From fdc0074c5fc8c7adb8186cbb123fe2082d9bd05f Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Mon, 9 Feb 2015 18:23:20 +0800 Subject: [PATCH 001/170] ARM: sunxi: Have ARCH_SUNXI select RESET_CONTROLLER for clock driver usage As the sunxi usb clocks all contain a reset controller, it is not possible to build the sunxi clock driver without RESET_CONTROLLER enabled. Doing so results in an undefined symbol error: drivers/built-in.o: In function `sunxi_gates_clk_setup': linux/drivers/clk/sunxi/clk-sunxi.c:1071: undefined reference to `reset_controller_register' This is possible if building a minimal kernel without PHY_SUN4I_USB. The dependency issue is made visible at compile time instead of link time by the new A80 mmc clocks, which also use a reset control itself. This patch makes ARCH_SUNXI select ARCH_HAS_RESET_CONTROLLER and RESET_CONTROLLER. Fixes: 559482d1f950 ARM: sunxi: Split the various SoCs support in Kconfig Cc: # 3.16+ Reported-by: Lourens Rozema Acked-by: Arnd Bergmann Signed-off-by: Chen-Yu Tsai Signed-off-by: Maxime Ripard --- arch/arm/mach-sunxi/Kconfig | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/arch/arm/mach-sunxi/Kconfig b/arch/arm/mach-sunxi/Kconfig index a77604fbaf25..81502b90dd91 100644 --- a/arch/arm/mach-sunxi/Kconfig +++ b/arch/arm/mach-sunxi/Kconfig @@ -1,10 +1,12 @@ menuconfig ARCH_SUNXI bool "Allwinner SoCs" if ARCH_MULTI_V7 select ARCH_REQUIRE_GPIOLIB + select ARCH_HAS_RESET_CONTROLLER select CLKSRC_MMIO select GENERIC_IRQ_CHIP select PINCTRL select SUN4I_TIMER + select RESET_CONTROLLER if ARCH_SUNXI @@ -20,10 +22,8 @@ config MACH_SUN5I config MACH_SUN6I bool "Allwinner A31 (sun6i) SoCs support" default ARCH_SUNXI - select ARCH_HAS_RESET_CONTROLLER select ARM_GIC select MFD_SUN6I_PRCM - select RESET_CONTROLLER select SUN5I_HSTIMER config MACH_SUN7I @@ -37,16 +37,12 @@ config MACH_SUN7I config MACH_SUN8I bool "Allwinner A23 (sun8i) SoCs support" default ARCH_SUNXI - select ARCH_HAS_RESET_CONTROLLER select ARM_GIC select MFD_SUN6I_PRCM - select RESET_CONTROLLER config MACH_SUN9I bool "Allwinner (sun9i) SoCs support" default ARCH_SUNXI - select ARCH_HAS_RESET_CONTROLLER select ARM_GIC - select RESET_CONTROLLER endif From 5c0c75d33d45a8dc7a2af815834812d41f5361e8 Mon Sep 17 00:00:00 2001 From: Masanari Iida Date: Sat, 31 Jan 2015 14:49:38 +0900 Subject: [PATCH 002/170] ARM: pxa: Fix typo in zeus.c This patch fix a typo in struct platform_device can_regulator_device. Signed-off-by: Masanari Iida Acked-by: Daniel Mack Signed-off-by: Robert Jarzmik --- arch/arm/mach-pxa/zeus.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/mach-pxa/zeus.c b/arch/arm/mach-pxa/zeus.c index 205f9bf3821e..ac2ae5c71ab4 100644 --- a/arch/arm/mach-pxa/zeus.c +++ b/arch/arm/mach-pxa/zeus.c @@ -412,7 +412,7 @@ static struct fixed_voltage_config can_regulator_pdata = { }; static struct platform_device can_regulator_device = { - .name = "reg-fixed-volage", + .name = "reg-fixed-voltage", .id = 0, .dev = { .platform_data = &can_regulator_pdata, From d6cf30ca716b347587b35923eda400ad2d9e8832 Mon Sep 17 00:00:00 2001 From: Robert Jarzmik Date: Sat, 14 Feb 2015 22:41:56 +0100 Subject: [PATCH 003/170] ARM: pxa: fix pxa interrupts handling in DT The commit "ARM: pxa: arbitrarily set first interrupt number" changed the first pxa interrupt to 16. As a consequence, device-tree builds got broken, because : - pxa_mask_irq() and pxa_unmask_irq() are using IRQ_BIT() - IRQ_BIT(x) calculates the interrupts as : x - PXA_IRQ(0) Before the commit, the first interrupt shift, PXA_IRQ(0) was 0, therefore IRQ_BIT(x) was x. After the change, it is necessary that the same shift of 16 is applied between the virtual interrupt number and the hardware irq number. This situation comes from the common irq_chip shared between legacy platform builds and device-tree builds. Fix the broken interrupts in DT case by adding this shift in the DT case too. As a consequence of the IRQ_BIT() is removed alltogether from interrupts handling, even in the platform data types of platforms : - a legacy irq domain is used - the irq_chip handles hardware interrupts - the virtual to hardware interrupt conversion is fully handled by irq domain mechanics Signed-off-by: Robert Jarzmik --- arch/arm/Kconfig | 1 + arch/arm/mach-pxa/irq.c | 111 +++++++++++++++++----------------------- 2 files changed, 49 insertions(+), 63 deletions(-) diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 9f1f09a2bc9b..cf4c0c99aa25 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -619,6 +619,7 @@ config ARCH_PXA select GENERIC_CLOCKEVENTS select GPIO_PXA select HAVE_IDE + select IRQ_DOMAIN select MULTI_IRQ_HANDLER select PLAT_PXA select SPARSE_IRQ diff --git a/arch/arm/mach-pxa/irq.c b/arch/arm/mach-pxa/irq.c index 0eecd83c624e..89a7c06570d3 100644 --- a/arch/arm/mach-pxa/irq.c +++ b/arch/arm/mach-pxa/irq.c @@ -11,6 +11,7 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ +#include #include #include #include @@ -40,7 +41,6 @@ #define ICHP_VAL_IRQ (1 << 31) #define ICHP_IRQ(i) (((i) >> 16) & 0x7fff) #define IPR_VALID (1 << 31) -#define IRQ_BIT(n) (((n) - PXA_IRQ(0)) & 0x1f) #define MAX_INTERNAL_IRQS 128 @@ -51,6 +51,7 @@ static void __iomem *pxa_irq_base; static int pxa_internal_irq_nr; static bool cpu_has_ipr; +static struct irq_domain *pxa_irq_domain; static inline void __iomem *irq_base(int i) { @@ -66,18 +67,20 @@ static inline void __iomem *irq_base(int i) void pxa_mask_irq(struct irq_data *d) { void __iomem *base = irq_data_get_irq_chip_data(d); + irq_hw_number_t irq = irqd_to_hwirq(d); uint32_t icmr = __raw_readl(base + ICMR); - icmr &= ~(1 << IRQ_BIT(d->irq)); + icmr &= ~BIT(irq & 0x1f); __raw_writel(icmr, base + ICMR); } void pxa_unmask_irq(struct irq_data *d) { void __iomem *base = irq_data_get_irq_chip_data(d); + irq_hw_number_t irq = irqd_to_hwirq(d); uint32_t icmr = __raw_readl(base + ICMR); - icmr |= 1 << IRQ_BIT(d->irq); + icmr |= BIT(irq & 0x1f); __raw_writel(icmr, base + ICMR); } @@ -118,40 +121,63 @@ asmlinkage void __exception_irq_entry ichp_handle_irq(struct pt_regs *regs) } while (1); } -void __init pxa_init_irq(int irq_nr, int (*fn)(struct irq_data *, unsigned int)) +static int pxa_irq_map(struct irq_domain *h, unsigned int virq, + irq_hw_number_t hw) { - int irq, i, n; + void __iomem *base = irq_base(hw / 32); - BUG_ON(irq_nr > MAX_INTERNAL_IRQS); + /* initialize interrupt priority */ + if (cpu_has_ipr) + __raw_writel(hw | IPR_VALID, pxa_irq_base + IPR(hw)); + + irq_set_chip_and_handler(virq, &pxa_internal_irq_chip, + handle_level_irq); + irq_set_chip_data(virq, base); + set_irq_flags(virq, IRQF_VALID); + + return 0; +} + +static struct irq_domain_ops pxa_irq_ops = { + .map = pxa_irq_map, + .xlate = irq_domain_xlate_onecell, +}; + +static __init void +pxa_init_irq_common(struct device_node *node, int irq_nr, + int (*fn)(struct irq_data *, unsigned int)) +{ + int n; pxa_internal_irq_nr = irq_nr; - cpu_has_ipr = !cpu_is_pxa25x(); - pxa_irq_base = io_p2v(0x40d00000); + pxa_irq_domain = irq_domain_add_legacy(node, irq_nr, + PXA_IRQ(0), 0, + &pxa_irq_ops, NULL); + if (!pxa_irq_domain) + panic("Unable to add PXA IRQ domain\n"); + irq_set_default_host(pxa_irq_domain); for (n = 0; n < irq_nr; n += 32) { void __iomem *base = irq_base(n >> 5); __raw_writel(0, base + ICMR); /* disable all IRQs */ __raw_writel(0, base + ICLR); /* all IRQs are IRQ, not FIQ */ - for (i = n; (i < (n + 32)) && (i < irq_nr); i++) { - /* initialize interrupt priority */ - if (cpu_has_ipr) - __raw_writel(i | IPR_VALID, pxa_irq_base + IPR(i)); - - irq = PXA_IRQ(i); - irq_set_chip_and_handler(irq, &pxa_internal_irq_chip, - handle_level_irq); - irq_set_chip_data(irq, base); - set_irq_flags(irq, IRQF_VALID); - } } - /* only unmasked interrupts kick us out of idle */ __raw_writel(1, irq_base(0) + ICCR); pxa_internal_irq_chip.irq_set_wake = fn; } +void __init pxa_init_irq(int irq_nr, int (*fn)(struct irq_data *, unsigned int)) +{ + BUG_ON(irq_nr > MAX_INTERNAL_IRQS); + + pxa_irq_base = io_p2v(0x40d00000); + cpu_has_ipr = !cpu_is_pxa25x(); + pxa_init_irq_common(NULL, irq_nr, fn); +} + #ifdef CONFIG_PM static unsigned long saved_icmr[MAX_INTERNAL_IRQS/32]; static unsigned long saved_ipr[MAX_INTERNAL_IRQS]; @@ -203,30 +229,6 @@ struct syscore_ops pxa_irq_syscore_ops = { }; #ifdef CONFIG_OF -static struct irq_domain *pxa_irq_domain; - -static int pxa_irq_map(struct irq_domain *h, unsigned int virq, - irq_hw_number_t hw) -{ - void __iomem *base = irq_base(hw / 32); - - /* initialize interrupt priority */ - if (cpu_has_ipr) - __raw_writel(hw | IPR_VALID, pxa_irq_base + IPR(hw)); - - irq_set_chip_and_handler(hw, &pxa_internal_irq_chip, - handle_level_irq); - irq_set_chip_data(hw, base); - set_irq_flags(hw, IRQF_VALID); - - return 0; -} - -static struct irq_domain_ops pxa_irq_ops = { - .map = pxa_irq_map, - .xlate = irq_domain_xlate_onecell, -}; - static const struct of_device_id intc_ids[] __initconst = { { .compatible = "marvell,pxa-intc", }, {} @@ -236,7 +238,7 @@ void __init pxa_dt_irq_init(int (*fn)(struct irq_data *, unsigned int)) { struct device_node *node; struct resource res; - int n, ret; + int ret; node = of_find_matching_node(NULL, intc_ids); if (!node) { @@ -267,23 +269,6 @@ void __init pxa_dt_irq_init(int (*fn)(struct irq_data *, unsigned int)) return; } - pxa_irq_domain = irq_domain_add_legacy(node, pxa_internal_irq_nr, 0, 0, - &pxa_irq_ops, NULL); - if (!pxa_irq_domain) - panic("Unable to add PXA IRQ domain\n"); - - irq_set_default_host(pxa_irq_domain); - - for (n = 0; n < pxa_internal_irq_nr; n += 32) { - void __iomem *base = irq_base(n >> 5); - - __raw_writel(0, base + ICMR); /* disable all IRQs */ - __raw_writel(0, base + ICLR); /* all IRQs are IRQ, not FIQ */ - } - - /* only unmasked interrupts kick us out of idle */ - __raw_writel(1, irq_base(0) + ICCR); - - pxa_internal_irq_chip.irq_set_wake = fn; + pxa_init_irq_common(node, pxa_internal_irq_nr, fn); } #endif /* CONFIG_OF */ From 7d70e15480c0450d2bfafaad338a32e884fc215e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 4 Mar 2015 10:37:43 -0500 Subject: [PATCH 004/170] writeback: add missing INITIAL_JIFFIES init in global_update_bandwidth() global_update_bandwidth() uses static variable update_time as the timestamp for the last update but forgets to initialize it to INITIALIZE_JIFFIES. This means that global_dirty_limit will be 5 mins into the future on 32bit and some large amount jiffies into the past on 64bit. This isn't critical as the only effect is that global_dirty_limit won't be updated for the first 5 mins after booting on 32bit machines, especially given the auxiliary nature of global_dirty_limit's role - protecting against global dirty threshold's sudden dips; however, it does lead to unintended suboptimal behavior. Fix it. Fixes: c42843f2f0bb ("writeback: introduce smoothed global dirty limit") Signed-off-by: Tejun Heo Acked-by: Jan Kara Cc: Wu Fengguang Cc: Jens Axboe Cc: stable@vger.kernel.org Signed-off-by: Jens Axboe --- mm/page-writeback.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 45e187b2d971..b4fd980a93eb 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -922,7 +922,7 @@ static void global_update_bandwidth(unsigned long thresh, unsigned long now) { static DEFINE_SPINLOCK(dirty_lock); - static unsigned long update_time; + static unsigned long update_time = INITIAL_JIFFIES; /* * check locklessly first to optimize away locking for the most time From ff6b8090e26ef7649ef0cc6b42389141ef48b0cf Mon Sep 17 00:00:00 2001 From: Sudip Mukherjee Date: Tue, 27 Jan 2015 18:08:22 +0530 Subject: [PATCH 005/170] nbd: fix possible memory leak we have already allocated memory for nbd_dev, but we were not releasing that memory and just returning the error value. Signed-off-by: Sudip Mukherjee Acked-by: Paul Clements Cc: Signed-off-by: Markus Pargmann --- drivers/block/nbd.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 4bc2a5cb9935..a98c41f72c63 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -803,10 +803,6 @@ static int __init nbd_init(void) return -EINVAL; } - nbd_dev = kcalloc(nbds_max, sizeof(*nbd_dev), GFP_KERNEL); - if (!nbd_dev) - return -ENOMEM; - part_shift = 0; if (max_part > 0) { part_shift = fls(max_part); @@ -828,6 +824,10 @@ static int __init nbd_init(void) if (nbds_max > 1UL << (MINORBITS - part_shift)) return -EINVAL; + nbd_dev = kcalloc(nbds_max, sizeof(*nbd_dev), GFP_KERNEL); + if (!nbd_dev) + return -ENOMEM; + for (i = 0; i < nbds_max; i++) { struct gendisk *disk = alloc_disk(1 << part_shift); if (!disk) From 32c006a99799f6f3c759b77ba761c3a5981e34eb Mon Sep 17 00:00:00 2001 From: Kevin Hao Date: Thu, 12 Feb 2015 14:52:49 +0800 Subject: [PATCH 006/170] gpio: mpc8xxx: remove __initdata annotation for mpc8xxx_gpio_ids[] Since commit 98686d9a52ee ("gpio: mpc8xxx: Convert to platform device interface"), we get the following section mismatch warning. Remove the __initdata annotation to fix it. WARNING: vmlinux.o(.data+0xbc28): Section mismatch in reference from the variable mpc8xxx_plat_driver to the variable .init.data:mpc8xxx_gpio_ids The variable mpc8xxx_plat_driver references the variable __initdata mpc8xxx_gpio_ids If the reference is valid then annotate the variable with __init* or __refdata (see linux/init.h) or name the variable: *_template, *_timer, *_sht, *_ops, *_probe, *_probe_one, *_console Signed-off-by: Kevin Hao Signed-off-by: Linus Walleij --- drivers/gpio/gpio-mpc8xxx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpio/gpio-mpc8xxx.c b/drivers/gpio/gpio-mpc8xxx.c index a6952ba343a8..a65b75161aa4 100644 --- a/drivers/gpio/gpio-mpc8xxx.c +++ b/drivers/gpio/gpio-mpc8xxx.c @@ -334,7 +334,7 @@ static struct irq_domain_ops mpc8xxx_gpio_irq_ops = { .xlate = irq_domain_xlate_twocell, }; -static struct of_device_id mpc8xxx_gpio_ids[] __initdata = { +static struct of_device_id mpc8xxx_gpio_ids[] = { { .compatible = "fsl,mpc8349-gpio", }, { .compatible = "fsl,mpc8572-gpio", }, { .compatible = "fsl,mpc8610-gpio", }, From 12cb89e37a0c25fae7a0f1d2e4985558db9d0b13 Mon Sep 17 00:00:00 2001 From: "Ivan T. Ivanov" Date: Fri, 6 Mar 2015 17:26:17 +0200 Subject: [PATCH 007/170] spi: qup: Fix cs-num DT property parsing num-cs is 32 bit property, don't read just upper 16 bits. Fixes: 4a8573abe965 (spi: qup: Remove chip select function) Signed-off-by: Ivan T. Ivanov Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- drivers/spi/spi-qup.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/spi/spi-qup.c b/drivers/spi/spi-qup.c index ff9cdbdb6672..2b2c359f5a50 100644 --- a/drivers/spi/spi-qup.c +++ b/drivers/spi/spi-qup.c @@ -498,7 +498,7 @@ static int spi_qup_probe(struct platform_device *pdev) struct resource *res; struct device *dev; void __iomem *base; - u32 max_freq, iomode; + u32 max_freq, iomode, num_cs; int ret, irq, size; dev = &pdev->dev; @@ -550,10 +550,11 @@ static int spi_qup_probe(struct platform_device *pdev) } /* use num-cs unless not present or out of range */ - if (of_property_read_u16(dev->of_node, "num-cs", - &master->num_chipselect) || - (master->num_chipselect > SPI_NUM_CHIPSELECTS)) + if (of_property_read_u32(dev->of_node, "num-cs", &num_cs) || + num_cs > SPI_NUM_CHIPSELECTS) master->num_chipselect = SPI_NUM_CHIPSELECTS; + else + master->num_chipselect = num_cs; master->bus_num = pdev->id; master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_LOOP; From 854d2f241d71f6ca08ccde30e6c7c2e403363e52 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 6 Mar 2015 14:42:01 +0200 Subject: [PATCH 008/170] spi: dw-mid: clear BUSY flag fist and test other one The logic of DMA completion is broken now since test_and_clear_bit() never returns the other bit is set. It means condition are always false and we have spi_finalize_current_transfer() called per each DMA completion which is wrong. The patch fixes logic by clearing BUSY bit first and then check for the other one. Fixes: 30c8eb52cc4a (spi: dw-mid: split rx and tx callbacks when DMA) Signed-off-by: Andy Shevchenko Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- drivers/spi/spi-dw-mid.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/spi/spi-dw-mid.c b/drivers/spi/spi-dw-mid.c index 3ce39d10fafb..4f8c798e0633 100644 --- a/drivers/spi/spi-dw-mid.c +++ b/drivers/spi/spi-dw-mid.c @@ -108,7 +108,8 @@ static void dw_spi_dma_tx_done(void *arg) { struct dw_spi *dws = arg; - if (test_and_clear_bit(TX_BUSY, &dws->dma_chan_busy) & BIT(RX_BUSY)) + clear_bit(TX_BUSY, &dws->dma_chan_busy); + if (test_bit(RX_BUSY, &dws->dma_chan_busy)) return; dw_spi_xfer_done(dws); } @@ -156,7 +157,8 @@ static void dw_spi_dma_rx_done(void *arg) { struct dw_spi *dws = arg; - if (test_and_clear_bit(RX_BUSY, &dws->dma_chan_busy) & BIT(TX_BUSY)) + clear_bit(RX_BUSY, &dws->dma_chan_busy); + if (test_bit(TX_BUSY, &dws->dma_chan_busy)) return; dw_spi_xfer_done(dws); } From 3a43477fa36eee2997313380cb52f486e2bff316 Mon Sep 17 00:00:00 2001 From: Roger Tseng Date: Fri, 6 Mar 2015 11:36:06 +0800 Subject: [PATCH 009/170] mfd: rtsx_usb: Prevent DMA from stack Functions rtsx_usb_ep0_read_register() and rtsx_usb_get_card_status() both use arbitrary buffer addresses from arguments directly for DMA and the buffers could be located in stack. This was caught by DMA-API debug check. Fixes this by using double-buffers via kzalloc in both functions to guarantee the validity of DMA buffer. WARNING: CPU: 1 PID: 25 at lib/dma-debug.c:1166 check_for_stack+0x96/0xe0() ehci-pci 0000:00:1a.0: DMA-API: device driver maps memory from stack [addr=ffff8801199e3cef] Modules linked in: rtsx_usb_ms arc4 memstick intel_rapl iosf_mbi rtl8192ce snd_hda_codec_hdmi snd_hda_codec_realtek snd_hda_codec_generic snd_hda_intel rtl_pci rtl8192c_common snd_hda_controller x86_pkg_temp_thermal snd_hda_codec rtlwifi mac80211 coretemp kvm_intel kvm iTCO_wdt snd_hwdep snd_seq snd_seq_device crct10dif_pclmul iTCO_vendor_support sparse_keymap cfg80211 crc32_pclmul snd_pcm crc32c_intel ghash_clmulni_intel rfkill i2c_i801 snd_timer shpchp snd serio_raw mei_me lpc_ich soundcore mei tpm_tis tpm wmi nfsd auth_rpcgss nfs_acl lockd grace sunrpc i915 rtsx_usb_sdmmc mmc_core 8021q uas garp stp i2c_algo_bit llc mrp drm_kms_helper usb_storage drm rtsx_usb mfd_core r8169 mii video CPU: 1 PID: 25 Comm: kworker/1:2 Not tainted 3.20.0-0.rc0.git7.3.fc22.x86_64 #1 Hardware name: WB WB-B06211/WB-B0621, BIOS EB062IWB V1.0 12/12/2013 Workqueue: events rtsx_usb_ms_handle_req [rtsx_usb_ms] 0000000000000000 000000003d188e66 ffff8801199e3808 ffffffff8187642b 0000000000000000 ffff8801199e3860 ffff8801199e3848 ffffffff810ab39a ffff8801199e3864 ffff8801199e3cef ffff880119b57098 ffff880119b37320 Call Trace: [] dump_stack+0x4c/0x65 [] warn_slowpath_common+0x8a/0xc0 [] warn_slowpath_fmt+0x55/0x70 [] ? _raw_spin_unlock_irqrestore+0x36/0x70 [] check_for_stack+0x96/0xe0 [] debug_dma_map_page+0x104/0x150 [] usb_hcd_map_urb_for_dma+0x646/0x790 [] usb_hcd_submit_urb+0x1d5/0xa90 [] ? mark_held_locks+0x7f/0xc0 [] ? mark_held_locks+0x7f/0xc0 [] ? lockdep_init_map+0x65/0x5d0 [] usb_submit_urb+0x42e/0x5f0 [] usb_start_wait_urb+0x77/0x190 [] ? __kmalloc+0x205/0x2d0 [] usb_control_msg+0xdc/0x130 [] rtsx_usb_ep0_read_register+0x59/0x70 [rtsx_usb] [] ? rtsx_usb_get_rsp+0x41/0x50 [rtsx_usb] [] rtsx_usb_ms_handle_req+0x7ce/0x9c5 [rtsx_usb_ms] Reported-by: Josh Boyer Signed-off-by: Roger Tseng Signed-off-by: Lee Jones --- drivers/mfd/rtsx_usb.c | 30 ++++++++++++++++++++++++------ 1 file changed, 24 insertions(+), 6 deletions(-) diff --git a/drivers/mfd/rtsx_usb.c b/drivers/mfd/rtsx_usb.c index ede50244f265..dbd907d7170e 100644 --- a/drivers/mfd/rtsx_usb.c +++ b/drivers/mfd/rtsx_usb.c @@ -196,18 +196,27 @@ EXPORT_SYMBOL_GPL(rtsx_usb_ep0_write_register); int rtsx_usb_ep0_read_register(struct rtsx_ucr *ucr, u16 addr, u8 *data) { u16 value; + u8 *buf; + int ret; if (!data) return -EINVAL; - *data = 0; + + buf = kzalloc(sizeof(u8), GFP_KERNEL); + if (!buf) + return -ENOMEM; addr |= EP0_READ_REG_CMD << EP0_OP_SHIFT; value = swab16(addr); - return usb_control_msg(ucr->pusb_dev, + ret = usb_control_msg(ucr->pusb_dev, usb_rcvctrlpipe(ucr->pusb_dev, 0), RTSX_USB_REQ_REG_OP, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, - value, 0, data, 1, 100); + value, 0, buf, 1, 100); + *data = *buf; + + kfree(buf); + return ret; } EXPORT_SYMBOL_GPL(rtsx_usb_ep0_read_register); @@ -288,18 +297,27 @@ static int rtsx_usb_get_status_with_bulk(struct rtsx_ucr *ucr, u16 *status) int rtsx_usb_get_card_status(struct rtsx_ucr *ucr, u16 *status) { int ret; + u16 *buf; if (!status) return -EINVAL; - if (polling_pipe == 0) + if (polling_pipe == 0) { + buf = kzalloc(sizeof(u16), GFP_KERNEL); + if (!buf) + return -ENOMEM; + ret = usb_control_msg(ucr->pusb_dev, usb_rcvctrlpipe(ucr->pusb_dev, 0), RTSX_USB_REQ_POLL, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, - 0, 0, status, 2, 100); - else + 0, 0, buf, 2, 100); + *status = *buf; + + kfree(buf); + } else { ret = rtsx_usb_get_status_with_bulk(ucr, status); + } /* usb_control_msg may return positive when success */ if (ret < 0) From c8648508ebfc597058d2cd00b6c539110264a167 Mon Sep 17 00:00:00 2001 From: Ameya Palande <2ameya@gmail.com> Date: Thu, 26 Feb 2015 12:05:51 -0800 Subject: [PATCH 010/170] mfd: kempld-core: Fix callback return value check On success, callback function returns 0. So invert the if condition check so that we can break out of loop. Cc: stable@vger.kernel.org Signed-off-by: Ameya Palande <2ameya@gmail.com> Signed-off-by: Lee Jones --- drivers/mfd/kempld-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mfd/kempld-core.c b/drivers/mfd/kempld-core.c index f38ec424872e..5615522f8d62 100644 --- a/drivers/mfd/kempld-core.c +++ b/drivers/mfd/kempld-core.c @@ -739,7 +739,7 @@ static int __init kempld_init(void) for (id = kempld_dmi_table; id->matches[0].slot != DMI_NONE; id++) if (strstr(id->ident, force_device_id)) - if (id->callback && id->callback(id)) + if (id->callback && !id->callback(id)) break; if (id->matches[0].slot == DMI_NONE) return -ENODEV; From 0a64815091bd0ad6c6cdfaac2fae55b0f3ecf974 Mon Sep 17 00:00:00 2001 From: Hendrik Brueckner Date: Mon, 9 Mar 2015 17:34:18 +0100 Subject: [PATCH 011/170] s390/cpum_sf: add diagnostic sampling event only if it is authorized The SF_CYCLES_BASIC_DIAG is always registered even if it is turned of in the current hardware configuration. Because diagnostic-sampling is typically not turned on in the hardware configuration, do not register this perf event by default. Enable it only if the diagnostic-sampling function is authorized. Signed-off-by: Hendrik Brueckner Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/perf_cpum_sf.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index c3f8d157cb0d..e6a1578fc000 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -1415,7 +1415,7 @@ CPUMF_EVENT_ATTR(SF, SF_CYCLES_BASIC_DIAG, PERF_EVENT_CPUM_SF_DIAG); static struct attribute *cpumsf_pmu_events_attr[] = { CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC), - CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC_DIAG), + NULL, NULL, }; @@ -1606,8 +1606,11 @@ static int __init init_cpum_sampling_pmu(void) return -EINVAL; } - if (si.ad) + if (si.ad) { sfb_set_limits(CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB); + cpumsf_pmu_events_attr[1] = + CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC_DIAG); + } sfdbg = debug_register(KMSG_COMPONENT, 2, 1, 80); if (!sfdbg) From 20e76ee184a7cea155268377c4e414eea1dab6fd Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 13 Mar 2015 10:31:42 +0100 Subject: [PATCH 012/170] s390/ftrace: fix compile error if CONFIG_KPROBES is disabled Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/ftrace.c | 61 +++++++++++++++++++++++++++++---------- 1 file changed, 45 insertions(+), 16 deletions(-) diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 82c19899574f..6c79f1b44fe7 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -57,6 +57,44 @@ unsigned long ftrace_plt; +static inline void ftrace_generate_orig_insn(struct ftrace_insn *insn) +{ +#ifdef CC_USING_HOTPATCH + /* brcl 0,0 */ + insn->opc = 0xc004; + insn->disp = 0; +#else + /* stg r14,8(r15) */ + insn->opc = 0xe3e0; + insn->disp = 0xf0080024; +#endif +} + +static inline int is_kprobe_on_ftrace(struct ftrace_insn *insn) +{ +#ifdef CONFIG_KPROBES + if (insn->opc == BREAKPOINT_INSTRUCTION) + return 1; +#endif + return 0; +} + +static inline void ftrace_generate_kprobe_nop_insn(struct ftrace_insn *insn) +{ +#ifdef CONFIG_KPROBES + insn->opc = BREAKPOINT_INSTRUCTION; + insn->disp = KPROBE_ON_FTRACE_NOP; +#endif +} + +static inline void ftrace_generate_kprobe_call_insn(struct ftrace_insn *insn) +{ +#ifdef CONFIG_KPROBES + insn->opc = BREAKPOINT_INSTRUCTION; + insn->disp = KPROBE_ON_FTRACE_CALL; +#endif +} + int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr) { @@ -72,16 +110,9 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, return -EFAULT; if (addr == MCOUNT_ADDR) { /* Initial code replacement */ -#ifdef CC_USING_HOTPATCH - /* We expect to see brcl 0,0 */ - ftrace_generate_nop_insn(&orig); -#else - /* We expect to see stg r14,8(r15) */ - orig.opc = 0xe3e0; - orig.disp = 0xf0080024; -#endif + ftrace_generate_orig_insn(&orig); ftrace_generate_nop_insn(&new); - } else if (old.opc == BREAKPOINT_INSTRUCTION) { + } else if (is_kprobe_on_ftrace(&old)) { /* * If we find a breakpoint instruction, a kprobe has been * placed at the beginning of the function. We write the @@ -89,9 +120,8 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, * bytes of the original instruction so that the kprobes * handler can execute a nop, if it reaches this breakpoint. */ - new.opc = orig.opc = BREAKPOINT_INSTRUCTION; - orig.disp = KPROBE_ON_FTRACE_CALL; - new.disp = KPROBE_ON_FTRACE_NOP; + ftrace_generate_kprobe_call_insn(&orig); + ftrace_generate_kprobe_nop_insn(&new); } else { /* Replace ftrace call with a nop. */ ftrace_generate_call_insn(&orig, rec->ip); @@ -111,7 +141,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) if (probe_kernel_read(&old, (void *) rec->ip, sizeof(old))) return -EFAULT; - if (old.opc == BREAKPOINT_INSTRUCTION) { + if (is_kprobe_on_ftrace(&old)) { /* * If we find a breakpoint instruction, a kprobe has been * placed at the beginning of the function. We write the @@ -119,9 +149,8 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) * bytes of the original instruction so that the kprobes * handler can execute a brasl if it reaches this breakpoint. */ - new.opc = orig.opc = BREAKPOINT_INSTRUCTION; - orig.disp = KPROBE_ON_FTRACE_NOP; - new.disp = KPROBE_ON_FTRACE_CALL; + ftrace_generate_kprobe_nop_insn(&orig); + ftrace_generate_kprobe_call_insn(&new); } else { /* Replace nop with an ftrace call. */ ftrace_generate_nop_insn(&orig); From e143fa93c28669a7f0851e6850b1da5b1945fd53 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Fri, 13 Mar 2015 11:19:09 +0100 Subject: [PATCH 013/170] s390/mm: limit STACK_RND_MASK for compat tasks For compat tasks the mmap randomization does not use the maximum randomization value from mmap_rnd_mask but the fixed value of 0x7ff. This needs to be respected in the definition of STACK_RND_MASK as well. Signed-off-by: Martin Schwidefsky --- arch/s390/include/asm/elf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h index c9df40b5c0ac..c9c875d9ed31 100644 --- a/arch/s390/include/asm/elf.h +++ b/arch/s390/include/asm/elf.h @@ -211,7 +211,7 @@ do { \ extern unsigned long mmap_rnd_mask; -#define STACK_RND_MASK (mmap_rnd_mask) +#define STACK_RND_MASK (test_thread_flag(TIF_31BIT) ? 0x7ff : mmap_rnd_mask) #define ARCH_DLINFO \ do { \ From 9a30b096b543932de218dd3501b5562e00a8792d Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 12 Mar 2015 23:53:26 -0400 Subject: [PATCH 014/170] blk-mq: fix use of incorrect goto label in blk_mq_init_queue error path If percpu_ref_init() fails the allocated q and hctxs must get cleaned up; using 'err_map' doesn't allow that to happen. Signed-off-by: Mike Snitzer Reviewed-by: Ming Lei Cc: stable@kernel.org Signed-off-by: Jens Axboe --- block/blk-mq.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index 4f4bea21052e..b7b8933ec241 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1938,7 +1938,7 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set) */ if (percpu_ref_init(&q->mq_usage_counter, blk_mq_usage_counter_release, PERCPU_REF_INIT_ATOMIC, GFP_KERNEL)) - goto err_map; + goto err_mq_usage; setup_timer(&q->timeout, blk_mq_rq_timer, (unsigned long) q); blk_queue_rq_timeout(q, 30000); @@ -1981,7 +1981,7 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set) blk_mq_init_cpu_queues(q, set->nr_hw_queues); if (blk_mq_init_hw_queues(q, set)) - goto err_hw; + goto err_mq_usage; mutex_lock(&all_q_mutex); list_add_tail(&q->all_q_node, &all_q_list); @@ -1993,7 +1993,7 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set) return q; -err_hw: +err_mq_usage: blk_cleanup_queue(q); err_hctxs: kfree(map); From b4331b433a2860389c9e35a523f0127788248500 Mon Sep 17 00:00:00 2001 From: Heiko Stuebner Date: Sat, 14 Mar 2015 19:32:06 +0100 Subject: [PATCH 015/170] MAINTAINERS: add rockchip regexp to the ARM/Rockchip entry The regexp option is a nice way to catch even weirder paths like the current drivers/gpu/drm/rockchip/* or others in the future. Signed-off-by: Heiko Stuebner --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index ddc5a8cf9a8a..0d273bd264ac 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1351,6 +1351,7 @@ F: drivers/i2c/busses/i2c-rk3x.c F: drivers/*/*rockchip* F: drivers/*/*/*rockchip* F: sound/soc/rockchip/ +N: rockchip ARM/SAMSUNG EXYNOS ARM ARCHITECTURES M: Kukjin Kim From 54b0bc602541fcc2dd9f2480623c00552e0b220e Mon Sep 17 00:00:00 2001 From: Alexandru M Stan Date: Fri, 13 Mar 2015 17:55:32 -0700 Subject: [PATCH 016/170] ARM: dts: rockchip: disable gmac by default in rk3288.dtsi This block should not be enabled by default or else if the kconfig is set, it will try to load/probe even if there's no phy connected. Signed-off-by: Alexandru M Stan Signed-off-by: Heiko Stuebner --- arch/arm/boot/dts/rk3288.dtsi | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi index d771f687a13b..eccc78d3220b 100644 --- a/arch/arm/boot/dts/rk3288.dtsi +++ b/arch/arm/boot/dts/rk3288.dtsi @@ -411,6 +411,7 @@ gmac: ethernet@ff290000 { "mac_clk_rx", "mac_clk_tx", "clk_mac_ref", "clk_mac_refout", "aclk_mac", "pclk_mac"; + status = "disabled"; }; usb_host0_ehci: usb@ff500000 { From 1cf48f22c98ae24a49a3f1b6900e4c9a9a0fcc62 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Thu, 12 Mar 2015 17:17:18 +0100 Subject: [PATCH 017/170] ath9k: fix tracking of enabled AP beacons sc->nbcnvifs tracks assigned beacon slots, not enabled beacons. Therefore, it cannot be used to decide if cur_conf->enable_beacon (bool) should be updated, or if beacons have been enabled already. With the current code (depending on the order of calls), beacons often do not get enabled in an AP+STA setup. To fix tracking of enabled beacons, convert cur_conf->enable_beacon to a bitmask of enabled beacon slots. Cc: stable@vger.kernel.org Signed-off-by: Felix Fietkau Signed-off-by: Kalle Valo --- drivers/net/wireless/ath/ath9k/beacon.c | 20 ++++++++++++-------- drivers/net/wireless/ath/ath9k/common.h | 2 +- 2 files changed, 13 insertions(+), 9 deletions(-) diff --git a/drivers/net/wireless/ath/ath9k/beacon.c b/drivers/net/wireless/ath/ath9k/beacon.c index cb366adc820b..f50a6bc5d06e 100644 --- a/drivers/net/wireless/ath/ath9k/beacon.c +++ b/drivers/net/wireless/ath/ath9k/beacon.c @@ -219,12 +219,15 @@ void ath9k_beacon_remove_slot(struct ath_softc *sc, struct ieee80211_vif *vif) struct ath_common *common = ath9k_hw_common(sc->sc_ah); struct ath_vif *avp = (void *)vif->drv_priv; struct ath_buf *bf = avp->av_bcbuf; + struct ath_beacon_config *cur_conf = &sc->cur_chan->beacon; ath_dbg(common, CONFIG, "Removing interface at beacon slot: %d\n", avp->av_bslot); tasklet_disable(&sc->bcon_tasklet); + cur_conf->enable_beacon &= ~BIT(avp->av_bslot); + if (bf && bf->bf_mpdu) { struct sk_buff *skb = bf->bf_mpdu; dma_unmap_single(sc->dev, bf->bf_buf_addr, @@ -521,8 +524,7 @@ static bool ath9k_allow_beacon_config(struct ath_softc *sc, } if (sc->sc_ah->opmode == NL80211_IFTYPE_AP) { - if ((vif->type != NL80211_IFTYPE_AP) || - (sc->nbcnvifs > 1)) { + if (vif->type != NL80211_IFTYPE_AP) { ath_dbg(common, CONFIG, "An AP interface is already present !