt-platdev.c +++ b/drivers/cpufreq/cpufreq-dt-platdev.c @@ -74,6 +74,8 @@ static const struct of_device_id machines[] __initconst = { { .compatible = "ti,omap5", }, { .compatible = "xlnx,zynq-7000", }, + + { } }; static int __init cpufreq_dt_platdev_init(void) From d44c950e9398e639e124014e5872480a37b67259 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 26 Apr 2016 13:38:55 -0700 Subject: [PATCH 472/531] PM / runtime: Add _rcuidle suffix to allow rpm_resume() to be called from idle This commit applies another _rcuidle suffix to fix an RCU use from idle. > =============================== > [ INFO: suspicious RCU usage. ] > 4.6.0-rc5-next-20160426+ #1122 Not tainted > ------------------------------- > include/trace/events/rpm.h:69 suspicious rcu_dereference_check() usage! > > other info that might help us debug this: > > > RCU used illegally from idle CPU! > rcu_scheduler_active = 1, debug_locks = 0 > RCU used illegally from extended quiescent state! > 1 lock held by swapper/0/0: > #0: (&(&dev->power.lock)->rlock){-.-...}, at: [] __pm_runtime_resume+0x3c/0x64 > > stack backtrace: > CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.6.0-rc5-next-20160426+ #1122 > Hardware name: Generic OMAP36xx (Flattened Device Tree) > [] (unwind_backtrace) from [] (show_stack+0x10/0x14) > [] (show_stack) from [] (dump_stack+0xb0/0xe4) > [] (dump_stack) from [] (rpm_resume+0x5cc/0x7f4) > [] (rpm_resume) from [] (__pm_runtime_resume+0x4c/0x64) > [] (__pm_runtime_resume) from [] (omap2_gpio_resume_after_idle+0x54/0x68) > [] (omap2_gpio_resume_after_idle) from [] (omap3_enter_idle_bm+0xfc/0x1ec) > [] (omap3_enter_idle_bm) from [] (cpuidle_enter_state+0x80/0x3d4) > [] (cpuidle_enter_state) from [] (cpu_startup_entry+0x198/0x3a0) > [] (cpu_startup_entry) from [] (start_kernel+0x354/0x3c8) > [] (start_kernel) from [<8000807c>] (0x8000807c) Reported-by: Tony Lindgren Signed-off-by: Paul E. McKenney Tested-by: Tony Lindgren Tested-by: Guenter Roeck Signed-off-by: Rafael J. Wysocki --- drivers/base/power/runtime.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index e097d355cc04..76127e109ed2 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -601,7 +601,7 @@ static int rpm_resume(struct device *dev, int rpmflags) struct device *parent = NULL; int retval = 0; - trace_rpm_resume(dev, rpmflags); + trace_rpm_resume_rcuidle(dev, rpmflags); repeat: if (dev->power.runtime_error) @@ -764,7 +764,7 @@ static int rpm_resume(struct device *dev, int rpmflags) spin_lock_irq(&dev->power.lock); } - trace_rpm_return_int(dev, _THIS_IP_, retval); + trace_rpm_return_int_rcuidle(dev, _THIS_IP_, retval); return retval; } From d7737ce964d944dd07e25b0f569edcd550ede18c Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 26 Apr 2016 13:03:51 -0700 Subject: [PATCH 473/531] PM / runtime: Add _rcuidle suffix to allow rpm_idle() use from idle This commit appends a few _rcuidle suffixes to fix the following RCU-used-from-idle bug: > =============================== > [ INFO: suspicious RCU usage. ] > 4.6.0-rc5-next-20160426+ #1116 Not tainted > ------------------------------- > include/trace/events/rpm.h:95 suspicious rcu_dereference_check() usage! > > other info that might help us debug this: > > > RCU used illegally from idle CPU! > rcu_scheduler_active = 1, debug_locks = 0 > RCU used illegally from extended quiescent state! > 1 lock held by swapper/0/0: > #0: (&(&dev->power.lock)->rlock){-.-...}, at: [] __rpm_callback+0x58/0x60 > > stack backtrace: > CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.6.0-rc5-next-20160426+ #1116 > Hardware name: Generic OMAP36xx (Flattened Device Tree) > [] (unwind_backtrace) from [] (show_stack+0x10/0x14) > [] (show_stack) from [] (dump_stack+0xb0/0xe4) > [] (dump_stack) from [] (rpm_suspend+0x580/0x768) > [] (rpm_suspend) from [] (__pm_runtime_suspend+0x64/0x84) > [] (__pm_runtime_suspend) from [] (omap2_gpio_prepare_for_idle+0x5c/0x70) > [] (omap2_gpio_prepare_for_idle) from [] (omap_sram_idle+0x140/0x244) > [] (omap_sram_idle) from [] (omap3_enter_idle_bm+0xfc/0x1ec) > [] (omap3_enter_idle_bm) from [] (cpuidle_enter_state+0x80/0x3d4) > [] (cpuidle_enter_state) from [] (cpu_startup_entry+0x198/0x3a0) > [] (cpu_startup_entry) from [] (start_kernel+0x354/0x3c8) > [] (start_kernel) from [<8000807c>] (0x8000807c) In the immortal words of Steven Rostedt, "*Whack* *Whack* *Whack*!!!" Reported-by: Tony Lindgren Signed-off-by: Paul E. McKenney Tested-by: Tony Lindgren Tested-by: Guenter Roeck WhACKED-by: Steven Rostedt Signed-off-by: Rafael J. Wysocki --- drivers/base/power/runtime.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 76127e109ed2..17995fadebd7 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -301,7 +301,7 @@ static int rpm_idle(struct device *dev, int rpmflags) int (*callback)(struct device *); int retval; - trace_rpm_idle(dev, rpmflags); + trace_rpm_idle_rcuidle(dev, rpmflags); retval = rpm_check_suspend_allowed(dev); if (retval < 0) ; /* Conditions are wrong. */ @@ -337,7 +337,7 @@ static int rpm_idle(struct device *dev, int rpmflags) dev->power.request_pending = true; queue_work(pm_wq, &dev->power.work); } - trace_rpm_return_int(dev, _THIS_IP_, 0); + trace_rpm_return_int_rcuidle(dev, _THIS_IP_, 0); return 0; } @@ -352,7 +352,7 @@ static int rpm_idle(struct device *dev, int rpmflags) wake_up_all(&dev->power.wait_queue); out: - trace_rpm_return_int(dev, _THIS_IP_, retval); + trace_rpm_return_int_rcuidle(dev, _THIS_IP_, retval); return retval ? retval : rpm_suspend(dev, rpmflags | RPM_AUTO); } From 279cf3f23870f7eb8ca071115e06d3d5ca0a2b9e Mon Sep 17 00:00:00 2001 From: Peter Wu Date: Fri, 26 Aug 2016 01:00:54 +0200 Subject: [PATCH 474/531] drm/nouveau/acpi: use DSM if bridge does not support D3cold Even if PR3 support is available on the bridge, it will not be used if the PCI layer considers it unavailable (i.e. on all laptops from 2013 and 2014). Ensure that this condition is checked to allow a fallback to the Optimus DSM for device poweroff. Initially I wanted to call pci_d3cold_enable before checking bridge_d3 (in case the user changed d3cold_allowed), but that is such an unlikely case and likely fragile anyway. The current patch is suggested by Mika in http://www.spinics.net/lists/linux-pci/msg52599.html Cc: Mika Westerberg Signed-off-by: Peter Wu Reviewed-by: Mika Westerberg Signed-off-by: Dave Airlie --- drivers/gpu/drm/nouveau/nouveau_acpi.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c index f2ad17aa33f0..dc57b628e074 100644 --- a/drivers/gpu/drm/nouveau/nouveau_acpi.c +++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c @@ -225,6 +225,17 @@ static bool nouveau_pr3_present(struct pci_dev *pdev) if (!parent_pdev) return false; + if (!parent_pdev->bridge_d3) { + /* + * Parent PCI bridge is currently not power managed. + * Since userspace can change these afterwards to be on + * the safe side we stick with _DSM and prevent usage of + * _PR3 from the bridge. + */ + pci_d3cold_disable(pdev); + return false; + } + parent_adev = ACPI_COMPANION(&parent_pdev->dev); if (!parent_adev) return false; From c012268b37db6b10b59dac9b7f45956cb9a8bcb2 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 5 Aug 2016 14:25:53 -0700 Subject: [PATCH 475/531] lkdtm: Mark lkdtm_rodata_do_nothing() notrace lkdtm_rodata_do_nothing() is an empty function which is generated in order to test the non-executability of rodata. Currently if function tracing is enabled then an mcount callsite will be generated for lkdtm_rodata_do_nothing(), and it will appear in the list of available functions for function tracing (available_filter_functions). Given it's purpose purely as a test function, it seems preferable for lkdtm_rodata_do_nothing() to be marked notrace, so it doesn't appear as traceable. This also avoids triggering a linker bug on powerpc: https://sourceware.org/bugzilla/show_bug.cgi?id=20428 When the linker sees code that needs to generate a call stub, eg. a branch to mcount(), it assumes the section is executable and dereferences a NULL pointer leading to a linker segfault. Marking lkdtm_rodata_do_nothing() notrace avoids triggering the bug because the function contains no other function calls. Signed-off-by: Michael Ellerman Signed-off-by: Kees Cook Signed-off-by: Greg Kroah-Hartman --- drivers/misc/lkdtm_rodata.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/misc/lkdtm_rodata.c b/drivers/misc/lkdtm_rodata.c index 166b1db3969f..3564477b8c2d 100644 --- a/drivers/misc/lkdtm_rodata.c +++ b/drivers/misc/lkdtm_rodata.c @@ -4,7 +4,7 @@ */ #include "lkdtm.h" -void lkdtm_rodata_do_nothing(void) +void notrace lkdtm_rodata_do_nothing(void) { /* Does nothing. We just want an architecture agnostic "return". */ } From 25eb7e5c7454c9e8407c5382b9fe32d3b45fe163 Mon Sep 17 00:00:00 2001 From: Andreas Noever Date: Tue, 26 Jul 2016 18:40:37 +0200 Subject: [PATCH 476/531] thunderbolt: Fix resume quirk for Falcon Ridge 4C. The quirk 'quirk_apple_wait_for_thunderbolt' did not fire on Falcon Ridge 4C controllers with subdevice/subvendor set to zero. This lead to lost pci devices on system resume. Older thunderbolt controllers (pre Falcon Ridge) used the same device id for bridges and for the controller. On Apple hardware the subvendor- & subdevice-ids were set for the controller, but not for bridges. So that is what was used to differentiate between the two. Starting with Falcon Ridge bridges and controllers received different device ids. Additionally on some MacBookPro models (but not all) the subvendor/subdevice was zeroed. Starting with a42fb351c (thunderbolt: Allow loading of module on recent Apple MacBooks with thunderbolt 2 controller) the thunderbolt driver binds to all Falcon Ridge 4C controllers (irregardless of subvendor/subdevice). The corresponding quirk was not updated. This commit changes the quirk to check the device class instead of its subvendor-/subdeviceids. This works for all generations of Thunderbolt controllers. Signed-off-by: Andreas Noever Reviewed-by: Lukas Wunner Signed-off-by: Greg Kroah-Hartman --- drivers/pci/quirks.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 37ff0158e45f..6ff6469dab2a 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -3328,8 +3328,7 @@ static void quirk_apple_wait_for_thunderbolt(struct pci_dev *dev) || (nhi->device != PCI_DEVICE_ID_INTEL_LIGHT_RIDGE && nhi->device != PCI_DEVICE_ID_INTEL_CACTUS_RIDGE_4C && nhi->device != PCI_DEVICE_ID_INTEL_FALCON_RIDGE_4C_NHI) - || nhi->subsystem_vendor != 0x2222 - || nhi->subsystem_device != 0x1111) + || nhi->class != PCI_CLASS_SYSTEM_OTHER << 8) goto out; dev_info(&dev->dev, "quirk: waiting for thunderbolt to reestablish PCI tunnels...\n"); device_pm_wait_for_dev(&dev->dev, &nhi->dev); From 82a6a81c2a38aa7a7813a0c532637877773c50ae Mon Sep 17 00:00:00 2001 From: Xavier Gnata Date: Tue, 26 Jul 2016 18:40:38 +0200 Subject: [PATCH 477/531] thunderbolt: Add support for INTEL_FALCON_RIDGE_2C controller. From: Xavier Gnata Add support to INTEL_FALCON_RIDGE_2C controller and corresponding quirk to support suspend/resume. Tested against 4.7 master on a MacBook Air 11" 2015. Signed-off-by: Andreas Noever Reviewed-by: Lukas Wunner Signed-off-by: Greg Kroah-Hartman --- drivers/pci/quirks.c | 4 ++++ drivers/thunderbolt/nhi.c | 6 ++++++ 2 files changed, 10 insertions(+) diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 6ff6469dab2a..44e0ff37480b 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -3327,6 +3327,7 @@ static void quirk_apple_wait_for_thunderbolt(struct pci_dev *dev) if (nhi->vendor != PCI_VENDOR_ID_INTEL || (nhi->device != PCI_DEVICE_ID_INTEL_LIGHT_RIDGE && nhi->device != PCI_DEVICE_ID_INTEL_CACTUS_RIDGE_4C && + nhi->device != PCI_DEVICE_ID_INTEL_FALCON_RIDGE_2C_NHI && nhi->device != PCI_DEVICE_ID_INTEL_FALCON_RIDGE_4C_NHI) || nhi->class != PCI_CLASS_SYSTEM_OTHER << 8) goto out; @@ -3342,6 +3343,9 @@ DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_INTEL, DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CACTUS_RIDGE_4C, quirk_apple_wait_for_thunderbolt); +DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_INTEL, + PCI_DEVICE_ID_INTEL_FALCON_RIDGE_2C_BRIDGE, + quirk_apple_wait_for_thunderbolt); DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_FALCON_RIDGE_4C_BRIDGE, quirk_apple_wait_for_thunderbolt); diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index 9c15344b657a..a8c20413dbda 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -648,6 +648,12 @@ static struct pci_device_id nhi_ids[] = { .device = PCI_DEVICE_ID_INTEL_CACTUS_RIDGE_4C, .subvendor = 0x2222, .subdevice = 0x1111, }, + { + .class = PCI_CLASS_SYSTEM_OTHER << 8, .class_mask = ~0, + .vendor = PCI_VENDOR_ID_INTEL, + .device = PCI_DEVICE_ID_INTEL_FALCON_RIDGE_2C_NHI, + .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, + }, { .class = PCI_CLASS_SYSTEM_OTHER << 8, .class_mask = ~0, .vendor = PCI_VENDOR_ID_INTEL, From ccdf3b888d87df1b914fedde91ed1848f0651c65 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Wed, 3 Aug 2016 10:44:12 +0200 Subject: [PATCH 478/531] thunderbolt: Don't declare Falcon Ridge unsupported Falcon Ridge 4C has been supported by the driver from the beginning, Falcon Ridge 2C support was just added. Don't irritate users with a warning declaring the opposite. Signed-off-by: Lukas Wunner Signed-off-by: Andreas Noever Signed-off-by: Greg Kroah-Hartman --- drivers/thunderbolt/switch.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 1e116f53d6dd..9840fdecb73b 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -372,7 +372,9 @@ struct tb_switch *tb_switch_alloc(struct tb *tb, u64 route) if (sw->config.device_id != PCI_DEVICE_ID_INTEL_LIGHT_RIDGE && sw->config.device_id != PCI_DEVICE_ID_INTEL_CACTUS_RIDGE_4C && - sw->config.device_id != PCI_DEVICE_ID_INTEL_PORT_RIDGE) + sw->config.device_id != PCI_DEVICE_ID_INTEL_PORT_RIDGE && + sw->config.device_id != PCI_DEVICE_ID_INTEL_FALCON_RIDGE_2C_BRIDGE && + sw->config.device_id != PCI_DEVICE_ID_INTEL_FALCON_RIDGE_4C_BRIDGE) tb_sw_warn(sw, "unsupported switch device id %#x\n", sw->config.device_id); From df6a58c5c5aa8ecb1e088ecead3fa33ae70181f1 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 17 Jun 2016 17:51:17 -0400 Subject: [PATCH 479/531] kernfs: don't depend on d_find_any_alias() when generating notifications kernfs_notify_workfn() sends out file modified events for the scheduled kernfs_nodes. Because the modifications aren't from userland, it doesn't have the matching file struct at hand and can't use fsnotify_modify(). Instead, it looked up the inode and then used d_find_any_alias() to find the dentry and used fsnotify_parent() and fsnotify() directly to generate notifications. The assumption was that the relevant dentries would have been pinned if there are listeners, which isn't true as inotify doesn't pin dentries at all and watching the parent doesn't pin the child dentries even for dnotify. This led to, for example, inotify watchers not getting notifications if the system is under memory pressure and the matching dentries got reclaimed. It can also be triggered through /proc/sys/vm/drop_caches or a remount attempt which involves shrinking dcache. fsnotify_parent() only uses the dentry to access the parent inode, which kernfs can do easily. Update kernfs_notify_workfn() so that it uses fsnotify() directly for both the parent and target inodes without going through d_find_any_alias(). While at it, supply the target file name to fsnotify() from kernfs_node->name. Signed-off-by: Tejun Heo Reported-by: Evgeny Vereshchagin Fixes: d911d9874801 ("kernfs: make kernfs_notify() trigger inotify events too") Cc: John McCutchan Cc: Robert Love Cc: Eric Paris Cc: stable@vger.kernel.org # v3.16+ Signed-off-by: Greg Kroah-Hartman --- fs/kernfs/file.c | 28 +++++++++++++++++++++------- 1 file changed, 21 insertions(+), 7 deletions(-) diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index e1574008adc9..2bcb86e6e6ca 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -840,21 +840,35 @@ static void kernfs_notify_workfn(struct work_struct *work) mutex_lock(&kernfs_mutex); list_for_each_entry(info, &kernfs_root(kn)->supers, node) { + struct kernfs_node *parent; struct inode *inode; - struct dentry *dentry; + /* + * We want fsnotify_modify() on @kn but as the + * modifications aren't originating from userland don't + * have the matching @file available. Look up the inodes + * and generate the events manually. + */ inode = ilookup(info->sb, kn->ino); if (!inode) continue; - dentry = d_find_any_alias(inode); - if (dentry) { - fsnotify_parent(NULL, dentry, FS_MODIFY); - fsnotify(inode, FS_MODIFY, inode, FSNOTIFY_EVENT_INODE, - NULL, 0); - dput(dentry); + parent = kernfs_get_parent(kn); + if (parent) { + struct inode *p_inode; + + p_inode = ilookup(info->sb, parent->ino); + if (p_inode) { + fsnotify(p_inode, FS_MODIFY | FS_EVENT_ON_CHILD, + inode, FSNOTIFY_EVENT_INODE, kn->name, 0); + iput(p_inode); + } + + kernfs_put(parent); } + fsnotify(inode, FS_MODIFY, inode, FSNOTIFY_EVENT_INODE, + kn->name, 0); iput(inode); } From 96b0af4b729cabd44e237c5a6b9bd4e0ea4ed457 Mon Sep 17 00:00:00 2001 From: Martin Fuzzey Date: Fri, 20 May 2016 14:23:38 +0200 Subject: [PATCH 480/531] documentation: drivers/core/of: fix name of of_node symlink commit 5590f3196b29 ("drivers/core/of: Add symlink to device-tree from devices with an OF node") added a symlink called "of_node" to sysfs however the documentation describes it as "of_path". Fix the documentation to match what the code actually does. Signed-off-by: Martin Fuzzey Acked-by: Rob Herring Signed-off-by: Greg Kroah-Hartman --- Documentation/ABI/stable/sysfs-devices | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/ABI/stable/sysfs-devices b/Documentation/ABI/stable/sysfs-devices index 43f78b88da28..df449d79b563 100644 --- a/Documentation/ABI/stable/sysfs-devices +++ b/Documentation/ABI/stable/sysfs-devices @@ -1,7 +1,7 @@ # Note: This documents additional properties of any device beyond what # is documented in Documentation/sysfs-rules.txt -What: /sys/devices/*/of_path +What: /sys/devices/*/of_node Date: February 2015 Contact: Device Tree mailing list Description: From 17d0774f80681020eccc9638d925a23f1fc4f671 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Wed, 22 Jun 2016 21:42:16 +0300 Subject: [PATCH 481/531] sysfs: correctly handle read offset on PREALLOC attrs Attributes declared with __ATTR_PREALLOC use sysfs_kf_read() which returns zero bytes for non-zero offset. This breaks script checkarray in mdadm tool in debian where /bin/sh is 'dash' because its builtin 'read' reads only one byte at a time. Script gets 'i' instead of 'idle' when reads current action from /sys/block/$dev/md/sync_action and as a result does nothing. This patch adds trivial implementation of partial read: generate whole string and move required part into buffer head. Signed-off-by: Konstantin Khlebnikov Fixes: 4ef67a8c95f3 ("sysfs/kernfs: make read requests on pre-alloc files use the buffer.") Link: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=787950 Cc: Stable # v3.19+ Acked-by: Tejun Heo Signed-off-by: Greg Kroah-Hartman --- fs/sysfs/file.