From f0414087a1b9933adac40974c3ea50261227b5f0 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 22 Jul 2019 14:44:43 +0200 Subject: [PATCH 001/157] dmaengine: dw-edma: fix unnecessary stack usage Putting large constant data on the stack causes unnecessary overhead and stack usage: drivers/dma/dw-edma/dw-edma-v0-debugfs.c:285:6: error: stack frame size of 1376 bytes in function 'dw_edma_v0_debugfs_on' [-Werror,-Wframe-larger-than=] Mark the variable 'static const' in order for the compiler to move it into the .rodata section where it does no such harm. Fixes: 305aebeff879 ("dmaengine: Add Synopsys eDMA IP version 0 debugfs support") Signed-off-by: Arnd Bergmann Acked-by: Gustavo Pimentel Link: https://lore.kernel.org/r/20190722124457.1093886-1-arnd@arndb.de Signed-off-by: Vinod Koul --- drivers/dma/dw-edma/dw-edma-v0-debugfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/dma/dw-edma/dw-edma-v0-debugfs.c b/drivers/dma/dw-edma/dw-edma-v0-debugfs.c index 3226f528cc11..5728b6fe938c 100644 --- a/drivers/dma/dw-edma/dw-edma-v0-debugfs.c +++ b/drivers/dma/dw-edma/dw-edma-v0-debugfs.c @@ -48,7 +48,7 @@ static struct { } lim[2][EDMA_V0_MAX_NR_CH]; struct debugfs_entries { - char name[24]; + const char *name; dma_addr_t *reg; }; From 756c3ef93492af382c541e039c1417b96a3d335e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 22 Jul 2019 14:44:44 +0200 Subject: [PATCH 002/157] dmaengine: dw-edma: fix __iomem type confusion The new driver mixes up dma_addr_t and __iomem pointers, which results in warnings on some 32-bit architectures, like: drivers/dma/dw-edma/dw-edma-v0-core.c: In function '__dw_regs': drivers/dma/dw-edma/dw-edma-v0-core.c:28:9: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast] return (struct dw_edma_v0_regs __iomem *)dw->rg_region.vaddr; Make it use __iomem pointers consistently here, and avoid using dma_addr_t for __iomem tokens altogether. A small complication here is the debugfs code, which passes an __iomem token as the private data for debugfs files, requiring the use of extra __force. Fixes: 7e4b8a4fbe2c ("dmaengine: Add Synopsys eDMA IP version 0 support") Link: https://lore.kernel.org/lkml/20190617131918.2518727-1-arnd@arndb.de/ Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20190722124457.1093886-2-arnd@arndb.de Signed-off-by: Vinod Koul --- drivers/dma/dw-edma/dw-edma-core.h | 2 +- drivers/dma/dw-edma/dw-edma-pcie.c | 18 ++++++++-------- drivers/dma/dw-edma/dw-edma-v0-core.c | 10 ++++----- drivers/dma/dw-edma/dw-edma-v0-debugfs.c | 27 ++++++++++++------------ 4 files changed, 29 insertions(+), 28 deletions(-) diff --git a/drivers/dma/dw-edma/dw-edma-core.h b/drivers/dma/dw-edma/dw-edma-core.h index b6cc90cbc9dc..4e5f9f6e901b 100644 --- a/drivers/dma/dw-edma/dw-edma-core.h +++ b/drivers/dma/dw-edma/dw-edma-core.h @@ -50,7 +50,7 @@ struct dw_edma_burst { struct dw_edma_region { phys_addr_t paddr; - dma_addr_t vaddr; + void __iomem *vaddr; size_t sz; }; diff --git a/drivers/dma/dw-edma/dw-edma-pcie.c b/drivers/dma/dw-edma/dw-edma-pcie.c index 4c96e1c948f2..dc85f55e1bb8 100644 --- a/drivers/dma/dw-edma/dw-edma-pcie.c +++ b/drivers/dma/dw-edma/dw-edma-pcie.c @@ -130,19 +130,19 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev, chip->id = pdev->devfn; chip->irq = pdev->irq; - dw->rg_region.vaddr = (dma_addr_t)pcim_iomap_table(pdev)[pdata->rg_bar]; + dw->rg_region.vaddr = pcim_iomap_table(pdev)[pdata->rg_bar]; dw->rg_region.vaddr += pdata->rg_off; dw->rg_region.paddr = pdev->resource[pdata->rg_bar].start; dw->rg_region.paddr += pdata->rg_off; dw->rg_region.sz = pdata->rg_sz; - dw->ll_region.vaddr = (dma_addr_t)pcim_iomap_table(pdev)[pdata->ll_bar]; + dw->ll_region.vaddr = pcim_iomap_table(pdev)[pdata->ll_bar]; dw->ll_region.vaddr += pdata->ll_off; dw->ll_region.paddr = pdev->resource[pdata->ll_bar].start; dw->ll_region.paddr += pdata->ll_off; dw->ll_region.sz = pdata->ll_sz; - dw->dt_region.vaddr = (dma_addr_t)pcim_iomap_table(pdev)[pdata->dt_bar]; + dw->dt_region.vaddr = pcim_iomap_table(pdev)[pdata->dt_bar]; dw->dt_region.vaddr += pdata->dt_off; dw->dt_region.paddr = pdev->resource[pdata->dt_bar].start; dw->dt_region.paddr += pdata->dt_off; @@ -158,17 +158,17 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev, pci_dbg(pdev, "Mode:\t%s\n", dw->mode == EDMA_MODE_LEGACY ? "Legacy" : "Unroll"); - pci_dbg(pdev, "Registers:\tBAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%pa, p=%pa)\n", + pci_dbg(pdev, "Registers:\tBAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n", pdata->rg_bar, pdata->rg_off, pdata->rg_sz, - &dw->rg_region.vaddr, &dw->rg_region.paddr); + dw->rg_region.vaddr, &dw->rg_region.paddr); - pci_dbg(pdev, "L. List:\tBAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%pa, p=%pa)\n", + pci_dbg(pdev, "L. List:\tBAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n", pdata->ll_bar, pdata->ll_off, pdata->ll_sz, - &dw->ll_region.vaddr, &dw->ll_region.paddr); + dw->ll_region.vaddr, &dw->ll_region.paddr); - pci_dbg(pdev, "Data:\tBAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%pa, p=%pa)\n", + pci_dbg(pdev, "Data:\tBAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n", pdata->dt_bar, pdata->dt_off, pdata->dt_sz, - &dw->dt_region.vaddr, &dw->dt_region.paddr); + dw->dt_region.vaddr, &dw->dt_region.paddr); pci_dbg(pdev, "Nr. IRQs:\t%u\n", dw->nr_irqs); diff --git a/drivers/dma/dw-edma/dw-edma-v0-core.c b/drivers/dma/dw-edma/dw-edma-v0-core.c index 8a3180ed49a6..97e3fd41c8a8 100644 --- a/drivers/dma/dw-edma/dw-edma-v0-core.c +++ b/drivers/dma/dw-edma/dw-edma-v0-core.c @@ -25,7 +25,7 @@ enum dw_edma_control { static inline struct dw_edma_v0_regs __iomem *__dw_regs(struct dw_edma *dw) { - return (struct dw_edma_v0_regs __iomem *)dw->rg_region.vaddr; + return dw->rg_region.vaddr; } #define SET(dw, name, value) \ @@ -192,13 +192,13 @@ u32 dw_edma_v0_core_status_abort_int(struct dw_edma *dw, enum dw_edma_dir dir) static void dw_edma_v0_core_write_chunk(struct dw_edma_chunk *chunk) { struct dw_edma_burst *child; - struct dw_edma_v0_lli *lli; - struct dw_edma_v0_llp *llp; + struct dw_edma_v0_lli __iomem *lli; + struct dw_edma_v0_llp __iomem *llp; u32 control = 0, i = 0; u64 sar, dar, addr; int j; - lli = (struct dw_edma_v0_lli *)chunk->ll_region.vaddr; + lli = chunk->ll_region.vaddr; if (chunk->cb) control = DW_EDMA_V0_CB; @@ -224,7 +224,7 @@ static void dw_edma_v0_core_write_chunk(struct dw_edma_chunk *chunk) i++; } - llp = (struct dw_edma_v0_llp *)&lli[i]; + llp = (void __iomem *)&lli[i]; control = DW_EDMA_V0_LLP | DW_EDMA_V0_TCB; if (!chunk->cb) control |= DW_EDMA_V0_CB; diff --git a/drivers/dma/dw-edma/dw-edma-v0-debugfs.c b/drivers/dma/dw-edma/dw-edma-v0-debugfs.c index 5728b6fe938c..42739508c0d8 100644 --- a/drivers/dma/dw-edma/dw-edma-v0-debugfs.c +++ b/drivers/dma/dw-edma/dw-edma-v0-debugfs.c @@ -14,7 +14,7 @@ #include "dw-edma-core.h" #define REGS_ADDR(name) \ - ((dma_addr_t *)®s->name) + ((void __force *)®s->name) #define REGISTER(name) \ { #name, REGS_ADDR(name) } @@ -40,11 +40,11 @@ static struct dentry *base_dir; static struct dw_edma *dw; -static struct dw_edma_v0_regs *regs; +static struct dw_edma_v0_regs __iomem *regs; static struct { - void *start; - void *end; + void __iomem *start; + void __iomem *end; } lim[2][EDMA_V0_MAX_NR_CH]; struct debugfs_entries { @@ -54,22 +54,23 @@ struct debugfs_entries { static int dw_edma_debugfs_u32_get(void *data, u64 *val) { + void __iomem *reg = (void __force __iomem *)data; if (dw->mode == EDMA_MODE_LEGACY && - data >= (void *)®s->type.legacy.ch) { - void *ptr = (void *)®s->type.legacy.ch; + reg >= (void __iomem *)®s->type.legacy.ch) { + void __iomem *ptr = ®s->type.legacy.ch; u32 viewport_sel = 0; unsigned long flags; u16 ch; for (ch = 0; ch < dw->wr_ch_cnt; ch++) - if (lim[0][ch].start >= data && data < lim[0][ch].end) { - ptr += (data - lim[0][ch].start); + if (lim[0][ch].start >= reg && reg < lim[0][ch].end) { + ptr += (reg - lim[0][ch].start); goto legacy_sel_wr; } for (ch = 0; ch < dw->rd_ch_cnt; ch++) - if (lim[1][ch].start >= data && data < lim[1][ch].end) { - ptr += (data - lim[1][ch].start); + if (lim[1][ch].start >= reg && reg < lim[1][ch].end) { + ptr += (reg - lim[1][ch].start); goto legacy_sel_rd; } @@ -86,7 +87,7 @@ static int dw_edma_debugfs_u32_get(void *data, u64 *val) raw_spin_unlock_irqrestore(&dw->lock, flags); } else { - *val = readl(data); + *val = readl(reg); } return 0; @@ -105,7 +106,7 @@ static void dw_edma_debugfs_create_x32(const struct debugfs_entries entries[], } } -static void dw_edma_debugfs_regs_ch(struct dw_edma_v0_ch_regs *regs, +static void dw_edma_debugfs_regs_ch(struct dw_edma_v0_ch_regs __iomem *regs, struct dentry *dir) { int nr_entries; @@ -288,7 +289,7 @@ void dw_edma_v0_debugfs_on(struct dw_edma_chip *chip) if (!dw) return; - regs = (struct dw_edma_v0_regs *)dw->rg_region.vaddr; + regs = dw->rg_region.vaddr; if (!regs) return; From 6f4722b1d1ebf274deb0459a36fad57a7d7fab31 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 22 Jul 2019 14:44:45 +0200 Subject: [PATCH 003/157] dmaengine: dw-edma: fix endianess confusion When building with 'make C=1', sparse reports an endianess bug: drivers/dma/dw-edma/dw-edma-v0-debugfs.c:60:30: warning: cast removes address space of expression drivers/dma/dw-edma/dw-edma-v0-debugfs.c:86:24: warning: incorrect type in argument 1 (different address spaces) drivers/dma/dw-edma/dw-edma-v0-debugfs.c:86:24: expected void const volatile [noderef] *addr drivers/dma/dw-edma/dw-edma-v0-debugfs.c:86:24: got void *[assigned] ptr drivers/dma/dw-edma/dw-edma-v0-debugfs.c:86:24: warning: incorrect type in argument 1 (different address spaces) drivers/dma/dw-edma/dw-edma-v0-debugfs.c:86:24: expected void const volatile [noderef] *addr drivers/dma/dw-edma/dw-edma-v0-debugfs.c:86:24: got void *[assigned] ptr drivers/dma/dw-edma/dw-edma-v0-debugfs.c:86:24: warning: incorrect type in argument 1 (different address spaces) drivers/dma/dw-edma/dw-edma-v0-debugfs.c:86:24: expected void const volatile [noderef] *addr drivers/dma/dw-edma/dw-edma-v0-debugfs.c:86:24: got void *[assigned] ptr The current code is clearly wrong, as it passes an endian-swapped word into a register function where it gets swapped again. Just pass the variables directly into lower_32_bits()/upper_32_bits(). Fixes: 7e4b8a4fbe2c ("dmaengine: Add Synopsys eDMA IP version 0 support") Link: https://lore.kernel.org/lkml/20190617131820.2470686-1-arnd@arndb.de/ Signed-off-by: Arnd Bergmann Acked-by: Gustavo Pimentel Link: https://lore.kernel.org/r/20190722124457.1093886-3-arnd@arndb.de Signed-off-by: Vinod Koul --- drivers/dma/dw-edma/dw-edma-v0-core.c | 24 ++++++++++-------------- 1 file changed, 10 insertions(+), 14 deletions(-) diff --git a/drivers/dma/dw-edma/dw-edma-v0-core.c b/drivers/dma/dw-edma/dw-edma-v0-core.c index 97e3fd41c8a8..692de47b1670 100644 --- a/drivers/dma/dw-edma/dw-edma-v0-core.c +++ b/drivers/dma/dw-edma/dw-edma-v0-core.c @@ -195,7 +195,6 @@ static void dw_edma_v0_core_write_chunk(struct dw_edma_chunk *chunk) struct dw_edma_v0_lli __iomem *lli; struct dw_edma_v0_llp __iomem *llp; u32 control = 0, i = 0; - u64 sar, dar, addr; int j; lli = chunk->ll_region.vaddr; @@ -214,13 +213,11 @@ static void dw_edma_v0_core_write_chunk(struct dw_edma_chunk *chunk) /* Transfer size */ SET_LL(&lli[i].transfer_size, child->sz); /* SAR - low, high */ - sar = cpu_to_le64(child->sar); - SET_LL(&lli[i].sar_low, lower_32_bits(sar)); - SET_LL(&lli[i].sar_high, upper_32_bits(sar)); + SET_LL(&lli[i].sar_low, lower_32_bits(child->sar)); + SET_LL(&lli[i].sar_high, upper_32_bits(child->sar)); /* DAR - low, high */ - dar = cpu_to_le64(child->dar); - SET_LL(&lli[i].dar_low, lower_32_bits(dar)); - SET_LL(&lli[i].dar_high, upper_32_bits(dar)); + SET_LL(&lli[i].dar_low, lower_32_bits(child->dar)); + SET_LL(&lli[i].dar_high, upper_32_bits(child->dar)); i++; } @@ -232,9 +229,8 @@ static void dw_edma_v0_core_write_chunk(struct dw_edma_chunk *chunk) /* Channel control */ SET_LL(&llp->control, control); /* Linked list - low, high */ - addr = cpu_to_le64(chunk->ll_region.paddr); - SET_LL(&llp->llp_low, lower_32_bits(addr)); - SET_LL(&llp->llp_high, upper_32_bits(addr)); + SET_LL(&llp->llp_low, lower_32_bits(chunk->ll_region.paddr)); + SET_LL(&llp->llp_high, upper_32_bits(chunk->ll_region.paddr)); } void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first) @@ -242,7 +238,6 @@ void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first) struct dw_edma_chan *chan = chunk->chan; struct dw_edma *dw = chan->chip->dw; u32 tmp; - u64 llp; dw_edma_v0_core_write_chunk(chunk); @@ -262,9 +257,10 @@ void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first) SET_CH(dw, chan->dir, chan->id, ch_control1, (DW_EDMA_V0_CCS | DW_EDMA_V0_LLE)); /* Linked list - low, high */ - llp = cpu_to_le64(chunk->ll_region.paddr); - SET_CH(dw, chan->dir, chan->id, llp_low, lower_32_bits(llp)); - SET_CH(dw, chan->dir, chan->id, llp_high, upper_32_bits(llp)); + SET_CH(dw, chan->dir, chan->id, llp_low, + lower_32_bits(chunk->ll_region.paddr)); + SET_CH(dw, chan->dir, chan->id, llp_high, + upper_32_bits(chunk->ll_region.paddr)); } /* Doorbell */ SET_RW(dw, chan->dir, doorbell, From 5d6fb560729a5d5554e23db8d00eb57cd0021083 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 12 Jul 2019 11:13:30 +0200 Subject: [PATCH 004/157] dmaengine: ste_dma40: fix unneeded variable warning clang-9 points out that there are two variables that depending on the configuration may only be used in an ARRAY_SIZE() expression but not referenced: drivers/dma/ste_dma40.c:145:12: error: variable 'd40_backup_regs' is not needed and will not be emitted [-Werror,-Wunneeded-internal-declaration] static u32 d40_backup_regs[] = { ^ drivers/dma/ste_dma40.c:214:12: error: variable 'd40_backup_regs_chan' is not needed and will not be emitted [-Werror,-Wunneeded-internal-declaration] static u32 d40_backup_regs_chan[] = { Mark these __maybe_unused to shut up the warning. Signed-off-by: Arnd Bergmann Reviewed-by: Nathan Chancellor Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/20190712091357.744515-1-arnd@arndb.de Signed-off-by: Vinod Koul --- drivers/dma/ste_dma40.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c index 89d710899010..de8bfd9a76e9 100644 --- a/drivers/dma/ste_dma40.c +++ b/drivers/dma/ste_dma40.c @@ -142,7 +142,7 @@ enum d40_events { * when the DMA hw is powered off. * TODO: Add save/restore of D40_DREG_GCC on dma40 v3 or later, if that works. */ -static u32 d40_backup_regs[] = { +static __maybe_unused u32 d40_backup_regs[] = { D40_DREG_LCPA, D40_DREG_LCLA, D40_DREG_PRMSE, @@ -211,7 +211,7 @@ static u32 d40_backup_regs_v4b[] = { #define BACKUP_REGS_SZ_V4B ARRAY_SIZE(d40_backup_regs_v4b) -static u32 d40_backup_regs_chan[] = { +static __maybe_unused u32 d40_backup_regs_chan[] = { D40_CHAN_REG_SSCFG, D40_CHAN_REG_SSELT, D40_CHAN_REG_SSPTR, From d105ef8120dd522c3233a1395ee0b318ed0929e8 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Tue, 9 Jul 2019 16:32:58 +0800 Subject: [PATCH 005/157] dmaengine: tegra210-adma: Fix unused function warnings If CONFIG_PM is not set, build warnings: drivers/dma/tegra210-adma.c:747:12: warning: tegra_adma_runtime_resume defined but not used [-Wunused-function] static int tegra_adma_runtime_resume(struct device *dev) drivers/dma/tegra210-adma.c:715:12: warning: tegra_adma_runtime_suspend defined but not used [-Wunused-function] static int tegra_adma_runtime_suspend(struct device *dev) Mark the two function as __maybe_unused. Reported-by: Hulk Robot Signed-off-by: YueHaibing Fixes: 3145d73e69ba ("dmaengine: tegra210-adma: remove PM_CLK dependency") Fixes: f46b195799b5 ("dmaengine: tegra-adma: Add support for Tegra210 ADMA") Reported-by: Arnd Bergmann Acked-by: Jon Hunter Link: https://lore.kernel.org/r/20190709083258.57112-1-yuehaibing@huawei.com Signed-off-by: Vinod Koul --- drivers/dma/tegra210-adma.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c index 2805853e963f..b33cf6e8ab8e 100644 --- a/drivers/dma/tegra210-adma.c +++ b/drivers/dma/tegra210-adma.c @@ -712,7 +712,7 @@ static struct dma_chan *tegra_dma_of_xlate(struct of_phandle_args *dma_spec, return chan; } -static int tegra_adma_runtime_suspend(struct device *dev) +static int __maybe_unused tegra_adma_runtime_suspend(struct device *dev) { struct tegra_adma *tdma = dev_get_drvdata(dev); struct tegra_adma_chan_regs *ch_reg; @@ -744,7 +744,7 @@ static int tegra_adma_runtime_suspend(struct device *dev) return 0; } -static int tegra_adma_runtime_resume(struct device *dev) +static int __maybe_unused tegra_adma_runtime_resume(struct device *dev) { struct tegra_adma *tdma = dev_get_drvdata(dev); struct tegra_adma_chan_regs *ch_reg; From fab7772bfbcfe8fb8e3e352a6a8fcaf044cded17 Mon Sep 17 00:00:00 2001 From: Anthony Iliopoulos Date: Mon, 29 Jul 2019 14:40:40 +0200 Subject: [PATCH 006/157] nvme-multipath: revalidate nvme_ns_head gendisk in nvme_validate_ns When CONFIG_NVME_MULTIPATH is set, only the hidden gendisk associated with the per-controller ns is run through revalidate_disk when a rescan is triggered, while the visible blockdev never gets its size (bdev->bd_inode->i_size) updated to reflect any capacity changes that may have occurred. This prevents online resizing of nvme block devices and in extension of any filesystems atop that will are unable to expand while mounted, as userspace relies on the blockdev size for obtaining the disk capacity (via BLKGETSIZE/64 ioctls). Fix this by explicitly revalidating the actual namespace gendisk in addition to the per-controller gendisk, when multipath is enabled. Signed-off-by: Anthony Iliopoulos Reviewed-by: Sagi Grimberg Reviewed-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 8f3fbe5ca937..80c7a7ee240b 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1715,6 +1715,7 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id) if (ns->head->disk) { nvme_update_disk_info(ns->head->disk, ns, id); blk_queue_stack_limits(ns->head->disk->queue, ns->queue); + revalidate_disk(ns->head->disk); } #endif } From 2067b2b3f4846402a040286135f98f46f8919939 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 30 Jul 2019 14:38:51 +0100 Subject: [PATCH 007/157] afs: Fix the CB.ProbeUuid service handler to reply correctly Fix the service handler function for the CB.ProbeUuid RPC call so that it replies in the correct manner - that is an empty reply for success and an abort of 1 for failure. Putting 0 or 1 in an integer in the body of the reply should result in the fileserver throwing an RX_PROTOCOL_ERROR abort and discarding its record of the client; older servers, however, don't necessarily check that all the data got consumed, and so might incorrectly think that they got a positive response and associate the client with the wrong host record. If the client is incorrectly associated, this will result in callbacks intended for a different client being delivered to this one and then, when the other client connects and responds positively, all of the callback promises meant for the client that issued the improper response will be lost and it won't receive any further change notifications. Fixes: 9396d496d745 ("afs: support the CB.ProbeUuid RPC op") Signed-off-by: David Howells Reviewed-by: Jeffrey Altman --- fs/afs/cmservice.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index 4f1b6f466ff5..b86195e4dc6c 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -505,18 +505,14 @@ static void SRXAFSCB_ProbeUuid(struct work_struct *work) struct afs_call *call = container_of(work, struct afs_call, work); struct afs_uuid *r = call->request; - struct { - __be32 match; - } reply; - _enter(""); if (memcmp(r, &call->net->uuid, sizeof(call->net->uuid)) == 0) - reply.match = htonl(0); + afs_send_empty_reply(call); else - reply.match = htonl(1); + rxrpc_kernel_abort_call(call->net->socket, call->rxcall, + 1, 1, "K-1"); - afs_send_simple_reply(call, &reply, sizeof(reply)); afs_put_call(call); _leave(""); } From 4a46fdba449a5cd890271df5a9e23927d519ed00 Mon Sep 17 00:00:00 2001 From: Marc Dionne Date: Tue, 30 Jul 2019 14:38:51 +0100 Subject: [PATCH 008/157] afs: Fix loop index mixup in afs_deliver_vl_get_entry_by_name_u() afs_deliver_vl_get_entry_by_name_u() scans through the vl entry received from the volume location server and builds a return list containing the sites that are currently valid. When assigning values for the return list, the index into the vl entry (i) is used rather than the one for the new list (entry->nr_server). If all sites are usable, this works out fine as the indices will match. If some sites are not valid, for example if AFS_VLSF_DONTUSE is set, fs_mask and the uuid will be set for the wrong return site. Fix this by using entry->nr_server as the index into the arrays being filled in rather than i. This can lead to EDESTADDRREQ errors if none of the returned sites have a valid fs_mask. Fixes: d2ddc776a458 ("afs: Overhaul volume and server record caching and fileserver rotation") Signed-off-by: Marc Dionne Signed-off-by: David Howells Reviewed-by: Jeffrey Altman --- fs/afs/vlclient.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c index d7e0fd3c00df..cfb0ac4bd039 100644 --- a/fs/afs/vlclient.c +++ b/fs/afs/vlclient.c @@ -56,23 +56,24 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call) struct afs_uuid__xdr *xdr; struct afs_uuid *uuid; int j; + int n = entry->nr_servers; tmp = ntohl(uvldb->serverFlags[i]); if (tmp & AFS_VLSF_DONTUSE || (new_only && !(tmp & AFS_VLSF_NEWREPSITE))) continue; if (tmp & AFS_VLSF_RWVOL) { - entry->fs_mask[i] |= AFS_VOL_VTM_RW; + entry->fs_mask[n] |= AFS_VOL_VTM_RW; if (vlflags & AFS_VLF_BACKEXISTS) - entry->fs_mask[i] |= AFS_VOL_VTM_BAK; + entry->fs_mask[n] |= AFS_VOL_VTM_BAK; } if (tmp & AFS_VLSF_ROVOL) - entry->fs_mask[i] |= AFS_VOL_VTM_RO; - if (!entry->fs_mask[i]) + entry->fs_mask[n] |= AFS_VOL_VTM_RO; + if (!entry->fs_mask[n]) continue; xdr = &uvldb->serverNumber[i]; - uuid = (struct afs_uuid *)&entry->fs_server[i]; + uuid = (struct afs_uuid *)&entry->fs_server[n]; uuid->time_low = xdr->time_low; uuid->time_mid = htons(ntohl(xdr->time_mid)); uuid->time_hi_and_version = htons(ntohl(xdr->time_hi_and_version)); From a6eed4ab5dd4bfb696c1a3f49742b8d1846a66a0 Mon Sep 17 00:00:00 2001 From: Jia-Ju Bai Date: Tue, 30 Jul 2019 14:38:51 +0100 Subject: [PATCH 009/157] fs: afs: Fix a possible null-pointer dereference in afs_put_read() In afs_read_dir(), there is an if statement on line 255 to check whether req->pages is NULL: if (!req->pages) goto error; If req->pages is NULL, afs_put_read() on line 337 is executed. In afs_put_read(), req->pages[i] is used on line 195. Thus, a possible null-pointer dereference may occur in this case. To fix this possible bug, an if statement is added in afs_put_read() to check req->pages. This bug is found by a static analysis tool STCheck written by us. Fixes: f3ddee8dc4e2 ("afs: Fix directory handling") Signed-off-by: Jia-Ju Bai Signed-off-by: David Howells --- fs/afs/file.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/fs/afs/file.c b/fs/afs/file.c index 56b69576274d..dd3c55c9101c 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -191,11 +191,13 @@ void afs_put_read(struct afs_read *req) int i; if (refcount_dec_and_test(&req->usage)) { - for (i = 0; i < req->nr_pages; i++) - if (req->pages[i]) - put_page(req->pages[i]); - if (req->pages != req->array) - kfree(req->pages); + if (req->pages) { + for (i = 0; i < req->nr_pages; i++) + if (req->pages[i]) + put_page(req->pages[i]); + if (req->pages != req->array) + kfree(req->pages); + } kfree(req); } } From 37c0bbb3326674940e657118306ac52364314523 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 30 Jul 2019 14:38:51 +0100 Subject: [PATCH 010/157] afs: Fix off-by-one in afs_rename() expected data version calculation When afs_rename() calculates the expected data version of the target directory in a cross-directory rename, it doesn't increment it as it should, so it always thinks that the target inode is unexpectedly modified on the server. Fixes: a58823ac4589 ("afs: Fix application of status and callback to be under same lock") Signed-off-by: David Howells --- fs/afs/dir.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/afs/dir.c b/fs/afs/dir.c index e640d67274be..20aa18b38a49 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -1804,7 +1804,7 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, afs_end_vnode_operation(&fc); goto error_rehash; } - new_data_version = new_dvnode->status.data_version; + new_data_version = new_dvnode->status.data_version + 1; } else { new_data_version = orig_data_version; new_scb = &scb[0]; From 5dc84855b0fc7e1db182b55c5564fd539d6eff92 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 30 Jul 2019 14:38:51 +0100 Subject: [PATCH 011/157] afs: Only update d_fsdata if different in afs_d_revalidate() In the in-kernel afs filesystem, d_fsdata is set with the data version of the parent directory. afs_d_revalidate() will update this to the current directory version, but it shouldn't do this if it the value it read from d_fsdata is the same as no lock is held and cmpxchg() is not used. Fix the code to only change the value if it is different from the current directory version. Fixes: 260a980317da ("[AFS]: Add "directory write" support.") Signed-off-by: David Howells --- fs/afs/dir.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 20aa18b38a49..618e26cea887 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -1017,7 +1017,7 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) dir_version = (long)dir->status.data_version; de_version = (long)dentry->d_fsdata; if (de_version == dir_version) - goto out_valid; + goto out_valid_noupdate; dir_version = (long)dir->invalid_before; if (de_version - dir_version >= 0) @@ -1081,6 +1081,7 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) out_valid: dentry->d_fsdata = (void *)dir_version; +out_valid_noupdate: dput(parent); key_put(key); _leave(" = 1 [valid]"); From 9dd0b82ef530cdfe805c9f7079c99e104be59a14 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 30 Jul 2019 14:38:52 +0100 Subject: [PATCH 012/157] afs: Fix missing dentry data version updating In the in-kernel afs filesystem, the d_fsdata dentry field is used to hold the data version of the parent directory when it was created or when d_revalidate() last caused it to be updated. This is compared to the ->invalid_before field in the directory inode, rather than the actual data version number, thereby allowing changes due to local edits to be ignored. Only if the server data version gets bumped unexpectedly (eg. by a competing client), do we need to revalidate stuff. However, the d_fsdata field should also be updated if an rpc op is performed that modifies that particular dentry. Such ops return the revised data version of the directory(ies) involved, so we should use that. This is particularly problematic for rename, since a dentry from one directory may be moved directly into another directory (ie. mv a/x b/x). It would then be sporting the wrong data version - and if this is in the future, for the destination directory, revalidations would be missed, leading to foreign renames and hard-link deletion being missed. Fix this by the following means: (1) Return the data version number from operations that read the directory contents - if they issue the read. This starts in afs_dir_iterate() and is used, ignored or passed back by its callers. (2) In afs_lookup*(), set the dentry version to the version returned by (1) before d_splice_alias() is called and the dentry published. (3) In afs_d_revalidate(), set the dentry version to that returned from (1) if an rpc call was issued. This means that if a parallel procedure, such as mkdir(), modifies the directory, we won't accidentally use the data version from that. (4) In afs_{mkdir,create,link,symlink}(), set the new dentry's version to the directory data version before d_instantiate() is called. (5) In afs_{rmdir,unlink}, update the target dentry's version to the directory data version as soon as we've updated the directory inode. (6) In afs_rename(), we need to unhash the old dentry before we start so that we don't get afs_d_revalidate() reverting the version change in cross-directory renames. We then need to set both the old and the new dentry versions the data version of the new directory before we call d_move() as d_move() will rehash them. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: David Howells --- fs/afs/dir.c | 84 +++++++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 70 insertions(+), 14 deletions(-) diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 618e26cea887..81207dc3c997 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -440,7 +440,7 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode, * iterate through the data blob that lists the contents of an AFS directory */ static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx, - struct key *key) + struct key *key, afs_dataversion_t *_dir_version) { struct afs_vnode *dvnode = AFS_FS_I(dir); struct afs_xdr_dir_page *dbuf; @@ -460,6 +460,7 @@ static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx, req = afs_read_dir(dvnode, key); if (IS_ERR(req)) return PTR_ERR(req); + *_dir_version = req->data_version; /* round the file position up to the next entry boundary */ ctx->pos += sizeof(union afs_xdr_dirent) - 1; @@ -514,7 +515,10 @@ static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx, */ static int afs_readdir(struct file *file, struct dir_context *ctx) { - return afs_dir_iterate(file_inode(file), ctx, afs_file_key(file)); + afs_dataversion_t dir_version; + + return afs_dir_iterate(file_inode(file), ctx, afs_file_key(file), + &dir_version); } /* @@ -555,7 +559,8 @@ static int afs_lookup_one_filldir(struct dir_context *ctx, const char *name, * - just returns the FID the dentry name maps to if found */ static int afs_do_lookup_one(struct inode *dir, struct dentry *dentry, - struct afs_fid *fid, struct key *key) + struct afs_fid *fid, struct key *key, + afs_dataversion_t *_dir_version) { struct afs_super_info *as = dir->i_sb->s_fs_info; struct afs_lookup_one_cookie cookie = { @@ -568,7 +573,7 @@ static int afs_do_lookup_one(struct inode *dir, struct dentry *dentry, _enter("{%lu},%p{%pd},", dir->i_ino, dentry, dentry); /* search the directory */ - ret = afs_dir_iterate(dir, &cookie.ctx, key); + ret = afs_dir_iterate(dir, &cookie.ctx, key, _dir_version); if (ret < 0) { _leave(" = %d [iter]", ret); return ret; @@ -642,6 +647,7 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, struct afs_server *server; struct afs_vnode *dvnode = AFS_FS_I(dir), *vnode; struct inode *inode = NULL, *ti; + afs_dataversion_t data_version = READ_ONCE(dvnode->status.data_version); int ret, i; _enter("{%lu},%p{%pd},", dir->i_ino, dentry, dentry); @@ -669,12 +675,14 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, cookie->fids[i].vid = as->volume->vid; /* search the directory */ - ret = afs_dir_iterate(dir, &cookie->ctx, key); + ret = afs_dir_iterate(dir, &cookie->ctx, key, &data_version); if (ret < 0) { inode = ERR_PTR(ret); goto out; } + dentry->d_fsdata = (void *)(unsigned long)data_version; + inode = ERR_PTR(-ENOENT); if (!cookie->found) goto out; @@ -968,7 +976,8 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) struct dentry *parent; struct inode *inode; struct key *key; - long dir_version, de_version; + afs_dataversion_t dir_version; + long de_version; int ret; if (flags & LOOKUP_RCU) @@ -1014,20 +1023,20 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) * on a 32-bit system, we only have 32 bits in the dentry to store the * version. */ - dir_version = (long)dir->status.data_version; + dir_version = dir->status.data_version; de_version = (long)dentry->d_fsdata; - if (de_version == dir_version) + if (de_version == (long)dir_version) goto out_valid_noupdate; - dir_version = (long)dir->invalid_before; - if (de_version - dir_version >= 0) + dir_version = dir->invalid_before; + if (de_version - (long)dir_version >= 0) goto out_valid; _debug("dir modified"); afs_stat_v(dir, n_reval); /* search the directory for this vnode */ - ret = afs_do_lookup_one(&dir->vfs_inode, dentry, &fid, key); + ret = afs_do_lookup_one(&dir->vfs_inode, dentry, &fid, key, &dir_version); switch (ret) { case 0: /* the filename maps to something */ @@ -1080,7 +1089,7 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) } out_valid: - dentry->d_fsdata = (void *)dir_version; + dentry->d_fsdata = (void *)(unsigned long)dir_version; out_valid_noupdate: dput(parent); key_put(key); @@ -1186,6 +1195,20 @@ static void afs_prep_for_new_inode(struct afs_fs_cursor *fc, iget_data->cb_s_break = fc->cbi->server->cb_s_break; } +/* + * Note that a dentry got changed. We need to set d_fsdata to the data version + * number derived from the result of the operation. It doesn't matter if + * d_fsdata goes backwards as we'll just revalidate. + */ +static void afs_update_dentry_version(struct afs_fs_cursor *fc, + struct dentry *dentry, + struct afs_status_cb *scb) +{ + if (fc->ac.error == 0) + dentry->d_fsdata = + (void *)(unsigned long)scb->status.data_version; +} + /* * create a directory on an AFS filesystem */ @@ -1228,6 +1251,7 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) afs_check_for_remote_deletion(&fc, dvnode); afs_vnode_commit_status(&fc, dvnode, fc.cb_break, &data_version, &scb[0]); + afs_update_dentry_version(&fc, dentry, &scb[0]); afs_vnode_new_inode(&fc, dentry, &iget_data, &scb[1]); ret = afs_end_vnode_operation(&fc); if (ret < 0) @@ -1320,6 +1344,7 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry) afs_vnode_commit_status(&fc, dvnode, fc.cb_break, &data_version, scb); + afs_update_dentry_version(&fc, dentry, scb); ret = afs_end_vnode_operation(&fc); if (ret == 0) { afs_dir_remove_subdir(dentry); @@ -1459,6 +1484,7 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry) &data_version, &scb[0]); afs_vnode_commit_status(&fc, vnode, fc.cb_break_2, &data_version_2, &scb[1]); + afs_update_dentry_version(&fc, dentry, &scb[0]); ret = afs_end_vnode_operation(&fc); if (ret == 0 && !(scb[1].have_status || scb[1].have_error)) ret = afs_dir_remove_link(dvnode, dentry, key); @@ -1527,6 +1553,7 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode, afs_check_for_remote_deletion(&fc, dvnode); afs_vnode_commit_status(&fc, dvnode, fc.cb_break, &data_version, &scb[0]); + afs_update_dentry_version(&fc, dentry, &scb[0]); afs_vnode_new_inode(&fc, dentry, &iget_data, &scb[1]); ret = afs_end_vnode_operation(&fc); if (ret < 0) @@ -1608,6 +1635,7 @@ static int afs_link(struct dentry *from, struct inode *dir, afs_vnode_commit_status(&fc, vnode, fc.cb_break_2, NULL, &scb[1]); ihold(&vnode->vfs_inode); + afs_update_dentry_version(&fc, dentry, &scb[0]); d_instantiate(dentry, &vnode->vfs_inode); mutex_unlock(&vnode->io_lock); @@ -1687,6 +1715,7 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry, afs_check_for_remote_deletion(&fc, dvnode); afs_vnode_commit_status(&fc, dvnode, fc.cb_break, &data_version, &scb[0]); + afs_update_dentry_version(&fc, dentry, &scb[0]); afs_vnode_new_inode(&fc, dentry, &iget_data, &scb[1]); ret = afs_end_vnode_operation(&fc); if (ret < 0) @@ -1792,6 +1821,17 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, } } + /* This bit is potentially nasty as there's a potential race with + * afs_d_revalidate{,_rcu}(). We have to change d_fsdata on the dentry + * to reflect it's new parent's new data_version after the op, but + * d_revalidate may see old_dentry between the op having taken place + * and the version being updated. + * + * So drop the old_dentry for now to make other threads go through + * lookup instead - which we hold a lock against. + */ + d_drop(old_dentry); + ret = -ERESTARTSYS; if (afs_begin_vnode_operation(&fc, orig_dvnode, key, true)) { afs_dataversion_t orig_data_version; @@ -1803,7 +1843,7 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, if (orig_dvnode != new_dvnode) { if (mutex_lock_interruptible_nested(&new_dvnode->io_lock, 1) < 0) { afs_end_vnode_operation(&fc); - goto error_rehash; + goto error_rehash_old; } new_data_version = new_dvnode->status.data_version + 1; } else { @@ -1828,7 +1868,7 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, } ret = afs_end_vnode_operation(&fc); if (ret < 0) - goto error_rehash; + goto error_rehash_old; } if (ret == 0) { @@ -1854,10 +1894,26 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, drop_nlink(new_inode); spin_unlock(&new_inode->i_lock); } + + /* Now we can update d_fsdata on the dentries to reflect their + * new parent's data_version. + * + * Note that if we ever implement RENAME_EXCHANGE, we'll have + * to update both dentries with opposing dir versions. + */ + if (new_dvnode != orig_dvnode) { + afs_update_dentry_version(&fc, old_dentry, &scb[1]); + afs_update_dentry_version(&fc, new_dentry, &scb[1]); + } else { + afs_update_dentry_version(&fc, old_dentry, &scb[0]); + afs_update_dentry_version(&fc, new_dentry, &scb[0]); + } d_move(old_dentry, new_dentry); goto error_tmp; } +error_rehash_old: + d_rehash(new_dentry); error_rehash: if (rehash) d_rehash(rehash); From 2b089bf8d19c66f70ae3b2d2d101be1ae49bfe24 Mon Sep 17 00:00:00 2001 From: Thomas Huth Date: Mon, 22 Jul 2019 11:20:08 +0200 Subject: [PATCH 013/157] kernel/configs: Replace GPL boilerplate code with SPDX identifier The FSF does not reside in "675 Mass Ave, Cambridge" anymore... let's replace the old GPL boilerplate code with a proper SPDX identifier instead. Signed-off-by: Thomas Huth Signed-off-by: Greg Kroah-Hartman --- kernel/configs.c | 16 +--------------- 1 file changed, 1 insertion(+), 15 deletions(-) diff --git a/kernel/configs.c b/kernel/configs.c index b062425ccf8d..c09ea4c995e1 100644 --- a/kernel/configs.c +++ b/kernel/configs.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * kernel/configs.c * Echo the kernel .config file used to build the kernel @@ -6,21 +7,6 @@ * Copyright (C) 2002 Randy Dunlap * Copyright (C) 2002 Al Stone * Copyright (C) 2002 Hewlett-Packard Company - * - * 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, GOOD TITLE or - * NON INFRINGEMENT. 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, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #include From ef349abd91c1b37f87639170bcd9d11fe3ac58ff Mon Sep 17 00:00:00 2001 From: Matthias Maennich Date: Thu, 25 Jul 2019 11:17:04 +0100 Subject: [PATCH 014/157] coccinelle: api/atomic_as_refcounter: add SPDX License Identifier Add the missing GPLv2 SPDX license identifier. It appears this single file was missing from 7f904d7e1f3e ("treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 505"), which addressed all other files in scripts/coccinelle. Hence I added GPL-2.0-only consitently with the mentioned patch. Cc: linux-spdx@vger.kernel.org Cc: Elena Reshetova Signed-off-by: Matthias Maennich Acked-by: Julia Lawall Signed-off-by: Greg Kroah-Hartman --- scripts/coccinelle/api/atomic_as_refcounter.cocci | 1 + 1 file changed, 1 insertion(+) diff --git a/scripts/coccinelle/api/atomic_as_refcounter.cocci b/scripts/coccinelle/api/atomic_as_refcounter.cocci index 988120e0fd67..0f78d94abc35 100644 --- a/scripts/coccinelle/api/atomic_as_refcounter.cocci +++ b/scripts/coccinelle/api/atomic_as_refcounter.cocci @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only // Check if refcount_t type and API should be used // instead of atomic_t type when dealing with refcounters // From fac7b714c514fcc555541e1d6450c694b0a5f8d3 Mon Sep 17 00:00:00 2001 From: Nishad Kamdar Date: Fri, 26 Jul 2019 19:58:45 +0530 Subject: [PATCH 015/157] intel_th: Use the correct style for SPDX License Identifier This patch corrects the SPDX License Identifier style in header files related to Drivers for Intel(R) Trace Hub controller. For C header files Documentation/process/license-rules.rst mandates C-like comments (opposed to C source files where C++ style should be used) Changes made by using a script provided by Joe Perches here: https://lkml.org/lkml/2019/2/7/46 Suggested-by: Joe Perches Signed-off-by: Nishad Kamdar Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/intel_th/msu.h | 2 +- drivers/hwtracing/intel_th/pti.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/hwtracing/intel_th/msu.h b/drivers/hwtracing/intel_th/msu.h index 574c16004cb2..13d9b141daaa 100644 --- a/drivers/hwtracing/intel_th/msu.h +++ b/drivers/hwtracing/intel_th/msu.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0 */ /* * Intel(R) Trace Hub Memory Storage Unit (MSU) data structures * diff --git a/drivers/hwtracing/intel_th/pti.h b/drivers/hwtracing/intel_th/pti.h index e9381babc84c..7dfc0431333b 100644 --- a/drivers/hwtracing/intel_th/pti.h +++ b/drivers/hwtracing/intel_th/pti.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0 */ /* * Intel(R) Trace Hub PTI output data structures * From 740ce365a4dccc1df4d05219cd5bf68f01359196 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 30 Jul 2019 08:49:34 -0600 Subject: [PATCH 016/157] dt-bindings: Fix generated example files getting added to schemas MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 837158b847a4 ("dt-bindings: Check the examples against the schemas") started generating YAML encoded DT files to validate the examples against the schema. When running 'make dt_binding_check' in tree after the 1st time, the generated example .dt.yaml files are mistakenly added to the list of schema files. Exclude *.example.dt.yaml files from the search for schema files. Fixes: 837158b847a4 ("dt-bindings: Check the examples against the schemas") Reported-by: Guido Günther Tested-by: Guido Günther Signed-off-by: Rob Herring --- Documentation/devicetree/bindings/Makefile | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/Makefile b/Documentation/devicetree/bindings/Makefile index 6b0dfd5c17ba..5138a2f6232a 100644 --- a/Documentation/devicetree/bindings/Makefile +++ b/Documentation/devicetree/bindings/Makefile @@ -19,7 +19,9 @@ quiet_cmd_mk_schema = SCHEMA $@ DT_DOCS = $(shell \ cd $(srctree)/$(src) && \ - find * \( -name '*.yaml' ! -name $(DT_TMP_SCHEMA) \) \ + find * \( -name '*.yaml' ! \ + -name $(DT_TMP_SCHEMA) ! \ + -name '*.example.dt.yaml' \) \ ) DT_SCHEMA_FILES ?= $(addprefix $(src)/,$(DT_DOCS)) From 3aed86731ee2b23e4dc4d2c6d943d33992cd551b Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Wed, 31 Jul 2019 17:35:31 -0600 Subject: [PATCH 017/157] nvmet: Fix use-after-free bug when a port is removed When a port is removed through configfs, any connected controllers are still active and can still send commands. This causes a use-after-free bug which is detected by KASAN for any admin command that dereferences req->port (like in nvmet_execute_identify_ctrl). To fix this, disconnect all active controllers when a subsystem is removed from a port. This ensures there are no active controllers when the port is eventually removed. Signed-off-by: Logan Gunthorpe Reviewed-by: Sagi Grimberg Reviewed-by: Max Gurtovoy Reviewed-by : Chaitanya Kulkarni Signed-off-by: Sagi Grimberg --- drivers/nvme/target/configfs.c | 1 + drivers/nvme/target/core.c | 12 ++++++++++++ drivers/nvme/target/nvmet.h | 3 +++ 3 files changed, 16 insertions(+) diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index cd52b9f15376..98613a45bd3b 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -675,6 +675,7 @@ static void nvmet_port_subsys_drop_link(struct config_item *parent, found: list_del(&p->entry); + nvmet_port_del_ctrls(port, subsys); nvmet_port_disc_changed(port, subsys); if (list_empty(&port->subsystems)) diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index dad0243c7c96..b86a23aa9020 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -280,6 +280,18 @@ void nvmet_unregister_transport(const struct nvmet_fabrics_ops *ops) } EXPORT_SYMBOL_GPL(nvmet_unregister_transport); +void nvmet_port_del_ctrls(struct nvmet_port *port, struct nvmet_subsys *subsys) +{ + struct nvmet_ctrl *ctrl; + + mutex_lock(&subsys->lock); + list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) { + if (ctrl->port == port) + ctrl->ops->delete_ctrl(ctrl); + } + mutex_unlock(&subsys->lock); +} + int nvmet_enable_port(struct nvmet_port *port) { const struct nvmet_fabrics_ops *ops; diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 6ee66c610739..c51f8dd01dc4 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -418,6 +418,9 @@ void nvmet_port_send_ana_event(struct nvmet_port *port); int nvmet_register_transport(const struct nvmet_fabrics_ops *ops); void nvmet_unregister_transport(const struct nvmet_fabrics_ops *ops); +void nvmet_port_del_ctrls(struct nvmet_port *port, + struct nvmet_subsys *subsys); + int nvmet_enable_port(struct nvmet_port *port); void nvmet_disable_port(struct nvmet_port *port); From 86b9a63e595ff03f9d0a7b92b6acc231fecefc29 Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Wed, 31 Jul 2019 17:35:32 -0600 Subject: [PATCH 018/157] nvmet-loop: Flush nvme_delete_wq when removing the port After calling nvme_loop_delete_ctrl(), the controllers will not yet be deleted because nvme_delete_ctrl() only schedules work to do the delete. This means a race can occur if a port is removed but there are still active controllers trying to access that memory. To fix this, flush the nvme_delete_wq before returning from nvme_loop_remove_port() so that any controllers that might be in the process of being deleted won't access a freed port. Signed-off-by: Logan Gunthorpe Reviewed-by: Sagi Grimberg Reviewed-by: Max Gurtovoy Reviewed-by : Chaitanya Kulkarni Signed-off-by: Sagi Grimberg --- drivers/nvme/target/loop.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index b16dc3981c69..0940c5024a34 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -654,6 +654,14 @@ static void nvme_loop_remove_port(struct nvmet_port *port) mutex_lock(&nvme_loop_ports_mutex); list_del_init(&port->entry); mutex_unlock(&nvme_loop_ports_mutex); + + /* + * Ensure any ctrls that are in the process of being + * deleted are in fact deleted before we return + * and free the port. This is to prevent active + * ctrls from using a port after it's freed. + */ + flush_workqueue(nvme_delete_wq); } static const struct nvmet_fabrics_ops nvme_loop_ops = { From cfc1a1af56200362d1508b82b9a3cc3acb2eae0c Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Wed, 31 Jul 2019 17:35:33 -0600 Subject: [PATCH 019/157] nvmet-file: fix nvmet_file_flush() always returning an error Presently, nvmet_file_flush() always returns a call to errno_to_nvme_status() but that helper doesn't take into account the case when errno=0. So nvmet_file_flush() always returns an error code. All other callers of errno_to_nvme_status() check for success before calling it. To fix this, ensure errno_to_nvme_status() returns success if the errno is zero. This should prevent future mistakes like this from happening. Fixes: c6aa3542e010 ("nvmet: add error log support for file backend") Signed-off-by: Logan Gunthorpe Reviewed-by: Sagi Grimberg Reviewed-by: Chaitanya Kulkarni Signed-off-by: Sagi Grimberg --- drivers/nvme/target/core.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index b86a23aa9020..3a67e244e568 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -46,6 +46,9 @@ inline u16 errno_to_nvme_status(struct nvmet_req *req, int errno) u16 status; switch (errno) { + case 0: + status = NVME_SC_SUCCESS; + break; case -ENOSPC: req->error_loc = offsetof(struct nvme_rw_command, length); status = NVME_SC_CAP_EXCEEDED | NVME_SC_DNR; From 8c36e66fb407ce076535a7db98ab9f6d720b866a Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Wed, 31 Jul 2019 17:35:34 -0600 Subject: [PATCH 020/157] nvme-core: Fix extra device_put() call on error path In the error path for nvme_init_subsystem(), nvme_put_subsystem() will call device_put(), but it will get called again after the mutex_unlock(). The device_put() only needs to be called if device_add() fails. This bug caused a KASAN use-after-free error when adding and removing subsytems in a loop: BUG: KASAN: use-after-free in device_del+0x8d9/0x9a0 Read of size 8 at addr ffff8883cdaf7120 by task multipathd/329 CPU: 0 PID: 329 Comm: multipathd Not tainted 5.2.0-rc6-vmlocalyes-00019-g70a2b39005fd-dirty #314 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014 Call Trace: dump_stack+0x7b/0xb5 print_address_description+0x6f/0x280 ? device_del+0x8d9/0x9a0 __kasan_report+0x148/0x199 ? device_del+0x8d9/0x9a0 ? class_release+0x100/0x130 ? device_del+0x8d9/0x9a0 kasan_report+0x12/0x20 __asan_report_load8_noabort+0x14/0x20 device_del+0x8d9/0x9a0 ? device_platform_notify+0x70/0x70 nvme_destroy_subsystem+0xf9/0x150 nvme_free_ctrl+0x280/0x3a0 device_release+0x72/0x1d0 kobject_put+0x144/0x410 put_device+0x13/0x20 nvme_free_ns+0xc4/0x100 nvme_release+0xb3/0xe0 __blkdev_put+0x549/0x6e0 ? kasan_check_write+0x14/0x20 ? bd_set_size+0xb0/0xb0 ? kasan_check_write+0x14/0x20 ? mutex_lock+0x8f/0xe0 ? __mutex_lock_slowpath+0x20/0x20 ? locks_remove_file+0x239/0x370 blkdev_put+0x72/0x2c0 blkdev_close+0x8d/0xd0 __fput+0x256/0x770 ? _raw_read_lock_irq+0x40/0x40 ____fput+0xe/0x10 task_work_run+0x10c/0x180 ? filp_close+0xf7/0x140 exit_to_usermode_loop+0x151/0x170 do_syscall_64+0x240/0x2e0 ? prepare_exit_to_usermode+0xd5/0x190 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7f5a79af05d7 Code: 00 00 0f 05 48 3d 00 f0 ff ff 77 3f c3 66 0f 1f 44 00 00 53 89 fb 48 83 ec 10 e8 c4 fb ff ff 89 df 89 c2 b8 03 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 2b 89 d7 89 44 24 0c e8 06 fc ff ff 8b 44 24 RSP: 002b:00007f5a7799c810 EFLAGS: 00000293 ORIG_RAX: 0000000000000003 RAX: 0000000000000000 RBX: 0000000000000008 RCX: 00007f5a79af05d7 RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000008 RBP: 00007f5a58000f98 R08: 0000000000000002 R09: 00007f5a7935ee80 R10: 0000000000000000 R11: 0000000000000293 R12: 000055e432447240 R13: 0000000000000000 R14: 0000000000000001 R15: 000055e4324a9cf0 Allocated by task 1236: save_stack+0x21/0x80 __kasan_kmalloc.constprop.6+0xab/0xe0 kasan_kmalloc+0x9/0x10 kmem_cache_alloc_trace+0x102/0x210 nvme_init_identify+0x13c3/0x3820 nvme_loop_configure_admin_queue+0x4fa/0x5e0 nvme_loop_create_ctrl+0x469/0xf40 nvmf_dev_write+0x19a3/0x21ab __vfs_write+0x66/0x120 vfs_write+0x154/0x490 ksys_write+0x104/0x240 __x64_sys_write+0x73/0xb0 do_syscall_64+0xa5/0x2e0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Freed by task 329: save_stack+0x21/0x80 __kasan_slab_free+0x129/0x190 kasan_slab_free+0xe/0x10 kfree+0xa7/0x200 nvme_release_subsystem+0x49/0x60 device_release+0x72/0x1d0 kobject_put+0x144/0x410 put_device+0x13/0x20 klist_class_dev_put+0x31/0x40 klist_put+0x8f/0xf0 klist_del+0xe/0x10 device_del+0x3a7/0x9a0 nvme_destroy_subsystem+0xf9/0x150 nvme_free_ctrl+0x280/0x3a0 device_release+0x72/0x1d0 kobject_put+0x144/0x410 put_device+0x13/0x20 nvme_free_ns+0xc4/0x100 nvme_release+0xb3/0xe0 __blkdev_put+0x549/0x6e0 blkdev_put+0x72/0x2c0 blkdev_close+0x8d/0xd0 __fput+0x256/0x770 ____fput+0xe/0x10 task_work_run+0x10c/0x180 exit_to_usermode_loop+0x151/0x170 do_syscall_64+0x240/0x2e0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Fixes: 32fd90c40768 ("nvme: change locking for the per-subsystem controller list") Signed-off-by: Logan Gunthorpe Reviewed-by: Sagi Grimberg Reviewed-by : Chaitanya Kulkarni Signed-off-by: Sagi Grimberg --- drivers/nvme/host/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 80c7a7ee240b..e35f16b60fc9 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2488,6 +2488,7 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) if (ret) { dev_err(ctrl->device, "failed to register subsystem device.