\n"); return false; @@ -616,12 +618,14 @@ void ath9k_beacon_config(struct ath_softc *sc, struct ieee80211_vif *vif, * enabling/disabling SWBA. */ if (changed & BSS_CHANGED_BEACON_ENABLED) { - if (!bss_conf->enable_beacon && - (sc->nbcnvifs <= 1)) { - cur_conf->enable_beacon = false; - } else if (bss_conf->enable_beacon) { - cur_conf->enable_beacon = true; - ath9k_cache_beacon_config(sc, ctx, bss_conf); + bool enabled = cur_conf->enable_beacon; + + if (!bss_conf->enable_beacon) { + cur_conf->enable_beacon &= ~BIT(avp->av_bslot); + } else { + cur_conf->enable_beacon |= BIT(avp->av_bslot); + if (!enabled) + ath9k_cache_beacon_config(sc, ctx, bss_conf); } } diff --git a/drivers/net/wireless/ath/ath9k/common.h b/drivers/net/wireless/ath/ath9k/common.h index 2b79a568e803..d23737342f4f 100644 --- a/drivers/net/wireless/ath/ath9k/common.h +++ b/drivers/net/wireless/ath/ath9k/common.h @@ -54,7 +54,7 @@ struct ath_beacon_config { u16 dtim_period; u16 bmiss_timeout; u8 dtim_count; - bool enable_beacon; + u8 enable_beacon; bool ibss_creator; u32 nexttbtt; u32 intval; From c09396eb8e5a8df668174993c6400763022b2466 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Sun, 15 Mar 2015 08:07:04 +0100 Subject: [PATCH 018/170] ath9k: disable TPC support again (for now) TPC support has been observed to cause some tx power fluctuations on some devices with at least AR934x and AR938x chips. Disable it for now until the bugs have been found and fixed Signed-off-by: Felix Fietkau Signed-off-by: Kalle Valo --- drivers/net/wireless/ath/ath9k/hw.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c index 60aa8d71e753..8529014e1a5e 100644 --- a/drivers/net/wireless/ath/ath9k/hw.c +++ b/drivers/net/wireless/ath/ath9k/hw.c @@ -424,7 +424,7 @@ static void ath9k_hw_init_defaults(struct ath_hw *ah) ah->power_mode = ATH9K_PM_UNDEFINED; ah->htc_reset_init = true; - ah->tpc_enabled = true; + ah->tpc_enabled = false; ah->ani_function = ATH9K_ANI_ALL; if (!AR_SREV_9300_20_OR_LATER(ah)) From d6e5b7cc9819f9a108294f256dd80939e91a0a1f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Thu, 26 Feb 2015 14:49:56 +0100 Subject: [PATCH 019/170] ARM: dts: omap3: Add missing dmas for crypto MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds missing dma DTS definitions for omap aes and sham drivers. Without it kernel drivers do not work for device tree based booting while it works for legacy booting on general purpose SoCs. Note that further changes are still needed for high secure SoCs. But since that never worked in legacy boot mode either, those will be sent separately. Signed-off-by: Pali Rohár Acked-by: Pavel Machek [tony@atomide.com: updated comments] Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/omap3.dtsi | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/arm/boot/dts/omap3.dtsi b/arch/arm/boot/dts/omap3.dtsi index f4f78c40b564..3fdc84fddb70 100644 --- a/arch/arm/boot/dts/omap3.dtsi +++ b/arch/arm/boot/dts/omap3.dtsi @@ -92,6 +92,8 @@ aes: aes@480c5000 { ti,hwmods = "aes"; reg = <0x480c5000 0x50>; interrupts = <0>; + dmas = <&sdma 65 &sdma 66>; + dma-names = "tx", "rx"; }; prm: prm@48306000 { @@ -550,6 +552,8 @@ sham: sham@480c3000 { ti,hwmods = "sham"; reg = <0x480c3000 0x64>; interrupts = <49>; + dmas = <&sdma 69>; + dma-names = "rx"; }; smartreflex_core: smartreflex@480cb000 { From e5ed5b60272871786b1c5434079925bc60d771b7 Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Wed, 11 Mar 2015 18:38:38 -0500 Subject: [PATCH 020/170] ARM: OMAP2+: Fix socbus family info for AM33xx devices The family information in the soc-bus data is currently not classified properly for AM33xx devices, and a read of /sys/bus/soc/devices/soc0/family currently shows "Unknown". Fix the same. Signed-off-by: Suman Anna Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/id.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm/mach-omap2/id.c b/arch/arm/mach-omap2/id.c index 2a2f4d56e4c8..25f1beea453e 100644 --- a/arch/arm/mach-omap2/id.c +++ b/arch/arm/mach-omap2/id.c @@ -720,6 +720,8 @@ static const char * __init omap_get_family(void) return kasprintf(GFP_KERNEL, "OMAP4"); else if (soc_is_omap54xx()) return kasprintf(GFP_KERNEL, "OMAP5"); + else if (soc_is_am33xx() || soc_is_am335x()) + return kasprintf(GFP_KERNEL, "AM33xx"); else if (soc_is_am43xx()) return kasprintf(GFP_KERNEL, "AM43xx"); else if (soc_is_dra7xx()) From e03826d5045e81a66a4fad7be9a8ecdaeb7911cf Mon Sep 17 00:00:00 2001 From: Keerthy Date: Tue, 17 Mar 2015 15:56:04 +0530 Subject: [PATCH 021/170] regulator: palmas: Correct TPS659038 register definition for REGEN2 The register offset for REGEN2_CTRL in different for TPS659038 chip as when compared with other Palmas family PMICs. In the case of TPS659038 the wrong offset pointed to PLLEN_CTRL and was causing a hang. Correcting the same. Signed-off-by: Keerthy Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- drivers/regulator/palmas-regulator.c | 4 ++++ include/linux/mfd/palmas.h | 3 +++ 2 files changed, 7 insertions(+) diff --git a/drivers/regulator/palmas-regulator.c b/drivers/regulator/palmas-regulator.c index 9205f433573c..18198316b6cf 100644 --- a/drivers/regulator/palmas-regulator.c +++ b/drivers/regulator/palmas-regulator.c @@ -1572,6 +1572,10 @@ static int palmas_regulators_probe(struct platform_device *pdev) if (!pmic) return -ENOMEM; + if (of_device_is_compatible(node, "ti,tps659038-pmic")) + palmas_generic_regs_info[PALMAS_REG_REGEN2].ctrl_addr = + TPS659038_REGEN2_CTRL; + pmic->dev = &pdev->dev; pmic->palmas = palmas; palmas->pmic = pmic; diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index fb0390a1a498..ee7b1ce7a6f8 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -2999,6 +2999,9 @@ enum usb_irq_events { #define PALMAS_GPADC_TRIM15 0x0E #define PALMAS_GPADC_TRIM16 0x0F +/* TPS659038 regen2_ctrl offset iss different from palmas */ +#define TPS659038_REGEN2_CTRL 0x12 + /* TPS65917 Interrupt registers */ /* Registers for function INTERRUPT */ From a2f4870697a5bcf4a87073ec6b32dd2928c1211d Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 17 Mar 2015 12:23:19 -0400 Subject: [PATCH 022/170] fs: make sure the timestamps for lazytime inodes eventually get written Jan Kara pointed out that if there is an inode which is constantly getting dirtied with I_DIRTY_PAGES, an inode with an updated timestamp will never be written since inode->dirtied_when is constantly getting updated. We fix this by adding an extra field to the inode, dirtied_time_when, so inodes with a stale dirtytime can get detected and handled. In addition, if we have a dirtytime inode caused by an atime update, and there is no write activity on the file system, we need to have a secondary system to make sure these inodes get written out. We do this by setting up a second delayed work structure which wakes up the CPU much more rarely compared to writeback_expire_centisecs. Signed-off-by: Theodore Ts'o Reviewed-by: Jan Kara --- fs/fs-writeback.c | 82 ++++++++++++++++++++++++++++++++++++++++------ include/linux/fs.h | 1 + 2 files changed, 73 insertions(+), 10 deletions(-) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index e907052eeadb..2cfcd74faf87 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -53,6 +53,18 @@ struct wb_writeback_work { struct completion *done; /* set if the caller waits */ }; +/* + * If an inode is constantly having its pages dirtied, but then the + * updates stop dirtytime_expire_interval seconds in the past, it's + * possible for the worst case time between when an inode has its + * timestamps updated and when they finally get written out to be two + * dirtytime_expire_intervals. We set the default to 12 hours (in + * seconds), which means most of the time inodes will have their + * timestamps written to disk after 12 hours, but in the worst case a + * few inodes might not their timestamps updated for 24 hours. + */ +unsigned int dirtytime_expire_interval = 12 * 60 * 60; + /** * writeback_in_progress - determine whether there is writeback in progress * @bdi: the device's backing_dev_info structure. @@ -275,8 +287,8 @@ static int move_expired_inodes(struct list_head *delaying_queue, if ((flags & EXPIRE_DIRTY_ATIME) == 0) older_than_this = work->older_than_this; - else if ((work->reason == WB_REASON_SYNC) == 0) { - expire_time = jiffies - (HZ * 86400); + else if (!work->for_sync) { + expire_time = jiffies - (dirtytime_expire_interval * HZ); older_than_this = &expire_time; } while (!list_empty(delaying_queue)) { @@ -458,6 +470,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, */ redirty_tail(inode, wb); } else if (inode->i_state & I_DIRTY_TIME) { + inode->dirtied_when = jiffies; list_move(&inode->i_wb_list, &wb->b_dirty_time); } else { /* The inode is clean. Remove from writeback lists. */ @@ -505,12 +518,17 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) spin_lock(&inode->i_lock); dirty = inode->i_state & I_DIRTY; - if (((dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) && - (inode->i_state & I_DIRTY_TIME)) || - (inode->i_state & I_DIRTY_TIME_EXPIRED)) { - dirty |= I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED; - trace_writeback_lazytime(inode); - } + if (inode->i_state & I_DIRTY_TIME) { + if ((dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) || + unlikely(inode->i_state & I_DIRTY_TIME_EXPIRED) || + unlikely(time_after(jiffies, + (inode->dirtied_time_when + + dirtytime_expire_interval * HZ)))) { + dirty |= I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED; + trace_writeback_lazytime(inode); + } + } else + inode->i_state &= ~I_DIRTY_TIME_EXPIRED; inode->i_state &= ~dirty; /* @@ -1131,6 +1149,45 @@ void wakeup_flusher_threads(long nr_pages, enum wb_reason reason) rcu_read_unlock(); } +/* + * Wake up bdi's periodically to make sure dirtytime inodes gets + * written back periodically. We deliberately do *not* check the + * b_dirtytime list in wb_has_dirty_io(), since this would cause the + * kernel to be constantly waking up once there are any dirtytime + * inodes on the system. So instead we define a separate delayed work + * function which gets called much more rarely. (By default, only + * once every 12 hours.) + * + * If there is any other write activity going on in the file system, + * this function won't be necessary. But if the only thing that has + * happened on the file system is a dirtytime inode caused by an atime + * update, we need this infrastructure below to make sure that inode + * eventually gets pushed out to disk. + */ +static void wakeup_dirtytime_writeback(struct work_struct *w); +static DECLARE_DELAYED_WORK(dirtytime_work, wakeup_dirtytime_writeback); + +static void wakeup_dirtytime_writeback(struct work_struct *w) +{ + struct backing_dev_info *bdi; + + rcu_read_lock(); + list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { + if (list_empty(&bdi->wb.b_dirty_time)) + continue; + bdi_wakeup_thread(bdi); + } + rcu_read_unlock(); + schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); +} + +static int __init start_dirtytime_writeback(void) +{ + schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); + return 0; +} +__initcall(start_dirtytime_writeback); + static noinline void block_dump___mark_inode_dirty(struct inode *inode) { if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) { @@ -1269,8 +1326,13 @@ void __mark_inode_dirty(struct inode *inode, int flags) } inode->dirtied_when = jiffies; - list_move(&inode->i_wb_list, dirtytime ? - &bdi->wb.b_dirty_time : &bdi->wb.b_dirty); + if (dirtytime) + inode->dirtied_time_when = jiffies; + if (inode->i_state & (I_DIRTY_INODE | I_DIRTY_PAGES)) + list_move(&inode->i_wb_list, &bdi->wb.b_dirty); + else + list_move(&inode->i_wb_list, + &bdi->wb.b_dirty_time); spin_unlock(&bdi->wb.list_lock); trace_writeback_dirty_inode_enqueue(inode); diff --git a/include/linux/fs.h b/include/linux/fs.h index b4d71b5e1ff2..f4131e8ead74 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -604,6 +604,7 @@ struct inode { struct mutex i_mutex; unsigned long dirtied_when; /* jiffies of first dirtying */ + unsigned long dirtied_time_when; struct hlist_node i_hash; struct list_head i_wb_list; /* backing dev IO list */ From 1efff914afac8a965ad63817ecf8861a927c2ace Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 17 Mar 2015 12:23:32 -0400 Subject: [PATCH 023/170] fs: add dirtytime_expire_seconds sysctl Add a tuning knob so we can adjust the dirtytime expiration timeout, which is very useful for testing lazytime. Signed-off-by: Theodore Ts'o Reviewed-by: Jan Kara --- fs/fs-writeback.c | 11 +++++++++++ include/linux/writeback.h | 3 +++ kernel/sysctl.c | 8 ++++++++ 3 files changed, 22 insertions(+) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 2cfcd74faf87..32a8bbd7a9ad 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1188,6 +1188,17 @@ static int __init start_dirtytime_writeback(void) } __initcall(start_dirtytime_writeback); +int dirtytime_interval_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int ret; + + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (ret == 0 && write) + mod_delayed_work(system_wq, &dirtytime_work, 0); + return ret; +} + static noinline void block_dump___mark_inode_dirty(struct inode *inode) { if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) { diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 00048339c23e..b2dd371ec0ca 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -130,6 +130,7 @@ extern int vm_dirty_ratio; extern unsigned long vm_dirty_bytes; extern unsigned int dirty_writeback_interval; extern unsigned int dirty_expire_interval; +extern unsigned int dirtytime_expire_interval; extern int vm_highmem_is_dirtyable; extern int block_dump; extern int laptop_mode; @@ -146,6 +147,8 @@ extern int dirty_ratio_handler(struct ctl_table *table, int write, extern int dirty_bytes_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); +int dirtytime_interval_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); struct ctl_table; int dirty_writeback_centisecs_handler(struct ctl_table *, int, diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 88ea2d6e0031..ce410bb9f2e1 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1227,6 +1227,14 @@ static struct ctl_table vm_table[] = { .proc_handler = proc_dointvec_minmax, .extra1 = &zero, }, + { + .procname = "dirtytime_expire_seconds", + .data = &dirtytime_expire_interval, + .maxlen = sizeof(dirty_expire_interval), + .mode = 0644, + .proc_handler = dirtytime_interval_handler, + .extra1 = &zero, + }, { .procname = "nr_pdflush_threads", .mode = 0444 /* read-only */, From a76fc9dda87b51010e4bc60b5e0065a70180b465 Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Mon, 16 Mar 2015 20:14:02 -0500 Subject: [PATCH 024/170] ARM: OMAP: dmtimer: check for pm_runtime_get_sync() failure The current OMAP dmtimer probe does not check for the return status of pm_runtime_get_sync() before initializing the timer registers. Any timer with missing hwmod data would return a failure here, and the access of registers without enabling the clocks for the timer would trigger a l3_noc interrupt and a kernel boot hang. Add proper checking so that the probe would return a failure graciously without hanging the kernel boot. Signed-off-by: Suman Anna Signed-off-by: Tony Lindgren --- arch/arm/plat-omap/dmtimer.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/arch/arm/plat-omap/dmtimer.c b/arch/arm/plat-omap/dmtimer.c index db10169a08de..f32c74c0e1de 100644 --- a/arch/arm/plat-omap/dmtimer.c +++ b/arch/arm/plat-omap/dmtimer.c @@ -799,6 +799,7 @@ static int omap_dm_timer_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; const struct of_device_id *match; const struct dmtimer_platform_data *pdata; + int ret; match = of_match_device(of_match_ptr(omap_timer_match), dev); pdata = match ? match->data : dev->platform_data; @@ -860,7 +861,12 @@ static int omap_dm_timer_probe(struct platform_device *pdev) } if (!timer->reserved) { - pm_runtime_get_sync(dev); + ret = pm_runtime_get_sync(dev); + if (ret < 0) { + dev_err(dev, "%s: pm_runtime_get_sync failed!\n", + __func__); + goto err_get_sync; + } __omap_dm_timer_init_regs(timer); pm_runtime_put(dev); } @@ -873,6 +879,11 @@ static int omap_dm_timer_probe(struct platform_device *pdev) dev_dbg(dev, "Device Probed.\n"); return 0; + +err_get_sync: + pm_runtime_put_noidle(dev); + pm_runtime_disable(dev); + return ret; } /** From 51b7e5728ebcded3f2ced9cd3ff71076c91e85de Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Mon, 16 Mar 2015 20:14:03 -0500 Subject: [PATCH 025/170] ARM: OMAP: dmtimer: disable pm runtime on remove Disable the pm_runtime of the device upon remove. This is added to balance the pm_runtime_enable() invoked in the probe. Signed-off-by: Suman Anna Signed-off-by: Tony Lindgren --- arch/arm/plat-omap/dmtimer.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm/plat-omap/dmtimer.c b/arch/arm/plat-omap/dmtimer.c index f32c74c0e1de..8ca94d379bc3 100644 --- a/arch/arm/plat-omap/dmtimer.c +++ b/arch/arm/plat-omap/dmtimer.c @@ -910,6 +910,8 @@ static int omap_dm_timer_remove(struct platform_device *pdev) } spin_unlock_irqrestore(&dm_timer_lock, flags); + pm_runtime_disable(&pdev->dev); + return ret; } From 0790ec172de1bd2e23f1dbd4925426b6cc3c1b72 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= Date: Tue, 17 Mar 2015 14:02:32 +0100 Subject: [PATCH 026/170] KVM: nVMX: mask unrestricted_guest if disabled on L0 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If EPT was enabled, unrestricted_guest was allowed in L1 regardless of L0. L1 triple faulted when running L2 guest that required emulation. Another side effect was 'WARN_ON_ONCE(vmx->nested.nested_run_pending)' in L0's dmesg: WARNING: CPU: 0 PID: 0 at arch/x86/kvm/vmx.c:9190 nested_vmx_vmexit+0x96e/0xb00 [kvm_intel] () Prevent this scenario by masking SECONDARY_EXEC_UNRESTRICTED_GUEST when the host doesn't have it enabled. Fixes: 78051e3b7e35 ("KVM: nVMX: Disable unrestricted mode if ept=0") Cc: stable@vger.kernel.org Tested-By: Kashyap Chamarthy Signed-off-by: Radim Krčmář Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/vmx.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 10a481b7674d..ae4f6d35d19c 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2479,8 +2479,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) if (enable_ept) { /* nested EPT: emulate EPT also to L1 */ vmx->nested.nested_vmx_secondary_ctls_high |= - SECONDARY_EXEC_ENABLE_EPT | - SECONDARY_EXEC_UNRESTRICTED_GUEST; + SECONDARY_EXEC_ENABLE_EPT; vmx->nested.nested_vmx_ept_caps = VMX_EPT_PAGE_WALK_4_BIT | VMX_EPTP_WB_BIT | VMX_EPT_2MB_PAGE_BIT | VMX_EPT_INVEPT_BIT; @@ -2494,6 +2493,10 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) } else vmx->nested.nested_vmx_ept_caps = 0; + if (enable_unrestricted_guest) + vmx->nested.nested_vmx_secondary_ctls_high |= + SECONDARY_EXEC_UNRESTRICTED_GUEST; + /* miscellaneous data */ rdmsr(MSR_IA32_VMX_MISC, vmx->nested.nested_vmx_misc_low, From 391949b6f02121371e3d7d9082c6d17fd9853034 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 18 Mar 2015 11:27:28 +0100 Subject: [PATCH 027/170] spi: trigger trace event for message-done before mesg->complete MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With spidev the mesg->complete callback points to spidev_complete. Calling this unblocks spidev_sync and so spidev_sync_write finishes. As the struct spi_message just read is a local variable in spidev_sync_write and recording the trace event accesses this message the recording is better done first. The same can happen for spidev_sync_read. This fixes an oops observed on a 3.14-rt system with spidev activity after echo 1 > /sys/kernel/debug/tracing/events/spi/enable . Signed-off-by: Uwe Kleine-König Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- drivers/spi/spi.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index c64a3e59fce3..57a195041dc7 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -1105,13 +1105,14 @@ void spi_finalize_current_message(struct spi_master *master) "failed to unprepare message: %d\n", ret); } } + + trace_spi_message_done(mesg); + master->cur_msg_prepared = false; mesg->state = NULL; if (mesg->complete) mesg->complete(mesg->context); - - trace_spi_message_done(mesg); } EXPORT_SYMBOL_GPL(spi_finalize_current_message); From cf39284d41f67964cf42b21bb386c012cf5b7f65 Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Wed, 18 Mar 2015 08:57:41 +0800 Subject: [PATCH 028/170] regulator: Fix documentation for regmap in the config dev_get_regulator() does not exist, fix the typo. Signed-off-by: Axel Lin Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index d4ad5b5a02bb..045f709cb89b 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -316,7 +316,7 @@ struct regulator_desc { * @driver_data: private regulator data * @of_node: OpenFirmware node to parse for device tree bindings (may be * NULL). - * @regmap: regmap to use for core regmap helpers if dev_get_regulator() is + * @regmap: regmap to use for core regmap helpers if dev_get_regmap() is * insufficient. * @ena_gpio_initialized: GPIO controlling regulator enable was properly * initialized, meaning that >= 0 is a valid gpio From 077155332265f1d64c57bd6c49748a8b7e72a3f9 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Fri, 20 Feb 2015 14:21:14 +0530 Subject: [PATCH 029/170] ARM: dts: dra7: remove ti,hwmod property from pcie phy Now that we don't have hwmod entry for pcie PHY remove the ti,hwmod property from PCIE PHY's. Otherwise we will get: platform 4a094000.pciephy: Cannot lookup hwmod 'pcie1-phy' Signed-off-by: Kishon Vijay Abraham I [tony@atomide.com: updated comments] Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/dra7.dtsi | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index 127608d79033..c4659a979c41 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -1111,7 +1111,6 @@ pcie1_phy: pciephy@4a094000 { "wkupclk", "refclk", "div-clk", "phy-div"; #phy-cells = <0>; - ti,hwmods = "pcie1-phy"; }; pcie2_phy: pciephy@4a095000 { @@ -1130,7 +1129,6 @@ pcie2_phy: pciephy@4a095000 { "wkupclk", "refclk", "div-clk", "phy-div"; #phy-cells = <0>; - ti,hwmods = "pcie2-phy"; status = "disabled"; }; }; From 599c376c49323127c9bdbb0fa61a3d4743819bc2 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Wed, 18 Mar 2015 13:41:34 -0700 Subject: [PATCH 030/170] ARM: dts: Fix gpio interrupts for dm816x Commit 7800064ba507 ("ARM: dts: Add basic dm816x device tree configuration") added basic devices for dm816x, but I was not able to test the GPIO interrupts earlier until I found some suitable pins to test with. We can mux the MMC card detect and write protect pins from SD_SDCD and SD_SDWP mode to use a normal GPIO interrupts that are also suitable for the MMC subsystem. This turned out several issues that need to be fixed: - I set the GPIO type wrong to be compatible with omap3 instead of omap4. The GPIO controller on dm816x has EOI interrupt register like omap4 and am335x. - I got the GPIO interrupt numbers wrong as each bank has two and we only use one. They need to be set up the same way as on am335x. - The gpio banks are missing interrupt controller related properties. With these changes the GPIO interrupts can be used with the MMC card detect pin, so let's wire that up. Let's also mux all the MMC lines for completeness while at it. For the first GPIO bank I tested using GPMC lines temporarily muxed to GPIOs on the dip switch 10. Cc: Brian Hutchinson Cc: Matthijs van Duin Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/dm8168-evm.dts | 19 +++++++++++++++++++ arch/arm/boot/dts/dm816x.dtsi | 18 ++++++++++++++---- 2 files changed, 33 insertions(+), 4 deletions(-) diff --git a/arch/arm/boot/dts/dm8168-evm.dts b/arch/arm/boot/dts/dm8168-evm.dts index d3a29c1b8417..afe678f6d2e9 100644 --- a/arch/arm/boot/dts/dm8168-evm.dts +++ b/arch/arm/boot/dts/dm8168-evm.dts @@ -36,6 +36,20 @@ DM816X_IOPAD(0x0aac, PIN_INPUT | MUX_MODE0) /* SPI_D1 */ >; }; + mmc_pins: pinmux_mmc_pins { + pinctrl-single,pins = < + DM816X_IOPAD(0x0a70, MUX_MODE0) /* SD_POW */ + DM816X_IOPAD(0x0a74, MUX_MODE0) /* SD_CLK */ + DM816X_IOPAD(0x0a78, MUX_MODE0) /* SD_CMD */ + DM816X_IOPAD(0x0a7C, MUX_MODE0) /* SD_DAT0 */ + DM816X_IOPAD(0x0a80, MUX_MODE0) /* SD_DAT1 */ + DM816X_IOPAD(0x0a84, MUX_MODE0) /* SD_DAT2 */ + DM816X_IOPAD(0x0a88, MUX_MODE0) /* SD_DAT2 */ + DM816X_IOPAD(0x0a8c, MUX_MODE2) /* GP1[7] */ + DM816X_IOPAD(0x0a90, MUX_MODE2) /* GP1[8] */ + >; + }; + usb0_pins: pinmux_usb0_pins { pinctrl-single,pins = < DM816X_IOPAD(0x0d00, MUX_MODE0) /* USB0_DRVVBUS */ @@ -137,7 +151,12 @@ m25p80@0 { }; &mmc1 { + pinctrl-names = "default"; + pinctrl-0 = <&mmc_pins>; vmmc-supply = <&vmmcsd_fixed>; + bus-width = <4>; + cd-gpios = <&gpio2 7 GPIO_ACTIVE_LOW>; + wp-gpios = <&gpio2 8 GPIO_ACTIVE_LOW>; }; /* At least dm8168-evm rev c won't support multipoint, later may */ diff --git a/arch/arm/boot/dts/dm816x.dtsi b/arch/arm/boot/dts/dm816x.dtsi index 3c97b5f2addc..f35715bc6992 100644 --- a/arch/arm/boot/dts/dm816x.dtsi +++ b/arch/arm/boot/dts/dm816x.dtsi @@ -150,17 +150,27 @@ elm: elm@48080000 { }; gpio1: gpio@48032000 { - compatible = "ti,omap3-gpio"; + compatible = "ti,omap4-gpio"; ti,hwmods = "gpio1"; + ti,gpio-always-on; reg = <0x48032000 0x1000>; - interrupts = <97>; + interrupts = <96>; + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; }; gpio2: gpio@4804c000 { - compatible = "ti,omap3-gpio"; + compatible = "ti,omap4-gpio"; ti,hwmods = "gpio2"; + ti,gpio-always-on; reg = <0x4804c000 0x1000>; - interrupts = <99>; + interrupts = <98>; + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; }; gpmc: gpmc@50000000 { From bc188d818edf325ae38cfa43254a0b10a4defd65 Mon Sep 17 00:00:00 2001 From: Sam Bradshaw Date: Wed, 18 Mar 2015 17:06:18 -0600 Subject: [PATCH 031/170] blkmq: Fix NULL pointer deref when all reserved tags in When allocating from the reserved tags pool, bt_get() is called with a NULL hctx. If all tags are in use, the hw queue is kicked to push out any pending IO, potentially freeing tags, and tag allocation is retried. The problem is that blk_mq_run_hw_queue() doesn't check for a NULL hctx. So we avoid it with a simple NULL hctx test. Tested by hammering mtip32xx with concurrent smartctl/hdparm. Signed-off-by: Sam Bradshaw Signed-off-by: Selvan Mani Fixes: b32232073e80 ("blk-mq: fix hang in bt_get()") Cc: stable@kernel.org Added appropriate comment. Signed-off-by: Jens Axboe --- block/blk-mq-tag.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index d53a764b05ea..be3290cc0644 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -278,9 +278,11 @@ static int bt_get(struct blk_mq_alloc_data *data, /* * We're out of tags on this hardware queue, kick any * pending IO submits before going to sleep waiting for - * some to complete. + * some to complete. Note that hctx can be NULL here for + * reserved tag allocation. */ - blk_mq_run_hw_queue(hctx, false); + if (hctx) + blk_mq_run_hw_queue(hctx, false); /* * Retry tag allocation after running the hardware queue, From 4de60970abf9f49737f51ec6e7a1e3bcf6d36742 Mon Sep 17 00:00:00 2001 From: "qipeng.zha" Date: Wed, 11 Mar 2015 01:15:38 +0800 Subject: [PATCH 032/170] gpiolib: translate pin number in GPIO ACPI callbacks If GPIO driver use pin mapping, need to translate pin number between ACPI table and GPIO driver. This issue is found on one platform with Cherryview gpio controller, kernel is hang when executed _PS0 method of one ACPI device, since without this translation, it access invalid gpiodesc array. Verified it works again with this patch. Signed-off-by: qipeng.zha Acked-by: Mika Westerberg Signed-off-by: Linus Walleij --- drivers/gpio/gpiolib-acpi.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index c0929d938ced..df990f29757a 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -201,6 +201,10 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares, if (!handler) return AE_BAD_PARAMETER; + pin = acpi_gpiochip_pin_to_gpio_offset(chip, pin); + if (pin < 0) + return AE_BAD_PARAMETER; + desc = gpiochip_request_own_desc(chip, pin, "ACPI:Event"); if (IS_ERR(desc)) { dev_err(chip->dev, "Failed to request GPIO\n"); @@ -551,6 +555,12 @@ acpi_gpio_adr_space_handler(u32 function, acpi_physical_address address, struct gpio_desc *desc; bool found; + pin = acpi_gpiochip_pin_to_gpio_offset(chip, pin); + if (pin < 0) { + status = AE_BAD_PARAMETER; + goto out; + } + mutex_lock(&achip->conn_lock); found = false; From 9c8928f5176766bec79f272bd47b7124e11cccbd Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Mon, 16 Mar 2015 09:08:07 +0200 Subject: [PATCH 033/170] iwlwifi: dvm: run INIT firmware again upon .start() The assumption before this patch was that we don't need to run again the INIT firmware after the system booted. The INIT firmware runs calibrations which impact the physical layer's behavior. Users reported that it may be helpful to run these calibrations again every time the interface is brought up. The penatly is minimal, since the calibrations run fast. This fixes: https://bugzilla.kernel.org/show_bug.cgi?id=94341 CC: Signed-off-by: Emmanuel Grumbach --- drivers/net/wireless/iwlwifi/dvm/dev.h | 1 - drivers/net/wireless/iwlwifi/dvm/ucode.c | 5 ----- 2 files changed, 6 deletions(-) diff --git a/drivers/net/wireless/iwlwifi/dvm/dev.h b/drivers/net/wireless/iwlwifi/dvm/dev.h index a6f22c32a279..3811878ab9cd 100644 --- a/drivers/net/wireless/iwlwifi/dvm/dev.h +++ b/drivers/net/wireless/iwlwifi/dvm/dev.h @@ -708,7 +708,6 @@ struct iwl_priv { unsigned long reload_jiffies; int reload_count; bool ucode_loaded; - bool init_ucode_run; /* Don't run init uCode again */ u8 plcp_delta_threshold; diff --git a/drivers/net/wireless/iwlwifi/dvm/ucode.c b/drivers/net/wireless/iwlwifi/dvm/ucode.c index 4dbef7e58c2e..5244e43bfafb 100644 --- a/drivers/net/wireless/iwlwifi/dvm/ucode.c +++ b/drivers/net/wireless/iwlwifi/dvm/ucode.c @@ -418,9 +418,6 @@ int iwl_run_init_ucode(struct iwl_priv *priv) if (!priv->fw->img[IWL_UCODE_INIT].sec[0].len) return 0; - if (priv->init_ucode_run) - return 0; - iwl_init_notification_wait(&priv->notif_wait, &calib_wait, calib_complete, ARRAY_SIZE(calib_complete), iwlagn_wait_calib, priv); @@ -440,8 +437,6 @@ int iwl_run_init_ucode(struct iwl_priv *priv) */ ret = iwl_wait_notification(&priv->notif_wait, &calib_wait, UCODE_CALIB_TIMEOUT); - if (!ret) - priv->init_ucode_run = true; goto out; From dcbc17ad7c7525ed04a45a94cfc5640d5cccf480 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 10 Mar 2015 21:24:34 +0100 Subject: [PATCH 034/170] iwlwifi: mvm: protect rate scaling against non-mvm IBSS stations When the driver callback returns that it's out of space for new stations, the mac80211 IBSS code still keeps the station so it doesn't try to add it over and over again. Since the rate scaling algorithm is separate in mac80211, it also invokes the rate scaling algorithm for such stations. It doesn't know that our rate scaling algorithm is tightly integrated with the MVM code and relies on those data structures, and it cannot as the abstraction doesn't allow for it. This leads to crashes when the rate scaling algorithm tries to use uninitialized data, notably the mvmsta->vif pointer. Protect against this in the rate scaling algorithm. We cannot get good rates with such peers anyway since the firmware cannot do anything with them. This should fix https://bugzilla.kernel.org/show_bug.cgi?id=93461 CC: Reported-by: Richard Taylor Signed-off-by: Johannes Berg Signed-off-by: Emmanuel Grumbach --- drivers/net/wireless/iwlwifi/mvm/rs.c | 24 ++++++++++++++++++++++-- 1 file changed, 22 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/iwlwifi/mvm/rs.c b/drivers/net/wireless/iwlwifi/mvm/rs.c index efa9688a4cf1..078f24cf4af3 100644 --- a/drivers/net/wireless/iwlwifi/mvm/rs.c +++ b/drivers/net/wireless/iwlwifi/mvm/rs.c @@ -1278,6 +1278,9 @@ static void rs_mac80211_tx_status(void *mvm_r, struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode); struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + if (!iwl_mvm_sta_from_mac80211(sta)->vif) + return; + if (!ieee80211_is_data(hdr->frame_control) || info->flags & IEEE80211_TX_CTL_NO_ACK) return; @@ -2511,6 +2514,14 @@ static void rs_get_rate(void *mvm_r, struct ieee80211_sta *sta, void *mvm_sta, struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct iwl_lq_sta *lq_sta = mvm_sta; + if (sta && !iwl_mvm_sta_from_mac80211(sta)->vif) { + /* if vif isn't initialized mvm doesn't know about + * this station, so don't do anything with the it + */ + sta = NULL; + mvm_sta = NULL; + } + /* TODO: handle rate_idx_mask and rate_idx_mcs_mask */ /* Treat uninitialized rate scaling data same as non-existing. */ @@ -2827,6 +2838,9 @@ static void rs_rate_update(void *mvm_r, (struct iwl_op_mode *)mvm_r; struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode); + if (!iwl_mvm_sta_from_mac80211(sta)->vif) + return; + /* Stop any ongoing aggregations as rs starts off assuming no agg */ for (tid = 0; tid < IWL_MAX_TID_COUNT; tid++) ieee80211_stop_tx_ba_session(sta, tid); @@ -3587,9 +3601,15 @@ static ssize_t iwl_dbgfs_ss_force_write(struct iwl_lq_sta *lq_sta, char *buf, MVM_DEBUGFS_READ_WRITE_FILE_OPS(ss_force, 32); -static void rs_add_debugfs(void *mvm, void *mvm_sta, struct dentry *dir) +static void rs_add_debugfs(void *mvm, void *priv_sta, struct dentry *dir) { - struct iwl_lq_sta *lq_sta = mvm_sta; + struct iwl_lq_sta *lq_sta = priv_sta; + struct iwl_mvm_sta *mvmsta; + + mvmsta = container_of(lq_sta, struct iwl_mvm_sta, lq_sta); + + if (!mvmsta->vif) + return; debugfs_create_file("rate_scale_table", S_IRUSR | S_IWUSR, dir, lq_sta, &rs_sta_dbgfs_scale_table_ops); From 132fee062655e90948e189c8c14ce21f115ebbda Mon Sep 17 00:00:00 2001 From: Oren Givon Date: Thu, 19 Mar 2015 12:46:06 +0200 Subject: [PATCH 035/170] iwlwifi: add new 3165 series PCI IDs Add new 3165 PCI IDs for new 1x1 cards. Signed-off-by: Oren Givon Signed-off-by: Emmanuel Grumbach --- drivers/net/wireless/iwlwifi/pcie/drv.