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index f35523d4fa3a..b803213d1307 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -114,9 +114,15 @@ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf, * If buf != of->prealloc_buf, we don't know how * large it is, so cannot safely pass it to ->show */ - if (pos || WARN_ON_ONCE(buf != of->prealloc_buf)) + if (WARN_ON_ONCE(buf != of->prealloc_buf)) return 0; len = ops->show(kobj, of->kn->priv, buf); + if (pos) { + if (len <= pos) + return 0; + len -= pos; + memmove(buf, buf + pos, len); + } return min(count, len); } From 5db4f7f80d165fc9725f356e99feec409e446baa Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 16 Aug 2016 15:06:54 +0300 Subject: [PATCH 482/531] Revert "tty/serial/8250: use mctrl_gpio helpers" Serial console is broken in v4.8-rcX. Mika and I independently bisected down to commit 4ef03d328769 ("tty/serial/8250: use mctrl_gpio helpers"). Since neither author nor anyone else didn't propose a solution we better revert it for now. This reverts commit 4ef03d328769eddbfeca1f1c958fdb181a69c341. Link: https://lkml.kernel.org/r/20160809130229.GN1729@lahna.fi.intel.com Signed-off-by: Andy Shevchenko Tested-by: Heikki Krogerus Tested-by: Mika Westerberg Signed-off-by: Greg Kroah-Hartman --- .../devicetree/bindings/serial/8250.txt | 19 ---------- drivers/tty/serial/8250/8250.h | 35 +------------------ drivers/tty/serial/8250/8250_core.c | 9 ----- drivers/tty/serial/8250/8250_omap.c | 31 +++++++--------- drivers/tty/serial/8250/8250_port.c | 7 +--- drivers/tty/serial/8250/Kconfig | 1 - include/linux/serial_8250.h | 1 - 7 files changed, 15 insertions(+), 88 deletions(-) diff --git a/Documentation/devicetree/bindings/serial/8250.txt b/Documentation/devicetree/bindings/serial/8250.txt index f5561ac7e17e..936ab5b87324 100644 --- a/Documentation/devicetree/bindings/serial/8250.txt +++ b/Documentation/devicetree/bindings/serial/8250.txt @@ -42,9 +42,6 @@ Optional properties: - auto-flow-control: one way to enable automatic flow control support. The driver is allowed to detect support for the capability even without this property. -- {rts,cts,dtr,dsr,rng,dcd}-gpios: specify a GPIO for RTS/CTS/DTR/DSR/RI/DCD - line respectively. It will use specified GPIO instead of the peripheral - function pin for the UART feature. If unsure, don't specify this property. Note: * fsl,ns16550: @@ -66,19 +63,3 @@ Example: interrupts = <10>; reg-shift = <2>; }; - -Example for OMAP UART using GPIO-based modem control signals: - - uart4: serial@49042000 { - compatible = "ti,omap3-uart"; - reg = <0x49042000 0x400>; - interrupts = <80>; - ti,hwmods = "uart4"; - clock-frequency = <48000000>; - cts-gpios = <&gpio3 5 GPIO_ACTIVE_LOW>; - rts-gpios = <&gpio3 6 GPIO_ACTIVE_LOW>; - dtr-gpios = <&gpio1 12 GPIO_ACTIVE_LOW>; - dsr-gpios = <&gpio1 13 GPIO_ACTIVE_LOW>; - dcd-gpios = <&gpio1 14 GPIO_ACTIVE_LOW>; - rng-gpios = <&gpio1 15 GPIO_ACTIVE_LOW>; - }; diff --git a/drivers/tty/serial/8250/8250.h b/drivers/tty/serial/8250/8250.h index 122e0e4029fe..1a16feac9a36 100644 --- a/drivers/tty/serial/8250/8250.h +++ b/drivers/tty/serial/8250/8250.h @@ -15,8 +15,6 @@ #include #include -#include "../serial_mctrl_gpio.h" - struct uart_8250_dma { int (*tx_dma)(struct uart_8250_port *p); int (*rx_dma)(struct uart_8250_port *p); @@ -133,43 +131,12 @@ void serial8250_em485_destroy(struct uart_8250_port *p); static inline void serial8250_out_MCR(struct uart_8250_port *up, int value) { - int mctrl_gpio = 0; - serial_out(up, UART_MCR, value); - - if (value & UART_MCR_RTS) - mctrl_gpio |= TIOCM_RTS; - if (value & UART_MCR_DTR) - mctrl_gpio |= TIOCM_DTR; - - mctrl_gpio_set(up->gpios, mctrl_gpio); } static inline int serial8250_in_MCR(struct uart_8250_port *up) { - int mctrl, mctrl_gpio = 0; - - mctrl = serial_in(up, UART_MCR); - - /* save current MCR values */ - if (mctrl & UART_MCR_RTS) - mctrl_gpio |= TIOCM_RTS; - if (mctrl & UART_MCR_DTR) - mctrl_gpio |= TIOCM_DTR; - - mctrl_gpio = mctrl_gpio_get_outputs(up->gpios, &mctrl_gpio); - - if (mctrl_gpio & TIOCM_RTS) - mctrl |= UART_MCR_RTS; - else - mctrl &= ~UART_MCR_RTS; - - if (mctrl_gpio & TIOCM_DTR) - mctrl |= UART_MCR_DTR; - else - mctrl &= ~UART_MCR_DTR; - - return mctrl; + return serial_in(up, UART_MCR); } #if defined(__alpha__) && !defined(CONFIG_PCI) diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index 13ad5c3d2e68..dcf43f66404f 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -974,8 +974,6 @@ int serial8250_register_8250_port(struct uart_8250_port *up) uart = serial8250_find_match_or_unused(&up->port); if (uart && uart->port.type != PORT_8250_CIR) { - struct mctrl_gpios *gpios; - if (uart->port.dev) uart_remove_one_port(&serial8250_reg, &uart->port); @@ -1013,13 +1011,6 @@ int serial8250_register_8250_port(struct uart_8250_port *up) if (up->port.flags & UPF_FIXED_TYPE) uart->port.type = up->port.type; - gpios = mctrl_gpio_init(&uart->port, 0); - if (IS_ERR(gpios)) { - if (PTR_ERR(gpios) != -ENOSYS) - return PTR_ERR(gpios); - } else - uart->gpios = gpios; - serial8250_set_defaults(uart); /* Possibly override default I/O functions. */ diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c index e14982f36a04..61ad6c3b20a0 100644 --- a/drivers/tty/serial/8250/8250_omap.c +++ b/drivers/tty/serial/8250/8250_omap.c @@ -134,21 +134,18 @@ static void omap8250_set_mctrl(struct uart_port *port, unsigned int mctrl) serial8250_do_set_mctrl(port, mctrl); - if (IS_ERR_OR_NULL(mctrl_gpio_to_gpiod(up->gpios, - UART_GPIO_RTS))) { - /* - * Turn off autoRTS if RTS is lowered and restore autoRTS - * setting if RTS is raised - */ - lcr = serial_in(up, UART_LCR); - serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); - if ((mctrl & TIOCM_RTS) && (port->status & UPSTAT_AUTORTS)) - priv->efr |= UART_EFR_RTS; - else - priv->efr &= ~UART_EFR_RTS; - serial_out(up, UART_EFR, priv->efr); - serial_out(up, UART_LCR, lcr); - } + /* + * Turn off autoRTS if RTS is lowered and restore autoRTS setting + * if RTS is raised + */ + lcr = serial_in(up, UART_LCR); + serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); + if ((mctrl & TIOCM_RTS) && (port->status & UPSTAT_AUTORTS)) + priv->efr |= UART_EFR_RTS; + else + priv->efr &= ~UART_EFR_RTS; + serial_out(up, UART_EFR, priv->efr); + serial_out(up, UART_LCR, lcr); } /* @@ -449,9 +446,7 @@ static void omap_8250_set_termios(struct uart_port *port, priv->efr = 0; up->port.status &= ~(UPSTAT_AUTOCTS | UPSTAT_AUTORTS | UPSTAT_AUTOXOFF); - if (termios->c_cflag & CRTSCTS && up->port.flags & UPF_HARD_FLOW - && IS_ERR_OR_NULL(mctrl_gpio_to_gpiod(up->gpios, - UART_GPIO_RTS))) { + if (termios->c_cflag & CRTSCTS && up->port.flags & UPF_HARD_FLOW) { /* Enable AUTOCTS (autoRTS is enabled when RTS is raised) */ up->port.status |= UPSTAT_AUTOCTS | UPSTAT_AUTORTS; priv->efr |= UART_EFR_CTS; diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 7481b95c6d84..bdfa659b9606 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1618,8 +1618,6 @@ static void serial8250_disable_ms(struct uart_port *port) if (up->bugs & UART_BUG_NOMSR) return; - mctrl_gpio_disable_ms(up->gpios); - up->ier &= ~UART_IER_MSI; serial_port_out(port, UART_IER, up->ier); } @@ -1632,8 +1630,6 @@ static void serial8250_enable_ms(struct uart_port *port) if (up->bugs & UART_BUG_NOMSR) return; - mctrl_gpio_enable_ms(up->gpios); - up->ier |= UART_IER_MSI; serial8250_rpm_get(up); @@ -1917,8 +1913,7 @@ unsigned int serial8250_do_get_mctrl(struct uart_port *port) ret |= TIOCM_DSR; if (status & UART_MSR_CTS) ret |= TIOCM_CTS; - - return mctrl_gpio_get(up->gpios, &ret); + return ret; } EXPORT_SYMBOL_GPL(serial8250_do_get_mctrl); diff --git a/drivers/tty/serial/8250/Kconfig b/drivers/tty/serial/8250/Kconfig index c9ec839a5ddf..7c6f7afca5dd 100644 --- a/drivers/tty/serial/8250/Kconfig +++ b/drivers/tty/serial/8250/Kconfig @@ -6,7 +6,6 @@ config SERIAL_8250 tristate "8250/16550 and compatible serial support" select SERIAL_CORE - select SERIAL_MCTRL_GPIO if GPIOLIB ---help--- This selects whether you want to include the driver for the standard serial ports. The standard answer is Y. People who might say N diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 923266cd294a..48ec7651989b 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -111,7 +111,6 @@ struct uart_8250_port { * if no_console_suspend */ unsigned char probe; - struct mctrl_gpios *gpios; #define UART_PROBE_RSA (1 << 0) /* From 47b34d2ef266e2c283b514d65c8963c2ccd42474 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 1 Jul 2016 17:21:49 +0300 Subject: [PATCH 483/531] serial: 8250_mid: fix divide error bug if baud rate is 0 Since the commit c1a67b48f6a5 ("serial: 8250_pci: replace switch-case by formula for Intel MID"), the 8250 driver crashes in the byt_set_termios() function with a divide error. This is caused by the fact that a baud rate of 0 (B0) is not handled properly. Fix it by falling back to B9600 in this case. Reported-by: "Mendez Salinas, Fernando" Fixes: c1a67b48f6a5 ("serial: 8250_pci: replace switch-case by formula for Intel MID") Cc: stable@vger.kernel.org Signed-off-by: Andy Shevchenko Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_mid.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/tty/serial/8250/8250_mid.c b/drivers/tty/serial/8250/8250_mid.c index 339de9cd0866..20c5db2f4264 100644 --- a/drivers/tty/serial/8250/8250_mid.c +++ b/drivers/tty/serial/8250/8250_mid.c @@ -168,6 +168,9 @@ static void mid8250_set_termios(struct uart_port *p, unsigned long w = BIT(24) - 1; unsigned long mul, div; + /* Gracefully handle the B0 case: fall back to B9600 */ + fuart = fuart ? fuart : 9600 * 16; + if (mid->board->freq < fuart) { /* Find prescaler value that satisfies Fuart < Fref */ if (mid->board->freq > baud) From c8d192428f52f244130b84650ad616df09f2b1e1 Mon Sep 17 00:00:00 2001 From: Jimi Damon Date: Wed, 20 Jul 2016 17:00:40 -0700 Subject: [PATCH 484/531] serial: 8250: added acces i/o products quad and octal serial cards Added devices ids for acces i/o products quad and octal serial cards that make use of existing Pericom PI7C9X7954 and PI7C9X7958 configurations . Signed-off-by: Jimi Damon Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_pci.c | 139 +++++++++++++++++++++++++++++ 1 file changed, 139 insertions(+) diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 20ebaea5c414..bc51b32b2774 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -1950,6 +1950,43 @@ pci_wch_ch38x_setup(struct serial_private *priv, #define PCI_DEVICE_ID_PERICOM_PI7C9X7954 0x7954 #define PCI_DEVICE_ID_PERICOM_PI7C9X7958 0x7958 +#define PCI_VENDOR_ID_ACCESIO 0x494f +#define PCI_DEVICE_ID_ACCESIO_PCIE_COM_2SDB 0x1051 +#define PCI_DEVICE_ID_ACCESIO_MPCIE_COM_2S 0x1053 +#define PCI_DEVICE_ID_ACCESIO_PCIE_COM_4SDB 0x105C +#define PCI_DEVICE_ID_ACCESIO_MPCIE_COM_4S 0x105E +#define PCI_DEVICE_ID_ACCESIO_PCIE_COM232_2DB 0x1091 +#define PCI_DEVICE_ID_ACCESIO_MPCIE_COM232_2 0x1093 +#define PCI_DEVICE_ID_ACCESIO_PCIE_COM232_4DB 0x1099 +#define PCI_DEVICE_ID_ACCESIO_MPCIE_COM232_4 0x109B +#define PCI_DEVICE_ID_ACCESIO_PCIE_COM_2SMDB 0x10D1 +#define PCI_DEVICE_ID_ACCESIO_MPCIE_COM_2SM 0x10D3 +#define PCI_DEVICE_ID_ACCESIO_PCIE_COM_4SMDB 0x10DA +#define PCI_DEVICE_ID_ACCESIO_MPCIE_COM_4SM 0x10DC +#define PCI_DEVICE_ID_ACCESIO_MPCIE_ICM485_1 0x1108 +#define PCI_DEVICE_ID_ACCESIO_MPCIE_ICM422_2 0x1110 +#define PCI_DEVICE_ID_ACCESIO_MPCIE_ICM485_2 0x1111 +#define PCI_DEVICE_ID_ACCESIO_MPCIE_ICM422_4 0x1118 +#define PCI_DEVICE_ID_ACCESIO_MPCIE_ICM485_4 0x1119 +#define PCI_DEVICE_ID_ACCESIO_PCIE_ICM_2S 0x1152 +#define PCI_DEVICE_ID_ACCESIO_PCIE_ICM_4S 0x115A +#define PCI_DEVICE_ID_ACCESIO_PCIE_ICM232_2 0x1190 +#define PCI_DEVICE_ID_ACCESIO_MPCIE_ICM232_2 0x1191 +#define PCI_DEVICE_ID_ACCESIO_PCIE_ICM232_4 0x1198 +#define PCI_DEVICE_ID_ACCESIO_MPCIE_ICM232_4 0x1199 +#define PCI_DEVICE_ID_ACCESIO_PCIE_ICM_2SM 0x11D0 +#define PCI_DEVICE_ID_ACCESIO_PCIE_COM422_4 0x105A +#define PCI_DEVICE_ID_ACCESIO_PCIE_COM485_4 0x105B +#define PCI_DEVICE_ID_ACCESIO_PCIE_COM422_8 0x106A +#define PCI_DEVICE_ID_ACCESIO_PCIE_COM485_8 0x106B +#define PCI_DEVICE_ID_ACCESIO_PCIE_COM232_4 0x1098 +#define PCI_DEVICE_ID_ACCESIO_PCIE_COM232_8 0x10A9 +#define PCI_DEVICE_ID_ACCESIO_PCIE_COM_4SM 0x10D9 +#define PCI_DEVICE_ID_ACCESIO_PCIE_COM_8SM 0x10E9 +#define PCI_DEVICE_ID_ACCESIO_PCIE_ICM_4SM 0x11D8 + + + /* Unknown vendors/cards - this should not be in linux/pci_ids.h */ #define PCI_SUBDEVICE_ID_UNKNOWN_0x1584 0x1584 #define PCI_SUBDEVICE_ID_UNKNOWN_0x1588 0x1588 @@ -5112,6 +5149,108 @@ static struct pci_device_id serial_pci_tbl[] = { PCI_ANY_ID, PCI_ANY_ID, 0, 0, pbn_pericom_PI7C9X7958 }, + /* + * ACCES I/O Products quad + */ + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM_2SDB, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7954 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_COM_2S, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7954 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM_4SDB, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7954 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_COM_4S, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7954 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM232_2DB, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7954 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_COM232_2, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7954 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM232_4DB, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7954 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_COM232_4, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7954 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM_2SMDB, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7954 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_COM_2SM, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7954 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM_4SMDB, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7954 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_COM_4SM, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7954 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_ICM485_1, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7954 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_ICM422_2, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7954 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_ICM485_2, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7954 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_ICM422_4, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7954 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_ICM485_4, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7954 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_ICM_2S, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7954 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_ICM_4S, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7954 