\n"); + put_device(&subsys->dev); goto out_unlock; } ida_init(&subsys->ns_ida); @@ -2510,7 +2511,6 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) nvme_put_subsystem(subsys); out_unlock: mutex_unlock(&nvme_subsystems_lock); - put_device(&subsys->dev); return ret; } From b9156daeb1601d69007b7e50efcf89d69d72ec1d Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Wed, 31 Jul 2019 11:00:26 -0700 Subject: [PATCH 021/157] nvme: fix a possible deadlock when passthru commands sent to a multipath device When the user issues a command with side effects, we will end up freezing the namespace request queue when updating disk info (and the same for the corresponding mpath disk node). However, we are not freezing the mpath node request queue, which means that mpath I/O can still come in and block on blk_queue_enter (called from nvme_ns_head_make_request -> direct_make_request). This is a deadlock, because blk_queue_enter will block until the inner namespace request queue is unfroze, but that process is blocked because the namespace revalidation is trying to update the mpath disk info and freeze its request queue (which will never complete because of the I/O that is blocked on blk_queue_enter). Fix this by freezing all the subsystem nsheads request queues before executing the passthru command. Given that these commands are infrequent we should not worry about this temporary I/O freeze to keep things sane. Here is the matching hang traces: -- [ 374.465002] INFO: task systemd-udevd:17994 blocked for more than 122 seconds. [ 374.472975] Not tainted 5.2.0-rc3-mpdebug+ #42 [ 374.478522] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 374.487274] systemd-udevd D 0 17994 1 0x00000000 [ 374.493407] Call Trace: [ 374.496145] __schedule+0x2ef/0x620 [ 374.500047] schedule+0x38/0xa0 [ 374.503569] blk_queue_enter+0x139/0x220 [ 374.507959] ? remove_wait_queue+0x60/0x60 [ 374.512540] direct_make_request+0x60/0x130 [ 374.517219] nvme_ns_head_make_request+0x11d/0x420 [nvme_core] [ 374.523740] ? generic_make_request_checks+0x307/0x6f0 [ 374.529484] generic_make_request+0x10d/0x2e0 [ 374.534356] submit_bio+0x75/0x140 [ 374.538163] ? guard_bio_eod+0x32/0xe0 [ 374.542361] submit_bh_wbc+0x171/0x1b0 [ 374.546553] block_read_full_page+0x1ed/0x330 [ 374.551426] ? check_disk_change+0x70/0x70 [ 374.556008] ? scan_shadow_nodes+0x30/0x30 [ 374.560588] blkdev_readpage+0x18/0x20 [ 374.564783] do_read_cache_page+0x301/0x860 [ 374.569463] ? blkdev_writepages+0x10/0x10 [ 374.574037] ? prep_new_page+0x88/0x130 [ 374.578329] ? get_page_from_freelist+0xa2f/0x1280 [ 374.583688] ? __alloc_pages_nodemask+0x179/0x320 [ 374.588947] read_cache_page+0x12/0x20 [ 374.593142] read_dev_sector+0x2d/0xd0 [ 374.597337] read_lba+0x104/0x1f0 [ 374.601046] find_valid_gpt+0xfa/0x720 [ 374.605243] ? string_nocheck+0x58/0x70 [ 374.609534] ? find_valid_gpt+0x720/0x720 [ 374.614016] efi_partition+0x89/0x430 [ 374.618113] ? string+0x48/0x60 [ 374.621632] ? snprintf+0x49/0x70 [ 374.625339] ? find_valid_gpt+0x720/0x720 [ 374.629828] check_partition+0x116/0x210 [ 374.634214] rescan_partitions+0xb6/0x360 [ 374.638699] __blkdev_reread_part+0x64/0x70 [ 374.643377] blkdev_reread_part+0x23/0x40 [ 374.647860] blkdev_ioctl+0x48c/0x990 [ 374.651956] block_ioctl+0x41/0x50 [ 374.655766] do_vfs_ioctl+0xa7/0x600 [ 374.659766] ? locks_lock_inode_wait+0xb1/0x150 [ 374.664832] ksys_ioctl+0x67/0x90 [ 374.668539] __x64_sys_ioctl+0x1a/0x20 [ 374.672732] do_syscall_64+0x5a/0x1c0 [ 374.676828] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 374.738474] INFO: task nvmeadm:49141 blocked for more than 123 seconds. [ 374.745871] Not tainted 5.2.0-rc3-mpdebug+ #42 [ 374.751419] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 374.760170] nvmeadm D 0 49141 36333 0x00004080 [ 374.766301] Call Trace: [ 374.769038] __schedule+0x2ef/0x620 [ 374.772939] schedule+0x38/0xa0 [ 374.776452] blk_mq_freeze_queue_wait+0x59/0x100 [ 374.781614] ? remove_wait_queue+0x60/0x60 [ 374.786192] blk_mq_freeze_queue+0x1a/0x20 [ 374.790773] nvme_update_disk_info.isra.57+0x5f/0x350 [nvme_core] [ 374.797582] ? nvme_identify_ns.isra.50+0x71/0xc0 [nvme_core] [ 374.804006] __nvme_revalidate_disk+0xe5/0x110 [nvme_core] [ 374.810139] nvme_revalidate_disk+0xa6/0x120 [nvme_core] [ 374.816078] ? nvme_submit_user_cmd+0x11e/0x320 [nvme_core] [ 374.822299] nvme_user_cmd+0x264/0x370 [nvme_core] [ 374.827661] nvme_dev_ioctl+0x112/0x1d0 [nvme_core] [ 374.833114] do_vfs_ioctl+0xa7/0x600 [ 374.837117] ? __audit_syscall_entry+0xdd/0x130 [ 374.842184] ksys_ioctl+0x67/0x90 [ 374.845891] __x64_sys_ioctl+0x1a/0x20 [ 374.850082] do_syscall_64+0x5a/0x1c0 [ 374.854178] entry_SYSCALL_64_after_hwframe+0x44/0xa9 -- Reported-by: James Puthukattukaran Tested-by: James Puthukattukaran Reviewed-by: Keith Busch Signed-off-by: Sagi Grimberg --- drivers/nvme/host/core.c | 5 +++++ drivers/nvme/host/multipath.c | 30 ++++++++++++++++++++++++++++++ drivers/nvme/host/nvme.h | 12 ++++++++++++ 3 files changed, 47 insertions(+) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index e35f16b60fc9..88b8dfd7928a 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1286,6 +1286,9 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns, */ if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) { mutex_lock(&ctrl->scan_lock); + mutex_lock(&ctrl->subsys->lock); + nvme_mpath_start_freeze(ctrl->subsys); + nvme_mpath_wait_freeze(ctrl->subsys); nvme_start_freeze(ctrl); nvme_wait_freeze(ctrl); } @@ -1316,6 +1319,8 @@ static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects) nvme_update_formats(ctrl); if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) { nvme_unfreeze(ctrl); + nvme_mpath_unfreeze(ctrl->subsys); + mutex_unlock(&ctrl->subsys->lock); mutex_unlock(&ctrl->scan_lock); } if (effects & NVME_CMD_EFFECTS_CCC) diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 4f0d0d12744e..b34dcb2288e7 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -12,6 +12,36 @@ module_param(multipath, bool, 0444); MODULE_PARM_DESC(multipath, "turn on native support for multiple controllers per subsystem"); +void nvme_mpath_unfreeze(struct nvme_subsystem *subsys) +{ + struct nvme_ns_head *h; + + lockdep_assert_held(&subsys->lock); + list_for_each_entry(h, &subsys->nsheads, entry) + if (h->disk) + blk_mq_unfreeze_queue(h->disk->queue); +} + +void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys) +{ + struct nvme_ns_head *h; + + lockdep_assert_held(&subsys->lock); + list_for_each_entry(h, &subsys->nsheads, entry) + if (h->disk) + blk_mq_freeze_queue_wait(h->disk->queue); +} + +void nvme_mpath_start_freeze(struct nvme_subsystem *subsys) +{ + struct nvme_ns_head *h; + + lockdep_assert_held(&subsys->lock); + list_for_each_entry(h, &subsys->nsheads, entry) + if (h->disk) + blk_freeze_queue_start(h->disk->queue); +} + /* * If multipathing is enabled we need to always use the subsystem instance * number for numbering our devices to avoid conflicts between subsystems that diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 26b563f9985b..6b4fb67124c6 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -490,6 +490,9 @@ static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl) return ctrl->ana_log_buf != NULL; } +void nvme_mpath_unfreeze(struct nvme_subsystem *subsys); +void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys); +void nvme_mpath_start_freeze(struct nvme_subsystem *subsys); void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns, struct nvme_ctrl *ctrl, int *flags); void nvme_failover_req(struct request *req); @@ -568,6 +571,15 @@ static inline void nvme_mpath_uninit(struct nvme_ctrl *ctrl) static inline void nvme_mpath_stop(struct nvme_ctrl *ctrl) { } +static inline void nvme_mpath_unfreeze(struct nvme_subsystem *subsys) +{ +} +static inline void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys) +{ +} +static inline void nvme_mpath_start_freeze(struct nvme_subsystem *subsys) +{ +} #endif /* CONFIG_NVME_MULTIPATH */ #ifdef CONFIG_NVM From d94211b8bad3787e0655a67284105f57db728cb1 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Fri, 26 Jul 2019 10:29:49 -0700 Subject: [PATCH 022/157] nvme-rdma: fix possible use-after-free in connect error flow When start_queue fails, we need to make sure to drain the queue cq before freeing the rdma resources because we might still race with the completion path. Have start_queue() error path safely stop the queue. -- [30371.808111] nvme nvme1: Failed reconnect attempt 11 [30371.808113] nvme nvme1: Reconnecting in 10 seconds... [...] [30382.069315] nvme nvme1: creating 4 I/O queues. [30382.257058] nvme nvme1: Connect Invalid SQE Parameter, qid 4 [30382.257061] nvme nvme1: failed to connect queue: 4 ret=386 [30382.305001] BUG: unable to handle kernel NULL pointer dereference at 0000000000000018 [30382.305022] IP: qedr_poll_cq+0x8a3/0x1170 [qedr] [30382.305028] PGD 0 P4D 0 [30382.305037] Oops: 0000 [#1] SMP PTI [...] [30382.305153] Call Trace: [30382.305166] ? __switch_to_asm+0x34/0x70 [30382.305187] __ib_process_cq+0x56/0xd0 [ib_core] [30382.305201] ib_poll_handler+0x26/0x70 [ib_core] [30382.305213] irq_poll_softirq+0x88/0x110 [30382.305223] ? sort_range+0x20/0x20 [30382.305232] __do_softirq+0xde/0x2c6 [30382.305241] ? sort_range+0x20/0x20 [30382.305249] run_ksoftirqd+0x1c/0x60 [30382.305258] smpboot_thread_fn+0xef/0x160 [30382.305265] kthread+0x113/0x130 [30382.305273] ? kthread_create_worker_on_cpu+0x50/0x50 [30382.305281] ret_from_fork+0x35/0x40 -- Reported-by: Nicolas Morey-Chaisemartin Reviewed-by: Max Gurtovoy Reviewed-by: Hannes Reinecke Signed-off-by: Sagi Grimberg --- drivers/nvme/host/rdma.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index a249db528d54..1a6449bc547b 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -562,13 +562,17 @@ static int nvme_rdma_alloc_queue(struct nvme_rdma_ctrl *ctrl, return ret; } +static void __nvme_rdma_stop_queue(struct nvme_rdma_queue *queue) +{ + rdma_disconnect(queue->cm_id); + ib_drain_qp(queue->qp); +} + static void nvme_rdma_stop_queue(struct nvme_rdma_queue *queue) { if (!test_and_clear_bit(NVME_RDMA_Q_LIVE, &queue->flags)) return; - - rdma_disconnect(queue->cm_id); - ib_drain_qp(queue->qp); + __nvme_rdma_stop_queue(queue); } static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue) @@ -607,11 +611,13 @@ static int nvme_rdma_start_queue(struct nvme_rdma_ctrl *ctrl, int idx) else ret = nvmf_connect_admin_queue(&ctrl->ctrl); - if (!ret) + if (!ret) { set_bit(NVME_RDMA_Q_LIVE, &queue->flags); - else + } else { + __nvme_rdma_stop_queue(queue); dev_info(ctrl->ctrl.device, "failed to connect queue: %d ret=%d\n", idx, ret); + } return ret; } From 0157ec8dad3c8fc9bc9790f76e0831ffdaf2e7f0 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Thu, 25 Jul 2019 11:56:57 -0700 Subject: [PATCH 023/157] nvme: fix controller removal race with scan work With multipath enabled, nvme_scan_work() can read from the device (through nvme_mpath_add_disk()) and hang [1]. However, with fabrics, once ctrl->state is set to NVME_CTRL_DELETING, the reads will hang (see nvmf_check_ready()) and the mpath stack device make_request will block if head->list is not empty. However, when the head->list consistst of only DELETING/DEAD controllers, we should actually not block, but rather fail immediately. In addition, before we go ahead and remove the namespaces, make sure to clear the current path and kick the requeue list so that the request will fast fail upon requeuing. [1]: -- INFO: task kworker/u4:3:166 blocked for more than 120 seconds. Not tainted 5.2.0-rc6-vmlocalyes-00005-g808c8c2dc0cf #316 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. kworker/u4:3 D 0 166 2 0x80004000 Workqueue: nvme-wq nvme_scan_work Call Trace: __schedule+0x851/0x1400 schedule+0x99/0x210 io_schedule+0x21/0x70 do_read_cache_page+0xa57/0x1330 read_cache_page+0x4a/0x70 read_dev_sector+0xbf/0x380 amiga_partition+0xc4/0x1230 check_partition+0x30f/0x630 rescan_partitions+0x19a/0x980 __blkdev_get+0x85a/0x12f0 blkdev_get+0x2a5/0x790 __device_add_disk+0xe25/0x1250 device_add_disk+0x13/0x20 nvme_mpath_set_live+0x172/0x2b0 nvme_update_ns_ana_state+0x130/0x180 nvme_set_ns_ana_state+0x9a/0xb0 nvme_parse_ana_log+0x1c3/0x4a0 nvme_mpath_add_disk+0x157/0x290 nvme_validate_ns+0x1017/0x1bd0 nvme_scan_work+0x44d/0x6a0 process_one_work+0x7d7/0x1240 worker_thread+0x8e/0xff0 kthread+0x2c3/0x3b0 ret_from_fork+0x35/0x40 INFO: task kworker/u4:1:1034 blocked for more than 120 seconds. Not tainted 5.2.0-rc6-vmlocalyes-00005-g808c8c2dc0cf #316 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. kworker/u4:1 D 0 1034 2 0x80004000 Workqueue: nvme-delete-wq nvme_delete_ctrl_work Call Trace: __schedule+0x851/0x1400 schedule+0x99/0x210 schedule_timeout+0x390/0x830 wait_for_completion+0x1a7/0x310 __flush_work+0x241/0x5d0 flush_work+0x10/0x20 nvme_remove_namespaces+0x85/0x3d0 nvme_do_delete_ctrl+0xb4/0x1e0 nvme_delete_ctrl_work+0x15/0x20 process_one_work+0x7d7/0x1240 worker_thread+0x8e/0xff0 kthread+0x2c3/0x3b0 ret_from_fork+0x35/0x40 -- Reported-by: Logan Gunthorpe Tested-by: Logan Gunthorpe Reviewed-by: Logan Gunthorpe Reviewed-by: Ming Lei Signed-off-by: Sagi Grimberg --- drivers/nvme/host/core.c | 7 ++++++ drivers/nvme/host/multipath.c | 46 ++++++++++++++++++++++++++++++----- drivers/nvme/host/nvme.h | 9 +++++-- 3 files changed, 54 insertions(+), 8 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 88b8dfd7928a..c258a1ce4b28 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3577,6 +3577,13 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl) struct nvme_ns *ns, *next; LIST_HEAD(ns_list); + /* + * make sure to requeue I/O to all namespaces as these + * might result from the scan itself and must complete + * for the scan_work to make progress + */ + nvme_mpath_clear_ctrl_paths(ctrl); + /* prevent racing with ns scanning */ flush_work(&ctrl->scan_work); diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index b34dcb2288e7..888d4543894e 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -134,18 +134,34 @@ static const char *nvme_ana_state_names[] = { [NVME_ANA_CHANGE] = "change", }; -void nvme_mpath_clear_current_path(struct nvme_ns *ns) +bool nvme_mpath_clear_current_path(struct nvme_ns *ns) { struct nvme_ns_head *head = ns->head; + bool changed = false; int node; if (!head) - return; + goto out; for_each_node(node) { - if (ns == rcu_access_pointer(head->current_path[node])) + if (ns == rcu_access_pointer(head->current_path[node])) { rcu_assign_pointer(head->current_path[node], NULL); + changed = true; + } } +out: + return changed; +} + +void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl) +{ + struct nvme_ns *ns; + + mutex_lock(&ctrl->scan_lock); + list_for_each_entry(ns, &ctrl->namespaces, list) + if (nvme_mpath_clear_current_path(ns)) + kblockd_schedule_work(&ns->head->requeue_work); + mutex_unlock(&ctrl->scan_lock); } static bool nvme_path_is_disabled(struct nvme_ns *ns) @@ -256,6 +272,24 @@ inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head) return ns; } +static bool nvme_available_path(struct nvme_ns_head *head) +{ + struct nvme_ns *ns; + + list_for_each_entry_rcu(ns, &head->list, siblings) { + switch (ns->ctrl->state) { + case NVME_CTRL_LIVE: + case NVME_CTRL_RESETTING: + case NVME_CTRL_CONNECTING: + /* fallthru */ + return true; + default: + break; + } + } + return false; +} + static blk_qc_t nvme_ns_head_make_request(struct request_queue *q, struct bio *bio) { @@ -282,14 +316,14 @@ static blk_qc_t nvme_ns_head_make_request(struct request_queue *q, disk_devt(ns->head->disk), bio->bi_iter.bi_sector); ret = direct_make_request(bio); - } else if (!list_empty_careful(&head->list)) { - dev_warn_ratelimited(dev, "no path available - requeuing I/O\n"); + } else if (nvme_available_path(head)) { + dev_warn_ratelimited(dev, "no usable path - requeuing I/O\n"); spin_lock_irq(&head->requeue_lock); bio_list_add(&head->requeue_list, bio); spin_unlock_irq(&head->requeue_lock); } else { - dev_warn_ratelimited(dev, "no path - failing I/O\n"); + dev_warn_ratelimited(dev, "no available path - failing I/O\n"); bio->bi_status = BLK_STS_IOERR; bio_endio(bio); diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 6b4fb67124c6..778b3a0b6adb 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -503,7 +503,8 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head); int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id); void nvme_mpath_uninit(struct nvme_ctrl *ctrl); void nvme_mpath_stop(struct nvme_ctrl *ctrl); -void nvme_mpath_clear_current_path(struct nvme_ns *ns); +bool nvme_mpath_clear_current_path(struct nvme_ns *ns); +void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl); struct nvme_ns *nvme_find_path(struct nvme_ns_head *head); static inline void nvme_mpath_check_last_path(struct nvme_ns *ns) @@ -551,7 +552,11 @@ static inline void nvme_mpath_add_disk(struct nvme_ns *ns, static inline void nvme_mpath_remove_disk(struct nvme_ns_head *head) { } -static inline void nvme_mpath_clear_current_path(struct nvme_ns *ns) +static inline bool nvme_mpath_clear_current_path(struct nvme_ns *ns) +{ + return false; +} +static inline void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl) { } static inline void nvme_mpath_check_last_path(struct nvme_ns *ns) From bd46a90634302bfe791e93ad5496f98f165f7ae0 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Mon, 29 Jul 2019 16:34:52 -0600 Subject: [PATCH 024/157] nvme-pci: Fix async probe remove race Ensure the controller is not in the NEW state when nvme_probe() exits. This will always allow a subsequent nvme_remove() to set the state to DELETING, fixing a potential race between the initial asynchronous probe and device removal. Reported-by: Li Zhong Reviewed-by: Sagi Grimberg Signed-off-by: Keith Busch Signed-off-by: Sagi Grimberg --- drivers/nvme/host/pci.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index db160cee42ad..0c2c4b0c6655 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2695,7 +2695,7 @@ static void nvme_async_probe(void *data, async_cookie_t cookie) { struct nvme_dev *dev = data; - nvme_reset_ctrl_sync(&dev->ctrl); + flush_work(&dev->ctrl.reset_work); flush_work(&dev->ctrl.scan_work); nvme_put_ctrl(&dev->ctrl); } @@ -2761,6 +2761,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev)); + nvme_reset_ctrl(&dev->ctrl); nvme_get_ctrl(&dev->ctrl); async_schedule(nvme_async_probe, dev); From b07dd9b400981f487940a4d84292d3a0e7cd9362 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Thu, 25 Jul 2019 18:40:05 -0500 Subject: [PATCH 025/157] soundwire: cadence_master: fix register definition for SLAVE_STATE wrong prefix and wrong macro. Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20190725234032.21152-14-pierre-louis.bossart@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/cadence_master.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c index ff4badc9b3de..c2e3d93c4ddc 100644 --- a/drivers/soundwire/cadence_master.c +++ b/drivers/soundwire/cadence_master.c @@ -81,8 +81,8 @@ #define CDNS_MCP_INTSET 0x4C -#define CDNS_SDW_SLAVE_STAT 0x50 -#define CDNS_MCP_SLAVE_STAT_MASK BIT(1, 0) +#define CDNS_MCP_SLAVE_STAT 0x50 +#define CDNS_MCP_SLAVE_STAT_MASK GENMASK(1, 0) #define CDNS_MCP_SLAVE_INTSTAT0 0x54 #define CDNS_MCP_SLAVE_INTSTAT1 0x58 From 664b16589f882202b8fa8149d0074f3159bade76 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Thu, 25 Jul 2019 18:40:06 -0500 Subject: [PATCH 026/157] soundwire: cadence_master: fix definitions for INTSTAT0/1 Two off-by-one errors: INTSTAT0 missed BIT(31) and INTSTAT1 is only defined on first 16 bits. Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20190725234032.21152-15-pierre-louis.bossart@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/cadence_master.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c index c2e3d93c4ddc..60e8bdee5c75 100644 --- a/drivers/soundwire/cadence_master.c +++ b/drivers/soundwire/cadence_master.c @@ -96,8 +96,8 @@ #define CDNS_MCP_SLAVE_INTMASK0 0x5C #define CDNS_MCP_SLAVE_INTMASK1 0x60 -#define CDNS_MCP_SLAVE_INTMASK0_MASK GENMASK(30, 0) -#define CDNS_MCP_SLAVE_INTMASK1_MASK GENMASK(16, 0) +#define CDNS_MCP_SLAVE_INTMASK0_MASK GENMASK(31, 0) +#define CDNS_MCP_SLAVE_INTMASK1_MASK GENMASK(15, 0) #define CDNS_MCP_PORT_INTSTAT 0x64 #define CDNS_MCP_PDI_STAT 0x6C From 294fc7a4c8ec42b3053b1d2e87b0dafef80a76b8 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Thu, 1 Aug 2019 13:47:07 -0700 Subject: [PATCH 027/157] fs: xfs: xfs_log: Don't use KM_MAYFAIL at xfs_log_reserve(). When the system is close-to-OOM, fsync() may fail due to -ENOMEM because xfs_log_reserve() is using KM_MAYFAIL. It is a bad thing to fail writeback operation due to user-triggerable OOM condition. Since we are not using KM_MAYFAIL at xfs_trans_alloc() before calling xfs_log_reserve(), let's use the same flags at xfs_log_reserve(). oom-torture: page allocation failure: order:0, mode:0x46c40(GFP_NOFS|__GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_COMP), nodemask=(null) CPU: 7 PID: 1662 Comm: oom-torture Kdump: loaded Not tainted 5.3.0-rc2+ #925 Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 Call Trace: dump_stack+0x67/0x95 warn_alloc+0xa9/0x140 __alloc_pages_slowpath+0x9a8/0xbce __alloc_pages_nodemask+0x372/0x3b0 alloc_slab_page+0x3a/0x8d0 new_slab+0x330/0x420 ___slab_alloc.constprop.94+0x879/0xb00 __slab_alloc.isra.89.constprop.93+0x43/0x6f kmem_cache_alloc+0x331/0x390 kmem_zone_alloc+0x9f/0x110 [xfs] kmem_zone_alloc+0x9f/0x110 [xfs] xlog_ticket_alloc+0x33/0xd0 [xfs] xfs_log_reserve+0xb4/0x410 [xfs] xfs_trans_reserve+0x1d1/0x2b0 [xfs] xfs_trans_alloc+0xc9/0x250 [xfs] xfs_setfilesize_trans_alloc.isra.27+0x44/0xc0 [xfs] xfs_submit_ioend.isra.28+0xa5/0x180 [xfs] xfs_vm_writepages+0x76/0xa0 [xfs] do_writepages+0x17/0x80 __filemap_fdatawrite_range+0xc1/0xf0 file_write_and_wait_range+0x53/0xa0 xfs_file_fsync+0x87/0x290 [xfs] vfs_fsync_range+0x37/0x80 do_fsync+0x38/0x60 __x64_sys_fsync+0xf/0x20 do_syscall_64+0x4a/0x1c0 entry_SYSCALL_64_after_hwframe+0x49/0xbe Fixes: eb01c9cd87 ("[XFS] Remove the xlog_ticket allocator") Signed-off-by: Tetsuo Handa Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_log.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 00e9f5c388d3..7fc3c1ad36bc 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -429,10 +429,7 @@ xfs_log_reserve( ASSERT(*ticp == NULL); tic = xlog_ticket_alloc(log, unit_bytes, cnt, client, permanent, - KM_SLEEP | KM_MAYFAIL); - if (!tic) - return -ENOMEM; - + KM_SLEEP); *ticp = tic; xlog_grant_push_ail(log, tic->t_cnt ? tic->t_unit_res * tic->t_cnt From 7e7ae38bf928c5cfa6dd6e9a2cf8b42c84a27c92 Mon Sep 17 00:00:00 2001 From: Yoshiaki Okamoto Date: Sat, 20 Jul 2019 22:23:18 +0900 Subject: [PATCH 028/157] USB: serial: option: Add support for ZTE MF871A This patch adds support for MF871A USB modem (aka Speed USB STICK U03) to option driver. This modem is manufactured by ZTE corporation, and sold by KDDI. Interface layout: 0: AT 1: MODEM usb-devices output: T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 9 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=19d2 ProdID=1481 Rev=52.87 S: Manufacturer=ZTE,Incorporated S: Product=ZTE Technologies MSM S: SerialNumber=1234567890ABCDEF C: #Ifs= 2 Cfg#= 1 Atr=80 MxPwr=500mA I: If#= 0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option Co-developed-by: Hiroyuki Yamamoto Signed-off-by: Hiroyuki Yamamoto Signed-off-by: Yoshiaki Okamoto Cc: stable Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index c1582fbd1150..23d4a5f543af 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1549,6 +1549,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1428, 0xff, 0xff, 0xff), /* Telewell TW-LTE 4G v2 */ .driver_info = RSVD(2) }, { USB_DEVICE_INTERFACE_CLASS(ZTE_VENDOR_ID, 0x1476, 0xff) }, /* GosunCn ZTE WeLink ME3630 (ECM/NCM mode) */ + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1481, 0xff, 0x00, 0x00) }, /* ZTE MF871A */ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1533, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1534, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1535, 0xff, 0xff, 0xff) }, From 552573e42aab5f75aff9bab855a9677979d9a7d5 Mon Sep 17 00:00:00 2001 From: Rogan Dawes Date: Wed, 17 Jul 2019 11:11:34 +0200 Subject: [PATCH 029/157] USB: serial: option: add D-Link DWM-222 device ID Add device id for D-Link DWM-222 A2. MI_00 D-Link HS-USB Diagnostics MI_01 D-Link HS-USB Modem MI_02 D-Link HS-USB AT Port MI_03 D-Link HS-USB NMEA MI_04 D-Link HS-USB WWAN Adapter (qmi_wwan) MI_05 USB Mass Storage Device Cc: stable@vger.kernel.org Signed-off-by: Rogan Dawes Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 23d4a5f543af..f2c19660ed16 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1953,6 +1953,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(4) }, { USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7e35, 0xff), /* D-Link DWM-222 */ .driver_info = RSVD(4) }, + { USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7e3d, 0xff), /* D-Link DWM-222 A2 */ + .driver_info = RSVD(4) }, { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e01, 0xff, 0xff, 0xff) }, /* D-Link DWM-152/C1 */ { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e02, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/C1 */ { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x7e11, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/A3 */ From 0dda5907b0fc60f72f67f479f224e02c95d06e21 Mon Sep 17 00:00:00 2001 From: Nishad Kamdar Date: Sat, 3 Aug 2019 19:43:35 +0530 Subject: [PATCH 030/157] i2c: stm32: Use the correct style for SPDX License Identifier This patch corrects the SPDX License Identifier style in header file related to STM32 Driver for I2C hardware bus support. For C header files Documentation/process/license-rules.rst mandates C-like comments (opposed to C source files where C++ style should be used) Changes made by using a script provided by Joe Perches here: https://lkml.org/lkml/2019/2/7/46 Suggested-by: Joe Perches Signed-off-by: Nishad Kamdar Signed-off-by: Greg Kroah-Hartman --- drivers/i2c/busses/i2c-stm32.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/i2c/busses/i2c-stm32.h b/drivers/i2c/busses/i2c-stm32.h index 868755f82f88..2c21893905a3 100644 --- a/drivers/i2c/busses/i2c-stm32.h +++ b/drivers/i2c/busses/i2c-stm32.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0 */ /* * i2c-stm32.h * From 82a5008a341d301da3ab529ca888c64f529bd075 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Mon, 5 Aug 2019 15:37:16 +0200 Subject: [PATCH 031/157] iio: frequency: adf4371: Fix output frequency setting MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The fract1 word was not being properly programmed on the device leading to wrong output frequencies. Fixes: 7f699bd14913 (iio: frequency: adf4371: Add support for ADF4371 PLL) Signed-off-by: Nuno Sá Reviewed-by: Stefan Popa Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/frequency/adf4371.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/iio/frequency/adf4371.c b/drivers/iio/frequency/adf4371.c index e48f15cc9ab5..ff82863cbf42 100644 --- a/drivers/iio/frequency/adf4371.c +++ b/drivers/iio/frequency/adf4371.c @@ -276,11 +276,11 @@ static int adf4371_set_freq(struct adf4371_state *st, unsigned long long freq, st->buf[0] = st->integer >> 8; st->buf[1] = 0x40; /* REG12 default */ st->buf[2] = 0x00; - st->buf[3] = st->fract2 & 0xFF; - st->buf[4] = st->fract2 >> 7; - st->buf[5] = st->fract2 >> 15; + st->buf[3] = st->fract1 & 0xFF; + st->buf[4] = st->fract1 >> 8; + st->buf[5] = st->fract1 >> 16; st->buf[6] = ADF4371_FRAC2WORD_L(st->fract2 & 0x7F) | - ADF4371_FRAC1WORD(st->fract1 >> 23); + ADF4371_FRAC1WORD(st->fract1 >> 24); st->buf[7] = ADF4371_FRAC2WORD_H(st->fract2 >> 7); st->buf[8] = st->mod2 & 0xFF; st->buf[9] = ADF4371_MOD2WORD(st->mod2 >> 8); From b9ddd5091160793ee9fac10da765cf3f53d2aaf0 Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Mon, 5 Aug 2019 17:55:15 +0200 Subject: [PATCH 032/157] iio: adc: max9611: Fix temperature reading in probe The max9611 driver reads the die temperature at probe time to validate the communication channel. Use the actual read value to perform the test instead of the read function return value, which was mistakenly used so far. The temperature reading test was only successful because the 0 return value is in the range of supported temperatures. Fixes: 69780a3bbc0b ("iio: adc: Add Maxim max9611 ADC driver") Signed-off-by: Jacopo Mondi Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/adc/max9611.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/adc/max9611.c b/drivers/iio/adc/max9611.c index 0e3c6529fc4c..da073d72f649 100644 --- a/drivers/iio/adc/max9611.c +++ b/drivers/iio/adc/max9611.c @@ -480,7 +480,7 @@ static int max9611_init(struct max9611_dev *max9611) if (ret) return ret; - regval = ret & MAX9611_TEMP_MASK; + regval &= MAX9611_TEMP_MASK; if ((regval > MAX9611_TEMP_MAX_POS && regval < MAX9611_TEMP_MIN_NEG) || From b33d567560c1aadf3033290d74d4fd67af47aa61 Mon Sep 17 00:00:00 2001 From: zhengbin Date: Mon, 8 Jul 2019 20:42:18 +0800 Subject: [PATCH 033/157] auxdisplay: panel: need to delete scan_timer when misc_register fails in panel_attach In panel_attach, if misc_register fails, we need to delete scan_timer, which was setup in keypad_init->init_scan_timer. Reported-by: Hulk Robot Signed-off-by: zhengbin Signed-off-by: Miguel Ojeda --- drivers/auxdisplay/panel.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/auxdisplay/panel.c b/drivers/auxdisplay/panel.c index e06de63497cf..e6bd727da503 100644 --- a/drivers/auxdisplay/panel.c +++ b/drivers/auxdisplay/panel.c @@ -1617,6 +1617,8 @@ static void panel_attach(struct parport *port) return; err_lcd_unreg: + if (scan_timer.function) + del_timer_sync(&scan_timer); if (lcd.enabled) charlcd_unregister(lcd.charlcd); err_unreg_device: From ba2c1340d7c8e1ba5957d814ec18592b315fd4de Mon Sep 17 00:00:00 2001 From: Mans Rullgard Date: Thu, 4 Jul 2019 20:33:54 +0100 Subject: [PATCH 034/157] auxdisplay: charlcd: add help text for backlight initial state While the individual CHARLCD_BL_xxx options have help texts, the menu itself does not. Fix this. Suggested-by: Linus Torvalds Signed-off-by: Mans Rullgard [Added a bit more text to address Linus' suggestion] Signed-off-by: Miguel Ojeda --- drivers/auxdisplay/Kconfig | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/auxdisplay/Kconfig b/drivers/auxdisplay/Kconfig index dd61fdd400f0..68489d1f00bb 100644 --- a/drivers/auxdisplay/Kconfig +++ b/drivers/auxdisplay/Kconfig @@ -448,6 +448,11 @@ config PANEL_BOOT_MESSAGE choice prompt "Backlight initial state" default CHARLCD_BL_FLASH + ---help--- + Select the initial backlight state on boot or module load. + + Previously, there was no option for this: the backlight flashed + briefly on init. Now you can also turn it off/on. config CHARLCD_BL_OFF bool "Off" From 8af23fad626173eed7cc02733874d4124049bd5e Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 29 Jul 2019 16:32:38 +0100 Subject: [PATCH 035/157] iommu/dma: Handle MSI mappings separately MSI pages must always be mapped into a device's *current* domain, which *might* be the default DMA domain, but might instead be a VFIO domain with its own MSI cookie. This subtlety got accidentally lost in the streamlining of __iommu_dma_map(), but rather than reintroduce more complexity and/or special-casing, it turns out neater to just split this path out entirely. Since iommu_dma_get_msi_page() already duplicates much of what __iommu_dma_map() does, it can easily just make the allocation and mapping calls directly as well. That way we can further streamline the helper back to exclusively operating on DMA domains. Fixes: b61d271e59d7 ("iommu/dma: Move domain lookup into __iommu_dma_{map,unmap}") Reported-by: Shameer Kolothum Reported-by: Andre Przywara Signed-off-by: Robin Murphy Tested-by: Marc Zyngier Tested-by: Andre Przywara Tested-by: Shameer Kolothum Signed-off-by: Joerg Roedel --- drivers/iommu/dma-iommu.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index a7f9c3edbcb2..6441197a75ea 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -459,13 +459,11 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys, { struct iommu_domain *domain = iommu_get_dma_domain(dev); struct iommu_dma_cookie *cookie = domain->iova_cookie; - size_t iova_off = 0; + struct iova_domain *iovad = &cookie->iovad; + size_t iova_off = iova_offset(iovad, phys); dma_addr_t iova; - if (cookie->type == IOMMU_DMA_IOVA_COOKIE) { - iova_off = iova_offset(&cookie->iovad, phys); - size = iova_align(&cookie->iovad, size + iova_off); - } + size = iova_align(iovad, size + iova_off); iova = iommu_dma_alloc_iova(domain, size, dma_get_mask(dev), dev); if (!iova) @@ -1147,16 +1145,21 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev, if (!msi_page) return NULL; - iova = __iommu_dma_map(dev, msi_addr, size, prot); - if (iova == DMA_MAPPING_ERROR) + iova = iommu_dma_alloc_iova(domain, size, dma_get_mask(dev), dev); + if (!iova) goto out_free_page; + if (iommu_map(domain, iova, msi_addr, size, prot)) + goto out_free_iova; + INIT_LIST_HEAD(&msi_page->list); msi_page->phys = msi_addr; msi_page->iova = iova; list_add(&msi_page->list, &cookie->msi_page_list); return msi_page; +out_free_iova: + iommu_dma_free_iova(cookie, iova, size); out_free_page: kfree(msi_page); return NULL; From 11f4fe9ba3c85a4efac7ec25e75056a9b612d9da Mon Sep 17 00:00:00 2001 From: Anders Roxell Date: Tue, 30 Jul 2019 17:20:11 +0200 Subject: [PATCH 036/157] iommu/arm-smmu: Mark expected switch fall-through MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Now that -Wimplicit-fallthrough is passed to GCC by default, the following warning shows up: ../drivers/iommu/arm-smmu-v3.c: In function ‘arm_smmu_write_strtab_ent’: ../drivers/iommu/arm-smmu-v3.c:1189:7: warning: this statement may fall through [-Wimplicit-fallthrough=] if (disable_bypass) ^ ../drivers/iommu/arm-smmu-v3.c:1191:3: note: here default: ^~~~~~~ Rework so that the compiler doesn't warn about fall-through. Make it clearer by calling 'BUG_ON()' when disable_bypass is set, and always 'break;' Signed-off-by: Anders Roxell Acked-by: Will Deacon Signed-off-by: Joerg Roedel --- 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 a9a9fabd3968..c5c93e48b4db 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -1186,8 +1186,8 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid, ste_live = true; break; case STRTAB_STE_0_CFG_ABORT: - if (disable_bypass) - break; + BUG_ON(!disable_bypass); + break; default: BUG(); /* STE corruption */ } From 458b7c8e0dde12d140e3472b80919cbb9ae793f4 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Thu, 1 Aug 2019 11:14:58 +0800 Subject: [PATCH 037/157] iommu/vt-d: Detach domain when move device out of group When removing a device from an iommu group, the domain should be detached from the device. Otherwise, the stale domain info will still be cached by the driver and the driver will refuse to attach any domain to the device again. Cc: Ashok Raj Cc: Jacob Pan Cc: Kevin Tian Fixes: b7297783c2bb6 ("iommu/vt-d: Remove duplicated code for device hotplug") Reported-and-tested-by: Vlad Buslov Suggested-by: Robin Murphy Link: https://lkml.org/lkml/2019/7/26/1133 Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel-iommu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index bdaed2da8a55..3e22fa6ae8c8 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -5316,6 +5316,8 @@ static void intel_iommu_remove_device(struct device *dev) if (!iommu) return; + dmar_remove_one_dev_info(dev); + iommu_group_remove_device(dev); iommu_device_unlink(&iommu->iommu, dev); From d7cd4dd907c19c0295829c947d79afa290b6fc24 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 7 Aug 2019 11:21:46 +0100 Subject: [PATCH 038/157] Btrfs: fix sysfs warning and missing raid sysfs directories In the 5.3 merge window, commit 7c7e301406d0a9 ("btrfs: sysfs: Replace default_attrs in ktypes with groups"), we started using the member "defaults_groups" for the kobject type "btrfs_raid_ktype". That leads to a series of warnings when running some test cases of fstests, such as btrfs/027, btrfs/124 and btrfs/176. The traces produced by those warnings are like the following: [116648.059212] kernfs: can not remove 'total_bytes', no directory [116648.060112] WARNING: CPU: 3 PID: 28500 at fs/kernfs/dir.c:1504 kernfs_remove_by_name_ns+0x75/0x80 (...) [116648.066482] CPU: 3 PID: 28500 Comm: umount Tainted: G W 5.3.0-rc3-btrfs-next-54 #1 (...) [116648.069376] RIP: 0010:kernfs_remove_by_name_ns+0x75/0x80 (...) [116648.072385] RSP: 0018:ffffabfd0090bd08 EFLAGS: 00010282 [116648.073437] RAX: 0000000000000000 RBX: ffffffffc0c11998 RCX: 0000000000000000 [116648.074201] RDX: ffff9fff603a7a00 RSI: ffff9fff603978a8 RDI: ffff9fff603978a8 [116648.074956] RBP: ffffffffc0b9ca2f R08: 0000000000000000 R09: 0000000000000001 [116648.075708] R10: ffff9ffe1f72e1c0 R11: 0000000000000000 R12: ffffffffc0b94120 [116648.076434] R13: ffffffffb3d9b4e0 R14: 0000000000000000 R15: dead000000000100 [116648.077143] FS: 00007f9cdc78a2c0(0000) GS:ffff9fff60380000(0000) knlGS:0000000000000000 [116648.077852] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [116648.078546] CR2: 00007f9fc4747ab4 CR3: 00000005c7832003 CR4: 00000000003606e0 [116648.079235] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [116648.079907] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [116648.080585] Call Trace: [116648.081262] remove_files+0x31/0x70 [116648.081929] sysfs_remove_group+0x38/0x80 [116648.082596] sysfs_remove_groups+0x34/0x70 [116648.083258] kobject_del+0x20/0x60 [116648.083933] btrfs_free_block_groups+0x405/0x430 [btrfs] [116648.084608] close_ctree+0x19a/0x380 [btrfs] [116648.085278] generic_shutdown_super+0x6c/0x110 [116648.085951] kill_anon_super+0xe/0x30 [116648.086621] btrfs_kill_super+0x12/0xa0 [btrfs] [116648.087289] deactivate_locked_super+0x3a/0x70 [116648.087956] cleanup_mnt+0xb4/0x160 [116648.088620] task_work_run+0x7e/0xc0 [116648.089285] exit_to_usermode_loop+0xfa/0x100 [116648.089933] do_syscall_64+0x1cb/0x220 [116648.090567] entry_SYSCALL_64_after_hwframe+0x49/0xbe [116648.091197] RIP: 0033:0x7f9cdc073b37 (...) [116648.100046] ---[ end trace 22e24db328ccadf8 ]--- [116648.100618] ------------[ cut here ]------------ [116648.101175] kernfs: can not remove 'used_bytes', no directory [116648.101731] WARNING: CPU: 3 PID: 28500 at fs/kernfs/dir.c:1504 kernfs_remove_by_name_ns+0x75/0x80 (...) [116648.105649] CPU: 3 PID: 28500 Comm: umount Tainted: G W 5.3.0-rc3-btrfs-next-54 #1 (...) [116648.107461] RIP: 0010:kernfs_remove_by_name_ns+0x75/0x80 (...) [116648.109336] RSP: 0018:ffffabfd0090bd08 EFLAGS: 00010282 [116648.109979] RAX: 0000000000000000 RBX: ffffffffc0c119a0 RCX: 0000000000000000 [116648.110625] RDX: ffff9fff603a7a00 RSI: ffff9fff603978a8 RDI: ffff9fff603978a8 [116648.111283] RBP: ffffffffc0b9ca41 R08: 0000000000000000 R09: 0000000000000001 [116648.111940] R10: ffff9ffe1f72e1c0 R11: 0000000000000000 R12: ffffffffc0b94120 [116648.112603] R13: ffffffffb3d9b4e0 R14: 0000000000000000 R15: dead000000000100 [116648.113268] FS: 00007f9cdc78a2c0(0000) GS:ffff9fff60380000(0000) knlGS:0000000000000000 [116648.113939] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [116648.114607] CR2: 00007f9fc4747ab4 CR3: 00000005c7832003 CR4: 00000000003606e0 [116648.115286] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [116648.115966] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [116648.116649] Call Trace: [116648.117326] remove_files+0x31/0x70 [116648.117997] sysfs_remove_group+0x38/0x80 [116648.118671] sysfs_remove_groups+0x34/0x70 [116648.119342] kobject_del+0x20/0x60 [116648.120022] btrfs_free_block_groups+0x405/0x430 [btrfs] [116648.120707] close_ctree+0x19a/0x380 [btrfs] [116648.121396] generic_shutdown_super+0x6c/0x110 [116648.122057] kill_anon_super+0xe/0x30 [116648.122702] btrfs_kill_super+0x12/0xa0 [btrfs] [116648.123335] deactivate_locked_super+0x3a/0x70 [116648.123961] cleanup_mnt+0xb4/0x160 [116648.124586] task_work_run+0x7e/0xc0 [116648.125210] exit_to_usermode_loop+0xfa/0x100 [116648.125830] do_syscall_64+0x1cb/0x220 [116648.126463] entry_SYSCALL_64_after_hwframe+0x49/0xbe [116648.127080] RIP: 0033:0x7f9cdc073b37 (...) [116648.135923] ---[ end trace 22e24db328ccadf9 ]--- These happen because, during the unmount path, we call kobject_del() for raid kobjects that are not fully initialized, meaning that we set their ktype (as btrfs_raid_ktype) through link_block_group() but we didn't set their parent kobject, which is done through btrfs_add_raid_kobjects(). We have this split raid kobject setup since commit 75cb379d263521 ("btrfs: defer adding raid type kobject until after chunk relocation") in order to avoid triggering reclaim during contextes where we can not (either we are holding a transaction handle or some lock required by the transaction commit path), so that we do the calls to kobject_add(), which triggers GFP_KERNEL allocations, through btrfs_add_raid_kobjects() in contextes where it is safe to trigger reclaim. That change expected that a new raid kobject can only be created either when mounting the filesystem or after raid profile conversion through the relocation path. However, we can have new raid kobject created in other two cases at least: 1) During device replace (or scrub) after adding a device a to the filesystem. The replace procedure (and scrub) do calls to btrfs_inc_block_group_ro() which can allocate a new block group with a new raid profile (because we now have more devices). This can be triggered by test cases btrfs/027 and btrfs/176. 2) During a degraded mount trough any write path. This can be triggered by test case btrfs/124. Fixing this by adding extra calls to btrfs_add_raid_kobjects(), not only makes things more complex and fragile, can also introduce deadlocks with reclaim the following way: 1) Calling btrfs_add_raid_kobjects() at btrfs_inc_block_group_ro() or anywhere in the replace/scrub path will cause a deadlock with reclaim because if reclaim happens and a transaction commit is triggered, the transaction commit path will block at btrfs_scrub_pause(). 2) During degraded mounts it is essentially impossible to figure out where to add extra calls to btrfs_add_raid_kobjects(), because allocation of a block group with a new raid profile can happen anywhere, which means we can't safely figure out which contextes are safe for reclaim, as we can either hold a transaction handle or some lock needed by the transaction commit path. So it is too complex and error prone to have this split setup of raid kobjects. So fix the issue by consolidating the setup of the kobjects in a single place, at link_block_group(), and setup a nofs context there in order to prevent reclaim being triggered by the memory allocations done through the call chain of kobject_add(). Besides fixing the sysfs warnings during kobject_del(), this also ensures the sysfs directories for the new raid profiles end up created and visible to users (a bug that existed before the 5.3 commit 7c7e301406d0a9 ("btrfs: sysfs: Replace default_attrs in ktypes with groups")). Fixes: 75cb379d263521 ("btrfs: defer adding raid type kobject until after chunk relocation") Fixes: 7c7e301406d0a9 ("btrfs: sysfs: Replace default_attrs in ktypes with groups") Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 4 --- fs/btrfs/disk-io.c | 2 -- fs/btrfs/extent-tree.c | 57 ++++++++++++++++++------------------------ fs/btrfs/volumes.c | 13 ---------- 4 files changed, 24 insertions(+), 52 deletions(-) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 299e11e6c554..94660063a162 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -401,7 +401,6 @@ struct btrfs_dev_replace { struct raid_kobject { u64 flags; struct kobject kobj; - struct list_head list; }; /* @@ -915,8 +914,6 @@ struct btrfs_fs_info { u32 thread_pool_size; struct kobject *space_info_kobj; - struct list_head pending_raid_kobjs; - spinlock_t pending_raid_kobjs_lock; /* uncontended */ u64 total_pinned; @@ -2698,7 +2695,6 @@ int btrfs_can_relocate(struct btrfs_fs_info *fs_info, u64 bytenr); int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, u64 type, u64 chunk_offset, u64 size); -void btrfs_add_raid_kobjects(struct btrfs_fs_info *fs_info); struct btrfs_trans_handle *btrfs_start_trans_remove_block_group( struct btrfs_fs_info *fs_info, const u64 chunk_offset); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 5f7ee70b3d1a..97beb351a10c 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2683,8 +2683,6 @@ int open_ctree(struct super_block *sb, INIT_LIST_HEAD(&fs_info->delayed_iputs); INIT_LIST_HEAD(&fs_info->delalloc_roots); INIT_LIST_HEAD(&fs_info->caching_block_groups); - INIT_LIST_HEAD(&fs_info->pending_raid_kobjs); - spin_lock_init(&fs_info->pending_raid_kobjs_lock); spin_lock_init(&fs_info->delalloc_root_lock); spin_lock_init(&fs_info->trans_lock); spin_lock_init(&fs_info->fs_roots_radix_lock); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index d3b58e388535..25b2c9d7fa7f 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4,6 +4,7 @@ */ #include +#include #include #include #include @@ -7888,33 +7889,6 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info) return 0; } -/* link_block_group will queue up kobjects to add when we're reclaim-safe */ -void btrfs_add_raid_kobjects(struct btrfs_fs_info *fs_info) -{ - struct btrfs_space_info *space_info; - struct raid_kobject *rkobj; - LIST_HEAD(list); - int ret = 0; - - spin_lock(&fs_info->pending_raid_kobjs_lock); - list_splice_init(&fs_info->pending_raid_kobjs, &list); - spin_unlock(&fs_info->pending_raid_kobjs_lock); - - list_for_each_entry(rkobj, &list, list) { - space_info = btrfs_find_space_info(fs_info, rkobj->flags); - - ret = kobject_add(&rkobj->kobj, &space_info->kobj, - "%s", btrfs_bg_type_to_raid_name(rkobj->flags)); - if (ret) { - kobject_put(&rkobj->kobj); - break; - } - } - if (ret) - btrfs_warn(fs_info, - "failed to add kobject for block cache, ignoring"); -} - static void link_block_group(struct btrfs_block_group_cache *cache) { struct btrfs_space_info *space_info = cache->space_info; @@ -7929,18 +7903,36 @@ static void link_block_group(struct btrfs_block_group_cache *cache) up_write(&space_info->groups_sem); if (first) { - struct raid_kobject *rkobj = kzalloc(sizeof(*rkobj), GFP_NOFS); + struct raid_kobject *rkobj; + unsigned int nofs_flag; + int ret; + + /* + * Setup a NOFS context because kobject_add(), deep in its call + * chain, does GFP_KERNEL allocations, and we are often called + * in a context where if reclaim is triggered we can deadlock + * (we are either holding a transaction handle or some lock + * required for a transaction commit). + */ + nofs_flag = memalloc_nofs_save(); + rkobj = kzalloc(sizeof(*rkobj), GFP_KERNEL); if (!rkobj) { + memalloc_nofs_restore(nofs_flag); btrfs_warn(cache->fs_info, "couldn't alloc memory for raid level kobject"); return; } rkobj->flags = cache->flags; kobject_init(&rkobj->kobj, &btrfs_raid_ktype); - - spin_lock(&fs_info->pending_raid_kobjs_lock); - list_add_tail(&rkobj->list, &fs_info->pending_raid_kobjs); - spin_unlock(&fs_info->pending_raid_kobjs_lock); + ret = kobject_add(&rkobj->kobj, &space_info->kobj, "%s", + btrfs_bg_type_to_raid_name(rkobj->flags)); + memalloc_nofs_restore(nofs_flag); + if (ret) { + kobject_put(&rkobj->kobj); + btrfs_warn(fs_info, + "failed to add kobject for block cache, ignoring"); + return; + } space_info->block_group_kobjs[index] = &rkobj->kobj; } } @@ -8206,7 +8198,6 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info) inc_block_group_ro(cache, 1); } - btrfs_add_raid_kobjects(info); btrfs_init_global_block_rsv(info); ret = check_chunk_block_group_mappings(info); error: diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index d74b74ca07af..a447d3ec48d5 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3087,16 +3087,6 @@ static int btrfs_relocate_chunk(struct btrfs_fs_info *fs_info, u64 chunk_offset) if (ret) return ret; - /* - * We add the kobjects here (and after forcing data chunk creation) - * since relocation is the only place we'll create chunks of a new - * type at runtime. The only place where we'll remove the last - * chunk of a type is the call immediately below this one. Even - * so, we're protected against races with the cleaner thread since - * we're covered by the delete_unused_bgs_mutex. - */ - btrfs_add_raid_kobjects(fs_info); - trans = btrfs_start_trans_remove_block_group(root->fs_info, chunk_offset); if (IS_ERR(trans)) { @@ -3223,9 +3213,6 @@ static int btrfs_may_alloc_data_chunk(struct btrfs_fs_info *fs_info, btrfs_end_transaction(trans); if (ret < 0) return ret; - - btrfs_add_raid_kobjects(fs_info); - return 1; } } From 07301df7d2fc220d3de5f7ad804dcb941400cb00 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Tue, 28 May 2019 16:21:54 +0800 Subject: [PATCH 039/157] btrfs: trim: Check the range passed into to prevent overflow Normally the range->len is set to default value (U64_MAX), but when it's not default value, we should check if the range overflows. And if it overflows, return -EINVAL before doing anything. Reviewed-by: Nikolay Borisov Reviewed-by: Anand Jain Signed-off-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/extent-tree.