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/iwlwifi/pcie/drv.c b/drivers/net/wireless/iwlwifi/pcie/drv.c index dbd6bcf52205..686dd301cd53 100644 --- a/drivers/net/wireless/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/iwlwifi/pcie/drv.c @@ -368,10 +368,12 @@ static const struct pci_device_id iwl_hw_card_ids[] = { /* 3165 Series */ {IWL_PCI_DEVICE(0x3165, 0x4010, iwl3165_2ac_cfg)}, {IWL_PCI_DEVICE(0x3165, 0x4012, iwl3165_2ac_cfg)}, - {IWL_PCI_DEVICE(0x3165, 0x4110, iwl3165_2ac_cfg)}, - {IWL_PCI_DEVICE(0x3165, 0x4210, iwl3165_2ac_cfg)}, {IWL_PCI_DEVICE(0x3165, 0x4410, iwl3165_2ac_cfg)}, {IWL_PCI_DEVICE(0x3165, 0x4510, iwl3165_2ac_cfg)}, + {IWL_PCI_DEVICE(0x3165, 0x4110, iwl3165_2ac_cfg)}, + {IWL_PCI_DEVICE(0x3166, 0x4310, iwl3165_2ac_cfg)}, + {IWL_PCI_DEVICE(0x3166, 0x4210, iwl3165_2ac_cfg)}, + {IWL_PCI_DEVICE(0x3165, 0x8010, iwl3165_2ac_cfg)}, /* 7265 Series */ {IWL_PCI_DEVICE(0x095A, 0x5010, iwl7265_2ac_cfg)}, From 1f16ea294d2ef63013740f4c8539e430b6c12dff Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 6 Mar 2015 09:17:37 +0100 Subject: [PATCH 036/170] iwlwifi: mvm: remove WARN_ON for invalid BA notification The firmware frequently manages to trigger this, and there's no known driver workaround, so stop warning. Signed-off-by: Johannes Berg Signed-off-by: Emmanuel Grumbach --- drivers/net/wireless/iwlwifi/mvm/tx.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/iwlwifi/mvm/tx.c b/drivers/net/wireless/iwlwifi/mvm/tx.c index 07304e1fd64a..96a05406babf 100644 --- a/drivers/net/wireless/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/iwlwifi/mvm/tx.c @@ -949,8 +949,10 @@ int iwl_mvm_rx_ba_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb, mvmsta = iwl_mvm_sta_from_mac80211(sta); tid_data = &mvmsta->tid_data[tid]; - if (WARN_ONCE(tid_data->txq_id != scd_flow, "Q %d, tid %d, flow %d", - tid_data->txq_id, tid, scd_flow)) { + if (tid_data->txq_id != scd_flow) { + IWL_ERR(mvm, + "invalid BA notification: Q %d, tid %d, flow %d\n", + tid_data->txq_id, tid, scd_flow); rcu_read_unlock(); return 0; } From 1ac31de744202a3a14601170a57f155b4a8d2c21 Mon Sep 17 00:00:00 2001 From: Mark James Date: Tue, 17 Mar 2015 21:35:23 +0000 Subject: [PATCH 037/170] ARM: socfpga: dts: fix spi1 interrupt The socfpga.dtsi currently has the wrong interrupt number set for SPI master 1 Trying to use the master without this change results in the kernel boot process waiting forever for an interrupt that will never occur while attempting to probe any slave devices configured in the device tree as being under SPI master 1. The change works for the Cyclone V, and according to the Arria 5 handbook should be good there too. Signed-off-by: Mark James Acked-by: Steffen Trumtrar Signed-off-by: Dinh Nguyen --- arch/arm/boot/dts/socfpga.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/socfpga.dtsi b/arch/arm/boot/dts/socfpga.dtsi index 9d8760956752..d9176e606173 100644 --- a/arch/arm/boot/dts/socfpga.dtsi +++ b/arch/arm/boot/dts/socfpga.dtsi @@ -660,7 +660,7 @@ spi1: spi@fff01000 { #address-cells = <1>; #size-cells = <0>; reg = <0xfff01000 0x1000>; - interrupts = <0 156 4>; + interrupts = <0 155 4>; num-cs = <4>; clocks = <&spi_m_clk>; status = "disabled"; From 67d8712dcc70aa16d8e14a52eb73870e3cbddfc2 Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Wed, 18 Mar 2015 11:57:39 -0600 Subject: [PATCH 038/170] selftests: Fix build failures when invoked from kselftest target Several tests that rely on implicit build rules fail to build, when invoked from the main Makefile kselftest target. These failures are due to --no-builtin-rules and --no-builtin-variables options set in the inherited MAKEFLAGS. --no-builtin-rules eliminates the use of built-in implicit rules and --no-builtin-variables is for not defining built-in variables. These two options override the use of implicit rules resulting in build failures. In addition, inherited LDFLAGS result in build failures and there is no need to define LDFLAGS. Clear LDFLAGS and MAKEFLAG when make is invoked from the main Makefile kselftest target. Fixing this at selftests Makefile avoids changing the main Makefile and keeps this change self contained at selftests level. Signed-off-by: Shuah Khan Acked-by: Michael Ellerman --- tools/testing/selftests/Makefile | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 4e511221a0c1..0db571340edb 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -22,6 +22,14 @@ TARGETS += vm TARGETS_HOTPLUG = cpu-hotplug TARGETS_HOTPLUG += memory-hotplug +# Clear LDFLAGS and MAKEFLAGS if called from main +# Makefile to avoid test build failures when test +# Makefile doesn't have explicit build rules. +ifeq (1,$(MAKELEVEL)) +undefine LDFLAGS +override MAKEFLAGS = +endif + all: for TARGET in $(TARGETS); do \ make -C $$TARGET; \ From 5067c0469c643512f24786990e315f9c15cc7d24 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Thu, 12 Mar 2015 10:32:18 -0700 Subject: [PATCH 039/170] ata: Add a new flag to destinguish sas controller SAS controller has its own tag allocation, which doesn't directly match to ATA tag, so SAS and SATA have different code path for ata tags. Originally we use port->scsi_host (98bd4be1) to destinguish SAS controller, but libsas set ->scsi_host too, so we can't use it for the destinguish, we add a new flag for this purpose. Without this patch, the following oops can happen because scsi-mq uses a host-wide tag map shared among all devices with some integer tag values >= ATA_MAX_QUEUE. These unexpectedly high tag values cause __ata_qc_from_tag() to return NULL, which is then dereferenced in ata_qc_new_init(). BUG: unable to handle kernel NULL pointer dereference at 0000000000000058 IP: [] ata_qc_new_init+0x3e/0x120 PGD 32adf0067 PUD 32adf1067 PMD 0 Oops: 0002 [#1] SMP DEBUG_PAGEALLOC Modules linked in: iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi igb i2c_algo_bit ptp pps_core pm80xx libsas scsi_transport_sas sg coretemp eeprom w83795 i2c_i801 CPU: 4 PID: 1450 Comm: cydiskbench Not tainted 4.0.0-rc3 #1 Hardware name: Supermicro X8DTH-i/6/iF/6F/X8DTH, BIOS 2.1b 05/04/12 task: ffff8800ba86d500 ti: ffff88032a064000 task.ti: ffff88032a064000 RIP: 0010:[] [] ata_qc_new_init+0x3e/0x120 RSP: 0018:ffff88032a067858 EFLAGS: 00010046 RAX: 0000000000000000 RBX: ffff8800ba0d2230 RCX: 000000000000002a RDX: ffffffff80505ae0 RSI: 0000000000000020 RDI: ffff8800ba0d2230 RBP: ffff88032a067868 R08: 0000000000000201 R09: 0000000000000001 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8800ba0d0000 R13: ffff8800ba0d2230 R14: ffffffff80505ae0 R15: ffff8800ba0d0000 FS: 0000000041223950(0063) GS:ffff88033e480000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000000058 CR3: 000000032a0a3000 CR4: 00000000000006e0 Stack: ffff880329eee758 ffff880329eee758 ffff88032a0678a8 ffffffff80502dad ffff8800ba167978 ffff880329eee758 ffff88032bf9c520 ffff8800ba167978 ffff88032bf9c520 ffff88032bf9a290 ffff88032a0678b8 ffffffff80506909 Call Trace: [] ata_scsi_translate+0x3d/0x1b0 [] ata_sas_queuecmd+0x149/0x2a0 [] sas_queuecommand+0xa0/0x1f0 [libsas] [] scsi_dispatch_cmd+0xd4/0x1a0 [] scsi_queue_rq+0x66f/0x7f0 [] __blk_mq_run_hw_queue+0x208/0x3f0 [] blk_mq_run_hw_queue+0x88/0xc0 [] blk_mq_insert_request+0xc4/0x130 [] blk_execute_rq_nowait+0x73/0x160 [] sg_common_write+0x3da/0x720 [sg] [] sg_new_write+0x250/0x360 [sg] [] sg_write+0x13b/0x450 [sg] [] vfs_write+0xd1/0x1b0 [] SyS_write+0x54/0xc0 [] system_call_fastpath+0x12/0x17 tj: updated description. Fixes: 12cb5ce101ab ("libata: use blk taging") Reported-and-tested-by: Tony Battersby Signed-off-by: Shaohua Li Signed-off-by: Tejun Heo --- drivers/ata/libata-core.c | 4 ++-- drivers/scsi/ipr.c | 3 ++- drivers/scsi/libsas/sas_ata.c | 3 ++- include/linux/libata.h | 1 + 4 files changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 4c35f0822d06..ef150ebb4c30 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4737,7 +4737,7 @@ struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev, int tag) return NULL; /* libsas case */ - if (!ap->scsi_host) { + if (ap->flags & ATA_FLAG_SAS_HOST) { tag = ata_sas_allocate_tag(ap); if (tag < 0) return NULL; @@ -4776,7 +4776,7 @@ void ata_qc_free(struct ata_queued_cmd *qc) tag = qc->tag; if (likely(ata_tag_valid(tag))) { qc->tag = ATA_TAG_POISON; - if (!ap->scsi_host) + if (ap->flags & ATA_FLAG_SAS_HOST) ata_sas_free_tag(tag, ap); } } diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index 9219953ee949..d9afc51af7d3 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -6815,7 +6815,8 @@ static struct ata_port_operations ipr_sata_ops = { }; static struct ata_port_info sata_port_info = { - .flags = ATA_FLAG_SATA | ATA_FLAG_PIO_DMA, + .flags = ATA_FLAG_SATA | ATA_FLAG_PIO_DMA | + ATA_FLAG_SAS_HOST, .pio_mask = ATA_PIO4_ONLY, .mwdma_mask = ATA_MWDMA2, .udma_mask = ATA_UDMA6, diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c index 932d9cc98d2f..9c706d8c1441 100644 --- a/drivers/scsi/libsas/sas_ata.c +++ b/drivers/scsi/libsas/sas_ata.c @@ -547,7 +547,8 @@ static struct ata_port_operations sas_sata_ops = { }; static struct ata_port_info sata_port_info = { - .flags = ATA_FLAG_SATA | ATA_FLAG_PIO_DMA | ATA_FLAG_NCQ, + .flags = ATA_FLAG_SATA | ATA_FLAG_PIO_DMA | ATA_FLAG_NCQ | + ATA_FLAG_SAS_HOST, .pio_mask = ATA_PIO4, .mwdma_mask = ATA_MWDMA2, .udma_mask = ATA_UDMA6, diff --git a/include/linux/libata.h b/include/linux/libata.h index fc03efa64ffe..6b08cc106c21 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -232,6 +232,7 @@ enum { * led */ ATA_FLAG_NO_DIPM = (1 << 23), /* host not happy with DIPM */ ATA_FLAG_LOWTAG = (1 << 24), /* host wants lowest available tag */ + ATA_FLAG_SAS_HOST = (1 << 25), /* SAS host */ /* bits 24:31 of ap->flags are reserved for LLD specific flags */ From c6b570d97c0e77f570bb6b2ed30d372b2b1e9aae Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Mon, 9 Mar 2015 12:20:13 +0100 Subject: [PATCH 040/170] regmap: introduce regmap_name to fix syscon regmap trace events This patch fixes a NULL pointer dereference when enabling regmap event tracing in the presence of a syscon regmap, introduced by commit bdb0066df96e ("mfd: syscon: Decouple syscon interface from platform devices"). That patch introduced syscon regmaps that have their dev field set to NULL. The regmap trace events expect it to point to a valid struct device and feed it to dev_name(): $ echo 1 > /sys/kernel/debug/tracing/events/regmap/enable Unable to handle kernel NULL pointer dereference at virtual address 0000002c pgd = 80004000 [0000002c] *pgd=00000000 Internal error: Oops: 17 [#1] SMP ARM Modules linked in: coda videobuf2_vmalloc CPU: 0 PID: 304 Comm: kworker/0:2 Not tainted 4.0.0-rc2+ #9197 Hardware name: Freescale i.MX6 Quad/DualLite (Device Tree) Workqueue: events_freezable thermal_zone_device_check task: 9f25a200 ti: 9f1ee000 task.ti: 9f1ee000 PC is at ftrace_raw_event_regmap_block+0x3c/0xe4 LR is at _regmap_raw_read+0x1bc/0x1cc pc : [<803636e8>] lr : [<80365f2c>] psr: 600f0093 sp : 9f1efd78 ip : 9f1efdb8 fp : 9f1efdb4 r10: 00000004 r9 : 00000001 r8 : 00000001 r7 : 00000180 r6 : 00000000 r5 : 9f00e3c0 r4 : 00000003 r3 : 00000001 r2 : 00000180 r1 : 00000000 r0 : 9f00e3c0 Flags: nZCv IRQs off FIQs on Mode SVC_32 ISA ARM Segment kernel Control: 10c5387d Table: 2d91004a DAC: 00000015 Process kworker/0:2 (pid: 304, stack limit = 0x9f1ee210) Stack: (0x9f1efd78 to 0x9f1f0000) fd60: 9f1efda4 9f1efd88 fd80: 800708c0 805f9510 80927140 800f0013 9f1fc800 9eb2f490 00000000 00000180 fda0: 808e3840 00000001 9f1efdfc 9f1efdb8 80365f2c 803636b8 805f8958 800708e0 fdc0: a00f0013 803636ac 9f16de00 00000180 80927140 9f1fc800 9f1fc800 9f1efe6c fde0: 9f1efe6c 9f732400 00000000 00000000 9f1efe1c 9f1efe00 80365f70 80365d7c fe00: 80365f3c 9f1fc800 9f1fc800 00000180 9f1efe44 9f1efe20 803656a4 80365f48 fe20: 9f1fc800 00000180 9f1efe6c 9f1efe6c 9f732400 00000000 9f1efe64 9f1efe48 fe40: 803657bc 80365634 00000001 9e95f910 9f1fc800 9f1efeb4 9f1efe8c 9f1efe68 fe60: 80452ac0 80365778 9f1efe8c 9f1efe78 9e93d400 9e93d5e8 9f1efeb4 9f72ef40 fe80: 9f1efeac 9f1efe90 8044e11c 80452998 8045298c 9e93d608 9e93d400 808e1978 fea0: 9f1efecc 9f1efeb0 8044fd14 8044e0d0 ffffffff 9f25a200 9e93d608 9e481380 fec0: 9f1efedc 9f1efed0 8044fde8 8044fcec 9f1eff1c 9f1efee0 80038d50 8044fdd8 fee0: 9f1ee020 9f72ef40 9e481398 00000000 00000008 9f72ef54 9f1ee020 9f72ef40 ff00: 9e481398 9e481380 00000008 9f72ef40 9f1eff5c 9f1eff20 80039754 80038bfc ff20: 00000000 9e481380 80894100 808e1662 00000000 9e4f2ec0 00000000 9e481380 ff40: 800396f8 00000000 00000000 00000000 9f1effac 9f1eff60 8003e020 80039704 ff60: ffffffff 00000000 ffffffff 9e481380 00000000 00000000 9f1eff78 9f1eff78 ff80: 00000000 00000000 9f1eff88 9f1eff88 9e4f2ec0 8003df30 00000000 00000000 ffa0: 00000000 9f1effb0 8000eb60 8003df3c 00000000 00000000 00000000 00000000 ffc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 ffe0: 00000000 00000000 00000000 00000000 00000013 00000000 ffffffff ffffffff Backtrace: [<803636ac>] (ftrace_raw_event_regmap_block) from [<80365f2c>] (_regmap_raw_read+0x1bc/0x1cc) r9:00000001 r8:808e3840 r7:00000180 r6:00000000 r5:9eb2f490 r4:9f1fc800 [<80365d70>] (_regmap_raw_read) from [<80365f70>] (_regmap_bus_read+0x34/0x6c) r10:00000000 r9:00000000 r8:9f732400 r7:9f1efe6c r6:9f1efe6c r5:9f1fc800 r4:9f1fc800 [<80365f3c>] (_regmap_bus_read) from [<803656a4>] (_regmap_read+0x7c/0x144) r6:00000180 r5:9f1fc800 r4:9f1fc800 r3:80365f3c [<80365628>] (_regmap_read) from [<803657bc>] (regmap_read+0x50/0x70) r9:00000000 r8:9f732400 r7:9f1efe6c r6:9f1efe6c r5:00000180 r4:9f1fc800 [<8036576c>] (regmap_read) from [<80452ac0>] (imx_get_temp+0x134/0x1a4) r6:9f1efeb4 r5:9f1fc800 r4:9e95f910 r3:00000001 [<8045298c>] (imx_get_temp) from [<8044e11c>] (thermal_zone_get_temp+0x58/0x74) r7:9f72ef40 r6:9f1efeb4 r5:9e93d5e8 r4:9e93d400 [<8044e0c4>] (thermal_zone_get_temp) from [<8044fd14>] (thermal_zone_device_update+0x34/0xec) r6:808e1978 r5:9e93d400 r4:9e93d608 r3:8045298c [<8044fce0>] (thermal_zone_device_update) from [<8044fde8>] (thermal_zone_device_check+0x1c/0x20) r5:9e481380 r4:9e93d608 [<8044fdcc>] (thermal_zone_device_check) from [<80038d50>] (process_one_work+0x160/0x3d4) [<80038bf0>] (process_one_work) from [<80039754>] (worker_thread+0x5c/0x4f4) r10:9f72ef40 r9:00000008 r8:9e481380 r7:9e481398 r6:9f72ef40 r5:9f1ee020 r4:9f72ef54 [<800396f8>] (worker_thread) from [<8003e020>] (kthread+0xf0/0x108) r10:00000000 r9:00000000 r8:00000000 r7:800396f8 r6:9e481380 r5:00000000 r4:9e4f2ec0 [<8003df30>] (kthread) from [<8000eb60>] (ret_from_fork+0x14/0x34) r7:00000000 r6:00000000 r5:8003df30 r4:9e4f2ec0 Code: e3140040 1a00001a e3140020 1a000016 (e596002c) ---[ end trace 193c15c2494ec960 ]--- Fixes: bdb0066df96e (mfd: syscon: Decouple syscon interface from platform devices) Signed-off-by: Philipp Zabel Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- drivers/base/regmap/internal.h | 8 +++ drivers/base/regmap/regcache.c | 16 ++--- drivers/base/regmap/regmap.c | 32 ++++----- include/trace/events/regmap.h | 123 ++++++++++++++++----------------- 4 files changed, 91 insertions(+), 88 deletions(-) diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h index beb8b27d4621..a13587b5c2be 100644 --- a/drivers/base/regmap/internal.h +++ b/drivers/base/regmap/internal.h @@ -243,4 +243,12 @@ extern struct regcache_ops regcache_rbtree_ops; extern struct regcache_ops regcache_lzo_ops; extern struct regcache_ops regcache_flat_ops; +static inline const char *regmap_name(const struct regmap *map) +{ + if (map->dev) + return dev_name(map->dev); + + return map->name; +} + #endif diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c index f373c35f9e1d..f5db662e951e 100644 --- a/drivers/base/regmap/regcache.c +++ b/drivers/base/regmap/regcache.c @@ -218,7 +218,7 @@ int regcache_read(struct regmap *map, ret = map->cache_ops->read(map, reg, value); if (ret == 0) - trace_regmap_reg_read_cache(map->dev, reg, *value); + trace_regmap_reg_read_cache(map, reg, *value); return ret; } @@ -311,7 +311,7 @@ int regcache_sync(struct regmap *map) dev_dbg(map->dev, "Syncing %s cache\n", map->cache_ops->name); name = map->cache_ops->name; - trace_regcache_sync(map->dev, name, "start"); + trace_regcache_sync(map, name, "start"); if (!map->cache_dirty) goto out; @@ -346,7 +346,7 @@ int regcache_sync(struct regmap *map) regmap_async_complete(map); - trace_regcache_sync(map->dev, name, "stop"); + trace_regcache_sync(map, name, "stop"); return ret; } @@ -381,7 +381,7 @@ int regcache_sync_region(struct regmap *map, unsigned int min, name = map->cache_ops->name; dev_dbg(map->dev, "Syncing %s cache from %d-%d\n", name, min, max); - trace_regcache_sync(map->dev, name, "start region"); + trace_regcache_sync(map, name, "start region"); if (!map->cache_dirty) goto out; @@ -401,7 +401,7 @@ int regcache_sync_region(struct regmap *map, unsigned int min, regmap_async_complete(map); - trace_regcache_sync(map->dev, name, "stop region"); + trace_regcache_sync(map, name, "stop region"); return ret; } @@ -428,7 +428,7 @@ int regcache_drop_region(struct regmap *map, unsigned int min, map->lock(map->lock_arg); - trace_regcache_drop_region(map->dev, min, max); + trace_regcache_drop_region(map, min, max); ret = map->cache_ops->drop(map, min, max); @@ -455,7 +455,7 @@ void regcache_cache_only(struct regmap *map, bool enable) map->lock(map->lock_arg); WARN_ON(map->cache_bypass && enable); map->cache_only = enable; - trace_regmap_cache_only(map->dev, enable); + trace_regmap_cache_only(map, enable); map->unlock(map->lock_arg); } EXPORT_SYMBOL_GPL(regcache_cache_only); @@ -493,7 +493,7 @@ void regcache_cache_bypass(struct regmap *map, bool enable) map->lock(map->lock_arg); WARN_ON(map->cache_only && enable); map->cache_bypass = enable; - trace_regmap_cache_bypass(map->dev, enable); + trace_regmap_cache_bypass(map, enable); map->unlock(map->lock_arg); } EXPORT_SYMBOL_GPL(regcache_cache_bypass); diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index f99b098ddabf..dbfe6a69c3da 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -1281,7 +1281,7 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg, if (map->async && map->bus->async_write) { struct regmap_async *async; - trace_regmap_async_write_start(map->dev, reg, val_len); + trace_regmap_async_write_start(map, reg, val_len); spin_lock_irqsave(&map->async_lock, flags); async = list_first_entry_or_null(&map->async_free, @@ -1339,8 +1339,7 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg, return ret; } - trace_regmap_hw_write_start(map->dev, reg, - val_len / map->format.val_bytes); + trace_regmap_hw_write_start(map, reg, val_len / map->format.val_bytes); /* If we're doing a single register write we can probably just * send the work_buf directly, otherwise try to do a gather @@ -1372,8 +1371,7 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg, kfree(buf); } - trace_regmap_hw_write_done(map->dev, reg, - val_len / map->format.val_bytes); + trace_regmap_hw_write_done(map, reg, val_len / map->format.val_bytes); return ret; } @@ -1407,12 +1405,12 @@ static int _regmap_bus_formatted_write(void *context, unsigned int reg, map->format.format_write(map, reg, val); - trace_regmap_hw_write_start(map->dev, reg, 1); + trace_regmap_hw_write_start(map, reg, 1); ret = map->bus->write(map->bus_context, map->work_buf, map->format.buf_size); - trace_regmap_hw_write_done(map->dev, reg, 1); + trace_regmap_hw_write_done(map, reg, 1); return ret; } @@ -1470,7 +1468,7 @@ int _regmap_write(struct regmap *map, unsigned int reg, dev_info(map->dev, "%x <= %x\n", reg, val); #endif - trace_regmap_reg_write(map->dev, reg, val); + trace_regmap_reg_write(map, reg, val); return map->reg_write(context, reg, val); } @@ -1773,7 +1771,7 @@ static int _regmap_raw_multi_reg_write(struct regmap *map, for (i = 0; i < num_regs; i++) { int reg = regs[i].reg; int val = regs[i].def; - trace_regmap_hw_write_start(map->dev, reg, 1); + trace_regmap_hw_write_start(map, reg, 1); map->format.format_reg(u8, reg, map->reg_shift); u8 += reg_bytes + pad_bytes; map->format.format_val(u8, val, 0); @@ -1788,7 +1786,7 @@ static int _regmap_raw_multi_reg_write(struct regmap *map, for (i = 0; i < num_regs; i++) { int reg = regs[i].reg; - trace_regmap_hw_write_done(map->dev, reg, 1); + trace_regmap_hw_write_done(map, reg, 1); } return ret; } @@ -2059,15 +2057,13 @@ static int _regmap_raw_read(struct regmap *map, unsigned int reg, void *val, */ u8[0] |= map->read_flag_mask; - trace_regmap_hw_read_start(map->dev, reg, - val_len / map->format.val_bytes); + trace_regmap_hw_read_start(map, reg, val_len / map->format.val_bytes); ret = map->bus->read(map->bus_context, map->work_buf, map->format.reg_bytes + map->format.pad_bytes, val, val_len); - trace_regmap_hw_read_done(map->dev, reg, - val_len / map->format.val_bytes); + trace_regmap_hw_read_done(map, reg, val_len / map->format.val_bytes); return ret; } @@ -2123,7 +2119,7 @@ static int _regmap_read(struct regmap *map, unsigned int reg, dev_info(map->dev, "%x => %x\n", reg, *val); #endif - trace_regmap_reg_read(map->dev, reg, *val); + trace_regmap_reg_read(map, reg, *val); if (!map->cache_bypass) regcache_write(map, reg, *val); @@ -2480,7 +2476,7 @@ void regmap_async_complete_cb(struct regmap_async *async, int ret) struct regmap *map = async->map; bool wake; - trace_regmap_async_io_complete(map->dev); + trace_regmap_async_io_complete(map); spin_lock(&map->async_lock); list_move(&async->list, &map->async_free); @@ -2525,7 +2521,7 @@ int regmap_async_complete(struct regmap *map) if (!map->bus || !map->bus->async_write) return 0; - trace_regmap_async_complete_start(map->dev); + trace_regmap_async_complete_start(map); wait_event(map->async_waitq, regmap_async_is_done(map)); @@ -2534,7 +2530,7 @@ int regmap_async_complete(struct regmap *map) map->async_ret = 0; spin_unlock_irqrestore(&map->async_lock, flags); - trace_regmap_async_complete_done(map->dev); + trace_regmap_async_complete_done(map); return ret; } diff --git a/include/trace/events/regmap.h b/include/trace/events/regmap.h index 23d561512f64..22317d2b52ab 100644 --- a/include/trace/events/regmap.h +++ b/include/trace/events/regmap.h @@ -7,27 +7,26 @@ #include #include -struct device; -struct regmap; +#include "../../../drivers/base/regmap/internal.h" /* * Log register events */ DECLARE_EVENT_CLASS(regmap_reg, - TP_PROTO(struct device *dev, unsigned int reg, + TP_PROTO(struct regmap *map, unsigned int reg, unsigned int val), - TP_ARGS(dev, reg, val), + TP_ARGS(map, reg, val), TP_STRUCT__entry( - __string( name, dev_name(dev) ) - __field( unsigned int, reg ) - __field( unsigned int, val ) + __string( name, regmap_name(map) ) + __field( unsigned int, reg ) + __field( unsigned int, val ) ), TP_fast_assign( - __assign_str(name, dev_name(dev)); + __assign_str(name, regmap_name(map)); __entry->reg = reg; __entry->val = val; ), @@ -39,45 +38,45 @@ DECLARE_EVENT_CLASS(regmap_reg, DEFINE_EVENT(regmap_reg, regmap_reg_write, - TP_PROTO(struct device *dev, unsigned int reg, + TP_PROTO(struct regmap *map, unsigned int reg, unsigned int val), - TP_ARGS(dev, reg, val) + TP_ARGS(map, reg, val) ); DEFINE_EVENT(regmap_reg, regmap_reg_read, - TP_PROTO(struct device *dev, unsigned int reg, + TP_PROTO(struct regmap *map, unsigned int reg, unsigned int val), - TP_ARGS(dev, reg, val) + TP_ARGS(map, reg, val) ); DEFINE_EVENT(regmap_reg, regmap_reg_read_cache, - TP_PROTO(struct device *dev, unsigned int reg, + TP_PROTO(struct regmap *map, unsigned int reg, unsigned int val), - TP_ARGS(dev, reg, val) + TP_ARGS(map, reg, val) ); DECLARE_EVENT_CLASS(regmap_block, - TP_PROTO(struct device *dev, unsigned int reg, int count), + TP_PROTO(struct regmap *map, unsigned int reg, int count), - TP_ARGS(dev, reg, count), + TP_ARGS(map, reg, count), TP_STRUCT__entry( - __string( name, dev_name(dev) ) - __field( unsigned int, reg ) - __field( int, count ) + __string( name, regmap_name(map) ) + __field( unsigned int, reg ) + __field( int, count ) ), TP_fast_assign( - __assign_str(name, dev_name(dev)); + __assign_str(name, regmap_name(map)); __entry->reg = reg; __entry->count = count; ), @@ -89,48 +88,48 @@ DECLARE_EVENT_CLASS(regmap_block, DEFINE_EVENT(regmap_block, regmap_hw_read_start, - TP_PROTO(struct device *dev, unsigned int reg, int count), + TP_PROTO(struct regmap *map, unsigned int reg, int count), - TP_ARGS(dev, reg, count) + TP_ARGS(map, reg, count) ); DEFINE_EVENT(regmap_block, regmap_hw_read_done, - TP_PROTO(struct device *dev, unsigned int reg, int count), + TP_PROTO(struct regmap *map, unsigned int reg, int count), - TP_ARGS(dev, reg, count) + TP_ARGS(map, reg, count) ); DEFINE_EVENT(regmap_block, regmap_hw_write_start, - TP_PROTO(struct device *dev, unsigned int reg, int count), + TP_PROTO(struct regmap *map, unsigned int reg, int count), - TP_ARGS(dev, reg, count) + TP_ARGS(map, reg, count) ); DEFINE_EVENT(regmap_block, regmap_hw_write_done, - TP_PROTO(struct device *dev, unsigned int reg, int count), + TP_PROTO(struct regmap *map, unsigned int reg, int count), - TP_ARGS(dev, reg, count) + TP_ARGS(map, reg, count) ); TRACE_EVENT(regcache_sync, - TP_PROTO(struct device *dev, const char *type, + TP_PROTO(struct regmap *map, const char *type, const char *status), - TP_ARGS(dev, type, status), + TP_ARGS(map, type, status), TP_STRUCT__entry( - __string( name, dev_name(dev) ) - __string( status, status ) - __string( type, type ) - __field( int, type ) + __string( name, regmap_name(map) ) + __string( status, status ) + __string( type, type ) + __field( int, type ) ), TP_fast_assign( - __assign_str(name, dev_name(dev)); + __assign_str(name, regmap_name(map)); __assign_str(status, status); __assign_str(type, type); ), @@ -141,17 +140,17 @@ TRACE_EVENT(regcache_sync, DECLARE_EVENT_CLASS(regmap_bool, - TP_PROTO(struct device *dev, bool flag), + TP_PROTO(struct regmap *map, bool flag), - TP_ARGS(dev, flag), + TP_ARGS(map, flag), TP_STRUCT__entry( - __string( name, dev_name(dev) ) - __field( int, flag ) + __string( name, regmap_name(map) ) + __field( int, flag ) ), TP_fast_assign( - __assign_str(name, dev_name(dev)); + __assign_str(name, regmap_name(map)); __entry->flag = flag; ), @@ -161,32 +160,32 @@ DECLARE_EVENT_CLASS(regmap_bool, DEFINE_EVENT(regmap_bool, regmap_cache_only, - TP_PROTO(struct device *dev, bool flag), + TP_PROTO(struct regmap *map, bool flag), - TP_ARGS(dev, flag) + TP_ARGS(map, flag) ); DEFINE_EVENT(regmap_bool, regmap_cache_bypass, - TP_PROTO(struct device *dev, bool flag), + TP_PROTO(struct regmap *map, bool flag), - TP_ARGS(dev, flag) + TP_ARGS(map, flag) ); DECLARE_EVENT_CLASS(regmap_async, - TP_PROTO(struct device *dev), + TP_PROTO(struct regmap *map), - TP_ARGS(dev), + TP_ARGS(map), TP_STRUCT__entry( - __string( name, dev_name(dev) ) + __string( name, regmap_name(map) ) ), TP_fast_assign( - __assign_str(name, dev_name(dev)); + __assign_str(name, regmap_name(map)); ), TP_printk("%s", __get_str(name)) @@ -194,50 +193,50 @@ DECLARE_EVENT_CLASS(regmap_async, DEFINE_EVENT(regmap_block, regmap_async_write_start, - TP_PROTO(struct device *dev, unsigned int reg, int count), + TP_PROTO(struct regmap *map, unsigned int reg, int count), - TP_ARGS(dev, reg, count) + TP_ARGS(map, reg, count) ); DEFINE_EVENT(regmap_async, regmap_async_io_complete, - TP_PROTO(struct device *dev), + TP_PROTO(struct regmap *map), - TP_ARGS(dev) + TP_ARGS(map) ); DEFINE_EVENT(regmap_async, regmap_async_complete_start, - TP_PROTO(struct device *dev), + TP_PROTO(struct regmap *map), - TP_ARGS(dev) + TP_ARGS(map) ); DEFINE_EVENT(regmap_async, regmap_async_complete_done, - TP_PROTO(struct device *dev), + TP_PROTO(struct regmap *map), - TP_ARGS(dev) + TP_ARGS(map) ); TRACE_EVENT(regcache_drop_region, - TP_PROTO(struct device *dev, unsigned int from, + TP_PROTO(struct regmap *map, unsigned int from, unsigned int to), - TP_ARGS(dev, from, to), + TP_ARGS(map, from, to), TP_STRUCT__entry( - __string( name, dev_name(dev) ) - __field( unsigned int, from ) - __field( unsigned int, to ) + __string( name, regmap_name(map) ) + __field( unsigned int, from ) + __field( unsigned int, to ) ), TP_fast_assign( - __assign_str(name, dev_name(dev)); + __assign_str(name, regmap_name(map)); __entry->from = from; __entry->to = to; ), From 755563bc79c764c90b9f44db5e4fe6c556d3440c Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Thu, 19 Mar 2015 19:29:01 +1100 Subject: [PATCH 041/170] powerpc/powernv: Fixes for hypervisor doorbell handling Since we can now use hypervisor doorbells for host IPIs, this makes sure we clear the host IPI flag when taking a doorbell interrupt, and clears any pending doorbell IPI in pnv_smp_cpu_kill_self() (as we already do for IPIs sent via the XICS interrupt controller). Otherwise if there did happen to be a leftover pending doorbell interrupt for an offline CPU thread for any reason, it would prevent that thread from going into a power-saving mode; it would instead keep waking up because of the interrupt. Signed-off-by: Paul Mackerras Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/ppc-opcode.h | 3 +++ arch/powerpc/include/asm/reg.h | 3 +++ arch/powerpc/kernel/dbell.c | 2 ++ arch/powerpc/platforms/powernv/smp.c | 14 ++++++++++++-- 4 files changed, 20 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 03cd858a401c..4cbe23af400a 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -153,6 +153,7 @@ #define PPC_INST_MFSPR_PVR_MASK 0xfc1fffff #define PPC_INST_MFTMR 0x7c0002dc #define PPC_INST_MSGSND 0x7c00019c +#define PPC_INST_MSGCLR 0x7c0001dc #define PPC_INST_MSGSNDP 0x7c00011c #define PPC_INST_MTTMR 0x7c0003dc #define PPC_INST_NOP 0x60000000 @@ -309,6 +310,8 @@ ___PPC_RB(b) | __PPC_EH(eh)) #define PPC_MSGSND(b) stringify_in_c(.long PPC_INST_MSGSND | \ ___PPC_RB(b)) +#define PPC_MSGCLR(b) stringify_in_c(.long PPC_INST_MSGCLR | \ + ___PPC_RB(b)) #define PPC_MSGSNDP(b) stringify_in_c(.long PPC_INST_MSGSNDP | \ ___PPC_RB(b)) #define PPC_POPCNTB(a, s) stringify_in_c(.long PPC_INST_POPCNTB | \ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 1c874fb533bb..af56b5c6c81a 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -608,13 +608,16 @@ #define SRR1_ISI_N_OR_G 0x10000000 /* ISI: Access is no-exec or G */ #define SRR1_ISI_PROT 0x08000000 /* ISI: Other protection fault */ #define SRR1_WAKEMASK 0x00380000 /* reason for wakeup */ +#define SRR1_WAKEMASK_P8 0x003c0000 /* reason for wakeup on POWER8 */ #define SRR1_WAKESYSERR 0x00300000 /* System error */ #define SRR1_WAKEEE 0x00200000 /* External interrupt */ #define SRR1_WAKEMT 0x00280000 /* mtctrl */ #define SRR1_WAKEHMI 0x00280000 /* Hypervisor maintenance */ #define SRR1_WAKEDEC 0x00180000 /* Decrementer interrupt */ +#define SRR1_WAKEDBELL 0x00140000 /* Privileged doorbell on P8 */ #define SRR1_WAKETHERM 0x00100000 /* Thermal management interrupt */ #define SRR1_WAKERESET 0x00100000 /* System reset */ +#define SRR1_WAKEHDBELL 0x000c0000 /* Hypervisor doorbell on P8 */ #define SRR1_WAKESTATE 0x00030000 /* Powersave exit mask [46:47] */ #define SRR1_WS_DEEPEST 0x00030000 /* Some resources not maintained, * may not be recoverable */ diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c index f4217819cc31..2128f3a96c32 100644 --- a/arch/powerpc/kernel/dbell.c +++ b/arch/powerpc/kernel/dbell.c @@ -17,6 +17,7 @@ #include #include +#include #ifdef CONFIG_SMP void doorbell_setup_this_cpu(void) @@ -41,6 +42,7 @@ void doorbell_exception(struct pt_regs *regs) may_hard_irq_enable(); + kvmppc_set_host_ipi(smp_processor_id(), 0); __this_cpu_inc(irq_stat.doorbell_irqs); smp_ipi_demux(); diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index fc34025ef822..38a45088f633 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -33,6 +33,8 @@ #include #include #include +#include +#include #include "powernv.h" @@ -149,7 +151,7 @@ static int pnv_smp_cpu_disable(void) static void pnv_smp_cpu_kill_self(void) { unsigned int cpu; - unsigned long srr1; + unsigned long srr1, wmask; u32 idle_states; /* Standard hot unplug procedure */ @@ -161,6 +163,10 @@ static void pnv_smp_cpu_kill_self(void) generic_set_cpu_dead(cpu); smp_wmb(); + wmask = SRR1_WAKEMASK; + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + wmask = SRR1_WAKEMASK_P8; + idle_states = pnv_get_supported_cpuidle_states(); /* We don't want to take decrementer interrupts while we are offline, * so clear LPCR:PECE1. We keep PECE2 enabled. @@ -191,10 +197,14 @@ static void pnv_smp_cpu_kill_self(void) * having finished executing in a KVM guest, then srr1 * contains 0. */ - if ((srr1 & SRR1_WAKEMASK) == SRR1_WAKEEE) { + if ((srr1 & wmask) == SRR1_WAKEEE) { icp_native_flush_interrupt(); local_paca->irq_happened &= PACA_IRQ_HARD_DIS; smp_mb(); + } else if ((srr1 & wmask) == SRR1_WAKEHDBELL) { + unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER); + asm volatile(PPC_MSGCLR(%0) : : "r" (msg)); + kvmppc_set_host_ipi(cpu, 0); } if (cpu_core_split_required()) From ddee09c099c35074e50aaf9157efd22429d3acdf Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 19 Mar 2015 14:12:06 +1100 Subject: [PATCH 042/170] powerpc: Add PVR for POWER8NVL processor There's a new variant of POWER8 coming called "POWER8 with NVLink". The core is identical to POWER8 but unfortunately they strapped it with a different PVR, so we need to add an explicit entry for it. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/cputable.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index f337666768a7..f83046878336 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -437,6 +437,26 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check_early = __machine_check_early_realmode_p8, .platform = "power8", }, + { /* Power8NVL */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x004c0000, + .cpu_name = "POWER8NVL (raw)", + .cpu_features = CPU_FTRS_POWER8, + .cpu_user_features = COMMON_USER_POWER8, + .cpu_user_features2 = COMMON_USER2_POWER8, + .mmu_features = MMU_FTRS_POWER8, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .oprofile_cpu_type = "ppc64/power8", + .oprofile_type = PPC_OPROFILE_INVALID, + .cpu_setup = __setup_cpu_power8, + .cpu_restore = __restore_cpu_power8, + .flush_tlb = __flush_tlb_power8, + .machine_check_early = __machine_check_early_realmode_p8, + .platform = "power8", + }, { /* Power8 DD1: Does not support doorbell IPIs */ .pvr_mask = 0xffffff00, .pvr_value = 0x004d0100, From f6ff04149637723261aa4738958b0098b929ee9e Mon Sep 17 00:00:00 2001 From: Tyrel Datwyler Date: Wed, 4 Mar 2015 11:59:33 -0800 Subject: [PATCH 043/170] powerpc/pseries: Little endian fixes for post mobility device tree update We currently use the device tree update code in the kernel after resuming from a suspend operation to re-sync the kernels view of the device tree with that of the hypervisor. The code as it stands is not endian safe as it relies on parsing buffers returned by RTAS calls that thusly contains data in big endian format. This patch annotates variables and structure members with __be types as well as performing necessary byte swaps to cpu endian for data that needs to be parsed. Signed-off-by: Tyrel Datwyler Cc: Nathan Fontenot Cc: Cyril Bur Cc: stable@vger.kernel.org Signed-off-by: Michael Ellerman --- arch/powerpc/platforms/pseries/mobility.c | 44 ++++++++++++----------- 1 file changed, 23 insertions(+), 21 deletions(-) diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index 90cf3dcbd9f2..8f35d525cede 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -25,10 +25,10 @@ static struct kobject *mobility_kobj; struct update_props_workarea { - u32 phandle; - u32 state; - u64 reserved; - u32 nprops; + __be32 phandle; + __be32 state; + __be64 reserved; + __be32 nprops; } __packed; #define NODE_ACTION_MASK 0xff000000 @@ -54,11 +54,11 @@ static int mobility_rtas_call(int token, char *buf, s32 scope) return rc; } -static int delete_dt_node(u32 phandle) +static int delete_dt_node(__be32 phandle) { struct device_node *dn; - dn = of_find_node_by_phandle(phandle); + dn = of_find_node_by_phandle(be32_to_cpu(phandle)); if (!dn) return -ENOENT; @@ -127,7 +127,7 @@ static int update_dt_property(struct device_node *dn, struct property **prop, return 0; } -static int update_dt_node(u32 phandle, s32 scope) +static int update_dt_node(__be32 phandle, s32 scope) { struct update_props_workarea *upwa; struct device_node *dn; @@ -136,6 +136,7 @@ static int update_dt_node(u32 phandle, s32 scope) char *prop_data; char *rtas_buf; int update_properties_token; + u32 nprops; u32 vd; update_properties_token = rtas_token("ibm,update-properties"); @@ -146,7 +147,7 @@ static int update_dt_node(u32 phandle, s32 scope) if (!rtas_buf) return -ENOMEM; - dn = of_find_node_by_phandle(phandle); + dn = of_find_node_by_phandle(be32_to_cpu(phandle)); if (!dn) { kfree(rtas_buf); return -ENOENT; @@ -162,6 +163,7 @@ static int update_dt_node(u32 phandle, s32 scope) break; prop_data = rtas_buf + sizeof(*upwa); + nprops = be32_to_cpu(upwa->nprops); /* On the first call to ibm,update-properties for a node the * the first property value descriptor contains an empty @@ -170,17 +172,17 @@ static int update_dt_node(u32 phandle, s32 scope) */ if (*prop_data == 0) { prop_data++; - vd = *(u32 *)prop_data; + vd = be32_to_cpu(*(__be32 *)prop_data); prop_data += vd + sizeof(vd); - upwa->nprops--; + nprops--; } - for (i = 0; i < upwa->nprops; i++) { + for (i = 0; i < nprops; i++) { char *prop_name; prop_name = prop_data; prop_data += strlen(prop_name) + 1; - vd = *(u32 *)prop_data; + vd = be32_to_cpu(*(__be32 *)prop_data); prop_data += sizeof(vd); switch (vd) { @@ -212,13 +214,13 @@ static int update_dt_node(u32 phandle, s32 scope) return 0; } -static int add_dt_node(u32 parent_phandle, u32 drc_index) +static int add_dt_node(__be32 parent_phandle, __be32 drc_index) { struct device_node *dn; struct device_node *parent_dn; int rc; - parent_dn = of_find_node_by_phandle(parent_phandle); + parent_dn = of_find_node_by_phandle(be32_to_cpu(parent_phandle)); if (!parent_dn) return -ENOENT; @@ -237,7 +239,7 @@ static int add_dt_node(u32 parent_phandle, u32 drc_index) int pseries_devicetree_update(s32 scope) { char *rtas_buf; - u32 *data; + __be32 *data; int update_nodes_token; int rc; @@ -254,17 +256,17 @@ int pseries_devicetree_update(s32 scope) if (rc && rc != 1) break; - data = (u32 *)rtas_buf + 4; - while (*data & NODE_ACTION_MASK) { + data = (__be32 *)rtas_buf + 4; + while (be32_to_cpu(*data) & NODE_ACTION_MASK) { int i; - u32 action = *data & NODE_ACTION_MASK; - int node_count = *data & NODE_COUNT_MASK; + u32 action = be32_to_cpu(*data) & NODE_ACTION_MASK; + u32 node_count = be32_to_cpu(*data) & NODE_COUNT_MASK; data++; for (i = 0; i < node_count; i++) { - u32 phandle = *data++; - u32 drc_index; + __be32 phandle = *data++; + __be32 drc_index; switch (action) { case DELETE_DT_NODE: From 8f902b005ece690f0f50b217975601b804905dc8 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Fri, 20 Mar 2015 20:39:38 +1100 Subject: [PATCH 044/170] KVM: PPC: Book3S HV: Fix spinlock/mutex ordering issue in kvmppc_set_lpcr() Currently, kvmppc_set_lpcr() has a spinlock around the whole function, and inside that does mutex_lock(&kvm->lock). It is not permitted to take a mutex while holding a spinlock, because the mutex_lock might call schedule(). In addition, this causes lockdep to warn about a lock ordering issue: ====================================================== [ INFO: possible circular locking dependency detected ] 3.18.0-kvm-04645-gdfea862-dirty #131 Not tainted ------------------------------------------------------- qemu-system-ppc/8179 is trying to acquire lock: (&kvm->lock){+.+.+.}, at: [] .kvmppc_set_lpcr+0xf4/0x1c0 [kvm_hv] but task is already holding lock: (&(&vcore->lock)->rlock){+.+...}, at: [] .kvmppc_set_lpcr+0x40/0x1c0 [kvm_hv] which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&(&vcore->lock)->rlock){+.+...}: [] .mutex_lock_nested+0x80/0x570 [] .kvmppc_vcpu_run_hv+0xc4/0xe40 [kvm_hv] [] .kvmppc_vcpu_run+0x2c/0x40 [kvm] [] .kvm_arch_vcpu_ioctl_run+0x54/0x160 [kvm] [] .kvm_vcpu_ioctl+0x4a8/0x7b0 [kvm] [] .do_vfs_ioctl+0x444/0x770 [] .SyS_ioctl+0xc4/0xe0 [] syscall_exit+0x0/0x98 -> #0 (&kvm->lock){+.+.+.}: [] .lock_acquire+0xcc/0x1a0 [] .mutex_lock_nested+0x80/0x570 [] .kvmppc_set_lpcr+0xf4/0x1c0 [kvm_hv] [] .kvmppc_set_one_reg_hv+0x4dc/0x990 [kvm_hv] [] .kvmppc_set_one_reg+0x44/0x330 [kvm] [] .kvm_vcpu_ioctl_set_one_reg+0x5c/0x150 [kvm] [] .kvm_arch_vcpu_ioctl+0x214/0x2c0 [kvm] [] .kvm_vcpu_ioctl+0xe0/0x7b0 [kvm] [] .do_vfs_ioctl+0x444/0x770 [] .SyS_ioctl+0xc4/0xe0 [] syscall_exit+0x0/0x98 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&(&vcore->lock)->rlock); lock(&kvm->lock); lock(&(&vcore->lock)->rlock); lock(&kvm->lock); *** DEADLOCK *** 2 locks held by qemu-system-ppc/8179: #0: (&vcpu->mutex){+.+.+.}, at: [] .vcpu_load+0x28/0x90 [kvm] #1: (&(&vcore->lock)->rlock){+.+...}, at: [] .kvmppc_set_lpcr+0x40/0x1c0 [kvm_hv] stack backtrace: CPU: 4 PID: 8179 Comm: qemu-system-ppc Not tainted 3.18.0-kvm-04645-gdfea862-dirty #131 Call Trace: [c000001a66c0f310] [c000000000b486ac] .dump_stack+0x88/0xb4 (unreliable) [c000001a66c0f390] [c0000000000f8bec] .print_circular_bug+0x27c/0x3d0 [c000001a66c0f440] [c0000000000fe9e8] .__lock_acquire+0x2028/0x2190 [c000001a66c0f5d0] [c0000000000ff28c] .lock_acquire+0xcc/0x1a0 [c000001a66c0f6a0] [c000000000b3c120] .mutex_lock_nested+0x80/0x570 [c000001a66c0f7c0] [d00000000ecc1f54] .kvmppc_set_lpcr+0xf4/0x1c0 [kvm_hv] [c000001a66c0f860] [d00000000ecc510c] .kvmppc_set_one_reg_hv+0x4dc/0x990 [kvm_hv] [c000001a66c0f8d0] [d00000000eb9f234] .kvmppc_set_one_reg+0x44/0x330 [kvm] [c000001a66c0f960] [d00000000eb9c9dc] .kvm_vcpu_ioctl_set_one_reg+0x5c/0x150 [kvm] [c000001a66c0f9f0] [d00000000eb9ced4] .kvm_arch_vcpu_ioctl+0x214/0x2c0 [kvm] [c000001a66c0faf0] [d00000000eb940b0] .kvm_vcpu_ioctl+0xe0/0x7b0 [kvm] [c000001a66c0fcb0] [c00000000026cbb4] .do_vfs_ioctl+0x444/0x770 [c000001a66c0fd90] [c00000000026cfa4] .SyS_ioctl+0xc4/0xe0 [c000001a66c0fe30] [c000000000009264] syscall_exit+0x0/0x98 This fixes it by moving the mutex_lock()/mutex_unlock() pair outside the spin-locked region. Signed-off-by: Paul Mackerras Signed-off-by: Alexander Graf --- arch/powerpc/kvm/book3s_hv.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index de4018a1bc4b..b2731933f807 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -942,20 +942,20 @@ static int kvm_arch_vcpu_ioctl_set_sregs_hv(struct kvm_vcpu *vcpu, static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr, bool preserve_top32) { + struct kvm *kvm = vcpu->kvm; struct kvmppc_vcore *vc = vcpu->arch.vcore; u64 mask; + mutex_lock(&kvm->lock); spin_lock(&vc->lock); /* * If ILE (interrupt little-endian) has changed, update the * MSR_LE bit in the intr_msr for each vcpu in this vcore. */ if ((new_lpcr & LPCR_ILE) != (vc->lpcr & LPCR_ILE)) { - struct kvm *kvm = vcpu->kvm; struct kvm_vcpu *vcpu; int i; - mutex_lock(&kvm->lock); kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->arch.vcore != vc) continue; @@ -964,7 +964,6 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr, else vcpu->arch.intr_msr &= ~MSR_LE; } - mutex_unlock(&kvm->lock); } /* @@ -981,6 +980,7 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr, mask &= 0xFFFFFFFF; vc->lpcr = (vc->lpcr & ~mask) | (new_lpcr & mask); spin_unlock(&vc->lock); + mutex_unlock(&kvm->lock); } static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, From ecb6d6185b3ae40067330eb889977bf2a51f7429 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Fri, 20 Mar 2015 20:39:39 +1100 Subject: [PATCH 045/170] KVM: PPC: Book3S HV: Endian fix for accessing VPA yield count The VPA (virtual processor area) is defined by PAPR and is therefore big-endian, so we need a be32_to_cpu when reading it in kvmppc_get_yield_count(). Without this, H_CONFER always fails on a little-endian host, causing SMP guests to waste time spinning on spinlocks. Signed-off-by: Paul Mackerras Signed-off-by: Alexander Graf --- arch/powerpc/kvm/book3s_hv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index b2731933f807..de747563d29d 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -636,7 +636,7 @@ static int kvmppc_get_yield_count(struct kvm_vcpu *vcpu) spin_lock(&vcpu->arch.vpa_update_lock); lppaca = (struct lppaca *)vcpu->arch.vpa.pinned_addr; if (lppaca) - yield_count = lppaca->yield_count; + yield_count = be32_to_cpu(lppaca->yield_count); spin_unlock(&vcpu->arch.vpa_update_lock); return yield_count; } From 2bf27601c7b50b6ced72f27304109dc52eb52919 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Fri, 20 Mar 2015 20:39:40 +1100 Subject: [PATCH 046/170] KVM: PPC: Book3S HV: Fix instruction emulation Commit 4a157d61b48c ("KVM: PPC: Book3S HV: Fix endianness of instruction obtained from HEIR register") had the side effect that we no longer reset vcpu->arch.last_inst to -1 on guest exit in the cases where the instruction is not fetched from the guest. This means that if instruction emulation turns out to be required in those cases, the host will emulate the wrong instruction, since vcpu->arch.last_inst will contain the last instruction that was emulated. This fixes it by making sure that vcpu->arch.last_inst is reset to -1 in those cases. Signed-off-by: Paul Mackerras Signed-off-by: Alexander Graf --- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index bb94e6f20c81..6cbf1630cb70 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1005,6 +1005,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) /* Save HEIR (HV emulation assist reg) in emul_inst if this is an HEI (HV emulation interrupt, e40) */ li r3,KVM_INST_FETCH_FAILED + stw r3,VCPU_LAST_INST(r9) cmpwi r12,BOOK3S_INTERRUPT_H_EMUL_ASSIST bne 11f mfspr r3,SPRN_HEIR From 7ee8e4f3983c4ff700958a6099c8fd212ea67b94 Mon Sep 17 00:00:00 2001 From: Wenbo Wang Date: Fri, 20 Mar 2015 01:04:54 -0400 Subject: [PATCH 047/170] Fix bug in blk_rq_merge_ok Use the right array index to reference the last element of rq->biotail->bi_io_vec[] Signed-off-by: Wenbo Wang Reviewed-by: Chong Yuan Fixes: 66cb45aa41315 ("block: add support for limiting gaps in SG lists") Cc: stable@kernel.org Signed-off-by: Jens Axboe --- block/blk-merge.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/blk-merge.c b/block/blk-merge.c index fc1ff3b1ea1f..fd3fee81c23c 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -592,7 +592,7 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio) if (q->queue_flags & (1 << QUEUE_FLAG_SG_GAPS)) { struct bio_vec *bprev; - bprev = &rq->biotail->bi_io_vec[bio->bi_vcnt - 1]; + bprev = &rq->biotail->bi_io_vec[rq->biotail->bi_vcnt - 1]; if (bvec_gap_to_prev(bprev, bio->bi_io_vec[0].bv_offset)) return false; } From 715a03d2848275269bd4014a49212cc83452f32d Mon Sep 17 00:00:00 2001 From: Kinglong Mee Date: Fri, 20 Mar 2015 15:56:40 +0800 Subject: [PATCH 048/170] NFSD: restore trace event lost in mismerge 31ef83dc05 "nfsd: add trace events" had a typo that dropped a trace event and replaced it by an incorrect recursive call to nfsd4_cb_layout_fail. 133d558216d9 "Subject: nfsd: don't recursively call nfsd4_cb_layout_fail" fixed the crash, this restores the tracepoint. Reviewed-by: Christoph Hellwig Signed-off-by: Kinglong Mee Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4layouts.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 1028a0629543..0a616b51c5bb 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -587,6 +587,8 @@ nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls) rpc_ntop((struct sockaddr *)&clp->cl_addr, addr_str, sizeof(addr_str)); + trace_layout_recall_fail(&ls->ls_stid.sc_stateid); + printk(KERN_WARNING "nfsd: client %s failed to respond to layout recall. " " Fencing..\n", addr_str); From 6f8f28ec5f88715515e70dd52f16b326a5e63f81 Mon Sep 17 00:00:00 2001 From: Kinglong Mee Date: Thu, 19 Mar 2015 19:04:14 +0800 Subject: [PATCH 049/170] NFSD: Check layout type when returning client layouts According to RFC5661: " When lr_returntype is LAYOUTRETURN4_FSID, the current filehandle is used to identify the file system and all layouts matching the client ID, the fsid of the file system, lora_layout_type, and lora_iomode are returned. When lr_returntype is LAYOUTRETURN4_ALL, all layouts matching the client ID, lora_layout_type, and lora_iomode are returned and the current filehandle is not used. " When returning client layouts, always check layout type. Signed-off-by: Kinglong Mee Reviewed-by: Christoph Hellwig Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4layouts.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 0a616b51c5bb..6964613bad90 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -513,6 +513,9 @@ nfsd4_return_client_layouts(struct svc_rqst *rqstp, spin_lock(&clp->cl_lock); list_for_each_entry_safe(ls, n, &clp->cl_lo_states, ls_perclnt) { + if (ls->ls_layout_type != lrp->lr_layout_type) + continue; + if (lrp->lr_return_type == RETURN_FSID && !fh_fsid_match(&ls->ls_stid.sc_file->fi_fhandle, &cstate->current_fh.fh_handle)) From db59c0ef08ca56758dcee6495d9d6a086682c5ec Mon Sep 17 00:00:00 2001 From: Kinglong Mee Date: Thu, 19 Mar 2015 19:04:41 +0800 Subject: [PATCH 050/170] NFSD: Take care the return value from nfsd4_decode_stateid Return status after nfsd4_decode_stateid failed. Signed-off-by: Kinglong Mee Reviewed-by: Christoph Hellwig Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4xdr.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index df5e66caf100..c76654c3605f 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1562,7 +1562,11 @@ nfsd4_decode_layoutget(struct nfsd4_compoundargs *argp, p = xdr_decode_hyper(p, &lgp->lg_seg.offset); p = xdr_decode_hyper(p, &lgp->lg_seg.length); p = xdr_decode_hyper(p, &lgp->lg_minlength); - nfsd4_decode_stateid(argp, &lgp->lg_sid); + + status = nfsd4_decode_stateid(argp, &lgp->lg_sid); + if (status) + return status; + READ_BUF(4); lgp->lg_maxcount = be32_to_cpup(p++); @@ -1580,7 +1584,11 @@ nfsd4_decode_layoutcommit(struct nfsd4_compoundargs *argp, p = xdr_decode_hyper(p, &lcp->lc_seg.offset); p = xdr_decode_hyper(p, &lcp->lc_seg.length); lcp->lc_reclaim = be32_to_cpup(p++); - nfsd4_decode_stateid(argp, &lcp->lc_sid); + + status = nfsd4_decode_stateid(argp, &lcp->lc_sid); + if (status) + return status; + READ_BUF(4); lcp->lc_newoffset = be32_to_cpup(p++); if (lcp->lc_newoffset) { @@ -1628,7 +1636,11 @@ nfsd4_decode_layoutreturn(struct nfsd4_compoundargs *argp, READ_BUF(16); p = xdr_decode_hyper(p, &lrp->lr_seg.offset); p = xdr_decode_hyper(p, &lrp->lr_seg.length); - nfsd4_decode_stateid(argp, &lrp->lr_sid); + + status = nfsd4_decode_stateid(argp, &lrp->lr_sid); + if (status) + return status; + READ_BUF(4); lrp->lrf_body_len = be32_to_cpup(p++); if (lrp->lrf_body_len > 0) { From a68465c9cb435feadb0efe6acbd0a9a7d1038465 Mon Sep 17 00:00:00 2001 From: Kinglong Mee Date: Thu, 19 Mar 2015 19:48:31 +0800 Subject: [PATCH 051/170] NFSD: Error out when register_shrinker() fail If register_shrinker() failed, nfsd will cause a NULL pointer access as, [ 9250.875465] nfsd: last server has exited, flushing export cache [ 9251.427270] BUG: unable to handle kernel NULL pointer dereference at (null) [ 9251.427393] IP: [] __list_del_entry+0x29/0xd0 [ 9251.427579] PGD 13e4d067 PUD 13e4c067 PMD 0 [ 9251.427633] Oops: 0000 [#1] SMP DEBUG_PAGEALLOC [ 9251.427706] Modules linked in: ip6t_rpfilter ip6t_REJECT bnep bluetooth xt_conntrack cfg80211 rfkill ebtable_nat ebtable_broute bridge stp llc ebtable_filter ebtables ip6table_nat nf_conntrack_ipv6 nf_defrag_ipv6 nf_nat_ipv6 ip6table_mangle ip6table_security ip6table_raw ip6table_filter ip6_tables iptable_nat nf_conntrack_ipv4 nf_defrag_ipv4 nf_nat_ipv4 nf_nat nf_conntrack iptable_mangle iptable_security iptable_raw btrfs xfs microcode ppdev serio_raw pcspkr xor libcrc32c raid6_pq e1000 parport_pc parport i2c_piix4 i2c_core nfsd(OE-) auth_rpcgss nfs_acl lockd sunrpc(E) ata_generic pata_acpi [ 9251.428240] CPU: 0 PID: 1557 Comm: rmmod Tainted: G OE 3.16.0-rc2+ #22 [ 9251.428366] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 07/31/2013 [ 9251.428496] task: ffff880000849540 ti: ffff8800136f4000 task.ti: ffff8800136f4000 [ 9251.428593] RIP: 0010:[] [] __list_del_entry+0x29/0xd0 [ 9251.428696] RSP: 0018:ffff8800136f7ea0 EFLAGS: 00010207 [ 9251.428751] RAX: 0000000000000000 RBX: ffffffffa0116d48 RCX: dead000000200200 [ 9251.428814] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffffffa0116d48 [ 9251.428876] RBP: ffff8800136f7ea0 R08: ffff8800136f4000 R09: 0000000000000001 [ 9251.428939] R10: 8080808080808080 R11: 0000000000000000 R12: ffffffffa011a5a0 [ 9251.429002] R13: 0000000000000800 R14: 0000000000000000 R15: 00000000018ac090 [ 9251.429064] FS: 00007fb9acef0740(0000) GS:ffff88003fa00000(0000) knlGS:0000000000000000 [ 9251.429164] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 9251.429221] CR2: 0000000000000000 CR3: 0000000031a17000 CR4: 00000000001407f0 [ 9251.429306] Stack: [ 9251.429410] ffff8800136f7eb8 ffffffff8136fcdd ffffffffa0116d20 ffff8800136f7ed0 [ 9251.429511] ffffffff8118a0f2 0000000000000000 ffff8800136f7ee0 ffffffffa00eb765 [ 9251.429610] ffff8800136f7ef0 ffffffffa010e93c ffff8800136f7f78 ffffffff81104ac2 [ 9251.429709] Call Trace: [ 9251.429755] [] list_del+0xd/0x30 [ 9251.429896] [] unregister_shrinker+0x22/0x40 [ 9251.430037] [] nfsd_reply_cache_shutdown+0x15/0x90 [nfsd] [ 9251.430106] [] exit_nfsd+0x9/0x6cd [nfsd] [ 9251.430192] [] SyS_delete_module+0x162/0x200 [ 9251.430280] [] ? do_notify_resume+0x59/0x90 [ 9251.430395] [] system_call_fastpath+0x16/0x1b [ 9251.430457] Code: 00 00 55 48 8b 17 48 b9 00 01 10 00 00 00 ad de 48 8b 47 08 48 89 e5 48 39 ca 74 29 48 b9 00 02 20 00 00 00 ad de 48 39 c8 74 7a <4c> 8b 00 4c 39 c7 75 53 4c 8b 42 08 4c 39 c7 75 2b 48 89 42 08 [ 9251.430691] RIP [] __list_del_entry+0x29/0xd0 [ 9251.430755] RSP [ 9251.430805] CR2: 0000000000000000 [ 9251.431033] ---[ end trace 080f3050d082b4ea ]--- Signed-off-by: Kinglong Mee Reviewed-by: Christoph Hellwig Signed-off-by: J. Bruce Fields --- fs/nfsd/nfscache.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index 83a9694ec485..46ec934f5dee 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -165,13 +165,17 @@ int nfsd_reply_cache_init(void) { unsigned int hashsize; unsigned int i; + int status = 0; max_drc_entries = nfsd_cache_size_limit(); atomic_set(&num_drc_entries, 0); hashsize = nfsd_hashsize(max_drc_entries); maskbits = ilog2(hashsize); - register_shrinker(&nfsd_reply_cache_shrinker); + status = register_shrinker(&nfsd_reply_cache_shrinker); + if (status) + return status; + drc_slab = kmem_cache_create("nfsd_drc", sizeof(struct svc_cacherep), 0, 0, NULL); if (!drc_slab) From a1420384e3aa83b4ac8af85ae92d84f320272756 Mon Sep 17 00:00:00 2001 From: Kinglong Mee Date: Sun, 15 Mar 2015 23:12:15 +0800 Subject: [PATCH 052/170] NFSD: Put exports after nfsd4_layout_verify fail Fix commit 9cf514ccfa (nfsd: implement pNFS operations). Signed-off-by: Kinglong Mee Reviewed-by: Christoph Hellwig Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4proc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index d30bea8d0277..92b9d97aff4f 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1237,8 +1237,8 @@ nfsd4_getdeviceinfo(struct svc_rqst *rqstp, nfserr = ops->proc_getdeviceinfo(exp->ex_path.mnt->mnt_sb, gdp); gdp->gd_notify_types &= ops->notify_types; - exp_put(exp); out: + exp_put(exp); return nfserr; } From f93a25b38cbd840f26c9fd2dd8a6611a57b259b7 Mon Sep 17 00:00:00 2001 From: Arend van Spriel Date: Fri, 20 Mar 2015 22:18:17 +0100 Subject: [PATCH 053/170] brcmfmac: disable MBSS feature for BCM43362 The BCM43362 firmware falsely reports it is capable of providing MBSS. As a result AP mode no longer works for this device. Therefor disable MBSS in the driver for this chipset. Cc: stable@vger.kernel.org # 3.19.y Reported-by: Jorg Krause Reviewed-by: Hante Meuleman Reviewed-by: Pieter-Paul Giesberts Signed-off-by: Arend van Spriel Signed-off-by: Kalle Valo --- drivers/net/wireless/brcm80211/brcmfmac/feature.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/brcm80211/brcmfmac/feature.c b/drivers/net/wireless/brcm80211/brcmfmac/feature.c index defb7a44e0bc..7748a1ccf14f 100644 --- a/drivers/net/wireless/brcm80211/brcmfmac/feature.c +++ b/drivers/net/wireless/brcm80211/brcmfmac/feature.c @@ -126,7 +126,8 @@ void brcmf_feat_attach(struct brcmf_pub *drvr) brcmf_feat_iovar_int_get(ifp, BRCMF_FEAT_MCHAN, "mchan"); if (drvr->bus_if->wowl_supported) brcmf_feat_iovar_int_get(ifp, BRCMF_FEAT_WOWL, "wowl"); - brcmf_feat_iovar_int_set(ifp, BRCMF_FEAT_MBSS, "mbss", 0); + if (drvr->bus_if->chip != BRCM_CC_43362_CHIP_ID) + brcmf_feat_iovar_int_set(ifp, BRCMF_FEAT_MBSS, "mbss", 0); /* set chip related quirks */ switch (drvr->bus_if->chip) { From be0b5e635883678bfbc695889772fed545f3427d Mon Sep 17 00:00:00 2001 From: Larry Finger Date: Sat, 21 Mar 2015 15:16:05 -0500 Subject: [PATCH 054/170] rtlwifi: Fix IOMMU mapping leak in AP mode Transmission of an AP beacon does not call the TX interrupt service routine, which usually does the cleanup. Instead, cleanup is handled in a tasklet completion routine. Unfortunately, this routine has a serious bug in that it does not release the DMA mapping before it frees the skb, thus one IOMMU mapping is leaked for each beacon. The test system failed with no free IOMMU mapping slots approximately one hour after hostapd was used to start an AP. This issue was reported and tested at https://github.com/lwfinger/rtlwifi_new/issues/30. Reported-and-tested-by: Kevin Mullican Cc: Kevin Mullican Signed-off-by: Shao Fu Signed-off-by: Larry Finger Cc: Stable [3.18+] Signed-off-by: Kalle Valo --- drivers/net/wireless/rtlwifi/pci.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/rtlwifi/pci.c b/drivers/net/wireless/rtlwifi/pci.c index a62170ea0481..8c45cf44ce24 100644 --- a/drivers/net/wireless/rtlwifi/pci.c +++ b/drivers/net/wireless/rtlwifi/pci.c @@ -1124,12 +1124,22 @@ static void _rtl_pci_prepare_bcn_tasklet(struct ieee80211_hw *hw) /*This is for new trx flow*/ struct rtl_tx_buffer_desc *pbuffer_desc = NULL; u8 temp_one = 1; + u8 *entry; memset(&tcb_desc, 0, sizeof(struct rtl_tcb_desc)); ring = &rtlpci->tx_ring[BEACON_QUEUE]; pskb = __skb_dequeue(&ring->queue); - if (pskb) + if (rtlpriv->use_new_trx_flow) + entry = (u8 *)(&ring->buffer_desc[ring->idx]); + else + entry = (u8 *)(&ring->desc[ring->idx]); + if (pskb) { + pci_unmap_single(rtlpci->pdev, + rtlpriv->cfg->ops->get_desc( + (u8 *)entry, true, HW_DESC_TXBUFF_ADDR), + pskb->len, PCI_DMA_TODEVICE); kfree_skb(pskb); + } /*NB: the beacon data buffer must be 32-bit aligned. */ pskb = ieee80211_beacon_get(hw, mac->vif); From 082d70b6142f623c10f7a032d9b63a2399fb4ded Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Sun, 15 Mar 2015 11:03:38 -0400 Subject: [PATCH 055/170] can: kvaser_usb: Comply with firmware max tx URBs value Current driver code arbitrarily assumes a max outstanding tx value of 16 parallel transmissions. Meanwhile, the device firmware provides its actual maximum inside its reply to the CMD_GET_SOFTWARE_INFO message. Under heavy tx traffic, if the interleaved transmissions count increases above the limit reported by firmware, the firmware breaks up badly, reports a massive list of internal errors, and the candump traces hardly matches the actual frames sent and received. On the other hand, in certain models, the firmware can support up to 48 tx URBs instead of just 16, increasing the driver throughput by two-fold and reducing the possibility of -ENOBUFs. Thus dynamically set the driver's max tx URBs value according to firmware replies. Signed-off-by: Ahmed S. Darwish Signed-off-by: Marc Kleine-Budde --- drivers/net/can/usb/kvaser_usb.c | 62 +++++++++++++++++++------------- 1 file changed, 38 insertions(+), 24 deletions(-) diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c index e97a08ce0b90..2f9733a8e125 100644 --- a/drivers/net/can/usb/kvaser_usb.c +++ b/drivers/net/can/usb/kvaser_usb.c @@ -25,7 +25,6 @@ #include #include -#define MAX_TX_URBS 16 #define MAX_RX_URBS 4 #define START_TIMEOUT 1000 /* msecs */ #define STOP_TIMEOUT 1000 /* msecs */ @@ -443,6 +442,7 @@ struct kvaser_usb_error_summary { }; }; +/* Context for an outstanding, not yet ACKed, transmission */ struct kvaser_usb_tx_urb_context { struct kvaser_usb_net_priv *priv; u32 echo_index; @@ -456,8 +456,13 @@ struct kvaser_usb { struct usb_endpoint_descriptor *bulk_in, *bulk_out; struct usb_anchor rx_submitted; + /* @max_tx_urbs: Firmware-reported maximum number of oustanding, + * not yet ACKed, transmissions on this device. This value is + * also used as a sentinel for marking free tx contexts. + */ u32 fw_version; unsigned int nchannels; + unsigned int max_tx_urbs; enum kvaser_usb_family family; bool rxinitdone; @@ -467,19 +472,18 @@ struct kvaser_usb { struct kvaser_usb_net_priv { struct can_priv can; - - spinlock_t tx_contexts_lock; - int active_tx_contexts; - struct kvaser_usb_tx_urb_context tx_contexts[MAX_TX_URBS]; - - struct usb_anchor tx_submitted; - struct completion start_comp, stop_comp; + struct can_berr_counter bec; struct kvaser_usb *dev; struct net_device *netdev; int channel; - struct can_berr_counter bec; + struct completion start_comp, stop_comp; + struct usb_anchor tx_submitted; + + spinlock_t tx_contexts_lock; + int active_tx_contexts; + struct kvaser_usb_tx_urb_context tx_contexts[]; }; static const struct usb_device_id kvaser_usb_table[] = { @@ -657,9 +661,13 @@ static int kvaser_usb_get_software_info(struct kvaser_usb *dev) switch (dev->family) { case KVASER_LEAF: dev->fw_version = le32_to_cpu(msg.u.leaf.softinfo.fw_version); + dev->max_tx_urbs = + le16_to_cpu(msg.u.leaf.softinfo.max_outstanding_tx); break; case KVASER_USBCAN: dev->fw_version = le32_to_cpu(msg.u.usbcan.softinfo.fw_version); + dev->max_tx_urbs = + le16_to_cpu(msg.u.usbcan.softinfo.max_outstanding_tx); break; } @@ -715,7 +723,7 @@ static void kvaser_usb_tx_acknowledge(const struct kvaser_usb *dev, stats = &priv->netdev->stats; - context = &priv->tx_contexts[tid % MAX_TX_URBS]; + context = &priv->tx_contexts[tid % dev->max_tx_urbs]; /* Sometimes the state change doesn't come after a bus-off event */ if (priv->can.restart_ms && @@ -744,7 +752,7 @@ static void kvaser_usb_tx_acknowledge(const struct kvaser_usb *dev, spin_lock_irqsave(&priv->tx_contexts_lock, flags); can_get_echo_skb(priv->netdev, context->echo_index); - context->echo_index = MAX_TX_URBS; + context->echo_index = dev->max_tx_urbs; --priv->active_tx_contexts; netif_wake_queue(priv->netdev); @@ -1512,11 +1520,13 @@ static int kvaser_usb_open(struct net_device *netdev) static void kvaser_usb_reset_tx_urb_contexts(struct kvaser_usb_net_priv *priv) { - int i; + int i, max_tx_urbs; + + max_tx_urbs = priv->dev->max_tx_urbs; priv->active_tx_contexts = 0; - for (i = 0; i < MAX_TX_URBS; i++) - priv->tx_contexts[i].echo_index = MAX_TX_URBS; + for (i = 0; i < max_tx_urbs; i++) + priv->tx_contexts[i].echo_index = max_tx_urbs; } /* This method might sleep. Do not call it in the atomic context @@ -1702,14 +1712,14 @@ static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb, *msg_tx_can_flags |= MSG_FLAG_REMOTE_FRAME; spin_lock_irqsave(&priv->tx_contexts_lock, flags); - for (i = 0; i < ARRAY_SIZE(priv->tx_contexts); i++) { - if (priv->tx_contexts[i].echo_index == MAX_TX_URBS) { + for (i = 0; i < dev->max_tx_urbs; i++) { + if (priv->tx_contexts[i].echo_index == dev->max_tx_urbs) { context = &priv->tx_contexts[i]; context->echo_index = i; can_put_echo_skb(skb, netdev, context->echo_index); ++priv->active_tx_contexts; - if (priv->active_tx_contexts >= MAX_TX_URBS) + if (priv->active_tx_contexts >= dev->max_tx_urbs) netif_stop_queue(netdev); break; @@ -1743,7 +1753,7 @@ static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb, spin_lock_irqsave(&priv->tx_contexts_lock, flags); can_free_echo_skb(netdev, context->echo_index); - context->echo_index = MAX_TX_URBS; + context->echo_index = dev->max_tx_urbs; --priv->active_tx_contexts; netif_wake_queue(netdev); @@ -1881,7 +1891,9 @@ static int kvaser_usb_init_one(struct usb_interface *intf, if (err) return err; - netdev = alloc_candev(sizeof(*priv), MAX_TX_URBS); + netdev = alloc_candev(sizeof(*priv) + + dev->max_tx_urbs * sizeof(*priv->tx_contexts), + dev->max_tx_urbs); if (!netdev) { dev_err(&intf->dev, "Cannot alloc candev\n"); return -ENOMEM; @@ -2009,6 +2021,13 @@ static int kvaser_usb_probe(struct usb_interface *intf, return err; } + dev_dbg(&intf->dev, "Firmware version: %d.