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_ICM232_2, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7954 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_ICM232_2, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7954 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_ICM232_4, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7954 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_ICM232_4, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7954 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_ICM_2SM, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7954 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM422_4, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7958 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM485_4, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7958 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM422_8, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7958 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM485_8, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7958 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM232_4, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7958 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM232_8, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7958 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM_4SM, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7958 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM_8SM, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7958 }, + { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_ICM_4SM, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_pericom_PI7C9X7958 }, /* * Topic TP560 Data/Fax/Voice 56k modem (reported by Evan Clarke) */ From 9f834ec18defc369d73ccf9e87a2790bfa05bf46 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 22 Aug 2016 16:41:46 -0700 Subject: [PATCH 485/531] binfmt_elf: switch to new creds when switching to new mm MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We used to delay switching to the new credentials until after we had mapped the executable (and possible elf interpreter). That was kind of odd to begin with, since the new executable will actually then _run_ with the new creds, but whatever. The bigger problem was that we also want to make sure that we turn off prof events and tracing before we start mapping the new executable state. So while this is a cleanup, it's also a fix for a possible information leak. Reported-by: Robert Święcki Tested-by: Peter Zijlstra Acked-by: David Howells Acked-by: Oleg Nesterov Acked-by: Andy Lutomirski Acked-by: Eric W. Biederman Cc: Willy Tarreau Cc: Kees Cook Cc: Al Viro Signed-off-by: Linus Torvalds --- fs/binfmt_elf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 7f6aff3f72eb..e5495f37c6ed 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -853,6 +853,7 @@ static int load_elf_binary(struct linux_binprm *bprm) current->flags |= PF_RANDOMIZE; setup_new_exec(bprm); + install_exec_creds(bprm); /* Do this so that we can load the interpreter, if need be. We will change some of these later */ @@ -1044,7 +1045,6 @@ static int load_elf_binary(struct linux_binprm *bprm) goto out; #endif /* ARCH_HAS_SETUP_ADDITIONAL_PAGES */ - install_exec_creds(bprm); retval = create_elf_tables(bprm, &loc->elf_ex, load_addr, interp_load_addr); if (retval < 0) From 10ea9434065e56fe14287f89258ecf2fb684ed1a Mon Sep 17 00:00:00 2001 From: jimqu Date: Tue, 30 Aug 2016 08:59:42 +0800 Subject: [PATCH 486/531] drm/amd/amdgpu: sdma resume fail during S4 on CI SDMA could be fail in the thaw() and restore() processes, do software reset if each SDMA engine is busy. Signed-off-by: JimQu Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/cik_sdma.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c index ee6466912497..77fdd9911c3c 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c @@ -52,6 +52,7 @@ static void cik_sdma_set_ring_funcs(struct amdgpu_device *adev); static void cik_sdma_set_irq_funcs(struct amdgpu_device *adev); static void cik_sdma_set_buffer_funcs(struct amdgpu_device *adev); static void cik_sdma_set_vm_pte_funcs(struct amdgpu_device *adev); +static int cik_sdma_soft_reset(void *handle); MODULE_FIRMWARE("radeon/bonaire_sdma.bin"); MODULE_FIRMWARE("radeon/bonaire_sdma1.bin"); @@ -1037,6 +1038,8 @@ static int cik_sdma_resume(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + cik_sdma_soft_reset(handle); + return cik_sdma_hw_init(adev); } From 53960b4f89db58bc155d6f8aa0a44ccc59ccb26f Mon Sep 17 00:00:00 2001 From: jimqu Date: Tue, 30 Aug 2016 09:03:16 +0800 Subject: [PATCH 487/531] drm/amd/amdgpu: compute ring test fail during S4 on CI unhalt Instrction Fetch Unit after all rings are inited. Signed-off-by: JimQu Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c index d869d058ef24..425413fcaf02 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c @@ -2755,8 +2755,7 @@ static int gfx_v7_0_cp_compute_resume(struct amdgpu_device *adev) u64 wb_gpu_addr; u32 *buf; struct bonaire_mqd *mqd; - - gfx_v7_0_cp_compute_enable(adev, true); + struct amdgpu_ring *ring; /* fix up chicken bits */ tmp = RREG32(mmCP_CPF_DEBUG); @@ -2791,7 +2790,7 @@ static int gfx_v7_0_cp_compute_resume(struct amdgpu_device *adev) /* init the queues. Just two for now. */ for (i = 0; i < adev->gfx.num_compute_rings; i++) { - struct amdgpu_ring *ring = &adev->gfx.compute_ring[i]; + ring = &adev->gfx.compute_ring[i]; if (ring->mqd_obj == NULL) { r = amdgpu_bo_create(adev, @@ -2970,6 +2969,13 @@ static int gfx_v7_0_cp_compute_resume(struct amdgpu_device *adev) amdgpu_bo_unreserve(ring->mqd_obj); ring->ready = true; + } + + gfx_v7_0_cp_compute_enable(adev, true); + + for (i = 0; i < adev->gfx.num_compute_rings; i++) { + ring = &adev->gfx.compute_ring[i]; + r = amdgpu_ring_test_ring(ring); if (r) ring->ready = false; From 1f703e6679f373f5bba4efe7093aa82e91af4037 Mon Sep 17 00:00:00 2001 From: Chunming Zhou Date: Tue, 30 Aug 2016 17:59:11 +0800 Subject: [PATCH 488/531] drm/amdgpu: record error code when ring test failed MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Otherwise we may miss errors. Signed-off-by: Chunming Zhou Reviewed-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c index a31d7ef3032c..ec1282af2479 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c @@ -280,7 +280,7 @@ void amdgpu_ib_pool_fini(struct amdgpu_device *adev) int amdgpu_ib_ring_tests(struct amdgpu_device *adev) { unsigned i; - int r; + int r, ret = 0; for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { struct amdgpu_ring *ring = adev->rings[i]; @@ -301,10 +301,11 @@ int amdgpu_ib_ring_tests(struct amdgpu_device *adev) } else { /* still not good, but we can live with it */ DRM_ERROR("amdgpu: failed testing IB on ring %d (%d).\n", i, r); + ret = r; } } } - return 0; + return ret; } /* From cd81a9170e69e018bbaba547c1fd85a585f5697a Mon Sep 17 00:00:00 2001 From: Mateusz Guzik Date: Tue, 23 Aug 2016 16:20:38 +0200 Subject: [PATCH 489/531] mm: introduce get_task_exe_file For more convenient access if one has a pointer to the task. As a minor nit take advantage of the fact that only task lock + rcu are needed to safely grab ->exe_file. This saves mm refcount dance. Use the helper in proc_exe_link. Signed-off-by: Mateusz Guzik Acked-by: Konstantin Khlebnikov Acked-by: Richard Guy Briggs Cc: # 4.3.x Signed-off-by: Paul Moore --- fs/proc/base.c | 7 +------ include/linux/mm.h | 1 + kernel/fork.c | 23 +++++++++++++++++++++++ 3 files changed, 25 insertions(+), 6 deletions(-) diff --git a/fs/proc/base.c b/fs/proc/base.c index 0d163a84082d..da8b1943ba04 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1552,18 +1552,13 @@ static const struct file_operations proc_pid_set_comm_operations = { static int proc_exe_link(struct dentry *dentry, struct path *exe_path) { struct task_struct *task; - struct mm_struct *mm; struct file *exe_file; task = get_proc_task(d_inode(dentry)); if (!task) return -ENOENT; - mm = get_task_mm(task); + exe_file = get_task_exe_file(task); put_task_struct(task); - if (!mm) - return -ENOENT; - exe_file = get_mm_exe_file(mm); - mmput(mm); if (exe_file) { *exe_path = exe_file->f_path; path_get(&exe_file->f_path); diff --git a/include/linux/mm.h b/include/linux/mm.h index 8f468e0d2534..004c73a988b7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1987,6 +1987,7 @@ extern void mm_drop_all_locks(struct mm_struct *mm); extern void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file); extern struct file *get_mm_exe_file(struct mm_struct *mm); +extern struct file *get_task_exe_file(struct task_struct *task); extern bool may_expand_vm(struct mm_struct *, vm_flags_t, unsigned long npages); extern void vm_stat_account(struct mm_struct *, vm_flags_t, long npages); diff --git a/kernel/fork.c b/kernel/fork.c index d277e83ed3e0..42451aeb245f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -773,6 +773,29 @@ struct file *get_mm_exe_file(struct mm_struct *mm) } EXPORT_SYMBOL(get_mm_exe_file); +/** + * get_task_exe_file - acquire a reference to the task's executable file + * + * Returns %NULL if task's mm (if any) has no associated executable file or + * this is a kernel thread with borrowed mm (see the comment above get_task_mm). + * User must release file via fput(). + */ +struct file *get_task_exe_file(struct task_struct *task) +{ + struct file *exe_file = NULL; + struct mm_struct *mm; + + task_lock(task); + mm = task->mm; + if (mm) { + if (!(task->flags & PF_KTHREAD)) + exe_file = get_mm_exe_file(mm); + } + task_unlock(task); + return exe_file; +} +EXPORT_SYMBOL(get_task_exe_file); + /** * get_task_mm - acquire a reference to the task's mm * From 5efc244346f9f338765da3d592f7947b0afdc4b5 Mon Sep 17 00:00:00 2001 From: Mateusz Guzik Date: Tue, 23 Aug 2016 16:20:39 +0200 Subject: [PATCH 490/531] audit: fix exe_file access in audit_exe_compare Prior to the change the function would blindly deference mm, exe_file and exe_file->f_inode, each of which could have been NULL or freed. Use get_task_exe_file to safely obtain stable exe_file. Signed-off-by: Mateusz Guzik Acked-by: Konstantin Khlebnikov Acked-by: Richard Guy Briggs Cc: # 4.3.x Signed-off-by: Paul Moore --- kernel/audit_watch.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 3cf1c5978d39..4846691957da 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -19,6 +19,7 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#include #include #include #include @@ -544,10 +545,11 @@ int audit_exe_compare(struct task_struct *tsk, struct audit_fsnotify_mark *mark) unsigned long ino; dev_t dev; - rcu_read_lock(); - exe_file = rcu_dereference(tsk->mm->exe_file); + exe_file = get_task_exe_file(tsk); + if (!exe_file) + return 0; ino = exe_file->f_inode->i_ino; dev = exe_file->f_inode->i_sb->s_dev; - rcu_read_unlock(); + fput(exe_file); return audit_mark_compare(mark, ino, dev); } From 38b256973ea90fc7c2b7e1b734fa0e8b83538d50 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 1 Sep 2016 11:11:59 +0200 Subject: [PATCH 491/531] ovl: handle umask and posix_acl_default correctly on creation Setting MS_POSIXACL in sb->s_flags has the side effect of passing mode to create functions without masking against umask. Another problem when creating over a whiteout is that the default posix acl is not inherited from the parent dir (because the real parent dir at the time of creation is the work directory). Fix these problems by: a) If upper fs does not have MS_POSIXACL, then mask mode with umask. b) If creating over a whiteout, call posix_acl_create() to get the inherited acls. After creation (but before moving to the final destination) set these acls on the created file. posix_acl_create() also updates the file creation mode as appropriate. Fixes: 39a25b2b3762 ("ovl: define ->get_acl() for overlay inodes") Signed-off-by: Miklos Szeredi --- fs/overlayfs/dir.c | 54 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 12bcd07b9e32..f485dd4288e4 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -12,6 +12,8 @@ #include #include #include +#include +#include #include "overlayfs.h" void ovl_cleanup(struct inode *wdir, struct dentry *wdentry) @@ -186,6 +188,9 @@ static int ovl_create_upper(struct dentry *dentry, struct inode *inode, struct dentry *newdentry; int err; + if (!hardlink && !IS_POSIXACL(udir)) + stat->mode &= ~current_umask(); + inode_lock_nested(udir, I_MUTEX_PARENT); newdentry = lookup_one_len(dentry->d_name.name, upperdir, dentry->d_name.len); @@ -335,6 +340,32 @@ static struct dentry *ovl_check_empty_and_clear(struct dentry *dentry) return ret; } +static int ovl_set_upper_acl(struct dentry *upperdentry, const char *name, + const struct posix_acl *acl) +{ + void *buffer; + size_t size; + int err; + + if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !acl) + return 0; + + size = posix_acl_to_xattr(NULL, acl, NULL, 0); + buffer = kmalloc(size, GFP_KERNEL); + if (!buffer) + return -ENOMEM; + + size = posix_acl_to_xattr(&init_user_ns, acl, buffer, size); + err = size; + if (err < 0) + goto out_free; + + err = vfs_setxattr(upperdentry, name, buffer, size, XATTR_CREATE); +out_free: + kfree(buffer); + return err; +} + static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode, struct kstat *stat, const char *link, struct dentry *hardlink) @@ -346,10 +377,18 @@ static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode, struct dentry *upper; struct dentry *newdentry; int err; + struct posix_acl *acl, *default_acl; if (WARN_ON(!workdir)) return -EROFS; + if (!hardlink) { + err = posix_acl_create(dentry->d_parent->d_inode, + &stat->mode, &default_acl, &acl); + if (err) + return err; + } + err = ovl_lock_rename_workdir(workdir, upperdir); if (err) goto out; @@ -384,6 +423,17 @@ static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode, if (err) goto out_cleanup; } + if (!hardlink) { + err = ovl_set_upper_acl(newdentry, XATTR_NAME_POSIX_ACL_ACCESS, + acl); + if (err) + goto out_cleanup; + + err = ovl_set_upper_acl(newdentry, XATTR_NAME_POSIX_ACL_DEFAULT, + default_acl); + if (err) + goto out_cleanup; + } if (!hardlink && S_ISDIR(stat->mode)) { err = ovl_set_opaque(newdentry); @@ -410,6 +460,10 @@ static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode, out_unlock: unlock_rename(workdir, upperdir); out: + if (!hardlink) { + posix_acl_release(acl); + posix_acl_release(default_acl); + } return err; out_cleanup: From c11b9fdd6a612f376a5e886505f1c54c16d8c380 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 1 Sep 2016 11:11:59 +0200 Subject: [PATCH 492/531] ovl: remove posix_acl_default from workdir Clear out posix acl xattrs on workdir and also reset the mode after creation so that an inherited sgid bit is cleared. Signed-off-by: Miklos Szeredi Cc: --- fs/overlayfs/super.