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 25b2c9d7fa7f..8b7eb22d508a 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -8966,6 +8966,7 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range) struct btrfs_device *device; struct list_head *devices; u64 group_trimmed; + u64 range_end = U64_MAX; u64 start; u64 end; u64 trimmed = 0; @@ -8975,16 +8976,23 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range) int dev_ret = 0; int ret = 0; + /* + * Check range overflow if range->len is set. + * The default range->len is U64_MAX. + */ + if (range->len != U64_MAX && + check_add_overflow(range->start, range->len, &range_end)) + return -EINVAL; + cache = btrfs_lookup_first_block_group(fs_info, range->start); for (; cache; cache = next_block_group(cache)) { - if (cache->key.objectid >= (range->start + range->len)) { + if (cache->key.objectid >= range_end) { btrfs_put_block_group(cache); break; } start = max(range->start, cache->key.objectid); - end = min(range->start + range->len, - cache->key.objectid + cache->key.offset); + end = min(range_end, cache->key.objectid + cache->key.offset); if (end - start >= range->minlen) { if (!block_group_cache_done(cache)) { From f591822c3cf314442819486f45ff7dc1f690e0c0 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Mon, 5 Aug 2019 11:30:10 +0300 Subject: [PATCH 040/157] IB/mlx5: Fix implicit MR release flow Once implicit MR is being called to be released by ib_umem_notifier_release() its leaves were marked as "dying". However, when dereg_mr()->mlx5_ib_free_implicit_mr()->mr_leaf_free() is called, it skips running the mr_leaf_free_action (i.e. umem_odp->work) when those leaves were marked as "dying". As such ib_umem_release() for the leaves won't be called and their MRs will be leaked as well. When an application exits/killed without calling dereg_mr we might hit the above flow. This fatal scenario is reported by WARN_ON() upon mlx5_ib_dealloc_ucontext() as ibcontext->per_mm_list is not empty, the call trace can be seen below. Originally the "dying" mark as part of ib_umem_notifier_release() was introduced to prevent pagefault_mr() from returning a success response once this happened. However, we already have today the completion mechanism so no need for that in those flows any more. Even in case a success response will be returned the firmware will not find the pages and an error will be returned in the following call as a released mm will cause ib_umem_odp_map_dma_pages() to permanently fail mmget_not_zero(). Fix the above issue by dropping the "dying" from the above flows. The other flows that are using "dying" are still needed it for their synchronization purposes. WARNING: CPU: 1 PID: 7218 at drivers/infiniband/hw/mlx5/main.c:2004 mlx5_ib_dealloc_ucontext+0x84/0x90 [mlx5_ib] CPU: 1 PID: 7218 Comm: ibv_rc_pingpong Tainted: G E 5.2.0-rc6+ #13 Call Trace: uverbs_destroy_ufile_hw+0xb5/0x120 [ib_uverbs] ib_uverbs_close+0x1f/0x80 [ib_uverbs] __fput+0xbe/0x250 task_work_run+0x88/0xa0 do_exit+0x2cb/0xc30 ? __fput+0x14b/0x250 do_group_exit+0x39/0xb0 get_signal+0x191/0x920 ? _raw_spin_unlock_bh+0xa/0x20 ? inet_csk_accept+0x229/0x2f0 do_signal+0x36/0x5e0 ? put_unused_fd+0x5b/0x70 ? __sys_accept4+0x1a6/0x1e0 ? inet_hash+0x35/0x40 ? release_sock+0x43/0x90 ? _raw_spin_unlock_bh+0xa/0x20 ? inet_listen+0x9f/0x120 exit_to_usermode_loop+0x5c/0xc6 do_syscall_64+0x182/0x1b0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Fixes: 81713d3788d2 ("IB/mlx5: Add implicit MR support") Link: https://lore.kernel.org/r/20190805083010.21777-1-leon@kernel.org Signed-off-by: Yishai Hadas Reviewed-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky Reviewed-by: Jason Gunthorpe Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/umem_odp.c | 4 ---- drivers/infiniband/hw/mlx5/odp.c | 22 ++++++++-------------- 2 files changed, 8 insertions(+), 18 deletions(-) diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c index 2a75c6f8d827..c0e15db34680 100644 --- a/drivers/infiniband/core/umem_odp.c +++ b/drivers/infiniband/core/umem_odp.c @@ -112,10 +112,6 @@ static int ib_umem_notifier_release_trampoline(struct ib_umem_odp *umem_odp, * prevent any further fault handling on this MR. */ ib_umem_notifier_start_account(umem_odp); - umem_odp->dying = 1; - /* Make sure that the fact the umem is dying is out before we release - * all pending page faults. */ - smp_wmb(); complete_all(&umem_odp->notifier_completion); umem_odp->umem.context->invalidate_range( umem_odp, ib_umem_start(umem_odp), ib_umem_end(umem_odp)); diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index 81da82050d05..1d257d1b3b0d 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -579,7 +579,6 @@ static int pagefault_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr, u32 flags) { int npages = 0, current_seq, page_shift, ret, np; - bool implicit = false; struct ib_umem_odp *odp_mr = to_ib_umem_odp(mr->umem); bool downgrade = flags & MLX5_PF_FLAGS_DOWNGRADE; bool prefetch = flags & MLX5_PF_FLAGS_PREFETCH; @@ -594,7 +593,6 @@ static int pagefault_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr, if (IS_ERR(odp)) return PTR_ERR(odp); mr = odp->private; - implicit = true; } else { odp = odp_mr; } @@ -682,19 +680,15 @@ static int pagefault_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr, out: if (ret == -EAGAIN) { - if (implicit || !odp->dying) { - unsigned long timeout = - msecs_to_jiffies(MMU_NOTIFIER_TIMEOUT); + unsigned long timeout = msecs_to_jiffies(MMU_NOTIFIER_TIMEOUT); - if (!wait_for_completion_timeout( - &odp->notifier_completion, - timeout)) { - mlx5_ib_warn(dev, "timeout waiting for mmu notifier. seq %d against %d. notifiers_count=%d\n", - current_seq, odp->notifiers_seq, odp->notifiers_count); - } - } else { - /* The MR is being killed, kill the QP as well. */ - ret = -EFAULT; + if (!wait_for_completion_timeout(&odp->notifier_completion, + timeout)) { + mlx5_ib_warn( + dev, + "timeout waiting for mmu notifier. seq %d against %d. notifiers_count=%d\n", + current_seq, odp->notifiers_seq, + odp->notifiers_count); } } From d97de8887a12c598abc4d2e4e57a54c1f030e112 Mon Sep 17 00:00:00 2001 From: Mark Zhang Date: Wed, 7 Aug 2019 13:18:19 +0300 Subject: [PATCH 041/157] RDMA/counter: Prevent QP counter binding if counters unsupported In case of rdma_counter_init() fails, counter allocation and QP bind should not be allowed. Fixes: 413d3347503b ("RDMA/counter: Add set/clear per-port auto mode support") Fixes: 1bd8e0a9d0fd ("RDMA/counter: Allow manual mode configuration support") Signed-off-by: Mark Zhang Reviewed-by: Parav Pandit Signed-off-by: Leon Romanovsky Link: https://lore.kernel.org/r/20190807101819.7581-1-leon@kernel.org Signed-off-by: Doug Ledford --- drivers/infiniband/core/counters.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/infiniband/core/counters.c b/drivers/infiniband/core/counters.c index 45d5164e9574..b79890739a2c 100644 --- a/drivers/infiniband/core/counters.c +++ b/drivers/infiniband/core/counters.c @@ -38,6 +38,9 @@ int rdma_counter_set_auto_mode(struct ib_device *dev, u8 port, int ret; port_counter = &dev->port_data[port].port_counter; + if (!port_counter->hstats) + return -EOPNOTSUPP; + mutex_lock(&port_counter->lock); if (on) { ret = __counter_set_mode(&port_counter->mode, @@ -509,6 +512,9 @@ int rdma_counter_bind_qpn_alloc(struct ib_device *dev, u8 port, if (!rdma_is_port_valid(dev, port)) return -EINVAL; + if (!dev->port_data[port].port_counter.hstats) + return -EOPNOTSUPP; + qp = rdma_counter_get_qp(dev, qp_num); if (!qp) return -ENOENT; From e7e6c6320c8c9ed923250cd019e5f9ca0f59b4b8 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 7 Aug 2019 15:32:36 +0300 Subject: [PATCH 042/157] IB/mlx5: Check the correct variable in error handling code The code accidentally checks "event_sub" instead of "event_sub->eventfd". Fixes: 759738537142 ("IB/mlx5: Enable subscription for device events over DEVX") Signed-off-by: Dan Carpenter Reviewed-by: Jason Gunthorpe Acked-by: Leon Romanovsky Link: https://lore.kernel.org/r/20190807123236.GA11452@mwanda Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/devx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index ec4370f99381..2d1b3d9609d9 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -2026,7 +2026,7 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_SUBSCRIBE_EVENT)( event_sub->eventfd = eventfd_ctx_fdget(redirect_fd); - if (IS_ERR(event_sub)) { + if (IS_ERR(event_sub->eventfd)) { err = PTR_ERR(event_sub->eventfd); event_sub->eventfd = NULL; goto err; From a86c71ba3022331f79662d7f12d1b25188c7e377 Mon Sep 17 00:00:00 2001 From: James Smart Date: Fri, 2 Aug 2019 13:26:12 -0700 Subject: [PATCH 043/157] scsi: lpfc: Fix crash when cpu count is 1 and null irq affinity mask When a configurations runs with a single cpu (such as a kdump kernel), which causes the driver to request a single vector, when the driver subsequently requests an irq affinity mask, the mask comes back null. The driver currently does nothing in this scenario, which leaves mappings to hardware queues incomplete and crashes the system. Fix by recognizing the null mask and assigning the vector to the first cpu in the system. Signed-off-by: Dick Kennedy Signed-off-by: James Smart Signed-off-by: Martin K. Petersen --- drivers/scsi/lpfc/lpfc_init.c | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index faf43b1d3dbe..a7549ae32542 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -10776,12 +10776,31 @@ lpfc_cpu_affinity_check(struct lpfc_hba *phba, int vectors) /* This loop sets up all CPUs that are affinitized with a * irq vector assigned to the driver. All affinitized CPUs * will get a link to that vectors IRQ and EQ. + * + * NULL affinity mask handling: + * If irq count is greater than one, log an error message. + * If the null mask is received for the first irq, find the + * first present cpu, and assign the eq index to ensure at + * least one EQ is assigned. */ for (idx = 0; idx < phba->cfg_irq_chann; idx++) { /* Get a CPU mask for all CPUs affinitized to this vector */ maskp = pci_irq_get_affinity(phba->pcidev, idx); - if (!maskp) - continue; + if (!maskp) { + if (phba->cfg_irq_chann > 1) + lpfc_printf_log(phba, KERN_ERR, LOG_INIT, + "3329 No affinity mask found " + "for vector %d (%d)\n", + idx, phba->cfg_irq_chann); + if (!idx) { + cpu = cpumask_first(cpu_present_mask); + cpup = &phba->sli4_hba.cpu_map[cpu]; + cpup->eq = idx; + cpup->irq = pci_irq_vector(phba->pcidev, idx); + cpup->flag |= LPFC_CPU_FIRST_IRQ; + } + break; + } i = 0; /* Loop through all CPUs associated with vector idx */ From 39c71a5b8212f4b502d9a630c6706ac723abd422 Mon Sep 17 00:00:00 2001 From: Jia-Ju Bai Date: Mon, 29 Jul 2019 10:08:49 +0800 Subject: [PATCH 044/157] dmaengine: stm32-mdma: Fix a possible null-pointer dereference in stm32_mdma_irq_handler() In stm32_mdma_irq_handler(), chan is checked on line 1368. When chan is NULL, it is still used on line 1369: dev_err(chan2dev(chan), "MDMA channel not initialized\n"); Thus, a possible null-pointer dereference may occur. To fix this bug, "dev_dbg(mdma2dev(dmadev), ...)" is used instead. Signed-off-by: Jia-Ju Bai Fixes: a4ffb13c8946 ("dmaengine: Add STM32 MDMA driver") Link: https://lore.kernel.org/r/20190729020849.17971-1-baijiaju1990@gmail.com Signed-off-by: Vinod Koul --- drivers/dma/stm32-mdma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/dma/stm32-mdma.c b/drivers/dma/stm32-mdma.c index d6e919d3936a..1311de74bfdd 100644 --- a/drivers/dma/stm32-mdma.c +++ b/drivers/dma/stm32-mdma.c @@ -1366,7 +1366,7 @@ static irqreturn_t stm32_mdma_irq_handler(int irq, void *devid) chan = &dmadev->chan[id]; if (!chan) { - dev_err(chan2dev(chan), "MDMA channel not initialized\n"); + dev_dbg(mdma2dev(dmadev), "MDMA channel not initialized\n"); goto exit; } From 75354284cc3aa58f7e54d479d9bee69bd2ca828f Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 6 Aug 2019 16:14:44 +0900 Subject: [PATCH 045/157] auxdisplay: charlcd: move charlcd.h to drivers/auxdisplay This header is included in drivers/auxdisplay/. Make it a local header. Reviewed-by: Geert Uytterhoeven Signed-off-by: Masahiro Yamada Signed-off-by: Miguel Ojeda --- drivers/auxdisplay/charlcd.c | 2 +- {include/misc => drivers/auxdisplay}/charlcd.h | 0 drivers/auxdisplay/hd44780.c | 3 +-- drivers/auxdisplay/panel.c | 2 +- 4 files changed, 3 insertions(+), 4 deletions(-) rename {include/misc => drivers/auxdisplay}/charlcd.h (100%) diff --git a/drivers/auxdisplay/charlcd.c b/drivers/auxdisplay/charlcd.c index 92745efefb54..bef6b85778b6 100644 --- a/drivers/auxdisplay/charlcd.c +++ b/drivers/auxdisplay/charlcd.c @@ -20,7 +20,7 @@ #include -#include +#include "charlcd.h" #define LCD_MINOR 156 diff --git a/include/misc/charlcd.h b/drivers/auxdisplay/charlcd.h similarity index 100% rename from include/misc/charlcd.h rename to drivers/auxdisplay/charlcd.h diff --git a/drivers/auxdisplay/hd44780.c b/drivers/auxdisplay/hd44780.c index ab15b64707ad..bcbe13092327 100644 --- a/drivers/auxdisplay/hd44780.c +++ b/drivers/auxdisplay/hd44780.c @@ -14,8 +14,7 @@ #include #include -#include - +#include "charlcd.h" enum hd44780_pin { /* Order does matter due to writing to GPIO array subsets! */ diff --git a/drivers/auxdisplay/panel.c b/drivers/auxdisplay/panel.c index e6bd727da503..85965953683e 100644 --- a/drivers/auxdisplay/panel.c +++ b/drivers/auxdisplay/panel.c @@ -55,7 +55,7 @@ #include #include -#include +#include "charlcd.h" #define KEYPAD_MINOR 185 From 390235c3e66036351e2a89b925843a741c8afd6c Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 6 Aug 2019 16:14:45 +0900 Subject: [PATCH 046/157] auxdisplay: charlcd: add include guard to charlcd.h Add a header include guard just in case. Signed-off-by: Masahiro Yamada Signed-off-by: Miguel Ojeda --- drivers/auxdisplay/charlcd.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/auxdisplay/charlcd.h b/drivers/auxdisplay/charlcd.h index 8cf6c18b0adb..00911ad0f3de 100644 --- a/drivers/auxdisplay/charlcd.h +++ b/drivers/auxdisplay/charlcd.h @@ -6,6 +6,9 @@ * Copyright (C) 2016-2017 Glider bvba */ +#ifndef _CHARLCD_H +#define _CHARLCD_H + struct charlcd { const struct charlcd_ops *ops; const unsigned char *char_conv; /* Optional */ @@ -37,3 +40,5 @@ int charlcd_register(struct charlcd *lcd); int charlcd_unregister(struct charlcd *lcd); void charlcd_poke(struct charlcd *lcd); + +#endif /* CHARLCD_H */ From 6c4d6bc5486466e3a67cc47270001d0b4a26eed4 Mon Sep 17 00:00:00 2001 From: Masanari Iida Date: Tue, 6 Aug 2019 23:23:28 +0900 Subject: [PATCH 047/157] auxdisplay: Fix a typo in cfag12864b-example.c This patch fix a spelling typo in cfag12864b-example.c Signed-off-by: Masanari Iida Signed-off-by: Miguel Ojeda --- samples/auxdisplay/cfag12864b-example.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/samples/auxdisplay/cfag12864b-example.c b/samples/auxdisplay/cfag12864b-example.c index 85571e90191f..bfeab44f81d0 100644 --- a/samples/auxdisplay/cfag12864b-example.c +++ b/samples/auxdisplay/cfag12864b-example.c @@ -245,7 +245,7 @@ int main(int argc, char *argv[]) if (argc != 2) { printf( - "Sintax: %s fbdev\n" + "Syntax: %s fbdev\n" "Usually: /dev/fb0, /dev/fb1...\n", argv[0]); return -1; } From 8676b3ca4673517650fd509d7fa586aff87b3c28 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Thu, 18 Jul 2019 18:02:15 -0500 Subject: [PATCH 048/157] soundwire: fix regmap dependencies and align with other serial links The existing code has a mixed select/depend usage which makes no sense. config SOUNDWIRE_BUS tristate select REGMAP_SOUNDWIRE config REGMAP_SOUNDWIRE tristate depends on SOUNDWIRE_BUS Let's remove one layer of Kconfig definitions and align with the solutions used by all other serial links. Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20190718230215.18675-1-pierre-louis.bossart@linux.intel.com Signed-off-by: Vinod Koul --- drivers/base/regmap/Kconfig | 2 +- drivers/soundwire/Kconfig | 7 +------ drivers/soundwire/Makefile | 2 +- 3 files changed, 3 insertions(+), 8 deletions(-) diff --git a/drivers/base/regmap/Kconfig b/drivers/base/regmap/Kconfig index a4984136c19d..0fd6f97ee523 100644 --- a/drivers/base/regmap/Kconfig +++ b/drivers/base/regmap/Kconfig @@ -44,7 +44,7 @@ config REGMAP_IRQ config REGMAP_SOUNDWIRE tristate - depends on SOUNDWIRE_BUS + depends on SOUNDWIRE config REGMAP_SCCB tristate diff --git a/drivers/soundwire/Kconfig b/drivers/soundwire/Kconfig index 3a01cfd70fdc..f518273cfbe3 100644 --- a/drivers/soundwire/Kconfig +++ b/drivers/soundwire/Kconfig @@ -4,7 +4,7 @@ # menuconfig SOUNDWIRE - bool "SoundWire support" + tristate "SoundWire support" help SoundWire is a 2-Pin interface with data and clock line ratified by the MIPI Alliance. SoundWire is used for transporting data @@ -17,17 +17,12 @@ if SOUNDWIRE comment "SoundWire Devices" -config SOUNDWIRE_BUS - tristate - select REGMAP_SOUNDWIRE - config SOUNDWIRE_CADENCE tristate config SOUNDWIRE_INTEL tristate "Intel SoundWire Master driver" select SOUNDWIRE_CADENCE - select SOUNDWIRE_BUS depends on X86 && ACPI && SND_SOC help SoundWire Intel Master driver. diff --git a/drivers/soundwire/Makefile b/drivers/soundwire/Makefile index fd99a831b92a..45b7e5001653 100644 --- a/drivers/soundwire/Makefile +++ b/drivers/soundwire/Makefile @@ -5,7 +5,7 @@ #Bus Objs soundwire-bus-objs := bus_type.o bus.o slave.o mipi_disco.o stream.o -obj-$(CONFIG_SOUNDWIRE_BUS) += soundwire-bus.o +obj-$(CONFIG_SOUNDWIRE) += soundwire-bus.o #Cadence Objs soundwire-cadence-objs := cadence_master.o From eac4471d0882da14be652ef0a55b914145fab15a Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 8 Aug 2019 13:32:36 +0300 Subject: [PATCH 049/157] drm/i915: Use after free in error path in intel_vgpu_create_workload() We can't free "workload" until after the printk or it's a use after free. Fixes: 2089a76ade90 ("drm/i915/gvt: Checking workload's gma earlier") Signed-off-by: Dan Carpenter Reviewed-by: Chris Wilson Signed-off-by: Zhenyu Wang --- drivers/gpu/drm/i915/gvt/scheduler.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index 9f3fd7d96a69..75baff657e43 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -1528,9 +1528,9 @@ intel_vgpu_create_workload(struct intel_vgpu *vgpu, int ring_id, if (!intel_gvt_ggtt_validate_range(vgpu, workload->wa_ctx.indirect_ctx.guest_gma, workload->wa_ctx.indirect_ctx.size)) { - kmem_cache_free(s->workloads, workload); gvt_vgpu_err("invalid wa_ctx at: 0x%lx\n", workload->wa_ctx.indirect_ctx.guest_gma); + kmem_cache_free(s->workloads, workload); return ERR_PTR(-EINVAL); } } @@ -1542,9 +1542,9 @@ intel_vgpu_create_workload(struct intel_vgpu *vgpu, int ring_id, if (!intel_gvt_ggtt_validate_range(vgpu, workload->wa_ctx.per_ctx.guest_gma, CACHELINE_BYTES)) { - kmem_cache_free(s->workloads, workload); gvt_vgpu_err("invalid per_ctx at: 0x%lx\n", workload->wa_ctx.per_ctx.guest_gma); + kmem_cache_free(s->workloads, workload); return ERR_PTR(-EINVAL); } } From de768ce45466f3009809719eb7b1f6f5277d9373 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 9 Aug 2019 11:23:00 +0200 Subject: [PATCH 050/157] ALSA: hda - Apply workaround for another AMD chip 1022:1487 MSI MPG X570 board is with another AMD HD-audio controller (PCI ID 1022:1487) and it requires the same workaround applied for X370, etc (PCI ID 1022:1457). BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=195303 Cc: Signed-off-by: Takashi Iwai --- sound/pci/hda/hda_intel.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index a6d8c0d77b84..99fc0917339b 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2508,6 +2508,9 @@ static const struct pci_device_id azx_ids[] = { /* AMD, X370 & co */ { PCI_DEVICE(0x1022, 0x1457), .driver_data = AZX_DRIVER_GENERIC | AZX_DCAPS_PRESET_AMD_SB }, + /* AMD, X570 & co */ + { PCI_DEVICE(0x1022, 0x1487), + .driver_data = AZX_DRIVER_GENERIC | AZX_DCAPS_PRESET_AMD_SB }, /* AMD Stoney */ { PCI_DEVICE(0x1022, 0x157a), .driver_data = AZX_DRIVER_GENERIC | AZX_DCAPS_PRESET_ATI_SB | From d555c34338cae844b207564c482e5a3fb089d25e Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 9 Aug 2019 10:32:40 +0200 Subject: [PATCH 051/157] omap-dma/omap_vout_vrfb: fix off-by-one fi value The OMAP 4 TRM specifies that when using double-index addressing the address increases by the ES plus the EI value minus 1 within a frame. When a full frame is transferred, the address increases by the ES plus the frame index (FI) value minus 1. The omap-dma code didn't account for the 'minus 1' in the FI register. To get correct addressing, add 1 to the src_icg value. This was found when testing a hacked version of the media m2m-deinterlace.c driver on a Pandaboard. The only other source that uses this feature is omap_vout_vrfb.c, and that adds a + 1 when setting the dst_icg. This is a workaround for the broken omap-dma.c behavior. So remove the workaround at the same time that we fix omap-dma.c. I tested the omap_vout driver with a Beagle XM board to check that the '+ 1' in omap_vout_vrfb.c was indeed a workaround for the omap-dma bug. Signed-off-by: Hans Verkuil Reviewed-by: Laurent Pinchart Acked-by: Peter Ujfalusi Acked-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/952e7f51-f208-9333-6f58-b7ed20d2ea0b@xs4all.nl Signed-off-by: Vinod Koul --- drivers/dma/ti/omap-dma.c | 4 ++-- drivers/media/platform/omap/omap_vout_vrfb.c | 3 +-- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/dma/ti/omap-dma.c b/drivers/dma/ti/omap-dma.c index ba2489d4ea24..ba27802efcd0 100644 --- a/drivers/dma/ti/omap-dma.c +++ b/drivers/dma/ti/omap-dma.c @@ -1234,7 +1234,7 @@ static struct dma_async_tx_descriptor *omap_dma_prep_dma_interleaved( if (src_icg) { d->ccr |= CCR_SRC_AMODE_DBLIDX; d->ei = 1; - d->fi = src_icg; + d->fi = src_icg + 1; } else if (xt->src_inc) { d->ccr |= CCR_SRC_AMODE_POSTINC; d->fi = 0; @@ -1249,7 +1249,7 @@ static struct dma_async_tx_descriptor *omap_dma_prep_dma_interleaved( if (dst_icg) { d->ccr |= CCR_DST_AMODE_DBLIDX; sg->ei = 1; - sg->fi = dst_icg; + sg->fi = dst_icg + 1; } else if (xt->dst_inc) { d->ccr |= CCR_DST_AMODE_POSTINC; sg->fi = 0; diff --git a/drivers/media/platform/omap/omap_vout_vrfb.c b/drivers/media/platform/omap/omap_vout_vrfb.c index 29e3f5da59c1..11ec048929e8 100644 --- a/drivers/media/platform/omap/omap_vout_vrfb.c +++ b/drivers/media/platform/omap/omap_vout_vrfb.c @@ -253,8 +253,7 @@ int omap_vout_prepare_vrfb(struct omap_vout_device *vout, */ pixsize = vout->bpp * vout->vrfb_bpp; - dst_icg = ((MAX_PIXELS_PER_LINE * pixsize) - - (vout->pix.width * vout->bpp)) + 1; + dst_icg = MAX_PIXELS_PER_LINE * pixsize - vout->pix.width * vout->bpp; xt->src_start = vout->buf_phy_addr[vb->i]; xt->dst_start = vout->vrfb_context[vb->i].paddr[0]; From bfeaec7f7d2f6b09764a1b48e88e9ca3d5076419 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Sat, 20 Jul 2019 10:01:26 +0800 Subject: [PATCH 052/157] iommu/vt-d: Correctly check format of page table in debugfs PASID support and enable bit in the context entry isn't the right indicator for the type of tables (legacy or scalable mode). Check the DMA_RTADDR_SMT bit in the root context pointer instead. Cc: Ashok Raj Cc: Jacob Pan Cc: Kevin Tian Cc: Sai Praneeth Fixes: dd5142ca5d24b ("iommu/vt-d: Add debugfs support to show scalable mode DMAR table internals") Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel-iommu-debugfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/intel-iommu-debugfs.c b/drivers/iommu/intel-iommu-debugfs.c index 2b25d9c59336..471f05d452e0 100644 --- a/drivers/iommu/intel-iommu-debugfs.c +++ b/drivers/iommu/intel-iommu-debugfs.c @@ -235,7 +235,7 @@ static void ctx_tbl_walk(struct seq_file *m, struct intel_iommu *iommu, u16 bus) tbl_wlk.ctx_entry = context; m->private = &tbl_wlk; - if (pasid_supported(iommu) && is_pasid_enabled(context)) { + if (dmar_readq(iommu->reg + DMAR_RTADDR_REG) & DMA_RTADDR_SMT) { pasid_dir_ptr = context->lo & VTD_PAGE_MASK; pasid_dir_size = get_pasid_dir_size(context); pasid_dir_walk(m, pasid_dir_ptr, pasid_dir_size); From ab2cbeb0ed301a9f0460078e91b09f39958212ef Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 29 Jul 2019 17:46:00 +0100 Subject: [PATCH 053/157] iommu/dma: Handle SG length overflow better Since scatterlist dimensions are all unsigned ints, in the relatively rare cases where a device's max_segment_size is set to UINT_MAX, then the "cur_len + s_length <= max_len" check in __finalise_sg() will always return true. As a result, the corner case of such a device mapping an excessively large scatterlist which is mergeable to or beyond a total length of 4GB can lead to overflow and a bogus truncated dma_length in the resulting segment. As we already assume that any single segment must be no longer than max_len to begin with, this can easily be addressed by reshuffling the comparison. Fixes: 809eac54cdd6 ("iommu/dma: Implement scatterlist segment merging") Reported-by: Nicolin Chen Tested-by: Nicolin Chen Signed-off-by: Robin Murphy Signed-off-by: Joerg Roedel --- drivers/iommu/dma-iommu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 6441197a75ea..4ea9cf02ba2d 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -762,7 +762,7 @@ static int __finalise_sg(struct device *dev, struct scatterlist *sg, int nents, * - and wouldn't make the resulting output segment too long */ if (cur_len && !s_iova_off && (dma_addr & seg_mask) && - (cur_len + s_length <= max_len)) { + (max_len - cur_len >= s_length)) { /* ...then concatenate it with the previous one */ cur_len += s_length; } else { From ae23bfb68f2896835e54a137688906713cb607e7 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Tue, 6 Aug 2019 08:14:08 +0800 Subject: [PATCH 054/157] iommu/vt-d: Detach domain before using a private one When the default domain of a group doesn't work for a device, the iommu driver will try to use a private domain. The domain which was previously attached to the device must be detached. Cc: Ashok Raj Cc: Jacob Pan Cc: Kevin Tian Cc: Alex Williamson Fixes: 942067f1b6b97 ("iommu/vt-d: Identify default domains replaced with private") Reported-by: Alex Williamson Link: https://lkml.org/lkml/2019/8/2/1379 Signed-off-by: Lu Baolu Tested-by: Alex Williamson Signed-off-by: Joerg Roedel --- drivers/iommu/intel-iommu.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 3e22fa6ae8c8..37259b7f95a7 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -3449,6 +3449,7 @@ static bool iommu_need_mapping(struct device *dev) dmar_domain = to_dmar_domain(domain); dmar_domain->flags |= DOMAIN_FLAG_LOSE_CHILDREN; } + dmar_remove_one_dev_info(dev); get_private_domain_for_dev(dev); } @@ -4803,7 +4804,8 @@ static void dmar_remove_one_dev_info(struct device *dev) spin_lock_irqsave(&device_domain_lock, flags); info = dev->archdata.iommu; - __dmar_remove_one_dev_info(info); + if (info) + __dmar_remove_one_dev_info(info); spin_unlock_irqrestore(&device_domain_lock, flags); } @@ -5281,6 +5283,7 @@ static int intel_iommu_add_device(struct device *dev) if (device_def_domain_type(dev) == IOMMU_DOMAIN_IDENTITY) { ret = iommu_request_dm_for_dev(dev); if (ret) { + dmar_remove_one_dev_info(dev); dmar_domain->flags |= DOMAIN_FLAG_LOSE_CHILDREN; domain_add_dev_info(si_domain, dev); dev_info(dev, @@ -5291,6 +5294,7 @@ static int intel_iommu_add_device(struct device *dev) if (device_def_domain_type(dev) == IOMMU_DOMAIN_DMA) { ret = iommu_request_dma_domain_for_dev(dev); if (ret) { + dmar_remove_one_dev_info(dev); dmar_domain->flags |= DOMAIN_FLAG_LOSE_CHILDREN; if (!get_private_domain_for_dev(dev)) { dev_warn(dev, From 3a18844dcf89e636b2d0cbf577e3963b0bcb6d23 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Tue, 6 Aug 2019 08:14:09 +0800 Subject: [PATCH 055/157] iommu/vt-d: Fix possible use-after-free of private domain Multiple devices might share a private domain. One real example is a pci bridge and all devices behind it. When remove a private domain, make sure that it has been detached from all devices to avoid use-after-free case. Cc: Ashok Raj Cc: Jacob Pan Cc: Kevin Tian Cc: Alex Williamson Fixes: 942067f1b6b97 ("iommu/vt-d: Identify default domains replaced with private") Signed-off-by: Lu Baolu Tested-by: Alex Williamson Signed-off-by: Joerg Roedel --- drivers/iommu/intel-iommu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 37259b7f95a7..12d094d08c0a 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -4791,7 +4791,8 @@ static void __dmar_remove_one_dev_info(struct device_domain_info *info) /* free the private domain */ if (domain->flags & DOMAIN_FLAG_LOSE_CHILDREN && - !(domain->flags & DOMAIN_FLAG_STATIC_IDENTITY)) + !(domain->flags & DOMAIN_FLAG_STATIC_IDENTITY) && + list_empty(&domain->devices)) domain_exit(info->domain); free_devinfo_mem(info); From cfef67f016e4c00a2f423256fc678a6967a9fc09 Mon Sep 17 00:00:00 2001 From: Wenwen Wang Date: Fri, 9 Aug 2019 23:29:48 -0500 Subject: [PATCH 056/157] ALSA: hda - Fix a memory leak bug In snd_hda_parse_generic_codec(), 'spec' is allocated through kzalloc(). Then, the pin widgets in 'codec' are parsed. However, if the parsing process fails, 'spec' is not deallocated, leading to a memory leak. To fix the above issue, free 'spec' before returning the error. Fixes: 352f7f914ebb ("ALSA: hda - Merge Realtek parser code to generic parser") Signed-off-by: Wenwen Wang Cc: Signed-off-by: Takashi Iwai --- sound/pci/hda/hda_generic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index 485edaba0037..8f2beb1f3ae4 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -6100,7 +6100,7 @@ static int snd_hda_parse_generic_codec(struct hda_codec *codec) err = snd_hda_parse_pin_defcfg(codec, &spec->autocfg, NULL, 0); if (err < 0) - return err; + goto error; err = snd_hda_gen_parse_auto_config(codec, &spec->autocfg); if (err < 0) From e61a41256edf9f425039129757af4a80b5ed8162 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Fri, 9 Aug 2019 08:01:17 +0530 Subject: [PATCH 057/157] cpufreq: dev_pm_qos_update_request() can return 1 on success dev_pm_qos_update_request() can return 1 on success, so don't treat it as an error. Fixes: 18c49926c4bf ("cpufreq: Add QoS requests for userspace constraints") Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/cpufreq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 8dda62367816..c28ebf2810f1 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -2528,7 +2528,7 @@ static int cpufreq_boost_set_sw(int state) } ret = dev_pm_qos_update_request(policy->max_freq_req, policy->max); - if (ret) + if (ret < 0) break; } From 600f5badb78c316146d062cfd7af4a2cfb655baa Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 7 Aug 2019 12:36:01 +0530 Subject: [PATCH 058/157] cpufreq: schedutil: Don't skip freq update when limits change To avoid reducing the frequency of a CPU prematurely, we skip reducing the frequency if the CPU had been busy recently. This should not be done when the limits of the policy are changed, for example due to thermal throttling. We should always get the frequency within the new limits as soon as possible. Trying to fix this by using only one flag, i.e. need_freq_update, can lead to a race condition where the flag gets cleared without forcing us to change the frequency at least once. And so this patch introduces another flag to avoid that race condition. Fixes: ecd288429126 ("cpufreq: schedutil: Don't set next_freq to UINT_MAX") Cc: v4.18+ # v4.18+ Reported-by: Doug Smythies Tested-by: Doug Smythies Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- kernel/sched/cpufreq_schedutil.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 636ca6f88c8e..867b4bb6d4be 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -40,6 +40,7 @@ struct sugov_policy { struct task_struct *thread; bool work_in_progress; + bool limits_changed; bool need_freq_update; }; @@ -89,8 +90,11 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time) !cpufreq_this_cpu_can_update(sg_policy->policy)) return false; - if (unlikely(sg_policy->need_freq_update)) + if (unlikely(sg_policy->limits_changed)) { + sg_policy->limits_changed = false; + sg_policy->need_freq_update = true; return true; + } delta_ns = time - sg_policy->last_freq_update_time; @@ -437,7 +441,7 @@ static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; } static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu, struct sugov_policy *sg_policy) { if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_dl) - sg_policy->need_freq_update = true; + sg_policy->limits_changed = true; } static void sugov_update_single(struct update_util_data *hook, u64 time, @@ -457,7 +461,8 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, if (!sugov_should_update_freq(sg_policy, time)) return; - busy = sugov_cpu_is_busy(sg_cpu); + /* Limits may have changed, don't skip frequency update */ + busy = !sg_policy->need_freq_update && sugov_cpu_is_busy(sg_cpu); util = sugov_get_util(sg_cpu); max = sg_cpu->max; @@ -831,6 +836,7 @@ static int sugov_start(struct cpufreq_policy *policy) sg_policy->last_freq_update_time = 0; sg_policy->next_freq = 0; sg_policy->work_in_progress = false; + sg_policy->limits_changed = false; sg_policy->need_freq_update = false; sg_policy->cached_raw_freq = 0; @@ -879,7 +885,7 @@ static void sugov_limits(struct cpufreq_policy *policy) mutex_unlock(&sg_policy->work_lock); } - sg_policy->need_freq_update = true; + sg_policy->limits_changed = true; } struct cpufreq_governor schedutil_gov = { From cf14be0b41c659ede89abef3f7ec0e98e6cfea5b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 6 Aug 2019 14:33:23 +0300 Subject: [PATCH 059/157] dma-direct: fix DMA_ATTR_NO_KERNEL_MAPPING The new DMA_ATTR_NO_KERNEL_MAPPING needs to actually assign a dma_addr to work. Also skip it if the architecture needs forced decryption handling, as that needs a kernel virtual address. Fixes: d98849aff879 (dma-direct: handle DMA_ATTR_NO_KERNEL_MAPPING in common code) Signed-off-by: Christoph Hellwig Reviewed-by: Lucas Stach --- kernel/dma/direct.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 59bdceea3737..974e96a1de44 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -130,10 +130,12 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, if (!page) return NULL; - if (attrs & DMA_ATTR_NO_KERNEL_MAPPING) { + if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) && + !force_dma_unencrypted(dev)) { /* remove any dirty cache lines on the kernel alias */ if (!PageHighMem(page)) arch_dma_prep_coherent(page, size); + *dma_handle = phys_to_dma(dev, page_to_phys(page)); /* return the page pointer as the opaque cookie */ return page; } @@ -178,7 +180,8 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr, { unsigned int page_order = get_order(size); - if (attrs & DMA_ATTR_NO_KERNEL_MAPPING) { + if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) && + !force_dma_unencrypted(dev)) { /* cpu_addr is a struct page cookie, not a kernel address */ __dma_direct_free_pages(dev, size, cpu_addr); return; From d8ad55538abe443919e20e0bb996561bca9cad84 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Mon, 5 Aug 2019 17:51:53 +0200 Subject: [PATCH 060/157] dma-direct: don't truncate dma_required_mask to bus addressing capabilities The dma required_mask needs to reflect the actual addressing capabilities needed to handle the whole system RAM. When truncated down to the bus addressing capabilities dma_addressing_limited() will incorrectly signal no limitations for devices which are restricted by the bus_dma_mask. Fixes: b4ebe6063204 (dma-direct: implement complete bus_dma_mask handling) Signed-off-by: Lucas Stach Tested-by: Atish Patra Signed-off-by: Christoph Hellwig --- kernel/dma/direct.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 974e96a1de44..795c9b095d75 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -47,9 +47,6 @@ u64 dma_direct_get_required_mask(struct device *dev) { u64 max_dma = phys_to_dma_direct(dev, (max_pfn - 1) << PAGE_SHIFT); - if (dev->bus_dma_mask && dev->bus_dma_mask < max_dma) - max_dma = dev->bus_dma_mask; - return (1ULL << (fls64(max_dma) - 1)) * 2 - 1; } From 33dcb37cef741294b481f4d889a465b8091f11bf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 26 Jul 2019 09:26:40 +0200 Subject: [PATCH 061/157] dma-mapping: fix page attributes for dma_mmap_* All the way back to introducing dma_common_mmap we've defaulted to mark the pages as uncached. But this is wrong for DMA coherent devices. Later on DMA_ATTR_WRITE_COMBINE also got incorrect treatment as that flag is only treated special on the alloc side for non-coherent devices. Introduce a new dma_pgprot helper that deals with the check for coherent devices so that only the remapping cases ever reach arch_dma_mmap_pgprot and we thus ensure no aliasing of page attributes happens, which makes the powerpc version of arch_dma_mmap_pgprot obsolete and simplifies the remaining ones. Note that this means arch_dma_mmap_pgprot is a bit misnamed now, but we'll phase it out soon. Fixes: 64ccc9c033c6 ("common: dma-mapping: add support for generic dma_mmap_* calls") Reported-by: Shawn Anastasio Reported-by: Gavin Li Signed-off-by: Christoph Hellwig Acked-by: Catalin Marinas # arm64 --- arch/arm/mm/dma-mapping.c | 4 +--- arch/arm64/mm/dma-mapping.c | 4 +--- arch/powerpc/Kconfig | 1 - arch/powerpc/kernel/Makefile | 3 +-- arch/powerpc/kernel/dma-common.c | 17 ----------------- drivers/iommu/dma-iommu.c | 6 +++--- include/linux/dma-noncoherent.h | 13 +++++++++---- kernel/dma/mapping.c | 19 ++++++++++++++++++- kernel/dma/remap.c | 2 +- 9 files changed, 34 insertions(+), 35 deletions(-) delete mode 100644 arch/powerpc/kernel/dma-common.c diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 6774b03aa405..d42557ee69c2 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -2405,9 +2405,7 @@ long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr, pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs) { - if (!dev_is_dma_coherent(dev)) - return __get_dma_pgprot(attrs, prot); - return prot; + return __get_dma_pgprot(attrs, prot); } void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 1d3f0b5a9940..bd2b039f43a6 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -14,9 +14,7 @@ pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs) { - if (!dev_is_dma_coherent(dev) || (attrs & DMA_ATTR_WRITE_COMBINE)) - return pgprot_writecombine(prot); - return prot; + return pgprot_writecombine(prot); } void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 77f6ebf97113..d8dcd8820369 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -121,7 +121,6 @@ config PPC select ARCH_32BIT_OFF_T if PPC32 select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEVMEM_IS_ALLOWED - select ARCH_HAS_DMA_MMAP_PGPROT select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index ea0c69236789..56dfa7a2a6f2 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -49,8 +49,7 @@ obj-y := cputable.o ptrace.o syscalls.o \ signal.o sysfs.o cacheinfo.o time.o \ prom.o traps.o setup-common.o \ udbg.o misc.o io.o misc_$(BITS).o \ - of_platform.o prom_parse.o \ - dma-common.o + of_platform.o prom_parse.o obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \ signal_64.o ptrace32.o \ paca.o nvram_64.o firmware.o diff --git a/arch/powerpc/kernel/dma-common.c b/arch/powerpc/kernel/dma-common.c deleted file mode 100644 index dc7ef6b17b69..000000000000 --- a/arch/powerpc/kernel/dma-common.c +++ /dev/null @@ -1,17 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Contains common dma routines for all powerpc platforms. - * - * Copyright (C) 2019 Shawn Anastasio. - */ - -#include -#include - -pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot, - unsigned long attrs) -{ - if (!dev_is_dma_coherent(dev)) - return pgprot_noncached(prot); - return prot; -} diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index a7f9c3edbcb2..0015fe610b23 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -574,7 +574,7 @@ static void *iommu_dma_alloc_remap(struct device *dev, size_t size, struct iova_domain *iovad = &cookie->iovad; bool coherent = dev_is_dma_coherent(dev); int ioprot = dma_info_to_prot(DMA_BIDIRECTIONAL, coherent, attrs); - pgprot_t prot = arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs); + pgprot_t prot = dma_pgprot(dev, PAGE_KERNEL, attrs); unsigned int count, min_size, alloc_sizes = domain->pgsize_bitmap; struct page **pages; struct sg_table sgt; @@ -975,7 +975,7 @@ static void *iommu_dma_alloc_pages(struct device *dev, size_t size, return NULL; if (IS_ENABLED(CONFIG_DMA_REMAP) && (!coherent || PageHighMem(page))) { - pgprot_t prot = arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs); + pgprot_t prot = dma_pgprot(dev, PAGE_KERNEL, attrs); cpu_addr = dma_common_contiguous_remap(page, alloc_size, VM_USERMAP, prot, __builtin_return_address(0)); @@ -1035,7 +1035,7 @@ static int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma, unsigned long pfn, off = vma->vm_pgoff; int ret; - vma->vm_page_prot = arch_dma_mmap_pgprot(dev, vma->vm_page_prot, attrs); + vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs); if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret)) return ret; diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h index 3813211a9aad..0bff3d7fac92 100644 --- a/include/linux/dma-noncoherent.h +++ b/include/linux/dma-noncoherent.h @@ -42,13 +42,18 @@ void arch_dma_free(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs); long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr, dma_addr_t dma_addr); - -#ifdef CONFIG_ARCH_HAS_DMA_MMAP_PGPROT pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs); + +#ifdef CONFIG_MMU +pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs); #else -# define arch_dma_mmap_pgprot(dev, prot, attrs) pgprot_noncached(prot) -#endif +static inline pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, + unsigned long attrs) +{ + return prot; /* no protection bits supported without page tables */ +} +#endif /* CONFIG_MMU */ #ifdef CONFIG_DMA_NONCOHERENT_CACHE_SYNC void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size, diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index b945239621d8..b0038ca3aa92 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -150,6 +150,23 @@ int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, } EXPORT_SYMBOL(dma_get_sgtable_attrs); +#ifdef CONFIG_MMU +/* + * Return the page attributes used for mapping dma_alloc_* memory, either in + * kernel space if remapping is needed, or to userspace through dma_mmap_*. + */ +pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs) +{ + if (dev_is_dma_coherent(dev) || + (IS_ENABLED(CONFIG_DMA_NONCOHERENT_CACHE_SYNC) && + (attrs & DMA_ATTR_NON_CONSISTENT))) + return prot; + if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_MMAP_PGPROT)) + return arch_dma_mmap_pgprot(dev, prot, attrs); + return pgprot_noncached(prot); +} +#endif /* CONFIG_MMU */ + /* * Create userspace mapping for the DMA-coherent memory. */ @@ -164,7 +181,7 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, unsigned long pfn; int ret = -ENXIO; - vma->vm_page_prot = arch_dma_mmap_pgprot(dev, vma->vm_page_prot, attrs); + vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs); if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret)) return ret; diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c index a594aec07882..ffe78f0b2fe4 100644 --- a/kernel/dma/remap.c +++ b/kernel/dma/remap.c @@ -218,7 +218,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, /* create a coherent mapping */ ret = dma_common_contiguous_remap(page, size, VM_USERMAP, - arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs), + dma_pgprot(dev, PAGE_KERNEL, attrs), __builtin_return_address(0)); if (!ret) { __dma_direct_free_pages(dev, size, page); From 54b13723f765122f3f5f49d07f3e48fa9fcf8c7c Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Sat, 10 Aug 2019 00:19:11 -0500 Subject: [PATCH 062/157] sh: kernel: disassemble: Mark expected switch fall-throughs Remove logically dead code and mark switch cases where we are expecting to fall through. Fix the following warnings (Building: defconfig sh): arch/sh/kernel/disassemble.c:478:8: warning: this statement may fall through [-Wimplicit-fallthrough=] arch/sh/kernel/disassemble.c:487:8: warning: this statement may fall through [-Wimplicit-fallthrough=] arch/sh/kernel/disassemble.c:496:8: warning: this statement may fall through [-Wimplicit-fallthrough=] Reviewed-by: Geert Uytterhoeven Reviewed-by: Guenter Roeck Tested-by: Guenter Roeck Signed-off-by: Gustavo A. R. Silva --- arch/sh/kernel/disassemble.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/sh/kernel/disassemble.c b/arch/sh/kernel/disassemble.c index defebf1a9c8a..845543780cc5 100644 --- a/arch/sh/kernel/disassemble.c +++ b/arch/sh/kernel/disassemble.c @@ -475,8 +475,6 @@ static void print_sh_insn(u32 memaddr, u16 insn) printk("dbr"); break; case FD_REG_N: - if (0) - goto d_reg_n; case F_REG_N: printk("fr%d", rn); break; @@ -488,7 +486,7 @@ static void print_sh_insn(u32 memaddr, u16 insn) printk("xd%d", rn & ~1); break; } - d_reg_n: + /* else, fall through */ case D_REG_N: printk("dr%d", rn); break; @@ -497,6 +495,7 @@ static void print_sh_insn(u32 memaddr, u16 insn) printk("xd%d", rm & ~1); break; } + /* else, fall through */ case D_REG_M: printk("dr%d", rm); break; From 1ee1119d184bb06af921b48c3021d921bbd85bac Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Fri, 9 Aug 2019 23:43:56 -0500 Subject: [PATCH 063/157] sh: kernel: hw_breakpoint: Fix missing break in switch statement Add missing break statement in order to prevent the code from falling through to case SH_BREAKPOINT_WRITE. Fixes: 09a072947791 ("sh: hw-breakpoints: Add preliminary support for SH-4A UBC.") Cc: stable@vger.kernel.org Reviewed-by: Geert Uytterhoeven Reviewed-by: Guenter Roeck Tested-by: Guenter Roeck Signed-off-by: Gustavo A. R. Silva --- arch/sh/kernel/hw_breakpoint.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/sh/kernel/hw_breakpoint.c b/arch/sh/kernel/hw_breakpoint.c index 3bd010b4c55f..f10d64311127 100644 --- a/arch/sh/kernel/hw_breakpoint.c +++ b/arch/sh/kernel/hw_breakpoint.c @@ -157,6 +157,7 @@ int arch_bp_generic_fields(int sh_len, int sh_type, switch (sh_type) { case SH_BREAKPOINT_READ: *gen_type = HW_BREAKPOINT_R; + break; case SH_BREAKPOINT_WRITE: *gen_type = HW_BREAKPOINT_W; break; From 5dac665cf403967bb79a7aeb8c182a621fe617ff Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Wed, 31 Jul 2019 19:15:43 +0900 Subject: [PATCH 064/157] usb: gadget: udc: renesas_usb3: Fix sysfs interface of "role" Since the role_store() uses strncmp(), it's possible to refer out-of-memory if the sysfs data size is smaller than strlen("host"). This patch fixes it by using sysfs_streq() instead of strncmp(). Fixes: cc995c9ec118 ("usb: gadget: udc: renesas_usb3: add support for usb role swap") Cc: # v4.12+ Reviewed-by: Geert Uytterhoeven Signed-off-by: Yoshihiro Shimoda Signed-off-by: Felipe Balbi --- drivers/usb/gadget/udc/renesas_usb3.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/usb/gadget/udc/renesas_usb3.c b/drivers/usb/gadget/udc/renesas_usb3.c index 87062d22134d..1f4c3fbd1df8 100644 --- a/drivers/usb/gadget/udc/renesas_usb3.c +++ b/drivers/usb/gadget/udc/renesas_usb3.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -2450,9 +2451,9 @@ static ssize_t role_store(struct device *dev, struct device_attribute *attr, if (usb3->forced_b_device) return -EBUSY; - if (!strncmp(buf, "host", strlen("host"))) + if (sysfs_streq(buf, "host")) new_mode_is_host = true; - else if (!strncmp(buf, "peripheral", strlen("peripheral"))) + else if (sysfs_streq(buf, "peripheral")) new_mode_is_host = false; else return -EINVAL; From 602fda17c7356bb7ae98467d93549057481d11dd Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Fri, 26 Jul 2019 14:59:03 +1000 Subject: [PATCH 065/157] usb: gadget: composite: Clear "suspended" on reset/disconnect In some cases, one can get out of suspend with a reset or a disconnect followed by a reconnect. Previously we would leave a stale suspended flag set. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Felipe Balbi --- drivers/usb/gadget/composite.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index 9118b42c70b6..76883ff4f5bb 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -1976,6 +1976,7 @@ void composite_disconnect(struct usb_gadget *gadget) * disconnect callbacks? */ spin_lock_irqsave(&cdev->lock, flags); + cdev->suspended = 0; if (cdev->config) reset_config(cdev); if (cdev->driver->disconnect) From 4a56a478a525d6427be90753451c40e1327caa1a Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Fri, 26 Jul 2019 14:59:04 +1000 Subject: [PATCH 066/157] usb: gadget: mass_storage: Fix races between fsg_disable and fsg_set_alt If fsg_disable() and fsg_set_alt() are called too closely to each other (for example due to a quick reset/reconnect), what can happen is that fsg_set_alt sets common->new_fsg from an interrupt while handle_exception is trying to process the config change caused by fsg_disable(): fsg_disable() ... handle_exception() sets state back to FSG_STATE_NORMAL hasn't yet called do_set_interface() or is inside it. ---> interrupt fsg_set_alt sets common->new_fsg queues a new FSG_STATE_CONFIG_CHANGE <--- Now, the first handle_exception can "see" the updated new_fsg, treats it as if it was a fsg_set_alt() response, call usb_composite_setup_continue() etc... But then, the thread sees the second FSG_STATE_CONFIG_CHANGE, and goes back down the same path, wipes and reattaches a now active fsg, and .. calls usb_composite_setup_continue() which at this point is wrong. Not only we get a backtrace, but I suspect the second set_interface wrecks some state causing the host to get upset in my case. This fixes it by replacing "new_fsg" by a "state argument" (same principle) which is set in the same lock section as the state update, and retrieved similarly. That way, there is never any discrepancy between the dequeued state and the observed value of it. We keep the ability to have the latest reconfig operation take precedence, but we guarantee that once "dequeued" the argument (new_fsg) will not be clobbered by any new event. Signed-off-by: Benjamin Herrenschmidt Acked-by: Alan Stern Signed-off-by: Felipe Balbi --- drivers/usb/gadget/function/f_mass_storage.c | 28 +++++++++++++------- 1 file changed, 18 insertions(+), 10 deletions(-) diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c index 29cc5693e05c..7c96c4665178 100644 --- a/drivers/usb/gadget/function/f_mass_storage.c +++ b/drivers/usb/gadget/function/f_mass_storage.c @@ -261,7 +261,7 @@ struct fsg_common; struct fsg_common { struct usb_gadget *gadget; struct usb_composite_dev *cdev; - struct fsg_dev *fsg, *new_fsg; + struct fsg_dev *fsg; wait_queue_head_t io_wait; wait_queue_head_t fsg_wait; @@ -290,6 +290,7 @@ struct fsg_common { unsigned int bulk_out_maxpacket; enum fsg_state state; /* For exception handling */ unsigned int exception_req_tag; + void *exception_arg; enum data_direction data_dir; u32 data_size; @@ -391,7 +392,8 @@ static int fsg_set_halt(struct fsg_dev *fsg, struct usb_ep *ep) /* These routines may be called in process context or in_irq */ -static void raise_exception(struct fsg_common *common, enum fsg_state new_state) +static void __raise_exception(struct fsg_common *common, enum fsg_state new_state, + void *arg) { unsigned long flags; @@ -404,6 +406,7 @@ static void raise_exception(struct fsg_common *common, enum fsg_state new_state) if (common->state <= new_state) { common->exception_req_tag = common->ep0_req_tag; common->state = new_state; + common->exception_arg = arg; if (common->thread_task) send_sig_info(SIGUSR1, SEND_SIG_PRIV, common->thread_task); @@ -411,6 +414,10 @@ static void raise_exception(struct fsg_common *common, enum fsg_state new_state) spin_unlock_irqrestore(&common->lock, flags); } +static void raise_exception(struct fsg_common *common, enum fsg_state new_state) +{ + __raise_exception(common, new_state, NULL); +} /*-------------------------------------------------------------------------*/ @@ -2285,16 +2292,16 @@ static int do_set_interface(struct fsg_common *common, struct fsg_dev *new_fsg) static int fsg_set_alt(struct usb_function *f, unsigned intf, unsigned alt) { struct fsg_dev *fsg = fsg_from_func(f); - fsg->common->new_fsg = fsg; - raise_exception(fsg->common, FSG_STATE_CONFIG_CHANGE); + + __raise_exception(fsg->common, FSG_STATE_CONFIG_CHANGE, fsg); return USB_GADGET_DELAYED_STATUS; } static void fsg_disable(struct usb_function *f) { struct fsg_dev *fsg = fsg_from_func(f); - fsg->common->new_fsg = NULL; - raise_exception(fsg->common, FSG_STATE_CONFIG_CHANGE); + + __raise_exception(fsg->common, FSG_STATE_CONFIG_CHANGE, NULL); } @@ -2307,6 +2314,7 @@ static void handle_exception(struct fsg_common *common) enum fsg_state old_state; struct fsg_lun *curlun; unsigned int exception_req_tag; + struct fsg_dev *new_fsg; /* * Clear the existing signals. Anything but SIGUSR1 is converted @@ -2360,6 +2368,7 @@ static void handle_exception(struct fsg_common *common) common->next_buffhd_to_fill = &common->buffhds[0]; common->next_buffhd_to_drain = &common->buffhds[0]; exception_req_tag = common->exception_req_tag; + new_fsg = common->exception_arg; old_state = common->state; common->state = FSG_STATE_NORMAL; @@ -2413,8 +2422,8 @@ static void handle_exception(struct fsg_common *common) break; case FSG_STATE_CONFIG_CHANGE: - do_set_interface(common, common->new_fsg); - if (common->new_fsg) + do_set_interface(common, new_fsg); + if (new_fsg) usb_composite_setup_continue(common->cdev); break; @@ -2989,8 +2998,7 @@ static void fsg_unbind(struct usb_configuration *c, struct usb_function *f) DBG(fsg, "unbind\n"); if (fsg->common->fsg == fsg) { - fsg->common->new_fsg = NULL; - raise_exception(fsg->common, FSG_STATE_CONFIG_CHANGE); + __raise_exception(fsg->common, FSG_STATE_CONFIG_CHANGE, NULL); /* FIXME: make interruptible or killable somehow? */ wait_event(common->fsg_wait, common->fsg != fsg); } From 508c5849c62d009e03f37ad0f556071fac5112f0 Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Thu, 1 Aug 2019 13:57:36 +0000 Subject: [PATCH 067/157] habanalabs: Avoid double free in error flow In case kernel context init fails during device initialization, both hl_ctx_put() and kfree() are called, ending with a double free of the kernel context. Calling kfree() is needed only when a failure happens between the allocation of the kernel context and its initialization, so move it to there and remove it from the error flow. Signed-off-by: Tomer Tayar Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/device.