%d.%d\n", + ((dev->fw_version >> 24) & 0xff), + ((dev->fw_version >> 16) & 0xff), + (dev->fw_version & 0xffff)); + + dev_dbg(&intf->dev, "Max oustanding tx = %d URBs\n", dev->max_tx_urbs); + err = kvaser_usb_get_card_info(dev); if (err) { dev_err(&intf->dev, @@ -2016,11 +2035,6 @@ static int kvaser_usb_probe(struct usb_interface *intf, return err; } - dev_dbg(&intf->dev, "Firmware version: %d.%d.%d\n", - ((dev->fw_version >> 24) & 0xff), - ((dev->fw_version >> 16) & 0xff), - (dev->fw_version & 0xffff)); - for (i = 0; i < dev->nchannels; i++) { err = kvaser_usb_init_one(intf, id, i); if (err) { From 7e184c28636dce594426cd7d8781d52d1dd447cd Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Sun, 15 Mar 2015 11:10:49 -0400 Subject: [PATCH 056/170] can: kvaser_usb: Fix sparse warning __le16 degrades to integer USB endpoint's wMaxPacketSize field is an le16 entity. Use appropriate le16_to_cpu macros to maintain endian independence. Reported-by: Marc Kleine-Budde Signed-off-by: Ahmed S. Darwish Signed-off-by: Marc Kleine-Budde --- drivers/net/can/usb/kvaser_usb.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c index 2f9733a8e125..57611fd91229 100644 --- a/drivers/net/can/usb/kvaser_usb.c +++ b/drivers/net/can/usb/kvaser_usb.c @@ -596,8 +596,8 @@ static int kvaser_usb_wait_msg(const struct kvaser_usb *dev, u8 id, * for further details. */ if (tmp->len == 0) { - pos = round_up(pos, - dev->bulk_in->wMaxPacketSize); + pos = round_up(pos, le16_to_cpu(dev->bulk_in-> + wMaxPacketSize)); continue; } @@ -1337,7 +1337,8 @@ static void kvaser_usb_read_bulk_callback(struct urb *urb) * number of events in case of a heavy rx load on the bus. */ if (msg->len == 0) { - pos = round_up(pos, dev->bulk_in->wMaxPacketSize); + pos = round_up(pos, le16_to_cpu(dev->bulk_in-> + wMaxPacketSize)); continue; } From 37920a74abd6fdf0696730ba80a07843a62c9c54 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Mon, 16 Mar 2015 22:42:24 +0000 Subject: [PATCH 057/170] can: gs_usb: check for kzalloc allocation failure smatch detected the following issue: drivers/net/can/usb/gs_usb.c:904 gs_usb_probe() error: potential null dereference 'dev'. (kzalloc returns null) Add a check for null return from kzalloc and return -ENOMEM Signed-off-by: Colin Ian King Signed-off-by: Marc Kleine-Budde --- drivers/net/can/usb/gs_usb.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index 009acc8641fc..8b4d3e6875eb 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -901,6 +901,8 @@ static int gs_usb_probe(struct usb_interface *intf, const struct usb_device_id * } dev = kzalloc(sizeof(*dev), GFP_KERNEL); + if (!dev) + return -ENOMEM; init_usb_anchor(&dev->rx_submitted); atomic_set(&dev->active_channels, 0); From 3ef5247e033972ddbd16f65ec2ad8a7dfc2e4170 Mon Sep 17 00:00:00 2001 From: Stephane Grosjean Date: Mon, 16 Mar 2015 11:57:52 +0100 Subject: [PATCH 058/170] can: peak_usb: rename usb option cmds definition and structs The PUCAN_CMD_RX_FRAME_(ENABLE|DISABLE) command has extended its purpose and was therefore renamed to PUCAN_CMD_SET_(EN|DIS)_OPTION. Signed-off-by: Stephane Grosjean Signed-off-by: Oliver Hartkopp Tested-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- drivers/net/can/usb/peak_usb/pcan_ucan.h | 14 ++++---- drivers/net/can/usb/peak_usb/pcan_usb_fd.c | 42 +++++++++++----------- 2 files changed, 28 insertions(+), 28 deletions(-) diff --git a/drivers/net/can/usb/peak_usb/pcan_ucan.h b/drivers/net/can/usb/peak_usb/pcan_ucan.h index 1ba7c25002e1..1fb33307be4e 100644 --- a/drivers/net/can/usb/peak_usb/pcan_ucan.h +++ b/drivers/net/can/usb/peak_usb/pcan_ucan.h @@ -26,8 +26,8 @@ #define PUCAN_CMD_FILTER_STD 0x008 #define PUCAN_CMD_TX_ABORT 0x009 #define PUCAN_CMD_WR_ERR_CNT 0x00a -#define PUCAN_CMD_RX_FRAME_ENABLE 0x00b -#define PUCAN_CMD_RX_FRAME_DISABLE 0x00c +#define PUCAN_CMD_SET_EN_OPTION 0x00b +#define PUCAN_CMD_CLR_DIS_OPTION 0x00c #define PUCAN_CMD_END_OF_COLLECTION 0x3ff /* uCAN received messages list */ @@ -101,14 +101,14 @@ struct __packed pucan_wr_err_cnt { u16 unused; }; -/* uCAN RX_FRAME_ENABLE command fields */ -#define PUCAN_FLTEXT_ERROR 0x0001 -#define PUCAN_FLTEXT_BUSLOAD 0x0002 +/* uCAN SET_EN/CLR_DIS _OPTION command fields */ +#define PUCAN_OPTION_ERROR 0x0001 +#define PUCAN_OPTION_BUSLOAD 0x0002 -struct __packed pucan_filter_ext { +struct __packed pucan_options { __le16 opcode_channel; - __le16 ext_mask; + __le16 options; u32 unused; }; diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c index 0bac0f14edc3..7506a8352edd 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c @@ -110,13 +110,13 @@ struct __packed pcan_ufd_led { u8 unused[5]; }; -/* Extended usage of uCAN commands CMD_RX_FRAME_xxxABLE for PCAN-USB Pro FD */ +/* Extended usage of uCAN commands CMD_xxx_xx_OPTION for PCAN-USB Pro FD */ #define PCAN_UFD_FLTEXT_CALIBRATION 0x8000 -struct __packed pcan_ufd_filter_ext { +struct __packed pcan_ufd_options { __le16 opcode_channel; - __le16 ext_mask; + __le16 ucan_mask; u16 unused; __le16 usb_mask; }; @@ -321,21 +321,21 @@ static int pcan_usb_fd_set_filter_std(struct peak_usb_device *dev, int idx, return pcan_usb_fd_send_cmd(dev, cmd); } -/* set/unset notifications filter: +/* set/unset options * - * onoff sets(1)/unset(0) notifications - * mask each bit defines a kind of notification to set/unset + * onoff set(1)/unset(0) options + * mask each bit defines a kind of options to set/unset */ -static int pcan_usb_fd_set_filter_ext(struct peak_usb_device *dev, - bool onoff, u16 ext_mask, u16 usb_mask) +static int pcan_usb_fd_set_options(struct peak_usb_device *dev, + bool onoff, u16 ucan_mask, u16 usb_mask) { - struct pcan_ufd_filter_ext *cmd = pcan_usb_fd_cmd_buffer(dev); + struct pcan_ufd_options *cmd = pcan_usb_fd_cmd_buffer(dev); cmd->opcode_channel = pucan_cmd_opcode_channel(dev, - (onoff) ? PUCAN_CMD_RX_FRAME_ENABLE : - PUCAN_CMD_RX_FRAME_DISABLE); + (onoff) ? PUCAN_CMD_SET_EN_OPTION : + PUCAN_CMD_CLR_DIS_OPTION); - cmd->ext_mask = cpu_to_le16(ext_mask); + cmd->ucan_mask = cpu_to_le16(ucan_mask); cmd->usb_mask = cpu_to_le16(usb_mask); /* send the command */ @@ -770,9 +770,9 @@ static int pcan_usb_fd_start(struct peak_usb_device *dev) &pcan_usb_pro_fd); /* enable USB calibration messages */ - err = pcan_usb_fd_set_filter_ext(dev, 1, - PUCAN_FLTEXT_ERROR, - PCAN_UFD_FLTEXT_CALIBRATION); + err = pcan_usb_fd_set_options(dev, 1, + PUCAN_OPTION_ERROR, + PCAN_UFD_FLTEXT_CALIBRATION); } pdev->usb_if->dev_opened_count++; @@ -806,9 +806,9 @@ static int pcan_usb_fd_stop(struct peak_usb_device *dev) /* turn off special msgs for that interface if no other dev opened */ if (pdev->usb_if->dev_opened_count == 1) - pcan_usb_fd_set_filter_ext(dev, 0, - PUCAN_FLTEXT_ERROR, - PCAN_UFD_FLTEXT_CALIBRATION); + pcan_usb_fd_set_options(dev, 0, + PUCAN_OPTION_ERROR, + PCAN_UFD_FLTEXT_CALIBRATION); pdev->usb_if->dev_opened_count--; return 0; @@ -937,9 +937,9 @@ static void pcan_usb_fd_exit(struct peak_usb_device *dev) if (dev->ctrl_idx == 0) { /* turn off calibration message if any device were opened */ if (pdev->usb_if->dev_opened_count > 0) - pcan_usb_fd_set_filter_ext(dev, 0, - PUCAN_FLTEXT_ERROR, - PCAN_UFD_FLTEXT_CALIBRATION); + pcan_usb_fd_set_options(dev, 0, + PUCAN_OPTION_ERROR, + PCAN_UFD_FLTEXT_CALIBRATION); /* tell USB adapter that the driver is being unloaded */ pcan_usb_fd_drv_loaded(dev, 0); From 0f251e45c7cbb1a494b5600485ea8ff64f664b3f Mon Sep 17 00:00:00 2001 From: Stephane Grosjean Date: Mon, 16 Mar 2015 11:57:53 +0100 Subject: [PATCH 059/170] can: peak_usb_fd: add support for ISO / non-ISO mode switching The PCAN USB (pro) FD adapters with firmware versions > 2.x support the switching between ISO (default) and non-ISO conform bitstreams on the CAN bus. The setting for the 2.x firmware adapters can be modified with the 'ip' tool from the iproute2 package (option: fd-non-iso [on|off]). Signed-off-by: Stephane Grosjean Signed-off-by: Oliver Hartkopp Tested-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- drivers/net/can/usb/peak_usb/pcan_ucan.h | 1 + drivers/net/can/usb/peak_usb/pcan_usb_fd.c | 31 ++++++++++++++++++++-- 2 files changed, 30 insertions(+), 2 deletions(-) diff --git a/drivers/net/can/usb/peak_usb/pcan_ucan.h b/drivers/net/can/usb/peak_usb/pcan_ucan.h index 1fb33307be4e..e8fc4952c6b0 100644 --- a/drivers/net/can/usb/peak_usb/pcan_ucan.h +++ b/drivers/net/can/usb/peak_usb/pcan_ucan.h @@ -104,6 +104,7 @@ struct __packed pucan_wr_err_cnt { /* uCAN SET_EN/CLR_DIS _OPTION command fields */ #define PUCAN_OPTION_ERROR 0x0001 #define PUCAN_OPTION_BUSLOAD 0x0002 +#define PUCAN_OPTION_CANDFDISO 0x0004 struct __packed pucan_options { __le16 opcode_channel; diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c index 7506a8352edd..a9221ad9f1a0 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c @@ -251,6 +251,27 @@ static int pcan_usb_fd_build_restart_cmd(struct peak_usb_device *dev, u8 *buf) /* moves the pointer forward */ pc += sizeof(struct pucan_wr_err_cnt); + /* add command to switch from ISO to non-ISO mode, if fw allows it */ + if (dev->can.ctrlmode_supported & CAN_CTRLMODE_FD_NON_ISO) { + struct pucan_options *puo = (struct pucan_options *)pc; + + puo->opcode_channel = + (dev->can.ctrlmode & CAN_CTRLMODE_FD_NON_ISO) ? + pucan_cmd_opcode_channel(dev, + PUCAN_CMD_CLR_DIS_OPTION) : + pucan_cmd_opcode_channel(dev, PUCAN_CMD_SET_EN_OPTION); + + puo->options = cpu_to_le16(PUCAN_OPTION_CANDFDISO); + + /* to be sure that no other extended bits will be taken into + * account + */ + puo->unused = 0; + + /* moves the pointer forward */ + pc += sizeof(struct pucan_options); + } + /* next, go back to operational mode */ cmd = (struct pucan_command *)pc; cmd->opcode_channel = pucan_cmd_opcode_channel(dev, @@ -860,8 +881,14 @@ static int pcan_usb_fd_init(struct peak_usb_device *dev) pdev->usb_if->fw_info.fw_version[2], dev->adapter->ctrl_count); - /* the currently supported hw is non-ISO */ - dev->can.ctrlmode = CAN_CTRLMODE_FD_NON_ISO; + /* check for ability to switch between ISO/non-ISO modes */ + if (pdev->usb_if->fw_info.fw_version[0] >= 2) { + /* firmware >= 2.x supports ISO/non-ISO switching */ + dev->can.ctrlmode_supported |= CAN_CTRLMODE_FD_NON_ISO; + } else { + /* firmware < 2.x only supports fixed(!) non-ISO */ + dev->can.ctrlmode |= CAN_CTRLMODE_FD_NON_ISO; + } /* tell the hardware the can driver is running */ err = pcan_usb_fd_drv_loaded(dev, 1); From 258ce80e19211f06c97a562a71308ec21a9ab98f Mon Sep 17 00:00:00 2001 From: Andri Yngvason Date: Tue, 17 Mar 2015 13:03:09 +0000 Subject: [PATCH 060/170] can: flexcan: fix bus-off error state handling. Making sure that the bus-off state gets passed to can_change_state(). Signed-off-by: Andri Yngvason Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- drivers/net/can/flexcan.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index 80c46ad4cee4..ee944ae6bb96 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -592,13 +592,12 @@ static int flexcan_poll_state(struct net_device *dev, u32 reg_esr) rx_state = unlikely(reg_esr & FLEXCAN_ESR_RX_WRN) ? CAN_STATE_ERROR_WARNING : CAN_STATE_ERROR_ACTIVE; new_state = max(tx_state, rx_state); - } else if (unlikely(flt == FLEXCAN_ESR_FLT_CONF_PASSIVE)) { + } else { __flexcan_get_berr_counter(dev, &bec); - new_state = CAN_STATE_ERROR_PASSIVE; + new_state = flt == FLEXCAN_ESR_FLT_CONF_PASSIVE ? + CAN_STATE_ERROR_PASSIVE : CAN_STATE_BUS_OFF; rx_state = bec.rxerr >= bec.txerr ? new_state : 0; tx_state = bec.rxerr <= bec.txerr ? new_state : 0; - } else { - new_state = CAN_STATE_BUS_OFF; } /* state hasn't changed */ From 555828ef45f825d6ee06559f0304163550eed380 Mon Sep 17 00:00:00 2001 From: Andreas Werner Date: Sun, 22 Mar 2015 17:35:52 +0100 Subject: [PATCH 061/170] can: flexcan: Deferred on Regulator return EPROBE_DEFER Return EPROBE_DEFER if Regulator returns EPROBE_DEFER If the Flexcan driver is built into kernel and a regulator is used to enable the CAN transceiver, the Flexcan driver may not use the regulator. When initializing the Flexcan device with a regulator defined in the device tree, but not initialized, the regulator subsystem returns EPROBE_DEFER, hence the Flexcan init fails. The solution for this is to return EPROBE_DEFER if regulator is not initialized and wait until the regulator is initialized. Signed-off-by: Andreas Werner Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- drivers/net/can/flexcan.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index ee944ae6bb96..ad0a7e8c2c2b 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -1157,12 +1157,19 @@ static int flexcan_probe(struct platform_device *pdev) const struct flexcan_devtype_data *devtype_data; struct net_device *dev; struct flexcan_priv *priv; + struct regulator *reg_xceiver; struct resource *mem; struct clk *clk_ipg = NULL, *clk_per = NULL; void __iomem *base; int err, irq; u32 clock_freq = 0; + reg_xceiver = devm_regulator_get(&pdev->dev, "xceiver"); + if (PTR_ERR(reg_xceiver) == -EPROBE_DEFER) + return -EPROBE_DEFER; + else if (IS_ERR(reg_xceiver)) + reg_xceiver = NULL; + if (pdev->dev.of_node) of_property_read_u32(pdev->dev.of_node, "clock-frequency", &clock_freq); @@ -1223,9 +1230,7 @@ static int flexcan_probe(struct platform_device *pdev) priv->pdata = dev_get_platdata(&pdev->dev); priv->devtype_data = devtype_data; - priv->reg_xceiver = devm_regulator_get(&pdev->dev, "xceiver"); - if (IS_ERR(priv->reg_xceiver)) - priv->reg_xceiver = NULL; + priv->reg_xceiver = reg_xceiver; netif_napi_add(dev, &priv->napi, flexcan_poll, FLEXCAN_NAPI_WEIGHT); From 44d5f6f5901e996744858c175baee320ccf1eda3 Mon Sep 17 00:00:00 2001 From: Mahesh Salgaonkar Date: Tue, 17 Mar 2015 16:14:41 +0530 Subject: [PATCH 062/170] powerpc/book3s: Fix the MCE code to use CONFIG_KVM_BOOK3S_64_HANDLER commit id 2ba9f0d has changed CONFIG_KVM_BOOK3S_64_HV to tristate to allow HV/PR bits to be built as modules. But the MCE code still depends on CONFIG_KVM_BOOK3S_64_HV which is wrong. When user selects CONFIG_KVM_BOOK3S_64_HV=m to build HV/PR bits as a separate module the relevant MCE code gets excluded. This patch fixes the MCE code to use CONFIG_KVM_BOOK3S_64_HANDLER. This makes sure that the relevant MCE code is included when HV/PR bits are built as a separate modules. Fixes: 2ba9f0d88750 ("kvm: powerpc: book3s: Support building HV and PR KVM as module") Cc: stable@vger.kernel.org # v3.14+ Signed-off-by: Mahesh Salgaonkar Acked-by: Paul Mackerras Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/exceptions-64s.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index c2df8150bd7a..9519e6bdc6d7 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1408,7 +1408,7 @@ machine_check_handle_early: bne 9f /* continue in V mode if we are. */ 5: -#ifdef CONFIG_KVM_BOOK3S_64_HV +#ifdef CONFIG_KVM_BOOK3S_64_HANDLER /* * We are coming from kernel context. Check if we are coming from * guest. if yes, then we can continue. We will fall through From d525211f9d1be8b523ec7633f080f2116f5ea536 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 19 Feb 2015 18:03:11 +0100 Subject: [PATCH 063/170] perf: Fix irq_work 'tail' recursion Vince reported a watchdog lockup like: [] perf_tp_event+0xc4/0x210 [] perf_trace_lock+0x12a/0x160 [] lock_release+0x130/0x260 [] _raw_spin_unlock_irqrestore+0x24/0x40 [] do_send_sig_info+0x5d/0x80 [] send_sigio_to_task+0x12f/0x1a0 [] send_sigio+0xae/0x100 [] kill_fasync+0x97/0xf0 [] perf_event_wakeup+0xd4/0xf0 [] perf_pending_event+0x33/0x60 [] irq_work_run_list+0x4c/0x80 [] irq_work_run+0x18/0x40 [] smp_trace_irq_work_interrupt+0x3f/0xc0 [] trace_irq_work_interrupt+0x6d/0x80 Which is caused by an irq_work generating new irq_work and therefore not allowing forward progress. This happens because processing the perf irq_work triggers another perf event (tracepoint stuff) which in turn generates an irq_work ad infinitum. Avoid this by raising the recursion counter in the irq_work -- which effectively disables all software events (including tracepoints) from actually triggering again. Reported-by: Vince Weaver Tested-by: Vince Weaver Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Paul Mackerras Cc: Steven Rostedt Cc: Link: http://lkml.kernel.org/r/20150219170311.GH21418@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- kernel/events/core.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/kernel/events/core.c b/kernel/events/core.c index 453ef61311d4..2fabc0627165 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4574,6 +4574,13 @@ static void perf_pending_event(struct irq_work *entry) { struct perf_event *event = container_of(entry, struct perf_event, pending); + int rctx; + + rctx = perf_swevent_get_recursion_context(); + /* + * If we 'fail' here, that's OK, it means recursion is already disabled + * and we won't recurse 'further'. + */ if (event->pending_disable) { event->pending_disable = 0; @@ -4584,6 +4591,9 @@ static void perf_pending_event(struct irq_work *entry) event->pending_wakeup = 0; perf_event_wakeup(event); } + + if (rctx >= 0) + perf_swevent_put_recursion_context(rctx); } /* From 746db9443ea57fd9c059f62c4bfbf41cf224fe13 Mon Sep 17 00:00:00 2001 From: Brian Silverman Date: Wed, 18 Feb 2015 16:23:56 -0800 Subject: [PATCH 064/170] sched: Fix RLIMIT_RTTIME when PI-boosting to RT When non-realtime tasks get priority-inheritance boosted to a realtime scheduling class, RLIMIT_RTTIME starts to apply to them. However, the counter used for checking this (the same one used for SCHED_RR timeslices) was not getting reset. This meant that tasks running with a non-realtime scheduling class which are repeatedly boosted to a realtime one, but never block while they are running realtime, eventually hit the timeout without ever running for a time over the limit. This patch resets the realtime timeslice counter when un-PI-boosting from an RT to a non-RT scheduling class. I have some test code with two threads and a shared PTHREAD_PRIO_INHERIT mutex which induces priority boosting and spins while boosted that gets killed by a SIGXCPU on non-fixed kernels but doesn't with this patch applied. It happens much faster with a CONFIG_PREEMPT_RT kernel, and does happen eventually with PREEMPT_VOLUNTARY kernels. Signed-off-by: Brian Silverman Signed-off-by: Peter Zijlstra (Intel) Cc: austin@peloton-tech.com Cc: Link: http://lkml.kernel.org/r/1424305436-6716-1-git-send-email-brian@peloton-tech.com Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f0f831e8a345..62671f53202a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3034,6 +3034,8 @@ void rt_mutex_setprio(struct task_struct *p, int prio) } else { if (dl_prio(oldprio)) p->dl.dl_boosted = 0; + if (rt_prio(oldprio)) + p->rt.timeout = 0; p->sched_class = &fair_sched_class; } From 35a9393c95b31870a74f51a3e7455f33f5657b6f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 26 Feb 2015 16:23:11 +0100 Subject: [PATCH 065/170] lockdep: Fix the module unload key range freeing logic Module unload calls lockdep_free_key_range(), which removes entries from the data structures. Most of the lockdep code OTOH assumes the data structures are append only; in specific see the comments in add_lock_to_list() and look_up_lock_class(). Clearly this has only worked by accident; make it work proper. The actual scenario to make it go boom would involve the memory freed by the module unlock being re-allocated and re-used for a lock inside of a rcu-sched grace period. This is a very unlikely scenario, still better plug the hole. Use RCU list iteration in all places and ammend the comments. Change lockdep_free_key_range() to issue a sync_sched() between removal from the lists and returning -- which results in the memory being freed. Further ensure the callers are placed correctly and comment the requirements. Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Andrey Tsyvarev Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Rusty Russell Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- kernel/locking/lockdep.c | 81 +++++++++++++++++++++++++++------------- kernel/module.c | 8 ++-- 2 files changed, 59 insertions(+), 30 deletions(-) diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 88d0d4420ad2..ba77ab5f64dd 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -633,7 +633,7 @@ static int count_matching_names(struct lock_class *new_class) if (!new_class->name) return 0; - list_for_each_entry(class, &all_lock_classes, lock_entry) { + list_for_each_entry_rcu(class, &all_lock_classes, lock_entry) { if (new_class->key - new_class->subclass == class->key) return class->name_version; if (class->name && !strcmp(class->name, new_class->name)) @@ -700,10 +700,12 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass) hash_head = classhashentry(key); /* - * We can walk the hash lockfree, because the hash only - * grows, and we are careful when adding entries to the end: + * We do an RCU walk of the hash, see lockdep_free_key_range(). */ - list_for_each_entry(class, hash_head, hash_entry) { + if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) + return NULL; + + list_for_each_entry_rcu(class, hash_head, hash_entry) { if (class->key == key) { /* * Huh! same key, different name? Did someone trample @@ -728,7 +730,8 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) struct lockdep_subclass_key *key; struct list_head *hash_head; struct lock_class *class; - unsigned long flags; + + DEBUG_LOCKS_WARN_ON(!irqs_disabled()); class = look_up_lock_class(lock, subclass); if (likely(class)) @@ -750,28 +753,26 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) key = lock->key->subkeys + subclass; hash_head = classhashentry(key); - raw_local_irq_save(flags); if (!graph_lock()) { - raw_local_irq_restore(flags); return NULL; } /* * We have to do the hash-walk again, to avoid races * with another CPU: */ - list_for_each_entry(class, hash_head, hash_entry) + list_for_each_entry_rcu(class, hash_head, hash_entry) { if (class->key == key) goto out_unlock_set; + } + /* * Allocate a new key from the static array, and add it to * the hash: */ if (nr_lock_classes >= MAX_LOCKDEP_KEYS) { if (!debug_locks_off_graph_unlock()) { - raw_local_irq_restore(flags); return NULL; } - raw_local_irq_restore(flags); print_lockdep_off("BUG: MAX_LOCKDEP_KEYS too low!"); dump_stack(); @@ -798,7 +799,6 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) if (verbose(class)) { graph_unlock(); - raw_local_irq_restore(flags); printk("\nnew class %p: %s", class->key, class->name); if (class->name_version > 1) @@ -806,15 +806,12 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) printk("\n"); dump_stack(); - raw_local_irq_save(flags); if (!graph_lock()) { - raw_local_irq_restore(flags); return NULL; } } out_unlock_set: graph_unlock(); - raw_local_irq_restore(flags); out_set_class_cache: if (!subclass || force) @@ -870,11 +867,9 @@ static int add_lock_to_list(struct lock_class *class, struct lock_class *this, entry->distance = distance; entry->trace = *trace; /* - * Since we never remove from the dependency list, the list can - * be walked lockless by other CPUs, it's only allocation - * that must be protected by the spinlock. But this also means - * we must make new entries visible only once writes to the - * entry become visible - hence the RCU op: + * Both allocation and removal are done under the graph lock; but + * iteration is under RCU-sched; see look_up_lock_class() and + * lockdep_free_key_range(). */ list_add_tail_rcu(&entry->entry, head); @@ -1025,7 +1020,9 @@ static int __bfs(struct lock_list *source_entry, else head = &lock->class->locks_before; - list_for_each_entry(entry, head, entry) { + DEBUG_LOCKS_WARN_ON(!irqs_disabled()); + + list_for_each_entry_rcu(entry, head, entry) { if (!lock_accessed(entry)) { unsigned int cq_depth; mark_lock_accessed(entry, lock); @@ -2022,7 +2019,7 @@ static inline int lookup_chain_cache(struct task_struct *curr, * We can walk it lock-free, because entries only get added * to the hash: */ - list_for_each_entry(chain, hash_head, entry) { + list_for_each_entry_rcu(chain, hash_head, entry) { if (chain->chain_key == chain_key) { cache_hit: debug_atomic_inc(chain_lookup_hits); @@ -2996,8 +2993,18 @@ void lockdep_init_map(struct lockdep_map *lock, const char *name, if (unlikely(!debug_locks)) return; - if (subclass) + if (subclass) { + unsigned long flags; + + if (DEBUG_LOCKS_WARN_ON(current->lockdep_recursion)) + return; + + raw_local_irq_save(flags); + current->lockdep_recursion = 1; register_lock_class(lock, subclass, 1); + current->lockdep_recursion = 0; + raw_local_irq_restore(flags); + } } EXPORT_SYMBOL_GPL(lockdep_init_map); @@ -3887,9 +3894,17 @@ static inline int within(const void *addr, void *start, unsigned long size) return addr >= start && addr < start + size; } +/* + * Used in module.c to remove lock classes from memory that is going to be + * freed; and possibly re-used by other modules. + * + * We will have had one sync_sched() before getting here, so we're guaranteed + * nobody will look up these exact classes -- they're properly dead but still + * allocated. + */ void lockdep_free_key_range(void *start, unsigned long size) { - struct lock_class *class, *next; + struct lock_class *class; struct list_head *head; unsigned long flags; int i; @@ -3905,7 +3920,7 @@ void lockdep_free_key_range(void *start, unsigned long size) head = classhash_table + i; if (list_empty(head)) continue; - list_for_each_entry_safe(class, next, head, hash_entry) { + list_for_each_entry_rcu(class, head, hash_entry) { if (within(class->key, start, size)) zap_class(class); else if (within(class->name, start, size)) @@ -3916,11 +3931,25 @@ void lockdep_free_key_range(void *start, unsigned long size) if (locked) graph_unlock(); raw_local_irq_restore(flags); + + /* + * Wait for any possible iterators from look_up_lock_class() to pass + * before continuing to free the memory they refer to. + * + * sync_sched() is sufficient because the read-side is IRQ disable. + */ + synchronize_sched(); + + /* + * XXX at this point we could return the resources to the pool; + * instead we leak them. We would need to change to bitmap allocators + * instead of the linear allocators we have now. + */ } void lockdep_reset_lock(struct lockdep_map *lock) { - struct lock_class *class, *next; + struct lock_class *class; struct list_head *head; unsigned long flags; int i, j; @@ -3948,7 +3977,7 @@ void lockdep_reset_lock(struct lockdep_map *lock) head = classhash_table + i; if (list_empty(head)) continue; - list_for_each_entry_safe(class, next, head, hash_entry) { + list_for_each_entry_rcu(class, head, hash_entry) { int match = 0; for (j = 0; j < NR_LOCKDEP_CACHING_CLASSES; j++) diff --git a/kernel/module.c b/kernel/module.c index b3d634ed06c9..99fdf94efce8 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1865,7 +1865,7 @@ static void free_module(struct module *mod) kfree(mod->args); percpu_modfree(mod); - /* Free lock-classes: */ + /* Free lock-classes; relies on the preceding sync_rcu(). */ lockdep_free_key_range(mod->module_core, mod->core_size); /* Finally, free the core (containing the module structure) */ @@ -3349,9 +3349,6 @@ static int load_module(struct load_info *info, const char __user *uargs, module_bug_cleanup(mod); mutex_unlock(&module_mutex); - /* Free lock-classes: */ - lockdep_free_key_range(mod->module_core, mod->core_size); - /* we can't deallocate the module until we clear memory protection */ unset_module_init_ro_nx(mod); unset_module_core_ro_nx(mod); @@ -3375,6 +3372,9 @@ static int load_module(struct load_info *info, const char __user *uargs, synchronize_rcu(); mutex_unlock(&module_mutex); free_module: + /* Free lock-classes; relies on the preceding sync_rcu() */ + lockdep_free_key_range(mod->module_core, mod->core_size); + module_deallocate(mod, info); free_copy: free_copy(info); From a127d2bcf1fbc8c8e0b5cf0dab54f7d3ff50ce47 Mon Sep 17 00:00:00 2001 From: Preeti U Murthy Date: Wed, 18 Mar 2015 16:19:27 +0530 Subject: [PATCH 066/170] timers/tick/broadcast-hrtimer: Fix suspicious RCU usage in idle loop The hrtimer mode of broadcast queues hrtimers in the idle entry path so as to wakeup cpus in deep idle states. The associated call graph is : cpuidle_idle_call() |____ clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, ....)) |_____tick_broadcast_set_event() |____clockevents_program_event() |____bc_set_next() The hrtimer_{start/cancel} functions call into tracing which uses RCU. But it is not legal to call into RCU in cpuidle because it is one of the quiescent states. Hence protect this region with RCU_NONIDLE which informs RCU that the cpu is momentarily non-idle. As an aside it is helpful to point out that the clock event device that is programmed here is not a per-cpu clock device; it is a pseudo clock device, used by the broadcast framework alone. The per-cpu clock device programming never goes through bc_set_next(). Signed-off-by: Preeti U Murthy Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Paul E. McKenney Cc: linuxppc-dev@ozlabs.org Cc: mpe@ellerman.id.au Cc: tglx@linutronix.de Link: http://lkml.kernel.org/r/20150318104705.17763.56668.stgit@preeti.in.ibm.com Signed-off-by: Ingo Molnar --- kernel/time/tick-broadcast-hrtimer.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c index eb682d5c697c..6aac4beedbbe 100644 --- a/kernel/time/tick-broadcast-hrtimer.c +++ b/kernel/time/tick-broadcast-hrtimer.c @@ -49,6 +49,7 @@ static void bc_set_mode(enum clock_event_mode mode, */ static int bc_set_next(ktime_t expires, struct clock_event_device *bc) { + int bc_moved; /* * We try to cancel the timer first. If the callback is on * flight on some other cpu then we let it handle it. If we @@ -60,9 +61,15 @@ static int bc_set_next(ktime_t expires, struct clock_event_device *bc) * restart the timer because we are in the callback, but we * can set the expiry time and let the callback return * HRTIMER_RESTART. + * + * Since we are in the idle loop at this point and because + * hrtimer_{start/cancel} functions call into tracing, + * calls to these functions must be bound within RCU_NONIDLE. */ - if (hrtimer_try_to_cancel(&bctimer) >= 0) { - hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED); + RCU_NONIDLE(bc_moved = (hrtimer_try_to_cancel(&bctimer) >= 0) ? + !hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED) : + 0); + if (bc_moved) { /* Bind the "device" to the cpu */ bc->bound_on = smp_processor_id(); } else if (bc->bound_on == smp_processor_id()) { From 47514da3ac20150cdf764466fbc2010c0fca0163 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Sun, 15 Mar 2015 21:32:12 +0100 Subject: [PATCH 067/170] parisc: Add compile-time check when adding new syscalls Signed-off-by: Helge Deller --- arch/parisc/kernel/syscall_table.S | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S index 5a8997d63899..8eefb12d1d33 100644 --- a/arch/parisc/kernel/syscall_table.S +++ b/arch/parisc/kernel/syscall_table.S @@ -55,8 +55,8 @@ #define ENTRY_COMP(_name_) .word sys_##_name_ #endif - ENTRY_SAME(restart_syscall) /* 0 */ - ENTRY_SAME(exit) +90: ENTRY_SAME(restart_syscall) /* 0 */ +91: ENTRY_SAME(exit) ENTRY_SAME(fork_wrapper) ENTRY_SAME(read) ENTRY_SAME(write) @@ -439,7 +439,10 @@ ENTRY_SAME(bpf) ENTRY_COMP(execveat) - /* Nothing yet */ + +.ifne (. - 90b) - (__NR_Linux_syscalls * (91b - 90b)) +.error "size of syscall table does not fit value of __NR_Linux_syscalls" +.endif #undef ENTRY_SAME #undef ENTRY_DIFF From 0e0da48dee8dfbcc0df4b8e2ff4efc7a2c89ba6b Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Wed, 18 Mar 2015 13:42:38 -0400 Subject: [PATCH 068/170] parisc: mm: don't count preallocated pmds The patch dc6c9a35b66b520cf67e05d8ca60ebecad3b0479 that counts pmds allocated for a process introduced a bug on 64-bit PA-RISC kernels. The PA-RISC architecture preallocates one pmd with each pgd. This preallocated pmd can never be freed - pmd_free does nothing when it is called with this pmd. When the kernel attempts to free this preallocated pmd, it decreases the count of allocated pmds. The result is that the counter underflows and this error is reported. This patch fixes the bug by artifically incrementing the counter in pmd_free when the kernel tries to free the preallocated pmd. Signed-off-by: Mikulas Patocka Acked-by: Kirill A. Shutemov Signed-off-by: Helge Deller --- arch/parisc/include/asm/pgalloc.