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 4036132842b5..452fb7130efa 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -814,6 +814,10 @@ static struct dentry *ovl_workdir_create(struct vfsmount *mnt, struct kstat stat = { .mode = S_IFDIR | 0, }; + struct iattr attr = { + .ia_valid = ATTR_MODE, + .ia_mode = stat.mode, + }; if (work->d_inode) { err = -EEXIST; @@ -829,6 +833,21 @@ static struct dentry *ovl_workdir_create(struct vfsmount *mnt, err = ovl_create_real(dir, work, &stat, NULL, NULL, true); if (err) goto out_dput; + + err = vfs_removexattr(work, XATTR_NAME_POSIX_ACL_DEFAULT); + if (err && err != -ENODATA) + goto out_dput; + + err = vfs_removexattr(work, XATTR_NAME_POSIX_ACL_ACCESS); + if (err && err != -ENODATA) + goto out_dput; + + /* Clear any inherited mode bits */ + inode_lock(work->d_inode); + err = notify_change(work, &attr, NULL); + inode_unlock(work->d_inode); + if (err) + goto out_dput; } out_unlock: inode_unlock(dir); From eea2fb4851e9dcbab6b991aaf47e2e024f1f55a0 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 1 Sep 2016 11:11:59 +0200 Subject: [PATCH 493/531] ovl: proper cleanup of workdir When mounting overlayfs it needs a clean "work" directory under the supplied workdir. Previously the mount code removed this directory if it already existed and created a new one. If the removal failed (e.g. directory was not empty) then it fell back to a read-only mount not using the workdir. While this has never been reported, it is possible to get a non-empty "work" dir from a previous mount of overlayfs in case of crash in the middle of an operation using the work directory. In this case the left over state should be discarded and the overlay filesystem will be consistent, guaranteed by the atomicity of operations on moving to/from the workdir to the upper layer. This patch implements cleaning out any files left in workdir. It is implemented using real recursion for simplicity, but the depth is limited to 2, because the worst case is that of a directory containing whiteouts under "work". Signed-off-by: Miklos Szeredi Cc: --- fs/overlayfs/overlayfs.h | 2 ++ fs/overlayfs/readdir.c | 63 +++++++++++++++++++++++++++++++++++++++- fs/overlayfs/super.c | 2 +- 3 files changed, 65 insertions(+), 2 deletions(-) diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 34839bd2b6b8..9a95e2c5653e 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -179,6 +179,8 @@ int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list); void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list); void ovl_cache_free(struct list_head *list); int ovl_check_d_type_supported(struct path *realpath); +void ovl_workdir_cleanup(struct inode *dir, struct vfsmount *mnt, + struct dentry *dentry, int level); /* inode.c */ int ovl_setattr(struct dentry *dentry, struct iattr *attr); diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index cf37fc76fc9f..f241b4ee3d8a 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -248,7 +248,7 @@ static inline int ovl_dir_read(struct path *realpath, err = rdd->err; } while (!err && rdd->count); - if (!err && rdd->first_maybe_whiteout) + if (!err && rdd->first_maybe_whiteout && rdd->dentry) err = ovl_check_whiteouts(realpath->dentry, rdd); fput(realfile); @@ -606,3 +606,64 @@ int ovl_check_d_type_supported(struct path *realpath) return rdd.d_type_supported; } + +static void ovl_workdir_cleanup_recurse(struct path *path, int level) +{ + int err; + struct inode *dir = path->dentry->d_inode; + LIST_HEAD(list); + struct ovl_cache_entry *p; + struct ovl_readdir_data rdd = { + .ctx.actor = ovl_fill_merge, + .dentry = NULL, + .list = &list, + .root = RB_ROOT, + .is_lowest = false, + }; + + err = ovl_dir_read(path, &rdd); + if (err) + goto out; + + inode_lock_nested(dir, I_MUTEX_PARENT); + list_for_each_entry(p, &list, l_node) { + struct dentry *dentry; + + if (p->name[0] == '.') { + if (p->len == 1) + continue; + if (p->len == 2 && p->name[1] == '.') + continue; + } + dentry = lookup_one_len(p->name, path->dentry, p->len); + if (IS_ERR(dentry)) + continue; + if (dentry->d_inode) + ovl_workdir_cleanup(dir, path->mnt, dentry, level); + dput(dentry); + } + inode_unlock(dir); +out: + ovl_cache_free(&list); +} + +void ovl_workdir_cleanup(struct inode *dir, struct vfsmount *mnt, + struct dentry *dentry, int level) +{ + int err; + + if (!d_is_dir(dentry) || level > 1) { + ovl_cleanup(dir, dentry); + return; + } + + err = ovl_do_rmdir(dir, dentry); + if (err) { + struct path path = { .mnt = mnt, .dentry = dentry }; + + inode_unlock(dir); + ovl_workdir_cleanup_recurse(&path, level + 1); + inode_lock_nested(dir, I_MUTEX_PARENT); + ovl_cleanup(dir, dentry); + } +} diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 452fb7130efa..219534e5ca0b 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -825,7 +825,7 @@ static struct dentry *ovl_workdir_create(struct vfsmount *mnt, goto out_dput; retried = true; - ovl_cleanup(dir, work); + ovl_workdir_cleanup(dir, mnt, work, 0); dput(work); goto retry; } From 5201dc449e4b6b6d7e92f7f974269b11681f98b5 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 1 Sep 2016 11:11:59 +0200 Subject: [PATCH 494/531] ovl: use cached acl on underlying layer Instead of calling ->get_acl() directly, use get_acl() to get the cached value. We will have the acl cached on the underlying inode anyway, because we do permission checking on the both the overlay and the underlying fs. So, since we already have double caching, this improves performance without any cost. Signed-off-by: Miklos Szeredi --- fs/overlayfs/inode.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 024352f1d405..d50d1ead1b6f 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -10,6 +10,7 @@ #include #include #include +#include #include "overlayfs.h" static int ovl_copy_up_truncate(struct dentry *dentry) @@ -314,14 +315,14 @@ struct posix_acl *ovl_get_acl(struct inode *inode, int type) const struct cred *old_cred; struct posix_acl *acl; - if (!IS_POSIXACL(realinode)) + if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !IS_POSIXACL(realinode)) return NULL; if (!realinode->i_op->get_acl) return NULL; old_cred = ovl_override_creds(inode->i_sb); - acl = realinode->i_op->get_acl(realinode, type); + acl = get_acl(realinode, type); revert_creds(old_cred); return acl; From 2a3a2a3f35249412e35fbb48b743348c40373409 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 1 Sep 2016 11:11:59 +0200 Subject: [PATCH 495/531] ovl: don't cache acl on overlay layer Some operations (setxattr/chmod) can make the cached acl stale. We either need to clear overlay's acl cache for the affected inode or prevent acl caching on the overlay altogether. Preventing caching has the following advantages: - no double caching, less memory used - overlay cache doesn't go stale when fs clears it's own cache Possible disadvantage is performance loss. If that becomes a problem get_acl() can be optimized for overlayfs. This patch disables caching by pre setting i_*acl to a value that - has bit 0 set, so is_uncached_acl() will return true - is not equal to ACL_NOT_CACHED, so get_acl() will not overwrite it The constant -3 was chosen for this purpose. Fixes: 39a25b2b3762 ("ovl: define ->get_acl() for overlay inodes") Signed-off-by: Miklos Szeredi --- fs/overlayfs/inode.c | 3 +++ include/linux/fs.h | 1 + 2 files changed, 4 insertions(+) diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index d50d1ead1b6f..47a4f33df47b 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -416,6 +416,9 @@ static void ovl_fill_inode(struct inode *inode, umode_t mode) inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_flags |= S_NOCMTIME; +#ifdef CONFIG_FS_POSIX_ACL + inode->i_acl = inode->i_default_acl = ACL_DONT_CACHE; +#endif mode &= S_IFMT; switch (mode) { diff --git a/include/linux/fs.h b/include/linux/fs.h index 3523bf62f328..901e25d495cc 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -574,6 +574,7 @@ static inline void mapping_allow_writable(struct address_space *mapping) struct posix_acl; #define ACL_NOT_CACHED ((void *)(-1)) +#define ACL_DONT_CACHE ((void *)(-3)) static inline struct posix_acl * uncached_acl_sentinel(struct task_struct *task) From fd36570a8805f39b40a0ebde19b08603aa201d17 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 18 Aug 2016 16:58:35 +0100 Subject: [PATCH 496/531] ovl: fix spelling mistake: "directries" -> "directories" Trivial fix to spelling mistake in pr_err message. Signed-off-by: Colin Ian King Signed-off-by: Miklos Szeredi --- fs/overlayfs/super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 219534e5ca0b..6aad7d4e2601 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1151,7 +1151,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) err = -EINVAL; stacklen = ovl_split_lowerdirs(lowertmp); if (stacklen > OVL_MAX_STACK) { - pr_err("overlayfs: too many lower directries, limit is %d\n", + pr_err("overlayfs: too many lower directories, limit is %d\n", OVL_MAX_STACK); goto out_free_lowertmp; } else if (!ufs->config.upperdir && stacklen == 1) { From fe2b75952347762a21f67d9df1199137ae5988b2 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Mon, 22 Aug 2016 17:59:22 +0200 Subject: [PATCH 497/531] ovl: Fix OVL_XATTR_PREFIX Make sure ovl_own_xattr_handler only matches attribute names starting with "overlay.", not "overlayXXX". Signed-off-by: Andreas Gruenbacher Fixes: d837a49bd57f ("ovl: fix POSIX ACL setting") Signed-off-by: Miklos Szeredi --- fs/overlayfs/inode.c | 5 ++--- fs/overlayfs/overlayfs.h | 4 ++-- 2 files changed, 4 insertions(+), 5 deletions(-) diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 47a4f33df47b..f523511b324f 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -194,9 +194,8 @@ static int ovl_readlink(struct dentry *dentry, char __user *buf, int bufsiz) bool ovl_is_private_xattr(const char *name) { -#define OVL_XATTR_PRE_NAME OVL_XATTR_PREFIX "." - return strncmp(name, OVL_XATTR_PRE_NAME, - sizeof(OVL_XATTR_PRE_NAME) - 1) == 0; + return strncmp(name, OVL_XATTR_PREFIX, + sizeof(OVL_XATTR_PREFIX) - 1) == 0; } int ovl_setxattr(struct dentry *dentry, struct inode *inode, diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 9a95e2c5653e..f50c390683a3 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -24,8 +24,8 @@ enum ovl_path_type { (OVL_TYPE_MERGE(type) || !OVL_TYPE_UPPER(type)) -#define OVL_XATTR_PREFIX XATTR_TRUSTED_PREFIX "overlay" -#define OVL_XATTR_OPAQUE OVL_XATTR_PREFIX ".opaque" +#define OVL_XATTR_PREFIX XATTR_TRUSTED_PREFIX "overlay." +#define OVL_XATTR_OPAQUE OVL_XATTR_PREFIX "opaque" #define OVL_ISUPPER_MASK 1UL From 0c97be22f928b85110504c4bbb8574facb4bd0c0 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Mon, 22 Aug 2016 16:36:49 +0200 Subject: [PATCH 498/531] ovl: Get rid of ovl_xattr_noacl_handlers array Use an ordinary #ifdef to conditionally include the POSIX ACL handlers in ovl_xattr_handlers, like the other filesystems do. Flag the code that is now only used conditionally with __maybe_unused. Signed-off-by: Andreas Gruenbacher Signed-off-by: Miklos Szeredi --- fs/overlayfs/super.c | 28 ++++++++++++---------------- 1 file changed, 12 insertions(+), 16 deletions(-) diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 6aad7d4e2601..c35619195385 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -986,10 +986,11 @@ static unsigned int ovl_split_lowerdirs(char *str) return ctr; } -static int ovl_posix_acl_xattr_set(const struct xattr_handler *handler, - struct dentry *dentry, struct inode *inode, - const char *name, const void *value, - size_t size, int flags) +static int __maybe_unused +ovl_posix_acl_xattr_set(const struct xattr_handler *handler, + struct dentry *dentry, struct inode *inode, + const char *name, const void *value, + size_t size, int flags) { struct dentry *workdir = ovl_workdir(dentry); struct inode *realinode = ovl_inode_real(inode, NULL); @@ -1040,13 +1041,15 @@ static int ovl_own_xattr_set(const struct xattr_handler *handler, return -EPERM; } -static const struct xattr_handler ovl_posix_acl_access_xattr_handler = { +static const struct xattr_handler __maybe_unused +ovl_posix_acl_access_xattr_handler = { .name = XATTR_NAME_POSIX_ACL_ACCESS, .flags = ACL_TYPE_ACCESS, .set = ovl_posix_acl_xattr_set, }; -static const struct xattr_handler ovl_posix_acl_default_xattr_handler = { +static const struct xattr_handler __maybe_unused +ovl_posix_acl_default_xattr_handler = { .name = XATTR_NAME_POSIX_ACL_DEFAULT, .flags = ACL_TYPE_DEFAULT, .set = ovl_posix_acl_xattr_set, @@ -1063,19 +1066,15 @@ static const struct xattr_handler ovl_other_xattr_handler = { }; static const struct xattr_handler *ovl_xattr_handlers[] = { +#ifdef CONFIG_FS_POSIX_ACL &ovl_posix_acl_access_xattr_handler, &ovl_posix_acl_default_xattr_handler, +#endif &ovl_own_xattr_handler, &ovl_other_xattr_handler, NULL }; -static const struct xattr_handler *ovl_xattr_noacl_handlers[] = { - &ovl_own_xattr_handler, - &ovl_other_xattr_handler, - NULL, -}; - static int ovl_fill_super(struct super_block *sb, void *data, int silent) { struct path upperpath = { NULL, NULL }; @@ -1288,10 +1287,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) sb->s_magic = OVERLAYFS_SUPER_MAGIC; sb->s_op = &ovl_super_operations; - if (IS_ENABLED(CONFIG_FS_POSIX_ACL)) - sb->s_xattr = ovl_xattr_handlers; - else - sb->s_xattr = ovl_xattr_noacl_handlers; + sb->s_xattr = ovl_xattr_handlers; sb->s_root = root_dentry; sb->s_fs_info = ufs; sb->s_flags |= MS_POSIXACL; From 0e585ccc13b3edbb187fb4f1b7cc9397f17d64a9 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Mon, 22 Aug 2016 17:22:11 +0200 Subject: [PATCH 499/531] ovl: Switch to generic_removexattr Commit d837a49bd57f ("ovl: fix POSIX ACL setting") switches from iop->setxattr from ovl_setxattr to generic_setxattr, so switch from ovl_removexattr to generic_removexattr as well. As far as permission checking goes, the same rules should apply in either case. While doing that, rename ovl_setxattr to ovl_xattr_set to indicate that this is not an iop->setxattr implementation and remove the unused inode argument. Move ovl_other_xattr_set above ovl_own_xattr_set so that they match the order of handlers in ovl_xattr_handlers. Signed-off-by: Andreas Gruenbacher Fixes: d837a49bd57f ("ovl: fix POSIX ACL setting") Signed-off-by: Miklos Szeredi --- fs/overlayfs/dir.c | 2 +- fs/overlayfs/inode.c | 65 +++++++++++++--------------------------- fs/overlayfs/overlayfs.h | 6 ++-- fs/overlayfs/super.c | 18 +++++------ 4 files changed, 33 insertions(+), 58 deletions(-) diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index f485dd4288e4..791c6a209656 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -1006,7 +1006,7 @@ const struct inode_operations ovl_dir_inode_operations = { .setxattr = generic_setxattr, .getxattr = ovl_getxattr, .listxattr = ovl_listxattr, - .removexattr = ovl_removexattr, + .removexattr = generic_removexattr, .get_acl = ovl_get_acl, .update_time = ovl_update_time, }; diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index f523511b324f..94bca710e6d2 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -198,25 +198,38 @@ bool ovl_is_private_xattr(const char *name) sizeof(OVL_XATTR_PREFIX) - 1) == 0; } -int ovl_setxattr(struct dentry *dentry, struct inode *inode, - const char *name, const void *value, - size_t size, int flags) +int ovl_xattr_set(struct dentry *dentry, const char *name, const void *value, + size_t size, int flags) { int err; - struct dentry *upperdentry; + struct path realpath; + enum ovl_path_type type = ovl_path_real(dentry, &realpath); const struct cred *old_cred; err = ovl_want_write(dentry); if (err) goto out; + if (!value && !OVL_TYPE_UPPER(type)) { + err = vfs_getxattr(realpath.dentry, name, NULL, 0); + if (err < 0) + goto out_drop_write; + } + err = ovl_copy_up(dentry); if (err) goto out_drop_write; - upperdentry = ovl_dentry_upper(dentry); + if (!OVL_TYPE_UPPER(type)) + ovl_path_upper(dentry, &realpath); + old_cred = ovl_override_creds(dentry->d_sb); - err = vfs_setxattr(upperdentry, name, value, size, flags); + if (value) + err = vfs_setxattr(realpath.dentry, name, value, size, flags); + else { + WARN_ON(flags != XATTR_REPLACE); + err = vfs_removexattr(realpath.dentry, name); + } revert_creds(old_cred); out_drop_write: @@ -272,42 +285,6 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size) return res; } -int ovl_removexattr(struct dentry *dentry, const char *name) -{ - int err; - struct path realpath; - enum ovl_path_type type = ovl_path_real(dentry, &realpath); - const struct cred *old_cred; - - err = ovl_want_write(dentry); - if (err) - goto out; - - err = -ENODATA; - if (ovl_is_private_xattr(name)) - goto out_drop_write; - - if (!OVL_TYPE_UPPER(type)) { - err = vfs_getxattr(realpath.dentry, name, NULL, 0); - if (err < 0) - goto out_drop_write; - - err = ovl_copy_up(dentry); - if (err) - goto out_drop_write; - - ovl_path_upper(dentry, &realpath); - } - - old_cred = ovl_override_creds(dentry->d_sb); - err = vfs_removexattr(realpath.dentry, name); - revert_creds(old_cred); -out_drop_write: - ovl_drop_write(dentry); -out: - return err; -} - struct posix_acl *ovl_get_acl(struct inode *inode, int type) { struct inode *realinode = ovl_inode_real(inode, NULL); @@ -393,7 +370,7 @@ static const struct inode_operations ovl_file_inode_operations = { .setxattr = generic_setxattr, .getxattr = ovl_getxattr, .listxattr = ovl_listxattr, - .removexattr = ovl_removexattr, + .removexattr = generic_removexattr, .get_acl = ovl_get_acl, .update_time = ovl_update_time, }; @@ -406,7 +383,7 @@ static const struct inode_operations ovl_symlink_inode_operations = { .setxattr = generic_setxattr, .getxattr = ovl_getxattr, .listxattr = ovl_listxattr, - .removexattr = ovl_removexattr, + .removexattr = generic_removexattr, .update_time = ovl_update_time, }; diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index f50c390683a3..5769aaf151a3 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -185,13 +185,11 @@ void ovl_workdir_cleanup(struct inode *dir, struct vfsmount *mnt, /* inode.c */ int ovl_setattr(struct dentry *dentry, struct iattr *attr); int ovl_permission(struct inode *inode, int mask); -int ovl_setxattr(struct dentry *dentry, struct inode *inode, - const char *name, const void *value, - size_t size, int flags); +int ovl_xattr_set(struct dentry *dentry, const char *name, const void *value, + size_t size, int flags); ssize_t ovl_getxattr(struct dentry *dentry, struct inode *inode, const char *name, void *value, size_t size); ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size); -int ovl_removexattr(struct dentry *dentry, const char *name); struct posix_acl *ovl_get_acl(struct inode *inode, int type); int ovl_open_maybe_copy_up(struct dentry *dentry, unsigned int file_flags); int ovl_update_time(struct inode *inode, struct timespec *ts, int flags); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index c35619195385..45a2eb0b4693 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1018,21 +1018,13 @@ ovl_posix_acl_xattr_set(const struct xattr_handler *handler, posix_acl_release(acl); - return ovl_setxattr(dentry, inode, handler->name, value, size, flags); + return ovl_xattr_set(dentry, handler->name, value, size, flags); out_acl_release: posix_acl_release(acl); return err; } -static int ovl_other_xattr_set(const struct xattr_handler *handler, - struct dentry *dentry, struct inode *inode, - const char *name, const void *value, - size_t size, int flags) -{ - return ovl_setxattr(dentry, inode, name, value, size, flags); -} - static int ovl_own_xattr_set(const struct xattr_handler *handler, struct dentry *dentry, struct inode *inode, const char *name, const void *value, @@ -1041,6 +1033,14 @@ static int ovl_own_xattr_set(const struct xattr_handler *handler, return -EPERM; } +static int ovl_other_xattr_set(const struct xattr_handler *handler, + struct dentry *dentry, struct inode *inode, + const char *name, const void *value, + size_t size, int flags) +{ + return ovl_xattr_set(dentry, name, value, size, flags); +} + static const struct xattr_handler __maybe_unused ovl_posix_acl_access_xattr_handler = { .name = XATTR_NAME_POSIX_ACL_ACCESS, From ce31513a9114f74fe3e9caa6534d201bdac7238d Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 1 Sep 2016 11:12:00 +0200 Subject: [PATCH 500/531] ovl: copyattr after setting POSIX ACL Setting POSIX acl may also modify the file mode, so need to copy that up to the overlay inode. Reported-by: Eryu Guan Fixes: d837a49bd57f ("ovl: fix POSIX ACL setting") Signed-off-by: Miklos Szeredi --- fs/overlayfs/super.