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c index 0c4894dd9c02..7a8f9d0b71b5 100644 --- a/drivers/misc/habanalabs/device.c +++ b/drivers/misc/habanalabs/device.c @@ -970,7 +970,8 @@ int hl_device_init(struct hl_device *hdev, struct class *hclass) rc = hl_ctx_init(hdev, hdev->kernel_ctx, true); if (rc) { dev_err(hdev->dev, "failed to initialize kernel context\n"); - goto free_ctx; + kfree(hdev->kernel_ctx); + goto mmu_fini; } rc = hl_cb_pool_init(hdev); @@ -1053,8 +1054,6 @@ int hl_device_init(struct hl_device *hdev, struct class *hclass) if (hl_ctx_put(hdev->kernel_ctx) != 1) dev_err(hdev->dev, "kernel ctx is still alive on initialization failure\n"); -free_ctx: - kfree(hdev->kernel_ctx); mmu_fini: hl_mmu_fini(hdev); eq_fini: From c8113756ba27298d6e95403c087dc5881b419a99 Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Sun, 4 Aug 2019 07:03:41 +0000 Subject: [PATCH 068/157] habanalabs: fix DRAM usage accounting on context tear down The patch fix the DRAM usage accounting by adding a missing update of the DRAM memory consumption, when a context is being torn down without an organized release of the allocated memory. Signed-off-by: Tomer Tayar Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/memory.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/misc/habanalabs/memory.c b/drivers/misc/habanalabs/memory.c index 42d237cae1dc..365fb0cb8dff 100644 --- a/drivers/misc/habanalabs/memory.c +++ b/drivers/misc/habanalabs/memory.c @@ -1629,6 +1629,8 @@ void hl_vm_ctx_fini(struct hl_ctx *ctx) dev_dbg(hdev->dev, "page list 0x%p of asid %d is still alive\n", phys_pg_list, ctx->asid); + atomic64_sub(phys_pg_list->total_size, + &hdev->dram_used_mem); free_phys_pg_pack(hdev, phys_pg_list); idr_remove(&vm->phys_pg_pack_handles, i); } From 213ad5ad016a0da975b35f54e8cd236c3b04724b Mon Sep 17 00:00:00 2001 From: Ben Segal Date: Thu, 1 Aug 2019 23:20:32 +0000 Subject: [PATCH 069/157] habanalabs: fix endianness handling for packets from user Packets that arrive from the user and need to be parsed by the driver are assumed to be in LE format. This patch fix all the places where the code handles these packets and use the correct endianness macros to handle them, as the driver handles the packets in CPU format (LE or BE depending on the arch). Signed-off-by: Ben Segal Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/goya/goya.c | 32 +++++++++++-------- .../habanalabs/include/goya/goya_packets.h | 13 ++++++++ 2 files changed, 32 insertions(+), 13 deletions(-) diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index a0e181714891..e8b1142910e0 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -3428,12 +3428,13 @@ static int goya_validate_cb(struct hl_device *hdev, while (cb_parsed_length < parser->user_cb_size) { enum packet_id pkt_id; u16 pkt_size; - void *user_pkt; + struct goya_packet *user_pkt; - user_pkt = (void *) (uintptr_t) + user_pkt = (struct goya_packet *) (uintptr_t) (parser->user_cb->kernel_address + cb_parsed_length); - pkt_id = (enum packet_id) (((*(u64 *) user_pkt) & + pkt_id = (enum packet_id) ( + (le64_to_cpu(user_pkt->header) & PACKET_HEADER_PACKET_ID_MASK) >> PACKET_HEADER_PACKET_ID_SHIFT); @@ -3453,7 +3454,8 @@ static int goya_validate_cb(struct hl_device *hdev, * need to validate here as well because patch_cb() is * not called in MMU path while this function is called */ - rc = goya_validate_wreg32(hdev, parser, user_pkt); + rc = goya_validate_wreg32(hdev, + parser, (struct packet_wreg32 *) user_pkt); break; case PACKET_WREG_BULK: @@ -3481,10 +3483,10 @@ static int goya_validate_cb(struct hl_device *hdev, case PACKET_LIN_DMA: if (is_mmu) rc = goya_validate_dma_pkt_mmu(hdev, parser, - user_pkt); + (struct packet_lin_dma *) user_pkt); else rc = goya_validate_dma_pkt_no_mmu(hdev, parser, - user_pkt); + (struct packet_lin_dma *) user_pkt); break; case PACKET_MSG_LONG: @@ -3657,15 +3659,16 @@ static int goya_patch_cb(struct hl_device *hdev, enum packet_id pkt_id; u16 pkt_size; u32 new_pkt_size = 0; - void *user_pkt, *kernel_pkt; + struct goya_packet *user_pkt, *kernel_pkt; - user_pkt = (void *) (uintptr_t) + user_pkt = (struct goya_packet *) (uintptr_t) (parser->user_cb->kernel_address + cb_parsed_length); - kernel_pkt = (void *) (uintptr_t) + kernel_pkt = (struct goya_packet *) (uintptr_t) (parser->patched_cb->kernel_address + cb_patched_cur_length); - pkt_id = (enum packet_id) (((*(u64 *) user_pkt) & + pkt_id = (enum packet_id) ( + (le64_to_cpu(user_pkt->header) & PACKET_HEADER_PACKET_ID_MASK) >> PACKET_HEADER_PACKET_ID_SHIFT); @@ -3680,15 +3683,18 @@ static int goya_patch_cb(struct hl_device *hdev, switch (pkt_id) { case PACKET_LIN_DMA: - rc = goya_patch_dma_packet(hdev, parser, user_pkt, - kernel_pkt, &new_pkt_size); + rc = goya_patch_dma_packet(hdev, parser, + (struct packet_lin_dma *) user_pkt, + (struct packet_lin_dma *) kernel_pkt, + &new_pkt_size); cb_patched_cur_length += new_pkt_size; break; case PACKET_WREG_32: memcpy(kernel_pkt, user_pkt, pkt_size); cb_patched_cur_length += pkt_size; - rc = goya_validate_wreg32(hdev, parser, kernel_pkt); + rc = goya_validate_wreg32(hdev, parser, + (struct packet_wreg32 *) kernel_pkt); break; case PACKET_WREG_BULK: diff --git a/drivers/misc/habanalabs/include/goya/goya_packets.h b/drivers/misc/habanalabs/include/goya/goya_packets.h index a14407b975e4..ef54bad20509 100644 --- a/drivers/misc/habanalabs/include/goya/goya_packets.h +++ b/drivers/misc/habanalabs/include/goya/goya_packets.h @@ -52,6 +52,19 @@ enum goya_dma_direction { #define GOYA_PKT_CTL_MB_SHIFT 31 #define GOYA_PKT_CTL_MB_MASK 0x80000000 +/* All packets have, at least, an 8-byte header, which contains + * the packet type. The kernel driver uses the packet header for packet + * validation and to perform any necessary required preparation before + * sending them off to the hardware. + */ +struct goya_packet { + __le64 header; + /* The rest of the packet data follows. Use the corresponding + * packet_XXX struct to deference the data, based on packet type + */ + u8 contents[0]; +}; + struct packet_nop { __le32 reserved; __le32 ctl; From 4e87334a0ef43663019dbaf3638ad10fd8c3320c Mon Sep 17 00:00:00 2001 From: Ben Segal Date: Thu, 1 Aug 2019 23:22:20 +0000 Subject: [PATCH 070/157] habanalabs: fix completion queue handling when host is BE This patch fix the CQ irq handler to work in hosts with BE architecture. It adds the correct endian-swapping macros around the relevant memory accesses. Signed-off-by: Ben Segal Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/irq.c | 27 +++++++++++++-------------- 1 file changed, 13 insertions(+), 14 deletions(-) diff --git a/drivers/misc/habanalabs/irq.c b/drivers/misc/habanalabs/irq.c index ea9f72ff456c..199791b57caf 100644 --- a/drivers/misc/habanalabs/irq.c +++ b/drivers/misc/habanalabs/irq.c @@ -80,8 +80,7 @@ irqreturn_t hl_irq_handler_cq(int irq, void *arg) struct hl_cs_job *job; bool shadow_index_valid; u16 shadow_index; - u32 *cq_entry; - u32 *cq_base; + struct hl_cq_entry *cq_entry, *cq_base; if (hdev->disabled) { dev_dbg(hdev->dev, @@ -90,29 +89,29 @@ irqreturn_t hl_irq_handler_cq(int irq, void *arg) return IRQ_HANDLED; } - cq_base = (u32 *) (uintptr_t) cq->kernel_address; + cq_base = (struct hl_cq_entry *) (uintptr_t) cq->kernel_address; while (1) { - bool entry_ready = ((cq_base[cq->ci] & CQ_ENTRY_READY_MASK) + bool entry_ready = ((le32_to_cpu(cq_base[cq->ci].data) & + CQ_ENTRY_READY_MASK) >> CQ_ENTRY_READY_SHIFT); if (!entry_ready) break; - cq_entry = (u32 *) &cq_base[cq->ci]; + cq_entry = (struct hl_cq_entry *) &cq_base[cq->ci]; - /* - * Make sure we read CQ entry contents after we've + /* Make sure we read CQ entry contents after we've * checked the ownership bit. */ dma_rmb(); - shadow_index_valid = - ((*cq_entry & CQ_ENTRY_SHADOW_INDEX_VALID_MASK) + shadow_index_valid = ((le32_to_cpu(cq_entry->data) & + CQ_ENTRY_SHADOW_INDEX_VALID_MASK) >> CQ_ENTRY_SHADOW_INDEX_VALID_SHIFT); - shadow_index = (u16) - ((*cq_entry & CQ_ENTRY_SHADOW_INDEX_MASK) + shadow_index = (u16) ((le32_to_cpu(cq_entry->data) & + CQ_ENTRY_SHADOW_INDEX_MASK) >> CQ_ENTRY_SHADOW_INDEX_SHIFT); queue = &hdev->kernel_queues[cq->hw_queue_id]; @@ -122,8 +121,7 @@ irqreturn_t hl_irq_handler_cq(int irq, void *arg) queue_work(hdev->cq_wq, &job->finish_work); } - /* - * Update ci of the context's queue. There is no + /* Update ci of the context's queue. There is no * need to protect it with spinlock because this update is * done only inside IRQ and there is a different IRQ per * queue @@ -131,7 +129,8 @@ irqreturn_t hl_irq_handler_cq(int irq, void *arg) queue->ci = hl_queue_inc_ptr(queue->ci); /* Clear CQ entry ready bit */ - cq_base[cq->ci] &= ~CQ_ENTRY_READY_MASK; + cq_entry->data = cpu_to_le32(le32_to_cpu(cq_entry->data) & + ~CQ_ENTRY_READY_MASK); cq->ci = hl_cq_inc_ptr(cq->ci); From b9040c99414ba5b85090595a61abc686a5dbb388 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Thu, 8 Aug 2019 15:45:58 +0300 Subject: [PATCH 071/157] habanalabs: fix endianness handling for internal QMAN submission The PQs of internal H/W queues (QMANs) can be located in different memory areas for different ASICs. Therefore, when writing PQEs, we need to use the correct function according to the location of the PQ. e.g. if the PQ is located in the device's memory (SRAM or DRAM), we need to use memcpy_toio() so it would work in architectures that have separate address ranges for IO memory. This patch makes the code that writes the PQE to be ASIC-specific so we can handle this properly per ASIC. Signed-off-by: Oded Gabbay Tested-by: Ben Segal --- drivers/misc/habanalabs/goya/goya.c | 7 ++++--- drivers/misc/habanalabs/goya/goyaP.h | 2 +- drivers/misc/habanalabs/habanalabs.h | 9 +++++++-- drivers/misc/habanalabs/hw_queue.c | 14 +++++--------- 4 files changed, 17 insertions(+), 15 deletions(-) diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index e8b1142910e0..b39b9c98fe1d 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -2729,9 +2729,10 @@ void goya_ring_doorbell(struct hl_device *hdev, u32 hw_queue_id, u32 pi) GOYA_ASYNC_EVENT_ID_PI_UPDATE); } -void goya_flush_pq_write(struct hl_device *hdev, u64 *pq, u64 exp_val) +void goya_pqe_write(struct hl_device *hdev, __le64 *pqe, struct hl_bd *bd) { - /* Not needed in Goya */ + /* The QMANs are on the SRAM so need to copy to IO space */ + memcpy_toio((void __iomem *) pqe, bd, sizeof(struct hl_bd)); } static void *goya_dma_alloc_coherent(struct hl_device *hdev, size_t size, @@ -5048,7 +5049,7 @@ static const struct hl_asic_funcs goya_funcs = { .resume = goya_resume, .cb_mmap = goya_cb_mmap, .ring_doorbell = goya_ring_doorbell, - .flush_pq_write = goya_flush_pq_write, + .pqe_write = goya_pqe_write, .asic_dma_alloc_coherent = goya_dma_alloc_coherent, .asic_dma_free_coherent = goya_dma_free_coherent, .get_int_queue_base = goya_get_int_queue_base, diff --git a/drivers/misc/habanalabs/goya/goyaP.h b/drivers/misc/habanalabs/goya/goyaP.h index f8c611883dc1..d7f48c9c41cd 100644 --- a/drivers/misc/habanalabs/goya/goyaP.h +++ b/drivers/misc/habanalabs/goya/goyaP.h @@ -177,7 +177,7 @@ int goya_late_init(struct hl_device *hdev); void goya_late_fini(struct hl_device *hdev); void goya_ring_doorbell(struct hl_device *hdev, u32 hw_queue_id, u32 pi); -void goya_flush_pq_write(struct hl_device *hdev, u64 *pq, u64 exp_val); +void goya_pqe_write(struct hl_device *hdev, __le64 *pqe, struct hl_bd *bd); void goya_update_eq_ci(struct hl_device *hdev, u32 val); void goya_restore_phase_topology(struct hl_device *hdev); int goya_context_switch(struct hl_device *hdev, u32 asid); diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h index 6a4c64b97f38..ce83adafcf2d 100644 --- a/drivers/misc/habanalabs/habanalabs.h +++ b/drivers/misc/habanalabs/habanalabs.h @@ -441,7 +441,11 @@ enum hl_pll_frequency { * @resume: handles IP specific H/W or SW changes for resume. * @cb_mmap: maps a CB. * @ring_doorbell: increment PI on a given QMAN. - * @flush_pq_write: flush PQ entry write if necessary, WARN if flushing failed. + * @pqe_write: Write the PQ entry to the PQ. This is ASIC-specific + * function because the PQs are located in different memory areas + * per ASIC (SRAM, DRAM, Host memory) and therefore, the method of + * writing the PQE must match the destination memory area + * properties. * @asic_dma_alloc_coherent: Allocate coherent DMA memory by calling * dma_alloc_coherent(). This is ASIC function because * its implementation is not trivial when the driver @@ -510,7 +514,8 @@ struct hl_asic_funcs { int (*cb_mmap)(struct hl_device *hdev, struct vm_area_struct *vma, u64 kaddress, phys_addr_t paddress, u32 size); void (*ring_doorbell)(struct hl_device *hdev, u32 hw_queue_id, u32 pi); - void (*flush_pq_write)(struct hl_device *hdev, u64 *pq, u64 exp_val); + void (*pqe_write)(struct hl_device *hdev, __le64 *pqe, + struct hl_bd *bd); void* (*asic_dma_alloc_coherent)(struct hl_device *hdev, size_t size, dma_addr_t *dma_handle, gfp_t flag); void (*asic_dma_free_coherent)(struct hl_device *hdev, size_t size, diff --git a/drivers/misc/habanalabs/hw_queue.c b/drivers/misc/habanalabs/hw_queue.c index e3b5517897ea..5f5673b74985 100644 --- a/drivers/misc/habanalabs/hw_queue.c +++ b/drivers/misc/habanalabs/hw_queue.c @@ -290,23 +290,19 @@ static void int_hw_queue_schedule_job(struct hl_cs_job *job) struct hl_device *hdev = job->cs->ctx->hdev; struct hl_hw_queue *q = &hdev->kernel_queues[job->hw_queue_id]; struct hl_bd bd; - u64 *pi, *pbd = (u64 *) &bd; + __le64 *pi; bd.ctl = 0; - bd.len = __cpu_to_le32(job->job_cb_size); - bd.ptr = __cpu_to_le64((u64) (uintptr_t) job->user_cb); + bd.len = cpu_to_le32(job->job_cb_size); + bd.ptr = cpu_to_le64((u64) (uintptr_t) job->user_cb); - pi = (u64 *) (uintptr_t) (q->kernel_address + + pi = (__le64 *) (uintptr_t) (q->kernel_address + ((q->pi & (q->int_queue_len - 1)) * sizeof(bd))); - pi[0] = pbd[0]; - pi[1] = pbd[1]; - q->pi++; q->pi &= ((q->int_queue_len << 1) - 1); - /* Flush PQ entry write. Relevant only for specific ASICs */ - hdev->asic_funcs->flush_pq_write(hdev, pi, pbd[0]); + hdev->asic_funcs->pqe_write(hdev, pi, &bd); hdev->asic_funcs->ring_doorbell(hdev, q->hw_queue_id, q->pi); } From b421d83a3947369fd5718824aecfaebe1efbf7ed Mon Sep 17 00:00:00 2001 From: Ben Segal Date: Wed, 7 Aug 2019 13:54:54 +0000 Subject: [PATCH 072/157] habanalabs: fix device IRQ unmasking for BE host When unmasking IRQs inside the ASIC, the driver passes an array of all the IRQ to unmask. The ASIC's CPU is working in LE so when running in a BE host, the driver needs to do the proper endianness swapping when preparing this array. In addition, this patch also fixes the endianness of a couple of kernel log debug messages that print values of packets Signed-off-by: Ben Segal Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/goya/goya.c | 33 +++++++++++++++++++++-------- 1 file changed, 24 insertions(+), 9 deletions(-) diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index b39b9c98fe1d..271c5c8f53b4 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -3314,9 +3314,11 @@ static int goya_validate_dma_pkt_no_mmu(struct hl_device *hdev, int rc; dev_dbg(hdev->dev, "DMA packet details:\n"); - dev_dbg(hdev->dev, "source == 0x%llx\n", user_dma_pkt->src_addr); - dev_dbg(hdev->dev, "destination == 0x%llx\n", user_dma_pkt->dst_addr); - dev_dbg(hdev->dev, "size == %u\n", user_dma_pkt->tsize); + dev_dbg(hdev->dev, "source == 0x%llx\n", + le64_to_cpu(user_dma_pkt->src_addr)); + dev_dbg(hdev->dev, "destination == 0x%llx\n", + le64_to_cpu(user_dma_pkt->dst_addr)); + dev_dbg(hdev->dev, "size == %u\n", le32_to_cpu(user_dma_pkt->tsize)); ctl = le32_to_cpu(user_dma_pkt->ctl); user_dir = (ctl & GOYA_PKT_LIN_DMA_CTL_DMA_DIR_MASK) >> @@ -3345,9 +3347,11 @@ static int goya_validate_dma_pkt_mmu(struct hl_device *hdev, struct packet_lin_dma *user_dma_pkt) { dev_dbg(hdev->dev, "DMA packet details:\n"); - dev_dbg(hdev->dev, "source == 0x%llx\n", user_dma_pkt->src_addr); - dev_dbg(hdev->dev, "destination == 0x%llx\n", user_dma_pkt->dst_addr); - dev_dbg(hdev->dev, "size == %u\n", user_dma_pkt->tsize); + dev_dbg(hdev->dev, "source == 0x%llx\n", + le64_to_cpu(user_dma_pkt->src_addr)); + dev_dbg(hdev->dev, "destination == 0x%llx\n", + le64_to_cpu(user_dma_pkt->dst_addr)); + dev_dbg(hdev->dev, "size == %u\n", le32_to_cpu(user_dma_pkt->tsize)); /* * WA for HW-23. @@ -3387,7 +3391,8 @@ static int goya_validate_wreg32(struct hl_device *hdev, dev_dbg(hdev->dev, "WREG32 packet details:\n"); dev_dbg(hdev->dev, "reg_offset == 0x%x\n", reg_offset); - dev_dbg(hdev->dev, "value == 0x%x\n", wreg_pkt->value); + dev_dbg(hdev->dev, "value == 0x%x\n", + le32_to_cpu(wreg_pkt->value)); if (reg_offset != (mmDMA_CH_0_WR_COMP_ADDR_LO & 0x1FFF)) { dev_err(hdev->dev, "WREG32 packet with illegal address 0x%x\n", @@ -4359,6 +4364,8 @@ static int goya_unmask_irq_arr(struct hl_device *hdev, u32 *irq_arr, size_t total_pkt_size; long result; int rc; + int irq_num_entries, irq_arr_index; + __le32 *goya_irq_arr; total_pkt_size = sizeof(struct armcp_unmask_irq_arr_packet) + irq_arr_size; @@ -4376,8 +4383,16 @@ static int goya_unmask_irq_arr(struct hl_device *hdev, u32 *irq_arr, if (!pkt) return -ENOMEM; - pkt->length = cpu_to_le32(irq_arr_size / sizeof(irq_arr[0])); - memcpy(&pkt->irqs, irq_arr, irq_arr_size); + irq_num_entries = irq_arr_size / sizeof(irq_arr[0]); + pkt->length = cpu_to_le32(irq_num_entries); + + /* We must perform any necessary endianness conversation on the irq + * array being passed to the goya hardware + */ + for (irq_arr_index = 0, goya_irq_arr = (__le32 *) &pkt->irqs; + irq_arr_index < irq_num_entries ; irq_arr_index++) + goya_irq_arr[irq_arr_index] = + cpu_to_le32(irq_arr[irq_arr_index]); pkt->armcp_pkt.ctl = cpu_to_le32(ARMCP_PACKET_UNMASK_RAZWI_IRQ_ARRAY << ARMCP_PKT_CTL_OPCODE_SHIFT); From accd2dd72c8f087441d725dd916688171519e4e6 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 9 Aug 2019 10:23:57 +0200 Subject: [PATCH 073/157] PCI/ASPM: Add pcie_aspm_enabled() Add a function checking whether or not PCIe ASPM has been enabled for a given device. It will be used by the NVMe driver to decide how to handle the device during system suspend. Signed-off-by: Rafael J. Wysocki Reviewed-by: Keith Busch Acked-by: Bjorn Helgaas --- drivers/pci/pcie/aspm.c | 20 ++++++++++++++++++++ include/linux/pci.h | 2 ++ 2 files changed, 22 insertions(+) diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index e44af7f4d37f..464f8f92653f 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -1170,6 +1170,26 @@ static int pcie_aspm_get_policy(char *buffer, const struct kernel_param *kp) module_param_call(policy, pcie_aspm_set_policy, pcie_aspm_get_policy, NULL, 0644); +/** + * pcie_aspm_enabled - Check if PCIe ASPM has been enabled for a device. + * @pdev: Target device. + */ +bool pcie_aspm_enabled(struct pci_dev *pdev) +{ + struct pci_dev *bridge = pci_upstream_bridge(pdev); + bool ret; + + if (!bridge) + return false; + + mutex_lock(&aspm_lock); + ret = bridge->link_state ? !!bridge->link_state->aspm_enabled : false; + mutex_unlock(&aspm_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(pcie_aspm_enabled); + #ifdef CONFIG_PCIEASPM_DEBUG static ssize_t link_state_show(struct device *dev, struct device_attribute *attr, diff --git a/include/linux/pci.h b/include/linux/pci.h index 9e700d9f9f28..82e4cd1b7ac3 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1567,8 +1567,10 @@ extern bool pcie_ports_native; #ifdef CONFIG_PCIEASPM bool pcie_aspm_support_enabled(void); +bool pcie_aspm_enabled(struct pci_dev *pdev); #else static inline bool pcie_aspm_support_enabled(void) { return false; } +static inline bool pcie_aspm_enabled(struct pci_dev *pdev) { return false; } #endif #ifdef CONFIG_PCIEAER From 4eaefe8c621c6195c91044396ed8060c179f7aae Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 8 Aug 2019 23:58:38 +0200 Subject: [PATCH 074/157] nvme-pci: Allow PCI bus-level PM to be used if ASPM is disabled One of the modifications made by commit d916b1be94b6 ("nvme-pci: use host managed power state for suspend") was adding a pci_save_state() call to nvme_suspend() so as to instruct the PCI bus type to leave devices handled by the nvme driver in D0 during suspend-to-idle. That was done with the assumption that ASPM would transition the device's PCIe link into a low-power state when the device became inactive. However, if ASPM is disabled for the device, its PCIe link will stay in L0 and in that case commit d916b1be94b6 is likely to cause the energy used by the system while suspended to increase. Namely, if the device in question works in accordance with the PCIe specification, putting it into D3hot causes its PCIe link to go to L1 or L2/L3 Ready, which is lower-power than L0. Since the energy used by the system while suspended depends on the state of its PCIe link (as a general rule, the lower-power the state of the link, the less energy the system will use), putting the device into D3hot during suspend-to-idle should be more energy-efficient that leaving it in D0 with disabled ASPM. For this reason, avoid leaving NVMe devices with disabled ASPM in D0 during suspend-to-idle. Instead, shut them down entirely and let the PCI bus type put them into D3. Fixes: d916b1be94b6 ("nvme-pci: use host managed power state for suspend") Link: https://lore.kernel.org/linux-pm/2763495.NmdaWeg79L@kreacher/T/#t Signed-off-by: Rafael J. Wysocki Reviewed-by: Keith Busch --- drivers/nvme/host/pci.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index db160cee42ad..108e109e99f1 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2846,7 +2846,7 @@ static int nvme_resume(struct device *dev) struct nvme_dev *ndev = pci_get_drvdata(to_pci_dev(dev)); struct nvme_ctrl *ctrl = &ndev->ctrl; - if (pm_resume_via_firmware() || !ctrl->npss || + if (ndev->last_ps == U32_MAX || nvme_set_power_state(ctrl, ndev->last_ps) != 0) nvme_reset_ctrl(ctrl); return 0; @@ -2859,6 +2859,8 @@ static int nvme_suspend(struct device *dev) struct nvme_ctrl *ctrl = &ndev->ctrl; int ret = -EBUSY; + ndev->last_ps = U32_MAX; + /* * The platform does not remove power for a kernel managed suspend so * use host managed nvme power settings for lowest idle power if @@ -2866,8 +2868,14 @@ static int nvme_suspend(struct device *dev) * shutdown. But if the firmware is involved after the suspend or the * device does not support any non-default power states, shut down the * device fully. + * + * If ASPM is not enabled for the device, shut down the device and allow + * the PCI bus layer to put it into D3 in order to take the PCIe link + * down, so as to allow the platform to achieve its minimum low-power + * state (which may not be possible if the link is up). */ - if (pm_suspend_via_firmware() || !ctrl->npss) { + if (pm_suspend_via_firmware() || !ctrl->npss || + !pcie_aspm_enabled(pdev)) { nvme_dev_disable(ndev, true); return 0; } @@ -2880,7 +2888,6 @@ static int nvme_suspend(struct device *dev) ctrl->state != NVME_CTRL_ADMIN_ONLY) goto unfreeze; - ndev->last_ps = 0; ret = nvme_get_power_state(ctrl, &ndev->last_ps); if (ret < 0) goto unfreeze; From b61fbc887af7a13a1c90c84c1feaeb4c9780e1e2 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 7 Aug 2019 23:59:03 +0200 Subject: [PATCH 075/157] efi-stub: Fix get_efi_config_table on mixed-mode setups Fix get_efi_config_table using the wrong structs when booting a 64 bit kernel on 32 bit firmware. Fixes: 82d736ac56d7 ("Abstract out support for locating an EFI config table") Signed-off-by: Hans de Goede Acked-By: Matthew Garrett Reviewed-by: Ard Biesheuvel Acked-by: Jarkko Sakkinen Signed-off-by: Ard Biesheuvel --- .../firmware/efi/libstub/efi-stub-helper.c | 38 +++++++++++++------ 1 file changed, 27 insertions(+), 11 deletions(-) diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c index 1db780c0f07b..3caae7f2cf56 100644 --- a/drivers/firmware/efi/libstub/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -927,17 +927,33 @@ efi_status_t efi_exit_boot_services(efi_system_table_t *sys_table_arg, return status; } +#define GET_EFI_CONFIG_TABLE(bits) \ +static void *get_efi_config_table##bits(efi_system_table_t *_sys_table, \ + efi_guid_t guid) \ +{ \ + efi_system_table_##bits##_t *sys_table; \ + efi_config_table_##bits##_t *tables; \ + int i; \ + \ + sys_table = (typeof(sys_table))_sys_table; \ + tables = (typeof(tables))(unsigned long)sys_table->tables; \ + \ + for (i = 0; i < sys_table->nr_tables; i++) { \ + if (efi_guidcmp(tables[i].guid, guid) != 0) \ + continue; \ + \ + return (void *)(unsigned long)tables[i].table; \ + } \ + \ + return NULL; \ +} +GET_EFI_CONFIG_TABLE(32) +GET_EFI_CONFIG_TABLE(64) + void *get_efi_config_table(efi_system_table_t *sys_table, efi_guid_t guid) { - efi_config_table_t *tables = (efi_config_table_t *)sys_table->tables; - int i; - - for (i = 0; i < sys_table->nr_tables; i++) { - if (efi_guidcmp(tables[i].guid, guid) != 0) - continue; - - return (void *)tables[i].table; - } - - return NULL; + if (efi_is_64bit()) + return get_efi_config_table64(sys_table, guid); + else + return get_efi_config_table32(sys_table, guid); } From e7409258845a0f64967f8377e99294d438137537 Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Fri, 9 Aug 2019 18:40:37 -0700 Subject: [PATCH 076/157] x86/umwait: Fix error handling in umwait_init() Currently, failure of cpuhp_setup_state() is ignored and the syscore ops and the control interfaces can still be added even after the failure. But, this error handling will cause a few issues: 1. The CPUs may have different values in the IA32_UMWAIT_CONTROL MSR because there is no way to roll back the control MSR on the CPUs which already set the MSR before the failure. 2. If the sysfs interface is added successfully, there will be a mismatch between the global control value and the control MSR: - The interface shows the default global control value. But, the control MSR is not set to the value because the CPU online function, which is supposed to set the MSR to the value, is not installed. - If the sysadmin changes the global control value through the interface, the control MSR on all current online CPUs is set to the new value. But, the control MSR on newly onlined CPUs after the value change will not be set to the new value due to lack of the CPU online function. 3. On resume from suspend/hibernation, the boot CPU restores the control MSR to the global control value through the syscore ops. But, the control MSR on all APs is not set due to lake of the CPU online function. To solve the issues and enforce consistent behavior on the failure of the CPU hotplug setup, make the following changes: 1. Cache the original control MSR value which is configured by hardware or BIOS before kernel boot. This value is likely to be 0. But it could be a different number as well. Cache the control MSR only once before the MSR is changed. 2. Add the CPU offline function so that the MSR is restored to the original control value on all CPUs on the failure. 3. On the failure, exit from cpumait_init() so that the syscore ops and the control interfaces are not added. Reported-by: Valdis Kletnieks Suggested-by: Thomas Gleixner Signed-off-by: Fenghua Yu Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/1565401237-60936-1-git-send-email-fenghua.yu@intel.com --- arch/x86/kernel/cpu/umwait.c | 39 +++++++++++++++++++++++++++++++++++- 1 file changed, 38 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/umwait.c b/arch/x86/kernel/cpu/umwait.c index 6a204e7336c1..32b4dc9030aa 100644 --- a/arch/x86/kernel/cpu/umwait.c +++ b/arch/x86/kernel/cpu/umwait.c @@ -17,6 +17,12 @@ */ static u32 umwait_control_cached = UMWAIT_CTRL_VAL(100000, UMWAIT_C02_ENABLE); +/* + * Cache the original IA32_UMWAIT_CONTROL MSR value which is configured by + * hardware or BIOS before kernel boot. + */ +static u32 orig_umwait_control_cached __ro_after_init; + /* * Serialize access to umwait_control_cached and IA32_UMWAIT_CONTROL MSR in * the sysfs write functions. @@ -52,6 +58,23 @@ static int umwait_cpu_online(unsigned int cpu) return 0; } +/* + * The CPU hotplug callback sets the control MSR to the original control + * value. + */ +static int umwait_cpu_offline(unsigned int cpu) +{ + /* + * This code is protected by the CPU hotplug already and + * orig_umwait_control_cached is never changed after it caches + * the original control MSR value in umwait_init(). So there + * is no race condition here. + */ + wrmsr(MSR_IA32_UMWAIT_CONTROL, orig_umwait_control_cached, 0); + + return 0; +} + /* * On resume, restore IA32_UMWAIT_CONTROL MSR on the boot processor which * is the only active CPU at this time. The MSR is set up on the APs via the @@ -185,8 +208,22 @@ static int __init umwait_init(void) if (!boot_cpu_has(X86_FEATURE_WAITPKG)) return -ENODEV; + /* + * Cache the original control MSR value before the control MSR is + * changed. This is the only place where orig_umwait_control_cached + * is modified. + */ + rdmsrl(MSR_IA32_UMWAIT_CONTROL, orig_umwait_control_cached); + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "umwait:online", - umwait_cpu_online, NULL); + umwait_cpu_online, umwait_cpu_offline); + if (ret < 0) { + /* + * On failure, the control MSR on all CPUs has the + * original control value. + */ + return ret; + } register_syscore_ops(&umwait_syscore_ops); From e26cc08265dda37d2acc8394604f220ef412299d Mon Sep 17 00:00:00 2001 From: zhengbin Date: Mon, 12 Aug 2019 20:36:55 +0800 Subject: [PATCH 077/157] blk-mq: move cancel of requeue_work to the front of blk_exit_queue blk_exit_queue will free elevator_data, while blk_mq_requeue_work will access it. Move cancel of requeue_work to the front of blk_exit_queue to avoid use-after-free. blk_exit_queue blk_mq_requeue_work __elevator_exit blk_mq_run_hw_queues blk_mq_exit_sched blk_mq_run_hw_queue dd_exit_queue blk_mq_hctx_has_pending kfree(elevator_data) blk_mq_sched_has_work dd_has_work Fixes: fbc2a15e3433 ("blk-mq: move cancel of requeue_work into blk_mq_release") Cc: stable@vger.kernel.org Reviewed-by: Ming Lei Signed-off-by: zhengbin Signed-off-by: Jens Axboe --- block/blk-mq.c | 2 -- block/blk-sysfs.c | 3 +++ 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index f78d3287dd82..a8e6a58f5f28 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2666,8 +2666,6 @@ void blk_mq_release(struct request_queue *q) struct blk_mq_hw_ctx *hctx, *next; int i; - cancel_delayed_work_sync(&q->requeue_work); - queue_for_each_hw_ctx(q, hctx, i) WARN_ON_ONCE(hctx && list_empty(&hctx->hctx_list)); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 977c659dcd18..9bfa3ea4ed63 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -892,6 +892,9 @@ static void __blk_release_queue(struct work_struct *work) blk_free_queue_stats(q->stats); + if (queue_is_mq(q)) + cancel_delayed_work_sync(&q->requeue_work); + blk_exit_queue(q); blk_queue_free_zone_bitmaps(q); From ae78ca3cf3d9e9f914bfcd0bc5c389ff18b9c2e0 Mon Sep 17 00:00:00 2001 From: Wenwen Wang Date: Sun, 11 Aug 2019 12:23:22 -0500 Subject: [PATCH 078/157] xen/blkback: fix memory leaks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In read_per_ring_refs(), after 'req' and related memory regions are allocated, xen_blkif_map() is invoked to map the shared frame, irq, and etc. However, if this mapping process fails, no cleanup is performed, leading to memory leaks. To fix this issue, invoke the cleanup before returning the error. Acked-by: Roger Pau Monné Reviewed-by: Boris Ostrovsky Signed-off-by: Wenwen Wang Signed-off-by: Jens Axboe --- drivers/block/xen-blkback/xenbus.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index 3ac6a5d18071..b90dbcd99c03 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -965,6 +965,7 @@ static int read_per_ring_refs(struct xen_blkif_ring *ring, const char *dir) } } + err = -ENOMEM; for (i = 0; i < nr_grefs * XEN_BLKIF_REQS_PER_PAGE; i++) { req = kzalloc(sizeof(*req), GFP_KERNEL); if (!req) @@ -987,7 +988,7 @@ static int read_per_ring_refs(struct xen_blkif_ring *ring, const char *dir) err = xen_blkif_map(ring, ring_ref, nr_grefs, evtchn); if (err) { xenbus_dev_fatal(dev, err, "mapping ring-ref port %u", evtchn); - return err; + goto fail; } return 0; @@ -1007,8 +1008,7 @@ static int read_per_ring_refs(struct xen_blkif_ring *ring, const char *dir) } kfree(req); } - return -ENOMEM; - + return err; } static int connect_ring(struct backend_info *be) From b4d98bc3fc93ec3a58459948a2c0e0c9b501cd88 Mon Sep 17 00:00:00 2001 From: Ian Abbott Date: Mon, 12 Aug 2019 12:15:17 +0100 Subject: [PATCH 079/157] staging: comedi: dt3000: Fix signed integer overflow 'divider * base' In `dt3k_ns_to_timer()` the following lines near the end of the function result in a signed integer overflow: prescale = 15; base = timer_base * (1 << prescale); divider = 65535; *nanosec = divider * base; (`divider`, `base` and `prescale` are type `int`, `timer_base` and `*nanosec` are type `unsigned int`. The value of `timer_base` will be either 50 or 100.) The main reason for the overflow is that the calculation for `base` is completely wrong. It should be: base = timer_base * (prescale + 1); which matches an earlier instance of this calculation in the same function. Reported-by: David Binderman Cc: Signed-off-by: Ian Abbott Link: https://lore.kernel.org/r/20190812111517.26803-1-abbotti@mev.co.uk Signed-off-by: Greg Kroah-Hartman --- drivers/staging/comedi/drivers/dt3000.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/staging/comedi/drivers/dt3000.c b/drivers/staging/comedi/drivers/dt3000.c index 2edf3ee91300..4ad176fc14ad 100644 --- a/drivers/staging/comedi/drivers/dt3000.c +++ b/drivers/staging/comedi/drivers/dt3000.c @@ -368,7 +368,7 @@ static int dt3k_ns_to_timer(unsigned int timer_base, unsigned int *nanosec, } prescale = 15; - base = timer_base * (1 << prescale); + base = timer_base * (prescale + 1); divider = 65535; *nanosec = divider * base; return (prescale << 16) | (divider); From 8e2a589a3fc36ce858d42e767c3bcd8fc62a512b Mon Sep 17 00:00:00 2001 From: Ian Abbott Date: Mon, 12 Aug 2019 13:08:14 +0100 Subject: [PATCH 080/157] staging: comedi: dt3000: Fix rounding up of timer divisor `dt3k_ns_to_timer()` determines the prescaler and divisor to use to produce a desired timing period. It is influenced by a rounding mode and can round the divisor up, down, or to the nearest value. However, the code for rounding up currently does the same as rounding down! Fix ir by using the `DIV_ROUND_UP()` macro to calculate the divisor when rounding up. Also, change the types of the `divider`, `base` and `prescale` variables from `int` to `unsigned int` to avoid mixing signed and unsigned types in the calculations. Also fix a typo in a nearby comment: "improvment" => "improvement". Signed-off-by: Ian Abbott Cc: stable Link: https://lore.kernel.org/r/20190812120814.21188-1-abbotti@mev.co.uk Signed-off-by: Greg Kroah-Hartman --- drivers/staging/comedi/drivers/dt3000.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/staging/comedi/drivers/dt3000.c b/drivers/staging/comedi/drivers/dt3000.c index 4ad176fc14ad..caf4d4df4bd3 100644 --- a/drivers/staging/comedi/drivers/dt3000.c +++ b/drivers/staging/comedi/drivers/dt3000.c @@ -342,9 +342,9 @@ static irqreturn_t dt3k_interrupt(int irq, void *d) static int dt3k_ns_to_timer(unsigned int timer_base, unsigned int *nanosec, unsigned int flags) { - int divider, base, prescale; + unsigned int divider, base, prescale; - /* This function needs improvment */ + /* This function needs improvement */ /* Don't know if divider==0 works. */ for (prescale = 0; prescale < 16; prescale++) { @@ -358,7 +358,7 @@ static int dt3k_ns_to_timer(unsigned int timer_base, unsigned int *nanosec, divider = (*nanosec) / base; break; case CMDF_ROUND_UP: - divider = (*nanosec) / base; + divider = DIV_ROUND_UP(*nanosec, base); break; } if (divider < 65536) { From e9eec6a55c95fb918036bfe29c26a535dca1ad49 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 8 Aug 2019 11:15:38 +0300 Subject: [PATCH 081/157] IB/mlx5: Fix use-after-free error while accessing ev_file pointer Call to uverbs_close_fd() releases file pointer to 'ev_file' and mlx5_ib_dev is going to be inaccessible. Cache pointer prior cleaning resources to solve the KASAN warning below. BUG: KASAN: use-after-free in devx_async_event_close+0x391/0x480 [mlx5_ib] Read of size 8 at addr ffff888301e3cec0 by task devx_direct_tes/4631 CPU: 1 PID: 4631 Comm: devx_direct_tes Tainted: G OE 5.3.0-rc1-for-upstream-dbg-2019-07-26_01-19-56-93 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu2 04/01/2014 Call Trace: dump_stack+0x9a/0xeb print_address_description+0x1e2/0x400 ? devx_async_event_close+0x391/0x480 [mlx5_ib] __kasan_report+0x15c/0x1df ? devx_async_event_close+0x391/0x480 [mlx5_ib] kasan_report+0xe/0x20 devx_async_event_close+0x391/0x480 [mlx5_ib] __fput+0x26a/0x7b0 task_work_run+0x10d/0x180 exit_to_usermode_loop+0x137/0x160 do_syscall_64+0x3c7/0x490 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7f5df907d664 Code: 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 80 00 00 00 00 8b 05 6a cd 20 00 48 63 ff 85 c0 75 13 b8 03 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 44 f3 c3 66 90 48 83 ec 18 48 89 7c 24 08 e8 RSP: 002b:00007ffd353cb958 EFLAGS: 00000246 ORIG_RAX: 0000000000000003 RAX: 0000000000000000 RBX: 000056017a88c348 RCX: 00007f5df907d664 RDX: 00007f5df969d400 RSI: 00007f5de8f1ec90 RDI: 0000000000000006 RBP: 00007f5df9681dc0 R08: 00007f5de8736410 R09: 000056017a9d2dd0 R10: 000000000000000b R11: 0000000000000246 R12: 00007f5de899d7d0 R13: 00007f5df96c4248 R14: 00007f5de8f1ecb0 R15: 000056017ae41308 Allocated by task 4631: save_stack+0x19/0x80 kasan_kmalloc.constprop.3+0xa0/0xd0 alloc_uobj+0x71/0x230 [ib_uverbs] alloc_begin_fd_uobject+0x2e/0xc0 [ib_uverbs] rdma_alloc_begin_uobject+0x96/0x140 [ib_uverbs] ib_uverbs_run_method+0xdf0/0x1940 [ib_uverbs] ib_uverbs_cmd_verbs+0x57e/0xdb0 [ib_uverbs] ib_uverbs_ioctl+0x177/0x260 [ib_uverbs] do_vfs_ioctl+0x18f/0x1010 ksys_ioctl+0x70/0x80 __x64_sys_ioctl+0x6f/0xb0 do_syscall_64+0x95/0x490 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 4631: save_stack+0x19/0x80 __kasan_slab_free+0x11d/0x160 slab_free_freelist_hook+0x67/0x1a0 kfree+0xb9/0x2a0 uverbs_close_fd+0x118/0x1c0 [ib_uverbs] devx_async_event_close+0x28a/0x480 [mlx5_ib] __fput+0x26a/0x7b0 task_work_run+0x10d/0x180 exit_to_usermode_loop+0x137/0x160 do_syscall_64+0x3c7/0x490 entry_SYSCALL_64_after_hwframe+0x49/0xbe The buggy address belongs to the object at ffff888301e3cda8 which belongs to the cache kmalloc-512 of size 512 The buggy address is located 280 bytes inside of 512-byte region [ffff888301e3cda8, ffff888301e3cfa8) The buggy address belongs to the page: page:ffffea000c078e00 refcount:1 mapcount:0 mapping:ffff888352811300 index:0x0 compound_mapcount: 0 flags: 0x2fffff80010200(slab|head) raw: 002fffff80010200 ffffea000d152608 ffffea000c077808 ffff888352811300 raw: 0000000000000000 0000000000250025 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888301e3cd80: fc fc fc fc fc fb fb fb fb fb fb fb fb fb fb fb ffff888301e3ce00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888301e3ce80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888301e3cf00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888301e3cf80: fb fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc Disabling lock debugging due to kernel taint Cc: # 5.2 Fixes: 759738537142 ("IB/mlx5: Enable subscription for device events over DEVX") Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20190808081538.28772-1-leon@kernel.org Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/devx.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index 2d1b3d9609d9..af5bbb35c058 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -2644,12 +2644,13 @@ static int devx_async_event_close(struct inode *inode, struct file *filp) struct devx_async_event_file *ev_file = filp->private_data; struct devx_event_subscription *event_sub, *event_sub_tmp; struct devx_async_event_data *entry, *tmp; + struct mlx5_ib_dev *dev = ev_file->dev; - mutex_lock(&ev_file->dev->devx_event_table.event_xa_lock); + mutex_lock(&dev->devx_event_table.event_xa_lock); /* delete the subscriptions which are related to this FD */ list_for_each_entry_safe(event_sub, event_sub_tmp, &ev_file->subscribed_events_list, file_list) { - devx_cleanup_subscription(ev_file->dev, event_sub); + devx_cleanup_subscription(dev, event_sub); if (event_sub->eventfd) eventfd_ctx_put(event_sub->eventfd); @@ -2658,7 +2659,7 @@ static int devx_async_event_close(struct inode *inode, struct file *filp) kfree_rcu(event_sub, rcu); } - mutex_unlock(&ev_file->dev->devx_event_table.event_xa_lock); + mutex_unlock(&dev->devx_event_table.event_xa_lock); /* free the pending events allocation */ if (!ev_file->omit_data) { @@ -2670,7 +2671,7 @@ static int devx_async_event_close(struct inode *inode, struct file *filp) } uverbs_close_fd(filp); - put_device(&ev_file->dev->ib_dev.dev); + put_device(&dev->ib_dev.dev); return 0; } From 17c19287ecf54fb55f155902dcd39c62a9547c4e Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 9 Aug 2019 17:09:04 +0300 Subject: [PATCH 082/157] RDMA/siw: Fix a memory leak in siw_init_cpulist() The error handling code doesn't free siw_cpu_info.tx_valid_cpus[0]. The first iteration through the loop is a no-op so this is sort of an off by one bug. Also Bernard pointed out that we can remove the NULL assignment and simplify the code a bit. Fixes: bdcf26bf9b3a ("rdma/siw: network and RDMA core interface") Signed-off-by: Dan Carpenter Reviewed-by: Bernard Metzler Reviewed-by: Bernard Metzler Link: https://lore.kernel.org/r/20190809140904.GB3552@mwanda Signed-off-by: Doug Ledford --- drivers/infiniband/sw/siw/siw_main.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/infiniband/sw/siw/siw_main.c b/drivers/infiniband/sw/siw/siw_main.c index d0f140daf659..05a92f997f60 100644 --- a/drivers/infiniband/sw/siw/siw_main.c +++ b/drivers/infiniband/sw/siw/siw_main.c @@ -160,10 +160,8 @@ static int siw_init_cpulist(void) out_err: siw_cpu_info.num_nodes = 0; - while (i) { + while (--i >= 0) kfree(siw_cpu_info.tx_valid_cpus[i]); - siw_cpu_info.tx_valid_cpus[i--] = NULL; - } kfree(siw_cpu_info.tx_valid_cpus); siw_cpu_info.tx_valid_cpus = NULL; From 932727c55653c1d7838d0ecd0cdce4393be156e0 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 9 Aug 2019 13:13:19 +0300 Subject: [PATCH 083/157] RDMA/core: Fix error code in stat_get_doit_qp() We need to set the error codes on these paths. Currently the only possible error code is -EMSGSIZE so that's what the patch uses. Fixes: 83c2c1fcbd08 ("RDMA/nldev: Allow get counter mode through RDMA netlink") Signed-off-by: Dan Carpenter Reviewed-by: Leon Romanovsky Link: https://lore.kernel.org/r/20190809101311.GA17867@mwanda Signed-off-by: Doug Ledford --- drivers/infiniband/core/nldev.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c index 783e465e7c41..87d40d1ecdde 100644 --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -1952,12 +1952,16 @@ static int stat_get_doit_qp(struct sk_buff *skb, struct nlmsghdr *nlh, if (fill_nldev_handle(msg, device) || nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port) || - nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_MODE, mode)) + nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_MODE, mode)) { + ret = -EMSGSIZE; goto err_msg; + } if ((mode == RDMA_COUNTER_MODE_AUTO) && - nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_AUTO_MODE_MASK, mask)) + nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_AUTO_MODE_MASK, mask)) { + ret = -EMSGSIZE; goto err_msg; + } nlmsg_end(msg, nlh); ib_device_put(device); From 858b44dc62a1018312fd9cbd15db24237a897e0e Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Sun, 11 Aug 2019 15:52:26 -0700 Subject: [PATCH 084/157] xfs: remove more ondisk directory corruption asserts Continue our game of replacing ASSERTs for corrupt ondisk metadata with EFSCORRUPTED returns. Signed-off-by: Darrick J. Wong Reviewed-by: Bill O'Donnell --- fs/xfs/libxfs/xfs_da_btree.c | 19 ++++++++++++------- fs/xfs/libxfs/xfs_dir2_node.c | 3 ++- 2 files changed, 14 insertions(+), 8 deletions(-) diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c index d1c77fd0815d..0bf56e94bfe9 100644 --- a/fs/xfs/libxfs/xfs_da_btree.c +++ b/fs/xfs/libxfs/xfs_da_btree.c @@ -487,10 +487,8 @@ xfs_da3_split( ASSERT(state->path.active == 0); oldblk = &state->path.blk[0]; error = xfs_da3_root_split(state, oldblk, addblk); - if (error) { - addblk->bp = NULL; - return error; /* GROT: dir is inconsistent */ - } + if (error) + goto out; /* * Update pointers to the node which used to be block 0 and just got @@ -505,7 +503,10 @@ xfs_da3_split( */ node = oldblk->bp->b_addr; if (node->hdr.info.forw) { - ASSERT(be32_to_cpu(node->hdr.info.forw) == addblk->blkno); + if (be32_to_cpu(node->hdr.info.forw) != addblk->blkno) { + error = -EFSCORRUPTED; + goto out; + } node = addblk->bp->b_addr; node->hdr.info.back = cpu_to_be32(oldblk->blkno); xfs_trans_log_buf(state->args->trans, addblk->bp, @@ -514,15 +515,19 @@ xfs_da3_split( } node = oldblk->bp->b_addr; if (node->hdr.info.back) { - ASSERT(be32_to_cpu(node->hdr.info.back) == addblk->blkno); + if (be32_to_cpu(node->hdr.info.back) != addblk->blkno) { + error = -EFSCORRUPTED; + goto out; + } node = addblk->bp->b_addr; node->hdr.info.forw = cpu_to_be32(oldblk->blkno); xfs_trans_log_buf(state->args->trans, addblk->bp, XFS_DA_LOGRANGE(node, &node->hdr.info, sizeof(node->hdr.info))); } +out: addblk->bp = NULL; - return 0; + return error; } /* diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c index afcc6642690a..1fc44efc344d 100644 --- a/fs/xfs/libxfs/xfs_dir2_node.c +++ b/fs/xfs/libxfs/xfs_dir2_node.c @@ -741,7 +741,8 @@ xfs_dir2_leafn_lookup_for_entry( ents = dp->d_ops->leaf_ents_p(leaf); xfs_dir3_leaf_check(dp, bp); - ASSERT(leafhdr.count > 0); + if (leafhdr.count <= 0) + return -EFSCORRUPTED; /* * Look up the hash value in the leaf entries. From 8612de3f7ba6e900465e340516b8313806d27b2d Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Sun, 11 Aug 2019 15:52:27 -0700 Subject: [PATCH 085/157] xfs: don't crash on null attr fork xfs_bmapi_read Zorro Lang reported a crash in generic/475 if we try to inactivate a corrupt inode with a NULL attr fork (stack trace shortened somewhat): RIP: 0010:xfs_bmapi_read+0x311/0xb00 [xfs] RSP: 0018:ffff888047f9ed68 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: ffff888047f9f038 RCX: 1ffffffff5f99f51 RDX: 0000000000000002 RSI: 0000000000000008 RDI: 0000000000000012 RBP: ffff888002a41f00 R08: ffffed10005483f0 R09: ffffed10005483ef R10: ffffed10005483ef R11: ffff888002a41f7f R12: 0000000000000004 R13: ffffe8fff53b5768 R14: 0000000000000005 R15: 0000000000000001 FS: 00007f11d44b5b80(0000) GS:ffff888114200000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000ef6000 CR3: 000000002e176003 CR4: 00000000001606e0 Call Trace: xfs_dabuf_map.constprop.18+0x696/0xe50 [xfs] xfs_da_read_buf+0xf5/0x2c0 [xfs] xfs_da3_node_read+0x1d/0x230 [xfs] xfs_attr_inactive+0x3cc/0x5e0 [xfs] xfs_inactive+0x4c8/0x5b0 [xfs] xfs_fs_destroy_inode+0x31b/0x8e0 [xfs] destroy_inode+0xbc/0x190 xfs_bulkstat_one_int+0xa8c/0x1200 [xfs] xfs_bulkstat_one+0x16/0x20 [xfs] xfs_bulkstat+0x6fa/0xf20 [xfs] xfs_ioc_bulkstat+0x182/0x2b0 [xfs] xfs_file_ioctl+0xee0/0x12a0 [xfs] do_vfs_ioctl+0x193/0x1000 ksys_ioctl+0x60/0x90 __x64_sys_ioctl+0x6f/0xb0 do_syscall_64+0x9f/0x4d0 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7f11d39a3e5b The "obvious" cause is that the attr ifork is null despite the inode claiming an attr fork having at least one extent, but it's not so obvious why we ended up with an inode in that state. Reported-by: Zorro Lang Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=204031 Signed-off-by: Darrick J. Wong Reviewed-by: Bill O'Donnell --- fs/xfs/libxfs/xfs_bmap.c | 29 +++++++++++++++++++++-------- 1 file changed, 21 insertions(+), 8 deletions(-) diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index baf0b72c0a37..07aad70f3931 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -3835,15 +3835,28 @@ xfs_bmapi_read( XFS_STATS_INC(mp, xs_blk_mapr); ifp = XFS_IFORK_PTR(ip, whichfork); + if (!ifp) { + /* No CoW fork? Return a hole. */ + if (whichfork == XFS_COW_FORK) { + mval->br_startoff = bno; + mval->br_startblock = HOLESTARTBLOCK; + mval->br_blockcount = len; + mval->br_state = XFS_EXT_NORM; + *nmap = 1; + return 0; + } - /* No CoW fork? Return a hole. */ - if (whichfork == XFS_COW_FORK && !ifp) { - mval->br_startoff = bno; - mval->br_startblock = HOLESTARTBLOCK; - mval->br_blockcount = len; - mval->br_state = XFS_EXT_NORM; - *nmap = 1; - return 0; + /* + * A missing attr ifork implies that the inode says we're in + * extents or btree format but failed to pass the inode fork + * verifier while trying to load it. Treat that as a file + * corruption too. + */ +#ifdef DEBUG + xfs_alert(mp, "%s: inode %llu missing fork %d", + __func__, ip->i_ino, whichfork); +#endif /* DEBUG */ + return -EFSCORRUPTED; } if (!