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h index f213f5b4c423..63e9ecae1310 100644 --- a/arch/parisc/include/asm/pgalloc.h +++ b/arch/parisc/include/asm/pgalloc.h @@ -74,8 +74,13 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) { #ifdef CONFIG_64BIT if(pmd_flag(*pmd) & PxD_FLAG_ATTACHED) - /* This is the permanent pmd attached to the pgd; - * cannot free it */ + /* + * This is the permanent pmd attached to the pgd; + * cannot free it. + * Increment the counter to compensate for the decrement + * done by generic mm code. + */ + mm_inc_nr_pmds(mm); return; #endif free_pages((unsigned long)pmd, PMD_ORDER); From 2e3f0ab2bb4853694570b9610b1fcfbfa8fd295b Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Mon, 16 Mar 2015 21:17:50 +0100 Subject: [PATCH 069/170] parisc: Fix pmd code to depend on PT_NLEVELS value, not on CONFIG_64BIT Make the code which sets up the pmd depend on PT_NLEVELS == 3, not on CONFIG_64BIT. The reason is, that a 64bit kernel with a page size greater than 4k doesn't need the pmd and thus has PT_NLEVELS = 2. Signed-off-by: Helge Deller --- arch/parisc/include/asm/pgalloc.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h index 63e9ecae1310..d17437238a2c 100644 --- a/arch/parisc/include/asm/pgalloc.h +++ b/arch/parisc/include/asm/pgalloc.h @@ -26,7 +26,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) if (likely(pgd != NULL)) { memset(pgd, 0, PAGE_SIZE< Date: Mon, 23 Mar 2015 11:17:56 +0000 Subject: [PATCH 070/170] metag: Fix ioremap_wc/ioremap_cached build errors MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When ioremap_wc() or ioremap_cached() are used without first including asm/pgtable.h, the _PAGE_CACHEABLE or _PAGE_WR_COMBINE definitions aren't found, resulting in build errors like the following (in next-20150323 due to "lib: devres: add a helper function for ioremap_wc"): lib/devres.c: In function ‘devm_ioremap_wc’: lib/devres.c:91: error: ‘_PAGE_WR_COMBINE’ undeclared We can't easily include asm/pgtable.h in asm/io.h due to dependency problems, so split out the _PAGE_* definitions from asm/pgtable.h into a separate asm/pgtable-bits.h header (as a couple of other architectures already do), and include that in io.h instead. Signed-off-by: James Hogan Cc: linux-metag@vger.kernel.org Cc: Abhilash Kesavan Cc: Greg Kroah-Hartman --- arch/metag/include/asm/io.h | 1 + arch/metag/include/asm/pgtable-bits.h | 104 ++++++++++++++++++++++++++ arch/metag/include/asm/pgtable.h | 95 +---------------------- 3 files changed, 106 insertions(+), 94 deletions(-) create mode 100644 arch/metag/include/asm/pgtable-bits.h diff --git a/arch/metag/include/asm/io.h b/arch/metag/include/asm/io.h index 9359e5048442..d5779b0ec573 100644 --- a/arch/metag/include/asm/io.h +++ b/arch/metag/include/asm/io.h @@ -2,6 +2,7 @@ #define _ASM_METAG_IO_H #include +#include #define IO_SPACE_LIMIT 0 diff --git a/arch/metag/include/asm/pgtable-bits.h b/arch/metag/include/asm/pgtable-bits.h new file mode 100644 index 000000000000..25ba6729f496 --- /dev/null +++ b/arch/metag/include/asm/pgtable-bits.h @@ -0,0 +1,104 @@ +/* + * Meta page table definitions. + */ + +#ifndef _METAG_PGTABLE_BITS_H +#define _METAG_PGTABLE_BITS_H + +#include + +/* + * Definitions for MMU descriptors + * + * These are the hardware bits in the MMCU pte entries. + * Derived from the Meta toolkit headers. + */ +#define _PAGE_PRESENT MMCU_ENTRY_VAL_BIT +#define _PAGE_WRITE MMCU_ENTRY_WR_BIT +#define _PAGE_PRIV MMCU_ENTRY_PRIV_BIT +/* Write combine bit - this can cause writes to occur out of order */ +#define _PAGE_WR_COMBINE MMCU_ENTRY_WRC_BIT +/* Sys coherent bit - this bit is never used by Linux */ +#define _PAGE_SYS_COHERENT MMCU_ENTRY_SYS_BIT +#define _PAGE_ALWAYS_ZERO_1 0x020 +#define _PAGE_CACHE_CTRL0 0x040 +#define _PAGE_CACHE_CTRL1 0x080 +#define _PAGE_ALWAYS_ZERO_2 0x100 +#define _PAGE_ALWAYS_ZERO_3 0x200 +#define _PAGE_ALWAYS_ZERO_4 0x400 +#define _PAGE_ALWAYS_ZERO_5 0x800 + +/* These are software bits that we stuff into the gaps in the hardware + * pte entries that are not used. Note, these DO get stored in the actual + * hardware, but the hardware just does not use them. + */ +#define _PAGE_ACCESSED _PAGE_ALWAYS_ZERO_1 +#define _PAGE_DIRTY _PAGE_ALWAYS_ZERO_2 + +/* Pages owned, and protected by, the kernel. */ +#define _PAGE_KERNEL _PAGE_PRIV + +/* No cacheing of this page */ +#define _PAGE_CACHE_WIN0 (MMCU_CWIN_UNCACHED << MMCU_ENTRY_CWIN_S) +/* burst cacheing - good for data streaming */ +#define _PAGE_CACHE_WIN1 (MMCU_CWIN_BURST << MMCU_ENTRY_CWIN_S) +/* One cache way per thread */ +#define _PAGE_CACHE_WIN2 (MMCU_CWIN_C1SET << MMCU_ENTRY_CWIN_S) +/* Full on cacheing */ +#define _PAGE_CACHE_WIN3 (MMCU_CWIN_CACHED << MMCU_ENTRY_CWIN_S) + +#define _PAGE_CACHEABLE (_PAGE_CACHE_WIN3 | _PAGE_WR_COMBINE) + +/* which bits are used for cache control ... */ +#define _PAGE_CACHE_MASK (_PAGE_CACHE_CTRL0 | _PAGE_CACHE_CTRL1 | \ + _PAGE_WR_COMBINE) + +/* This is a mask of the bits that pte_modify is allowed to change. */ +#define _PAGE_CHG_MASK (PAGE_MASK) + +#define _PAGE_SZ_SHIFT 1 +#define _PAGE_SZ_4K (0x0) +#define _PAGE_SZ_8K (0x1 << _PAGE_SZ_SHIFT) +#define _PAGE_SZ_16K (0x2 << _PAGE_SZ_SHIFT) +#define _PAGE_SZ_32K (0x3 << _PAGE_SZ_SHIFT) +#define _PAGE_SZ_64K (0x4 << _PAGE_SZ_SHIFT) +#define _PAGE_SZ_128K (0x5 << _PAGE_SZ_SHIFT) +#define _PAGE_SZ_256K (0x6 << _PAGE_SZ_SHIFT) +#define _PAGE_SZ_512K (0x7 << _PAGE_SZ_SHIFT) +#define _PAGE_SZ_1M (0x8 << _PAGE_SZ_SHIFT) +#define _PAGE_SZ_2M (0x9 << _PAGE_SZ_SHIFT) +#define _PAGE_SZ_4M (0xa << _PAGE_SZ_SHIFT) +#define _PAGE_SZ_MASK (0xf << _PAGE_SZ_SHIFT) + +#if defined(CONFIG_PAGE_SIZE_4K) +#define _PAGE_SZ (_PAGE_SZ_4K) +#elif defined(CONFIG_PAGE_SIZE_8K) +#define _PAGE_SZ (_PAGE_SZ_8K) +#elif defined(CONFIG_PAGE_SIZE_16K) +#define _PAGE_SZ (_PAGE_SZ_16K) +#endif +#define _PAGE_TABLE (_PAGE_SZ | _PAGE_PRESENT) + +#if defined(CONFIG_HUGETLB_PAGE_SIZE_8K) +# define _PAGE_SZHUGE (_PAGE_SZ_8K) +#elif defined(CONFIG_HUGETLB_PAGE_SIZE_16K) +# define _PAGE_SZHUGE (_PAGE_SZ_16K) +#elif defined(CONFIG_HUGETLB_PAGE_SIZE_32K) +# define _PAGE_SZHUGE (_PAGE_SZ_32K) +#elif defined(CONFIG_HUGETLB_PAGE_SIZE_64K) +# define _PAGE_SZHUGE (_PAGE_SZ_64K) +#elif defined(CONFIG_HUGETLB_PAGE_SIZE_128K) +# define _PAGE_SZHUGE (_PAGE_SZ_128K) +#elif defined(CONFIG_HUGETLB_PAGE_SIZE_256K) +# define _PAGE_SZHUGE (_PAGE_SZ_256K) +#elif defined(CONFIG_HUGETLB_PAGE_SIZE_512K) +# define _PAGE_SZHUGE (_PAGE_SZ_512K) +#elif defined(CONFIG_HUGETLB_PAGE_SIZE_1M) +# define _PAGE_SZHUGE (_PAGE_SZ_1M) +#elif defined(CONFIG_HUGETLB_PAGE_SIZE_2M) +# define _PAGE_SZHUGE (_PAGE_SZ_2M) +#elif defined(CONFIG_HUGETLB_PAGE_SIZE_4M) +# define _PAGE_SZHUGE (_PAGE_SZ_4M) +#endif + +#endif /* _METAG_PGTABLE_BITS_H */ diff --git a/arch/metag/include/asm/pgtable.h b/arch/metag/include/asm/pgtable.h index d0604c0a8702..ffa3a3a2ecad 100644 --- a/arch/metag/include/asm/pgtable.h +++ b/arch/metag/include/asm/pgtable.h @@ -5,6 +5,7 @@ #ifndef _METAG_PGTABLE_H #define _METAG_PGTABLE_H +#include #include /* Invalid regions on Meta: 0x00000000-0x001FFFFF and 0xFFFF0000-0xFFFFFFFF */ @@ -20,100 +21,6 @@ #define VMALLOC_END 0x7FFFFFFF #endif -/* - * Definitions for MMU descriptors - * - * These are the hardware bits in the MMCU pte entries. - * Derived from the Meta toolkit headers. - */ -#define _PAGE_PRESENT MMCU_ENTRY_VAL_BIT -#define _PAGE_WRITE MMCU_ENTRY_WR_BIT -#define _PAGE_PRIV MMCU_ENTRY_PRIV_BIT -/* Write combine bit - this can cause writes to occur out of order */ -#define _PAGE_WR_COMBINE MMCU_ENTRY_WRC_BIT -/* Sys coherent bit - this bit is never used by Linux */ -#define _PAGE_SYS_COHERENT MMCU_ENTRY_SYS_BIT -#define _PAGE_ALWAYS_ZERO_1 0x020 -#define _PAGE_CACHE_CTRL0 0x040 -#define _PAGE_CACHE_CTRL1 0x080 -#define _PAGE_ALWAYS_ZERO_2 0x100 -#define _PAGE_ALWAYS_ZERO_3 0x200 -#define _PAGE_ALWAYS_ZERO_4 0x400 -#define _PAGE_ALWAYS_ZERO_5 0x800 - -/* These are software bits that we stuff into the gaps in the hardware - * pte entries that are not used. Note, these DO get stored in the actual - * hardware, but the hardware just does not use them. - */ -#define _PAGE_ACCESSED _PAGE_ALWAYS_ZERO_1 -#define _PAGE_DIRTY _PAGE_ALWAYS_ZERO_2 - -/* Pages owned, and protected by, the kernel. */ -#define _PAGE_KERNEL _PAGE_PRIV - -/* No cacheing of this page */ -#define _PAGE_CACHE_WIN0 (MMCU_CWIN_UNCACHED << MMCU_ENTRY_CWIN_S) -/* burst cacheing - good for data streaming */ -#define _PAGE_CACHE_WIN1 (MMCU_CWIN_BURST << MMCU_ENTRY_CWIN_S) -/* One cache way per thread */ -#define _PAGE_CACHE_WIN2 (MMCU_CWIN_C1SET << MMCU_ENTRY_CWIN_S) -/* Full on cacheing */ -#define _PAGE_CACHE_WIN3 (MMCU_CWIN_CACHED << MMCU_ENTRY_CWIN_S) - -#define _PAGE_CACHEABLE (_PAGE_CACHE_WIN3 | _PAGE_WR_COMBINE) - -/* which bits are used for cache control ... */ -#define _PAGE_CACHE_MASK (_PAGE_CACHE_CTRL0 | _PAGE_CACHE_CTRL1 | \ - _PAGE_WR_COMBINE) - -/* This is a mask of the bits that pte_modify is allowed to change. */ -#define _PAGE_CHG_MASK (PAGE_MASK) - -#define _PAGE_SZ_SHIFT 1 -#define _PAGE_SZ_4K (0x0) -#define _PAGE_SZ_8K (0x1 << _PAGE_SZ_SHIFT) -#define _PAGE_SZ_16K (0x2 << _PAGE_SZ_SHIFT) -#define _PAGE_SZ_32K (0x3 << _PAGE_SZ_SHIFT) -#define _PAGE_SZ_64K (0x4 << _PAGE_SZ_SHIFT) -#define _PAGE_SZ_128K (0x5 << _PAGE_SZ_SHIFT) -#define _PAGE_SZ_256K (0x6 << _PAGE_SZ_SHIFT) -#define _PAGE_SZ_512K (0x7 << _PAGE_SZ_SHIFT) -#define _PAGE_SZ_1M (0x8 << _PAGE_SZ_SHIFT) -#define _PAGE_SZ_2M (0x9 << _PAGE_SZ_SHIFT) -#define _PAGE_SZ_4M (0xa << _PAGE_SZ_SHIFT) -#define _PAGE_SZ_MASK (0xf << _PAGE_SZ_SHIFT) - -#if defined(CONFIG_PAGE_SIZE_4K) -#define _PAGE_SZ (_PAGE_SZ_4K) -#elif defined(CONFIG_PAGE_SIZE_8K) -#define _PAGE_SZ (_PAGE_SZ_8K) -#elif defined(CONFIG_PAGE_SIZE_16K) -#define _PAGE_SZ (_PAGE_SZ_16K) -#endif -#define _PAGE_TABLE (_PAGE_SZ | _PAGE_PRESENT) - -#if defined(CONFIG_HUGETLB_PAGE_SIZE_8K) -# define _PAGE_SZHUGE (_PAGE_SZ_8K) -#elif defined(CONFIG_HUGETLB_PAGE_SIZE_16K) -# define _PAGE_SZHUGE (_PAGE_SZ_16K) -#elif defined(CONFIG_HUGETLB_PAGE_SIZE_32K) -# define _PAGE_SZHUGE (_PAGE_SZ_32K) -#elif defined(CONFIG_HUGETLB_PAGE_SIZE_64K) -# define _PAGE_SZHUGE (_PAGE_SZ_64K) -#elif defined(CONFIG_HUGETLB_PAGE_SIZE_128K) -# define _PAGE_SZHUGE (_PAGE_SZ_128K) -#elif defined(CONFIG_HUGETLB_PAGE_SIZE_256K) -# define _PAGE_SZHUGE (_PAGE_SZ_256K) -#elif defined(CONFIG_HUGETLB_PAGE_SIZE_512K) -# define _PAGE_SZHUGE (_PAGE_SZ_512K) -#elif defined(CONFIG_HUGETLB_PAGE_SIZE_1M) -# define _PAGE_SZHUGE (_PAGE_SZ_1M) -#elif defined(CONFIG_HUGETLB_PAGE_SIZE_2M) -# define _PAGE_SZHUGE (_PAGE_SZ_2M) -#elif defined(CONFIG_HUGETLB_PAGE_SIZE_4M) -# define _PAGE_SZHUGE (_PAGE_SZ_4M) -#endif - /* * The Linux memory management assumes a three-level page table setup. On * Meta, we use that, but "fold" the mid level into the top-level page From 83a60ed8f0b5ce550afd5802b60468578db4e055 Mon Sep 17 00:00:00 2001 From: Baptiste Reynal Date: Wed, 4 Mar 2015 16:51:06 +0100 Subject: [PATCH 071/170] iommu/arm-smmu: fix ARM_SMMU_FEAT_TRANS_OPS condition This patch is a fix to "iommu/arm-smmu: add support for iova_to_phys through ATS1PR". According to ARM documentation, translation registers are optional even in SMMUv1, so ID0_S1TS needs to be checked to verify their presence. Also, we check that the domain is a stage-1 domain. Signed-off-by: Baptiste Reynal Acked-by: Will Deacon Signed-off-by: Joerg Roedel --- drivers/iommu/arm-smmu.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index fc13dd56953e..a3adde6519f0 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -1288,10 +1288,13 @@ static phys_addr_t arm_smmu_iova_to_phys(struct iommu_domain *domain, return 0; spin_lock_irqsave(&smmu_domain->pgtbl_lock, flags); - if (smmu_domain->smmu->features & ARM_SMMU_FEAT_TRANS_OPS) + if (smmu_domain->smmu->features & ARM_SMMU_FEAT_TRANS_OPS && + smmu_domain->stage == ARM_SMMU_DOMAIN_S1) { ret = arm_smmu_iova_to_phys_hard(domain, iova); - else + } else { ret = ops->iova_to_phys(ops, iova); + } + spin_unlock_irqrestore(&smmu_domain->pgtbl_lock, flags); return ret; @@ -1556,7 +1559,7 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu) return -ENODEV; } - if (smmu->version == 1 || (!(id & ID0_ATOSNS) && (id & ID0_S1TS))) { + if ((id & ID0_S1TS) && ((smmu->version == 1) || (id & ID0_ATOSNS))) { smmu->features |= ARM_SMMU_FEAT_TRANS_OPS; dev_notice(smmu->dev, "\taddress translation ops\n"); } From 71684406905f98f86a85e008b51f5c4c5d83af5a Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Wed, 4 Mar 2015 11:30:10 -0700 Subject: [PATCH 072/170] iommu/vt-d: Detach domain *only* from attached iommus Device domains never span IOMMU hardware units, which allows the domain ID space for each IOMMU to be an independent address space. Therefore we can have multiple, independent domains, each with the same domain->id, but attached to different hardware units. This is also why we need to do a heavy-weight search for VM domains since they can span multiple IOMMUs hardware units and we don't require a single global ID to use for all hardware units. Therefore, if we call iommu_detach_domain() across all active IOMMU hardware units for a non-VM domain, the result is that we clear domain IDs that are not associated with our domain, allowing them to be re-allocated and causing apparent coherency issues when the device cannot access IOVAs for the intended domain. This bug was introduced in commit fb170fb4c548 ("iommu/vt-d: Introduce helper functions to make code symmetric for readability"), but is significantly exacerbated by the more recent commit 62c22167dd70 ("iommu/vt-d: Fix dmar_domain leak in iommu_attach_device") which calls domain_exit() more frequently to resolve a domain leak. Fixes: fb170fb4c548 ("iommu/vt-d: Introduce helper functions to make code symmetric for readability") Signed-off-by: Alex Williamson Cc: Jiang Liu Cc: stable@vger.kernel.org # v3.17+ Signed-off-by: Joerg Roedel --- drivers/iommu/intel-iommu.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index ae4c1a854e57..a83c965410e0 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -1743,8 +1743,8 @@ static int domain_init(struct dmar_domain *domain, int guest_width) static void domain_exit(struct dmar_domain *domain) { struct dmar_drhd_unit *drhd; - struct intel_iommu *iommu; struct page *freelist = NULL; + int i; /* Domain 0 is reserved, so dont process it */ if (!domain) @@ -1764,8 +1764,8 @@ static void domain_exit(struct dmar_domain *domain) /* clear attached or cached domains */ rcu_read_lock(); - for_each_active_iommu(iommu, drhd) - iommu_detach_domain(domain, iommu); + for_each_set_bit(i, domain->iommu_bmp, g_num_of_iommus) + iommu_detach_domain(domain, g_iommus[i]); rcu_read_unlock(); dma_free_pagelist(freelist); From ac04f85a733b6af1faa10f7603e98bf07d2c4203 Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Tue, 17 Mar 2015 08:06:45 +0800 Subject: [PATCH 073/170] iommu: ipmmu-vmsa: Add terminating entry for ipmmu_of_ids The of_device_id table is supposed to be zero-terminated. Signed-off-by: Axel Lin Acked-by: Laurent Pinchart Signed-off-by: Joerg Roedel --- drivers/iommu/ipmmu-vmsa.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index 10186cac7716..bc39bdf7b99b 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -851,6 +851,7 @@ static int ipmmu_remove(struct platform_device *pdev) static const struct of_device_id ipmmu_of_ids[] = { { .compatible = "renesas,ipmmu-vmsa", }, + { } }; static struct platform_driver ipmmu_driver = { From e6e96d73a2aaaa54ed2c0f98693f4bf572712f1c Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Mon, 23 Mar 2015 09:32:37 -0600 Subject: [PATCH 074/170] NVMe: Initialize device list head before starting Driver recovery requires the device's list node to have been initialized. Fixes: https://lkml.org/lkml/2015/3/22/262 Reported-by: Steven Noonan Signed-off-by: Keith Busch Cc: Matthew Wilcox Cc: Jens Axboe Signed-off-by: Jens Axboe --- drivers/block/nvme-core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c index ceb32dd52a6c..e23be20a3417 100644 --- a/drivers/block/nvme-core.c +++ b/drivers/block/nvme-core.c @@ -3003,6 +3003,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) } get_device(dev->device); + INIT_LIST_HEAD(&dev->node); INIT_WORK(&dev->probe_work, nvme_async_probe); schedule_work(&dev->probe_work); return 0; From c72efb658f7c8b27ca3d0efb5cfd5ded9fcac89e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 23 Mar 2015 00:18:48 -0400 Subject: [PATCH 075/170] writeback: fix possible underflow in write bandwidth calculation From 1ebf33901ecc75d9496862dceb1ef0377980587c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 23 Mar 2015 00:08:19 -0400 2f800fbd777b ("writeback: fix dirtied pages accounting on redirty") introduced account_page_redirty() which reverts stat updates for a redirtied page, making BDI_DIRTIED no longer monotonically increasing. bdi_update_write_bandwidth() uses the delta in BDI_DIRTIED as the basis for bandwidth calculation. While unlikely, since the above patch, the newer value may be lower than the recorded past value and underflow the bandwidth calculation leading to a wild result. Fix it by subtracing min of the old and new values when calculating delta. AFAIK, there hasn't been any report of it happening but the resulting erratic behavior would be non-critical and temporary, so it's possible that the issue is happening without being reported. The risk of the fix is very low, so tagged for -stable. Signed-off-by: Tejun Heo Cc: Jens Axboe Cc: Jan Kara Cc: Wu Fengguang Cc: Greg Thelen Fixes: 2f800fbd777b ("writeback: fix dirtied pages accounting on redirty") Cc: stable@vger.kernel.org Signed-off-by: Jens Axboe --- mm/page-writeback.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/mm/page-writeback.c b/mm/page-writeback.c index b4fd980a93eb..644bcb665773 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -857,8 +857,11 @@ static void bdi_update_write_bandwidth(struct backing_dev_info *bdi, * bw * elapsed + write_bandwidth * (period - elapsed) * write_bandwidth = --------------------------------------------------- * period + * + * @written may have decreased due to account_page_redirty(). + * Avoid underflowing @bw calculation. */ - bw = written - bdi->written_stamp; + bw = written - min(written, bdi->written_stamp); bw *= HZ; if (unlikely(elapsed > period)) { do_div(bw, elapsed); From 80b311d3118842eb681397233faa0d588df13f92 Mon Sep 17 00:00:00 2001 From: Sebastian Wicki Date: Mon, 23 Mar 2015 17:23:11 +0100 Subject: [PATCH 076/170] ALSA: hda - Add dock support for Thinkpad T450s (17aa:5036) This model uses the same dock port as the previous generation. Signed-off-by: Sebastian Wicki 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 526398a4a442..7b0f72c5c6f1 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5036,6 +5036,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x501a, "Thinkpad", ALC283_FIXUP_INT_MIC), SND_PCI_QUIRK(0x17aa, 0x501e, "Thinkpad L440", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x5026, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), + SND_PCI_QUIRK(0x17aa, 0x5036, "Thinkpad T450s", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x5109, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x17aa, 0x3bf8, "Quanta FL1", ALC269_FIXUP_PCM_44K), SND_PCI_QUIRK(0x17aa, 0x9e54, "LENOVO NB", ALC269_FIXUP_LENOVO_EAPD), From e53f21bce4d35a93b23d8fa1a840860f6c74f59e Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Mon, 23 Mar 2015 15:06:50 +0000 Subject: [PATCH 077/170] arm64: Use the reserved TTBR0 if context switching to the init_mm The idle_task_exit() function may call switch_mm() with next == &init_mm. On arm64, init_mm.pgd cannot be used for user mappings, so this patch simply sets the reserved TTBR0. Cc: Reported-by: Jon Medhurst (Tixy) Tested-by: Jon Medhurst (Tixy) Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/mmu_context.h | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index a9eee33dfa62..101a42bde728 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -151,6 +151,15 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next, { unsigned int cpu = smp_processor_id(); + /* + * init_mm.pgd does not contain any user mappings and it is always + * active for kernel addresses in TTBR1. Just set the reserved TTBR0. + */ + if (next == &init_mm) { + cpu_set_reserved_ttbr0(); + return; + } + if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next) check_and_switch_context(next, tsk); } From 63a4f065ece613b6d575b538234375b0e9c23bbc Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Mon, 23 Mar 2015 17:01:43 -0400 Subject: [PATCH 078/170] dm: fix add_disk() NULL pointer due to race with free_dev() Commit c4db59d31e39 ("fs: don't reassign dirty inodes to default_backing_dev_info") exposed DM to a latent race in free_dev() vs add_disk() in relation to management of the device's minor number. Fix this by refactoring free_dev() to match cleanup order of the alloc_dev() error path. Move cleanup of the gendisk, queue, and bdev to _before_ the cleanup of the idr managed minor number. Also, purely due to cleanup that fell out during the free_dev() audit: - adjust dm_blk_close() to access the gendisk's private_data under the _minor_lock spinlock. - move __dm_destroy()'s dm_get_live_table() call out from under the _minor_lock spinlock. Resolves: https://bugzilla.redhat.com/show_bug.cgi?id=1202449 Reported-by: Zdenek Kabelac Reported-by: Jeff Moyer Signed-off-by: Mike Snitzer --- drivers/md/dm.c | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 9b641b38b857..8001fe9e3434 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -433,7 +433,6 @@ static int dm_blk_open(struct block_device *bdev, fmode_t mode) dm_get(md); atomic_inc(&md->open_count); - out: spin_unlock(&_minor_lock); @@ -442,16 +441,20 @@ static int dm_blk_open(struct block_device *bdev, fmode_t mode) static void dm_blk_close(struct gendisk *disk, fmode_t mode) { - struct mapped_device *md = disk->private_data; + struct mapped_device *md; spin_lock(&_minor_lock); + md = disk->private_data; + if (WARN_ON(!md)) + goto out; + if (atomic_dec_and_test(&md->open_count) && (test_bit(DMF_DEFERRED_REMOVE, &md->flags))) queue_work(deferred_remove_workqueue, &deferred_remove_work); dm_put(md); - +out: spin_unlock(&_minor_lock); } @@ -2241,7 +2244,6 @@ static void free_dev(struct mapped_device *md) int minor = MINOR(disk_devt(md->disk)); unlock_fs(md); - bdput(md->bdev); destroy_workqueue(md->wq); if (md->kworker_task) @@ -2252,19 +2254,22 @@ static void free_dev(struct mapped_device *md) mempool_destroy(md->rq_pool); if (md->bs) bioset_free(md->bs); - blk_integrity_unregister(md->disk); - del_gendisk(md->disk); + cleanup_srcu_struct(&md->io_barrier); free_table_devices(&md->table_devices); - free_minor(minor); + dm_stats_cleanup(&md->stats); spin_lock(&_minor_lock); md->disk->private_data = NULL; spin_unlock(&_minor_lock); - + if (blk_get_integrity(md->disk)) + blk_integrity_unregister(md->disk); + del_gendisk(md->disk); put_disk(md->disk); blk_cleanup_queue(md->queue); - dm_stats_cleanup(&md->stats); + bdput(md->bdev); + free_minor(minor); + module_put(THIS_MODULE); kfree(md); } @@ -2642,8 +2647,9 @@ static void __dm_destroy(struct mapped_device *md, bool wait) might_sleep(); - spin_lock(&_minor_lock); map = dm_get_live_table(md, &srcu_idx); + + spin_lock(&_minor_lock); idr_replace(&_minor_idr, MINOR_ALLOCED, MINOR(disk_devt(dm_disk(md)))); set_bit(DMF_FREEING, &md->flags); spin_unlock(&_minor_lock); From c806a6ad35bfa6c92249cd0ca4772d5ac3f8cb68 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= Date: Wed, 18 Mar 2015 19:38:22 +0100 Subject: [PATCH 079/170] KVM: x86: call irq notifiers with directed EOI MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit kvm_ioapic_update_eoi() wasn't called if directed EOI was enabled. We need to do that for irq notifiers. (Like with edge interrupts.) Fix it by skipping EOI broadcast only. Bug: https://bugzilla.kernel.org/show_bug.cgi?id=82211 Signed-off-by: Radim Krčmář Reviewed-by: Paolo Bonzini Tested-by: Bandan Das Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/ioapic.c | 4 +++- arch/x86/kvm/lapic.c | 3 +-- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index b1947e0f3e10..46d4449772bc 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -422,6 +422,7 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, struct kvm_ioapic *ioapic, int vector, int trigger_mode) { int i; + struct kvm_lapic *apic = vcpu->arch.apic; for (i = 0; i < IOAPIC_NUM_PINS; i++) { union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i]; @@ -443,7 +444,8 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, i); spin_lock(&ioapic->lock); - if (trigger_mode != IOAPIC_LEVEL_TRIG) + if (trigger_mode != IOAPIC_LEVEL_TRIG || + kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) continue; ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index bd4e34de24c7..4ee827d7bf36 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -833,8 +833,7 @@ int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2) static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector) { - if (!(kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) && - kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) { + if (kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) { int trigger_mode; if (apic_test_vector(vector, apic->regs + APIC_TMR)) trigger_mode = IOAPIC_LEVEL_TRIG; From 744961341d472db6272ed9b42319a90f5a2aa7c4 Mon Sep 17 00:00:00 2001 From: Igor Mammedov Date: Fri, 20 Mar 2015 12:21:37 +0000 Subject: [PATCH 080/170] kvm: avoid page allocation failure in kvm_set_memory_region() KVM guest can fail to startup with following trace on host: qemu-system-x86: page allocation failure: order:4, mode:0x40d0 Call Trace: dump_stack+0x47/0x67 warn_alloc_failed+0xee/0x150 __alloc_pages_direct_compact+0x14a/0x150 __alloc_pages_nodemask+0x776/0xb80 alloc_kmem_pages+0x3a/0x110 kmalloc_order+0x13/0x50 kmemdup+0x1b/0x40 __kvm_set_memory_region+0x24a/0x9f0 [kvm] kvm_set_ioapic+0x130/0x130 [kvm] kvm_set_memory_region+0x21/0x40 [kvm] kvm_vm_ioctl+0x43f/0x750 [kvm] Failure happens when attempting to allocate pages for 'struct kvm_memslots', however it doesn't have to be present in physically contiguous (kmalloc-ed) address space, change allocation to kvm_kvzalloc() so that it will be vmalloc-ed when its size is more then a page. Signed-off-by: Igor Mammedov Signed-off-by: Marcelo Tosatti --- virt/kvm/kvm_main.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index a2214d9609bd..cc6a25d95fbf 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -471,7 +471,7 @@ static struct kvm *kvm_create_vm(unsigned long type) BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX); r = -ENOMEM; - kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL); + kvm->memslots = kvm_kvzalloc(sizeof(struct kvm_memslots)); if (!kvm->memslots) goto out_err_no_srcu; @@ -522,7 +522,7 @@ static struct kvm *kvm_create_vm(unsigned long type) out_err_no_disable: for (i = 0; i < KVM_NR_BUSES; i++) kfree(kvm->buses[i]); - kfree(kvm->memslots); + kvfree(kvm->memslots); kvm_arch_free_vm(kvm); return ERR_PTR(r); } @@ -578,7 +578,7 @@ static void kvm_free_physmem(struct kvm *kvm) kvm_for_each_memslot(memslot, slots) kvm_free_physmem_slot(kvm, memslot, NULL); - kfree(kvm->memslots); + kvfree(kvm->memslots); } static void kvm_destroy_devices(struct kvm *kvm) @@ -871,10 +871,10 @@ int __kvm_set_memory_region(struct kvm *kvm, goto out_free; } - slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots), - GFP_KERNEL); + slots = kvm_kvzalloc(sizeof(struct kvm_memslots)); if (!slots) goto out_free; + memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots)); if ((change == KVM_MR_DELETE) || (change == KVM_MR_MOVE)) { slot = id_to_memslot(slots, mem->slot); @@ -917,7 +917,7 @@ int __kvm_set_memory_region(struct kvm *kvm, kvm_arch_commit_memory_region(kvm, mem, &old, change); kvm_free_physmem_slot(kvm, &old, &new); - kfree(old_memslots); + kvfree(old_memslots); /* * IOMMU mapping: New slots need to be mapped. Old slots need to be @@ -936,7 +936,7 @@ int __kvm_set_memory_region(struct kvm *kvm, return 0; out_slots: - kfree(slots); + kvfree(slots); out_free: kvm_free_physmem_slot(kvm, &new, &old); out: From 8218c3f4df3bb1c637c17552405039a6dd3c1ee1 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 27 Feb 2015 12:58:13 +0100 Subject: [PATCH 081/170] drm: Fixup racy refcounting in plane_force_disable Originally it was impossible to be dropping the last refcount in this function since there was always one around still from the idr. But in commit 83f45fc360c8e16a330474860ebda872d1384c8c Author: Daniel Vetter Date: Wed Aug 6 09:10:18 2014 +0200 drm: Don't grab an fb reference for the idr we've switched to weak references, broke that assumption but forgot to fix it up. Since we still force-disable planes it's only possible to hit this when racing multiple rmfb with fbdev restoring or similar evil things. As long as userspace is nice it's impossible to hit the BUG_ON. But the BUG_ON would most likely be hit from fbdev code, which usually invovles the console_lock besides all modeset locks. So very likely we'd never get the bug reports if this was hit in the wild, hence better be safe than sorry and backport. Spotted by Matt Roper while reviewing other patches. [airlied: pull this back into 4.0 - the oops happens there] Cc: stable@vger.kernel.org Cc: Matt Roper Reviewed-by: Matt Roper Signed-off-by: Daniel Vetter Signed-off-by: Dave Airlie --- drivers/gpu/drm/drm_crtc.c | 13 +------------ 1 file changed, 1 insertion(+), 12 deletions(-) diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index f6d04c7b5115..679b10e34fb5 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -525,17 +525,6 @@ void drm_framebuffer_reference(struct drm_framebuffer *fb) } EXPORT_SYMBOL(drm_framebuffer_reference); -static void drm_framebuffer_free_bug(struct kref *kref) -{ - BUG(); -} - -static void __drm_framebuffer_unreference(struct drm_framebuffer *fb) -{ - DRM_DEBUG("%p: FB ID: %d (%d)\n", fb, fb->base.id, atomic_read(&fb->refcount.refcount)); - kref_put(&fb->refcount, drm_framebuffer_free_bug); -} - /** * drm_framebuffer_unregister_private - unregister a private fb from the lookup idr * @fb: fb to unregister @@ -1320,7 +1309,7 @@ void drm_plane_force_disable(struct drm_plane *plane) return; } /* disconnect the plane from the fb and crtc: */ - __drm_framebuffer_unreference(plane->old_fb); + drm_framebuffer_unreference(plane->old_fb); plane->old_fb = NULL; plane->fb = NULL; plane->crtc = NULL; From dff173de84958a677ce0d24b1da3cdc3a32b4238 Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Mon, 23 Mar 2015 10:56:14 +0200 Subject: [PATCH 082/170] bnx2x: Fix statistics locking scheme Statistics' state-machine in bnx2x driver must be synced with various driver flows, but its current locking scheme manages to be wasteful [using 2 locks + additional local variable] and prone to race-conditions at the same time, as the state-machine and 'action' are being accessed under different locks. In addition, current 'safe exec' isn't in fact safe, since the only guarantee it gives is that DMA transactions are over, but ramrods might still be running. This patch cleans up said logic, leaving us with a single lock for the entire flow and removing the possible races. Changes from v2: - Switched into