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 45a2eb0b4693..cba2c9fea98c 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1018,7 +1018,11 @@ ovl_posix_acl_xattr_set(const struct xattr_handler *handler, posix_acl_release(acl); - return ovl_xattr_set(dentry, handler->name, value, size, flags); + err = ovl_xattr_set(dentry, handler->name, value, size, flags); + if (!err) + ovl_copyattr(ovl_inode_real(inode, NULL), inode); + + return err; out_acl_release: posix_acl_release(acl); From 0eb45fc3bb7a2cf9c9c93d9e95986a841e5f4625 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Mon, 22 Aug 2016 17:52:55 +0200 Subject: [PATCH 501/531] ovl: Switch to generic_getxattr Now that overlayfs has xattr handlers for iop->{set,remove}xattr, use those same handlers for iop->getxattr as well. Signed-off-by: Andreas Gruenbacher Signed-off-by: Miklos Szeredi --- fs/overlayfs/dir.c | 2 +- fs/overlayfs/inode.c | 11 ++++------- fs/overlayfs/overlayfs.h | 4 ++-- fs/overlayfs/super.c | 26 ++++++++++++++++++++++++++ 4 files changed, 33 insertions(+), 10 deletions(-) diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 791c6a209656..1560fdc09a5f 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -1004,7 +1004,7 @@ const struct inode_operations ovl_dir_inode_operations = { .permission = ovl_permission, .getattr = ovl_dir_getattr, .setxattr = generic_setxattr, - .getxattr = ovl_getxattr, + .getxattr = generic_getxattr, .listxattr = ovl_listxattr, .removexattr = generic_removexattr, .get_acl = ovl_get_acl, diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 94bca710e6d2..1878591f6a2d 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -238,16 +238,13 @@ int ovl_xattr_set(struct dentry *dentry, const char *name, const void *value, return err; } -ssize_t ovl_getxattr(struct dentry *dentry, struct inode *inode, - const char *name, void *value, size_t size) +int ovl_xattr_get(struct dentry *dentry, const char *name, + void *value, size_t size) { struct dentry *realdentry = ovl_dentry_real(dentry); ssize_t res; const struct cred *old_cred; - if (ovl_is_private_xattr(name)) - return -ENODATA; - old_cred = ovl_override_creds(dentry->d_sb); res = vfs_getxattr(realdentry, name, value, size); revert_creds(old_cred); @@ -368,7 +365,7 @@ static const struct inode_operations ovl_file_inode_operations = { .permission = ovl_permission, .getattr = ovl_getattr, .setxattr = generic_setxattr, - .getxattr = ovl_getxattr, + .getxattr = generic_getxattr, .listxattr = ovl_listxattr, .removexattr = generic_removexattr, .get_acl = ovl_get_acl, @@ -381,7 +378,7 @@ static const struct inode_operations ovl_symlink_inode_operations = { .readlink = ovl_readlink, .getattr = ovl_getattr, .setxattr = generic_setxattr, - .getxattr = ovl_getxattr, + .getxattr = generic_getxattr, .listxattr = ovl_listxattr, .removexattr = generic_removexattr, .update_time = ovl_update_time, diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 5769aaf151a3..5813ccff8cd9 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -187,8 +187,8 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr); int ovl_permission(struct inode *inode, int mask); int ovl_xattr_set(struct dentry *dentry, const char *name, const void *value, size_t size, int flags); -ssize_t ovl_getxattr(struct dentry *dentry, struct inode *inode, - const char *name, void *value, size_t size); +int ovl_xattr_get(struct dentry *dentry, const char *name, + void *value, size_t size); ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size); struct posix_acl *ovl_get_acl(struct inode *inode, int type); int ovl_open_maybe_copy_up(struct dentry *dentry, unsigned int file_flags); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index cba2c9fea98c..a4585f961bf9 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -986,6 +986,14 @@ static unsigned int ovl_split_lowerdirs(char *str) return ctr; } +static int __maybe_unused +ovl_posix_acl_xattr_get(const struct xattr_handler *handler, + struct dentry *dentry, struct inode *inode, + const char *name, void *buffer, size_t size) +{ + return ovl_xattr_get(dentry, handler->name, buffer, size); +} + static int __maybe_unused ovl_posix_acl_xattr_set(const struct xattr_handler *handler, struct dentry *dentry, struct inode *inode, @@ -1029,6 +1037,13 @@ ovl_posix_acl_xattr_set(const struct xattr_handler *handler, return err; } +static int ovl_own_xattr_get(const struct xattr_handler *handler, + struct dentry *dentry, struct inode *inode, + const char *name, void *buffer, size_t size) +{ + return -EPERM; +} + static int ovl_own_xattr_set(const struct xattr_handler *handler, struct dentry *dentry, struct inode *inode, const char *name, const void *value, @@ -1037,6 +1052,13 @@ static int ovl_own_xattr_set(const struct xattr_handler *handler, return -EPERM; } +static int ovl_other_xattr_get(const struct xattr_handler *handler, + struct dentry *dentry, struct inode *inode, + const char *name, void *buffer, size_t size) +{ + return ovl_xattr_get(dentry, name, buffer, size); +} + static int ovl_other_xattr_set(const struct xattr_handler *handler, struct dentry *dentry, struct inode *inode, const char *name, const void *value, @@ -1049,6 +1071,7 @@ static const struct xattr_handler __maybe_unused ovl_posix_acl_access_xattr_handler = { .name = XATTR_NAME_POSIX_ACL_ACCESS, .flags = ACL_TYPE_ACCESS, + .get = ovl_posix_acl_xattr_get, .set = ovl_posix_acl_xattr_set, }; @@ -1056,16 +1079,19 @@ static const struct xattr_handler __maybe_unused ovl_posix_acl_default_xattr_handler = { .name = XATTR_NAME_POSIX_ACL_DEFAULT, .flags = ACL_TYPE_DEFAULT, + .get = ovl_posix_acl_xattr_get, .set = ovl_posix_acl_xattr_set, }; static const struct xattr_handler ovl_own_xattr_handler = { .prefix = OVL_XATTR_PREFIX, + .get = ovl_own_xattr_get, .set = ovl_own_xattr_set, }; static const struct xattr_handler ovl_other_xattr_handler = { .prefix = "", /* catch all */ + .get = ovl_other_xattr_get, .set = ovl_other_xattr_set, }; From 7cb35119d067191ce9ebc380a599db0b03cbd9d9 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 1 Sep 2016 11:12:00 +0200 Subject: [PATCH 502/531] ovl: listxattr: use strnlen() Be defensive about what underlying fs provides us in the returned xattr list buffer. If it's not properly null terminated, bail out with a warning insead of BUG. Signed-off-by: Miklos Szeredi Cc: --- fs/overlayfs/inode.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 1878591f6a2d..c75625c1efa3 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -255,7 +255,8 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size) { struct dentry *realdentry = ovl_dentry_real(dentry); ssize_t res; - int off; + size_t len; + char *s; const struct cred *old_cred; old_cred = ovl_override_creds(dentry->d_sb); @@ -265,17 +266,19 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size) return res; /* filter out private xattrs */ - for (off = 0; off < res;) { - char *s = list + off; - size_t slen = strlen(s) + 1; + for (s = list, len = res; len;) { + size_t slen = strnlen(s, len) + 1; - BUG_ON(off + slen > res); + /* underlying fs providing us with an broken xattr list? */ + if (WARN_ON(slen > len)) + return -EIO; + len -= slen; if (ovl_is_private_xattr(s)) { res -= slen; - memmove(s, s + slen, res - off); + memmove(s, s + slen, len); } else { - off += slen; + s += slen; } } From 026e5e0cc12474495515275d9c176ef823238c70 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 1 Sep 2016 11:12:00 +0200 Subject: [PATCH 503/531] ovl: update doc Some of the documented quirks no longer apply. Signed-off-by: Miklos Szeredi --- Documentation/filesystems/overlayfs.txt | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/Documentation/filesystems/overlayfs.txt b/Documentation/filesystems/overlayfs.txt index d6259c786316..bcbf9710e4af 100644 --- a/Documentation/filesystems/overlayfs.txt +++ b/Documentation/filesystems/overlayfs.txt @@ -183,12 +183,10 @@ The copy_up operation essentially creates a new, identical file and moves it over to the old name. The new file may be on a different filesystem, so both st_dev and st_ino of the file may change. -Any open files referring to this inode will access the old data and -metadata. Similarly any file locks obtained before copy_up will not -apply to the copied up file. +Any open files referring to this inode will access the old data. -On a file opened with O_RDONLY fchmod(2), fchown(2), futimesat(2) and -fsetxattr(2) will fail with EROFS. +Any file locks (and leases) obtained before copy_up will not apply +to the copied up file. If a file with multiple hard links is copied up, then this will "break" the link. Changes will not be propagated to other names From 3dc09ec895f098cedd789a620c90ff1bf7f779a1 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 24 Aug 2016 11:57:52 -0400 Subject: [PATCH 504/531] Btrfs: kill invalid ASSERT() in process_all_refs() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Suppose you have the following tree in snap1 on a file system mounted with -o inode_cache so that inode numbers are recycled └── [ 258] a └── [ 257] b and then you remove b, rename a to c, and then re-create b in c so you have the following tree └── [ 258] c └── [ 257] b and then you try to do an incremental send you will hit ASSERT(pending_move == 0); in process_all_refs(). This is because we assume that any recycling of inodes will not have a pending change in our path, which isn't the case. This is the case for the DELETE side, since we want to remove the old file using the old path, but on the create side we could have a pending move and need to do the normal pending rename dance. So remove this ASSERT() and put a comment about why we ignore pending_move. Thanks, Signed-off-by: Josef Bacik Signed-off-by: David Sterba --- fs/btrfs/send.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index efe129fe2678..a87675ffd02b 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -4268,10 +4268,12 @@ static int process_all_refs(struct send_ctx *sctx, } btrfs_release_path(path); + /* + * We don't actually care about pending_move as we are simply + * re-creating this inode and will be rename'ing it into place once we + * rename the parent directory. + */ ret = process_recorded_refs(sctx, &pending_move); - /* Only applicable to an incremental send. */ - ASSERT(pending_move == 0); - out: btrfs_free_path(path); return ret; From a9b1fc851db054ddec703dc7951ed00620600b26 Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Wed, 31 Aug 2016 16:43:33 -0700 Subject: [PATCH 505/531] Btrfs: fix endless loop in balancing block groups Qgroup function may overwrite the saved error 'err' with 0 in case quota is not enabled, and this ends up with a endless loop in balance because we keep going back to balance the same block group. It really should use 'ret' instead. Signed-off-by: Liu Bo Reviewed-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/relocation.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 8a2c2a07987b..c0c13dc6fe12 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -4200,9 +4200,11 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc) err = PTR_ERR(trans); goto out_free; } - err = qgroup_fix_relocated_data_extents(trans, rc); - if (err < 0) { - btrfs_abort_transaction(trans, err); + ret = qgroup_fix_relocated_data_extents(trans, rc); + if (ret < 0) { + btrfs_abort_transaction(trans, ret); + if (!err) + err = ret; goto out_free; } btrfs_commit_transaction(trans, rc->extent_root); From e0af24849efb0eea572cf22d22bb65d164cb8a6f Mon Sep 17 00:00:00 2001 From: Wang Xiaoguang Date: Wed, 31 Aug 2016 19:46:16 +0800 Subject: [PATCH 506/531] btrfs: fix one bug that process may endlessly wait for ticket in wait_reserve_ticket() If can_overcommit() in btrfs_calc_reclaim_metadata_size() returns true, btrfs_async_reclaim_metadata_space() will not reclaim metadata space, just return directly and also forget to wake up process which are waiting for their tickets, so these processes will wait endlessly. Fstests case generic/172 with mount option "-o compress=lzo" have revealed this bug in my test machine. Here if we have tickets to handle, we must handle them first. Signed-off-by: Wang Xiaoguang Reviewed-by: Josef Bacik Signed-off-by: David Sterba --- fs/btrfs/extent-tree.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 60d4ae7ce974..64676a16d32a 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4901,11 +4901,6 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_root *root, u64 expected; u64 to_reclaim = 0; - to_reclaim = min_t(u64, num_online_cpus() * SZ_1M, SZ_16M); - if (can_overcommit(root, space_info, to_reclaim, - BTRFS_RESERVE_FLUSH_ALL)) - return 0; - list_for_each_entry(ticket, &space_info->tickets, list) to_reclaim += ticket->bytes; list_for_each_entry(ticket, &space_info->priority_tickets, list) @@ -4913,6 +4908,11 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_root *root, if (to_reclaim) return to_reclaim; + to_reclaim = min_t(u64, num_online_cpus() * SZ_1M, SZ_16M); + if (can_overcommit(root, space_info, to_reclaim, + BTRFS_RESERVE_FLUSH_ALL)) + return 0; + used = space_info->bytes_used + space_info->bytes_reserved + space_info->bytes_pinned + space_info->bytes_readonly + space_info->bytes_may_use; From 6b4e3181d7bd5ca5ab6f45929e4a5ffa7ab4ab7f Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Thu, 1 Sep 2016 16:14:41 -0700 Subject: [PATCH 507/531] mm, oom: prevent premature OOM killer invocation for high order request There have been several reports about pre-mature OOM killer invocation in 4.7 kernel when order-2 allocation request (for the kernel stack) invoked OOM killer even during basic workloads (light IO or even kernel compile on some filesystems). In all reported cases the memory is fragmented and there are no order-2+ pages available. There is usually a large amount of slab memory (usually dentries/inodes) and further debugging has shown that there are way too many unmovable blocks which are skipped during the compaction. Multiple reporters have confirmed that the current linux-next which includes [1] and [2] helped and OOMs are not reproducible anymore. A simpler fix for the late rc and stable is to simply ignore the compaction feedback and retry as long as there is a reclaim progress and we are not getting OOM for order-0 pages. We already do that for CONFING_COMPACTION=n so let's reuse the same code when compaction is enabled as well. [1] http://lkml.kernel.org/r/20160810091226.6709-1-vbabka@suse.cz [2] http://lkml.kernel.org/r/f7a9ea9d-bb88-bfd6-e340-3a933559305a@suse.cz Fixes: 0a0337e0d1d1 ("mm, oom: rework oom detection") Link: http://lkml.kernel.org/r/20160823074339.GB23577@dhcp22.suse.cz Signed-off-by: Michal Hocko Tested-by: Olaf Hering Tested-by: Ralf-Peter Rohbeck Cc: Markus Trippelsdorf Cc: Arkadiusz Miskiewicz Cc: Ralf-Peter Rohbeck Cc: Jiri Slaby Cc: Vlastimil Babka Cc: Joonsoo Kim Cc: Tetsuo Handa Cc: David Rientjes Cc: [4.7.x] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 51 ++----------------------------------------------- 1 file changed, 2 insertions(+), 49 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 3fbe73a6fe4b..7791a03f8deb 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3137,54 +3137,6 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, return NULL; } -static inline bool -should_compact_retry(struct alloc_context *ac, int order, int alloc_flags, - enum compact_result compact_result, - enum compact_priority *compact_priority, - int compaction_retries) -{ - int max_retries = MAX_COMPACT_RETRIES; - - if (!order) - return false; - - /* - * compaction considers all the zone as desperately out of memory - * so it doesn't really make much sense to retry except when the - * failure could be caused by insufficient priority - */ - if (compaction_failed(compact_result)) { - if (*compact_priority > MIN_COMPACT_PRIORITY) { - (*compact_priority)--; - return true; - } - return