(ifp->if_flags & XFS_IFEXTENTS)) { From 5785675dfef4f9edcee66edef7b3af21618d2707 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Sun, 11 Aug 2019 17:40:36 +0200 Subject: [PATCH 086/157] x86/apic/32: Fix yet another implicit fallthrough warning MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix arch/x86/kernel/apic/probe_32.c: In function ‘default_setup_apic_routing’: arch/x86/kernel/apic/probe_32.c:146:7: warning: this statement may fall through [-Wimplicit-fallthrough=] if (!APIC_XAPIC(version)) { ^ arch/x86/kernel/apic/probe_32.c:151:3: note: here case X86_VENDOR_HYGON: ^~~~ for 32-bit builds. Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20190811154036.29805-1-bp@alien8.de --- arch/x86/kernel/apic/probe_32.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 1492799b8f43..ee2d91e382f1 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -184,7 +184,8 @@ void __init default_setup_apic_routing(void) def_to_bigsmp = 0; break; } - /* If P4 and above fall through */ + /* P4 and above */ + /* fall through */ case X86_VENDOR_HYGON: case X86_VENDOR_AMD: def_to_bigsmp = 1; From 91be2587e82a0f16348fd8f12a57e4c328baffc7 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 12 Aug 2019 20:16:17 +0200 Subject: [PATCH 087/157] x86/fpu/math-emu: Address fallthrough warnings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit /home/tglx/work/kernel/linus/linux/arch/x86/math-emu/errors.c: In function ‘FPU_printall’: /home/tglx/work/kernel/linus/linux/arch/x86/math-emu/errors.c:187:9: warning: this statement may fall through [-Wimplicit-fallthrough=] tagi = FPU_Special(r); ~~~~~^~~~~~~~~~~~~~~~ /home/tglx/work/kernel/linus/linux/arch/x86/math-emu/errors.c:188:3: note: here case TAG_Valid: ^~~~ /home/tglx/work/kernel/linus/linux/arch/x86/math-emu/fpu_trig.c: In function ‘fyl2xp1’: /home/tglx/work/kernel/linus/linux/arch/x86/math-emu/fpu_trig.c:1353:7: warning: this statement may fall through [-Wimplicit-fallthrough=] if (denormal_operand() < 0) ^ /home/tglx/work/kernel/linus/linux/arch/x86/math-emu/fpu_trig.c:1356:3: note: here case TAG_Zero: Remove the pointless 'break;' after 'continue;' while at it. Signed-off-by: Thomas Gleixner --- arch/x86/math-emu/errors.c | 5 +++-- arch/x86/math-emu/fpu_trig.c | 2 +- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/arch/x86/math-emu/errors.c b/arch/x86/math-emu/errors.c index 6b468517ab71..73dc66d887f3 100644 --- a/arch/x86/math-emu/errors.c +++ b/arch/x86/math-emu/errors.c @@ -178,13 +178,15 @@ void FPU_printall(void) for (i = 0; i < 8; i++) { FPU_REG *r = &st(i); u_char tagi = FPU_gettagi(i); + switch (tagi) { case TAG_Empty: continue; - break; case TAG_Zero: case TAG_Special: + /* Update tagi for the printk below */ tagi = FPU_Special(r); + /* fall through */ case TAG_Valid: printk("st(%d) %c .%04lx %04lx %04lx %04lx e%+-6d ", i, getsign(r) ? '-' : '+', @@ -198,7 +200,6 @@ void FPU_printall(void) printk("Whoops! Error in errors.c: tag%d is %d ", i, tagi); continue; - break; } printk("%s\n", tag_desc[(int)(unsigned)tagi]); } diff --git a/arch/x86/math-emu/fpu_trig.c b/arch/x86/math-emu/fpu_trig.c index 783c509f957a..127ea54122d7 100644 --- a/arch/x86/math-emu/fpu_trig.c +++ b/arch/x86/math-emu/fpu_trig.c @@ -1352,7 +1352,7 @@ static void fyl2xp1(FPU_REG *st0_ptr, u_char st0_tag) case TW_Denormal: if (denormal_operand() < 0) return; - + /* fall through */ case TAG_Zero: case TAG_Valid: setsign(st0_ptr, getsign(st0_ptr) ^ getsign(st1_ptr)); From 303911cfc5b95d33687d9046133ff184cf5043ff Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Mon, 12 Aug 2019 16:11:07 -0400 Subject: [PATCH 088/157] USB: core: Fix races in character device registration and deregistraion The syzbot fuzzer has found two (!) races in the USB character device registration and deregistration routines. This patch fixes the races. The first race results from the fact that usb_deregister_dev() sets usb_minors[intf->minor] to NULL before calling device_destroy() on the class device. This leaves a window during which another thread can allocate the same minor number but will encounter a duplicate name error when it tries to register its own class device. A typical error message in the system log would look like: sysfs: cannot create duplicate filename '/class/usbmisc/ldusb0' The patch fixes this race by destroying the class device first. The second race is in usb_register_dev(). When that routine runs, it first allocates a minor number, then drops minor_rwsem, and then creates the class device. If the device creation fails, the minor number is deallocated and the whole routine returns an error. But during the time while minor_rwsem was dropped, there is a window in which the minor number is allocated and so another thread can successfully open the device file. Typically this results in use-after-free errors or invalid accesses when the other thread closes its open file reference, because the kernel then tries to release resources that were already deallocated when usb_register_dev() failed. The patch fixes this race by keeping minor_rwsem locked throughout the entire routine. Reported-and-tested-by: syzbot+30cf45ebfe0b0c4847a1@syzkaller.appspotmail.com Signed-off-by: Alan Stern CC: Link: https://lore.kernel.org/r/Pine.LNX.4.44L0.1908121607590.1659-100000@iolanthe.rowland.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/file.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/usb/core/file.c b/drivers/usb/core/file.c index 65de6f73b672..558890ada0e5 100644 --- a/drivers/usb/core/file.c +++ b/drivers/usb/core/file.c @@ -193,9 +193,10 @@ int usb_register_dev(struct usb_interface *intf, intf->minor = minor; break; } - up_write(&minor_rwsem); - if (intf->minor < 0) + if (intf->minor < 0) { + up_write(&minor_rwsem); return -EXFULL; + } /* create a usb class device for this usb interface */ snprintf(name, sizeof(name), class_driver->name, minor - minor_base); @@ -203,12 +204,11 @@ int usb_register_dev(struct usb_interface *intf, MKDEV(USB_MAJOR, minor), class_driver, "%s", kbasename(name)); if (IS_ERR(intf->usb_dev)) { - down_write(&minor_rwsem); usb_minors[minor] = NULL; intf->minor = -1; - up_write(&minor_rwsem); retval = PTR_ERR(intf->usb_dev); } + up_write(&minor_rwsem); return retval; } EXPORT_SYMBOL_GPL(usb_register_dev); @@ -234,12 +234,12 @@ void usb_deregister_dev(struct usb_interface *intf, return; dev_dbg(&intf->dev, "removing %d minor\n", intf->minor); + device_destroy(usb_class->class, MKDEV(USB_MAJOR, intf->minor)); down_write(&minor_rwsem); usb_minors[intf->minor] = NULL; up_write(&minor_rwsem); - device_destroy(usb_class->class, MKDEV(USB_MAJOR, intf->minor)); intf->usb_dev = NULL; intf->minor = -1; destroy_usb_class(); From cd8869f4cb257f22b89495ca40f5281e58ba359c Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Mon, 12 Aug 2019 15:01:30 -0700 Subject: [PATCH 089/157] xtensa: add missing isync to the cpu_reset TLB code ITLB entry modifications must be followed by the isync instruction before the new entries are possibly used. cpu_reset lacks one isync between ITLB way 6 initialization and jump to the identity mapping. Add missing isync to xtensa cpu_reset. Cc: stable@vger.kernel.org Signed-off-by: Max Filippov --- arch/xtensa/kernel/setup.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c index 5cb8a62e091c..7c3106093c75 100644 --- a/arch/xtensa/kernel/setup.c +++ b/arch/xtensa/kernel/setup.c @@ -511,6 +511,7 @@ void cpu_reset(void) "add %2, %2, %7\n\t" "addi %0, %0, -1\n\t" "bnez %0, 1b\n\t" + "isync\n\t" /* Jump to identity mapping */ "jx %3\n" "2:\n\t" From 60d437bbff358748fcfc3bce5f08da9a6b3761da Mon Sep 17 00:00:00 2001 From: Nishka Dasgupta Date: Tue, 16 Jul 2019 11:13:30 +0530 Subject: [PATCH 090/157] of: resolver: Add of_node_put() before return and break Each iteration of for_each_child_of_node puts the previous node, but in the case of a return or break from the middle of the loop, there is no put, thus causing a memory leak. Hence add an of_node_put before the return or break in three places. Issue found with Coccinelle. Signed-off-by: Nishka Dasgupta Signed-off-by: Rob Herring --- drivers/of/resolver.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/of/resolver.c b/drivers/of/resolver.c index c1b67dd7cd6e..83c766233181 100644 --- a/drivers/of/resolver.c +++ b/drivers/of/resolver.c @@ -206,16 +206,22 @@ static int adjust_local_phandle_references(struct device_node *local_fixups, for_each_child_of_node(local_fixups, child) { for_each_child_of_node(overlay, overlay_child) - if (!node_name_cmp(child, overlay_child)) + if (!node_name_cmp(child, overlay_child)) { + of_node_put(overlay_child); break; + } - if (!overlay_child) + if (!overlay_child) { + of_node_put(child); return -EINVAL; + } err = adjust_local_phandle_references(child, overlay_child, phandle_delta); - if (err) + if (err) { + of_node_put(child); return err; + } } return 0; From fd295733e702a63c189fea8294c12e04b5e5ecc0 Mon Sep 17 00:00:00 2001 From: Sven Van Asbroeck Date: Thu, 18 Jul 2019 16:14:53 -0400 Subject: [PATCH 091/157] dt-bindings: fec: explicitly mark deprecated properties fec's gpio phy reset properties have been deprecated. Update the dt-bindings documentation to explicitly mark them as such, and provide a short description of the recommended alternative. Signed-off-by: Sven Van Asbroeck Signed-off-by: Rob Herring --- .../devicetree/bindings/net/fsl-fec.txt | 30 +++++++++++-------- 1 file changed, 17 insertions(+), 13 deletions(-) diff --git a/Documentation/devicetree/bindings/net/fsl-fec.txt b/Documentation/devicetree/bindings/net/fsl-fec.txt index 2d41fb96ce0a..5b88fae0307d 100644 --- a/Documentation/devicetree/bindings/net/fsl-fec.txt +++ b/Documentation/devicetree/bindings/net/fsl-fec.txt @@ -7,18 +7,6 @@ Required properties: - phy-mode : See ethernet.txt file in the same directory Optional properties: -- phy-reset-gpios : Should specify the gpio for phy reset -- phy-reset-duration : Reset duration in milliseconds. Should present - only if property "phy-reset-gpios" is available. Missing the property - will have the duration be 1 millisecond. Numbers greater than 1000 are - invalid and 1 millisecond will be used instead. -- phy-reset-active-high : If present then the reset sequence using the GPIO - specified in the "phy-reset-gpios" property is reversed (H=reset state, - L=operation state). -- phy-reset-post-delay : Post reset delay in milliseconds. If present then - a delay of phy-reset-post-delay milliseconds will be observed after the - phy-reset-gpios has been toggled. Can be omitted thus no delay is - observed. Delay is in range of 1ms to 1000ms. Other delays are invalid. - phy-supply : regulator that powers the Ethernet PHY. - phy-handle : phandle to the PHY device connected to this device. - fixed-link : Assume a fixed link. See fixed-link.txt in the same directory. @@ -47,11 +35,27 @@ Optional properties: For imx6sx, "int0" handles all 3 queues and ENET_MII. "pps" is for the pulse per second interrupt associated with 1588 precision time protocol(PTP). - Optional subnodes: - mdio : specifies the mdio bus in the FEC, used as a container for phy nodes according to phy.txt in the same directory +Deprecated optional properties: + To avoid these, create a phy node according to phy.txt in the same + directory, and point the fec's "phy-handle" property to it. Then use + the phy's reset binding, again described by phy.txt. +- phy-reset-gpios : Should specify the gpio for phy reset +- phy-reset-duration : Reset duration in milliseconds. Should present + only if property "phy-reset-gpios" is available. Missing the property + will have the duration be 1 millisecond. Numbers greater than 1000 are + invalid and 1 millisecond will be used instead. +- phy-reset-active-high : If present then the reset sequence using the GPIO + specified in the "phy-reset-gpios" property is reversed (H=reset state, + L=operation state). +- phy-reset-post-delay : Post reset delay in milliseconds. If present then + a delay of phy-reset-post-delay milliseconds will be observed after the + phy-reset-gpios has been toggled. Can be omitted thus no delay is + observed. Delay is in range of 1ms to 1000ms. Other delays are invalid. + Example: ethernet@83fec000 { From 17b6d2d528542bc60ad400add35728b2259b3cc1 Mon Sep 17 00:00:00 2001 From: Pierre-Eric Pelloux-Prayer Date: Tue, 6 Aug 2019 18:27:26 +0200 Subject: [PATCH 092/157] drm/amdgpu: fix gfx9 soft recovery MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The SOC15_REG_OFFSET() macro wasn't used, making the soft recovery fail. v2: use WREG32_SOC15 instead of WREG32 + SOC15_REG_OFFSET Signed-off-by: Pierre-Eric Pelloux-Prayer Reviewed-by: Alex Deucher Reviewed-by: Christian König Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 1cf639a51178..04b8ac4432c7 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -4869,7 +4869,7 @@ static void gfx_v9_0_ring_soft_recovery(struct amdgpu_ring *ring, unsigned vmid) value = REG_SET_FIELD(value, SQ_CMD, MODE, 0x01); value = REG_SET_FIELD(value, SQ_CMD, CHECK_VMID, 1); value = REG_SET_FIELD(value, SQ_CMD, VM_ID, vmid); - WREG32(mmSQ_CMD, value); + WREG32_SOC15(GC, 0, mmSQ_CMD, value); } static void gfx_v9_0_set_gfx_eop_interrupt_state(struct amdgpu_device *adev, From 31ec0dd38085aaeb75ab04211bf3b51ad917c9b4 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 8 Aug 2019 00:29:23 -0500 Subject: [PATCH 093/157] drm/amd/display: use kvmalloc for dc_state (v2) It's large and doesn't need contiguous memory. Fixes allocation failures in some cases. v2: kvfree the memory. Reviewed-by: Andrey Grodzovsky Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index fa20201eef3a..cbc480a33376 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -23,6 +23,7 @@ */ #include +#include #include "dm_services.h" @@ -1171,8 +1172,8 @@ bool dc_post_update_surfaces_to_stream(struct dc *dc) struct dc_state *dc_create_state(struct dc *dc) { - struct dc_state *context = kzalloc(sizeof(struct dc_state), - GFP_KERNEL); + struct dc_state *context = kvzalloc(sizeof(struct dc_state), + GFP_KERNEL); if (!context) return NULL; @@ -1192,11 +1193,11 @@ struct dc_state *dc_create_state(struct dc *dc) struct dc_state *dc_copy_state(struct dc_state *src_ctx) { int i, j; - struct dc_state *new_ctx = kmemdup(src_ctx, - sizeof(struct dc_state), GFP_KERNEL); + struct dc_state *new_ctx = kvmalloc(sizeof(struct dc_state), GFP_KERNEL); if (!new_ctx) return NULL; + memcpy(new_ctx, src_ctx, sizeof(struct dc_state)); for (i = 0; i < MAX_PIPES; i++) { struct pipe_ctx *cur_pipe = &new_ctx->res_ctx.pipe_ctx[i]; @@ -1230,7 +1231,7 @@ static void dc_state_free(struct kref *kref) { struct dc_state *context = container_of(kref, struct dc_state, refcount); dc_resource_state_destruct(context); - kfree(context); + kvfree(context); } void dc_release_state(struct dc_state *context) From 5717fe5ab38f9ccb32718bcb03bea68409c9cce4 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Mon, 12 Aug 2019 16:02:25 +0100 Subject: [PATCH 094/157] arm64: cpufeature: Don't treat granule sizes as strict If a CPU doesn't support the page size for which the kernel is configured, then we will complain and refuse to bring it online. For secondary CPUs (and the boot CPU on a system booting with EFI), we will also print an error identifying the mismatch. Consequently, the only time that the cpufeature code can detect a granule size mismatch is for a granule other than the one that is currently being used. Although we would rather such systems didn't exist, we've unfortunately lost that battle and Kevin reports that on his amlogic S922X (odroid-n2 board) we end up warning and taining with defconfig because 16k pages are not supported by all of the CPUs. In such a situation, we don't actually care about the feature mismatch, particularly now that KVM only exposes the sanitised view of the CPU registers (commit 93390c0a1b20 - "arm64: KVM: Hide unsupported AArch64 CPU features from guests"). Treat the granule fields as non-strict and let Kevin run without a tainted kernel. Cc: Marc Zyngier Reported-by: Kevin Hilman Tested-by: Kevin Hilman Acked-by: Mark Rutland Acked-by: Suzuki K Poulose Signed-off-by: Will Deacon [catalin.marinas@arm.com: changelog updated with KVM sanitised regs commit] Signed-off-by: Catalin Marinas --- arch/arm64/kernel/cpufeature.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index d19d14ba9ae4..b1fdc486aed8 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -184,9 +184,17 @@ static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = { }; static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = { - S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI), - S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN16_SHIFT, 4, ID_AA64MMFR0_TGRAN16_NI), + /* + * We already refuse to boot CPUs that don't support our configured + * page size, so we can only detect mismatches for a page size other + * than the one we're currently using. Unfortunately, SoCs like this + * exist in the wild so, even though we don't like it, we'll have to go + * along with it and treat them as non-strict. + */ + S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI), + S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN16_SHIFT, 4, ID_AA64MMFR0_TGRAN16_NI), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_BIGENDEL0_SHIFT, 4, 0), /* Linux shouldn't care about secure memory */ ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_SNSMEM_SHIFT, 4, 0), From 834de5c1aa768eb3d233d6544ea7153826c4b206 Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Wed, 31 Jul 2019 08:46:16 +0000 Subject: [PATCH 095/157] mtd: spi-nor: Fix the disabling of write protection at init spi_nor_spansion_clear_sr_bp() depends on spansion_quad_enable(). While spansion_quad_enable() is selected as default when initializing the flash parameters, the nor->quad_enable() method can be overwritten later on when parsing BFPT. Select the write protection disable mechanism at spi_nor_init() time, when the nor->quad_enable() method is already known. Fixes: 191f5c2ed4b6faba ("mtd: spi-nor: use 16-bit WRR command when QE is set on spansion flashes") Signed-off-by: Tudor Ambarus Reviewed-by: Vignesh Raghavendra Signed-off-by: Richard Weinberger --- drivers/mtd/spi-nor/spi-nor.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index 03cc788511d5..654bdc41fc99 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -3780,8 +3780,6 @@ static int spi_nor_init_params(struct spi_nor *nor, default: /* Kept only for backward compatibility purpose. */ params->quad_enable = spansion_quad_enable; - if (nor->clear_sr_bp) - nor->clear_sr_bp = spi_nor_spansion_clear_sr_bp; break; } @@ -4035,6 +4033,9 @@ static int spi_nor_init(struct spi_nor *nor) int err; if (nor->clear_sr_bp) { + if (nor->quad_enable == spansion_quad_enable) + nor->clear_sr_bp = spi_nor_spansion_clear_sr_bp; + err = nor->clear_sr_bp(nor); if (err) { dev_err(nor->dev, From 9a67b72552f8d019948453e56ca7db8c7e5a94ba Mon Sep 17 00:00:00 2001 From: Denis Efremov Date: Tue, 13 Aug 2019 08:15:07 -0700 Subject: [PATCH 096/157] MAINTAINERS: iomap: Remove fs/iomap.c record Update MAINTAINERS to reflect that fs/iomap.c file was splitted into separate files in fs/iomap/ Cc: Darrick J. Wong Cc: Christoph Hellwig Cc: linux-fsdevel@vger.kernel.org Fixes: cb7181ff4b1c ("iomap: move the main iteration code into a separate file") Signed-off-by: Denis Efremov Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- MAINTAINERS | 1 - 1 file changed, 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 6426db5198f0..5a35c0dd1d35 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8416,7 +8416,6 @@ L: linux-xfs@vger.kernel.org L: linux-fsdevel@vger.kernel.org T: git git://git.kernel.org/pub/scm/fs/xfs/xfs-linux.git S: Supported -F: fs/iomap.c F: fs/iomap/ F: include/linux/iomap.h From 190d03814eb3b49d4f87ff38fef26d36f3568a60 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 13 Aug 2019 17:39:56 +0200 Subject: [PATCH 097/157] ALSA: hda/realtek - Add quirk for HP Envy x360 HP Envy x360 (AMD Ryzen-based model) with 103c:8497 needs the same quirk like HP Spectre x360 for enabling the mute LED over Mic3 pin. BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=204373 Cc: Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index de224cbea7a0..8aaf1d9c55cf 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6987,6 +6987,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x82bf, "HP G3 mini", ALC221_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x82c0, "HP G3 mini premium", ALC221_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x83b9, "HP Spectre x360", ALC269_FIXUP_HP_MUTE_LED_MIC3), + SND_PCI_QUIRK(0x103c, 0x8497, "HP Envy x360", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), From 2c8ccb37b08fe364f02a9914daca474d43151453 Mon Sep 17 00:00:00 2001 From: Bernard Metzler Date: Fri, 9 Aug 2019 17:18:16 +0200 Subject: [PATCH 098/157] RDMA/siw: Change CQ flags from 64->32 bits This patch changes the driver/user shared (mmapped) CQ notification flags field from unsigned 64-bits size to unsigned 32-bits size. This enables building siw on 32-bit architectures. This patch changes the siw-abi, but as siw was only just merged in this merge window cycle, there are no released kernels with the prior abi. We are making no attempt to be binary compatible with siw user space libraries prior to the merge of siw into the upstream kernel, only moving forward with upstream kernels and upstream rdma-core provided siw libraries are we guaranteeing compatibility. Signed-off-by: Bernard Metzler Link: https://lore.kernel.org/r/20190809151816.13018-1-bmt@zurich.ibm.com Signed-off-by: Doug Ledford --- drivers/infiniband/sw/siw/Kconfig | 2 +- drivers/infiniband/sw/siw/siw.h | 2 +- drivers/infiniband/sw/siw/siw_qp.c | 14 ++++++++++---- drivers/infiniband/sw/siw/siw_verbs.c | 16 +++++++++++----- include/uapi/rdma/siw-abi.h | 3 ++- 5 files changed, 25 insertions(+), 12 deletions(-) diff --git a/drivers/infiniband/sw/siw/Kconfig b/drivers/infiniband/sw/siw/Kconfig index dace276aea14..b622fc62f2cd 100644 --- a/drivers/infiniband/sw/siw/Kconfig +++ b/drivers/infiniband/sw/siw/Kconfig @@ -1,6 +1,6 @@ config RDMA_SIW tristate "Software RDMA over TCP/IP (iWARP) driver" - depends on INET && INFINIBAND && LIBCRC32C && 64BIT + depends on INET && INFINIBAND && LIBCRC32C select DMA_VIRT_OPS help This driver implements the iWARP RDMA transport over diff --git a/drivers/infiniband/sw/siw/siw.h b/drivers/infiniband/sw/siw/siw.h index 03fd7b2f595f..77b1aabf6ff3 100644 --- a/drivers/infiniband/sw/siw/siw.h +++ b/drivers/infiniband/sw/siw/siw.h @@ -214,7 +214,7 @@ struct siw_wqe { struct siw_cq { struct ib_cq base_cq; spinlock_t lock; - u64 *notify; + struct siw_cq_ctrl *notify; struct siw_cqe *queue; u32 cq_put; u32 cq_get; diff --git a/drivers/infiniband/sw/siw/siw_qp.c b/drivers/infiniband/sw/siw/siw_qp.c index e27bd5b35b96..0990307c5d2c 100644 --- a/drivers/infiniband/sw/siw/siw_qp.c +++ b/drivers/infiniband/sw/siw/siw_qp.c @@ -1013,18 +1013,24 @@ int siw_activate_tx(struct siw_qp *qp) */ static bool siw_cq_notify_now(struct siw_cq *cq, u32 flags) { - u64 cq_notify; + u32 cq_notify; if (!cq->base_cq.comp_handler) return false; - cq_notify = READ_ONCE(*cq->notify); + /* Read application shared notification state */ + cq_notify = READ_ONCE(cq->notify->flags); if ((cq_notify & SIW_NOTIFY_NEXT_COMPLETION) || ((cq_notify & SIW_NOTIFY_SOLICITED) && (flags & SIW_WQE_SOLICITED))) { - /* dis-arm CQ */ - smp_store_mb(*cq->notify, SIW_NOTIFY_NOT); + /* + * CQ notification is one-shot: Since the + * current CQE causes user notification, + * the CQ gets dis-aremd and must be re-aremd + * by the user for a new notification. + */ + WRITE_ONCE(cq->notify->flags, SIW_NOTIFY_NOT); return true; } diff --git a/drivers/infiniband/sw/siw/siw_verbs.c b/drivers/infiniband/sw/siw/siw_verbs.c index 32dc79d0e898..e7f3a2379d9d 100644 --- a/drivers/infiniband/sw/siw/siw_verbs.c +++ b/drivers/infiniband/sw/siw/siw_verbs.c @@ -1049,7 +1049,7 @@ int siw_create_cq(struct ib_cq *base_cq, const struct ib_cq_init_attr *attr, spin_lock_init(&cq->lock); - cq->notify = &((struct siw_cq_ctrl *)&cq->queue[size])->notify; + cq->notify = (struct siw_cq_ctrl *)&cq->queue[size]; if (udata) { struct siw_uresp_create_cq uresp = {}; @@ -1141,11 +1141,17 @@ int siw_req_notify_cq(struct ib_cq *base_cq, enum ib_cq_notify_flags flags) siw_dbg_cq(cq, "flags: 0x%02x\n", flags); if ((flags & IB_CQ_SOLICITED_MASK) == IB_CQ_SOLICITED) - /* CQ event for next solicited completion */ - smp_store_mb(*cq->notify, SIW_NOTIFY_SOLICITED); + /* + * Enable CQ event for next solicited completion. + * and make it visible to all associated producers. + */ + smp_store_mb(cq->notify->flags, SIW_NOTIFY_SOLICITED); else - /* CQ event for any signalled completion */ - smp_store_mb(*cq->notify, SIW_NOTIFY_ALL); + /* + * Enable CQ event for any signalled completion. + * and make it visible to all associated producers. + */ + smp_store_mb(cq->notify->flags, SIW_NOTIFY_ALL); if (flags & IB_CQ_REPORT_MISSED_EVENTS) return cq->cq_put - cq->cq_get; diff --git a/include/uapi/rdma/siw-abi.h b/include/uapi/rdma/siw-abi.h index 7de68f1dc707..af735f55b291 100644 --- a/include/uapi/rdma/siw-abi.h +++ b/include/uapi/rdma/siw-abi.h @@ -180,6 +180,7 @@ struct siw_cqe { * to control CQ arming. */ struct siw_cq_ctrl { - __aligned_u64 notify; + __u32 flags; + __u32 pad; }; #endif From 2d6c25215ab26bb009de3575faab7b685f138e92 Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Mon, 5 Aug 2019 18:44:27 +0200 Subject: [PATCH 099/157] KEYS: trusted: allow module init if TPM is inactive or deactivated Commit c78719203fc6 ("KEYS: trusted: allow trusted.ko to initialize w/o a TPM") allows the trusted module to be loaded even if a TPM is not found, to avoid module dependency problems. However, trusted module initialization can still fail if the TPM is inactive or deactivated. tpm_get_random() returns an error. This patch removes the call to tpm_get_random() and instead extends the PCR specified by the user with zeros. The security of this alternative is equivalent to the previous one, as either option prevents with a PCR update unsealing and misuse of sealed data by a user space process. Even if a PCR is extended with zeros, instead of random data, it is still computationally infeasible to find a value as input for a new PCR extend operation, to obtain again the PCR value that would allow unsealing. Cc: stable@vger.kernel.org Fixes: 240730437deb ("KEYS: trusted: explicitly use tpm_chip structure...") Signed-off-by: Roberto Sassu Reviewed-by: Tyler Hicks Suggested-by: Mimi Zohar Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen --- security/keys/trusted.c | 13 ------------- 1 file changed, 13 deletions(-) diff --git a/security/keys/trusted.c b/security/keys/trusted.c index 9a94672e7adc..ade699131065 100644 --- a/security/keys/trusted.c +++ b/security/keys/trusted.c @@ -1228,24 +1228,11 @@ static int __init trusted_shash_alloc(void) static int __init init_digests(void) { - u8 digest[TPM_MAX_DIGEST_SIZE]; - int ret; - int i; - - ret = tpm_get_random(chip, digest, TPM_MAX_DIGEST_SIZE); - if (ret < 0) - return ret; - if (ret < TPM_MAX_DIGEST_SIZE) - return -EFAULT; - digests = kcalloc(chip->nr_allocated_banks, sizeof(*digests), GFP_KERNEL); if (!digests) return -ENOMEM; - for (i = 0; i < chip->nr_allocated_banks; i++) - memcpy(digests[i].digest, digest, TPM_MAX_DIGEST_SIZE); - return 0; } From eb93685847a9055283d05951c1b205e737f38533 Mon Sep 17 00:00:00 2001 From: Paul Walmsley Date: Wed, 7 Aug 2019 19:07:34 -0700 Subject: [PATCH 100/157] riscv: fix flush_tlb_range() end address for flush_tlb_page() The RISC-V kernel implementation of flush_tlb_page() when CONFIG_SMP is set is wrong. It passes zero to flush_tlb_range() as the final address to flush, but it should be at least 'addr'. Some other Linux architecture ports use the beginning address to flush, plus PAGE_SIZE, as the final address to flush. This might flush slightly more than what's needed, but it seems unlikely that being more clever would improve anything. So let's just take that implementation for now. While here, convert the macro into a static inline function, primarily to avoid unintentional multiple evaluations of 'addr'. This second version of the patch fixes a coding style issue found by Christoph Hellwig . Reported-by: Andreas Schwab Signed-off-by: Paul Walmsley Reviewed-by: Christoph Hellwig --- arch/riscv/include/asm/tlbflush.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h index 687dd19735a7..4d9bbe8438bf 100644 --- a/arch/riscv/include/asm/tlbflush.h +++ b/arch/riscv/include/asm/tlbflush.h @@ -53,10 +53,17 @@ static inline void remote_sfence_vma(struct cpumask *cmask, unsigned long start, } #define flush_tlb_all() sbi_remote_sfence_vma(NULL, 0, -1) -#define flush_tlb_page(vma, addr) flush_tlb_range(vma, addr, 0) + #define flush_tlb_range(vma, start, end) \ remote_sfence_vma(mm_cpumask((vma)->vm_mm), start, (end) - (start)) -#define flush_tlb_mm(mm) \ + +static inline void flush_tlb_page(struct vm_area_struct *vma, + unsigned long addr) +{ + flush_tlb_range(vma, addr, addr + PAGE_SIZE); +} + +#define flush_tlb_mm(mm) \ remote_sfence_vma(mm_cpumask(mm), 0, -1) #endif /* CONFIG_SMP */ From 76470ccd62f18bfa0954bec10f2329339f793914 Mon Sep 17 00:00:00 2001 From: Ralph Campbell Date: Tue, 13 Aug 2019 15:37:04 -0700 Subject: [PATCH 101/157] mm: document zone device struct page field usage MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "mm/hmm: fixes for device private page migration", v3. Testing the latest linux git tree turned up a few bugs with page migration to and from ZONE_DEVICE private and anonymous pages. Hopefully it clarifies how ZONE_DEVICE private struct page uses the same mapping and index fields from the source anonymous page mapping. This patch (of 3): Struct page for ZONE_DEVICE private pages uses the page->mapping and and page->index fields while the source anonymous pages are migrated to device private memory. This is so rmap_walk() can find the page when migrating the ZONE_DEVICE private page back to system memory. ZONE_DEVICE pmem backed fsdax pages also use the page->mapping and page->index fields when files are mapped into a process address space. Add comments to struct page and remove the unused "_zd_pad_1" field to make this more clear. Link: http://lkml.kernel.org/r/20190724232700.23327-2-rcampbell@nvidia.com Signed-off-by: Ralph Campbell Reviewed-by: John Hubbard Cc: Matthew Wilcox Cc: Vlastimil Babka Cc: Christoph Lameter Cc: Dave Hansen Cc: Jérôme Glisse Cc: "Kirill A . Shutemov" Cc: Lai Jiangshan Cc: Martin Schwidefsky Cc: Pekka Enberg Cc: Randy Dunlap Cc: Andrey Ryabinin Cc: Christoph Hellwig Cc: Jason Gunthorpe Cc: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 3a37a89eb7a7..6a7a1083b6fb 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -159,7 +159,16 @@ struct page { /** @pgmap: Points to the hosting device page map. */ struct dev_pagemap *pgmap; void *zone_device_data; - unsigned long _zd_pad_1; /* uses mapping */ + /* + * ZONE_DEVICE private pages are counted as being + * mapped so the next 3 words hold the mapping, index, + * and private fields from the source anonymous or + * page cache page while the page is migrated to device + * private memory. + * ZONE_DEVICE MEMORY_DEVICE_FS_DAX pages also + * use the mapping, index, and private fields when + * pmem backed DAX files are mapped. + */ }; /** @rcu_head: You can use this to free a page by RCU. */ From 7ab0ad0e74f82db1a7e0810828785e44305cff20 Mon Sep 17 00:00:00 2001 From: Ralph Campbell Date: Tue, 13 Aug 2019 15:37:07 -0700 Subject: [PATCH 102/157] mm/hmm: fix ZONE_DEVICE anon page mapping reuse MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When a ZONE_DEVICE private page is freed, the page->mapping field can be set. If this page is reused as an anonymous page, the previous value can prevent the page from being inserted into the CPU's anon rmap table. For example, when migrating a pte_none() page to device memory: migrate_vma(ops, vma, start, end, src, dst, private) migrate_vma_collect() src[] = MIGRATE_PFN_MIGRATE migrate_vma_prepare() /* no page to lock or isolate so OK */ migrate_vma_unmap() /* no page to unmap so OK */ ops->alloc_and_copy() /* driver allocates ZONE_DEVICE page for dst[] */ migrate_vma_pages() migrate_vma_insert_page() page_add_new_anon_rmap() __page_set_anon_rmap() /* This check sees the page's stale mapping field */ if (PageAnon(page)) return /* page->mapping is not updated */ The result is that the migration appears to succeed but a subsequent CPU fault will be unable to migrate the page back to system memory or worse. Clear the page->mapping field when freeing the ZONE_DEVICE page so stale pointer data doesn't affect future page use. Link: http://lkml.kernel.org/r/20190719192955.30462-3-rcampbell@nvidia.com Fixes: b7a523109fb5c9d2d6dd ("mm: don't clear ->mapping in hmm_devmem_free") Signed-off-by: Ralph Campbell Reviewed-by: John Hubbard Reviewed-by: Christoph Hellwig Cc: Dan Williams Cc: Jason Gunthorpe Cc: Logan Gunthorpe Cc: Ira Weiny Cc: Matthew Wilcox Cc: Mel Gorman Cc: Jan Kara Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Andrea Arcangeli Cc: Mike Kravetz Cc: "Jérôme Glisse" Cc: Andrey Ryabinin Cc: Christoph Lameter Cc: Dave Hansen Cc: Lai Jiangshan Cc: Martin Schwidefsky Cc: Pekka Enberg Cc: Randy Dunlap Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memremap.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/mm/memremap.c b/mm/memremap.c index 86432650f829..ed70c4e8e52a 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -403,6 +403,30 @@ void __put_devmap_managed_page(struct page *page) mem_cgroup_uncharge(page); + /* + * When a device_private page is freed, the page->mapping field + * may still contain a (stale) mapping value. For example, the + * lower bits of page->mapping may still identify the page as + * an anonymous page. Ultimately, this entire field is just + * stale and wrong, and it will cause errors if not cleared. + * One example is: + * + * migrate_vma_pages() + * migrate_vma_insert_page() + * page_add_new_anon_rmap() + * __page_set_anon_rmap() + * ...checks page->mapping, via PageAnon(page) call, + * and incorrectly concludes that the page is an + * anonymous page. Therefore, it incorrectly, + * silently fails to set up the new anon rmap. + * + * For other types of ZONE_DEVICE pages, migration is either + * handled differently or not done at all, so there is no need + * to clear page->mapping. + */ + if (is_device_private_page(page)) + page->mapping = NULL; + page->pgmap->ops->page_free(page); } else if (!count) __put_page(page); From 1de13ee59225dfc98d483f8cce7d83f97c0b31de Mon Sep 17 00:00:00 2001 From: Ralph Campbell Date: Tue, 13 Aug 2019 15:37:11 -0700 Subject: [PATCH 103/157] mm/hmm: fix bad subpage pointer in try_to_unmap_one MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When migrating an anonymous private page to a ZONE_DEVICE private page, the source page->mapping and page->index fields are copied to the destination ZONE_DEVICE struct page and the page_mapcount() is increased. This is so rmap_walk() can be used to unmap and migrate the page back to system memory. However, try_to_unmap_one() computes the subpage pointer from a swap pte which computes an invalid page pointer and a kernel panic results such as: BUG: unable to handle page fault for address: ffffea1fffffffc8 Currently, only single pages can be migrated to device private memory so no subpage computation is needed and it can be set to "page". [rcampbell@nvidia.com: add comment] Link: http://lkml.kernel.org/r/20190724232700.23327-4-rcampbell@nvidia.com Link: http://lkml.kernel.org/r/20190719192955.30462-4-rcampbell@nvidia.com Fixes: a5430dda8a3a1c ("mm/migrate: support un-addressable ZONE_DEVICE page in migration") Signed-off-by: Ralph Campbell Cc: "Jérôme Glisse" Cc: "Kirill A. Shutemov" Cc: Mike Kravetz Cc: Christoph Hellwig Cc: Jason Gunthorpe Cc: John Hubbard Cc: Andrea Arcangeli Cc: Andrey Ryabinin Cc: Christoph Lameter Cc: Dan Williams Cc: Dave Hansen Cc: Ira Weiny Cc: Jan Kara Cc: Lai Jiangshan Cc: Logan Gunthorpe Cc: Martin Schwidefsky Cc: Matthew Wilcox Cc: Mel Gorman Cc: Michal Hocko Cc: Pekka Enberg Cc: Randy Dunlap Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/rmap.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/mm/rmap.c b/mm/rmap.c index e5dfe2ae6b0d..003377e24232 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1475,7 +1475,15 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, /* * No need to invalidate here it will synchronize on * against the special swap migration pte. + * + * The assignment to subpage above was computed from a + * swap PTE which results in an invalid pointer. + * Since only PAGE_SIZE pages can currently be + * migrated, just set it to page. This will need to be + * changed when hugepage migrations to device private + * memory are supported. */ + subpage = page; goto discard; } From d883544515aae54842c21730b880172e7894fde9 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Tue, 13 Aug 2019 15:37:15 -0700 Subject: [PATCH 104/157] mm: mempolicy: make the behavior consistent when MPOL_MF_MOVE* and MPOL_MF_STRICT were specified When both MPOL_MF_MOVE* and MPOL_MF_STRICT was specified, mbind() should try best to migrate misplaced pages, if some of the pages could not be migrated, then return -EIO. There are three different sub-cases: 1. vma is not migratable 2. vma is migratable, but there are unmovable pages 3. vma is migratable, pages are movable, but migrate_pages() fails If #1 happens, kernel would just abort immediately, then return -EIO, after a7f40cfe3b7a ("mm: mempolicy: make mbind() return -EIO when MPOL_MF_STRICT is specified"). If #3 happens, kernel would set policy and migrate pages with best-effort, but won't rollback the migrated pages and reset the policy back. Before that commit, they behaves in the same way. It'd better to keep their behavior consistent. But, rolling back the migrated pages and resetting the policy back sounds not feasible, so just make #1 behave as same as #3. Userspace will know that not everything was successfully migrated (via -EIO), and can take whatever steps it deems necessary - attempt rollback, determine which exact page(s) are violating the policy, etc. Make queue_pages_range() return 1 to indicate there are unmovable pages or vma is not migratable. The #2 is not handled correctly in the current kernel, the following patch will fix it. [yang.shi@linux.alibaba.com: fix review comments from Vlastimil] Link: http://lkml.kernel.org/r/1563556862-54056-2-git-send-email-yang.shi@linux.alibaba.com Link: http://lkml.kernel.org/r/1561162809-59140-2-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Yang Shi Reviewed-by: Vlastimil Babka Cc: Michal Hocko Cc: Mel Gorman Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mempolicy.c | 68 +++++++++++++++++++++++++++++++++++--------------- 1 file changed, 48 insertions(+), 20 deletions(-) diff --git a/mm/mempolicy.c b/mm/mempolicy.c index f48693f75b37..932c26845e3e 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -429,11 +429,14 @@ static inline bool queue_pages_required(struct page *page, } /* - * queue_pages_pmd() has three possible return values: - * 1 - pages are placed on the right node or queued successfully. - * 0 - THP was split. - * -EIO - is migration entry or MPOL_MF_STRICT was specified and an existing - * page was already on a node that does not follow the policy. + * queue_pages_pmd() has four possible return values: + * 0 - pages are placed on the right node or queued successfully. + * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were + * specified. + * 2 - THP was split. + * -EIO - is migration entry or only MPOL_MF_STRICT was specified and an + * existing page was already on a node that does not follow the + * policy. */ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, unsigned long end, struct mm_walk *walk) @@ -451,19 +454,17 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, if (is_huge_zero_page(page)) { spin_unlock(ptl); __split_huge_pmd(walk->vma, pmd, addr, false, NULL); + ret = 2; goto out; } - if (!queue_pages_required(page, qp)) { - ret = 1; + if (!queue_pages_required(page, qp)) goto unlock; - } - ret = 1; flags = qp->flags; /* go to thp migration */ if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { if (!vma_migratable(walk->vma)) { - ret = -EIO; + ret = 1; goto unlock; } @@ -479,6 +480,13 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, /* * Scan through pages checking if pages follow certain conditions, * and move them to the pagelist if they do. + * + * queue_pages_pte_range() has three possible return values: + * 0 - pages are placed on the right node or queued successfully. + * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were + * specified. + * -EIO - only MPOL_MF_STRICT was specified and an existing page was already + * on a node that does not follow the policy. */ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) @@ -488,17 +496,17 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; int ret; + bool has_unmovable = false; pte_t *pte; spinlock_t *ptl; ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { ret = queue_pages_pmd(pmd, ptl, addr, end, walk); - if (ret > 0) - return 0; - else if (ret < 0) + if (ret != 2) return ret; } + /* THP was split, fall through to pte walk */ if (pmd_trans_unstable(pmd)) return 0; @@ -519,14 +527,21 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, if (!queue_pages_required(page, qp)) continue; if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { - if (!vma_migratable(vma)) + /* MPOL_MF_STRICT must be specified if we get here */ + if (!vma_migratable(vma)) { + has_unmovable = true; break; + } migrate_page_add(page, qp->pagelist, flags); } else break; } pte_unmap_unlock(pte - 1, ptl); cond_resched(); + + if (has_unmovable) + return 1; + return addr != end ? -EIO : 0; } @@ -639,7 +654,13 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end, * * If pages found in a given range are on a set of nodes (determined by * @nodes and @flags,) it's isolated and queued to the pagelist which is - * passed via @private.) + * passed via @private. + * + * queue_pages_range() has three possible return values: + * 1 - there is unmovable page, but MPOL_MF_MOVE* & MPOL_MF_STRICT were + * specified. + * 0 - queue pages successfully or no misplaced page. + * -EIO - there is misplaced page and only MPOL_MF_STRICT was specified. */ static int queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, @@ -1182,6 +1203,7 @@ static long do_mbind(unsigned long start, unsigned long len, struct mempolicy *new; unsigned long end; int err; + int ret; LIST_HEAD(pagelist); if (flags & ~(unsigned long)MPOL_MF_VALID) @@ -1243,10 +1265,15 @@ static long do_mbind(unsigned long start, unsigned long len, if (err) goto mpol_out; - err = queue_pages_range(mm, start, end, nmask, + ret = queue_pages_range(mm, start, end, nmask, flags | MPOL_MF_INVERT, &pagelist); - if (!err) - err = mbind_range(mm, start, end, new); + + if (ret < 0) { + err = -EIO; + goto up_out; + } + + err = mbind_range(mm, start, end, new); if (!err) { int nr_failed = 0; @@ -1259,13 +1286,14 @@ static long do_mbind(unsigned long start, unsigned long len, putback_movable_pages(&pagelist); } - if (nr_failed && (flags & MPOL_MF_STRICT)) + if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT))) err = -EIO; } else putback_movable_pages(&pagelist); +up_out: up_write(&mm->mmap_sem); - mpol_out: +mpol_out: mpol_put(new); return err; } From a53190a4aaa36494f4d7209fd1fcc6f2ee08e0e0 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Tue, 13 Aug 2019 15:37:18 -0700 Subject: [PATCH 105/157] mm: mempolicy: handle vma with unmovable pages mapped correctly in mbind When running syzkaller internally, we ran into the below bug on 4.9.x kernel: kernel BUG at mm/huge_memory.c:2124! invalid opcode: 0000 [#1] SMP KASAN CPU: 0 PID: 1518 Comm: syz-executor107 Not tainted 4.9.168+ #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 0.5.1 01/01/2011 task: ffff880067b34900 task.stack: ffff880068998000 RIP: split_huge_page_to_list+0x8fb/0x1030 mm/huge_memory.c:2124 Call Trace: split_huge_page include/linux/huge_mm.h:100 [inline] queue_pages_pte_range+0x7e1/0x1480 mm/mempolicy.c:538 walk_pmd_range mm/pagewalk.c:50 [inline] walk_pud_range mm/pagewalk.c:90 [inline] walk_pgd_range mm/pagewalk.c:116 [inline] __walk_page_range+0x44a/0xdb0 mm/pagewalk.c:208 walk_page_range+0x154/0x370 mm/pagewalk.c:285 queue_pages_range+0x115/0x150 mm/mempolicy.c:694 do_mbind mm/mempolicy.c:1241 [inline] SYSC_mbind+0x3c3/0x1030 mm/mempolicy.c:1370 SyS_mbind+0x46/0x60 mm/mempolicy.c:1352 do_syscall_64+0x1d2/0x600 arch/x86/entry/common.c:282 entry_SYSCALL_64_after_swapgs+0x5d/0xdb Code: c7 80 1c 02 00 e8 26 0a 76 01 <0f> 0b 48 c7 c7 40 46 45 84 e8 4c RIP [] split_huge_page_to_list+0x8fb/0x1030 mm/huge_memory.c:2124 RSP with the below test: uint64_t r[1] = {0xffffffffffffffff}; int main(void) { syscall(__NR_mmap, 0x20000000, 0x1000000, 3, 0x32, -1, 0); intptr_t res = 0; res = syscall(__NR_socket, 0x11, 3, 0x300); if (res != -1) r[0] = res; *(uint32_t*)0x20000040 = 0x10000; *(uint32_t*)0x20000044 = 1; *(uint32_t*)0x20000048 = 0xc520; *(uint32_t*)0x2000004c = 1; syscall(__NR_setsockopt, r[0], 0x107, 0xd, 0x20000040, 0x10); syscall(__NR_mmap, 0x20fed000, 0x10000, 0, 0x8811, r[0], 0); *(uint64_t*)0x20000340 = 2; syscall(__NR_mbind, 0x20ff9000, 0x4000, 0x4002, 0x20000340, 0x45d4, 3); return 0; } Actually the test does: mmap(0x20000000, 16777216, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS, -1, 0) = 0x20000000 socket(AF_PACKET, SOCK_RAW, 768) = 3 setsockopt(3, SOL_PACKET, PACKET_TX_RING, {block_size=65536, block_nr=1, frame_size=50464, frame_nr=1}, 16) = 0 mmap(0x20fed000, 65536, PROT_NONE, MAP_SHARED|MAP_FIXED|MAP_POPULATE|MAP_DENYWRITE, 3, 0) = 0x20fed000 mbind(..., MPOL_MF_STRICT|MPOL_MF_MOVE) = 0 The setsockopt() would allocate compound pages (16 pages in this test) for packet tx ring, then the mmap() would call packet_mmap() to map the pages into the user address space specified by the mmap() call. When calling mbind(), it would scan the vma to queue the pages for migration to the new node. It would split any huge page since 4.9 doesn't support THP migration, however, the packet tx ring compound pages are not THP and even not movable. So, the above bug is triggered. However, the later kernel is not hit by this issue due to commit d44d363f6578 ("mm: don't assume anonymous pages have SwapBacked flag"), which just removes the PageSwapBacked check for a different reason. But, there is a deeper issue. According to the semantic of mbind(), it should return -EIO if MPOL_MF_MOVE or MPOL_MF_MOVE_ALL was specified and MPOL_MF_STRICT was also specified, but the kernel was unable to move all existing pages in the range. The tx ring of the packet socket is definitely not movable, however, mbind() returns success for this case. Although the most socket file associates with non-movable pages, but XDP may have movable pages from gup. So, it sounds not fine to just check the underlying file type of vma in vma_migratable(). Change migrate_page_add() to check if the page is movable or not, if it is unmovable, just return -EIO. But do not abort pte walk immediately, since there may be pages off LRU temporarily. We should migrate other pages if MPOL_MF_MOVE* is specified. Set has_unmovable flag if some paged could not be not moved, then return -EIO for mbind() eventually. With this change the above test would return -EIO as expected. [yang.shi@linux.alibaba.com: fix review comments from Vlastimil] Link: http://lkml.kernel.org/r/1563556862-54056-3-git-send-email-yang.shi@linux.alibaba.com Link: http://lkml.kernel.org/r/1561162809-59140-3-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Yang Shi Reviewed-by: Vlastimil Babka Cc: Michal Hocko Cc: Mel Gorman Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mempolicy.c | 32 +++++++++++++++++++++++++------- 1 file changed, 25 insertions(+), 7 deletions(-) diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 932c26845e3e..547cd403ed02 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -403,7 +403,7 @@ static const struct mempolicy_operations mpol_ops[MPOL_MAX] = { }, }; -static void migrate_page_add(struct page *page, struct list_head *pagelist, +static int migrate_page_add(struct page *page, struct list_head *pagelist, unsigned long flags); struct queue_pages { @@ -463,12 +463,11 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, flags = qp->flags; /* go to thp migration */ if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { - if (!vma_migratable(walk->vma)) { + if (!vma_migratable(walk->vma) || + migrate_page_add(page, qp->pagelist, flags)) { ret = 1; goto unlock; } - - migrate_page_add(page, qp->pagelist, flags); } else ret = -EIO; unlock: @@ -532,7 +531,14 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, has_unmovable = true; break; } - migrate_page_add(page, qp->pagelist, flags); + + /* + * Do not abort immediately since there may be + * temporary off LRU pages in the range. Still + * need migrate other LRU pages. + */ + if (migrate_page_add(page, qp->pagelist, flags)) + has_unmovable = true; } else break; } @@ -961,7 +967,7 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, /* * page migration, thp tail pages can be passed. */ -static void migrate_page_add(struct page *page, struct list_head *pagelist, +static int migrate_page_add(struct page *page, struct list_head *pagelist, unsigned long flags) { struct page *head = compound_head(page); @@ -974,8 +980,19 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist, mod_node_page_state(page_pgdat(head), NR_ISOLATED_ANON + page_is_file_cache(head), hpage_nr_pages(head)); + } else if (flags & MPOL_MF_STRICT) { + /* + * Non-movable page may reach here. And, there may be + * temporary off LRU pages or non-LRU movable pages. + * Treat them as unmovable pages since they can't be + * isolated, so they can't be moved at the moment. It + * should return -EIO for this case too. + */ + return -EIO; } } + + return 0; } /* page allocation callback for NUMA node migration */ @@ -1178,9 +1195,10 @@ static struct page *new_page(struct page *page, unsigned long start) } #else -static void migrate_page_add(struct page *page, struct list_head *pagelist, +static int migrate_page_add(struct page *page, struct list_head *pagelist, unsigned long flags) { + return -EIO; } int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, From 6051d3bd3b91e96c59e62b8be2dba1cc2b19ee40 Mon Sep 17 00:00:00 2001 From: Henry Burns Date: Tue, 13 Aug 2019 15:37:21 -0700 Subject: [PATCH 106/157] mm/z3fold.c: fix z3fold_destroy_pool() ordering The constraint from the zpool use of z3fold_destroy_pool() is there are no outstanding handles to memory (so no active allocations), but it is possible for there to be outstanding work on either of the two wqs in the pool. If there is work queued on pool->compact_workqueue when it is called, z3fold_destroy_pool() will do: z3fold_destroy_pool() destroy_workqueue(pool->release_wq) destroy_workqueue(pool->compact_wq) drain_workqueue(pool->compact_wq) do_compact_page(zhdr) kref_put(&zhdr->refcount) __release_z3fold_page(zhdr, ...) queue_work_on(pool->release_wq, &pool->work) *BOOM* So compact_wq needs to be destroyed before release_wq. Link: http://lkml.kernel.org/r/20190726224810.79660-1-henryburns@google.com Fixes: 5d03a6613957 ("mm/z3fold.c: use kref to prevent page free/compact race") Signed-off-by: Henry Burns Reviewed-by: Shakeel Butt Reviewed-by: Jonathan Adams Cc: Vitaly Vul Cc: Vitaly Wool Cc: David Howells Cc: Thomas Gleixner Cc: Al Viro Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/z3fold.