mutex locking from semaphore locking. - Release locks on error flows. Changes from v1: Failure to acquire lock fails flow instead of printing a warning and allowing access to the critical section. Signed-off-by: Yuval Mintz Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x.h | 4 +- .../net/ethernet/broadcom/bnx2x/bnx2x_main.c | 7 +- .../net/ethernet/broadcom/bnx2x/bnx2x_sriov.c | 4 +- .../net/ethernet/broadcom/bnx2x/bnx2x_stats.c | 164 ++++++++---------- .../net/ethernet/broadcom/bnx2x/bnx2x_stats.h | 6 +- 5 files changed, 84 insertions(+), 101 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h index 756053c028be..4085c4b31047 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -1811,7 +1811,7 @@ struct bnx2x { int stats_state; /* used for synchronization of concurrent threads statistics handling */ - spinlock_t stats_lock; + struct mutex stats_lock; /* used by dmae command loader */ struct dmae_command stats_dmae; @@ -1935,8 +1935,6 @@ struct bnx2x { int fp_array_size; u32 dump_preset_idx; - bool stats_started; - struct semaphore stats_sema; u8 phys_port_id[ETH_ALEN]; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 996e215fc324..ae571a199f2f 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -12037,9 +12037,8 @@ static int bnx2x_init_bp(struct bnx2x *bp) mutex_init(&bp->port.phy_mutex); mutex_init(&bp->fw_mb_mutex); mutex_init(&bp->drv_info_mutex); + mutex_init(&bp->stats_lock); bp->drv_info_mng_owner = false; - spin_lock_init(&bp->stats_lock); - sema_init(&bp->stats_sema, 1); INIT_DELAYED_WORK(&bp->sp_task, bnx2x_sp_task); INIT_DELAYED_WORK(&bp->sp_rtnl_task, bnx2x_sp_rtnl_task); @@ -13668,9 +13667,9 @@ static int bnx2x_eeh_nic_unload(struct bnx2x *bp) cancel_delayed_work_sync(&bp->sp_task); cancel_delayed_work_sync(&bp->period_task); - spin_lock_bh(&bp->stats_lock); + mutex_lock(&bp->stats_lock); bp->stats_state = STATS_STATE_DISABLED; - spin_unlock_bh(&bp->stats_lock); + mutex_unlock(&bp->stats_lock); bnx2x_save_statistics(bp); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index e5aca2de1871..cfe3c7695455 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -2238,7 +2238,9 @@ int bnx2x_vf_close(struct bnx2x *bp, struct bnx2x_virtf *vf) cookie.vf = vf; cookie.state = VF_ACQUIRED; - bnx2x_stats_safe_exec(bp, bnx2x_set_vf_state, &cookie); + rc = bnx2x_stats_safe_exec(bp, bnx2x_set_vf_state, &cookie); + if (rc) + goto op_err; } DP(BNX2X_MSG_IOV, "set state to acquired\n"); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c index d1608297c773..800ab44a07ce 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c @@ -123,36 +123,28 @@ static void bnx2x_dp_stats(struct bnx2x *bp) */ static void bnx2x_storm_stats_post(struct bnx2x *bp) { - if (!bp->stats_pending) { - int rc; + int rc; - spin_lock_bh(&bp->stats_lock); + if (bp->stats_pending) + return; - if (bp->stats_pending) { - spin_unlock_bh(&bp->stats_lock); - return; - } + bp->fw_stats_req->hdr.drv_stats_counter = + cpu_to_le16(bp->stats_counter++); - bp->fw_stats_req->hdr.drv_stats_counter = - cpu_to_le16(bp->stats_counter++); + DP(BNX2X_MSG_STATS, "Sending statistics ramrod %d\n", + le16_to_cpu(bp->fw_stats_req->hdr.drv_stats_counter)); - DP(BNX2X_MSG_STATS, "Sending statistics ramrod %d\n", - le16_to_cpu(bp->fw_stats_req->hdr.drv_stats_counter)); + /* adjust the ramrod to include VF queues statistics */ + bnx2x_iov_adjust_stats_req(bp); + bnx2x_dp_stats(bp); - /* adjust the ramrod to include VF queues statistics */ - bnx2x_iov_adjust_stats_req(bp); - bnx2x_dp_stats(bp); - - /* send FW stats ramrod */ - rc = bnx2x_sp_post(bp, RAMROD_CMD_ID_COMMON_STAT_QUERY, 0, - U64_HI(bp->fw_stats_req_mapping), - U64_LO(bp->fw_stats_req_mapping), - NONE_CONNECTION_TYPE); - if (rc == 0) - bp->stats_pending = 1; - - spin_unlock_bh(&bp->stats_lock); - } + /* send FW stats ramrod */ + rc = bnx2x_sp_post(bp, RAMROD_CMD_ID_COMMON_STAT_QUERY, 0, + U64_HI(bp->fw_stats_req_mapping), + U64_LO(bp->fw_stats_req_mapping), + NONE_CONNECTION_TYPE); + if (rc == 0) + bp->stats_pending = 1; } static void bnx2x_hw_stats_post(struct bnx2x *bp) @@ -221,7 +213,7 @@ static void bnx2x_stats_comp(struct bnx2x *bp) */ /* should be called under stats_sema */ -static void __bnx2x_stats_pmf_update(struct bnx2x *bp) +static void bnx2x_stats_pmf_update(struct bnx2x *bp) { struct dmae_command *dmae; u32 opcode; @@ -519,7 +511,7 @@ static void bnx2x_func_stats_init(struct bnx2x *bp) } /* should be called under stats_sema */ -static void __bnx2x_stats_start(struct bnx2x *bp) +static void bnx2x_stats_start(struct bnx2x *bp) { if (IS_PF(bp)) { if (bp->port.pmf) @@ -531,34 +523,13 @@ static void __bnx2x_stats_start(struct bnx2x *bp) bnx2x_hw_stats_post(bp); bnx2x_storm_stats_post(bp); } - - bp->stats_started = true; -} - -static void bnx2x_stats_start(struct bnx2x *bp) -{ - if (down_timeout(&bp->stats_sema, HZ/10)) - BNX2X_ERR("Unable to acquire stats lock\n"); - __bnx2x_stats_start(bp); - up(&bp->stats_sema); } static void bnx2x_stats_pmf_start(struct bnx2x *bp) { - if (down_timeout(&bp->stats_sema, HZ/10)) - BNX2X_ERR("Unable to acquire stats lock\n"); bnx2x_stats_comp(bp); - __bnx2x_stats_pmf_update(bp); - __bnx2x_stats_start(bp); - up(&bp->stats_sema); -} - -static void bnx2x_stats_pmf_update(struct bnx2x *bp) -{ - if (down_timeout(&bp->stats_sema, HZ/10)) - BNX2X_ERR("Unable to acquire stats lock\n"); - __bnx2x_stats_pmf_update(bp); - up(&bp->stats_sema); + bnx2x_stats_pmf_update(bp); + bnx2x_stats_start(bp); } static void bnx2x_stats_restart(struct bnx2x *bp) @@ -568,11 +539,9 @@ static void bnx2x_stats_restart(struct bnx2x *bp) */ if (IS_VF(bp)) return; - if (down_timeout(&bp->stats_sema, HZ/10)) - BNX2X_ERR("Unable to acquire stats lock\n"); + bnx2x_stats_comp(bp); - __bnx2x_stats_start(bp); - up(&bp->stats_sema); + bnx2x_stats_start(bp); } static void bnx2x_bmac_stats_update(struct bnx2x *bp) @@ -1246,18 +1215,12 @@ static void bnx2x_stats_update(struct bnx2x *bp) { u32 *stats_comp = bnx2x_sp(bp, stats_comp); - /* we run update from timer context, so give up - * if somebody is in the middle of transition - */ - if (down_trylock(&bp->stats_sema)) + if (bnx2x_edebug_stats_stopped(bp)) return; - if (bnx2x_edebug_stats_stopped(bp) || !bp->stats_started) - goto out; - if (IS_PF(bp)) { if (*stats_comp != DMAE_COMP_VAL) - goto out; + return; if (bp->port.pmf) bnx2x_hw_stats_update(bp); @@ -1267,7 +1230,7 @@ static void bnx2x_stats_update(struct bnx2x *bp) BNX2X_ERR("storm stats were not updated for 3 times\n"); bnx2x_panic(); } - goto out; + return; } } else { /* vf doesn't collect HW statistics, and doesn't get completions @@ -1281,7 +1244,7 @@ static void bnx2x_stats_update(struct bnx2x *bp) /* vf is done */ if (IS_VF(bp)) - goto out; + return; if (netif_msg_timer(bp)) { struct bnx2x_eth_stats *estats = &bp->eth_stats; @@ -1292,9 +1255,6 @@ static void bnx2x_stats_update(struct bnx2x *bp) bnx2x_hw_stats_post(bp); bnx2x_storm_stats_post(bp); - -out: - up(&bp->stats_sema); } static void bnx2x_port_stats_stop(struct bnx2x *bp) @@ -1358,12 +1318,7 @@ static void bnx2x_port_stats_stop(struct bnx2x *bp) static void bnx2x_stats_stop(struct bnx2x *bp) { - int update = 0; - - if (down_timeout(&bp->stats_sema, HZ/10)) - BNX2X_ERR("Unable to acquire stats lock\n"); - - bp->stats_started = false; + bool update = false; bnx2x_stats_comp(bp); @@ -1381,8 +1336,6 @@ static void bnx2x_stats_stop(struct bnx2x *bp) bnx2x_hw_stats_post(bp); bnx2x_stats_comp(bp); } - - up(&bp->stats_sema); } static void bnx2x_stats_do_nothing(struct bnx2x *bp) @@ -1410,18 +1363,28 @@ static const struct { void bnx2x_stats_handle(struct bnx2x *bp, enum bnx2x_stats_event event) { - enum bnx2x_stats_state state; - void (*action)(struct bnx2x *bp); + enum bnx2x_stats_state state = bp->stats_state; + if (unlikely(bp->panic)) return; - spin_lock_bh(&bp->stats_lock); - state = bp->stats_state; - bp->stats_state = bnx2x_stats_stm[state][event].next_state; - action = bnx2x_stats_stm[state][event].action; - spin_unlock_bh(&bp->stats_lock); + /* Statistics update run from timer context, and we don't want to stop + * that context in case someone is in the middle of a transition. + * For other events, wait a bit until lock is taken. + */ + if (!mutex_trylock(&bp->stats_lock)) { + if (event == STATS_EVENT_UPDATE) + return; - action(bp); + DP(BNX2X_MSG_STATS, + "Unlikely stats' lock contention [event %d]\n", event); + mutex_lock(&bp->stats_lock); + } + + bnx2x_stats_stm[state][event].action(bp); + bp->stats_state = bnx2x_stats_stm[state][event].next_state; + + mutex_unlock(&bp->stats_lock); if ((event != STATS_EVENT_UPDATE) || netif_msg_timer(bp)) DP(BNX2X_MSG_STATS, "state %d -> event %d -> state %d\n", @@ -1998,13 +1961,34 @@ void bnx2x_afex_collect_stats(struct bnx2x *bp, void *void_afex_stats, } } -void bnx2x_stats_safe_exec(struct bnx2x *bp, - void (func_to_exec)(void *cookie), - void *cookie){ - if (down_timeout(&bp->stats_sema, HZ/10)) - BNX2X_ERR("Unable to acquire stats lock\n"); +int bnx2x_stats_safe_exec(struct bnx2x *bp, + void (func_to_exec)(void *cookie), + void *cookie) +{ + int cnt = 10, rc = 0; + + /* Wait for statistics to end [while blocking further requests], + * then run supplied function 'safely'. + */ + mutex_lock(&bp->stats_lock); + bnx2x_stats_comp(bp); + while (bp->stats_pending && cnt--) + if (bnx2x_storm_stats_update(bp)) + usleep_range(1000, 2000); + if (bp->stats_pending) { + BNX2X_ERR("Failed to wait for stats pending to clear [possibly FW is stuck]\n"); + rc = -EBUSY; + goto out; + } + func_to_exec(cookie); - __bnx2x_stats_start(bp); - up(&bp->stats_sema); + +out: + /* No need to restart statistics - if they're enabled, the timer + * will restart the statistics. + */ + mutex_unlock(&bp->stats_lock); + + return rc; } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h index 2beceaefdeea..965539a9dabe 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h @@ -539,9 +539,9 @@ struct bnx2x; void bnx2x_memset_stats(struct bnx2x *bp); void bnx2x_stats_init(struct bnx2x *bp); void bnx2x_stats_handle(struct bnx2x *bp, enum bnx2x_stats_event event); -void bnx2x_stats_safe_exec(struct bnx2x *bp, - void (func_to_exec)(void *cookie), - void *cookie); +int bnx2x_stats_safe_exec(struct bnx2x *bp, + void (func_to_exec)(void *cookie), + void *cookie); /** * bnx2x_save_statistics - save statistics when unloading. From d0c294c53a771ae7e84506dfbd8c18c30f078735 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Michal=20Kube=C4=8Dek?= Date: Mon, 23 Mar 2015 15:14:00 +0100 Subject: [PATCH 083/170] tcp: prevent fetching dst twice in early demux code On s390x, gcc 4.8 compiles this part of tcp_v6_early_demux() struct dst_entry *dst = sk->sk_rx_dst; if (dst) dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie); to code reading sk->sk_rx_dst twice, once for the test and once for the argument of ip6_dst_check() (dst_check() is inline). This allows ip6_dst_check() to be called with null first argument, causing a crash. Protect sk->sk_rx_dst access by READ_ONCE() both in IPv4 and IPv6 TCP early demux code. Fixes: 41063e9dd119 ("ipv4: Early TCP socket demux.") Fixes: c7109986db3c ("ipv6: Early TCP socket demux") Signed-off-by: Michal Kubecek Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 2 +- net/ipv6/tcp_ipv6.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 5a2dfed4783b..f1756ee02207 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1518,7 +1518,7 @@ void tcp_v4_early_demux(struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_edemux; if (sk->sk_state != TCP_TIME_WAIT) { - struct dst_entry *dst = sk->sk_rx_dst; + struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst); if (dst) dst = dst_check(dst, 0); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 5d46832c6f72..b283a498f7a4 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1585,7 +1585,7 @@ static void tcp_v6_early_demux(struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_edemux; if (sk->sk_state != TCP_TIME_WAIT) { - struct dst_entry *dst = sk->sk_rx_dst; + struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst); if (dst) dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie); From a71aaf66725e8fc02253a3bbea15d27e656434fe Mon Sep 17 00:00:00 2001 From: Larry Finger Date: Mon, 23 Mar 2015 14:07:57 -0500 Subject: [PATCH 084/170] iwlwifi: Fix memory leak in iwl_req_fw_callback() In this routine, kzalloc allocates a memory block. This allocation is freed in the error paths, but not in the normal exit, thus the allocation is leaked. The kmemleak facility was used to find the leak. Signed-off-by: Larry Finger Cc: Johannes Berg Cc: Emmanuel Grumbach Cc: Intel Linux Wireless --- drivers/net/wireless/iwlwifi/iwl-drv.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/wireless/iwlwifi/iwl-drv.c b/drivers/net/wireless/iwlwifi/iwl-drv.c index 996e7f16adf9..c7154ac42c8c 100644 --- a/drivers/net/wireless/iwlwifi/iwl-drv.c +++ b/drivers/net/wireless/iwlwifi/iwl-drv.c @@ -1257,6 +1257,7 @@ static void iwl_req_fw_callback(const struct firmware *ucode_raw, void *context) op->name, err); #endif } + kfree(pieces); return; try_again: From 509fca899d5682a6eee3d1fb70bba7c89439034b Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 23 Mar 2015 19:50:21 -0600 Subject: [PATCH 085/170] iommu/vt-d: Remove unused variable Unused after commit 71684406905f ("iommu/vt-d: Detach domain *only* from attached iommus"). Reported by 0-day builder. Signed-off-by: Alex Williamson Signed-off-by: Joerg Roedel --- drivers/iommu/intel-iommu.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index a83c965410e0..2d1e05bdbb53 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -1742,7 +1742,6 @@ static int domain_init(struct dmar_domain *domain, int guest_width) static void domain_exit(struct dmar_domain *domain) { - struct dmar_drhd_unit *drhd; struct page *freelist = NULL; int i; From d079535d5e1bf5e2e7c856bae2483414ea21e137 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Mon, 23 Mar 2015 16:31:09 -0700 Subject: [PATCH 086/170] net: use for_each_netdev_safe() in rtnl_group_changelink() In case we move the whole dev group to another netns, we should call for_each_netdev_safe(), otherwise we get a soft lockup: NMI watchdog: BUG: soft lockup - CPU#0 stuck for 22s! [ip:798] irq event stamp: 255424 hardirqs last enabled at (255423): [] restore_args+0x0/0x30 hardirqs last disabled at (255424): [] apic_timer_interrupt+0x6a/0x80 softirqs last enabled at (255422): [] __do_softirq+0x2c1/0x3a9 softirqs last disabled at (255417): [] irq_exit+0x41/0x95 CPU: 0 PID: 798 Comm: ip Not tainted 4.0.0-rc4+ #881 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 task: ffff8800d1b88000 ti: ffff880119530000 task.ti: ffff880119530000 RIP: 0010:[] [] debug_lockdep_rcu_enabled+0x28/0x30 RSP: 0018:ffff880119533778 EFLAGS: 00000246 RAX: ffff8800d1b88000 RBX: 0000000000000002 RCX: 0000000000000038 RDX: 0000000000000000 RSI: ffff8800d1b888c8 RDI: ffff8800d1b888c8 RBP: ffff880119533778 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 000000000000b5c2 R12: 0000000000000246 R13: ffff880119533708 R14: 00000000001d5a40 R15: ffff88011a7d5a40 FS: 00007fc01315f740(0000) GS:ffff88011a600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 00007f367a120988 CR3: 000000011849c000 CR4: 00000000000007f0 Stack: ffff880119533798 ffffffff811ac868 ffffffff811ac831 ffffffff811ac828 ffff8801195337c8 ffffffff811ac8c9 ffff8801195339b0 ffff8801197633e0 0000000000000000 ffff8801195339b0 ffff8801195337d8 ffffffff811ad2d7 Call Trace: [] rcu_read_lock+0x37/0x6e [] ? rcu_read_unlock+0x5f/0x5f [] ? rcu_read_unlock+0x56/0x5f [] __fget+0x2a/0x7a [] fget+0x13/0x15 [] proc_ns_fget+0xe/0x38 [] get_net_ns_by_fd+0x11/0x59 [] rtnl_link_get_net+0x33/0x3e [] do_setlink+0x73/0x87b [] ? trace_hardirqs_off+0xd/0xf [] ? retint_restore_args+0xe/0xe [] rtnl_newlink+0x40c/0x699 [] ? rtnl_newlink+0xeb/0x699 [] ? _raw_spin_unlock+0x28/0x33 [] ? security_capable+0x18/0x1a [] ? ns_capable+0x4d/0x65 [] rtnetlink_rcv_msg+0x181/0x194 [] ? rtnl_lock+0x17/0x19 [] ? rtnl_lock+0x17/0x19 [] ? __rtnl_unlock+0x17/0x17 [] netlink_rcv_skb+0x4d/0x93 [] rtnetlink_rcv+0x26/0x2d [] netlink_unicast+0xcb/0x150 [] netlink_sendmsg+0x501/0x523 [] ? might_fault+0x59/0xa9 [] ? copy_from_user+0x2a/0x2c [] sock_sendmsg+0x34/0x3c [] ___sys_sendmsg+0x1b8/0x255 [] ? handle_pte_fault+0xbd5/0xd4a [] ? native_sched_clock+0x35/0x37 [] ? sched_clock_local+0x12/0x72 [] ? sched_clock_cpu+0x9e/0xb7 [] ? rcu_read_lock_held+0x3b/0x3d [] ? __fcheck_files+0x4c/0x58 [] ? __fget_light+0x2d/0x52 [] __sys_sendmsg+0x42/0x60 [] SyS_sendmsg+0x12/0x1c [] system_call_fastpath+0x12/0x17 Fixes: e7ed828f10bd8 ("netlink: support setting devgroup parameters") Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index ee0608bb3bc0..7ebed55b5f7d 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1932,10 +1932,10 @@ static int rtnl_group_changelink(const struct sk_buff *skb, struct ifinfomsg *ifm, struct nlattr **tb) { - struct net_device *dev; + struct net_device *dev, *aux; int err; - for_each_netdev(net, dev) { + for_each_netdev_safe(net, dev, aux) { if (dev->group == group) { err = do_setlink(skb, dev, ifm, tb, NULL, 0); if (err < 0) From f3eab7184ddcd4867cf42e3274ba24a66e1e093d Mon Sep 17 00:00:00 2001 From: Steve Capper Date: Sun, 22 Mar 2015 14:51:51 +0000 Subject: [PATCH 087/170] arm64: percpu: Make this_cpu accessors pre-empt safe this_cpu operations were implemented for arm64 in: 5284e1b arm64: xchg: Implement cmpxchg_double f97fc81 arm64: percpu: Implement this_cpu operations Unfortunately, it is possible for pre-emption to take place between address generation and data access. This can lead to cases where data is being manipulated by this_cpu for a different CPU than it was called on. Which effectively breaks the spec. This patch disables pre-emption for the this_cpu operations guaranteeing that address generation and data manipulation take place without a pre-emption in-between. Fixes: 5284e1b4bc8a ("arm64: xchg: Implement cmpxchg_double") Fixes: f97fc810798c ("arm64: percpu: Implement this_cpu operations") Reported-by: Mark Rutland Acked-by: Will Deacon Signed-off-by: Steve Capper [catalin.marinas@arm.com: remove space after type cast] Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/cmpxchg.h | 30 ++++++++++++++++----- arch/arm64/include/asm/percpu.h | 46 +++++++++++++++++++++++--------- 2 files changed, 57 insertions(+), 19 deletions(-) diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h index cb9593079f29..d8c25b7b18fb 100644 --- a/arch/arm64/include/asm/cmpxchg.h +++ b/arch/arm64/include/asm/cmpxchg.h @@ -246,14 +246,30 @@ static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old, __ret; \ }) -#define this_cpu_cmpxchg_1(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n) -#define this_cpu_cmpxchg_2(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n) -#define this_cpu_cmpxchg_4(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n) -#define this_cpu_cmpxchg_8(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n) +#define _protect_cmpxchg_local(pcp, o, n) \ +({ \ + typeof(*raw_cpu_ptr(&(pcp))) __ret; \ + preempt_disable(); \ + __ret = cmpxchg_local(raw_cpu_ptr(&(pcp)), o, n); \ + preempt_enable(); \ + __ret; \ +}) -#define this_cpu_cmpxchg_double_8(ptr1, ptr2, o1, o2, n1, n2) \ - cmpxchg_double_local(raw_cpu_ptr(&(ptr1)), raw_cpu_ptr(&(ptr2)), \ - o1, o2, n1, n2) +#define this_cpu_cmpxchg_1(ptr, o, n) _protect_cmpxchg_local(ptr, o, n) +#define this_cpu_cmpxchg_2(ptr, o, n) _protect_cmpxchg_local(ptr, o, n) +#define this_cpu_cmpxchg_4(ptr, o, n) _protect_cmpxchg_local(ptr, o, n) +#define this_cpu_cmpxchg_8(ptr, o, n) _protect_cmpxchg_local(ptr, o, n) + +#define this_cpu_cmpxchg_double_8(ptr1, ptr2, o1, o2, n1, n2) \ +({ \ + int __ret; \ + preempt_disable(); \ + __ret = cmpxchg_double_local( raw_cpu_ptr(&(ptr1)), \ + raw_cpu_ptr(&(ptr2)), \ + o1, o2, n1, n2); \ + preempt_enable(); \ + __ret; \ +}) #define cmpxchg64(ptr,o,n) cmpxchg((ptr),(o),(n)) #define cmpxchg64_local(ptr,o,n) cmpxchg_local((ptr),(o),(n)) diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h index 09da25bc596f..4fde8c1df97f 100644 --- a/arch/arm64/include/asm/percpu.h +++ b/arch/arm64/include/asm/percpu.h @@ -204,25 +204,47 @@ static inline unsigned long __percpu_xchg(void *ptr, unsigned long val, return ret; } -#define _percpu_add(pcp, val) \ - __percpu_add(raw_cpu_ptr(&(pcp)), val, sizeof(pcp)) +#define _percpu_read(pcp) \ +({ \ + typeof(pcp) __retval; \ + preempt_disable(); \ + __retval = (typeof(pcp))__percpu_read(raw_cpu_ptr(&(pcp)), \ + sizeof(pcp)); \ + preempt_enable(); \ + __retval; \ +}) -#define _percpu_add_return(pcp, val) (typeof(pcp)) (_percpu_add(pcp, val)) +#define _percpu_write(pcp, val) \ +do { \ + preempt_disable(); \ + __percpu_write(raw_cpu_ptr(&(pcp)), (unsigned long)(val), \ + sizeof(pcp)); \ + preempt_enable(); \ +} while(0) \ + +#define _pcp_protect(operation, pcp, val) \ +({ \ + typeof(pcp) __retval; \ + preempt_disable(); \ + __retval = (typeof(pcp))operation(raw_cpu_ptr(&(pcp)), \ + (val), sizeof(pcp)); \ + preempt_enable(); \ + __retval; \ +}) + +#define _percpu_add(pcp, val) \ + _pcp_protect(__percpu_add, pcp, val) + +#define _percpu_add_return(pcp, val) _percpu_add(pcp, val) #define _percpu_and(pcp, val) \ - __percpu_and(raw_cpu_ptr(&(pcp)), val, sizeof(pcp)) + _pcp_protect(__percpu_and, pcp, val) #define _percpu_or(pcp, val) \ - __percpu_or(raw_cpu_ptr(&(pcp)), val, sizeof(pcp)) - -#define _percpu_read(pcp) (typeof(pcp)) \ - (__percpu_read(raw_cpu_ptr(&(pcp)), sizeof(pcp))) - -#define _percpu_write(pcp, val) \ - __percpu_write(raw_cpu_ptr(&(pcp)), (unsigned long)(val), sizeof(pcp)) + _pcp_protect(__percpu_or, pcp, val) #define _percpu_xchg(pcp, val) (typeof(pcp)) \ - (__percpu_xchg(raw_cpu_ptr(&(pcp)), (unsigned long)(val), sizeof(pcp))) + _pcp_protect(__percpu_xchg, pcp, (unsigned long)(val)) #define this_cpu_add_1(pcp, val) _percpu_add(pcp, val) #define this_cpu_add_2(pcp, val) _percpu_add(pcp, val) From a6e95cc718c8916a13f1e1e9d33cacbc5db56c0f Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Tue, 24 Mar 2015 09:31:40 +0900 Subject: [PATCH 088/170] rocker: handle non-bridge master change Master change notifications may occur other than when joining or leaving a bridge, for example when being added to or removed from a bond or Open vSwitch. Previously in those cases rocker_port_bridge_leave() was called which results in a null-pointer dereference as rocker_port->bridge_dev is NULL because there is no bridge device. This patch makes provision for doing nothing in such cases. Fixes: 6c7079450071f ("rocker: implement L2 bridge offloading") Acked-by: Jiri Pirko Acked-by: Scott Feldman Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/rocker/rocker.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 9fb6948e14c6..5cecec282aba 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -4468,10 +4468,16 @@ static int rocker_port_master_changed(struct net_device *dev) struct net_device *master = netdev_master_upper_dev_get(dev); int err = 0; + /* There are currently three cases handled here: + * 1. Joining a bridge + * 2. Leaving a previously joined bridge + * 3. Other, e.g. being added to or removed from a bond or openvswitch, + * in which case nothing is done + */ if (master && master->rtnl_link_ops && !strcmp(master->rtnl_link_ops->kind, "bridge")) err = rocker_port_bridge_join(rocker_port, master); - else + else if (rocker_port_is_bridged(rocker_port)) err = rocker_port_bridge_leave(rocker_port); return err; From e5eda89d97ec256ba14e7e861387cc0468259c18 Mon Sep 17 00:00:00 2001 From: Ido Shamay Date: Tue, 24 Mar 2015 15:18:38 +0200 Subject: [PATCH 089/170] net/mlx4_en: Call register_netdevice in the proper location Netdevice registration should be performed a the end of the driver initialization flow. If we don't do that, after calling register_netdevice, device callbacks may be issued by higher layers of the stack before final configuration of the device is done. For example (VXLAN configuration race), mlx4_SET_PORT_VXLAN was issued after the register_netdev command. System network scripts may configure the interface (UP) right after the registration, which also attach unicast VXLAN steering rule, before mlx4_SET_PORT_VXLAN was called, causing the firmware to fail the rule attachment. Fixes: 837052d0ccc5 ("net/mlx4_en: Add netdev support for TCP/IP offloads of vxlan tunneling") Signed-off-by: Ido Shamay Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index ebce5bb24df9..3485acf03014 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2805,13 +2805,6 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, netif_carrier_off(dev); mlx4_en_set_default_moderation(priv); - err = register_netdev(dev); - if (err) { - en_err(priv, "Netdev registration failed for port %d\n", port); - goto out; - } - priv->registered = 1; - en_warn(priv, "Using %d TX rings\n", prof->tx_ring_num); en_warn(priv, "Using %d RX rings\n", prof->rx_ring_num); @@ -2853,6 +2846,14 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, mlx4_set_stats_bitmap(mdev->dev, &priv->stats_bitmap); + err = register_netdev(dev); + if (err) { + en_err(priv, "Netdev registration failed for port %d\n", port); + goto out; + } + + priv->registered = 1; + return 0; out: From bffb023ad2d44c0cfa8142ad8247391b32000998 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Tue, 24 Mar 2015 15:18:39 +0200 Subject: [PATCH 090/170] net/mlx4_core: Fix GEN_EQE accessing uninitialixed mutex We occasionally see in procedure mlx4_GEN_EQE that the driver tries to grab an uninitialized mutex. This can occur in only one of two ways: 1. We are trying to generate an async event on an uninitialized slave. 2. We are trying to generate an async event on an illegal slave number ( < 0 or > persist->num_vfs) or an inactive slave. To deal with #1: move the mutex initialization from specific slave init sequence in procedure mlx_master_do_cmd to mlx4_multi_func_init() (so that the mutex is always initialized for all slaves). To deal with #2: check in procedure mlx4_GEN_EQE that the slave number provided is in the proper range and that the slave is active. Signed-off-by: Jack Morgenstein Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/cmd.c | 2 +- drivers/net/ethernet/mellanox/mlx4/eq.c | 18 +++++++----------- .../ethernet/mellanox/mlx4/resource_tracker.c | 6 ++++++ 3 files changed, 14 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index a681d7c0bb9f..3350721bf515 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -1993,7 +1993,6 @@ static void mlx4_master_do_cmd(struct mlx4_dev *dev, int slave, u8 cmd, goto reset_slave; slave_state[slave].vhcr_dma = ((u64) param) << 48; priv->mfunc.master.slave_state[slave].cookie = 0; - mutex_init(&priv->mfunc.master.gen_eqe_mutex[slave]); break; case MLX4_COMM_CMD_VHCR1: if (slave_state[slave].last_cmd != MLX4_COMM_CMD_VHCR0) @@ -2225,6 +2224,7 @@ int mlx4_multi_func_init(struct mlx4_dev *dev) for (i = 0; i < dev->num_slaves; ++i) { s_state = &priv->mfunc.master.slave_state[i]; s_state->last_cmd = MLX4_COMM_CMD_RESET; + mutex_init(&priv->mfunc.master.gen_eqe_mutex[i]); for (j = 0; j < MLX4_EVENT_TYPES_NUM; ++j) s_state->event_eq[j].eqn = -1; __raw_writel((__force u32) 0, diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index 264bc15c1ff2..6e70ffee8e87 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -153,12 +153,10 @@ void mlx4_gen_slave_eqe(struct work_struct *work) /* All active slaves need to receive the event */ if (slave == ALL_SLAVES) { - for (i = 0; i < dev->num_slaves; i++) { - if (i != dev->caps.function && - master->slave_state[i].active) - if (mlx4_GEN_EQE(dev, i, eqe)) - mlx4_warn(dev, "Failed to generate event for slave %d\n", - i); + for (i = 0; i <= dev->persist->num_vfs; i++) { + if (mlx4_GEN_EQE(dev, i, eqe)) + mlx4_warn(dev, "Failed to generate event for slave %d\n", + i); } } else { if (mlx4_GEN_EQE(dev, slave, eqe)) @@ -203,13 +201,11 @@ static void mlx4_slave_event(struct mlx4_dev *dev, int slave, struct mlx4_eqe *eqe) { struct mlx4_priv *priv = mlx4_priv(dev); - struct mlx4_slave_state *s_slave = - &priv->mfunc.master.slave_state[slave]; - if (!s_slave->active) { - /*mlx4_warn(dev, "Trying to pass event to inactive slave\n");*/ + if (slave < 0 || slave > dev->persist->num_vfs || + slave == dev->caps.function || + !priv->mfunc.master.slave_state[slave].active) return; - } slave_event(dev, slave, eqe); } diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index d97ca88c55b5..6e413ac4e940 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -3095,6 +3095,12 @@ int mlx4_GEN_EQE(struct mlx4_dev *dev, int slave, struct mlx4_eqe *eqe) if (!priv->mfunc.master.slave_state) return -EINVAL; + /* check for slave valid, slave not PF, and slave active */ + if (slave < 0 || slave > dev->persist->num_vfs || + slave == dev->caps.function || + !priv->mfunc.master.slave_state[slave].active) + return 0; + event_eq = &priv->mfunc.master.slave_state[slave].event_eq[eqe->type]; /* Create the event only if the slave is registered */ From b3494a4ab20f6bdf74cdf2badf7918bb65ee8a00 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Mon, 23 Mar 2015 12:32:54 -0700 Subject: [PATCH 091/170] x86/asm/entry: Check for syscall exit work with IRQs disabled We currently have a race: if we're preempted during syscall exit, we can fail to process syscall return work that is queued up while we're preempted in ret_from_sys_call after checking ti.flags. Fix it by disabling interrupts before checking ti.flags. Reported-by: Stefan Seyfried Reported-by: Takashi Iwai Signed-off-by: Andy Lutomirski Acked-by: Denys Vlasenko Cc: Jiri Kosina Cc: Tejun Heo Fixes: 96b6352c1271 ("x86_64, entry: Remove the syscall exit audit") Link: http://lkml.kernel.org/r/189320d42b4d671df78c10555976bb10af1ffc75.1427137498.git.luto@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/entry_64.S | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 1d74d161687c..2babb393915e 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -364,12 +364,21 @@ system_call_fastpath: * Has incomplete stack frame and undefined top of stack. */ ret_from_sys_call: - testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) - jnz int_ret_from_sys_call_fixup /* Go the the slow path */ - LOCKDEP_SYS_EXIT DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF + + /* + * We must check ti flags with interrupts (or at least preemption) + * off because we must *never* return to userspace without + * processing exit work that is enqueued if we're preempted here. + * In particular, returning to userspace with any of the one-shot + * flags (TIF_NOTIFY_RESUME, TIF_USER_RETURN_NOTIFY, etc) set is + * very bad. + */ + testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) + jnz int_ret_from_sys_call_fixup /* Go the the slow path */ + CFI_REMEMBER_STATE /* * sysretq will re-enable interrupts: @@ -386,7 +395,7 @@ ret_from_sys_call: int_ret_from_sys_call_fixup: FIXUP_TOP_OF_STACK %r11, -ARGOFFSET - jmp int_ret_from_sys_call + jmp int_ret_from_sys_call_irqs_off /* Do syscall tracing */ tracesys: @@ -432,6 +441,7 @@ tracesys_phase2: GLOBAL(int_ret_from_sys_call) DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF +int_ret_from_sys_call_irqs_off: movl $_TIF_ALLWORK_MASK,%edi /* edi: mask to check */ GLOBAL(int_with_check) From 977104e5606a6df8fe22c0dacd3620fc00b58d61 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Wed, 25 Mar 2015 00:53:26 +0800 Subject: [PATCH 092/170] ARM: dts: sun4i: a10-lime: Override and remove 1008MHz OPP setting The Olimex A10-Lime is known to be unstable when running at 1008MHz. Signed-off-by: Chen-Yu Tsai Signed-off-by: Maxime Ripard --- arch/arm/boot/dts/sun4i-a10-olinuxino-lime.dts | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/arch/arm/boot/dts/sun4i-a10-olinuxino-lime.dts b/arch/arm/boot/dts/sun4i-a10-olinuxino-lime.dts index ab7891c43231..75742f8f96f3 100644 --- a/arch/arm/boot/dts/sun4i-a10-olinuxino-lime.dts +++ b/arch/arm/boot/dts/sun4i-a10-olinuxino-lime.dts @@ -56,6 +56,22 @@ / { model = "Olimex A10-OLinuXino-LIME"; compatible = "olimex,a10-olinuxino-lime", "allwinner,sun4i-a10"; + cpus { + cpu0: cpu@0 { + /* + * The A10-Lime is known to be unstable + * when running at 1008 MHz + */ + operating-points = < + /* kHz uV */ + 912000 1350000 + 864000 1300000 + 624000 1250000 + >; + cooling-max-level = <2>; + }; + }; + soc@01c00000 { emac: ethernet@01c0b000 { pinctrl-names = "default"; From 370a9b5fb04a0d5cc7b7699c788616d6976f4476 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Wed, 25 Mar 2015 00:53:27 +0800 Subject: [PATCH 093/170] ARM: dts: sunxi: Remove overclocked/overvoltaged OPP Without proper regulator support for individual boards, it is dangerous to have overclocked/overvoltaged OPPs in the list. Cpufreq will increase the frequency without the accompanying voltage increase, resulting in an unstable system. Remove them for now. We can revisit them with the new version of OPP bindings, which support boost settings and frequency ranges, among other things. Signed-off-by: Chen-Yu Tsai Signed-off-by: Maxime Ripard --- arch/arm/boot/dts/sun4i-a10.dtsi | 3 +-- arch/arm/boot/dts/sun5i-a13.dtsi | 3 +-- arch/arm/boot/dts/sun7i-a20.dtsi | 3 +-- 3 files changed, 3 insertions(+), 6 deletions(-) diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi index 5c2925831f20..eebb7853e00b 100644 --- a/arch/arm/boot/dts/sun4i-a10.dtsi +++ b/arch/arm/boot/dts/sun4i-a10.dtsi @@ -75,7 +75,6 @@ cpu0: cpu@0 { clock-latency = <244144>; /* 8 32k periods */ operating-points = < /* kHz uV */ - 1056000 1500000 1008000 1400000 912000 1350000 864000 1300000 @@ -83,7 +82,7 @@ cpu0: cpu@0 { >; #cooling-cells = <2>; cooling-min-level = <0>; - cooling-max-level = <4>; + cooling-max-level = <3>; }; }; diff --git a/arch/arm/boot/dts/sun5i-a13.dtsi b/arch/arm/boot/dts/sun5i-a13.dtsi index f8818f1edbbe..883cb4873688 100644 --- a/arch/arm/boot/dts/sun5i-a13.dtsi +++ b/arch/arm/boot/dts/sun5i-a13.dtsi @@ -47,7 +47,6 @@ cpu0: cpu@0 { clock-latency = <244144>; /* 8 32k periods */ operating-points = < /* kHz uV */ - 1104000 1500000 1008000 1400000 912000 1350000 864000 1300000 @@ -57,7 +56,7 @@ cpu0: cpu@0 { >; #cooling-cells = <2>; cooling-min-level = <0>; - cooling-max-level = <6>; + cooling-max-level = <5>; }; }; diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi index 3a8530b79f1c..fdd181792b4b 100644 --- a/arch/arm/boot/dts/sun7i-a20.dtsi +++ b/arch/arm/boot/dts/sun7i-a20.dtsi @@ -105,7 +105,6 @@ cpu0: cpu@0 { clock-latency = <244144>; /* 8 32k periods */ operating-points = < /* kHz uV */ - 1008000 1450000 960000 1400000 912000 1400000 864000 1300000 @@ -116,7 +115,7 @@ cpu0: cpu@0 { >; #cooling-cells = <2>; cooling-min-level = <0>; - cooling-max-level = <7>; + cooling-max-level = <6>; }; cpu@1 { From 1452db764c279f8b329f1b3b9469bd01d9e21afd Mon Sep 17 00:00:00 2001 From: Cliff Clark Date: Tue, 24 Mar 2015 14:07:26 -0700 Subject: [PATCH 094/170] ucc_geth: Intialize link state to down before register_netdev ucc_geth was indicating link up after a port is administratively enabled even when nothing is plugged in. This causes user-space tools to see a spurious link up the first time after boot. Signed-off-by: Cliff Clark Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/ucc_geth.