false; - } - - /* - * make sure the compaction wasn't deferred or didn't bail out early - * due to locks contention before we declare that we should give up. - * But do not retry if the given zonelist is not suitable for - * compaction. - */ - if (compaction_withdrawn(compact_result)) - return compaction_zonelist_suitable(ac, order, alloc_flags); - - /* - * !costly requests are much more important than __GFP_REPEAT - * costly ones because they are de facto nofail and invoke OOM - * killer to move on while costly can fail and users are ready - * to cope with that. 1/4 retries is rather arbitrary but we - * would need much more detailed feedback from compaction to - * make a better decision. - */ - if (order > PAGE_ALLOC_COSTLY_ORDER) - max_retries /= 4; - if (compaction_retries <= max_retries) - return true; - - return false; -} #else static inline struct page * __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, @@ -3195,6 +3147,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, return NULL; } +#endif /* CONFIG_COMPACTION */ + static inline bool should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_flags, enum compact_result compact_result, @@ -3221,7 +3175,6 @@ should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_fla } return false; } -#endif /* CONFIG_COMPACTION */ /* Perform direct synchronous page reclaim */ static int From 070c43eea5043e950daa423707ae3c77e2f48edb Mon Sep 17 00:00:00 2001 From: Thiago Jung Bauermann Date: Thu, 1 Sep 2016 16:14:44 -0700 Subject: [PATCH 508/531] kexec: fix double-free when failing to relocate the purgatory If kexec_apply_relocations fails, kexec_load_purgatory frees pi->sechdrs and pi->purgatory_buf. This is redundant, because in case of error kimage_file_prepare_segments calls kimage_file_post_load_cleanup, which will also free those buffers. This causes two warnings like the following, one for pi->sechdrs and the other for pi->purgatory_buf: kexec-bzImage64: Loading purgatory failed ------------[ cut here ]------------ WARNING: CPU: 1 PID: 2119 at mm/vmalloc.c:1490 __vunmap+0xc1/0xd0 Trying to vfree() nonexistent vm area (ffffc90000e91000) Modules linked in: CPU: 1 PID: 2119 Comm: kexec Not tainted 4.8.0-rc3+ #5 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: dump_stack+0x4d/0x65 __warn+0xcb/0xf0 warn_slowpath_fmt+0x4f/0x60 ? find_vmap_area+0x19/0x70 ? kimage_file_post_load_cleanup+0x47/0xb0 __vunmap+0xc1/0xd0 vfree+0x2e/0x70 kimage_file_post_load_cleanup+0x5e/0xb0 SyS_kexec_file_load+0x448/0x680 ? putname+0x54/0x60 ? do_sys_open+0x190/0x1f0 entry_SYSCALL_64_fastpath+0x13/0x8f ---[ end trace 158bb74f5950ca2b ]--- Fix by setting pi->sechdrs an pi->purgatory_buf to NULL, since vfree won't try to free a NULL pointer. Link: http://lkml.kernel.org/r/1472083546-23683-1-git-send-email-bauerman@linux.vnet.ibm.com Signed-off-by: Thiago Jung Bauermann Acked-by: Baoquan He Cc: "Eric W. Biederman" Cc: Vivek Goyal Cc: Dave Young Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/kexec_file.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 503bc2d348e5..037c321c5618 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -887,7 +887,10 @@ int kexec_load_purgatory(struct kimage *image, unsigned long min, return 0; out: vfree(pi->sechdrs); + pi->sechdrs = NULL; + vfree(pi->purgatory_buf); + pi->purgatory_buf = NULL; return ret; } From 236dec051078a8691950f56949612b4b74107e48 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 1 Sep 2016 16:14:47 -0700 Subject: [PATCH 509/531] kconfig: tinyconfig: provide whole choice blocks to avoid warnings Using "make tinyconfig" produces a couple of annoying warnings that show up for build test machines all the time: .config:966:warning: override: NOHIGHMEM changes choice state .config:965:warning: override: SLOB changes choice state .config:963:warning: override: KERNEL_XZ changes choice state .config:962:warning: override: CC_OPTIMIZE_FOR_SIZE changes choice state .config:933:warning: override: SLOB changes choice state .config:930:warning: override: CC_OPTIMIZE_FOR_SIZE changes choice state .config:870:warning: override: SLOB changes choice state .config:868:warning: override: KERNEL_XZ changes choice state .config:867:warning: override: CC_OPTIMIZE_FOR_SIZE changes choice state I've made a previous attempt at fixing them and we discussed a number of alternatives. I tried changing the Makefile to use "merge_config.sh -n $(fragment-list)" but couldn't get that to work properly. This is yet another approach, based on the observation that we do want to see a warning for conflicting 'choice' options, and that we can simply make them non-conflicting by listing all other options as disabled. This is a trivial patch that we can apply independent of plans for other changes. Link: http://lkml.kernel.org/r/20160829214952.1334674-2-arnd@arndb.de Link: https://storage.kernelci.org/mainline/v4.7-rc6/x86-tinyconfig/build.log https://patchwork.kernel.org/patch/9212749/ Signed-off-by: Arnd Bergmann Reviewed-by: Josh Triplett Reviewed-by: Masahiro Yamada Acked-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/configs/tiny.config | 2 ++ kernel/configs/tiny.config | 8 ++++++++ 2 files changed, 10 insertions(+) diff --git a/arch/x86/configs/tiny.config b/arch/x86/configs/tiny.config index 4e2ecfa23c15..4b429df40d7a 100644 --- a/arch/x86/configs/tiny.config +++ b/arch/x86/configs/tiny.config @@ -1 +1,3 @@ CONFIG_NOHIGHMEM=y +# CONFIG_HIGHMEM4G is not set +# CONFIG_HIGHMEM64G is not set diff --git a/kernel/configs/tiny.config b/kernel/configs/tiny.config index c2de56ab0fce..7fa0c4ae6394 100644 --- a/kernel/configs/tiny.config +++ b/kernel/configs/tiny.config @@ -1,4 +1,12 @@ +# CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE is not set CONFIG_CC_OPTIMIZE_FOR_SIZE=y +# CONFIG_KERNEL_GZIP is not set +# CONFIG_KERNEL_BZIP2 is not set +# CONFIG_KERNEL_LZMA is not set CONFIG_KERNEL_XZ=y +# CONFIG_KERNEL_LZO is not set +# CONFIG_KERNEL_LZ4 is not set CONFIG_OPTIMIZE_INLINING=y +# CONFIG_SLAB is not set +# CONFIG_SLUB is not set CONFIG_SLOB=y From ed76b7a131f41c91b0c725d472f9b969d75ce888 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 1 Sep 2016 16:14:50 -0700 Subject: [PATCH 510/531] lib/test_hash.c: fix warning in two-dimensional array init lib/test_hash.c: In function 'test_hash_init': lib/test_hash.c:146:2: warning: missing braces around initializer [-Wmissing-braces] Fixes: 468a9428521e7d00 (": Add support for architecture-specific functions") Link: http://lkml.kernel.org/r/20160829214952.1334674-3-arnd@arndb.de Signed-off-by: Geert Uytterhoeven Signed-off-by: Arnd Bergmann Acked-by: George Spelvin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/test_hash.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/test_hash.c b/lib/test_hash.c index 66c5fc8351e8..81702ee4c41c 100644 --- a/lib/test_hash.c +++ b/lib/test_hash.c @@ -143,7 +143,7 @@ static int __init test_hash_init(void) { char buf[SIZE+1]; - u32 string_or = 0, hash_or[2][33] = { 0 }; + u32 string_or = 0, hash_or[2][33] = { { 0, } }; unsigned tests = 0; unsigned long long h64 = 0; int i, j; From e6173ba42bbdba05fd4f3021c0beda0506271507 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 1 Sep 2016 16:14:53 -0700 Subject: [PATCH 511/531] lib/test_hash.c: fix warning in preprocessor symbol evaluation Some versions of gcc don't like tests for the value of an undefined preprocessor symbol, even in the #else branch of an #ifndef: lib/test_hash.c:224:7: warning: "HAVE_ARCH__HASH_32" is not defined [-Wundef] #elif HAVE_ARCH__HASH_32 != 1 ^ lib/test_hash.c:229:7: warning: "HAVE_ARCH_HASH_32" is not defined [-Wundef] #elif HAVE_ARCH_HASH_32 != 1 ^ lib/test_hash.c:234:7: warning: "HAVE_ARCH_HASH_64" is not defined [-Wundef] #elif HAVE_ARCH_HASH_64 != 1 ^ Seen with gcc 4.9, not seen with 4.1.2. Change the logic to only check the value inside an #ifdef to fix this. Fixes: 468a9428521e7d00 (": Add support for architecture-specific functions") Link: http://lkml.kernel.org/r/20160829214952.1334674-4-arnd@arndb.de Signed-off-by: Geert Uytterhoeven Signed-off-by: Arnd Bergmann Acked-by: George Spelvin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/test_hash.c | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) diff --git a/lib/test_hash.c b/lib/test_hash.c index 81702ee4c41c..cac20c5fb304 100644 --- a/lib/test_hash.c +++ b/lib/test_hash.c @@ -219,21 +219,27 @@ test_hash_init(void) } /* Issue notices about skipped tests. */ -#ifndef HAVE_ARCH__HASH_32 - pr_info("__hash_32() has no arch implementation to test."); -#elif HAVE_ARCH__HASH_32 != 1 +#ifdef HAVE_ARCH__HASH_32 +#if HAVE_ARCH__HASH_32 != 1 pr_info("__hash_32() is arch-specific; not compared to generic."); #endif -#ifndef HAVE_ARCH_HASH_32 - pr_info("hash_32() has no arch implementation to test."); -#elif HAVE_ARCH_HASH_32 != 1 +#else + pr_info("__hash_32() has no arch implementation to test."); +#endif +#ifdef HAVE_ARCH_HASH_32 +#if HAVE_ARCH_HASH_32 != 1 pr_info("hash_32() is arch-specific; not compared to generic."); #endif -#ifndef HAVE_ARCH_HASH_64 - pr_info("hash_64() has no arch implementation to test."); -#elif HAVE_ARCH_HASH_64 != 1 +#else + pr_info("hash_32() has no arch implementation to test."); +#endif +#ifdef HAVE_ARCH_HASH_64 +#if HAVE_ARCH_HASH_64 != 1 pr_info("hash_64() is arch-specific; not compared to generic."); #endif +#else + pr_info("hash_64() has no arch implementation to test."); +#endif pr_notice("%u tests passed.", tests); From 6aa303defb7454a2520c4ddcdf6b081f62a15890 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 1 Sep 2016 16:14:55 -0700 Subject: [PATCH 512/531] mm, vmscan: only allocate and reclaim from zones with pages managed by the buddy allocator Firmware Assisted Dump (FA_DUMP) on ppc64 reserves substantial amounts of memory when booting a secondary kernel. Srikar Dronamraju reported that multiple nodes may have no memory managed by the buddy allocator but still return true for populated_zone(). Commit 1d82de618ddd ("mm, vmscan: make kswapd reclaim in terms of nodes") was reported to cause kswapd to spin at 100% CPU usage when fadump was enabled. The old code happened to deal with the situation of a populated node with zero free pages by co-incidence but the current code tries to reclaim populated zones without realising that is impossible. We cannot just convert populated_zone() as many existing users really need to check for present_pages. This patch introduces a managed_zone() helper and uses it in the few cases where it is critical that the check is made for managed pages -- zonelist construction and page reclaim. Link: http://lkml.kernel.org/r/20160831195104.GB8119@techsingularity.net Signed-off-by: Mel Gorman Reported-by: Srikar Dronamraju Tested-by: Srikar Dronamraju Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 16 ++++++++++++++-- mm/page_alloc.c | 4 ++-- mm/vmscan.c | 22 +++++++++++----------- 3 files changed, 27 insertions(+), 15 deletions(-) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index d572b78b65e1..7f2ae99e5daf 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -828,9 +828,21 @@ unsigned long __init node_memmap_size_bytes(int, unsigned long, unsigned long); */ #define zone_idx(zone) ((zone) - (zone)->zone_pgdat->node_zones) -static inline int populated_zone(struct zone *zone) +/* + * Returns true if a zone has pages managed by the buddy allocator. + * All the reclaim decisions have to use this function rather than + * populated_zone(). If the whole zone is reserved then we can easily + * end up with populated_zone() && !managed_zone(). + */ +static inline bool managed_zone(struct zone *zone) { - return (!!zone->present_pages); + return zone->managed_pages; +} + +/* Returns true if a zone has memory */ +static inline bool populated_zone(struct zone *zone) +{ + return zone->present_pages; } extern int movable_zone; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7791a03f8deb..a2214c64ed3c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4360,7 +4360,7 @@ static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist, do { zone_type--; zone = pgdat->node_zones + zone_type; - if (populated_zone(zone)) { + if (managed_zone(zone)) { zoneref_set_zone(zone, &zonelist->_zonerefs[nr_zones++]); check_highest_zone(zone_type); @@ -4598,7 +4598,7 @@ static void build_zonelists_in_zone_order(pg_data_t *pgdat, int nr_nodes) for (j = 0; j < nr_nodes; j++) { node = node_order[j]; z = &NODE_DATA(node)->node_zones[zone_type]; - if (populated_zone(z)) { + if (managed_zone(z)) { zoneref_set_zone(z, &zonelist->_zonerefs[pos++]); check_highest_zone(zone_type); diff --git a/mm/vmscan.c b/mm/vmscan.c index 374d95d04178..b1e12a1ea9cf 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1665,7 +1665,7 @@ static bool inactive_reclaimable_pages(struct lruvec *lruvec, for (zid = sc->reclaim_idx; zid >= 0; zid--) { zone = &pgdat->node_zones[zid]; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; if (zone_page_state_snapshot(zone, NR_ZONE_LRU_BASE + @@ -2036,7 +2036,7 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file, struct zone *zone = &pgdat->node_zones[zid]; unsigned long inactive_zone, active_zone; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; inactive_zone = zone_page_state(zone, @@ -2171,7 +2171,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, for (z = 0; z < MAX_NR_ZONES; z++) { struct zone *zone = &pgdat->node_zones[z]; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; total_high_wmark += high_wmark_pages(zone); @@ -2510,7 +2510,7 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat, /* If compaction would go ahead or the allocation would succeed, stop */ for (z = 0; z <= sc->reclaim_idx; z++) { struct zone *zone = &pgdat->node_zones[z]; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; switch (compaction_suitable(zone, sc->order, 0, sc->reclaim_idx)) { @@ -2840,7 +2840,7 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat) for (i = 0; i <= ZONE_NORMAL; i++) { zone = &pgdat->node_zones[i]; - if (!populated_zone(zone) || + if (!managed_zone(zone) || pgdat_reclaimable_pages(pgdat) == 0) continue; @@ -3141,7 +3141,7 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int classzone_idx) for (i = 0; i <= classzone_idx; i++) { struct zone *zone = pgdat->node_zones + i; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; if (!zone_balanced(zone, order, classzone_idx)) @@ -3169,7 +3169,7 @@ static bool kswapd_shrink_node(pg_data_t *pgdat, sc->nr_to_reclaim = 0; for (z = 0; z <= sc->reclaim_idx; z++) { zone = pgdat->node_zones + z; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; sc->nr_to_reclaim += max(high_wmark_pages(zone), SWAP_CLUSTER_MAX); @@ -3242,7 +3242,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) if (buffer_heads_over_limit) { for (i = MAX_NR_ZONES - 1; i >= 0; i--) { zone = pgdat->node_zones + i; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; sc.reclaim_idx = i; @@ -3262,7 +3262,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) */ for (i = classzone_idx; i >= 0; i--) { zone = pgdat->node_zones + i; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; if (zone_balanced(zone, sc.order, classzone_idx)) @@ -3508,7 +3508,7 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx) pg_data_t *pgdat; int z; - if (!populated_zone(zone)) + if (!managed_zone(zone)) return; if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL)) @@ -3522,7 +3522,7 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx) /* Only wake kswapd if all zones are unbalanced */ for (z = 0; z <= classzone_idx; z++) { zone = pgdat->node_zones + z; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; if (zone_balanced(zone, order, classzone_idx)) From 8a793bea2745d9876030f892a84fc8be180f2e78 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Thu, 1 Sep 2016 16:14:58 -0700 Subject: [PATCH 513/531] drivers/scsi/wd719x.c: remove last declaration using DEFINE_PCI_DEVICE_TABLE Convert it to the preferred const struct pci_device_id instead. Link: http://lkml.kernel.org/r/95c5e4100c3cd4eda643624f5b70e8d7abceb86c.1472660229.git.joe@perches.com Signed-off-by: Joe Perches Reviewed-by: Bart Van Assche Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/scsi/wd719x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/wd719x.c b/drivers/scsi/wd719x.c index e3da1a2fdb66..2a9da2e0ea6b 100644 --- a/drivers/scsi/wd719x.c +++ b/drivers/scsi/wd719x.c @@ -962,7 +962,7 @@ static void wd719x_pci_remove(struct pci_dev *pdev) scsi_host_put(sh); } -static DEFINE_PCI_DEVICE_TABLE(wd719x_pci_table) = { +static const struct pci_device_id wd719x_pci_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_WD, 0x3296) }, {} }; From 7e932159901183283cd82d797bc9a7c681e48e9c Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Thu, 1 Sep 2016 16:15:01 -0700 Subject: [PATCH 514/531] treewide: remove references to the now unnecessary DEFINE_PCI_DEVICE_TABLE It's been eliminated from the sources, remove it from everywhere else. Link: http://lkml.kernel.org/r/076eff466fd7edb550c25c8b25d76924ca0eba62.1472660229.git.joe@perches.com Signed-off-by: Joe Perches Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Cc: Bjorn Helgaas Cc: Andy Whitcroft Cc: Jonathan Corbet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/PCI/pci.txt | 1 - include/linux/pci.h | 9 --------- scripts/checkpatch.pl | 9 --------- scripts/tags.sh | 1 - 4 files changed, 20 deletions(-) diff --git a/Documentation/PCI/pci.txt b/Documentation/PCI/pci.txt index 123881f62219..77f49dc5be23 100644 --- a/Documentation/PCI/pci.txt +++ b/Documentation/PCI/pci.txt @@ -124,7 +124,6 @@ initialization with a pointer to a structure describing the driver The ID table is an array of struct pci_device_id entries ending with an all-zero entry. Definitions with static const are generally preferred. -Use of the deprecated macro DEFINE_PCI_DEVICE_TABLE should be avoided. Each entry consists of: diff --git a/include/linux/pci.h b/include/linux/pci.h index fbc1fa625c3e..0ab835965669 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -682,15 +682,6 @@ struct pci_driver { #define to_pci_driver(drv) container_of(drv, struct pci_driver, driver) -/** - * DEFINE_PCI_DEVICE_TABLE - macro used to describe a pci device table - * @_table: device table name - * - * This macro is deprecated and should not be used in new code. - */ -#define DEFINE_PCI_DEVICE_TABLE(_table) \ - const struct pci_device_id _table[] - /** * PCI_DEVICE - macro used to describe a specific pci device * @vend: the 16 bit PCI Vendor ID diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 4de3cc42fc50..206a6b346a8d 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -3570,15 +3570,6 @@ sub process { } } -# check for uses of DEFINE_PCI_DEVICE_TABLE - if ($line =~ /\bDEFINE_PCI_DEVICE_TABLE\s*\(\s*(\w+)\s*\)\s*=/) { - if (WARN("DEFINE_PCI_DEVICE_TABLE", - "Prefer struct pci_device_id over deprecated DEFINE_PCI_DEVICE_TABLE\n" . $herecurr) && - $fix) { - $fixed[$fixlinenr] =~ s/\b(?:static\s+|)DEFINE_PCI_DEVICE_TABLE\s*\(\s*(\w+)\s*\)\s*=\s*/static const struct pci_device_id $1\[\] = /; - } - } - # check for new typedefs, only function parameters and sparse annotations # make sense. if ($line =~ /\btypedef\s/ && diff --git a/scripts/tags.sh b/scripts/tags.sh index ed7eef24ef89..b3775a9604ea 100755 --- a/scripts/tags.sh +++ b/scripts/tags.sh @@ -206,7 +206,6 @@ regex_c=( '/\ Date: Thu, 1 Sep 2016 16:15:04 -0700 Subject: [PATCH 515/531] printk/nmi: avoid direct printk()-s from __printk_nmi_flush() __printk_nmi_flush() can be called from nmi_panic(), therefore it has to test whether it's executed in NMI context and thus must route the messages through deferred printk() or via direct printk(). This is to avoid potential deadlocks, as described in commit cf9b1106c81c ("printk/nmi: flush NMI messages on the system panic"). However there remain two places where __printk_nmi_flush() does unconditional direct printk() calls: - pr_err("printk_nmi_flush: internal error ...") - pr_cont("\n") Factor out print_nmi_seq_line() parts into a new printk_nmi_flush_line() function, which takes care of in_nmi(), and use it in __printk_nmi_flush() for printing and error-reporting. Link: http://lkml.kernel.org/r/20160830161354.581-1-sergey.senozhatsky@gmail.com Signed-off-by: Sergey Senozhatsky Cc: Petr Mladek Cc: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/printk/nmi.c | 38 +++++++++++++++++++++++--------------- 1 file changed, 23 insertions(+), 15 deletions(-) diff --git a/kernel/printk/nmi.c b/kernel/printk/nmi.c index b69eb8a2876f..16bab471c7e2 100644 --- a/kernel/printk/nmi.c +++ b/kernel/printk/nmi.c @@ -99,26 +99,32 @@ static int vprintk_nmi(const char *fmt, va_list args) return add; } -/* - * printk one line from the temporary buffer from @start index until - * and including the @end index. - */ -static void print_nmi_seq_line(struct nmi_seq_buf *s, int start, int end) +static void printk_nmi_flush_line(const char *text, int len) { - const char *buf = s->buffer + start; - /* * The buffers are flushed in NMI only on panic. The messages must * go only into the ring buffer at this stage. Consoles will get * explicitly called later when a crashdump is not generated. */ if (in_nmi()) - printk_deferred("%.*s", (end - start) + 1, buf); + printk_deferred("%.*s", len, text); else - printk("%.*s", (end - start) + 1, buf); + printk("%.*s", len, text); } +/* + * printk one line from the temporary buffer from @start index until + * and including the @end index. + */ +static void printk_nmi_flush_seq_line(struct nmi_seq_buf *s, + int start, int end) +{ + const char *buf = s->buffer + start; + + printk_nmi_flush_line(buf, (end - start) + 1); +} + /* * Flush data from the associated per_CPU buffer. The function * can be called either via IRQ work or independently. @@ -150,9 +156,11 @@ static void __printk_nmi_flush(struct irq_work *work) * the buffer an unexpected way. If we printed something then * @len must only increase. */ - if (i && i >= len) - pr_err("printk_nmi_flush: internal error: i=%d >= len=%zu\n", - i, len); + if (i && i >= len) { + const char *msg = "printk_nmi_flush: internal error\n"; + + printk_nmi_flush_line(msg, strlen(msg)); + } if (!len) goto out; /* Someone else has already flushed the buffer. */ @@ -166,14 +174,14 @@ static void __printk_nmi_flush(struct irq_work *work) /* Print line by line. */ for (; i < size; i++) { if (s->buffer[i] == '\n') { - print_nmi_seq_line(s, last_i, i); + printk_nmi_flush_seq_line(s, last_i, i); last_i = i + 1; } } /* Check if there was a partial line. */ if (last_i < size) { - print_nmi_seq_line(s, last_i, size - 1); - pr_cont("\n"); + printk_nmi_flush_seq_line(s, last_i, size - 1); + printk_nmi_flush_line("\n", strlen("\n")); } /* From c11600e4fed67ae4cd6a8096936afd445410e8ed Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Thu, 1 Sep 2016 16:15:07 -0700 Subject: [PATCH 516/531] mm, mempolicy: task->mempolicy must be NULL before dropping final reference KASAN allocates memory from the page allocator as part of kmem_cache_free(), and that can reference current->mempolicy through any number of allocation functions. It needs to be NULL'd out before the final reference is dropped to prevent a use-after-free bug: BUG: KASAN: use-after-free in alloc_pages_current+0x363/0x370 at addr ffff88010b48102c CPU: 0 PID: 15425 Comm: trinity-c2 Not tainted 4.8.0-rc2+ #140 ... Call Trace: dump_stack kasan_object_err kasan_report_error __asan_report_load2_noabort alloc_pages_current <-- use after free depot_save_stack save_stack kasan_slab_free kmem_cache_free __mpol_put <-- free do_exit This patch sets current->mempolicy to NULL before dropping the final reference. Link: http://lkml.kernel.org/r/alpine.DEB.2.10.1608301442180.63329@chino.kir.corp.google.com Fixes: cd11016e5f52 ("mm, kasan: stackdepot implementation. Enable stackdepot for SLAB") Signed-off-by: David Rientjes Reported-by: Vegard Nossum Acked-by: Andrey Ryabinin Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: [4.6+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 4 ++++ kernel/exit.c | 7 +------ mm/mempolicy.c | 17 +++++++++++++++++ 3 files changed, 22 insertions(+), 6 deletions(-) diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 4429d255c8ab..5e5b2969d931 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -195,6 +195,7 @@ static inline bool vma_migratable(struct vm_area_struct *vma) } extern int mpol_misplaced(struct page *, struct vm_area_struct *, unsigned long); +extern void mpol_put_task_policy(struct task_struct *); #else @@ -297,5 +298,8 @@ static inline int mpol_misplaced(struct page *page, struct vm_area_struct *vma, return -1; /* no node preference */ } +static inline void mpol_put_task_policy(struct task_struct *task) +{ +} #endif /* CONFIG_NUMA */ #endif diff --git a/kernel/exit.c b/kernel/exit.c index 2f974ae042a6..091a78be3b09 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -848,12 +848,7 @@ void do_exit(long code) TASKS_RCU(preempt_enable()); exit_notify(tsk, group_dead); proc_exit_connector(tsk); -#ifdef CONFIG_NUMA - task_lock(tsk); - mpol_put(tsk->mempolicy); - tsk->mempolicy = NULL; - task_unlock(tsk); -#endif + mpol_put_task_policy(tsk); #ifdef CONFIG_FUTEX if (unlikely(current->pi_state_cache)) kfree(current->pi_state_cache); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index d8c4e38fb5f4..2da72a5b6ecc 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2336,6 +2336,23 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long return ret; } +/* + * Drop the (possibly final) reference to task->mempolicy. It needs to be + * dropped after task->mempolicy is set to NULL so that any allocation done as + * part of its kmem_cache_free(), such as by KASAN, doesn't reference a freed + * policy. + */ +void mpol_put_task_policy(struct task_struct *task) +{ + struct mempolicy *pol; + + task_lock(task); + pol = task->mempolicy; + task->mempolicy = NULL; + task_unlock(task); + mpol_put(pol); +} + static void sp_delete(struct shared_policy *sp, struct sp_node *n) { pr_debug("deleting %lx-l%lx\n", n->start, n->end); From c4e297386bd1621b83f6f7d58a729fb770597a91 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 1 Sep 2016 16:15:09 -0700 Subject: [PATCH 517/531] MAINTAINERS: Vladimir has moved vdavydov@{parallels,virtuozzo}.com will bounce from now on. Link: http://lkml.kernel.org/r/20160831180752.GB10353@esperanza Signed-off-by: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- .mailmap | 2 ++ MAINTAINERS | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/.mailmap b/.mailmap index 2a91c14c80bf..093a8ac9996e 100644 --- a/.mailmap +++ b/.mailmap @@ -158,6 +158,8 @@ Valdis Kletnieks Viresh Kumar Viresh Kumar Viresh Kumar +Vladimir Davydov +Vladimir Davydov Takashi YOSHII Yusuke Goda Gustavo Padovan diff --git a/MAINTAINERS b/MAINTAINERS index 71aa5daeae8f..d44be8ad997b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3247,7 +3247,7 @@ F: kernel/cpuset.c CONTROL GROUP - MEMORY RESOURCE CONTROLLER (MEMCG) M: Johannes Weiner M: Michal Hocko -M: Vladimir Davydov +M: Vladimir Davydov L: cgroups@vger.kernel.org L: linux-mm@kvack.org S: Maintained From 735f2770a770156100f534646158cb58cb8b2939 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Thu, 1 Sep 2016 16:15:13 -0700 Subject: [PATCH 518/531] kernel/fork: fix CLONE_CHILD_CLEARTID regression in nscd Commit fec1d0115240 ("[PATCH] Disable CLONE_CHILD_CLEARTID for abnormal exit") has caused a subtle regression in nscd which uses CLONE_CHILD_CLEARTID to clear the nscd_certainly_running flag in the shared databases, so that the clients are notified when nscd is restarted. Now, when nscd uses a non-persistent database, clients that have it mapped keep thinking the database is being updated by nscd, when in fact nscd has created a new (anonymous) one (for non-persistent databases it uses an unlinked file as backend). The original proposal for the CLONE_CHILD_CLEARTID change claimed (https://lkml.org/lkml/2006/10/25/233): : The NPTL library uses the CLONE_CHILD_CLEARTID flag on clone() syscalls : on behalf of pthread_create() library calls. This feature is used to : request that the kernel clear the thread-id in user space (at an address : provided in the syscall) when the thread disassociates itself from the : address space, which is done in mm_release(). : : Unfortunately, when a multi-threaded process incurs a core dump (such as : from a SIGSEGV), the core-dumping thread sends SIGKILL signals to all of : the other threads, which then proceed to clear their user-space tids : before synchronizing in exit_mm() with the start of core dumping. This : misrepresents the state of process's address space at the time of the : SIGSEGV and makes it more difficult for someone to debug NPTL and glibc : problems (misleading him/her to conclude that the threads had gone away : before the fault). : : The fix below is to simply avoid the CLONE_CHILD_CLEARTID action if a : core dump has been initiated. The resulting patch from Roland (https://lkml.org/lkml/2006/10/26/269) seems to have a larger scope than the original patch asked for. It seems that limitting the scope of the check to core dumping should work for SIGSEGV issue describe above. [Changelog partly based on Andreas' description] Fixes: fec1d0115240 ("[PATCH] Disable CLONE_CHILD_CLEARTID for abnormal exit") Link: http://lkml.kernel.org/r/1471968749-26173-1-git-send-email-mhocko@kernel.org Signed-off-by: Michal Hocko Tested-by: William Preston Acked-by: Oleg Nesterov Cc: Roland McGrath Cc: Andreas Schwab Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/kernel/fork.c b/kernel/fork.c index aaf782327bf3..93bdba13d7d9 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -913,14 +913,12 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm) deactivate_mm(tsk, mm); /* - * If we're exiting normally, clear a user-space tid field if - * requested. We leave this alone when dying by signal, to leave - * the value intact in a core dump, and to save the unnecessary - * trouble, say, a killed vfork parent shouldn't touch this mm. - * Userland only wants this done for a sys_exit. + * Signal userspace if we're not exiting with a core dump + * because we want to leave the value intact for debugging + * purposes. */ if (tsk->clear_child_tid) { - if (!(tsk->flags & PF_SIGNALED) && + if (!(tsk->signal->flags & SIGNAL_GROUP_COREDUMP) && atomic_read(&mm->mm_users) > 1) { /* * We don't check the error code - if userspace has From 1e1011af7a5725141aa4c8d30132acd93fe3da4e Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Thu, 1 Sep 2016 16:15:15 -0700 Subject: [PATCH 519/531] rapidio/documentation/mport_cdev: add missing parameter description Add missing description for rio_mport_cdev driver parameter 'dma_timeout'. This patch is applicable to kernel versions starting from v4.6. Link: http://lkml.kernel.org/r/20160901173104.2928-1-alexandre.bounine@idt.com Signed-off-by: Alexandre Bounine Cc: Matt Porter Cc: Andre van Herk Cc: Barry Wood Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/rapidio/mport_cdev.txt | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/Documentation/rapidio/mport_cdev.txt b/Documentation/rapidio/mport_cdev.txt index 6e491a662461..a53f786ee2e9 100644 --- a/Documentation/rapidio/mport_cdev.txt +++ b/Documentation/rapidio/mport_cdev.txt @@ -80,6 +80,10 @@ functionality of their platform when planning to use this driver: III. Module parameters +- 'dma_timeout' - DMA transfer completion timeout (in msec, default value 3000). + This parameter set a maximum completion wait time for SYNC mode DMA + transfer requests and for RIO_WAIT_FOR_ASYNC ioctl requests. + - 'dbg_level' - This parameter allows to control amount of debug information generated by this device driver. This parameter is formed by set of bit masks that correspond to the specific functional blocks. From b30069291dc7f9b9a073c33d619818fe4a8e50de Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Thu, 1 Sep 2016 16:15:18 -0700 Subject: [PATCH 520/531] rapidio/tsi721: fix incorrect detection of address translation condition Fix incorrect condition to identify involvment of a address translation mechanism. This bug results in NULL pointer kernel crash dump in cases when mapping of inbound RapidIO address range is requested within existing aprture. Link: http://lkml.kernel.org/r/20160901173144.2983-1-alexandre.bounine@idt.com Signed-off-by: Alexandre Bounine Cc: Matt Porter Cc: Andre van Herk Cc: Barry Wood Cc: [4.6+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/rapidio/devices/tsi721.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/rapidio/devices/tsi721.c b/drivers/rapidio/devices/tsi721.c index 32f0f014a067..9d19b9a62011 100644 --- a/drivers/rapidio/devices/tsi721.c +++ b/drivers/rapidio/devices/tsi721.c @@ -1161,7 +1161,7 @@ static int tsi721_rio_map_inb_mem(struct rio_mport *mport, dma_addr_t lstart, } else if (ibw_start < (ib_win->rstart + ib_win->size) && (ibw_start + ibw_size) > ib_win->rstart) { /* Return error if address translation involved */ - if (direct && ib_win->xlat) { + if (!direct || ib_win->xlat) { ret = -EFAULT; break; } From 08d072599234c959b0b82b63fa252c129225a899 Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Fri, 2 Sep 2016 14:38:23 +0800 Subject: [PATCH 521/531] tick/nohz: Fix softlockup on scheduler stalls in kvm guest MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit tick_nohz_start_idle() is prevented to be called if the idle tick can't be stopped since commit 1f3b0f8243cb934 ("tick/nohz: Optimize nohz idle enter"). As a result, after suspend/resume the host machine, full dynticks kvm guest will softlockup: NMI watchdog: BUG: soft lockup - CPU#0 stuck for 26s! [swapper/0:0] Call Trace: default_idle+0x31/0x1a0 arch_cpu_idle+0xf/0x20 default_idle_call+0x2a/0x50 cpu_startup_entry+0x39b/0x4d0 rest_init+0x138/0x140 ? rest_init+0x5/0x140 start_kernel+0x4c1/0x4ce ? set_init_arg+0x55/0x55 ? early_idt_handler_array+0x120/0x120 x86_64_start_reservations+0x24/0x26 x86_64_start_kernel+0x142/0x14f In addition, cat /proc/stat | grep cpu in guest or host: cpu 398 16 5049 15754 5490 0 1 46 0 0 cpu0 206 5 450 0 0 0 1 14 0 0 cpu1 81 0 3937 3149 1514 0 0 9 0 0 cpu2 45 6 332 6052 2243 0 0 11 0 0 cpu3 65 2 328 6552 1732 0 0 11 0 0 The idle and iowait states are weird 0 for cpu0(housekeeping). The bug is present in both guest and host kernels, and they both have cpu0's idle and iowait states issue, however, host kernel's suspend/resume path etc will touch watchdog to avoid the softlockup. - The watchdog will not be touched in tick_nohz_stop_idle path (need be touched since the scheduler stall is expected) if idle_active flags are not detected. - The idle and iowait states will not be accounted when exit idle loop (resched or interrupt) if idle start time and idle_active flags are not set. This patch fixes it by reverting commit 1f3b0f8243cb934 since can't stop idle tick doesn't mean can't be idle. Fixes: 1f3b0f8243cb934 ("tick/nohz: Optimize nohz idle enter") Signed-off-by: Wanpeng Li Cc: Sanjeev Yadav Cc: Gaurav Jindal Cc: stable@vger.kernel.org Cc: kvm@vger.kernel.org Cc: Radim Krčmář Cc: Peter Zijlstra Cc: Paolo Bonzini Link: http://lkml.kernel.org/r/1472798303-4154-1-git-send-email-wanpeng.li@hotmail.com Signed-off-by: Thomas Gleixner --- kernel/time/tick-sched.