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/mm/z3fold.c b/mm/z3fold.c index 1a029a7432ee..43de92f52961 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -818,8 +818,15 @@ static void z3fold_destroy_pool(struct z3fold_pool *pool) { kmem_cache_destroy(pool->c_handle); z3fold_unregister_migration(pool); - destroy_workqueue(pool->release_wq); + + /* + * We need to destroy pool->compact_wq before pool->release_wq, + * as any pending work on pool->compact_wq will call + * queue_work(pool->release_wq, &pool->work). + */ + destroy_workqueue(pool->compact_wq); + destroy_workqueue(pool->release_wq); kfree(pool); } From b997052bc3ac444a0bceab1093aff7ae71ed419e Mon Sep 17 00:00:00 2001 From: Henry Burns Date: Tue, 13 Aug 2019 15:37:25 -0700 Subject: [PATCH 107/157] mm/z3fold.c: fix z3fold_destroy_pool() race condition The constraint from the zpool use of z3fold_destroy_pool() is there are no outstanding handles to memory (so no active allocations), but it is possible for there to be outstanding work on either of the two wqs in the pool. Calling z3fold_deregister_migration() before the workqueues are drained means that there can be allocated pages referencing a freed inode, causing any thread in compaction to be able to trip over the bad pointer in PageMovable(). Link: http://lkml.kernel.org/r/20190726224810.79660-2-henryburns@google.com Fixes: 1f862989b04a ("mm/z3fold.c: support page migration") Signed-off-by: Henry Burns Reviewed-by: Shakeel Butt Reviewed-by: Jonathan Adams Cc: Vitaly Vul Cc: Vitaly Wool Cc: David Howells Cc: Thomas Gleixner Cc: Al Viro Cc: Henry Burns Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/z3fold.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/mm/z3fold.c b/mm/z3fold.c index 43de92f52961..ed19d98c9dcd 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -817,16 +817,19 @@ static struct z3fold_pool *z3fold_create_pool(const char *name, gfp_t gfp, static void z3fold_destroy_pool(struct z3fold_pool *pool) { kmem_cache_destroy(pool->c_handle); - z3fold_unregister_migration(pool); /* * We need to destroy pool->compact_wq before pool->release_wq, * as any pending work on pool->compact_wq will call * queue_work(pool->release_wq, &pool->work). + * + * There are still outstanding pages until both workqueues are drained, + * so we cannot unregister migration until then. */ destroy_workqueue(pool->compact_wq); destroy_workqueue(pool->release_wq); + z3fold_unregister_migration(pool); kfree(pool); } From 54a83d6bcbf8f4700013766b974bf9190d40b689 Mon Sep 17 00:00:00 2001 From: Miles Chen Date: Tue, 13 Aug 2019 15:37:28 -0700 Subject: [PATCH 108/157] mm/memcontrol.c: fix use after free in mem_cgroup_iter() This patch is sent to report an use after free in mem_cgroup_iter() after merging commit be2657752e9e ("mm: memcg: fix use after free in mem_cgroup_iter()"). I work with android kernel tree (4.9 & 4.14), and commit be2657752e9e ("mm: memcg: fix use after free in mem_cgroup_iter()") has been merged to the trees. However, I can still observe use after free issues addressed in the commit be2657752e9e. (on low-end devices, a few times this month) backtrace: css_tryget <- crash here mem_cgroup_iter shrink_node shrink_zones do_try_to_free_pages try_to_free_pages __perform_reclaim __alloc_pages_direct_reclaim __alloc_pages_slowpath __alloc_pages_nodemask To debug, I poisoned mem_cgroup before freeing it: static void __mem_cgroup_free(struct mem_cgroup *memcg) for_each_node(node) free_mem_cgroup_per_node_info(memcg, node); free_percpu(memcg->stat); + /* poison memcg before freeing it */ + memset(memcg, 0x78, sizeof(struct mem_cgroup)); kfree(memcg); } The coredump shows the position=0xdbbc2a00 is freed. (gdb) p/x ((struct mem_cgroup_per_node *)0xe5009e00)->iter[8] $13 = {position = 0xdbbc2a00, generation = 0x2efd} 0xdbbc2a00: 0xdbbc2e00 0x00000000 0xdbbc2800 0x00000100 0xdbbc2a10: 0x00000200 0x78787878 0x00026218 0x00000000 0xdbbc2a20: 0xdcad6000 0x00000001 0x78787800 0x00000000 0xdbbc2a30: 0x78780000 0x00000000 0x0068fb84 0x78787878 0xdbbc2a40: 0x78787878 0x78787878 0x78787878 0xe3fa5cc0 0xdbbc2a50: 0x78787878 0x78787878 0x00000000 0x00000000 0xdbbc2a60: 0x00000000 0x00000000 0x00000000 0x00000000 0xdbbc2a70: 0x00000000 0x00000000 0x00000000 0x00000000 0xdbbc2a80: 0x00000000 0x00000000 0x00000000 0x00000000 0xdbbc2a90: 0x00000001 0x00000000 0x00000000 0x00100000 0xdbbc2aa0: 0x00000001 0xdbbc2ac8 0x00000000 0x00000000 0xdbbc2ab0: 0x00000000 0x00000000 0x00000000 0x00000000 0xdbbc2ac0: 0x00000000 0x00000000 0xe5b02618 0x00001000 0xdbbc2ad0: 0x00000000 0x78787878 0x78787878 0x78787878 0xdbbc2ae0: 0x78787878 0x78787878 0x78787878 0x78787878 0xdbbc2af0: 0x78787878 0x78787878 0x78787878 0x78787878 0xdbbc2b00: 0x78787878 0x78787878 0x78787878 0x78787878 0xdbbc2b10: 0x78787878 0x78787878 0x78787878 0x78787878 0xdbbc2b20: 0x78787878 0x78787878 0x78787878 0x78787878 0xdbbc2b30: 0x78787878 0x78787878 0x78787878 0x78787878 0xdbbc2b40: 0x78787878 0x78787878 0x78787878 0x78787878 0xdbbc2b50: 0x78787878 0x78787878 0x78787878 0x78787878 0xdbbc2b60: 0x78787878 0x78787878 0x78787878 0x78787878 0xdbbc2b70: 0x78787878 0x78787878 0x78787878 0x78787878 0xdbbc2b80: 0x78787878 0x78787878 0x00000000 0x78787878 0xdbbc2b90: 0x78787878 0x78787878 0x78787878 0x78787878 0xdbbc2ba0: 0x78787878 0x78787878 0x78787878 0x78787878 In the reclaim path, try_to_free_pages() does not setup sc.target_mem_cgroup and sc is passed to do_try_to_free_pages(), ..., shrink_node(). In mem_cgroup_iter(), root is set to root_mem_cgroup because sc->target_mem_cgroup is NULL. It is possible to assign a memcg to root_mem_cgroup.nodeinfo.iter in mem_cgroup_iter(). try_to_free_pages struct scan_control sc = {...}, target_mem_cgroup is 0x0; do_try_to_free_pages shrink_zones shrink_node mem_cgroup *root = sc->target_mem_cgroup; memcg = mem_cgroup_iter(root, NULL, &reclaim); mem_cgroup_iter() if (!root) root = root_mem_cgroup; ... css = css_next_descendant_pre(css, &root->css); memcg = mem_cgroup_from_css(css); cmpxchg(&iter->position, pos, memcg); My device uses memcg non-hierarchical mode. When we release a memcg: invalidate_reclaim_iterators() reaches only dead_memcg and its parents. If non-hierarchical mode is used, invalidate_reclaim_iterators() never reaches root_mem_cgroup. static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg) { struct mem_cgroup *memcg = dead_memcg; for (; memcg; memcg = parent_mem_cgroup(memcg) ... } So the use after free scenario looks like: CPU1 CPU2 try_to_free_pages do_try_to_free_pages shrink_zones shrink_node mem_cgroup_iter() if (!root) root = root_mem_cgroup; ... css = css_next_descendant_pre(css, &root->css); memcg = mem_cgroup_from_css(css); cmpxchg(&iter->position, pos, memcg); invalidate_reclaim_iterators(memcg); ... __mem_cgroup_free() kfree(memcg); try_to_free_pages do_try_to_free_pages shrink_zones shrink_node mem_cgroup_iter() if (!root) root = root_mem_cgroup; ... mz = mem_cgroup_nodeinfo(root, reclaim->pgdat->node_id); iter = &mz->iter[reclaim->priority]; pos = READ_ONCE(iter->position); css_tryget(&pos->css) <- use after free To avoid this, we should also invalidate root_mem_cgroup.nodeinfo.iter in invalidate_reclaim_iterators(). [cai@lca.pw: fix -Wparentheses compilation warning] Link: http://lkml.kernel.org/r/1564580753-17531-1-git-send-email-cai@lca.pw Link: http://lkml.kernel.org/r/20190730015729.4406-1-miles.chen@mediatek.com Fixes: 5ac8fb31ad2e ("mm: memcontrol: convert reclaim iterator to simple css refcounting") Signed-off-by: Miles Chen Signed-off-by: Qian Cai Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Vladimir Davydov Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 39 +++++++++++++++++++++++++++++---------- 1 file changed, 29 insertions(+), 10 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index cdbb7a84cb6e..2e405e058eda 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1130,26 +1130,45 @@ void mem_cgroup_iter_break(struct mem_cgroup *root, css_put(&prev->css); } -static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg) +static void __invalidate_reclaim_iterators(struct mem_cgroup *from, + struct mem_cgroup *dead_memcg) { - struct mem_cgroup *memcg = dead_memcg; struct mem_cgroup_reclaim_iter *iter; struct mem_cgroup_per_node *mz; int nid; int i; - for (; memcg; memcg = parent_mem_cgroup(memcg)) { - for_each_node(nid) { - mz = mem_cgroup_nodeinfo(memcg, nid); - for (i = 0; i <= DEF_PRIORITY; i++) { - iter = &mz->iter[i]; - cmpxchg(&iter->position, - dead_memcg, NULL); - } + for_each_node(nid) { + mz = mem_cgroup_nodeinfo(from, nid); + for (i = 0; i <= DEF_PRIORITY; i++) { + iter = &mz->iter[i]; + cmpxchg(&iter->position, + dead_memcg, NULL); } } } +static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg) +{ + struct mem_cgroup *memcg = dead_memcg; + struct mem_cgroup *last; + + do { + __invalidate_reclaim_iterators(memcg, dead_memcg); + last = memcg; + } while ((memcg = parent_mem_cgroup(memcg))); + + /* + * When cgruop1 non-hierarchy mode is used, + * parent_mem_cgroup() does not walk all the way up to the + * cgroup root (root_mem_cgroup). So we have to handle + * dead_memcg from cgroup root separately. + */ + if (last != root_mem_cgroup) + __invalidate_reclaim_iterators(root_mem_cgroup, + dead_memcg); +} + /** * mem_cgroup_scan_tasks - iterate over tasks of a memory cgroup hierarchy * @memcg: hierarchy root From 5336e52c9e46afa69b7a85a0a091f0e4daa23d6e Mon Sep 17 00:00:00 2001 From: Kuppuswamy Sathyanarayanan Date: Tue, 13 Aug 2019 15:37:31 -0700 Subject: [PATCH 109/157] mm/vmalloc.c: fix percpu free VM area search criteria Recent changes to the vmalloc code by commit 68ad4a330433 ("mm/vmalloc.c: keep track of free blocks for vmap allocation") can cause spurious percpu allocation failures. These, in turn, can result in panic()s in the slub code. One such possible panic was reported by Dave Hansen in following link https://lkml.org/lkml/2019/6/19/939. Another related panic observed is, RIP: 0033:0x7f46f7441b9b Call Trace: dump_stack+0x61/0x80 pcpu_alloc.cold.30+0x22/0x4f mem_cgroup_css_alloc+0x110/0x650 cgroup_apply_control_enable+0x133/0x330 cgroup_mkdir+0x41b/0x500 kernfs_iop_mkdir+0x5a/0x90 vfs_mkdir+0x102/0x1b0 do_mkdirat+0x7d/0xf0 do_syscall_64+0x5b/0x180 entry_SYSCALL_64_after_hwframe+0x44/0xa9 VMALLOC memory manager divides the entire VMALLOC space (VMALLOC_START to VMALLOC_END) into multiple VM areas (struct vm_areas), and it mainly uses two lists (vmap_area_list & free_vmap_area_list) to track the used and free VM areas in VMALLOC space. And pcpu_get_vm_areas(offsets[], sizes[], nr_vms, align) function is used for allocating congruent VM areas for percpu memory allocator. In order to not conflict with VMALLOC users, pcpu_get_vm_areas allocates VM areas near the end of the VMALLOC space. So the search for free vm_area for the given requirement starts near VMALLOC_END and moves upwards towards VMALLOC_START. Prior to commit 68ad4a330433, the search for free vm_area in pcpu_get_vm_areas() involves following two main steps. Step 1: Find a aligned "base" adress near VMALLOC_END. va = free vm area near VMALLOC_END Step 2: Loop through number of requested vm_areas and check, Step 2.1: if (base < VMALLOC_START) 1. fail with error Step 2.2: // end is offsets[area] + sizes[area] if (base + end > va->vm_end) 1. Move the base downwards and repeat Step 2 Step 2.3: if (base + start < va->vm_start) 1. Move to previous free vm_area node, find aligned base address and repeat Step 2 But Commit 68ad4a330433 removed Step 2.2 and modified Step 2.3 as below: Step 2.3: if (base + start < va->vm_start || base + end > va->vm_end) 1. Move to previous free vm_area node, find aligned base address and repeat Step 2 Above change is the root cause of spurious percpu memory allocation failures. For example, consider a case where a relatively large vm_area (~ 30 TB) was ignored in free vm_area search because it did not pass the base + end < vm->vm_end boundary check. Ignoring such large free vm_area's would lead to not finding free vm_area within boundary of VMALLOC_start to VMALLOC_END which in turn leads to allocation failures. So modify the search algorithm to include Step 2.2. Link: http://lkml.kernel.org/r/20190729232139.91131-1-sathyanarayanan.kuppuswamy@linux.intel.com Fixes: 68ad4a330433 ("mm/vmalloc.c: keep track of free blocks for vmap allocation") Signed-off-by: Kuppuswamy Sathyanarayanan Reported-by: Dave Hansen Acked-by: Dennis Zhou Reviewed-by: Uladzislau Rezki (Sony) Cc: Roman Gushchin Cc: sathyanarayanan kuppuswamy Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmalloc.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index e0fc963acc41..7ba11e12a11f 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -3278,10 +3278,20 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, if (va == NULL) goto overflow; + /* + * If required width exeeds current VA block, move + * base downwards and then recheck. + */ + if (base + end > va->va_end) { + base = pvm_determine_end_from_reverse(&va, align) - end; + term_area = area; + continue; + } + /* * If this VA does not fit, move base downwards and recheck. */ - if (base + start < va->va_start || base + end > va->va_end) { + if (base + start < va->va_start) { va = node_to_va(rb_prev(&va->rb_node)); base = pvm_determine_end_from_reverse(&va, align) - end; term_area = area; From fcf3a5b62f431ce9feeac73afbe128b7b6395dbc Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Tue, 13 Aug 2019 15:37:34 -0700 Subject: [PATCH 110/157] mm: kmemleak: disable early logging in case of error If an error occurs during kmemleak_init() (e.g. kmem cache cannot be created), kmemleak is disabled but kmemleak_early_log remains enabled. Subsequently, when the .init.text section is freed, the log_early() function no longer exists. To avoid a page fault in such scenario, ensure that kmemleak_disable() also disables early logging. Link: http://lkml.kernel.org/r/20190731152302.42073-1-catalin.marinas@arm.com Signed-off-by: Catalin Marinas Reported-by: Qian Cai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kmemleak.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 6e9e8cca663e..f6e602918dac 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1966,6 +1966,7 @@ static void kmemleak_disable(void) /* stop any memory operation tracing */ kmemleak_enabled = 0; + kmemleak_early_log = 0; /* check whether it is too early for a kernel thread */ if (kmemleak_initialized) @@ -2009,7 +2010,6 @@ void __init kmemleak_init(void) #ifdef CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF if (!kmemleak_skip_disable) { - kmemleak_early_log = 0; kmemleak_disable(); return; } From 951531691c4bcaa59f56a316e018bc2ff1ddf855 Mon Sep 17 00:00:00 2001 From: "Isaac J. Manjarres" Date: Tue, 13 Aug 2019 15:37:37 -0700 Subject: [PATCH 111/157] mm/usercopy: use memory range to be accessed for wraparound check Currently, when checking to see if accessing n bytes starting at address "ptr" will cause a wraparound in the memory addresses, the check in check_bogus_address() adds an extra byte, which is incorrect, as the range of addresses that will be accessed is [ptr, ptr + (n - 1)]. This can lead to incorrectly detecting a wraparound in the memory address, when trying to read 4 KB from memory that is mapped to the the last possible page in the virtual address space, when in fact, accessing that range of memory would not cause a wraparound to occur. Use the memory range that will actually be accessed when considering if accessing a certain amount of bytes will cause the memory address to wrap around. Link: http://lkml.kernel.org/r/1564509253-23287-1-git-send-email-isaacm@codeaurora.org Fixes: f5509cc18daa ("mm: Hardened usercopy") Signed-off-by: Prasad Sodagudi Signed-off-by: Isaac J. Manjarres Co-developed-by: Prasad Sodagudi Reviewed-by: William Kucharski Acked-by: Kees Cook Cc: Greg Kroah-Hartman Cc: Trilok Soni Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/usercopy.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/usercopy.c b/mm/usercopy.c index 2a09796edef8..98e924864554 100644 --- a/mm/usercopy.c +++ b/mm/usercopy.c @@ -147,7 +147,7 @@ static inline void check_bogus_address(const unsigned long ptr, unsigned long n, bool to_user) { /* Reject if object wraps past end of memory. */ - if (ptr + n < ptr) + if (ptr + (n - 1) < ptr) usercopy_abort("wrapped address", NULL, to_user, 0, ptr + n); /* Reject if NULL or ZERO-allocation. */ From ec9f02384f6053f2a5417e82b65078edc5364a8d Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 13 Aug 2019 15:37:41 -0700 Subject: [PATCH 112/157] mm: workingset: fix vmstat counters for shadow nodes Memcg counters for shadow nodes are broken because the memcg pointer is obtained in a wrong way. The following approach is used: virt_to_page(xa_node)->mem_cgroup Since commit 4d96ba353075 ("mm: memcg/slab: stop setting page->mem_cgroup pointer for slab pages") page->mem_cgroup pointer isn't set for slab pages, so memcg_from_slab_page() should be used instead. Also I doubt that it ever worked correctly: virt_to_head_page() should be used instead of virt_to_page(). Otherwise objects residing on tail pages are not accounted, because only the head page contains a valid mem_cgroup pointer. That was a case since the introduction of these counters by the commit 68d48e6a2df5 ("mm: workingset: add vmstat counter for shadow nodes"). Link: http://lkml.kernel.org/r/20190801233532.138743-1-guro@fb.com Fixes: 4d96ba353075 ("mm: memcg/slab: stop setting page->mem_cgroup pointer for slab pages") Signed-off-by: Roman Gushchin Acked-by: Johannes Weiner Cc: Vladimir Davydov Cc: Shakeel Butt Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 19 +++++++++++++++++++ mm/memcontrol.c | 20 ++++++++++++++++++++ mm/workingset.c | 10 ++++------ 3 files changed, 43 insertions(+), 6 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 44c41462be33..2cd4359cb38c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -668,6 +668,7 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); +void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val); static inline void mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) @@ -1072,6 +1073,14 @@ static inline void mod_lruvec_page_state(struct page *page, mod_node_page_state(page_pgdat(page), idx, val); } +static inline void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, + int val) +{ + struct page *page = virt_to_head_page(p); + + __mod_node_page_state(page_pgdat(page), idx, val); +} + static inline unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, @@ -1159,6 +1168,16 @@ static inline void __dec_lruvec_page_state(struct page *page, __mod_lruvec_page_state(page, idx, -1); } +static inline void __inc_lruvec_slab_state(void *p, enum node_stat_item idx) +{ + __mod_lruvec_slab_state(p, idx, 1); +} + +static inline void __dec_lruvec_slab_state(void *p, enum node_stat_item idx) +{ + __mod_lruvec_slab_state(p, idx, -1); +} + /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void inc_memcg_state(struct mem_cgroup *memcg, int idx) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2e405e058eda..6f5c0c517c49 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -768,6 +768,26 @@ void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, __this_cpu_write(pn->lruvec_stat_cpu->count[idx], x); } +void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val) +{ + struct page *page = virt_to_head_page(p); + pg_data_t *pgdat = page_pgdat(page); + struct mem_cgroup *memcg; + struct lruvec *lruvec; + + rcu_read_lock(); + memcg = memcg_from_slab_page(page); + + /* Untracked pages have no memcg, no lruvec. Update only the node */ + if (!memcg || memcg == root_mem_cgroup) { + __mod_node_page_state(pgdat, idx, val); + } else { + lruvec = mem_cgroup_lruvec(pgdat, memcg); + __mod_lruvec_state(lruvec, idx, val); + } + rcu_read_unlock(); +} + /** * __count_memcg_events - account VM events in a cgroup * @memcg: the memory cgroup diff --git a/mm/workingset.c b/mm/workingset.c index e0b4edcb88c8..c963831d354f 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -380,14 +380,12 @@ void workingset_update_node(struct xa_node *node) if (node->count && node->count == node->nr_values) { if (list_empty(&node->private_list)) { list_lru_add(&shadow_nodes, &node->private_list); - __inc_lruvec_page_state(virt_to_page(node), - WORKINGSET_NODES); + __inc_lruvec_slab_state(node, WORKINGSET_NODES); } } else { if (!list_empty(&node->private_list)) { list_lru_del(&shadow_nodes, &node->private_list); - __dec_lruvec_page_state(virt_to_page(node), - WORKINGSET_NODES); + __dec_lruvec_slab_state(node, WORKINGSET_NODES); } } } @@ -480,7 +478,7 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, } list_lru_isolate(lru, item); - __dec_lruvec_page_state(virt_to_page(node), WORKINGSET_NODES); + __dec_lruvec_slab_state(node, WORKINGSET_NODES); spin_unlock(lru_lock); @@ -503,7 +501,7 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, * shadow entries we were tracking ... */ xas_store(&xas, NULL); - __inc_lruvec_page_state(virt_to_page(node), WORKINGSET_NODERECLAIM); + __inc_lruvec_slab_state(node, WORKINGSET_NODERECLAIM); out_invalid: xa_unlock_irq(&mapping->i_pages); From 6a2aeab59e97101b4001bac84388fc49a992f87e Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 13 Aug 2019 15:37:44 -0700 Subject: [PATCH 113/157] seq_file: fix problem when seeking mid-record If you use lseek or similar (e.g. pread) to access a location in a seq_file file that is within a record, rather than at a record boundary, then the first read will return the remainder of the record, and the second read will return the whole of that same record (instead of the next record). When seeking to a record boundary, the next record is correctly returned. This bug was introduced by a recent patch (identified below). Before that patch, seq_read() would increment m->index when the last of the buffer was returned (m->count == 0). After that patch, we rely on ->next to increment m->index after filling the buffer - but there was one place where that didn't happen. Link: https://lkml.kernel.org/lkml/877e7xl029.fsf@notabene.neil.brown.name/ Fixes: 1f4aace60b0e ("fs/seq_file.c: simplify seq_file iteration code and interface") Signed-off-by: NeilBrown Reported-by: Sergei Turchanov Tested-by: Sergei Turchanov Cc: Alexander Viro Cc: Markus Elfring Cc: [4.19+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/seq_file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/seq_file.c b/fs/seq_file.c index 04f09689cd6d..1600034a929b 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -119,6 +119,7 @@ static int traverse(struct seq_file *m, loff_t offset) } if (seq_has_overflowed(m)) goto Eoverflow; + p = m->op->next(m, p, &m->index); if (pos + m->count > offset) { m->from = offset - pos; m->count -= m->from; @@ -126,7 +127,6 @@ static int traverse(struct seq_file *m, loff_t offset) } pos += m->count; m->count = 0; - p = m->op->next(m, p, &m->index); if (pos == offset) break; } From 0cfaee2af3a04c0be5f056cebe5f804dedc59a43 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Tue, 13 Aug 2019 15:37:47 -0700 Subject: [PATCH 114/157] include/asm-generic/5level-fixup.h: fix variable 'p4d' set but not used A compiler throws a warning on an arm64 system since commit 9849a5697d3d ("arch, mm: convert all architectures to use 5level-fixup.h"), mm/kasan/init.c: In function 'kasan_free_p4d': mm/kasan/init.c:344:9: warning: variable 'p4d' set but not used [-Wunused-but-set-variable] p4d_t *p4d; ^~~ because p4d_none() in "5level-fixup.h" is compiled away while it is a static inline function in "pgtable-nopud.h". However, if converted p4d_none() to a static inline there, powerpc would be unhappy as it reads those in assembler language in "arch/powerpc/include/asm/book3s/64/pgtable.h", so it needs to skip assembly include for the static inline C function. While at it, converted a few similar functions to be consistent with the ones in "pgtable-nopud.h". Link: http://lkml.kernel.org/r/20190806232917.881-1-cai@lca.pw Signed-off-by: Qian Cai Acked-by: Arnd Bergmann Cc: Kirill A. Shutemov Cc: Michal Hocko Cc: Jason Gunthorpe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/5level-fixup.h | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) diff --git a/include/asm-generic/5level-fixup.h b/include/asm-generic/5level-fixup.h index bb6cb347018c..f6947da70d71 100644 --- a/include/asm-generic/5level-fixup.h +++ b/include/asm-generic/5level-fixup.h @@ -19,9 +19,24 @@ #define p4d_alloc(mm, pgd, address) (pgd) #define p4d_offset(pgd, start) (pgd) -#define p4d_none(p4d) 0 -#define p4d_bad(p4d) 0 -#define p4d_present(p4d) 1 + +#ifndef __ASSEMBLY__ +static inline int p4d_none(p4d_t p4d) +{ + return 0; +} + +static inline int p4d_bad(p4d_t p4d) +{ + return 0; +} + +static inline int p4d_present(p4d_t p4d) +{ + return 1; +} +#endif + #define p4d_ERROR(p4d) do { } while (0) #define p4d_clear(p4d) pgd_clear(p4d) #define p4d_val(p4d) pgd_val(p4d) From 92717d429b38e4f9f934eed7e605cc42858f1839 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Tue, 13 Aug 2019 15:37:50 -0700 Subject: [PATCH 115/157] Revert "Revert "mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask"" Patch series "reapply: relax __GFP_THISNODE for MADV_HUGEPAGE mappings". The fixes for what was originally reported as "pathological THP behavior" we rightfully reverted to be sure not to introduced regressions at end of a merge window after a severe regression report from the kernel bot. We can safely re-apply them now that we had time to analyze the problem. The mm process worked fine, because the good fixes were eventually committed upstream without excessive delay. The regression reported by the kernel bot however forced us to revert the good fixes to be sure not to introduce regressions and to give us the time to analyze the issue further. The silver lining is that this extra time allowed to think more at this issue and also plan for a future direction to improve things further in terms of THP NUMA locality. This patch (of 2): This reverts commit 356ff8a9a78fb35d ("Revert "mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask"). So it reapplies 89c83fb539f954 ("mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask"). Consolidation of the THP allocation flags at the same place was meant to be a clean up to easier handle otherwise scattered code which is imposing a maintenance burden. There were no real problems observed with the gfp mask consolidation but the reversion was rushed through without a larger consensus regardless. This patch brings the consolidation back because this should make the long term maintainability easier as well as it should allow future changes to be less error prone. [mhocko@kernel.org: changelog additions] Link: http://lkml.kernel.org/r/20190503223146.2312-2-aarcange@redhat.com Signed-off-by: Andrea Arcangeli Acked-by: Michal Hocko Cc: Mel Gorman Cc: Vlastimil Babka Cc: David Rientjes Cc: Zi Yan Cc: Stefan Priebe - Profihost AG Cc: "Kirill A. Shutemov" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 12 ++++-------- mm/huge_memory.c | 27 ++++++++++++++------------- mm/mempolicy.c | 32 +++----------------------------- mm/shmem.c | 2 +- 4 files changed, 22 insertions(+), 51 deletions(-) diff --git a/include/linux/gfp.h b/include/linux/gfp.h index fb07b503dc45..f33881688f42 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -510,22 +510,18 @@ alloc_pages(gfp_t gfp_mask, unsigned int order) } extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, - int node, bool hugepage); -#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ - alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true) + int node); #else #define alloc_pages(gfp_mask, order) \ alloc_pages_node(numa_node_id(), gfp_mask, order) -#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\ - alloc_pages(gfp_mask, order) -#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ +#define alloc_pages_vma(gfp_mask, order, vma, addr, node)\ alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) #define alloc_page_vma(gfp_mask, vma, addr) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false) + alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id()) #define alloc_page_vma_node(gfp_mask, vma, addr, node) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, node, false) + alloc_pages_vma(gfp_mask, 0, vma, addr, node) extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 1334ede667a8..f7e388b8662d 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -644,30 +644,30 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, * available * never: never stall for any thp allocation */ -static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma) +static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma, unsigned long addr) { const bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE); + const gfp_t gfp_mask = GFP_TRANSHUGE_LIGHT | __GFP_THISNODE; /* Always do synchronous compaction */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags)) - return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY); + return GFP_TRANSHUGE | __GFP_THISNODE | + (vma_madvised ? 0 : __GFP_NORETRY); /* Kick kcompactd and fail quickly */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags)) - return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM; + return gfp_mask | __GFP_KSWAPD_RECLAIM; /* Synchronous compaction if madvised, otherwise kick kcompactd */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags)) - return GFP_TRANSHUGE_LIGHT | - (vma_madvised ? __GFP_DIRECT_RECLAIM : - __GFP_KSWAPD_RECLAIM); + return gfp_mask | (vma_madvised ? __GFP_DIRECT_RECLAIM : + __GFP_KSWAPD_RECLAIM); /* Only do synchronous compaction if madvised */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags)) - return GFP_TRANSHUGE_LIGHT | - (vma_madvised ? __GFP_DIRECT_RECLAIM : 0); + return gfp_mask | (vma_madvised ? __GFP_DIRECT_RECLAIM : 0); - return GFP_TRANSHUGE_LIGHT; + return gfp_mask; } /* Caller must hold page table lock. */ @@ -739,8 +739,8 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) pte_free(vma->vm_mm, pgtable); return ret; } - gfp = alloc_hugepage_direct_gfpmask(vma); - page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER); + gfp = alloc_hugepage_direct_gfpmask(vma, haddr); + page = alloc_pages_vma(gfp, HPAGE_PMD_ORDER, vma, haddr, numa_node_id()); if (unlikely(!page)) { count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; @@ -1347,8 +1347,9 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd) alloc: if (__transparent_hugepage_enabled(vma) && !transparent_hugepage_debug_cow()) { - huge_gfp = alloc_hugepage_direct_gfpmask(vma); - new_page = alloc_hugepage_vma(huge_gfp, vma, haddr, HPAGE_PMD_ORDER); + huge_gfp = alloc_hugepage_direct_gfpmask(vma, haddr); + new_page = alloc_pages_vma(huge_gfp, HPAGE_PMD_ORDER, vma, + haddr, numa_node_id()); } else new_page = NULL; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 547cd403ed02..9c9877a43d58 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1180,8 +1180,8 @@ static struct page *new_page(struct page *page, unsigned long start) } else if (PageTransHuge(page)) { struct page *thp; - thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address, - HPAGE_PMD_ORDER); + thp = alloc_pages_vma(GFP_TRANSHUGE, HPAGE_PMD_ORDER, vma, + address, numa_node_id()); if (!thp) return NULL; prep_transhuge_page(thp); @@ -2083,7 +2083,6 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, * @vma: Pointer to VMA or NULL if not available. * @addr: Virtual Address of the allocation. Must be inside the VMA. * @node: Which node to prefer for allocation (modulo policy). - * @hugepage: for hugepages try only the preferred node if possible * * This function allocates a page from the kernel page pool and applies * a NUMA policy associated with the VMA or the current process. @@ -2094,7 +2093,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, */ struct page * alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, - unsigned long addr, int node, bool hugepage) + unsigned long addr, int node) { struct mempolicy *pol; struct page *page; @@ -2112,31 +2111,6 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, goto out; } - if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage)) { - int hpage_node = node; - - /* - * For hugepage allocation and non-interleave policy which - * allows the current node (or other explicitly preferred - * node) we only try to allocate from the current/preferred - * node and don't fall back to other nodes, as the cost of - * remote accesses would likely offset THP benefits. - * - * If the policy is interleave, or does not allow the current - * node in its nodemask, we allocate the standard way. - */ - if (pol->mode == MPOL_PREFERRED && !(pol->flags & MPOL_F_LOCAL)) - hpage_node = pol->v.preferred_node; - - nmask = policy_nodemask(gfp, pol); - if (!nmask || node_isset(hpage_node, *nmask)) { - mpol_cond_put(pol); - page = __alloc_pages_node(hpage_node, - gfp | __GFP_THISNODE, order); - goto out; - } - } - nmask = policy_nodemask(gfp, pol); preferred_nid = policy_node(gfp, pol, node); page = __alloc_pages_nodemask(gfp, order, preferred_nid, nmask); diff --git a/mm/shmem.c b/mm/shmem.c index 626d8c74b973..2bed4761f279 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1466,7 +1466,7 @@ static struct page *shmem_alloc_hugepage(gfp_t gfp, shmem_pseudo_vma_init(&pvma, info, hindex); page = alloc_pages_vma(gfp | __GFP_COMP | __GFP_NORETRY | __GFP_NOWARN, - HPAGE_PMD_ORDER, &pvma, 0, numa_node_id(), true); + HPAGE_PMD_ORDER, &pvma, 0, numa_node_id()); shmem_pseudo_vma_destroy(&pvma); if (page) prep_transhuge_page(page); From a8282608c88e08b1782141026eab61204c1e533f Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Tue, 13 Aug 2019 15:37:53 -0700 Subject: [PATCH 116/157] Revert "mm, thp: restore node-local hugepage allocations" This reverts commit 2f0799a0ffc033b ("mm, thp: restore node-local hugepage allocations"). commit 2f0799a0ffc033b was rightfully applied to avoid the risk of a severe regression that was reported by the kernel test robot at the end of the merge window. Now we understood the regression was a false positive and was caused by a significant increase in fairness during a swap trashing benchmark. So it's safe to re-apply the fix and continue improving the code from there. The benchmark that reported the regression is very useful, but it provides a meaningful result only when there is no significant alteration in fairness during the workload. The removal of __GFP_THISNODE increased fairness. __GFP_THISNODE cannot be used in the generic page faults path for new memory allocations under the MPOL_DEFAULT mempolicy, or the allocation behavior significantly deviates from what the MPOL_DEFAULT semantics are supposed to be for THP and 4k allocations alike. Setting THP defrag to "always" or using MADV_HUGEPAGE (with THP defrag set to "madvise") has never meant to provide an implicit MPOL_BIND on the "current" node the task is running on, causing swap storms and providing a much more aggressive behavior than even zone_reclaim_node = 3. Any workload who could have benefited from __GFP_THISNODE has now to enable zone_reclaim_mode=1||2||3. __GFP_THISNODE implicitly provided the zone_reclaim_mode behavior, but it only did so if THP was enabled: if THP was disabled, there would have been no chance to get any 4k page from the current node if the current node was full of pagecache, which further shows how this __GFP_THISNODE was misplaced in MADV_HUGEPAGE. MADV_HUGEPAGE has never been intended to provide any zone_reclaim_mode semantics, in fact the two are orthogonal, zone_reclaim_mode = 1|2|3 must work exactly the same with MADV_HUGEPAGE set or not. The performance characteristic of memory depends on the hardware details. The numbers below are obtained on Naples/EPYC architecture and the N/A projection extends them to show what we should aim for in the future as a good THP NUMA locality default. The benchmark used exercises random memory seeks (note: the cost of the page faults is not part of the measurement). D0 THP | D0 4k | D1 THP | D1 4k | D2 THP | D2 4k | D3 THP | D3 4k | ... 0% | +43% | +45% | +106% | +131% | +224% | N/A | N/A D0 means distance zero (i.e. local memory), D1 means distance one (i.e. intra socket memory), D2 means distance two (i.e. inter socket memory), etc... For the guest physical memory allocated by qemu and for guest mode kernel the performance characteristic of RAM is more complex and an ideal default could be: D0 THP | D1 THP | D0 4k | D2 THP | D1 4k | D3 THP | D2 4k | D3 4k | ... 0% | +58% | +101% | N/A | +222% | N/A | N/A | N/A NOTE: the N/A are projections and haven't been measured yet, the measurement in this case is done on a 1950x with only two NUMA nodes. The THP case here means THP was used both in the host and in the guest. After applying this commit the THP NUMA locality order that we'll get out of MADV_HUGEPAGE is this: D0 THP | D1 THP | D2 THP | D3 THP | ... | D0 4k | D1 4k | D2 4k | D3 4k | ... Before this commit it was: D0 THP | D0 4k | D1 4k | D2 4k | D3 4k | ... Even if we ignore the breakage of large workloads that can't fit in a single node that the __GFP_THISNODE implicit "current node" mbind caused, the THP NUMA locality order provided by __GFP_THISNODE was still not the one we shall aim for in the long term (i.e. the first one at the top). After this commit is applied, we can introduce a new allocator multi order API and to replace those two alloc_pages_vmas calls in the page fault path, with a single multi order call: unsigned int order = (1 << HPAGE_PMD_ORDER) | (1 << 0); page = alloc_pages_multi_order(..., &order); if (!page) goto out; if (!(order & (1 << 0))) { VM_WARN_ON(order != 1 << HPAGE_PMD_ORDER); /* THP fault */ } else { VM_WARN_ON(order != 1 << 0); /* 4k fallback */ } The page allocator logic has to be altered so that when it fails on any zone with order 9, it has to try again with a order 0 before falling back to the next zone in the zonelist. After that we need to do more measurements and evaluate if adding an opt-in feature for guest mode is worth it, to swap "DN 4k | DN+1 THP" with "DN+1 THP | DN 4k" at every NUMA distance crossing. Link: http://lkml.kernel.org/r/20190503223146.2312-3-aarcange@redhat.com Signed-off-by: Andrea Arcangeli Acked-by: Michal Hocko Acked-by: Mel Gorman Cc: Vlastimil Babka Cc: David Rientjes Cc: Zi Yan Cc: Stefan Priebe - Profihost AG Cc: "Kirill A. Shutemov" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 2 ++ mm/huge_memory.c | 42 ++++++++++++++++++++++++--------------- mm/mempolicy.c | 2 +- 3 files changed, 29 insertions(+), 17 deletions(-) diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 5228c62af416..bac395f1d00a 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -139,6 +139,8 @@ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, struct mempolicy *get_task_policy(struct task_struct *p); struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr); +struct mempolicy *get_vma_policy(struct vm_area_struct *vma, + unsigned long addr); bool vma_policy_mof(struct vm_area_struct *vma); extern void numa_default_policy(void); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index f7e388b8662d..738065f765ab 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -647,27 +647,37 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma, unsigned long addr) { const bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE); - const gfp_t gfp_mask = GFP_TRANSHUGE_LIGHT | __GFP_THISNODE; + gfp_t this_node = 0; + +#ifdef CONFIG_NUMA + struct mempolicy *pol; + /* + * __GFP_THISNODE is used only when __GFP_DIRECT_RECLAIM is not + * specified, to express a general desire to stay on the current + * node for optimistic allocation attempts. If the defrag mode + * and/or madvise hint requires the direct reclaim then we prefer + * to fallback to other node rather than node reclaim because that + * can lead to excessive reclaim even though there is free memory + * on other nodes. We expect that NUMA preferences are specified + * by memory policies. + */ + pol = get_vma_policy(vma, addr); + if (pol->mode != MPOL_BIND) + this_node = __GFP_THISNODE; + mpol_cond_put(pol); +#endif - /* Always do synchronous compaction */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags)) - return GFP_TRANSHUGE | __GFP_THISNODE | - (vma_madvised ? 0 : __GFP_NORETRY); - - /* Kick kcompactd and fail quickly */ + return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY); if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags)) - return gfp_mask | __GFP_KSWAPD_RECLAIM; - - /* Synchronous compaction if madvised, otherwise kick kcompactd */ + return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM | this_node; if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags)) - return gfp_mask | (vma_madvised ? __GFP_DIRECT_RECLAIM : - __GFP_KSWAPD_RECLAIM); - - /* Only do synchronous compaction if madvised */ + return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM : + __GFP_KSWAPD_RECLAIM | this_node); if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags)) - return gfp_mask | (vma_madvised ? __GFP_DIRECT_RECLAIM : 0); - - return gfp_mask; + return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM : + this_node); + return GFP_TRANSHUGE_LIGHT | this_node; } /* Caller must hold page table lock. */ diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 9c9877a43d58..65e0874fce17 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1734,7 +1734,7 @@ struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, * freeing by another task. It is the caller's responsibility to free the * extra reference for shared policies. */ -static struct mempolicy *get_vma_policy(struct vm_area_struct *vma, +struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr) { struct mempolicy *pol = __get_vma_policy(vma, addr); From 28360f398778d7623a5ff8a8e90958c0d925e120 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 13 Aug 2019 15:37:57 -0700 Subject: [PATCH 117/157] mm, vmscan: do not special-case slab reclaim when watermarks are boosted Dave Chinner reported a problem pointing a finger at commit 1c30844d2dfe ("mm: reclaim small amounts of memory when an external fragmentation event occurs"). The report is extensive: https://lore.kernel.org/linux-mm/20190807091858.2857-1-david@fromorbit.com/ and it's worth recording the most relevant parts (colorful language and typos included). When running a simple, steady state 4kB file creation test to simulate extracting tarballs larger than memory full of small files into the filesystem, I noticed that once memory fills up the cache balance goes to hell. The workload is creating one dirty cached inode for every dirty page, both of which should require a single IO each to clean and reclaim, and creation of inodes is throttled by the rate at which dirty writeback runs at (via balance dirty pages). Hence the ingest rate of new cached inodes and page cache pages is identical and steady. As a result, memory reclaim should quickly find a steady balance between page cache and inode caches. The moment memory fills, the page cache is reclaimed at a much faster rate than the inode cache, and evidence suggests that the inode cache shrinker is not being called when large batches of pages are being reclaimed. In roughly the same time period that it takes to fill memory with 50% pages and 50% slab caches, memory reclaim reduces the page cache down to just dirty pages and slab caches fill the entirety of memory. The LRU is largely full of dirty pages, and we're getting spikes of random writeback from memory reclaim so it's all going to shit. Behaviour never recovers, the page cache remains pinned at just dirty pages, and nothing I could tune would make any difference. vfs_cache_pressure makes no difference - I would set it so high it should trim the entire inode caches in a single pass, yet it didn't do anything. It was clear from tracing and live telemetry that the shrinkers were pretty much not running except when there was absolutely no memory free at all, and then they did the minimum necessary to free memory to make progress. So I went looking at the code, trying to find places where pages got reclaimed and the shrinkers weren't called. There's only one - kswapd doing boosted reclaim as per commit 1c30844d2dfe ("mm: reclaim small amounts of memory when an external fragmentation event occurs"). The watermark boosting introduced by the commit is triggered in response to an allocation "fragmentation event". The boosting was not intended to target THP specifically and triggers even if THP is disabled. However, with Dave's perfectly reasonable workload, fragmentation events can be very common given the ratio of slab to page cache allocations so boosting remains active for long periods of time. As high-order allocations might use compaction and compaction cannot move slab pages the decision was made in the commit to special-case kswapd when watermarks are boosted -- kswapd avoids reclaiming slab as reclaiming slab does not directly help compaction. As Dave notes, this decision means that slab can be artificially protected for long periods of time and messes up the balance with slab and page caches. Removing the special casing can still indirectly help avoid fragmentation by avoiding fragmentation-causing events due to slab allocation as pages from a slab pageblock will have some slab objects freed. Furthermore, with the special casing, reclaim behaviour is unpredictable as kswapd sometimes examines slab and sometimes does not in a manner that is tricky to tune or analyse. This patch removes the special casing. The downside is that this is not a universal performance win. Some benchmarks that depend on the residency of data when rereading metadata may see a regression when slab reclaim is restored to its original behaviour. Similarly, some benchmarks that only read-once or write-once may perform better when page reclaim is too aggressive. The primary upside is that slab shrinker is less surprising (arguably more sane but that's a matter of opinion), behaves consistently regardless of the fragmentation state of the system and properly obeys VM sysctls. A fsmark benchmark configuration was constructed similar to what Dave reported and is codified by the mmtest configuration config-io-fsmark-small-file-stream. It was evaluated on a 1-socket machine to avoid dealing with NUMA-related issues and the timing of reclaim. The storage was an SSD Samsung Evo and a fresh trimmed XFS filesystem was used for the test data. This is not an exact replication of Dave's setup. The configuration scales its parameters depending on the memory size of the SUT to behave similarly across machines. The parameters mean the first sample reported by fs_mark is using 50% of RAM which will barely be throttled and look like a big outlier. Dave used fake NUMA to have multiple kswapd instances which I didn't replicate. Finally, the number of iterations differ from Dave's test as the target disk was not large enough. While not identical, it should be representative. fsmark 5.3.0-rc3 5.3.0-rc3 vanilla shrinker-v1r1 Min 1-files/sec 4444.80 ( 0.00%) 4765.60 ( 7.22%) 1st-qrtle 1-files/sec 5005.10 ( 0.00%) 5091.70 ( 1.73%) 2nd-qrtle 1-files/sec 4917.80 ( 0.00%) 4855.60 ( -1.26%) 3rd-qrtle 1-files/sec 4667.40 ( 0.00%) 4831.20 ( 3.51%) Max-1 1-files/sec 11421.50 ( 0.00%) 9999.30 ( -12.45%) Max-5 1-files/sec 11421.50 ( 0.00%) 9999.30 ( -12.45%) Max-10 1-files/sec 11421.50 ( 0.00%) 9999.30 ( -12.45%) Max-90 1-files/sec 4649.60 ( 0.00%) 4780.70 ( 2.82%) Max-95 1-files/sec 4491.00 ( 0.00%) 4768.20 ( 6.17%) Max-99 1-files/sec 4491.00 ( 0.00%) 4768.20 ( 6.17%) Max 1-files/sec 11421.50 ( 0.00%) 9999.30 ( -12.45%) Hmean 1-files/sec 5004.75 ( 0.00%) 5075.96 ( 1.42%) Stddev 1-files/sec 1778.70 ( 0.00%) 1369.66 ( 23.00%) CoeffVar 1-files/sec 33.70 ( 0.00%) 26.05 ( 22.71%) BHmean-99 1-files/sec 5053.72 ( 0.00%) 5101.52 ( 0.95%) BHmean-95 1-files/sec 5053.72 ( 0.00%) 5101.52 ( 0.95%) BHmean-90 1-files/sec 5107.05 ( 0.00%) 5131.41 ( 0.48%) BHmean-75 1-files/sec 5208.45 ( 0.00%) 5206.68 ( -0.03%) BHmean-50 1-files/sec 5405.53 ( 0.00%) 5381.62 ( -0.44%) BHmean-25 1-files/sec 6179.75 ( 0.00%) 6095.14 ( -1.37%) 5.3.0-rc3 5.3.0-rc3 vanillashrinker-v1r1 Duration User 501.82 497.29 Duration System 4401.44 4424.08 Duration Elapsed 8124.76 8358.05 This is showing a slight skew for the max result representing a large outlier for the 1st, 2nd and 3rd quartile are similar indicating that the bulk of the results show little difference. Note that an earlier version of the fsmark configuration showed a regression but that included more samples taken while memory was still filling. Note that the elapsed time is higher. Part of this is that the configuration included time to delete all the test files when the test completes -- the test automation handles the possibility of testing fsmark with multiple thread counts. Without the patch, many of these objects would be memory resident which is part of what the patch is addressing. There are other important observations that justify the patch. 1. With the vanilla kernel, the number of dirty pages in the system is very low for much of the test. With this patch, dirty pages is generally kept at 10% which matches vm.dirty_background_ratio which is normal expected historical behaviour. 2. With the vanilla kernel, the ratio of Slab/Pagecache is close to 0.95 for much of the test i.e. Slab is being left alone and dominating memory consumption. With the patch applied, the ratio varies between 0.35 and 0.45 with the bulk of the measured ratios roughly half way between those values. This is a different balance to what Dave reported but it was at least consistent. 3. Slabs are scanned throughout the entire test with the patch applied. The vanille kernel has periods with no scan activity and then relatively massive spikes. 4. Without the patch, kswapd scan rates are very variable. With the patch, the scan rates remain quite steady. 4. Overall vmstats are closer to normal expectations 5.3.0-rc3 5.3.0-rc3 vanilla shrinker-v1r1 Ops Direct pages scanned 99388.00 328410.00 Ops Kswapd pages scanned 45382917.00 33451026.00 Ops Kswapd pages reclaimed 30869570.00 25239655.00 Ops Direct pages reclaimed 74131.00 5830.00 Ops Kswapd efficiency % 68.02 75.45 Ops Kswapd velocity 5585.75 4002.25 Ops Page reclaim immediate 1179721.00 430927.00 Ops Slabs scanned 62367361.00 73581394.00 Ops Direct inode steals 2103.00 1002.00 Ops Kswapd inode steals 570180.00 5183206.00 o Vanilla kernel is hitting direct reclaim more frequently, not very much in absolute terms but the fact the patch reduces it is interesting o "Page reclaim immediate" in the vanilla kernel indicates dirty pages are being encountered at the tail of the LRU. This is generally bad and means in this case that the LRU is not long enough for dirty pages to be cleaned by the background flush in time. This is much reduced by the patch. o With the patch, kswapd is reclaiming 10 times more slab pages than with the vanilla kernel. This is indicative of the watermark boosting over-protecting slab A more complete set of tests were run that were part of the basis for introducing boosting and while there are some differences, they are well within tolerances. Bottom line, the special casing kswapd to avoid slab behaviour is unpredictable and can lead to abnormal results for normal workloads. This patch restores the expected behaviour that slab and page cache is balanced consistently for a workload with a steady allocation ratio of slab/pagecache pages. It also means that if there are workloads that favour the preservation of slab over pagecache that it can be tuned via vm.vfs_cache_pressure where as the vanilla kernel effectively ignores the parameter when boosting is active. Link: http://lkml.kernel.org/r/20190808182946.GM2739@techsingularity.net Fixes: 1c30844d2dfe ("mm: reclaim small amounts of memory when an external fragmentation event occurs") Signed-off-by: Mel Gorman Reviewed-by: Dave Chinner Acked-by: Vlastimil Babka Cc: Michal Hocko Cc: [5.0+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmscan.c | 13 ++----------- 1 file changed, 2 insertions(+), 11 deletions(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index dbdc46a84f63..c77d1e3761a7 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -88,9 +88,6 @@ struct scan_control { /* Can pages be swapped as part of reclaim? */ unsigned int may_swap:1; - /* e.g. boosted watermark reclaim leaves slabs alone */ - unsigned int may_shrinkslab:1; - /* * Cgroups are not reclaimed below their configured memory.low, * unless we threaten to OOM. If any cgroups are skipped due to @@ -2714,10 +2711,8 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc) shrink_node_memcg(pgdat, memcg, sc, &lru_pages); node_lru_pages += lru_pages; - if (sc->may_shrinkslab) { - shrink_slab(sc->gfp_mask, pgdat->node_id, - memcg, sc->priority); - } + shrink_slab(sc->gfp_mask, pgdat->node_id, memcg, + sc->priority); /* Record the group's reclaim efficiency */ vmpressure(sc->gfp_mask, memcg, false, @@ -3194,7 +3189,6 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, .may_writepage = !laptop_mode, .may_unmap = 1, .may_swap = 1, - .may_shrinkslab = 1, }; /* @@ -3238,7 +3232,6 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, .may_unmap = 1, .reclaim_idx = MAX_NR_ZONES - 1, .may_swap = !noswap, - .may_shrinkslab = 1, }; unsigned long lru_pages; @@ -3286,7 +3279,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, .may_writepage = !laptop_mode, .may_unmap = 1, .may_swap = may_swap, - .may_shrinkslab = 1, }; set_task_reclaim_state(current, &sc.reclaim_state); @@ -3598,7 +3590,6 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) */ sc.may_writepage = !laptop_mode && !nr_boost_reclaim; sc.may_swap = !nr_boost_reclaim; - sc.may_shrinkslab = !nr_boost_reclaim; /* * Do some background aging of the anon list, to give From 4643d67e8cb0b3536ef0ab5cddd1cedc73fa14ad Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Tue, 13 Aug 2019 15:38:00 -0700 Subject: [PATCH 118/157] hugetlbfs: fix hugetlb page migration/fault race causing SIGBUS Li Wang discovered that LTP/move_page12 V2 sometimes triggers SIGBUS in the kernel-v5.2.3 testing. This is caused by a race between hugetlb page migration and page fault. If a hugetlb page can not be allocated to satisfy a page fault, the task is sent SIGBUS. This is normal hugetlbfs behavior. A hugetlb fault mutex exists to prevent two tasks from trying to instantiate the same page. This protects against the situation where there is only one hugetlb page, and both tasks would try to allocate. Without the mutex, one would fail and SIGBUS even though the other fault would be successful. There is a similar race between hugetlb page migration and fault. Migration code will allocate a page for the target of the migration. It will then unmap the original page from all page tables. It does this unmap by first clearing the pte and then writing a migration entry. The page table lock is held for the duration of this clear and write operation. However, the beginnings of the hugetlb page fault code optimistically checks the pte without taking the page table lock. If clear (as it can be during the migration unmap operation), a hugetlb page allocation is attempted to satisfy the fault. Note that the page which will eventually satisfy this fault was already allocated by the migration code. However, the allocation within the fault path could fail which would result in the task incorrectly being sent SIGBUS. Ideally, we could take the hugetlb fault mutex in the migration code when modifying the page tables. However, locks must be taken in the order of hugetlb fault mutex, page lock, page table lock. This would require significant rework of the migration code. Instead, the issue is addressed in the hugetlb fault code. After failing to allocate a huge page, take the page table lock and check for huge_pte_none before returning an error. This is the same check that must be made further in the code even if page allocation is successful. Link: http://lkml.kernel.org/r/20190808000533.7701-1-mike.kravetz@oracle.com Fixes: 290408d4a250 ("hugetlb: hugepage migration core") Signed-off-by: Mike Kravetz Reported-by: Li Wang Tested-by: Li Wang Reviewed-by: Naoya Horiguchi Acked-by: Michal Hocko Cc: Cyril Hrubis Cc: Xishi Qiu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ede7e7f5d1ab..6d7296dd11b8 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3856,6 +3856,25 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, page = alloc_huge_page(vma, haddr, 0); if (IS_ERR(page)) { + /* + * Returning error will result in faulting task being + * sent SIGBUS. The hugetlb fault mutex prevents two + * tasks from racing to fault in the same page which + * could result in false unable to allocate errors. + * Page migration does not take the fault mutex, but + * does a clear then write of pte's under page table + * lock. Page fault code could race with migration, + * notice the clear pte and try to allocate a page + * here. Before returning error, get ptl and make + * sure there really is no pte entry. + */ + ptl = huge_pte_lock(h, mm, ptep); + if (!huge_pte_none(huge_ptep_get(ptep))) { + ret = 0; + spin_unlock(ptl); + goto out; + } + spin_unlock(ptl); ret = vmf_error(PTR_ERR(page)); goto out; } From 500bc2c1f48aa6efad9474fdbe0c7cd8d600484c Mon Sep 17 00:00:00 2001 From: Alistair Francis Date: Tue, 13 Aug 2019 16:32:29 -0700 Subject: [PATCH 119/157] riscv: rv32_defconfig: Update the defconfig Update the rv32_defconfig: - Add 'CONFIG_DEVTMPFS_MOUNT=y' to match the RISC-V defconfig - Add CONFIG_HW_RANDOM=y and CONFIG_HW_RANDOM_VIRTIO=y to enable VirtIORNG when running on QEMU Signed-off-by: Alistair Francis Signed-off-by: Paul Walmsley --- arch/riscv/configs/rv32_defconfig | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig index d5449ef805a3..7da93e494445 100644 --- a/arch/riscv/configs/rv32_defconfig +++ b/arch/riscv/configs/rv32_defconfig @@ -34,6 +34,7 @@ CONFIG_PCIEPORTBUS=y CONFIG_PCI_HOST_GENERIC=y CONFIG_PCIE_XILINX=y CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y CONFIG_BLK_DEV_LOOP=y CONFIG_VIRTIO_BLK=y CONFIG_BLK_DEV_SD=y @@ -53,6 +54,8 @@ CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_OF_PLATFORM=y CONFIG_SERIAL_EARLYCON_RISCV_SBI=y CONFIG_HVC_RISCV_SBI=y +CONFIG_HW_RANDOM=y +CONFIG_HW_RANDOM_VIRTIO=y # CONFIG_PTP_1588_CLOCK is not set CONFIG_DRM=y CONFIG_DRM_RADEON=y From d568cb3f935123b4fb42b9029ebcfebc4e4533a2 Mon Sep 17 00:00:00 2001 From: Alistair Francis Date: Tue, 13 Aug 2019 16:32:30 -0700 Subject: [PATCH 120/157] riscv: defconfig: Update the defconfig Update the defconfig: - Add CONFIG_HW_RANDOM=y and CONFIG_HW_RANDOM_VIRTIO=y to enable VirtIORNG when running on QEMU Signed-off-by: Alistair Francis Signed-off-by: Paul Walmsley --- arch/riscv/configs/defconfig | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index 93205c0bf71d..3efff552a261 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -54,6 +54,8 @@ CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_OF_PLATFORM=y CONFIG_SERIAL_EARLYCON_RISCV_SBI=y CONFIG_HVC_RISCV_SBI=y +CONFIG_HW_RANDOM=y +CONFIG_HW_RANDOM_VIRTIO=y CONFIG_SPI=y CONFIG_SPI_SIFIVE=y # CONFIG_PTP_1588_CLOCK is not set From 401714d9534aad8c24196b32600da683116bbe09 Mon Sep 17 00:00:00 2001 From: Hui Wang Date: Wed, 14 Aug 2019 12:09:07 +0800 Subject: [PATCH 121/157] ALSA: hda - Let all conexant codec enter D3 when rebooting We have 3 new lenovo laptops which have conexant codec 0x14f11f86, these 3 laptops also have the noise issue when rebooting, after letting the codec enter D3 before rebooting or poweroff, the noise disappers. Instead of adding a new ID again in the reboot_notify(), let us make this function apply to all conexant codec. In theory make codec enter D3 before rebooting or poweroff is harmless, and I tested this change on a couple of other Lenovo laptops which have different conexant codecs, there is no side effect so far. Cc: stable@vger.kernel.org Signed-off-by: Hui Wang Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_conexant.c | 9 --------- 1 file changed, 9 deletions(-) diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index f299f137eaea..93a303676aea 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -163,15 +163,6 @@ static void cx_auto_reboot_notify(struct hda_codec *codec) { struct conexant_spec *spec = codec->spec; - switch (codec->core.vendor_id) { - case 0x14f12008: /* CX8200 */ - case 0x14f150f2: /* CX20722 */ - case 0x14f150f4: /* CX20724 */ - break; - default: - return; - } - /* Turn the problematic codec into D3 to avoid spurious noises from the internal speaker during (and after) reboot */ cx_auto_turn_eapd(codec, spec->num_eapds, spec->eapds, false); From 871b9066027702e6e6589da0e1edd3b7dede7205 Mon Sep 17 00:00:00 2001 From: Hui Wang Date: Wed, 14 Aug 2019 12:09:08 +0800 Subject: [PATCH 122/157] ALSA: hda - Add a generic reboot_notify Make codec enter D3 before rebooting or poweroff can fix the noise issue on some laptops. And in theory it is harmless for all codecs to enter D3 before rebooting or poweroff, let us add a generic reboot_notify, then realtek and conexant drivers can call this function. Cc: stable@vger.kernel.org Signed-off-by: Hui Wang Signed-off-by: Takashi Iwai --- sound/pci/hda/hda_generic.c | 19 +++++++++++++++++++ sound/pci/hda/hda_generic.h | 1 + sound/pci/hda/patch_conexant.c | 6 +----- sound/pci/hda/patch_realtek.c | 11 +---------- 4 files changed, 22 insertions(+), 15 deletions(-) diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index 8f2beb1f3ae4..5bf24fb819d2 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -6051,6 +6051,24 @@ void snd_hda_gen_free(struct hda_codec *codec) } EXPORT_SYMBOL_GPL(snd_hda_gen_free); +/** + * snd_hda_gen_reboot_notify - Make codec enter D3 before rebooting + * @codec: the HDA codec + * + * This can be put as patch_ops reboot_notify function. + */ +void snd_hda_gen_reboot_notify(struct hda_codec *codec) +{ + /* Make the codec enter D3 to avoid spurious noises from the internal + * speaker during (and after) reboot + */ + snd_hda_codec_set_power_to_all(codec, codec->core.afg, AC_PWRST_D3); + snd_hda_codec_write(codec, codec->core.afg, 0, + AC_VERB_SET_POWER_STATE, AC_PWRST_D3); + msleep(10); +} +EXPORT_SYMBOL_GPL(snd_hda_gen_reboot_notify); + #ifdef CONFIG_PM /** * snd_hda_gen_check_power_status - check the loopback power save state @@ -6078,6 +6096,7 @@ static const struct hda_codec_ops generic_patch_ops = { .init = snd_hda_gen_init, .free = snd_hda_gen_free, .unsol_event = snd_hda_jack_unsol_event, + .reboot_notify = snd_hda_gen_reboot_notify, #ifdef CONFIG_PM .check_power_status = snd_hda_gen_check_power_status, #endif diff --git a/sound/pci/hda/hda_generic.h b/sound/pci/hda/hda_generic.h index 35a670a71c42..5f199dcb0d18 100644 --- a/sound/pci/hda/hda_generic.h +++ b/sound/pci/hda/hda_generic.h @@ -332,6 +332,7 @@ int snd_hda_gen_parse_auto_config(struct hda_codec *codec, struct auto_pin_cfg *cfg); int snd_hda_gen_build_controls(struct hda_codec *codec); int snd_hda_gen_build_pcms(struct hda_codec *codec); +void snd_hda_gen_reboot_notify(struct hda_codec *codec); /* standard jack event callbacks */ void snd_hda_gen_hp_automute(struct hda_codec *codec, diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index 93a303676aea..14298ef45b21 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -166,11 +166,7 @@ static void cx_auto_reboot_notify(struct hda_codec *codec) /* Turn the problematic codec into D3 to avoid spurious noises from the internal speaker during (and after) reboot */ cx_auto_turn_eapd(codec, spec->num_eapds, spec->eapds, false); - - snd_hda_codec_set_power_to_all(codec, codec->core.afg, AC_PWRST_D3); - snd_hda_codec_write(codec, codec->core.afg, 0, - AC_VERB_SET_POWER_STATE, AC_PWRST_D3); - msleep(10); + snd_hda_gen_reboot_notify(codec); } static void cx_auto_free(struct hda_codec *codec) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 8aaf1d9c55cf..e333b3e30e31 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -869,15 +869,6 @@ static void alc_reboot_notify(struct hda_codec *codec) alc_shutup(codec); } -/* power down codec to D3 at reboot/shutdown; set as reboot_notify ops */ -static void alc_d3_at_reboot(struct hda_codec *codec) -{ - snd_hda_codec_set_power_to_all(codec, codec->core.afg, AC_PWRST_D3); - snd_hda_codec_write(codec, codec->core.afg, 0, - AC_VERB_SET_POWER_STATE, AC_PWRST_D3); - msleep(10); -} - #define alc_free snd_hda_gen_free #ifdef CONFIG_PM @@ -5152,7 +5143,7 @@ static void alc_fixup_tpt440_dock(struct hda_codec *codec, struct alc_spec *spec = codec->spec; if (action == HDA_FIXUP_ACT_PRE_PROBE) { - spec->reboot_notify = alc_d3_at_reboot; /* reduce noise */ + spec->reboot_notify = snd_hda_gen_reboot_notify; /* reduce noise */ spec->parse_flags = HDA_PINCFG_NO_HP_FIXUP; codec->power_save_node = 0; /* avoid click noises */ snd_hda_apply_pincfgs(codec, pincfgs); From e8c220fac415d9f4a994b0c2871b835feac1eb4e Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Thu, 8 Aug 2019 18:01:36 -0300 Subject: [PATCH 123/157] Revert "i2c: imx: improve the error handling in i2c_imx_dma_request()" Since commit e1ab9a468e3b ("i2c: imx: improve the error handling in i2c_imx_dma_request()") when booting with the DMA driver as module (such as CONFIG_FSL_EDMA=m) the following endless clk warnings are seen: [ 153.077831] ------------[ cut here ]------------ [ 153.082528] WARNING: CPU: 0 PID: 15 at drivers/clk/clk.c:924 clk_core_disable_lock+0x18/0x24 [ 153.093077] i2c0 already disabled [ 153.096416] Modules linked in: [ 153.099521] CPU: 0 PID: 15 Comm: kworker/0:1 Tainted: G W 5.2.0+ #321 [ 153.107290] Hardware name: Freescale Vybrid VF5xx/VF6xx (Device Tree) [ 153.113772] Workqueue: events deferred_probe_work_func [ 153.118979] [] (unwind_backtrace) from [] (show_stack+0x10/0x14) [ 153.126778] [] (show_stack) from [] (dump_stack+0x9c/0xd4) [ 153.134051] [] (dump_stack) from [] (__warn+0xf8/0x124) [ 153.141056] [] (__warn) from [] (warn_slowpath_fmt+0x38/0x48) [ 153.148580] [] (warn_slowpath_fmt) from [] (clk_core_disable_lock+0x18/0x24) [ 153.157413] [] (clk_core_disable_lock) from [] (i2c_imx_probe+0x554/0x6ec) [ 153.166076] [] (i2c_imx_probe) from [] (platform_drv_probe+0x48/0x98) [ 153.174297] [] (platform_drv_probe) from [] (really_probe+0x1d8/0x2c0) [ 153.182605] [] (really_probe) from [] (driver_probe_device+0x5c/0x174) [ 153.190909] [] (driver_probe_device) from [] (bus_for_each_drv+0x44/0x8c) [ 153.199480] [] (bus_for_each_drv) from [] (__device_attach+0xa0/0x108) [ 153.207782] [] (__device_attach) from [] (bus_probe_device+0x88/0x90) [ 153.215999] [] (bus_probe_device) from [] (deferred_probe_work_func+0x60/0x90) [ 153.225003] [] (deferred_probe_work_func) from [] (process_one_work+0x204/0x634) [ 153.234178] [] (process_one_work) from [] (worker_thread+0x20/0x484) [ 153.242315] [] (worker_thread) from [] (kthread+0x118/0x150) [ 153.249758] [] (kthread) from [] (ret_from_fork+0x14/0x20) [ 153.257006] Exception stack(0xdde43fb0 to 0xdde43ff8) [ 153.262095] 3fa0: 00000000 00000000 00000000 00000000 [ 153.270306] 3fc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 [ 153.278520] 3fe0: 00000000 00000000 00000000 00000000 00000013 00000000 [ 153.285159] irq event stamp: 3323022 [ 153.288787] hardirqs last enabled at (3323021): [] _raw_spin_unlock_irq+0x24/0x2c [ 153.297261] hardirqs last disabled at (3323022): [] clk_enable_lock+0x10/0x124 [ 153.305392] softirqs last enabled at (3322092): [] __do_softirq+0x344/0x540 [ 153.313352] softirqs last disabled at (3322081): [] irq_exit+0x10c/0x128 [ 153.320946] ---[ end trace a506731ccd9bd703 ]--- This endless clk warnings behaviour is well explained by Andrey Smirnov: "Allocating DMA after registering I2C adapter can lead to infinite probing loop, for example, consider the following scenario: 1. i2c_imx_probe() is called and successfully registers an I2C adapter via i2c_add_numbered_adapter() 2. As a part of i2c_add_numbered_adapter() new I2C slave devices are added from DT which results in a call to driver_deferred_probe_trigger() 3. i2c_imx_probe() continues and calls i2c_imx_dma_request() which due to lack of proper DMA driver returns -EPROBE_DEFER 4. i2c_imx_probe() fails, removes I2C adapter and returns -EPROBE_DEFER, which places it into deferred probe list 5. Deferred probe work triggered in #2 above kicks in and calls i2c_imx_probe() again thus bringing us to step #1" So revert commit e1ab9a468e3b ("i2c: imx: improve the error handling in i2c_imx_dma_request()") and restore the old behaviour, in order to avoid regressions on existing setups. Cc: Reported-by: Andrey Smirnov Reported-by: Russell King Fixes: e1ab9a468e3b ("i2c: imx: improve the error handling in i2c_imx_dma_request()") Signed-off-by: Fabio Estevam Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-imx.c | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index b1b8b938d7f4..15f6cde6452f 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -273,8 +273,8 @@ static inline unsigned char imx_i2c_read_reg(struct imx_i2c_struct *i2c_imx, } /* Functions for DMA support */ -static int i2c_imx_dma_request(struct imx_i2c_struct *i2c_imx, - dma_addr_t phy_addr) +static void i2c_imx_dma_request(struct imx_i2c_struct *i2c_imx, + dma_addr_t phy_addr) { struct imx_i2c_dma *dma; struct dma_slave_config dma_sconfig; @@ -283,7 +283,7 @@ static int i2c_imx_dma_request(struct imx_i2c_struct *i2c_imx, dma = devm_kzalloc(dev, sizeof(*dma), GFP_KERNEL); if (!dma) - return -ENOMEM; + return; dma->chan_tx = dma_request_chan(dev, "tx"); if (IS_ERR(dma->chan_tx)) { @@ -328,7 +328,7 @@ static int i2c_imx_dma_request(struct imx_i2c_struct *i2c_imx, dev_info(dev, "using %s (tx) and %s (rx) for DMA transfers\n", dma_chan_name(dma->chan_tx), dma_chan_name(dma->chan_rx)); - return 0; + return; fail_rx: dma_release_channel(dma->chan_rx); @@ -336,8 +336,6 @@ static int i2c_imx_dma_request(struct imx_i2c_struct *i2c_imx, dma_release_channel(dma->chan_tx); fail_al: devm_kfree(dev, dma); - /* return successfully if there is no dma support */ - return ret == -ENODEV ? 0 : ret; } static void i2c_imx_dma_callback(void *arg) @@ -1165,17 +1163,13 @@ static int i2c_imx_probe(struct platform_device *pdev) dev_dbg(&i2c_imx->adapter.dev, "device resources: %pR\n", res); dev_dbg(&i2c_imx->adapter.dev, "adapter name: \"%s\"\n", i2c_imx->adapter.name); + dev_info(&i2c_imx->adapter.dev, "IMX I2C adapter registered\n"); /* Init DMA config if supported */ - ret = i2c_imx_dma_request(i2c_imx, phy_addr); - if (ret < 0) - goto del_adapter; + i2c_imx_dma_request(i2c_imx, phy_addr); - dev_info(&i2c_imx->adapter.dev, "IMX I2C adapter registered\n"); return 0; /* Return OK */ -del_adapter: - i2c_del_adapter(&i2c_imx->adapter); clk_notifier_unregister: clk_notifier_unregister(i2c_imx->clk, &i2c_imx->clk_change_nb); rpm_disable: From 8fc3ae3b109d17157102f0abf9c8fb1e16bf810a Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Mon, 12 Aug 2019 07:08:17 +0200 Subject: [PATCH 124/157] MAINTAINERS: i2c-imx: take over maintainership I would like to maintain the i2c-imx driver. Since I work with different i.MX variants and have access to the hardware, I can spend some time on the reviewing of this driver. Signed-off-by: Oleksij Rempel Signed-off-by: Wolfram Sang --- MAINTAINERS | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index e81e60bd7c26..ddc1cf5cb0b9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6441,6 +6441,14 @@ S: Maintained F: drivers/perf/fsl_imx8_ddr_perf.c F: Documentation/devicetree/bindings/perf/fsl-imx-ddr.txt +FREESCALE IMX I2C DRIVER +M: Oleksij Rempel +R: Pengutronix Kernel Team +L: linux-i2c@vger.kernel.org +S: Maintained +F: drivers/i2c/busses/i2c-imx.c +F: Documentation/devicetree/bindings/i2c/i2c-imx.txt + FREESCALE IMX LPI2C DRIVER M: Dong Aisheng L: linux-i2c@vger.kernel.org From 7b814d852af6944657c2961039f404c4490771c0 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Thu, 8 Aug 2019 21:39:10 +0200 Subject: [PATCH 125/157] i2c: rcar: avoid race when unregistering slave client After we disabled interrupts, there might still be an active one running. Sync before clearing the pointer to the slave device. Fixes: de20d1857dd6 ("i2c: rcar: add slave support") Reported-by: Krzysztof Adamski Signed-off-by: Wolfram Sang Reviewed-by: Krzysztof Adamski Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-rcar.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c index d39a4606f72d..531c01100b56 100644 --- a/drivers/i2c/busses/i2c-rcar.c +++ b/drivers/i2c/busses/i2c-rcar.c @@ -139,6 +139,7 @@ struct rcar_i2c_priv { enum dma_data_direction dma_direction; struct reset_control *rstc; + int irq; }; #define rcar_i2c_priv_to_dev(p) ((p)->adap.dev.parent) @@ -861,9 +862,11 @@ static int rcar_unreg_slave(struct i2c_client *slave) WARN_ON(!priv->slave); + /* disable irqs and ensure none is running before clearing ptr */ rcar_i2c_write(priv, ICSIER, 0); rcar_i2c_write(priv, ICSCR, 0); + synchronize_irq(priv->irq); priv->slave = NULL; pm_runtime_put(rcar_i2c_priv_to_dev(priv)); @@ -918,7 +921,7 @@ static int rcar_i2c_probe(struct platform_device *pdev) struct i2c_adapter *adap; struct device *dev = &pdev->dev; struct i2c_timings i2c_t; - int irq, ret; + int ret; /* Otherwise logic will break because some bytes must always use PIO */ BUILD_BUG_ON_MSG(RCAR_MIN_DMA_LEN < 3, "Invalid min DMA length"); @@ -984,10 +987,10 @@ static int rcar_i2c_probe(struct platform_device *pdev) pm_runtime_put(dev); - irq = platform_get_irq(pdev, 0); - ret = devm_request_irq(dev, irq, rcar_i2c_irq, 0, dev_name(dev), priv); + priv->irq = platform_get_irq(pdev, 0); + ret = devm_request_irq(dev, priv->irq, rcar_i2c_irq, 0, dev_name(dev), priv); if (ret < 0) { - dev_err(dev, "cannot get irq %d\n", irq); + dev_err(dev, "cannot get irq %d\n", priv->irq); goto out_pm_disable; } From d7437fc0d8291181debe032671a289b6bd93f46f Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Thu, 8 Aug 2019 21:54:17 +0200 Subject: [PATCH 126/157] i2c: emev2: avoid race when unregistering slave client After we disabled interrupts, there might still be an active one running. Sync before clearing the pointer to the slave device. Fixes: c31d0a00021d ("i2c: emev2: add slave support") Reported-by: Krzysztof Adamski Signed-off-by: Wolfram Sang Reviewed-by: Krzysztof Adamski Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-emev2.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/drivers/i2c/busses/i2c-emev2.c b/drivers/i2c/busses/i2c-emev2.c index 35b302d983e0..959d4912ec0d 100644 --- a/drivers/i2c/busses/i2c-emev2.c +++ b/drivers/i2c/busses/i2c-emev2.c @@ -69,6 +69,7 @@ struct em_i2c_device { struct completion msg_done; struct clk *sclk; struct i2c_client *slave; + int irq; }; static inline void em_clear_set_bit(struct em_i2c_device *priv, u8 clear, u8 set, u8 reg) @@ -339,6 +340,12 @@ static int em_i2c_unreg_slave(struct i2c_client *slave) writeb(0, priv->base + I2C_OFS_SVA0); + /* + * Wait for interrupt to finish. New slave irqs cannot happen because we + * cleared the slave address and, thus, only extension codes will be + * detected which do not use the slave ptr. + */ + synchronize_irq(priv->irq); priv->slave = NULL; return 0; @@ -355,7 +362,7 @@ static int em_i2c_probe(struct platform_device *pdev) { struct em_i2c_device *priv; struct resource *r; - int irq, ret; + int ret; priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); if (!priv) @@ -390,8 +397,8 @@ static int em_i2c_probe(struct platform_device *pdev) em_i2c_reset(&priv->adap); - irq = platform_get_irq(pdev, 0); - ret = devm_request_irq(&pdev->dev, irq, em_i2c_irq_handler, 0, + priv->irq = platform_get_irq(pdev, 0); + ret = devm_request_irq(&pdev->dev, priv->irq, em_i2c_irq_handler, 0, "em_i2c", priv); if (ret) goto err_clk; @@ -401,7 +408,8 @@ static int em_i2c_probe(struct platform_device *pdev) if (ret) goto err_clk; - dev_info(&pdev->dev, "Added i2c controller %d, irq %d\n", priv->adap.nr, irq); + dev_info(&pdev->dev, "Added i2c controller %d, irq %d\n", priv->adap.nr, + priv->irq); return 0; From 90865a3dc597bd8463efacb749561095ba70b0aa Mon Sep 17 00:00:00 2001 From: Nishad Kamdar Date: Sat, 3 Aug 2019 19:43:35 +0530 Subject: [PATCH 127/157] i2c: stm32: Use the correct style for SPDX License Identifier This patch corrects the SPDX License Identifier style in header file related to STM32 Driver for I2C hardware bus support. For C header files Documentation/process/license-rules.rst mandates C-like comments (opposed to C source files where C++ style should be used) Changes made by using a script provided by Joe Perches here: https://lkml.org/lkml/2019/2/7/46 Suggested-by: Joe Perches Signed-off-by: Nishad Kamdar Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-stm32.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/i2c/busses/i2c-stm32.h b/drivers/i2c/busses/i2c-stm32.h index 868755f82f88..2c21893905a3 100644 --- a/drivers/i2c/busses/i2c-stm32.h +++ b/drivers/i2c/busses/i2c-stm32.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0 */ /* * i2c-stm32.h * From daac07156b330b18eb5071aec4b3ddca1c377f2c Mon Sep 17 00:00:00 2001 From: Hui Peng Date: Tue, 13 Aug 2019 22:34:04 -0400 Subject: [PATCH 128/157] ALSA: usb-audio: Fix an OOB bug in parse_audio_mixer_unit The `uac_mixer_unit_descriptor` shown as below is read from the device side. In `parse_audio_mixer_unit`, `baSourceID` field is accessed from index 0 to `bNrInPins` - 1, the current implementation assumes that descriptor is always valid (the length of descriptor is no shorter than 5 + `bNrInPins`). If a descriptor read from the device side is invalid, it may trigger out-of-bound memory access. ``` struct uac_mixer_unit_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bDescriptorSubtype; __u8 bUnitID; __u8 bNrInPins; __u8 baSourceID[]; } ``` This patch fixes the bug by add a sanity check on the length of the descriptor. Reported-by: Hui Peng Reported-by: Mathias Payer Cc: Signed-off-by: Hui Peng Signed-off-by: Takashi Iwai --- sound/usb/mixer.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 7498b5191b68..ea487378be17 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -744,6 +744,8 @@ static int uac_mixer_unit_get_channels(struct mixer_build *state, return -EINVAL; if (!desc->bNrInPins) return -EINVAL; + if (desc->bLength < sizeof(*desc) + desc->bNrInPins) + return -EINVAL; switch (state->mixer->protocol) { case UAC_VERSION_1: From 8ac71d7e46b94a4fc8ffc6f1c88004cdf24459e8 Mon Sep 17 00:00:00 2001 From: Vincent Chen Date: Wed, 14 Aug 2019 16:23:52 +0800 Subject: [PATCH 129/157] riscv: Correct the initialized flow of FP register The following two reasons cause FP registers are sometimes not initialized before starting the user program. 1. Currently, the FP context is initialized in flush_thread() function and we expect these initial values to be restored to FP register when doing FP context switch. However, the FP context switch only occurs in switch_to function. Hence, if this process does not be scheduled out and scheduled in before entering the user space, the FP registers have no chance to initialize. 2. In flush_thread(), the state of reg->sstatus.FS inherits from the parent. Hence, the state of reg->sstatus.FS may be dirty. If this process is scheduled out during flush_thread() and initializing the FP register, the fstate_save() in switch_to will corrupt the FP context which has been initialized until flush_thread(). To solve the 1st case, the initialization of the FP register will be completed in start_thread(). It makes sure all FP registers are initialized before starting the user program. For the 2nd case, the state of reg->sstatus.FS in start_thread will be set to SR_FS_OFF to prevent this process from corrupting FP context in doing context save. The FP state is set to SR_FS_INITIAL in start_trhead(). Signed-off-by: Vincent Chen Reviewed-by: Anup Patel Reviewed-by: Christoph Hellwig Fixes: 7db91e57a0acd ("RISC-V: Task implementation") Cc: stable@vger.kernel.org [paul.walmsley@sifive.com: fixed brace alignment issue reported by checkpatch] Signed-off-by: Paul Walmsley --- arch/riscv/include/asm/switch_to.h | 6 ++++++ arch/riscv/kernel/process.c | 11 +++++++++-- 2 files changed, 15 insertions(+), 2 deletions(-) diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h index 853b65ef656d..949d9cd91dec 100644 --- a/arch/riscv/include/asm/switch_to.h +++ b/arch/riscv/include/asm/switch_to.h @@ -19,6 +19,12 @@ static inline void __fstate_clean(struct pt_regs *regs) regs->sstatus |= (regs->sstatus & ~(SR_FS)) | SR_FS_CLEAN; } +static inline void fstate_off(struct task_struct *task, + struct pt_regs *regs) +{ + regs->sstatus = (regs->sstatus & ~SR_FS) | SR_FS_OFF; +} + static inline void fstate_save(struct task_struct *task, struct pt_regs *regs) { diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index f23794bd1e90..fb3a082362eb 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -64,8 +64,14 @@ void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) { regs->sstatus = SR_SPIE; - if (has_fpu) + if (has_fpu) { regs->sstatus |= SR_FS_INITIAL; + /* + * Restore the initial value to the FP register + * before starting the user program. + */ + fstate_restore(current, regs); + } regs->sepc = pc; regs->sp = sp; set_fs(USER_DS); @@ -75,10 +81,11 @@ void flush_thread(void) { #ifdef CONFIG_FPU /* - * Reset FPU context + * Reset FPU state and context * frm: round to nearest, ties to even (IEEE default) * fflags: accrued exceptions cleared */ + fstate_off(current, task_pt_regs(current)); memset(¤t->thread.fstate, 0, sizeof(current->thread.fstate)); #endif } From 69703eb9a8ae28a46cd5bce7d69ceeef6273a104 Mon Sep 17 00:00:00 2001 From: Vincent Chen Date: Wed, 14 Aug 2019 16:23:53 +0800 Subject: [PATCH 130/157] riscv: Make __fstate_clean() work correctly. Make the __fstate_clean() function correctly set the state of sstatus.FS in pt_regs to SR_FS_CLEAN. Fixes: 7db91e57a0acd ("RISC-V: Task implementation") Cc: linux-stable Signed-off-by: Vincent Chen Reviewed-by: Anup Patel Reviewed-by: Christoph Hellwig [paul.walmsley@sifive.com: expanded "Fixes" commit ID] Signed-off-by: Paul Walmsley --- arch/riscv/include/asm/switch_to.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h index 949d9cd91dec..f0227bdce0f0 100644 --- a/arch/riscv/include/asm/switch_to.h +++ b/arch/riscv/include/asm/switch_to.h @@ -16,7 +16,7 @@ extern void __fstate_restore(struct task_struct *restore_from); static inline void __fstate_clean(struct pt_regs *regs) { - regs->sstatus |= (regs->sstatus & ~(SR_FS)) | SR_FS_CLEAN; + regs->sstatus = (regs->sstatus & ~SR_FS) | SR_FS_CLEAN; } static inline void fstate_off(struct task_struct *task, From e1b4ce25dbc93ab0cb8ed0f236a3b9ff7b03802c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Fri, 9 Aug 2019 17:27:21 +0200 Subject: [PATCH 131/157] drm/scheduler: use job count instead of peek MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The spsc_queue_peek function is accessing queue->head which belongs to the consumer thread and shouldn't be accessed by the producer This is fixing a rare race condition when destroying entities. Signed-off-by: Christian König Acked-by: Andrey Grodzovsky Reviewed-by: Monk.liu@amd.com Signed-off-by: Alex Deucher --- drivers/gpu/drm/scheduler/sched_entity.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index 35ddbec1375a..671c90f34ede 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -95,7 +95,7 @@ static bool drm_sched_entity_is_idle(struct drm_sched_entity *entity) rmb(); /* for list_empty to work without lock */ if (list_empty(&entity->list) || - spsc_queue_peek(&entity->job_queue) == NULL) + spsc_queue_count(&entity->job_queue) == 0) return true; return false; @@ -281,7 +281,7 @@ void drm_sched_entity_fini(struct drm_sched_entity *entity) /* Consumption of existing IBs wasn't completed. Forcefully * remove them here. */ - if (spsc_queue_peek(&entity->job_queue)) { + if (spsc_queue_count(&entity->job_queue)) { if (sched) { /* Park the kernel for a moment to make sure it isn't processing * our enity. From 626633425c079742c04f4f2d81c16962b084605c Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 13 Aug 2019 14:47:54 -0600 Subject: [PATCH 132/157] dt-bindings: pinctrl: stm32: Fix 'st,syscfg' schema The proper way to add additional contraints to an existing json-schema is using 'allOf' to reference the base schema. Using just '$ref' doesn't work. Fix this for the 'st,syscfg' property. Cc: Mark Rutland Cc: Maxime Coquelin Cc: Alexandre Torgue Cc: linux-gpio@vger.kernel.org Cc: linux-stm32@st-md-mailman.stormreply.com Cc: linux-arm-kernel@lists.infradead.org Reviewed-by: Linus Walleij Signed-off-by: Rob Herring --- .../devicetree/bindings/pinctrl/st,stm32-pinctrl.yaml | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.yaml index 91d3e78b3395..400df2da018a 100644 --- a/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.yaml @@ -37,7 +37,8 @@ properties: hwlocks: true st,syscfg: - $ref: "/schemas/types.yaml#/definitions/phandle-array" + allOf: + - $ref: "/schemas/types.yaml#/definitions/phandle-array" description: Should be phandle/offset/mask items: - description: Phandle to the syscon node which includes IRQ mux selection. From 83f82d7a42583e93d0f0dde3d61ed10f75c0f4d8 Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Wed, 7 Aug 2019 15:22:31 +0200 Subject: [PATCH 133/157] of: irq: fix a trivial typo in a doc comment Diverged from what the code does with commit 530210c7814e ("of/irq: Replace of_irq with of_phandle_args"). Signed-off-by: Lubomir Rintel Signed-off-by: Rob Herring --- drivers/of/irq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/of/irq.c b/drivers/of/irq.c index 7f84bb4903ca..a296eaf52a5b 100644 --- a/drivers/of/irq.c +++ b/drivers/of/irq.c @@ -277,7 +277,7 @@ EXPORT_SYMBOL_GPL(of_irq_parse_raw); * of_irq_parse_one - Resolve an interrupt for a device * @device: the device whose interrupt is to be resolved * @index: index of the interrupt to resolve - * @out_irq: structure of_irq filled by this function + * @out_irq: structure of_phandle_args filled by this function * * This function resolves an interrupt for a node by walking the interrupt tree, * finding which interrupt controller node it is attached to, and returning the From 05b439711f6ff8700e8660f97a1179650778b9cb Mon Sep 17 00:00:00 2001 From: "Y.C. Chen" Date: Wed, 11 Apr 2018 09:27:39 +0800 Subject: [PATCH 134/157] drm/ast: Fixed reboot test may cause system hanged There is another thread still access standard VGA I/O while loading drm driver. Disable standard VGA I/O decode to avoid this issue. Signed-off-by: Y.C. Chen Reviewed-by: Benjamin Herrenschmidt Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/1523410059-18415-1-git-send-email-yc_chen@aspeedtech.com --- drivers/gpu/drm/ast/ast_main.c | 5 ++++- drivers/gpu/drm/ast/ast_mode.c | 2 +- drivers/gpu/drm/ast/ast_post.c | 2 +- 3 files changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c index 4c7e31cb45ff..a5d1494a3dc4 100644 --- a/drivers/gpu/drm/ast/ast_main.c +++ b/drivers/gpu/drm/ast/ast_main.c @@ -131,8 +131,8 @@ static int ast_detect_chip(struct drm_device *dev, bool *need_post) /* Enable extended register access */ - ast_enable_mmio(dev); ast_open_key(ast); + ast_enable_mmio(dev); /* Find out whether P2A works or whether to use device-tree */ ast_detect_config_mode(dev, &scu_rev); @@ -576,6 +576,9 @@ void ast_driver_unload(struct drm_device *dev) { struct ast_private *ast = dev->dev_private; + /* enable standard VGA decode */ + ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0xa1, 0x04); + ast_release_firmware(dev); kfree(ast->dp501_fw_addr); ast_mode_fini(dev); diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c index ffccbef962a4..a1cb020e07e5 100644 --- a/drivers/gpu/drm/ast/ast_mode.c +++ b/drivers/gpu/drm/ast/ast_mode.c @@ -604,7 +604,7 @@ static int ast_crtc_mode_set(struct drm_crtc *crtc, return -EINVAL; ast_open_key(ast); - ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa1, 0xff, 0x04); + ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0xa1, 0x06); ast_set_std_reg(crtc, adjusted_mode, &vbios_mode); ast_set_crtc_reg(crtc, adjusted_mode, &vbios_mode); diff --git a/drivers/gpu/drm/ast/ast_post.c b/drivers/gpu/drm/ast/ast_post.c index f7d421359d56..c1d1ac51d1c2 100644 --- a/drivers/gpu/drm/ast/ast_post.c +++ b/drivers/gpu/drm/ast/ast_post.c @@ -46,7 +46,7 @@ void ast_enable_mmio(struct drm_device *dev) { struct ast_private *ast = dev->dev_private; - ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa1, 0xff, 0x04); + ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0xa1, 0x06); } From db1231ddc04682f60d56ff42447f13099c6c4a4c Mon Sep 17 00:00:00 2001 From: Lyude Paul Date: Thu, 8 Aug 2019 20:53:05 -0400 Subject: [PATCH 135/157] drm/nouveau: Only recalculate PBN/VCPI on mode/connector changes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit I -thought- I had fixed this entirely, but it looks like that I didn't test this thoroughly enough as we apparently still make one big mistake with nv50_msto_atomic_check() - we don't handle the following scenario: * CRTC #1 has n VCPI allocated to it, is attached to connector DP-4 which is attached to encoder #1. enabled=y active=n * CRTC #1 is changed from DP-4 to DP-5, causing: * DP-4 crtc=#1→NULL (VCPI n→0) * DP-5 crtc=NULL→#1 * CRTC #1 steals encoder #1 back from DP-4 and gives it to DP-5 * CRTC #1 maintains the same mode as before, just with a different connector * mode_changed=n connectors_changed=y (we _SHOULD_ do VCPI 0→n here, but don't) Once the above scenario is repeated once, we'll attempt freeing VCPI from the connector that we didn't allocate due to the connectors changing, but the mode staying the same. Sigh. Since nv50_msto_atomic_check() has broken a few times now, let's rethink things a bit to be more careful: limit both VCPI/PBN allocations to mode_changed || connectors_changed, since neither VCPI or PBN should ever need to change outside of routing and mode changes. Changes since v1: * Fix accidental reversal of clock and bpp arguments in drm_dp_calc_pbn_mode() - William Lewis Signed-off-by: Lyude Paul Reported-by: Bohdan Milar Tested-by: Bohdan Milar Fixes: 232c9eec417a ("drm/nouveau: Use atomic VCPI helpers for MST") References: 412e85b60531 ("drm/nouveau: Only release VCPI slots on mode changes") Cc: Lyude Paul Cc: Ben Skeggs Cc: Daniel Vetter Cc: David Airlie Cc: Jerry Zuo Cc: Harry Wentland Cc: Juston Li Cc: Laurent Pinchart Cc: Karol Herbst Cc: Ilia Mirkin Cc: # v5.1+ Acked-by: Ben Skeggs Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20190809005307.18391-1-lyude@redhat.com --- drivers/gpu/drm/nouveau/dispnv50/disp.c | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 126703816794..5c36c75232e6 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -771,16 +771,20 @@ nv50_msto_atomic_check(struct drm_encoder *encoder, struct nv50_head_atom *asyh = nv50_head_atom(crtc_state); int slots; - /* When restoring duplicated states, we need to make sure that the - * bw remains the same and avoid recalculating it, as the connector's - * bpc may have changed after the state was duplicated - */ - if (!state->duplicated) - asyh->dp.pbn = - drm_dp_calc_pbn_mode(crtc_state->adjusted_mode.clock, - connector->display_info.bpc * 3); + if (crtc_state->mode_changed || crtc_state->connectors_changed) { + /* + * When restoring duplicated states, we need to make sure that + * the bw remains the same and avoid recalculating it, as the + * connector's bpc may have changed after the state was + * duplicated + */ + if (!state->duplicated) { + const int bpp = connector->display_info.bpc * 3; + const int clock = crtc_state->adjusted_mode.clock; + + asyh->dp.pbn = drm_dp_calc_pbn_mode(clock, bpp); + } - if (crtc_state->mode_changed) { slots = drm_dp_atomic_find_vcpi_slots(state, &mstm->mgr, mstc->port, asyh->dp.pbn); From 5ed1c835ed8b522ce25071cc2d56a9a09bd5b59e Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Wed, 14 Aug 2019 16:40:30 -0700 Subject: [PATCH 136/157] MAINTAINERS, x86/CPU: Tony Luck will maintain asm/intel-family.h There are a few different subsystems in the kernel that depend on model specific behaviour (perf, EDAC, power, ...). Easier for just one person to have the task to get new model numbers included instead of having these groups trip over each other to do it. [ bp: s/Cpu/CPU/ and add x86@kernel.org so that it gets CCed too as FYI. ] Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov Acked-by: Thomas Gleixner Cc: Dave Hansen Cc: x86-ml Link: https://lkml.kernel.org/r/20190814234030.30817-1-tony.luck@intel.com --- MAINTAINERS | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index e81e60bd7c26..f3a78403b47f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8064,6 +8064,13 @@ T: git git://git.code.sf.net/p/intel-sas/isci S: Supported F: drivers/scsi/isci/ +INTEL CPU family model numbers +M: Tony Luck +M: x86@kernel.org +L: linux-kernel@vger.kernel.org +S: Supported +F: arch/x86/include/asm/intel-family.h + INTEL DRM DRIVERS (excluding Poulsbo, Moorestown and derivative chipsets) M: Jani Nikula M: Joonas Lahtinen From 6caf0be40a707689e8ff8824fdb96ef77685b1ba Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Thu, 15 Aug 2019 01:26:02 -0700 Subject: [PATCH 137/157] USB: serial: option: Add Motorola modem UARTs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On Motorola Mapphone devices such as Droid 4 there are five USB ports that do not use the same layout as Gobi 1K/2K/etc devices listed in qcserial.c. So we should use qcaux.c or option.c as noted by Dan Williams . As the Motorola USB serial ports have an interrupt endpoint as shown with lsusb -v, we should use option.c instead of qcaux.c as pointed out by Johan Hovold . The ff/ff/ff interfaces seem to always be UARTs on Motorola devices. For the other interfaces, class 0x0a (CDC Data) should not in general be added as they are typically part of a multi-interface function as noted earlier by Bjørn Mork . However, looking at the Motorola mapphone kernel code, the mdm6600 0x0a class is only used for flashing the modem firmware, and there are no other interfaces. So I've added that too with more details below as it works just fine. The ttyUSB ports on Droid 4 are: ttyUSB0 DIAG, CQDM-capable ttyUSB1 MUX or NMEA, no response ttyUSB2 MUX or NMEA, no response ttyUSB3 TCMD ttyUSB4 AT-capable The ttyUSB0 is detected as QCDM capable by ModemManager. I think it's only used for debugging with ModemManager --debug for sending custom AT commands though. ModemManager already can manage data connection using the USB QMI ports that are already handled by the qmi_wwan.c driver. To enable the MUX or NMEA ports, it seems that something needs to be done additionally to enable them, maybe via the DIAG or TCMD port. It might be just a NVRAM setting somewhere, but I have no idea what NVRAM settings may need changing for that. The TCMD port seems to be a Motorola custom protocol for testing the modem and to configure it's NVRAM and seems to work just fine based on a quick test with a minimal tcmdrw tool I wrote. The voice modem AT-capable port seems to provide only partial support, and no PM support compared to the TS 27.010 based UART wired directly to the modem. The UARTs added with this change are the same product IDs as the Motorola Mapphone Android Linux kernel mdm6600_id_table. I don't have any mdm9600 based devices, so I have only tested these on mdm6600 based droid 4. Then for the class 0x0a (CDC Data) mode, the Motorola Mapphone Android Linux kernel driver moto_flashqsc.c just seems to change the port->bulk_out_size to 8K from the default. And is only used for flashing the modem firmware it seems. I've verified that flashing the modem with signed firmware works just fine with the option driver after manually toggling the GPIO pins, so I've added droid 4 modem flashing mode to the option driver. I've not added the other devices listed in moto_flashqsc.c in case they really need different port->bulk_out_size. Those can be added as they get tested to work for flashing the modem. After this patch the output of /sys/kernel/debug/usb/devices has the following for normal 22b8:2a70 mode including the related qmi_wwan interfaces: T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 2 Spd=12 MxCh= 0 D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=22b8 ProdID=2a70 Rev= 0.00 S: Manufacturer=Motorola, Incorporated S: Product=Flash MZ600 C:* #Ifs= 9 Cfg#= 1 Atr=e0 MxPwr=500mA I:* If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option E: Ad=81(I) Atr=02(Bulk) MxPS= 64 Ivl=0ms E: Ad=01(O) Atr=02(Bulk) MxPS= 64 Ivl=0ms I:* If#= 1 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option E: Ad=82(I) Atr=02(Bulk) MxPS= 64 Ivl=0ms E: Ad=02(O) Atr=02(Bulk) MxPS= 64 Ivl=0ms I:* If#= 2 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option E: Ad=83(I) Atr=02(Bulk) MxPS= 64 Ivl=0ms E: Ad=03(O) Atr=02(Bulk) MxPS= 64 Ivl=0ms I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option E: Ad=84(I) Atr=02(Bulk) MxPS= 64 Ivl=0ms E: Ad=04(O) Atr=02(Bulk) MxPS= 64 Ivl=0ms I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option E: Ad=85(I) Atr=03(Int.) MxPS= 64 Ivl=5ms E: Ad=86(I) Atr=02(Bulk) MxPS= 64 Ivl=0ms E: Ad=05(O) Atr=02(Bulk) MxPS= 64 Ivl=0ms I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=fb Prot=ff Driver=qmi_wwan E: Ad=87(I) Atr=03(Int.) MxPS= 64 Ivl=5ms E: Ad=88(I) Atr=02(Bulk) MxPS= 64 Ivl=0ms E: Ad=06(O) Atr=02(Bulk) MxPS= 64 Ivl=0ms I:* If#= 6 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=fb Prot=ff Driver=qmi_wwan E: Ad=89(I) Atr=03(Int.) MxPS= 64 Ivl=5ms E: Ad=8a(I) Atr=02(Bulk) MxPS= 64 Ivl=0ms E: Ad=07(O) Atr=02(Bulk) MxPS= 64 Ivl=0ms I:* If#= 7 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=fb Prot=ff Driver=qmi_wwan E: Ad=8b(I) Atr=03(Int.) MxPS= 64 Ivl=5ms E: Ad=8c(I) Atr=02(Bulk) MxPS= 64 Ivl=0ms E: Ad=08(O) Atr=02(Bulk) MxPS= 64 Ivl=0ms I:* If#= 8 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=fb Prot=ff Driver=qmi_wwan E: Ad=8d(I) Atr=03(Int.) MxPS= 64 Ivl=5ms E: Ad=8e(I) Atr=02(Bulk) MxPS= 64 Ivl=0ms E: Ad=09(O) Atr=02(Bulk) MxPS= 64 Ivl=0ms In 22b8:900e "qc_dload" mode the device shows up as: T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 2 Spd=12 MxCh= 0 D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=22b8 ProdID=900e Rev= 0.00 S: Manufacturer=Motorola, Incorporated S: Product=Flash MZ600 C:* #Ifs= 1 Cfg#= 1 Atr=e0 MxPwr=500mA I:* If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option E: Ad=81(I) Atr=02(Bulk) MxPS= 64 Ivl=0ms E: Ad=01(O) Atr=02(Bulk) MxPS= 64 Ivl=0ms And in 22b8:4281 "ram_downloader" mode the device shows up as: T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 2 Spd=12 MxCh= 0 D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=22b8 ProdID=4281 Rev= 0.00 S: Manufacturer=Motorola, Incorporated S: Product=Flash MZ600 C:* #Ifs= 1 Cfg#= 1 Atr=e0 MxPwr=500mA I:* If#= 0 Alt= 0 #EPs= 2 Cls=0a(data ) Sub=00 Prot=fc Driver=option E: Ad=81(I) Atr=02(Bulk) MxPS= 64 Ivl=0ms E: Ad=01(O) Atr=02(Bulk) MxPS= 64 Ivl=0ms Cc: Bjørn Mork Cc: Dan Williams Cc: Lars Melin Cc: Marcel Partap Cc: Merlijn Wajer Cc: Michael Scott Cc: NeKit Cc: Pavel Machek Cc: Sebastian Reichel Tested-by: Pavel Machek Signed-off-by: Tony Lindgren 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 f2c19660ed16..546d7f610a24 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -968,6 +968,11 @@ static const struct usb_device_id option_ids[] = { { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x7B) }, { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x7C) }, + /* Motorola devices */ + { USB_DEVICE_AND_INTERFACE_INFO(0x22b8, 0x2a70, 0xff, 0xff, 0xff) }, /* mdm6600 */ + { USB_DEVICE_AND_INTERFACE_INFO(0x22b8, 0x2e0a, 0xff, 0xff, 0xff) }, /* mdm9600 */ + { USB_DEVICE_AND_INTERFACE_INFO(0x22b8, 0x4281, 0x0a, 0x00, 0xfc) }, /* mdm ram dl */ + { USB_DEVICE_AND_INTERFACE_INFO(0x22b8, 0x900e, 0xff, 0xff, 0xff) }, /* mdm qc dl */ { USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_V640) }, { USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_V620) }, From e5d8badf37e6b547842f2fcde10361b29e08bd36 Mon Sep 17 00:00:00 2001 From: Bob Ham Date: Wed, 24 Jul 2019 07:52:26 -0700 Subject: [PATCH 138/157] USB: serial: option: add the BroadMobi BM818 card Add a VID:PID for the BroadMobi BM818 M.2 card T: Bus=01 Lev=03 Prnt=40 Port=03 Cnt=01 Dev#= 44 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=2020 ProdID=2060 Rev=00.00 S: Manufacturer=Qualcomm, Incorporated S: Product=Qualcomm CDMA Technologies MSM C: #Ifs= 5 Cfg#= 1 Atr=e0 MxPwr=500mA I: If#=0x0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) I: If#=0x1 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) I: If#=0x2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) I: If#=0x3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=fe Prot=ff Driver=(none) I: If#=0x4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) Signed-off-by: Bob Ham Signed-off-by: Angus Ainslie (Purism) Cc: stable [ johan: use USB_DEVICE_INTERFACE_CLASS() ] Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 546d7f610a24..38e920ac7f82 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1965,6 +1965,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x7e11, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/A3 */ { USB_DEVICE_INTERFACE_CLASS(0x2020, 0x2031, 0xff), /* Olicard 600 */ .driver_info = RSVD(4) }, + { USB_DEVICE_INTERFACE_CLASS(0x2020, 0x2060, 0xff), /* BroadMobi BM818 */ + .driver_info = RSVD(4) }, { USB_DEVICE_INTERFACE_CLASS(0x2020, 0x4000, 0xff) }, /* OLICARD300 - MT6225 */ { USB_DEVICE(INOVIA_VENDOR_ID, INOVIA_SEW858) }, { USB_DEVICE(VIATELECOM_VENDOR_ID, VIATELECOM_PRODUCT_CDS7) }, From c52873e5a1ef72f845526d9f6a50704433f9c625 Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Thu, 8 Aug 2019 16:21:19 +0200 Subject: [PATCH 139/157] usb: cdc-acm: make sure a refcount is taken early enough destroy() will decrement the refcount on the interface, so that it needs to be taken so early that it never undercounts. Fixes: 7fb57a019f94e ("USB: cdc-acm: Fix potential deadlock (lockdep warning)") Cc: stable Reported-and-tested-by: syzbot+1b2449b7b5dc240d107a@syzkaller.appspotmail.com Signed-off-by: Oliver Neukum Link: https://lore.kernel.org/r/20190808142119.7998-1-oneukum@suse.