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 204fdc86863d..2ec7c00228f3 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -908,10 +908,11 @@ static void __tick_nohz_idle_enter(struct tick_sched *ts) ktime_t now, expires; int cpu = smp_processor_id(); + now = tick_nohz_start_idle(ts); + if (can_stop_idle_tick(cpu, ts)) { int was_stopped = ts->tick_stopped; - now = tick_nohz_start_idle(ts); ts->idle_calls++; expires = tick_nohz_stop_sched_tick(ts, now, cpu); From 753246840d012ae34ea80a1d40bc1546c62fb957 Mon Sep 17 00:00:00 2001 From: Stefan Wahren Date: Sat, 27 Aug 2016 16:19:49 +0000 Subject: [PATCH 522/531] drivers/perf: arm_pmu: Fix leak in error path In case of a IRQ type mismatch in of_pmu_irq_cfg() the device node for interrupt affinity isn't freed. So fix this issue by calling of_node_put(). Signed-off-by: Stefan Wahren Fixes: fa8ad7889d83 ("arm: perf: factor arm_pmu core out to drivers") Signed-off-by: Will Deacon Signed-off-by: Catalin Marinas --- drivers/perf/arm_pmu.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index c494613c1909..1b48bf0a6780 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -925,6 +925,7 @@ static int of_pmu_irq_cfg(struct arm_pmu *pmu) if (i > 0 && spi != using_spi) { pr_err("PPI/SPI IRQ type mismatch for %s!\n", dn->name); + of_node_put(dn); kfree(irqs); return -EINVAL; } From 63fb0a9516b2c4e23293d7253c14c40aa9c2b7d1 Mon Sep 17 00:00:00 2001 From: Stefan Wahren Date: Sat, 27 Aug 2016 16:19:50 +0000 Subject: [PATCH 523/531] drivers/perf: arm_pmu: Fix NULL pointer dereference during probe Patch 7f1d642fbb5c ("drivers/perf: arm-pmu: Fix handling of SPI lacking interrupt-affinity property") unintended also fixes perf_event support for bcm2835 which doesn't have PMU interrupts. Unfortunately this change introduce a NULL pointer dereference on bcm2835, because irq_is_percpu always expected to be called with a valid IRQ. So fix this regression by validating the IRQ before. Tested-by: Kevin Hilman Signed-off-by: Stefan Wahren Fixes: 7f1d642fbb5c ("drivers/perf: arm-pmu: Fix handling of SPI lacking "interrupt-affinity" property") Signed-off-by: Will Deacon Signed-off-by: Catalin Marinas --- drivers/perf/arm_pmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index 1b48bf0a6780..f5e1008a223d 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -970,7 +970,7 @@ static int of_pmu_irq_cfg(struct arm_pmu *pmu) if (cpumask_weight(&pmu->supported_cpus) == 0) { int irq = platform_get_irq(pdev, 0); - if (irq_is_percpu(irq)) { + if (irq >= 0 && irq_is_percpu(irq)) { /* If using PPIs, check the affinity of the partition */ int ret; From 744c6c37cc18705d19e179622f927f5b781fe9cc Mon Sep 17 00:00:00 2001 From: James Morse Date: Fri, 26 Aug 2016 16:03:42 +0100 Subject: [PATCH 524/531] arm64: kernel: Fix unmasked debug exceptions when restoring mdscr_el1 Changes to make the resume from cpu_suspend() code behave more like secondary boot caused debug exceptions to be unmasked early by __cpu_setup(). We then go on to restore mdscr_el1 in cpu_do_resume(), potentially taking break or watch points based on uninitialised registers. Mask debug exceptions in cpu_do_resume(), which is specific to resume from cpu_suspend(). Debug exceptions will be restored to their original state by local_dbg_restore() in cpu_suspend(), which runs after hw_breakpoint_restore() has re-initialised the other registers. Reported-by: Lorenzo Pieralisi Fixes: cabe1c81ea5b ("arm64: Change cpu_resume() to enable mmu early then access sleep_sp by va") Cc: # 4.7+ Signed-off-by: James Morse Acked-by: Will Deacon Signed-off-by: Catalin Marinas --- arch/arm64/mm/proc.S | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 5bb61de23201..9d37e967fa19 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -100,7 +100,16 @@ ENTRY(cpu_do_resume) msr tcr_el1, x8 msr vbar_el1, x9 + + /* + * __cpu_setup() cleared MDSCR_EL1.MDE and friends, before unmasking + * debug exceptions. By restoring MDSCR_EL1 here, we may take a debug + * exception. Mask them until local_dbg_restore() in cpu_suspend() + * resets them. + */ + disable_dbg msr mdscr_el1, x10 + msr sctlr_el1, x12 /* * Restore oslsr_el1 by writing oslar_el1 From 15301a570754c7af60335d094dd2d1808b0641a5 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 25 May 2016 13:47:26 -0400 Subject: [PATCH 525/531] x86/paravirt: Do not trace _paravirt_ident_*() functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Łukasz Daniluk reported that on a RHEL kernel that his machine would lock up after enabling function tracer. I asked him to bisect the functions within available_filter_functions, which he did and it came down to three: _paravirt_nop(), _paravirt_ident_32() and _paravirt_ident_64() It was found that this is only an issue when noreplace-paravirt is added to the kernel command line. This means that those functions are most likely called within critical sections of the funtion tracer, and must not be traced. In newer kenels _paravirt_nop() is defined within gcc asm(), and is no longer an issue. But both _paravirt_ident_{32,64}() causes the following splat when they are traced: mm/pgtable-generic.c:33: bad pmd ffff8800d2435150(0000000001d00054) mm/pgtable-generic.c:33: bad pmd ffff8800d3624190(0000000001d00070) mm/pgtable-generic.c:33: bad pmd ffff8800d36a5110(0000000001d00054) mm/pgtable-generic.c:33: bad pmd ffff880118eb1450(0000000001d00054) NMI watchdog: BUG: soft lockup - CPU#2 stuck for 22s! [systemd-journal:469] Modules linked in: e1000e CPU: 2 PID: 469 Comm: systemd-journal Not tainted 4.6.0-rc4-test+ #513 Hardware name: Hewlett-Packard HP Compaq Pro 6300 SFF/339A, BIOS K01 v02.05 05/07/2012 task: ffff880118f740c0 ti: ffff8800d4aec000 task.ti: ffff8800d4aec000 RIP: 0010:[] [] queued_spin_lock_slowpath+0x118/0x1a0 RSP: 0018:ffff8800d4aefb90 EFLAGS: 00000246 RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffff88011eb16d40 RDX: ffffffff82485760 RSI: 000000001f288820 RDI: ffffea0000008030 RBP: ffff8800d4aefb90 R08: 00000000000c0000 R09: 0000000000000000 R10: ffffffff821c8e0e R11: 0000000000000000 R12: ffff880000200fb8 R13: 00007f7a4e3f7000 R14: ffffea000303f600 R15: ffff8800d4b562e0 FS: 00007f7a4e3d7840(0000) GS:ffff88011eb00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f7a4e3f7000 CR3: 00000000d3e71000 CR4: 00000000001406e0 Call Trace: _raw_spin_lock+0x27/0x30 handle_pte_fault+0x13db/0x16b0 handle_mm_fault+0x312/0x670 __do_page_fault+0x1b1/0x4e0 do_page_fault+0x22/0x30 page_fault+0x28/0x30 __vfs_read+0x28/0xe0 vfs_read+0x86/0x130 SyS_read+0x46/0xa0 entry_SYSCALL_64_fastpath+0x1e/0xa8 Code: 12 48 c1 ea 0c 83 e8 01 83 e2 30 48 98 48 81 c2 40 6d 01 00 48 03 14 c5 80 6a 5d 82 48 89 0a 8b 41 08 85 c0 75 09 f3 90 8b 41 08 <85> c0 74 f7 4c 8b 09 4d 85 c9 74 08 41 0f 18 09 eb 02 f3 90 8b Reported-by: Łukasz Daniluk Signed-off-by: Steven Rostedt Cc: stable@vger.kernel.org Signed-off-by: Linus Torvalds --- arch/x86/kernel/paravirt.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index ad5bc9578a73..1acfd76e3e26 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -56,12 +56,12 @@ asm (".pushsection .entry.text, \"ax\"\n" ".popsection"); /* identity function, which can be inlined */ -u32 _paravirt_ident_32(u32 x) +u32 notrace _paravirt_ident_32(u32 x) { return x; } -u64 _paravirt_ident_64(u64 x) +u64 notrace _paravirt_ident_64(u64 x) { return x; } From d1992996753132e2dafe955cccb2fb0714d3cfc4 Mon Sep 17 00:00:00 2001 From: Emanuel Czirai Date: Fri, 2 Sep 2016 07:35:50 +0200 Subject: [PATCH 526/531] x86/AMD: Apply erratum 665 on machines without a BIOS fix AMD F12h machines have an erratum which can cause DIV/IDIV to behave unpredictably. The workaround is to set MSRC001_1029[31] but sometimes there is no BIOS update containing that workaround so let's do it ourselves unconditionally. It is simple enough. [ Borislav: Wrote commit message. ] Signed-off-by: Emanuel Czirai Signed-off-by: Borislav Petkov Cc: Yaowu Xu Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/20160902053550.18097-1-bp@alien8.de Signed-off-by: Thomas Gleixner --- arch/x86/kernel/cpu/amd.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index f5c69d8974e1..b81fe2d63e15 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -669,6 +669,17 @@ static void init_amd_gh(struct cpuinfo_x86 *c) set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH); } +#define MSR_AMD64_DE_CFG 0xC0011029 + +static void init_amd_ln(struct cpuinfo_x86 *c) +{ + /* + * Apply erratum 665 fix unconditionally so machines without a BIOS + * fix work. + */ + msr_set_bit(MSR_AMD64_DE_CFG, 31); +} + static void init_amd_bd(struct cpuinfo_x86 *c) { u64 value; @@ -726,6 +737,7 @@ static void init_amd(struct cpuinfo_x86 *c) case 6: init_amd_k7(c); break; case 0xf: init_amd_k8(c); break; case 0x10: init_amd_gh(c); break; + case 0x12: init_amd_ln(c); break; case 0x15: init_amd_bd(c); break; } From 3feab13c919f99b0a17d0ca22ae00cf90f5d3fd1 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Tue, 16 Aug 2016 16:59:52 +0100 Subject: [PATCH 527/531] ACPI / drivers: fix typo in ACPI_DECLARE_PROBE_ENTRY macro When the ACPI_DECLARE_PROBE_ENTRY macro was added in commit e647b532275b ("ACPI: Add early device probing infrastructure"), a stub macro adding an unused entry was added for the !CONFIG_ACPI Kconfig option case to make sure kernel code making use of the macro did not require to be guarded within CONFIG_ACPI in order to be compiled. The stub macro was never used since all kernel code that defines ACPI_DECLARE_PROBE_ENTRY entries is currently guarded within CONFIG_ACPI; it contains a typo that should be nonetheless fixed. Fix the typo in the stub (ie !CONFIG_ACPI) ACPI_DECLARE_PROBE_ENTRY() macro so that it can actually be used if needed. Signed-off-by: Lorenzo Pieralisi Fixes: e647b532275b (ACPI: Add early device probing infrastructure) Cc: 4.4+ # 4.4+ Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 4d8452c2384b..c5eaf2f80a4c 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1056,7 +1056,7 @@ static inline struct fwnode_handle *acpi_get_next_subnode(struct device *dev, return NULL; } -#define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, validate, data, fn) \ +#define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, valid, data, fn) \ static const void * __acpi_table_##name[] \ __attribute__((unused)) \ = { (void *) table_id, \ From 5331d9cab32ef640b4cd38a43b0858874fbb7168 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Tue, 16 Aug 2016 16:59:53 +0100 Subject: [PATCH 528/531] ACPI / drivers: replace acpi_probe_lock spinlock with mutex Commit e647b532275b ("ACPI: Add early device probing infrastructure") introduced code that allows inserting driver specific struct acpi_probe_entry probe entries into ACPI linker sections (one per-subsystem, eg irqchip, clocksource) that are then walked to retrieve the data and function hooks required to probe the respective kernel components. Probing for all entries in a section is triggered through the __acpi_probe_device_table() function, that in turn, according to the table ID a given probe entry reports parses the table with the function retrieved from the respective section structures (ie struct acpi_probe_entry). Owing to the current ACPI table parsing implementation, the __acpi_probe_device_table() function has to share global variables with the acpi_match_madt() function, so in order to guarantee mutual exclusion locking is required between the two functions. Current kernel code implements the locking through the acpi_probe_lock spinlock; this has the side effect of requiring all code called within the lock (ie struct acpi_probe_entry.probe_{table/subtbl} hooks) not to sleep. However, kernel subsystems that make use of the early probing infrastructure are relying on kernel APIs that may sleep (eg irq_domain_alloc_fwnode(), among others) in the function calls pointed at by struct acpi_probe_entry.{probe_table/subtbl} entries (eg gic_v2_acpi_init()), which is a bug. Since __acpi_probe_device_table() is called from context that is allowed to sleep the acpi_probe_lock spinlock can be replaced with a mutex; this fixes the issue whilst still guaranteeing mutual exclusion. Signed-off-by: Lorenzo Pieralisi Fixes: e647b532275b (ACPI: Add early device probing infrastructure) Cc: 4.4+ # 4.4+ Signed-off-by: Rafael J. Wysocki --- drivers/acpi/scan.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index ad9fc84a8601..e878fc799af7 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -2054,7 +2054,7 @@ int __init acpi_scan_init(void) static struct acpi_probe_entry *ape; static int acpi_probe_count; -static DEFINE_SPINLOCK(acpi_probe_lock); +static DEFINE_MUTEX(acpi_probe_mutex); static int __init acpi_match_madt(struct acpi_subtable_header *header, const unsigned long end) @@ -2073,7 +2073,7 @@ int __init __acpi_probe_device_table(struct acpi_probe_entry *ap_head, int nr) if (acpi_disabled) return 0; - spin_lock(&acpi_probe_lock); + mutex_lock(&acpi_probe_mutex); for (ape = ap_head; nr; ape++, nr--) { if (ACPI_COMPARE_NAME(ACPI_SIG_MADT, ape->id)) { acpi_probe_count = 0; @@ -2086,7 +2086,7 @@ int __init __acpi_probe_device_table(struct acpi_probe_entry *ap_head, int nr) count++; } } - spin_unlock(&acpi_probe_lock); + mutex_unlock(&acpi_probe_mutex); return count; } From 4a29b3484f857ff350f203a2d9bf3b428c9e0bf2 Mon Sep 17 00:00:00 2001 From: Jarkko Sakkinen Date: Fri, 2 Sep 2016 02:36:58 +0300 Subject: [PATCH 529/531] tpm: invalid self test error message The driver emits invalid self test error message even though the init succeeds. Signed-off-by: Jarkko Sakkinen Fixes: cae8b441fc20 ("tpm: Factor out common startup code") Reviewed-by: James Morris Signed-off-by: James Morris --- drivers/char/tpm/tpm2-cmd.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index 08c7e23ed535..0c75c3f1689f 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -957,7 +957,7 @@ int tpm2_auto_startup(struct tpm_chip *chip) goto out; rc = tpm2_do_selftest(chip); - if (rc != TPM2_RC_INITIALIZE) { + if (rc != 0 && rc != TPM2_RC_INITIALIZE) { dev_err(&chip->dev, "TPM self test failed\n"); goto out; } @@ -974,7 +974,6 @@ int tpm2_auto_startup(struct tpm_chip *chip) } } - return rc; out: if (rc > 0) rc = -ENODEV; From 3e423945ea94412283eaba8bfbe9d6e0a80b434f Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 3 Sep 2016 11:02:50 -0700 Subject: [PATCH 530/531] devpts: return NULL pts 'priv' entry for non-devpts nodes In commit 8ead9dd54716 ("devpts: more pty driver interface cleanups") I made devpts_get_priv() just return the dentry->fs_data directly. And because I thought it wouldn't happen, I added a warning if you ever saw a pts node that wasn't on devpts. And no, that warning never triggered under any actual real use, but you can trigger it by creating nonsensical pts nodes by hand. So just revert the warning, and make devpts_get_priv() return NULL for that case like it used to. Reported-by: Dmitry Vyukov Cc: stable@vger.kernel.org # 4.6+ Cc: Eric W Biederman" Signed-off-by: Linus Torvalds --- fs/devpts/inode.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index d116453b0276..79a5941c2474 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -585,7 +585,8 @@ struct dentry *devpts_pty_new(struct pts_fs_info *fsi, int index, void *priv) */ void *devpts_get_priv(struct dentry *dentry) { - WARN_ON_ONCE(dentry->d_sb->s_magic != DEVPTS_SUPER_MAGIC); + if (dentry->d_sb->s_magic != DEVPTS_SUPER_MAGIC) + return NULL; return dentry->d_fsdata; } From c6935931c1894ff857616ff8549b61236a19148f Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 4 Sep 2016 14:31:46 -0700 Subject: [PATCH 531/531] Linux 4.8-rc5 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 67f42d57e6e7..a4e6cc531f81 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 8 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc5 NAME = Psychotic Stoned Sheep # *DOCUMENTATION*