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/class/cdc-acm.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 183b41753c98..62f4fb9b362f 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1301,10 +1301,6 @@ static int acm_probe(struct usb_interface *intf, tty_port_init(&acm->port); acm->port.ops = &acm_port_ops; - minor = acm_alloc_minor(acm); - if (minor < 0) - goto alloc_fail1; - ctrlsize = usb_endpoint_maxp(epctrl); readsize = usb_endpoint_maxp(epread) * (quirks == SINGLE_RX_URB ? 1 : 2); @@ -1312,6 +1308,13 @@ static int acm_probe(struct usb_interface *intf, acm->writesize = usb_endpoint_maxp(epwrite) * 20; acm->control = control_interface; acm->data = data_interface; + + usb_get_intf(acm->control); /* undone in destruct() */ + + minor = acm_alloc_minor(acm); + if (minor < 0) + goto alloc_fail1; + acm->minor = minor; acm->dev = usb_dev; if (h.usb_cdc_acm_descriptor) @@ -1458,7 +1461,6 @@ static int acm_probe(struct usb_interface *intf, usb_driver_claim_interface(&acm_driver, data_interface, acm); usb_set_intfdata(data_interface, acm); - usb_get_intf(control_interface); tty_dev = tty_port_register_device(&acm->port, acm_tty_driver, minor, &control_interface->dev); if (IS_ERR(tty_dev)) { From 54364278fb3cabdea51d6398b07c87415065b3fc Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Tue, 13 Aug 2019 11:35:41 +0200 Subject: [PATCH 140/157] USB: CDC: fix sanity checks in CDC union parser A few checks checked for the size of the pointer to a structure instead of the structure itself. Copy & paste issue presumably. Fixes: e4c6fb7794982 ("usbnet: move the CDC parser into USB core") Cc: stable Reported-by: syzbot+45a53506b65321c1fe91@syzkaller.appspotmail.com Signed-off-by: Oliver Neukum Link: https://lore.kernel.org/r/20190813093541.18889-1-oneukum@suse.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/message.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c index e844bb7b5676..5adf489428aa 100644 --- a/drivers/usb/core/message.c +++ b/drivers/usb/core/message.c @@ -2218,14 +2218,14 @@ int cdc_parse_cdc_header(struct usb_cdc_parsed_header *hdr, (struct usb_cdc_dmm_desc *)buffer; break; case USB_CDC_MDLM_TYPE: - if (elength < sizeof(struct usb_cdc_mdlm_desc *)) + if (elength < sizeof(struct usb_cdc_mdlm_desc)) goto next_desc; if (desc) return -EINVAL; desc = (struct usb_cdc_mdlm_desc *)buffer; break; case USB_CDC_MDLM_DETAIL_TYPE: - if (elength < sizeof(struct usb_cdc_mdlm_detail_desc *)) + if (elength < sizeof(struct usb_cdc_mdlm_detail_desc)) goto next_desc; if (detail) return -EINVAL; From 777758888ffe59ef754cc39ab2f275dc277732f4 Mon Sep 17 00:00:00 2001 From: Hans Ulli Kroll Date: Sat, 10 Aug 2019 17:04:58 +0200 Subject: [PATCH 141/157] usb: host: fotg2: restart hcd after port reset On the Gemini SoC the FOTG2 stalls after port reset so restart the HCD after each port reset. Signed-off-by: Hans Ulli Kroll Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20190810150458.817-1-linus.walleij@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/fotg210-hcd.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/usb/host/fotg210-hcd.c b/drivers/usb/host/fotg210-hcd.c index 77cc36efae95..0dbfa5c10703 100644 --- a/drivers/usb/host/fotg210-hcd.c +++ b/drivers/usb/host/fotg210-hcd.c @@ -1629,6 +1629,10 @@ static int fotg210_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, /* see what we found out */ temp = check_reset_complete(fotg210, wIndex, status_reg, fotg210_readl(fotg210, status_reg)); + + /* restart schedule */ + fotg210->command |= CMD_RUN; + fotg210_writel(fotg210, fotg210->command, &fotg210->regs->command); } if (!(temp & (PORT_RESUME|PORT_RESET))) { From 141822aa3f79efc8a2ec3ed464f2fd2c93ccd803 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Andr=C3=A9=20Draszik?= Date: Sat, 10 Aug 2019 16:07:58 +0100 Subject: [PATCH 142/157] usb: chipidea: imx: fix EPROBE_DEFER support during driver probe MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If driver probe needs to be deferred, e.g. because ci_hdrc_add_device() isn't ready yet, this driver currently misbehaves badly: a) success is still reported to the driver core (meaning a 2nd probe attempt will never be done), leaving the driver in a dysfunctional state and the hardware unusable b) driver remove / shutdown OOPSes: [ 206.786916] Unable to handle kernel paging request at virtual address fffffdff [ 206.794148] pgd = 880b9f82 [ 206.796890] [fffffdff] *pgd=abf5e861, *pte=00000000, *ppte=00000000 [ 206.803179] Internal error: Oops: 37 [#1] PREEMPT SMP ARM [ 206.808581] Modules linked in: wl18xx evbug [ 206.813308] CPU: 1 PID: 1 Comm: systemd-shutdow Not tainted 4.19.35+gf345c93b4195 #1 [ 206.821053] Hardware name: Freescale i.MX7 Dual (Device Tree) [ 206.826813] PC is at ci_hdrc_remove_device+0x4/0x20 [ 206.831699] LR is at ci_hdrc_imx_remove+0x20/0xe8 [ 206.836407] pc : [<805cd4b0>] lr : [<805d62cc>] psr: 20000013 [ 206.842678] sp : a806be40 ip : 00000001 fp : 80adbd3c [ 206.847906] r10: 80b1b794 r9 : 80d5dfe0 r8 : a8192c44 [ 206.853136] r7 : 80db93a0 r6 : a8192c10 r5 : a8192c00 r4 : a93a4a00 [ 206.859668] r3 : 00000000 r2 : a8192ce4 r1 : ffffffff r0 : fffffdfb [ 206.866201] Flags: nzCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment none [ 206.873341] Control: 10c5387d Table: a9e0c06a DAC: 00000051 [ 206.879092] Process systemd-shutdow (pid: 1, stack limit = 0xb271353c) [ 206.885624] Stack: (0xa806be40 to 0xa806c000) [ 206.889992] be40: a93a4a00 805d62cc a8192c1c a8170e10 a8192c10 8049a490 80d04d08 00000000 [ 206.898179] be60: 00000000 80d0da2c fee1dead 00000000 a806a000 00000058 00000000 80148b08 [ 206.906366] be80: 01234567 80148d8c a9858600 00000000 00000000 00000000 00000000 80d04d08 [ 206.914553] bea0: 00000000 00000000 a82741e0 a9858600 00000024 00000002 a9858608 00000005 [ 206.922740] bec0: 0000001e 8022c058 00000000 00000000 a806bf14 a9858600 00000000 a806befc [ 206.930927] bee0: a806bf78 00000000 7ee12c30 8022c18c a806bef8 a806befc 00000000 00000001 [ 206.939115] bf00: 00000000 00000024 a806bf14 00000005 7ee13b34 7ee12c68 00000004 7ee13f20 [ 206.947302] bf20: 00000010 7ee12c7c 00000005 7ee12d04 0000000a 76e7dc00 00000001 80d0f140 [ 206.955490] bf40: ab637880 a974de40 60000013 80d0f140 ab6378a0 80d04d08 a8080470 a9858600 [ 206.963677] bf60: a9858600 00000000 00000000 8022c24c 00000000 80144310 00000000 00000000 [ 206.971864] bf80: 80101204 80d04d08 00000000 80d04d08 00000000 00000000 00000003 00000058 [ 206.980051] bfa0: 80101204 80101000 00000000 00000000 fee1dead 28121969 01234567 00000000 [ 206.988237] bfc0: 00000000 00000000 00000003 00000058 00000000 00000000 00000000 00000000 [ 206.996425] bfe0: 0049ffb0 7ee13d58 0048a84b 76f245a6 60000030 fee1dead 00000000 00000000 [ 207.004622] [<805cd4b0>] (ci_hdrc_remove_device) from [<805d62cc>] (ci_hdrc_imx_remove+0x20/0xe8) [ 207.013509] [<805d62cc>] (ci_hdrc_imx_remove) from [<8049a490>] (device_shutdown+0x16c/0x218) [ 207.022050] [<8049a490>] (device_shutdown) from [<80148b08>] (kernel_restart+0xc/0x50) [ 207.029980] [<80148b08>] (kernel_restart) from [<80148d8c>] (sys_reboot+0xf4/0x1f0) [ 207.037648] [<80148d8c>] (sys_reboot) from [<80101000>] (ret_fast_syscall+0x0/0x54) [ 207.045308] Exception stack(0xa806bfa8 to 0xa806bff0) [ 207.050368] bfa0: 00000000 00000000 fee1dead 28121969 01234567 00000000 [ 207.058554] bfc0: 00000000 00000000 00000003 00000058 00000000 00000000 00000000 00000000 [ 207.066737] bfe0: 0049ffb0 7ee13d58 0048a84b 76f245a6 [ 207.071799] Code: ebffffa8 e3a00000 e8bd8010 e92d4010 (e5904004) [ 207.078021] ---[ end trace be47424e3fd46e9f ]--- [ 207.082647] Kernel panic - not syncing: Fatal exception [ 207.087894] ---[ end Kernel panic - not syncing: Fatal exception ]--- c) the error path in combination with driver removal causes imbalanced calls to the clk_*() and pm_()* APIs a) happens because the original intended return value is overwritten (with 0) by the return code of regulator_disable() in ci_hdrc_imx_probe()'s error path b) happens because ci_pdev is -EPROBE_DEFER, which causes ci_hdrc_remove_device() to OOPS Fix a) by being more careful in ci_hdrc_imx_probe()'s error path and not overwriting the real error code Fix b) by calling the respective cleanup functions during remove only when needed (when ci_pdev != NULL, i.e. when everything was initialised correctly). This also has the side effect of not causing imbalanced clk_*() and pm_*() API calls as part of the error code path. Fixes: 7c8e8909417e ("usb: chipidea: imx: add HSIC support") Signed-off-by: André Draszik Cc: stable CC: Peter Chen CC: Greg Kroah-Hartman CC: Shawn Guo CC: Sascha Hauer CC: Pengutronix Kernel Team CC: Fabio Estevam CC: NXP Linux Team CC: linux-usb@vger.kernel.org CC: linux-arm-kernel@lists.infradead.org CC: linux-kernel@vger.kernel.org Link: https://lore.kernel.org/r/20190810150758.17694-1-git@andred.net Signed-off-by: Greg Kroah-Hartman --- drivers/usb/chipidea/ci_hdrc_imx.c | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c index b5abfe89190c..df8812c30640 100644 --- a/drivers/usb/chipidea/ci_hdrc_imx.c +++ b/drivers/usb/chipidea/ci_hdrc_imx.c @@ -454,9 +454,11 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev) imx_disable_unprepare_clks(dev); disable_hsic_regulator: if (data->hsic_pad_regulator) - ret = regulator_disable(data->hsic_pad_regulator); + /* don't overwrite original ret (cf. EPROBE_DEFER) */ + regulator_disable(data->hsic_pad_regulator); if (pdata.flags & CI_HDRC_PMQOS) pm_qos_remove_request(&data->pm_qos_req); + data->ci_pdev = NULL; return ret; } @@ -469,14 +471,17 @@ static int ci_hdrc_imx_remove(struct platform_device *pdev) pm_runtime_disable(&pdev->dev); pm_runtime_put_noidle(&pdev->dev); } - ci_hdrc_remove_device(data->ci_pdev); + if (data->ci_pdev) + ci_hdrc_remove_device(data->ci_pdev); if (data->override_phy_control) usb_phy_shutdown(data->phy); - imx_disable_unprepare_clks(&pdev->dev); - if (data->plat_data->flags & CI_HDRC_PMQOS) - pm_qos_remove_request(&data->pm_qos_req); - if (data->hsic_pad_regulator) - regulator_disable(data->hsic_pad_regulator); + if (data->ci_pdev) { + imx_disable_unprepare_clks(&pdev->dev); + if (data->plat_data->flags & CI_HDRC_PMQOS) + pm_qos_remove_request(&data->pm_qos_req); + if (data->hsic_pad_regulator) + regulator_disable(data->hsic_pad_regulator); + } return 0; } From dd3ecf17ba70a70d2c9ef9ba725281b84f8eef12 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 11 Aug 2019 10:05:15 +0200 Subject: [PATCH 143/157] usb: don't create dma pools for HCDs with a localmem_pool If the HCD provides a localmem pool we will never use the DMA pools, so don't create them. Fixes: b0310c2f09bb ("USB: use genalloc for USB HCs with local memory") Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20190811080520.21712-2-hch@lst.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/buffer.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/usb/core/buffer.c b/drivers/usb/core/buffer.c index 1359b78a624e..1a5b3dcae930 100644 --- a/drivers/usb/core/buffer.c +++ b/drivers/usb/core/buffer.c @@ -66,9 +66,9 @@ int hcd_buffer_create(struct usb_hcd *hcd) char name[16]; int i, size; - if (!IS_ENABLED(CONFIG_HAS_DMA) || - (!is_device_dma_capable(hcd->self.sysdev) && - !hcd->localmem_pool)) + if (hcd->localmem_pool || + !IS_ENABLED(CONFIG_HAS_DMA) || + !is_device_dma_capable(hcd->self.sysdev)) return 0; for (i = 0; i < HCD_BUFFER_POOLS; i++) { From edfbcb321faf07ca970e4191abe061deeb7d3788 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 11 Aug 2019 10:05:16 +0200 Subject: [PATCH 144/157] usb: add a hcd_uses_dma helper The USB buffer allocation code is the only place in the usb core (and in fact the whole kernel) that uses is_device_dma_capable, while the URB mapping code uses the uses_dma flag in struct usb_bus. Switch the buffer allocation to use the uses_dma flag used by the rest of the USB code, and create a helper in hcd.h that checks this flag as well as the CONFIG_HAS_DMA to simplify the caller a bit. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20190811080520.21712-3-hch@lst.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/buffer.c | 10 +++------- drivers/usb/core/hcd.c | 4 ++-- drivers/usb/dwc2/hcd.c | 2 +- include/linux/usb.h | 2 +- include/linux/usb/hcd.h | 3 +++ 5 files changed, 10 insertions(+), 11 deletions(-) diff --git a/drivers/usb/core/buffer.c b/drivers/usb/core/buffer.c index 1a5b3dcae930..6cf22c27f2d2 100644 --- a/drivers/usb/core/buffer.c +++ b/drivers/usb/core/buffer.c @@ -66,9 +66,7 @@ int hcd_buffer_create(struct usb_hcd *hcd) char name[16]; int i, size; - if (hcd->localmem_pool || - !IS_ENABLED(CONFIG_HAS_DMA) || - !is_device_dma_capable(hcd->self.sysdev)) + if (hcd->localmem_pool || !hcd_uses_dma(hcd)) return 0; for (i = 0; i < HCD_BUFFER_POOLS; i++) { @@ -129,8 +127,7 @@ void *hcd_buffer_alloc( return gen_pool_dma_alloc(hcd->localmem_pool, size, dma); /* some USB hosts just use PIO */ - if (!IS_ENABLED(CONFIG_HAS_DMA) || - !is_device_dma_capable(bus->sysdev)) { + if (!hcd_uses_dma(hcd)) { *dma = ~(dma_addr_t) 0; return kmalloc(size, mem_flags); } @@ -160,8 +157,7 @@ void hcd_buffer_free( return; } - if (!IS_ENABLED(CONFIG_HAS_DMA) || - !is_device_dma_capable(bus->sysdev)) { + if (!hcd_uses_dma(hcd)) { kfree(addr); return; } diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 2ccbc2f83570..8592c0344fe8 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -1412,7 +1412,7 @@ int usb_hcd_map_urb_for_dma(struct usb_hcd *hcd, struct urb *urb, if (usb_endpoint_xfer_control(&urb->ep->desc)) { if (hcd->self.uses_pio_for_control) return ret; - if (IS_ENABLED(CONFIG_HAS_DMA) && hcd->self.uses_dma) { + if (hcd_uses_dma(hcd)) { if (is_vmalloc_addr(urb->setup_packet)) { WARN_ONCE(1, "setup packet is not dma capable\n"); return -EAGAIN; @@ -1446,7 +1446,7 @@ int usb_hcd_map_urb_for_dma(struct usb_hcd *hcd, struct urb *urb, dir = usb_urb_dir_in(urb) ? DMA_FROM_DEVICE : DMA_TO_DEVICE; if (urb->transfer_buffer_length != 0 && !(urb->transfer_flags & URB_NO_TRANSFER_DMA_MAP)) { - if (IS_ENABLED(CONFIG_HAS_DMA) && hcd->self.uses_dma) { + if (hcd_uses_dma(hcd)) { if (urb->num_sgs) { int n; diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c index ee144ff8af5b..111787a137ee 100644 --- a/drivers/usb/dwc2/hcd.c +++ b/drivers/usb/dwc2/hcd.c @@ -4608,7 +4608,7 @@ static int _dwc2_hcd_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, buf = urb->transfer_buffer; - if (hcd->self.uses_dma) { + if (hcd_uses_dma(hcd)) { if (!buf && (urb->transfer_dma & 3)) { dev_err(hsotg->dev, "%s: unaligned transfer with no transfer_buffer", diff --git a/include/linux/usb.h b/include/linux/usb.h index 83d35d993e8c..e87826e23d59 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1457,7 +1457,7 @@ typedef void (*usb_complete_t)(struct urb *); * field rather than determining a dma address themselves. * * Note that transfer_buffer must still be set if the controller - * does not support DMA (as indicated by bus.uses_dma) and when talking + * does not support DMA (as indicated by hcd_uses_dma()) and when talking * to root hub. If you have to trasfer between highmem zone and the device * on such controller, create a bounce buffer or bail out with an error. * If transfer_buffer cannot be set (is in highmem) and the controller is DMA diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index bab27ccc8ff5..a20e7815d814 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -422,6 +422,9 @@ static inline bool hcd_periodic_completion_in_progress(struct usb_hcd *hcd, return hcd->high_prio_bh.completing_ep == ep; } +#define hcd_uses_dma(hcd) \ + (IS_ENABLED(CONFIG_HAS_DMA) && (hcd)->self.uses_dma) + extern int usb_hcd_link_urb_to_ep(struct usb_hcd *hcd, struct urb *urb); extern int usb_hcd_check_unlink_urb(struct usb_hcd *hcd, struct urb *urb, int status); From 01fd150f4aff5bee03db5bda3b94c1bdbe9c6375 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 13 Aug 2019 16:01:20 -0700 Subject: [PATCH 145/157] misc: xilinx-sdfec: fix dependency and build error lib/devres.c, which implements devm_ioremap_resource(), is only built when CONFIG_HAS_IOMEM is set/enabled, so XILINX_SDFEC should depend on HAS_IOMEM. Fixes this build error (as seen on UML builds): ERROR: "devm_ioremap_resource" [drivers/misc/xilinx_sdfec.ko] undefined! Fixes: 76d83e1c3233 ("misc: xilinx-sdfec: add core driver") Signed-off-by: Randy Dunlap Cc: Derek Kiernan Cc: Dragan Cvetic Cc: Greg Kroah-Hartman Cc: Geert Uytterhoeven Cc: Arnd Bergmann Link: https://lore.kernel.org/r/f9004be5-9925-327b-3ec2-6506e46fe565@infradead.org Signed-off-by: Greg Kroah-Hartman --- drivers/misc/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig index 6abfc8e92fcc..16900357afc2 100644 --- a/drivers/misc/Kconfig +++ b/drivers/misc/Kconfig @@ -465,6 +465,7 @@ config PCI_ENDPOINT_TEST config XILINX_SDFEC tristate "Xilinx SDFEC 16" + depends on HAS_IOMEM help This option enables support for the Xilinx SDFEC (Soft Decision Forward Error Correction) driver. This enables a char driver From 99c79f6692ccdc42e04deea8a36e22bb48168a62 Mon Sep 17 00:00:00 2001 From: Aleix Roca Nonell Date: Thu, 15 Aug 2019 14:03:22 +0200 Subject: [PATCH 146/157] io_uring: fix manual setup of iov_iter for fixed buffers Commit bd11b3a391e3 ("io_uring: don't use iov_iter_advance() for fixed buffers") introduced an optimization to avoid using the slow iov_iter_advance by manually populating the iov_iter iterator in some cases. However, the computation of the iterator count field was erroneous: The first bvec was always accounted for an extent of page size even if the bvec length was smaller. In consequence, some I/O operations on fixed buffers were unable to operate on the full extent of the buffer, consistently skipping some bytes at the end of it. Fixes: bd11b3a391e3 ("io_uring: don't use iov_iter_advance() for fixed buffers") Cc: stable@vger.kernel.org Signed-off-by: Aleix Roca Nonell Signed-off-by: Jens Axboe --- fs/io_uring.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index d542f1cf4428..aa25b5bbd4ae 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1097,10 +1097,8 @@ static int io_import_fixed(struct io_ring_ctx *ctx, int rw, iter->bvec = bvec + seg_skip; iter->nr_segs -= seg_skip; - iter->count -= (seg_skip << PAGE_SHIFT); + iter->count -= bvec->bv_len + offset; iter->iov_offset = offset & ~PAGE_MASK; - if (iter->iov_offset) - iter->count -= iter->iov_offset; } } From 7b6620d7db566a46f49b4b9deab9fa061fd4b59b Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 15 Aug 2019 11:09:16 -0600 Subject: [PATCH 147/157] block: remove REQ_NOWAIT_INLINE We had a few issues with this code, and there's still a problem around how we deal with error handling for chained/split bios. For now, just revert the code and we'll try again with a thoroug solution. This reverts commits: e15c2ffa1091 ("block: fix O_DIRECT error handling for bio fragments") 0eb6ddfb865c ("block: Fix __blkdev_direct_IO() for bio fragments") 6a43074e2f46 ("block: properly handle IOCB_NOWAIT for async O_DIRECT IO") 893a1c97205a ("blk-mq: allow REQ_NOWAIT to return an error inline") Signed-off-by: Jens Axboe --- block/blk-mq.c | 8 ++----- fs/block_dev.c | 49 ++++----------------------------------- include/linux/blk_types.h | 5 +--- 3 files changed, 8 insertions(+), 54 deletions(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index a8e6a58f5f28..0835f4d8d42e 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1958,13 +1958,9 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) rq = blk_mq_get_request(q, bio, &data); if (unlikely(!rq)) { rq_qos_cleanup(q, bio); - - cookie = BLK_QC_T_NONE; - if (bio->bi_opf & REQ_NOWAIT_INLINE) - cookie = BLK_QC_T_EAGAIN; - else if (bio->bi_opf & REQ_NOWAIT) + if (bio->bi_opf & REQ_NOWAIT) bio_wouldblock_error(bio); - return cookie; + return BLK_QC_T_NONE; } trace_block_getrq(q, bio, bio->bi_opf); diff --git a/fs/block_dev.c b/fs/block_dev.c index eb657ab94060..677cb364d33f 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -345,24 +345,15 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) struct bio *bio; bool is_poll = (iocb->ki_flags & IOCB_HIPRI) != 0; bool is_read = (iov_iter_rw(iter) == READ), is_sync; - bool nowait = (iocb->ki_flags & IOCB_NOWAIT) != 0; loff_t pos = iocb->ki_pos; blk_qc_t qc = BLK_QC_T_NONE; - gfp_t gfp; - int ret; + int ret = 0; if ((pos | iov_iter_alignment(iter)) & (bdev_logical_block_size(bdev) - 1)) return -EINVAL; - if (nowait) - gfp = GFP_NOWAIT; - else - gfp = GFP_KERNEL; - - bio = bio_alloc_bioset(gfp, nr_pages, &blkdev_dio_pool); - if (!bio) - return -EAGAIN; + bio = bio_alloc_bioset(GFP_KERNEL, nr_pages, &blkdev_dio_pool); dio = container_of(bio, struct blkdev_dio, bio); dio->is_sync = is_sync = is_sync_kiocb(iocb); @@ -384,7 +375,6 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) if (!is_poll) blk_start_plug(&plug); - ret = 0; for (;;) { bio_set_dev(bio, bdev); bio->bi_iter.bi_sector = pos >> 9; @@ -409,14 +399,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) task_io_account_write(bio->bi_iter.bi_size); } - /* - * Tell underlying layer to not block for resource shortage. - * And if we would have blocked, return error inline instead - * of through the bio->bi_end_io() callback. - */ - if (nowait) - bio->bi_opf |= (REQ_NOWAIT | REQ_NOWAIT_INLINE); - + dio->size += bio->bi_iter.bi_size; pos += bio->bi_iter.bi_size; nr_pages = iov_iter_npages(iter, BIO_MAX_PAGES); @@ -428,13 +411,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) polled = true; } - dio->size += bio->bi_iter.bi_size; qc = submit_bio(bio); - if (qc == BLK_QC_T_EAGAIN) { - dio->size -= bio->bi_iter.bi_size; - ret = -EAGAIN; - goto error; - } if (polled) WRITE_ONCE(iocb->ki_cookie, qc); @@ -455,19 +432,8 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) atomic_inc(&dio->ref); } - dio->size += bio->bi_iter.bi_size; - qc = submit_bio(bio); - if (qc == BLK_QC_T_EAGAIN) { - dio->size -= bio->bi_iter.bi_size; - ret = -EAGAIN; - goto error; - } - - bio = bio_alloc(gfp, nr_pages); - if (!bio) { - ret = -EAGAIN; - goto error; - } + submit_bio(bio); + bio = bio_alloc(GFP_KERNEL, nr_pages); } if (!is_poll) @@ -487,7 +453,6 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) } __set_current_state(TASK_RUNNING); -out: if (!ret) ret = blk_status_to_errno(dio->bio.bi_status); if (likely(!ret)) @@ -495,10 +460,6 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) bio_put(&dio->bio); return ret; -error: - if (!is_poll) - blk_finish_plug(&plug); - goto out; } static ssize_t diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 1b1fa1557e68..feff3fe4467e 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -311,7 +311,6 @@ enum req_flag_bits { __REQ_RAHEAD, /* read ahead, can fail anytime */ __REQ_BACKGROUND, /* background IO */ __REQ_NOWAIT, /* Don't wait if request will block */ - __REQ_NOWAIT_INLINE, /* Return would-block error inline */ /* * When a shared kthread needs to issue a bio for a cgroup, doing * so synchronously can lead to priority inversions as the kthread @@ -346,7 +345,6 @@ enum req_flag_bits { #define REQ_RAHEAD (1ULL << __REQ_RAHEAD) #define REQ_BACKGROUND (1ULL << __REQ_BACKGROUND) #define REQ_NOWAIT (1ULL << __REQ_NOWAIT) -#define REQ_NOWAIT_INLINE (1ULL << __REQ_NOWAIT_INLINE) #define REQ_CGROUP_PUNT (1ULL << __REQ_CGROUP_PUNT) #define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP) @@ -420,13 +418,12 @@ static inline int op_stat_group(unsigned int op) typedef unsigned int blk_qc_t; #define BLK_QC_T_NONE -1U -#define BLK_QC_T_EAGAIN -2U #define BLK_QC_T_SHIFT 16 #define BLK_QC_T_INTERNAL (1U << 31) static inline bool blk_qc_t_valid(blk_qc_t cookie) { - return cookie != BLK_QC_T_NONE && cookie != BLK_QC_T_EAGAIN; + return cookie != BLK_QC_T_NONE; } static inline unsigned int blk_qc_t_to_queue_num(blk_qc_t cookie) From a982eeb09b6030e567b8b815277c8c9197168040 Mon Sep 17 00:00:00 2001 From: Jackie Liu Date: Wed, 14 Aug 2019 17:35:22 +0800 Subject: [PATCH 148/157] io_uring: fix an issue when IOSQE_IO_LINK is inserted into defer list This patch may fix two issues: First, when IOSQE_IO_DRAIN set, the next IOs need to be inserted into defer list to delay execution, but link io will be actively scheduled to run by calling io_queue_sqe. Second, when multiple LINK_IOs are inserted together with defer_list, the LINK_IO is no longer keep order. |-------------| | LINK_IO | ----> insert to defer_list ----------- |-------------| | | LINK_IO | ----> insert to defer_list ----------| |-------------| | | LINK_IO | ----> insert to defer_list ----------| |-------------| | | NORMAL_IO | ----> insert to defer_list ----------| |-------------| | | queue_work at same time <-----| Fixes: 9e645e1105c ("io_uring: add support for sqe links") Signed-off-by: Jackie Liu Signed-off-by: Jens Axboe --- fs/io_uring.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index aa25b5bbd4ae..24bbe3cb7ad4 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -2023,6 +2023,15 @@ static int io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, { int ret; + ret = io_req_defer(ctx, req, s->sqe); + if (ret) { + if (ret != -EIOCBQUEUED) { + io_free_req(req); + io_cqring_add_event(ctx, s->sqe->user_data, ret); + } + return 0; + } + ret = __io_submit_sqe(ctx, req, s, true); if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) { struct io_uring_sqe *sqe_copy; @@ -2095,13 +2104,6 @@ static void io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s, return; } - ret = io_req_defer(ctx, req, s->sqe); - if (ret) { - if (ret != -EIOCBQUEUED) - goto err_req; - return; - } - /* * If we already have a head request, queue this one for async * submittal once the head completes. If we don't have a head but From 19bce474c45be69a284ecee660aa12d8f1e88f18 Mon Sep 17 00:00:00 2001 From: Hui Peng Date: Thu, 15 Aug 2019 00:31:34 -0400 Subject: [PATCH 149/157] ALSA: usb-audio: Fix a stack buffer overflow bug in check_input_term `check_input_term` recursively calls itself with input from device side (e.g., uac_input_terminal_descriptor.bCSourceID) as argument (id). In `check_input_term`, if `check_input_term` is called with the same `id` argument as the caller, it triggers endless recursive call, resulting kernel space stack overflow. This patch fixes the bug by adding a bitmap to `struct mixer_build` to keep track of the checked ids and stop the execution if some id has been checked (similar to how parse_audio_unit handles unitid argument). Reported-by: Hui Peng Reported-by: Mathias Payer Signed-off-by: Hui Peng Cc: Signed-off-by: Takashi Iwai --- sound/usb/mixer.c | 35 +++++++++++++++++++++++++++-------- 1 file changed, 27 insertions(+), 8 deletions(-) diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index ea487378be17..b5927c3d5bc0 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -68,6 +68,7 @@ struct mixer_build { unsigned char *buffer; unsigned int buflen; DECLARE_BITMAP(unitbitmap, MAX_ID_ELEMS); + DECLARE_BITMAP(termbitmap, MAX_ID_ELEMS); struct usb_audio_term oterm; const struct usbmix_name_map *map; const struct usbmix_selector_map *selector_map; @@ -775,16 +776,25 @@ static int uac_mixer_unit_get_channels(struct mixer_build *state, * parse the source unit recursively until it reaches to a terminal * or a branched unit. */ -static int check_input_term(struct mixer_build *state, int id, +static int __check_input_term(struct mixer_build *state, int id, struct usb_audio_term *term) { int protocol = state->mixer->protocol; int err; void *p1; + unsigned char *hdr; memset(term, 0, sizeof(*term)); - while ((p1 = find_audio_control_unit(state, id)) != NULL) { - unsigned char *hdr = p1; + for (;;) { + /* a loop in the terminal chain? */ + if (test_and_set_bit(id, state->termbitmap)) + return -EINVAL; + + p1 = find_audio_control_unit(state, id); + if (!p1) + break; + + hdr = p1; term->id = id; if (protocol == UAC_VERSION_1 || protocol == UAC_VERSION_2) { @@ -802,7 +812,7 @@ static int check_input_term(struct mixer_build *state, int id, /* call recursively to verify that the * referenced clock entity is valid */ - err = check_input_term(state, d->bCSourceID, term); + err = __check_input_term(state, d->bCSourceID, term); if (err < 0) return err; @@ -836,7 +846,7 @@ static int check_input_term(struct mixer_build *state, int id, case UAC2_CLOCK_SELECTOR: { struct uac_selector_unit_descriptor *d = p1; /* call recursively to retrieve the channel info */ - err = check_input_term(state, d->baSourceID[0], term); + err = __check_input_term(state, d->baSourceID[0], term); if (err < 0) return err; term->type = UAC3_SELECTOR_UNIT << 16; /* virtual type */ @@ -899,7 +909,7 @@ static int check_input_term(struct mixer_build *state, int id, /* call recursively to verify that the * referenced clock entity is valid */ - err = check_input_term(state, d->bCSourceID, term); + err = __check_input_term(state, d->bCSourceID, term); if (err < 0) return err; @@ -950,7 +960,7 @@ static int check_input_term(struct mixer_build *state, int id, case UAC3_CLOCK_SELECTOR: { struct uac_selector_unit_descriptor *d = p1; /* call recursively to retrieve the channel info */ - err = check_input_term(state, d->baSourceID[0], term); + err = __check_input_term(state, d->baSourceID[0], term); if (err < 0) return err; term->type = UAC3_SELECTOR_UNIT << 16; /* virtual type */ @@ -966,7 +976,7 @@ static int check_input_term(struct mixer_build *state, int id, return -EINVAL; /* call recursively to retrieve the channel info */ - err = check_input_term(state, d->baSourceID[0], term); + err = __check_input_term(state, d->baSourceID[0], term); if (err < 0) return err; @@ -984,6 +994,15 @@ static int check_input_term(struct mixer_build *state, int id, return -ENODEV; } + +static int check_input_term(struct mixer_build *state, int id, + struct usb_audio_term *term) +{ + memset(term, 0, sizeof(*term)); + memset(state->termbitmap, 0, sizeof(state->termbitmap)); + return __check_input_term(state, id, term); +} + /* * Feature Unit */ From a90118c445cc7f07781de26a9684d4ec58bfcfd1 Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Tue, 30 Jul 2019 22:46:27 -0700 Subject: [PATCH 150/157] x86/boot: Save fields explicitly, zero out everything else Recent gcc compilers (gcc 9.1) generate warnings about an out of bounds memset, if the memset goes accross several fields of a struct. This generated a couple of warnings on x86_64 builds in sanitize_boot_params(). Fix this by explicitly saving the fields in struct boot_params that are intended to be preserved, and zeroing all the rest. [ tglx: Tagged for stable as it breaks the warning free build there as well ] Suggested-by: Thomas Gleixner Suggested-by: H. Peter Anvin Signed-off-by: John Hubbard Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20190731054627.5627-2-jhubbard@nvidia.com --- arch/x86/include/asm/bootparam_utils.h | 63 ++++++++++++++++++++------ 1 file changed, 48 insertions(+), 15 deletions(-) diff --git a/arch/x86/include/asm/bootparam_utils.h b/arch/x86/include/asm/bootparam_utils.h index 101eb944f13c..f5e90a849bca 100644 --- a/arch/x86/include/asm/bootparam_utils.h +++ b/arch/x86/include/asm/bootparam_utils.h @@ -18,6 +18,20 @@ * Note: efi_info is commonly left uninitialized, but that field has a * private magic, so it is better to leave it unchanged. */ + +#define sizeof_mbr(type, member) ({ sizeof(((type *)0)->member); }) + +#define BOOT_PARAM_PRESERVE(struct_member) \ + { \ + .start = offsetof(struct boot_params, struct_member), \ + .len = sizeof_mbr(struct boot_params, struct_member), \ + } + +struct boot_params_to_save { + unsigned int start; + unsigned int len; +}; + static void sanitize_boot_params(struct boot_params *boot_params) { /* @@ -35,21 +49,40 @@ static void sanitize_boot_params(struct boot_params *boot_params) * problems again. */ if (boot_params->sentinel) { - /* fields in boot_params are left uninitialized, clear them */ - boot_params->acpi_rsdp_addr = 0; - memset(&boot_params->ext_ramdisk_image, 0, - (char *)&boot_params->efi_info - - (char *)&boot_params->ext_ramdisk_image); - memset(&boot_params->kbd_status, 0, - (char *)&boot_params->hdr - - (char *)&boot_params->kbd_status); - memset(&boot_params->_pad7[0], 0, - (char *)&boot_params->edd_mbr_sig_buffer[0] - - (char *)&boot_params->_pad7[0]); - memset(&boot_params->_pad8[0], 0, - (char *)&boot_params->eddbuf[0] - - (char *)&boot_params->_pad8[0]); - memset(&boot_params->_pad9[0], 0, sizeof(boot_params->_pad9)); + static struct boot_params scratch; + char *bp_base = (char *)boot_params; + char *save_base = (char *)&scratch; + int i; + + const struct boot_params_to_save to_save[] = { + BOOT_PARAM_PRESERVE(screen_info), + BOOT_PARAM_PRESERVE(apm_bios_info), + BOOT_PARAM_PRESERVE(tboot_addr), + BOOT_PARAM_PRESERVE(ist_info), + BOOT_PARAM_PRESERVE(acpi_rsdp_addr), + BOOT_PARAM_PRESERVE(hd0_info), + BOOT_PARAM_PRESERVE(hd1_info), + BOOT_PARAM_PRESERVE(sys_desc_table), + BOOT_PARAM_PRESERVE(olpc_ofw_header), + BOOT_PARAM_PRESERVE(efi_info), + BOOT_PARAM_PRESERVE(alt_mem_k), + BOOT_PARAM_PRESERVE(scratch), + BOOT_PARAM_PRESERVE(e820_entries), + BOOT_PARAM_PRESERVE(eddbuf_entries), + BOOT_PARAM_PRESERVE(edd_mbr_sig_buf_entries), + BOOT_PARAM_PRESERVE(edd_mbr_sig_buffer), + BOOT_PARAM_PRESERVE(e820_table), + BOOT_PARAM_PRESERVE(eddbuf), + }; + + memset(&scratch, 0, sizeof(scratch)); + + for (i = 0; i < ARRAY_SIZE(to_save); i++) { + memcpy(save_base + to_save[i].start, + bp_base + to_save[i].start, to_save[i].len); + } + + memcpy(boot_params, save_base, sizeof(*boot_params)); } } From b6143d10d23ebb4a77af311e8b8b7f019d0163e6 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 16 Aug 2019 14:57:43 +0100 Subject: [PATCH 151/157] arm64: ftrace: Ensure module ftrace trampoline is coherent with I-side The initial support for dynamic ftrace trampolines in modules made use of an indirect branch which loaded its target from the beginning of a special section (e71a4e1bebaf7 ("arm64: ftrace: add support for far branches to dynamic ftrace")). Since no instructions were being patched, no cache maintenance was needed. However, later in be0f272bfc83 ("arm64: ftrace: emit ftrace-mod.o contents through code") this code was reworked to output the trampoline instructions directly into the PLT entry but, unfortunately, the necessary cache maintenance was overlooked. Add a call to __flush_icache_range() after writing the new trampoline instructions but before patching in the branch to the trampoline. Cc: Ard Biesheuvel Cc: James Morse Cc: Fixes: be0f272bfc83 ("arm64: ftrace: emit ftrace-mod.o contents through code") Signed-off-by: Will Deacon Signed-off-by: Catalin Marinas --- arch/arm64/kernel/ftrace.c | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index 1285c7b2947f..171773257974 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -73,7 +73,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) if (offset < -SZ_128M || offset >= SZ_128M) { #ifdef CONFIG_ARM64_MODULE_PLTS - struct plt_entry trampoline; + struct plt_entry trampoline, *dst; struct module *mod; /* @@ -106,23 +106,27 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) * to check if the actual opcodes are in fact identical, * regardless of the offset in memory so use memcmp() instead. */ - trampoline = get_plt_entry(addr, mod->arch.ftrace_trampoline); - if (memcmp(mod->arch.ftrace_trampoline, &trampoline, - sizeof(trampoline))) { - if (plt_entry_is_initialized(mod->arch.ftrace_trampoline)) { + dst = mod->arch.ftrace_trampoline; + trampoline = get_plt_entry(addr, dst); + if (memcmp(dst, &trampoline, sizeof(trampoline))) { + if (plt_entry_is_initialized(dst)) { pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n"); return -EINVAL; } /* point the trampoline to our ftrace entry point */ module_disable_ro(mod); - *mod->arch.ftrace_trampoline = trampoline; + *dst = trampoline; module_enable_ro(mod, true); - /* update trampoline before patching in the branch */ - smp_wmb(); + /* + * Ensure updated trampoline is visible to instruction + * fetch before we patch in the branch. + */ + __flush_icache_range((unsigned long)&dst[0], + (unsigned long)&dst[1]); } - addr = (unsigned long)(void *)mod->arch.ftrace_trampoline; + addr = (unsigned long)dst; #else /* CONFIG_ARM64_MODULE_PLTS */ return -EINVAL; #endif /* CONFIG_ARM64_MODULE_PLTS */ From 5912e791f3018de0a007c8cfa9cb38c97d3e5f5c Mon Sep 17 00:00:00 2001 From: Adrian Vladu Date: Mon, 6 May 2019 17:27:37 +0000 Subject: [PATCH 152/157] tools: hv: fixed Python pep8/flake8 warnings for lsvmbus Fixed pep8/flake8 python style code for lsvmbus tool. The TAB indentation was on purpose ignored (pep8 rule W191) to make sure the code is complying with the Linux code guideline. The following command doe not show any warnings now: pep8 --ignore=W191 lsvmbus flake8 --ignore=W191 lsvmbus Signed-off-by: Adrian Vladu Cc: "K. Y. Srinivasan" Cc: Haiyang Zhang Cc: Stephen Hemminger Cc: Sasha Levin Cc: Dexuan Cui Cc: Alessandro Pilotti Signed-off-by: Sasha Levin --- tools/hv/lsvmbus | 75 +++++++++++++++++++++++++++--------------------- 1 file changed, 42 insertions(+), 33 deletions(-) diff --git a/tools/hv/lsvmbus b/tools/hv/lsvmbus index 55e7374bade0..099f2c44dbed 100644 --- a/tools/hv/lsvmbus +++ b/tools/hv/lsvmbus @@ -4,10 +4,10 @@ import os from optparse import OptionParser +help_msg = "print verbose messages. Try -vv, -vvv for more verbose messages" parser = OptionParser() -parser.add_option("-v", "--verbose", dest="verbose", - help="print verbose messages. Try -vv, -vvv for \ - more verbose messages", action="count") +parser.add_option( + "-v", "--verbose", dest="verbose", help=help_msg, action="count") (options, args) = parser.parse_args() @@ -21,27 +21,28 @@ if not os.path.isdir(vmbus_sys_path): exit(-1) vmbus_dev_dict = { - '{0e0b6031-5213-4934-818b-38d90ced39db}' : '[Operating system shutdown]', - '{9527e630-d0ae-497b-adce-e80ab0175caf}' : '[Time Synchronization]', - '{57164f39-9115-4e78-ab55-382f3bd5422d}' : '[Heartbeat]', - '{a9a0f4e7-5a45-4d96-b827-8a841e8c03e6}' : '[Data Exchange]', - '{35fa2e29-ea23-4236-96ae-3a6ebacba440}' : '[Backup (volume checkpoint)]', - '{34d14be3-dee4-41c8-9ae7-6b174977c192}' : '[Guest services]', - '{525074dc-8985-46e2-8057-a307dc18a502}' : '[Dynamic Memory]', - '{cfa8b69e-5b4a-4cc0-b98b-8ba1a1f3f95a}' : 'Synthetic mouse', - '{f912ad6d-2b17-48ea-bd65-f927a61c7684}' : 'Synthetic keyboard', - '{da0a7802-e377-4aac-8e77-0558eb1073f8}' : 'Synthetic framebuffer adapter', - '{f8615163-df3e-46c5-913f-f2d2f965ed0e}' : 'Synthetic network adapter', - '{32412632-86cb-44a2-9b5c-50d1417354f5}' : 'Synthetic IDE Controller', - '{ba6163d9-04a1-4d29-b605-72e2ffb1dc7f}' : 'Synthetic SCSI Controller', - '{2f9bcc4a-0069-4af3-b76b-6fd0be528cda}' : 'Synthetic fiber channel adapter', - '{8c2eaf3d-32a7-4b09-ab99-bd1f1c86b501}' : 'Synthetic RDMA adapter', - '{44c4f61d-4444-4400-9d52-802e27ede19f}' : 'PCI Express pass-through', - '{276aacf4-ac15-426c-98dd-7521ad3f01fe}' : '[Reserved system device]', - '{f8e65716-3cb3-4a06-9a60-1889c5cccab5}' : '[Reserved system device]', - '{3375baf4-9e15-4b30-b765-67acb10d607b}' : '[Reserved system device]', + '{0e0b6031-5213-4934-818b-38d90ced39db}': '[Operating system shutdown]', + '{9527e630-d0ae-497b-adce-e80ab0175caf}': '[Time Synchronization]', + '{57164f39-9115-4e78-ab55-382f3bd5422d}': '[Heartbeat]', + '{a9a0f4e7-5a45-4d96-b827-8a841e8c03e6}': '[Data Exchange]', + '{35fa2e29-ea23-4236-96ae-3a6ebacba440}': '[Backup (volume checkpoint)]', + '{34d14be3-dee4-41c8-9ae7-6b174977c192}': '[Guest services]', + '{525074dc-8985-46e2-8057-a307dc18a502}': '[Dynamic Memory]', + '{cfa8b69e-5b4a-4cc0-b98b-8ba1a1f3f95a}': 'Synthetic mouse', + '{f912ad6d-2b17-48ea-bd65-f927a61c7684}': 'Synthetic keyboard', + '{da0a7802-e377-4aac-8e77-0558eb1073f8}': 'Synthetic framebuffer adapter', + '{f8615163-df3e-46c5-913f-f2d2f965ed0e}': 'Synthetic network adapter', + '{32412632-86cb-44a2-9b5c-50d1417354f5}': 'Synthetic IDE Controller', + '{ba6163d9-04a1-4d29-b605-72e2ffb1dc7f}': 'Synthetic SCSI Controller', + '{2f9bcc4a-0069-4af3-b76b-6fd0be528cda}': 'Synthetic fiber channel adapter', + '{8c2eaf3d-32a7-4b09-ab99-bd1f1c86b501}': 'Synthetic RDMA adapter', + '{44c4f61d-4444-4400-9d52-802e27ede19f}': 'PCI Express pass-through', + '{276aacf4-ac15-426c-98dd-7521ad3f01fe}': '[Reserved system device]', + '{f8e65716-3cb3-4a06-9a60-1889c5cccab5}': '[Reserved system device]', + '{3375baf4-9e15-4b30-b765-67acb10d607b}': '[Reserved system device]', } + def get_vmbus_dev_attr(dev_name, attr): try: f = open('%s/%s/%s' % (vmbus_sys_path, dev_name, attr), 'r') @@ -52,6 +53,7 @@ def get_vmbus_dev_attr(dev_name, attr): return lines + class VMBus_Dev: pass @@ -66,12 +68,13 @@ for f in os.listdir(vmbus_sys_path): chn_vp_mapping = get_vmbus_dev_attr(f, 'channel_vp_mapping') chn_vp_mapping = [c.strip() for c in chn_vp_mapping] - chn_vp_mapping = sorted(chn_vp_mapping, - key = lambda c : int(c.split(':')[0])) + chn_vp_mapping = sorted( + chn_vp_mapping, key=lambda c: int(c.split(':')[0])) - chn_vp_mapping = ['\tRel_ID=%s, target_cpu=%s' % - (c.split(':')[0], c.split(':')[1]) - for c in chn_vp_mapping] + chn_vp_mapping = [ + '\tRel_ID=%s, target_cpu=%s' % + (c.split(':')[0], c.split(':')[1]) for c in chn_vp_mapping + ] d = VMBus_Dev() d.sysfs_path = '%s/%s' % (vmbus_sys_path, f) d.vmbus_id = vmbus_id @@ -85,7 +88,7 @@ for f in os.listdir(vmbus_sys_path): vmbus_dev_list.append(d) -vmbus_dev_list = sorted(vmbus_dev_list, key = lambda d : int(d.vmbus_id)) +vmbus_dev_list = sorted(vmbus_dev_list, key=lambda d: int(d.vmbus_id)) format0 = '%2s: %s' format1 = '%2s: Class_ID = %s - %s\n%s' @@ -95,9 +98,15 @@ for d in vmbus_dev_list: if verbose == 0: print(('VMBUS ID ' + format0) % (d.vmbus_id, d.dev_desc)) elif verbose == 1: - print (('VMBUS ID ' + format1) % \ - (d.vmbus_id, d.class_id, d.dev_desc, d.chn_vp_mapping)) + print( + ('VMBUS ID ' + format1) % + (d.vmbus_id, d.class_id, d.dev_desc, d.chn_vp_mapping) + ) else: - print (('VMBUS ID ' + format2) % \ - (d.vmbus_id, d.class_id, d.dev_desc, \ - d.device_id, d.sysfs_path, d.chn_vp_mapping)) + print( + ('VMBUS ID ' + format2) % + ( + d.vmbus_id, d.class_id, d.dev_desc, + d.device_id, d.sysfs_path, d.chn_vp_mapping + ) + ) From b0995156071b0ff29a5902964a9dc8cfad6f81c0 Mon Sep 17 00:00:00 2001 From: Adrian Vladu Date: Mon, 6 May 2019 16:50:58 +0000 Subject: [PATCH 153/157] tools: hv: fix KVP and VSS daemons exit code HyperV KVP and VSS daemons should exit with 0 when the '--help' or '-h' flags are used. Signed-off-by: Adrian Vladu Cc: "K. Y. Srinivasan" Cc: Haiyang Zhang Cc: Stephen Hemminger Cc: Sasha Levin Cc: Alessandro Pilotti Signed-off-by: Sasha Levin --- tools/hv/hv_kvp_daemon.c | 2 ++ tools/hv/hv_vss_daemon.c | 2 ++ 2 files changed, 4 insertions(+) diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c index d7e06fe0270e..0ce50c319cfd 100644 --- a/tools/hv/hv_kvp_daemon.c +++ b/tools/hv/hv_kvp_daemon.c @@ -1386,6 +1386,8 @@ int main(int argc, char *argv[]) daemonize = 0; break; case 'h': + print_usage(argv); + exit(0); default: print_usage(argv); exit(EXIT_FAILURE); diff --git a/tools/hv/hv_vss_daemon.c b/tools/hv/hv_vss_daemon.c index efe1e34dd91b..8f813f5233d4 100644 --- a/tools/hv/hv_vss_daemon.c +++ b/tools/hv/hv_vss_daemon.c @@ -218,6 +218,8 @@ int main(int argc, char *argv[]) daemonize = 0; break; case 'h': + print_usage(argv); + exit(0); default: print_usage(argv); exit(EXIT_FAILURE); From 2d35c66036b2494c329a32468c85405493370e75 Mon Sep 17 00:00:00 2001 From: Adrian Vladu Date: Mon, 6 May 2019 16:51:24 +0000 Subject: [PATCH 154/157] tools: hv: fix typos in toolchain Fix typos in the HyperV toolchain. Signed-off-by: Adrian Vladu Cc: "K. Y. Srinivasan" Cc: Haiyang Zhang Cc: Stephen Hemminger Cc: Sasha Levin Cc: Alessandro Pilotti Signed-off-by: Sasha Levin --- tools/hv/hv_get_dhcp_info.sh | 2 +- tools/hv/hv_kvp_daemon.c | 6 +++--- tools/hv/hv_set_ifconfig.sh | 2 +- tools/hv/hv_vss_daemon.c | 2 +- 4 files changed, 6 insertions(+), 6 deletions(-) diff --git a/tools/hv/hv_get_dhcp_info.sh b/tools/hv/hv_get_dhcp_info.sh index c38686c44656..2f2a3c7df3de 100755 --- a/tools/hv/hv_get_dhcp_info.sh +++ b/tools/hv/hv_get_dhcp_info.sh @@ -13,7 +13,7 @@ # the script prints the string "Disabled" to stdout. # # Each Distro is expected to implement this script in a distro specific -# fashion. For instance on Distros that ship with Network Manager enabled, +# fashion. For instance, on Distros that ship with Network Manager enabled, # this script can be based on the Network Manager APIs for retrieving DHCP # information. diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c index 0ce50c319cfd..f5597503c771 100644 --- a/tools/hv/hv_kvp_daemon.c +++ b/tools/hv/hv_kvp_daemon.c @@ -700,7 +700,7 @@ static void kvp_get_ipconfig_info(char *if_name, /* - * Gather the DNS state. + * Gather the DNS state. * Since there is no standard way to get this information * across various distributions of interest; we just invoke * an external script that needs to be ported across distros @@ -1051,7 +1051,7 @@ static int parse_ip_val_buffer(char *in_buf, int *offset, char *start; /* - * in_buf has sequence of characters that are seperated by + * in_buf has sequence of characters that are separated by * the character ';'. The last sequence does not have the * terminating ";" character. */ @@ -1492,7 +1492,7 @@ int main(int argc, char *argv[]) case KVP_OP_GET_IP_INFO: kvp_ip_val = &hv_msg->body.kvp_ip_val; - error = kvp_mac_to_ip(kvp_ip_val); + error = kvp_mac_to_ip(kvp_ip_val); if (error) hv_msg->error = error; diff --git a/tools/hv/hv_set_ifconfig.sh b/tools/hv/hv_set_ifconfig.sh index 7ed9f85ef908..d10fe35b7f25 100755 --- a/tools/hv/hv_set_ifconfig.sh +++ b/tools/hv/hv_set_ifconfig.sh @@ -12,7 +12,7 @@ # be used to configure the interface. # # Each Distro is expected to implement this script in a distro specific -# fashion. For instance on Distros that ship with Network Manager enabled, +# fashion. For instance, on Distros that ship with Network Manager enabled, # this script can be based on the Network Manager APIs for configuring the # interface. # diff --git a/tools/hv/hv_vss_daemon.c b/tools/hv/hv_vss_daemon.c index 8f813f5233d4..92902a88f671 100644 --- a/tools/hv/hv_vss_daemon.c +++ b/tools/hv/hv_vss_daemon.c @@ -42,7 +42,7 @@ static int vss_do_freeze(char *dir, unsigned int cmd) * If a partition is mounted more than once, only the first * FREEZE/THAW can succeed and the later ones will get * EBUSY/EINVAL respectively: there could be 2 cases: - * 1) a user may mount the same partition to differnt directories + * 1) a user may mount the same partition to different directories * by mistake or on purpose; * 2) The subvolume of btrfs appears to have the same partition * mounted more than once. From 61e0f39105b7926a41bc03158eccf5ed13207ebd Mon Sep 17 00:00:00 2001 From: Nishad Kamdar Date: Mon, 22 Jul 2019 19:01:17 +0530 Subject: [PATCH 155/157] tools: hv: Use the correct style for SPDX License Identifier This patch corrects the SPDX License Identifier style in the trace header file related to Microsoft Hyper-V client drivers. For C header files Documentation/process/license-rules.rst mandates C-like comments (opposed to C source files where C++ style should be used) Changes made by using a script provided by Joe Perches here: https://lkml.org/lkml/2019/2/7/46 Suggested-by: Joe Perches Signed-off-by: Nishad Kamdar Acked-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/hv/hv_trace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hv/hv_trace.h b/drivers/hv/hv_trace.h index 999f80a63bff..e70783e33680 100644 --- a/drivers/hv/hv_trace.h +++ b/drivers/hv/hv_trace.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM hyperv From bafe1e79e05de725e26b3f60c90b49e635b686b9 Mon Sep 17 00:00:00 2001 From: Lan Tianyu Date: Tue, 26 Mar 2019 14:28:21 +0800 Subject: [PATCH 156/157] MAINTAINERS: Fix Hyperv vIOMMU driver file name The Hyperv vIOMMU file name should be "hyperv-iommu.c" rather than "hyperv_iommu.c". This patch is to fix it. Signed-off-by: Lan Tianyu Signed-off-by: Sasha Levin --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 783569e3c4b4..b03179510e26 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7454,7 +7454,7 @@ F: drivers/net/hyperv/ F: drivers/scsi/storvsc_drv.c F: drivers/uio/uio_hv_generic.c F: drivers/video/fbdev/hyperv_fb.c -F: drivers/iommu/hyperv_iommu.c +F: drivers/iommu/hyperv-iommu.c F: net/vmw_vsock/hyperv_transport.c F: include/clocksource/hyperv_timer.h F: include/linux/hyperv.h From d1abaeb3be7b5fa6d7a1fbbd2e14e3310005c4c1 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 18 Aug 2019 14:31:08 -0700 Subject: [PATCH 157/157] Linux 5.3-rc5 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 1b23f95db176..9fa18613566f 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 3 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc5 NAME = Bobtail Squid # *DOCUMENTATION*