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c index 357e8b576905..56b774d3a13d 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.c +++ b/drivers/net/ethernet/freescale/ucc_geth.c @@ -3893,6 +3893,9 @@ static int ucc_geth_probe(struct platform_device* ofdev) ugeth->phy_interface = phy_interface; ugeth->max_speed = max_speed; + /* Carrier starts down, phylib will bring it up */ + netif_carrier_off(dev); + err = register_netdev(dev); if (err) { if (netif_msg_probe(ugeth)) From 59a58cb34d3fe73e6c899cc5d9a87428ca662925 Mon Sep 17 00:00:00 2001 From: Damien Lespiau Date: Thu, 5 Feb 2015 18:30:20 +0000 Subject: [PATCH 095/170] drm/i915: Don't try to reference the fb in get_initial_plane_config() Tvrtko noticed a new warning on boot: WARNING: CPU: 1 PID: 353 at include/linux/kref.h:47 drm_framebuffer_reference+0x6c/0x80 [drm]() Call Trace: [] dump_stack+0x4f/0x7b [] warn_slowpath_common+0xaa/0xd0 [] warn_slowpath_null+0x1a/0x20 [] drm_framebuffer_reference+0x6c/0x80 [drm] [] update_state_fb.isra.54+0x47/0x50 [i915] [] skylake_get_initial_plane_config+0x93c/0x950 [i915] [] intel_modeset_init+0x1551/0x17c0 [i915] [] i915_driver_load+0xed0/0x11e0 [i915] [] ? _raw_spin_unlock_irqrestore+0x51/0x70 [] drm_dev_register+0x77/0x110 [drm] [] drm_get_pci_dev+0x11b/0x1f0 [drm] [] ? trace_hardirqs_on+0xd/0x10 [] ? _raw_spin_unlock_irqrestore+0x51/0x70 [] i915_pci_probe+0x56/0x60 [i915] [] pci_device_probe+0x7c/0x100 [] driver_probe_device+0x16d/0x380 We cannot take a reference at this point, not before intel_framebuffer_init() and the underlying drm_framebuffer_init(). Introduced in: commit 706dc7b549175e47f23e913b7f1e52874a7d0f56 Author: Matt Roper Date: Tue Feb 3 13:10:04 2015 -0800 drm/i915: Ensure plane->state->fb stays in sync with plane->fb v2: Don't move update_state_fb(). It was moved around because I originally put update_state_fb() in intel_alloc_plane_obj() before finding a better place. (Matt) Reviewed-by: Matt Roper Reported-by: Tvrtko Ursulin Cc: Matt Roper Cc: Tvrtko Ursulin Signed-off-by: Damien Lespiau Signed-off-by: Daniel Vetter From drm-next: (cherry picked from commit f55548b5af87ebfc586ca75748947f1c1b1a4a52) Signed-off-by: Dave Airlie --- drivers/gpu/drm/i915/intel_display.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 6d22128d97b1..1c12262029fb 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -2438,8 +2438,10 @@ intel_find_plane_obj(struct intel_crtc *intel_crtc, if (!intel_crtc->base.primary->fb) return; - if (intel_alloc_plane_obj(intel_crtc, plane_config)) + if (intel_alloc_plane_obj(intel_crtc, plane_config)) { + update_state_fb(intel_crtc->base.primary); return; + } kfree(intel_crtc->base.primary->fb); intel_crtc->base.primary->fb = NULL; @@ -6663,7 +6665,6 @@ i9xx_get_initial_plane_config(struct intel_crtc *crtc, plane_config->size); crtc->base.primary->fb = fb; - update_state_fb(crtc->base.primary); } static void chv_crtc_clock_get(struct intel_crtc *crtc, @@ -7704,7 +7705,6 @@ skylake_get_initial_plane_config(struct intel_crtc *crtc, plane_config->size); crtc->base.primary->fb = fb; - update_state_fb(crtc->base.primary); return; error: @@ -7798,7 +7798,6 @@ ironlake_get_initial_plane_config(struct intel_crtc *crtc, plane_config->size); crtc->base.primary->fb = fb; - update_state_fb(crtc->base.primary); } static bool ironlake_get_pipe_config(struct intel_crtc *crtc, From 1833c9f647e9bda1cd24653ff8f9c207b5f5b911 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Sat, 21 Mar 2015 12:43:08 +0100 Subject: [PATCH 096/170] s390/smp: reenable smt after resume After a suspend/resume cycle we missed to enable smt again, which leads to all sorts of bugs, since the kernel assumes smt is enabled, while the hardware thinks it is not. Reported-and-tested-by: Sebastian Ott Reported-by: Stefan Haberland Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/swsusp_asm64.S | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/arch/s390/kernel/swsusp_asm64.S b/arch/s390/kernel/swsusp_asm64.S index 6b09fdffbd2f..ca6294645dd3 100644 --- a/arch/s390/kernel/swsusp_asm64.S +++ b/arch/s390/kernel/swsusp_asm64.S @@ -177,6 +177,17 @@ restart_entry: lhi %r1,1 sigp %r1,%r0,SIGP_SET_ARCHITECTURE sam64 +#ifdef CONFIG_SMP + larl %r1,smp_cpu_mt_shift + icm %r1,15,0(%r1) + jz smt_done + llgfr %r1,%r1 +smt_loop: + sigp %r1,%r0,SIGP_SET_MULTI_THREADING + brc 8,smt_done /* accepted */ + brc 2,smt_loop /* busy, try again */ +smt_done: +#endif larl %r1,.Lnew_pgm_check_psw lpswe 0(%r1) pgm_check_entry: From 6fd99094de2b83d1d4c8457f2c83483b2828e75a Mon Sep 17 00:00:00 2001 From: "D.S. Ljungmark" Date: Wed, 25 Mar 2015 09:28:15 +0100 Subject: [PATCH 097/170] ipv6: Don't reduce hop limit for an interface A local route may have a lower hop_limit set than global routes do. RFC 3756, Section 4.2.7, "Parameter Spoofing" > 1. The attacker includes a Current Hop Limit of one or another small > number which the attacker knows will cause legitimate packets to > be dropped before they reach their destination. > As an example, one possible approach to mitigate this threat is to > ignore very small hop limits. The nodes could implement a > configurable minimum hop limit, and ignore attempts to set it below > said limit. Signed-off-by: D.S. Ljungmark Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/ipv6/ndisc.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 471ed24aabae..14ecdaf06bf7 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1218,7 +1218,14 @@ static void ndisc_router_discovery(struct sk_buff *skb) if (rt) rt6_set_expires(rt, jiffies + (HZ * lifetime)); if (ra_msg->icmph.icmp6_hop_limit) { - in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit; + /* Only set hop_limit on the interface if it is higher than + * the current hop_limit. + */ + if (in6_dev->cnf.hop_limit < ra_msg->icmph.icmp6_hop_limit) { + in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit; + } else { + ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than current\n"); + } if (rt) dst_metric_set(&rt->dst, RTAX_HOPLIMIT, ra_msg->icmph.icmp6_hop_limit); From dde93dfea53c72b07907d9e44a6e4b1545f6bdc4 Mon Sep 17 00:00:00 2001 From: Hariprasad Shenai Date: Wed, 25 Mar 2015 20:01:26 +0530 Subject: [PATCH 098/170] cxgb4: Fix frame size warning for 32 bit arch Fixes below warning by dynamically allocating memory All warnings: drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c: In function 'cctrl_tbl_show': >> drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c:689:1: warning: the >> frame >> size of 1028 bytes is larger than 1024 bytes [-Wframe-larger-than=] Reported-by: kbuild test robot Signed-off-by: Hariprasad Shenai Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index 78854ceb0870..dcb047945290 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -670,9 +670,13 @@ static int cctrl_tbl_show(struct seq_file *seq, void *v) "0.9375" }; int i; - u16 incr[NMTUS][NCCTRL_WIN]; + u16 (*incr)[NCCTRL_WIN]; struct adapter *adap = seq->private; + incr = kmalloc(sizeof(*incr) * NMTUS, GFP_KERNEL); + if (!incr) + return -ENOMEM; + t4_read_cong_tbl(adap, incr); for (i = 0; i < NCCTRL_WIN; ++i) { @@ -685,6 +689,8 @@ static int cctrl_tbl_show(struct seq_file *seq, void *v) adap->params.a_wnd[i], dec_fac[adap->params.b_wnd[i]]); } + + kfree(incr); return 0; } From 6436a123a147db51a0b06024a8350f4c230e73ff Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 23 Mar 2015 18:01:35 -0700 Subject: [PATCH 099/170] selinux: fix sel_write_enforce broken return value Return a negative error value like the rest of the entries in this function. Cc: Signed-off-by: Joe Perches Acked-by: Stephen Smalley [PM: tweaked subject line] Signed-off-by: Paul Moore --- security/selinux/selinuxfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index 33db1ad4fd10..138949a31eab 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -152,7 +152,7 @@ static ssize_t sel_write_enforce(struct file *file, const char __user *buf, goto out; /* No partial writes. */ - length = EINVAL; + length = -EINVAL; if (*ppos != 0) goto out; From fb903811c4e3bcd93ccc247235834e2632a3508d Mon Sep 17 00:00:00 2001 From: Ed Cashin Date: Wed, 25 Mar 2015 15:55:06 -0700 Subject: [PATCH 100/170] aoe: update aoe maintainer information The coraid.com email address is defunct. The old aoe support area hosted at coraid.com is no longer up. These changes update the email and website to current ones. Signed-off-by: Ed Cashin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- MAINTAINERS | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 358eb0105e00..c6cd0f60635c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1675,8 +1675,8 @@ F: drivers/misc/eeprom/at24.c F: include/linux/platform_data/at24.h ATA OVER ETHERNET (AOE) DRIVER -M: "Ed L. Cashin" -W: http://support.coraid.com/support/linux +M: "Ed L. Cashin" +W: http://www.openaoe.org/ S: Supported F: Documentation/aoe/ F: drivers/block/aoe/ From ddd2a30d41a5bc578ab094f6dbf080697ea1a7dd Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Wed, 25 Mar 2015 15:55:09 -0700 Subject: [PATCH 101/170] drivers/rtc/rtc-mrst: fix suspend/resume The Moorestown RTC driver implements suspend and resume callbacks and assigns them to the suspend and resume fields of the device_driver struct. These callbacks are never actually called by anything though. Modify the driver to properly use dev_pm_ops so that the suspend and resume functions are actually executed upon suspend/resume. [akpm@linux-foundation.org: device_driver.name is const char *] Signed-off-by: Lars-Peter Clausen Cc: Alessandro Zummo Cc: Feng Tang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/rtc/rtc-mrst.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/drivers/rtc/rtc-mrst.c b/drivers/rtc/rtc-mrst.c index e2436d140175..3a6fd3a8a2ec 100644 --- a/drivers/rtc/rtc-mrst.c +++ b/drivers/rtc/rtc-mrst.c @@ -413,8 +413,8 @@ static void rtc_mrst_do_remove(struct device *dev) mrst->dev = NULL; } -#ifdef CONFIG_PM -static int mrst_suspend(struct device *dev, pm_message_t mesg) +#ifdef CONFIG_PM_SLEEP +static int mrst_suspend(struct device *dev) { struct mrst_rtc *mrst = dev_get_drvdata(dev); unsigned char tmp; @@ -453,7 +453,7 @@ static int mrst_suspend(struct device *dev, pm_message_t mesg) */ static inline int mrst_poweroff(struct device *dev) { - return mrst_suspend(dev, PMSG_HIBERNATE); + return mrst_suspend(dev); } static int mrst_resume(struct device *dev) @@ -490,9 +490,11 @@ static int mrst_resume(struct device *dev) return 0; } +static SIMPLE_DEV_PM_OPS(mrst_pm_ops, mrst_suspend, mrst_resume); +#define MRST_PM_OPS (&mrst_pm_ops) + #else -#define mrst_suspend NULL -#define mrst_resume NULL +#define MRST_PM_OPS NULL static inline int mrst_poweroff(struct device *dev) { @@ -529,9 +531,8 @@ static struct platform_driver vrtc_mrst_platform_driver = { .remove = vrtc_mrst_platform_remove, .shutdown = vrtc_mrst_platform_shutdown, .driver = { - .name = (char *) driver_name, - .suspend = mrst_suspend, - .resume = mrst_resume, + .name = driver_name, + .pm = MRST_PM_OPS, } }; From 3fe89b3e2a7bbf3e97657104b9b33a9d81b950b3 Mon Sep 17 00:00:00 2001 From: Leon Yu Date: Wed, 25 Mar 2015 15:55:11 -0700 Subject: [PATCH 102/170] mm: fix anon_vma->degree underflow in anon_vma endless growing prevention I have constantly stumbled upon "kernel BUG at mm/rmap.c:399!" after upgrading to 3.19 and had no luck with 4.0-rc1 neither. So, after looking into new logic introduced by commit 7a3ef208e662 ("mm: prevent endless growth of anon_vma hierarchy"), I found chances are that unlink_anon_vmas() is called without incrementing dst->anon_vma->degree in anon_vma_clone() due to allocation failure. If dst->anon_vma is not NULL in error path, its degree will be incorrectly decremented in unlink_anon_vmas() and eventually underflow when exiting as a result of another call to unlink_anon_vmas(). That's how "kernel BUG at mm/rmap.c:399!" is triggered for me. This patch fixes the underflow by dropping dst->anon_vma when allocation fails. It's safe to do so regardless of original value of dst->anon_vma because dst->anon_vma doesn't have valid meaning if anon_vma_clone() fails. Besides, callers don't care dst->anon_vma in such case neither. Also suggested by Michal Hocko, we can clean up vma_adjust() a bit as anon_vma_clone() now does the work. [akpm@linux-foundation.org: tweak comment] Fixes: 7a3ef208e662 ("mm: prevent endless growth of anon_vma hierarchy") Signed-off-by: Leon Yu Signed-off-by: Konstantin Khlebnikov Reviewed-by: Michal Hocko Acked-by: Rik van Riel Acked-by: David Rientjes Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mmap.c | 4 +--- mm/rmap.c | 7 +++++++ 2 files changed, 8 insertions(+), 3 deletions(-) diff --git a/mm/mmap.c b/mm/mmap.c index da9990acc08b..9ec50a368634 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -774,10 +774,8 @@ again: remove_next = 1 + (end > next->vm_end); importer->anon_vma = exporter->anon_vma; error = anon_vma_clone(importer, exporter); - if (error) { - importer->anon_vma = NULL; + if (error) return error; - } } } diff --git a/mm/rmap.c b/mm/rmap.c index 5e3e09081164..c161a14b6a8f 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -287,6 +287,13 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) return 0; enomem_failure: + /* + * dst->anon_vma is dropped here otherwise its degree can be incorrectly + * decremented in unlink_anon_vmas(). + * We can safely do this because callers of anon_vma_clone() don't care + * about dst->anon_vma if anon_vma_clone() failed. + */ + dst->anon_vma = NULL; unlink_anon_vmas(dst); return -ENOMEM; } From f683739539e819e9b821a197d80e52258510837b Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 25 Mar 2015 15:55:14 -0700 Subject: [PATCH 103/170] mm/pagewalk.c: prevent positive return value of walk_page_test() from being passed to callers walk_page_test() is purely pagewalk's internal stuff, and its positive return values are not intended to be passed to the callers of pagewalk. However, in the current code if the last vma in the do-while loop in walk_page_range() happens to return a positive value, it leaks outside walk_page_range(). So the user visible effect is invalid/unexpected return value (according to the reporter, mbind() causes it.) This patch fixes it simply by reinitializing the return value after checked. Another exposed interface, walk_page_vma(), already returns 0 for such cases so no problem. Fixes: fafaa4264eba ("pagewalk: improve vma handling") Signed-off-by: Naoya Horiguchi Signed-off-by: Kazutomo Yoshii Reported-by: Kazutomo Yoshii Acked-by: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/pagewalk.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 75c1f2878519..29f2f8b853ae 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -265,8 +265,15 @@ int walk_page_range(unsigned long start, unsigned long end, vma = vma->vm_next; err = walk_page_test(start, next, walk); - if (err > 0) + if (err > 0) { + /* + * positive return values are purely for + * controlling the pagewalk, so should never + * be passed to the callers. + */ + err = 0; continue; + } if (err < 0) break; } From 59ec96719f7521002804c0862888971410e288af Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 25 Mar 2015 15:55:17 -0700 Subject: [PATCH 104/170] MAINTAINERS: correct rtc armada38x pattern entry Commit c6a95dbee793 ("MAINTAINERS: add the RTC driver for the Armada38x") typoed the pattern, fix it. Signed-off-by: Joe Perches Acked-by: Gregory CLEMENT Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index c6cd0f60635c..12ebef95224d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1186,7 +1186,7 @@ M: Sebastian Hesselbarth L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm/mach-mvebu/ -F: drivers/rtc/armada38x-rtc +F: drivers/rtc/rtc-armada38x.c ARM/Marvell Berlin SoC support M: Sebastian Hesselbarth From b0dc3a342af36f95a68fe229b8f0f73552c5ca08 Mon Sep 17 00:00:00 2001 From: Gu Zheng Date: Wed, 25 Mar 2015 15:55:20 -0700 Subject: [PATCH 105/170] mm/memory hotplug: postpone the reset of obsolete pgdat Qiu Xishi reported the following BUG when testing hot-add/hot-remove node under stress condition: BUG: unable to handle kernel paging request at 0000000000025f60 IP: next_online_pgdat+0x1/0x50 PGD 0 Oops: 0000 [#1] SMP ACPI: Device does not support D3cold Modules linked in: fuse nls_iso8859_1 nls_cp437 vfat fat loop dm_mod coretemp mperf crc32c_intel ghash_clmulni_intel aesni_intel ablk_helper cryptd lrw gf128mul glue_helper aes_x86_64 pcspkr microcode igb dca i2c_algo_bit ipv6 megaraid_sas iTCO_wdt i2c_i801 i2c_core iTCO_vendor_support tg3 sg hwmon ptp lpc_ich pps_core mfd_core acpi_pad rtc_cmos button ext3 jbd mbcache sd_mod crc_t10dif scsi_dh_alua scsi_dh_rdac scsi_dh_hp_sw scsi_dh_emc scsi_dh ahci libahci libata scsi_mod [last unloaded: rasf] CPU: 23 PID: 238 Comm: kworker/23:1 Tainted: G O 3.10.15-5885-euler0302 #1 Hardware name: HUAWEI TECHNOLOGIES CO.,LTD. Huawei N1/Huawei N1, BIOS V100R001 03/02/2015 Workqueue: events vmstat_update task: ffffa800d32c0000 ti: ffffa800d32ae000 task.ti: ffffa800d32ae000 RIP: 0010: next_online_pgdat+0x1/0x50 RSP: 0018:ffffa800d32afce8 EFLAGS: 00010286 RAX: 0000000000001440 RBX: ffffffff81da53b8 RCX: 0000000000000082 RDX: 0000000000000000 RSI: 0000000000000082 RDI: 0000000000000000 RBP: ffffa800d32afd28 R08: ffffffff81c93bfc R09: ffffffff81cbdc96 R10: 00000000000040ec R11: 00000000000000a0 R12: ffffa800fffb3440 R13: ffffa800d32afd38 R14: 0000000000000017 R15: ffffa800e6616800 FS: 0000000000000000(0000) GS:ffffa800e6600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000025f60 CR3: 0000000001a0b000 CR4: 00000000001407e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: refresh_cpu_vm_stats+0xd0/0x140 vmstat_update+0x11/0x50 process_one_work+0x194/0x3d0 worker_thread+0x12b/0x410 kthread+0xc6/0xd0 ret_from_fork+0x7c/0xb0 The cause is the "memset(pgdat, 0, sizeof(*pgdat))" at the end of try_offline_node, which will reset all the content of pgdat to 0, as the pgdat is accessed lock-free, so that the users still using the pgdat will panic, such as the vmstat_update routine. process A: offline node XX: vmstat_updat() refresh_cpu_vm_stats() for_each_populated_zone() find online node XX cond_resched() offline cpu and memory, then try_offline_node() node_set_offline(nid), and memset(pgdat, 0, sizeof(*pgdat)) zone = next_zone(zone) pg_data_t *pgdat = zone->zone_pgdat; // here pgdat is NULL now next_online_pgdat(pgdat) next_online_node(pgdat->node_id); // NULL pointer access So the solution here is postponing the reset of obsolete pgdat from try_offline_node() to hotadd_new_pgdat(), and just resetting pgdat->nr_zones and pgdat->classzone_idx to be 0 rather than the memset 0 to avoid breaking pointer information in pgdat. Signed-off-by: Gu Zheng Reported-by: Xishi Qiu Suggested-by: KAMEZAWA Hiroyuki Cc: David Rientjes Cc: Yasuaki Ishimatsu Cc: Taku Izumi Cc: Tang Chen Cc: Xie XiuQi Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 9fab10795bea..65842d688b7c 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1092,6 +1092,10 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) return NULL; arch_refresh_nodedata(nid, pgdat); + } else { + /* Reset the nr_zones and classzone_idx to 0 before reuse */ + pgdat->nr_zones = 0; + pgdat->classzone_idx = 0; } /* we can use NODE_DATA(nid) from here */ @@ -1977,15 +1981,6 @@ void try_offline_node(int nid) if (is_vmalloc_addr(zone->wait_table)) vfree(zone->wait_table); } - - /* - * Since there is no way to guarentee the address of pgdat/zone is not - * on stack of any kernel threads or used by other kernel objects - * without reference counting or other symchronizing method, do not - * reset node_data and free pgdat here. Just reset it to 0 and reuse - * the memory when the node is online again. - */ - memset(pgdat, 0, sizeof(*pgdat)); } EXPORT_SYMBOL(try_offline_node); From 859b7a0e89120505c304d7afbbe90325abaa0a6b Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 25 Mar 2015 15:55:23 -0700 Subject: [PATCH 106/170] mm/slub: fix lockups on PREEMPT && !SMP kernels Commit 9aabf810a67c ("mm/slub: optimize alloc/free fastpath by removing preemption on/off") introduced an occasional hang for kernels built with CONFIG_PREEMPT && !CONFIG_SMP. The problem is the following loop the patch introduced to slab_alloc_node and slab_free: do { tid = this_cpu_read(s->cpu_slab->tid); c = raw_cpu_ptr(s->cpu_slab); } while (IS_ENABLED(CONFIG_PREEMPT) && unlikely(tid != c->tid)); GCC 4.9 has been observed to hoist the load of c and c->tid above the loop for !SMP kernels (as in this case raw_cpu_ptr(x) is compile-time constant and does not force a reload). On arm64 the generated assembly looks like: ldr x4, [x0,#8] loop: ldr x1, [x0,#8] cmp x1, x4 b.ne loop If the thread is preempted between the load of c->tid (into x1) and tid (into x4), and an allocation or free occurs in another thread (bumping the cpu_slab's tid), the thread will be stuck in the loop until s->cpu_slab->tid wraps, which may be forever in the absence of allocations/frees on the same CPU. This patch changes the loop condition to access c->tid with READ_ONCE. This ensures that the value is reloaded even when the compiler would otherwise assume it could cache the value, and also ensures that the load will not be torn. Signed-off-by: Mark Rutland Cc: Catalin Marinas Acked-by: Christoph Lameter Cc: David Rientjes Cc: Jesper Dangaard Brouer Cc: Joonsoo Kim Cc: Pekka Enberg Cc: Steve Capper Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slub.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/mm/slub.c b/mm/slub.c index 6832c4eab104..82c473780c91 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2449,7 +2449,8 @@ static __always_inline void *slab_alloc_node(struct kmem_cache *s, do { tid = this_cpu_read(s->cpu_slab->tid); c = raw_cpu_ptr(s->cpu_slab); - } while (IS_ENABLED(CONFIG_PREEMPT) && unlikely(tid != c->tid)); + } while (IS_ENABLED(CONFIG_PREEMPT) && + unlikely(tid != READ_ONCE(c->tid))); /* * Irqless object alloc/free algorithm used here depends on sequence @@ -2718,7 +2719,8 @@ static __always_inline void slab_free(struct kmem_cache *s, do { tid = this_cpu_read(s->cpu_slab->tid); c = raw_cpu_ptr(s->cpu_slab); - } while (IS_ENABLED(CONFIG_PREEMPT) && unlikely(tid != c->tid)); + } while (IS_ENABLED(CONFIG_PREEMPT) && + unlikely(tid != READ_ONCE(c->tid))); /* Same with comment on barrier() in slab_alloc_node() */ barrier(); From cfa869438282be84ad4110bba5027ef1fbbe71e4 Mon Sep 17 00:00:00 2001 From: Laura Abbott Date: Wed, 25 Mar 2015 15:55:26 -0700 Subject: [PATCH 107/170] mm/page_alloc.c: call kernel_map_pages in unset_migrateype_isolate Commit 3c605096d315 ("mm/page_alloc: restrict max order of merging on isolated pageblock") changed the logic of unset_migratetype_isolate to check the buddy allocator and explicitly call __free_pages to merge. The page that is being freed in this path never had prep_new_page called so set_page_refcounted is called explicitly but there is no call to kernel_map_pages. With the default kernel_map_pages this is mostly harmless but if kernel_map_pages does any manipulation of the page tables (unmapping or setting pages to read only) this may trigger a fault: alloc_contig_range test_pages_isolated(ceb00, ced00) failed Unable to handle kernel paging request at virtual address ffffffc0cec00000 pgd = ffffffc045fc4000 [ffffffc0cec00000] *pgd=0000000000000000 Internal error: Oops: 9600004f [#1] PREEMPT SMP Modules linked in: exfatfs CPU: 1 PID: 23237 Comm: TimedEventQueue Not tainted 3.10.49-gc72ad36-dirty #1 task: ffffffc03de52100 ti: ffffffc015388000 task.ti: ffffffc015388000 PC is at memset+0xc8/0x1c0 LR is at kernel_map_pages+0x1ec/0x244 Fix this by calling kernel_map_pages to ensure the page is set in the page table properly Fixes: 3c605096d315 ("mm/page_alloc: restrict max order of merging on isolated pageblock") Signed-off-by: Laura Abbott Cc: Naoya Horiguchi Cc: Mel Gorman Acked-by: Rik van Riel Cc: Yasuaki Ishimatsu Cc: Zhang Yanfei Cc: Xishi Qiu Cc: Vladimir Davydov Acked-by: Joonsoo Kim Cc: Gioh Kim Cc: Michal Nazarewicz Cc: Marek Szyprowski Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_isolation.c | 1 + 1 file changed, 1 insertion(+) diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 72f5ac381ab3..755a42c76eb4 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -103,6 +103,7 @@ void unset_migratetype_isolate(struct page *page, unsigned migratetype) if (!is_migrate_isolate_page(buddy)) { __isolate_free_page(page, order); + kernel_map_pages(page, (1 << order), 1); set_page_refcounted(page); isolated_page = page; } From 3d5d472cf55d1be091e8a145f80602bf435ece85 Mon Sep 17 00:00:00 2001 From: Taesoo Kim Date: Wed, 25 Mar 2015 15:55:29 -0700 Subject: [PATCH 108/170] fs/affs/file.c: unlock/release page on error When affs_bread_ino() fails, correctly unlock the page and release the page cache with proper error value. All write_end() should unlock/release the page that was locked by write_beg(). Signed-off-by: Taesoo Kim Cc: Fabian Frederick Cc: Al Viro Cc: Geert Uytterhoeven Cc: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/affs/file.c | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) diff --git a/fs/affs/file.c b/fs/affs/file.c index d2468bf95669..a91795e01a7f 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -699,8 +699,10 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping, boff = tmp % bsize; if (boff) { bh = affs_bread_ino(inode, bidx, 0); - if (IS_ERR(bh)) - return PTR_ERR(bh); + if (IS_ERR(bh)) { + written = PTR_ERR(bh); + goto err_first_bh; + } tmp = min(bsize - boff, to - from); BUG_ON(boff + tmp > bsize || tmp > bsize); memcpy(AFFS_DATA(bh) + boff, data + from, tmp); @@ -712,14 +714,16 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping, bidx++; } else if (bidx) { bh = affs_bread_ino(inode, bidx - 1, 0); - if (IS_ERR(bh)) - return PTR_ERR(bh); + if (IS_ERR(bh)) { + written = PTR_ERR(bh); + goto err_first_bh; + } } while (from + bsize <= to) { prev_bh = bh; bh = affs_getemptyblk_ino(inode, bidx); if (IS_ERR(bh)) - goto out; + goto err_bh; memcpy(AFFS_DATA(bh), data + from, bsize); if (buffer_new(bh)) { AFFS_DATA_HEAD(bh)->ptype = cpu_to_be32(T_DATA); @@ -751,7 +755,7 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping, prev_bh = bh; bh = affs_bread_ino(inode, bidx, 1); if (IS_ERR(bh)) - goto out; + goto err_bh; tmp = min(bsize, to - from); BUG_ON(tmp > bsize); memcpy(AFFS_DATA(bh), data + from, tmp); @@ -790,12 +794,13 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping, if (tmp > inode->i_size) inode->i_size = AFFS_I(inode)->mmu_private = tmp; +err_first_bh: unlock_page(page); page_cache_release(page); return written; -out: +err_bh: bh = prev_bh; if (!written) written = PTR_ERR(bh); From 1f31e1b1963c240ced453489730bdfc9b0110ceb Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Wed, 25 Mar 2015 15:55:31 -0700 Subject: [PATCH 109/170] MAINTAINERS: add Jan as DMI/SMBIOS support maintainer I am familiar with these drivers and I care about them so let me add myself as their maintainer. Signed-off-by: Jean Delvare Acked-by: Matt Fleming Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- MAINTAINERS | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 12ebef95224d..88c09ca2584f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3252,6 +3252,13 @@ S: Maintained F: Documentation/hwmon/dme1737 F: drivers/hwmon/dme1737.c +DMI/SMBIOS SUPPORT +M: Jean Delvare +S: Maintained +F: drivers/firmware/dmi-id.c +F: drivers/firmware/dmi_scan.c +F: include/linux/dmi.h + DOCKING STATION DRIVER M: Shaohua Li L: linux-acpi@vger.kernel.org From 98cf21c61a7f5419d82f847c4d77bf6e96a76f5f Mon Sep 17 00:00:00 2001 From: Sergei Antonov Date: Wed, 25 Mar 2015 15:55:34 -0700 Subject: [PATCH 110/170] hfsplus: fix B-tree corruption after insertion at position 0 Fix B-tree corruption when a new record is inserted at position 0 in the node in hfs_brec_insert(). In this case a hfs_brec_update_parent() is called to update the parent index node (if exists) and it is passed hfs_find_data with a search_key containing a newly inserted key instead of the key to be updated. This results in an inconsistent index node. The bug reproduces on my machine after an extents overflow record for the catalog file (CNID=4) is inserted into the extents overflow B-tree. Because of a low (reserved) value of CNID=4, it has to become the first record in the first leaf node. The resulting first leaf node is correct: ---------------------------------------------------- | key0.CNID=4 | key1.CNID=123 | key2.CNID=456, ... | ---------------------------------------------------- But the parent index key0 still contains the previous key CNID=123: ----------------------- | key0.CNID=123 | ... | ----------------------- A change in hfs_brec_insert() makes hfs_brec_update_parent() work correctly by preventing it from getting fd->record=-1 value from __hfs_brec_find(). Along the way, I removed duplicate code with unification of the if condition. The resulting code is equivalent to the original code because node is never 0. Also hfs_brec_update_parent() will now return an error after getting a negative fd->record value. However, the return value of hfs_brec_update_parent() is not checked anywhere in the file and I'm leaving it unchanged by this patch. brec.c lacks error checking after some other calls too, but this issue is of less importance than the one being fixed by this patch. Signed-off-by: Sergei Antonov Cc: Joe Perches Reviewed-by: Vyacheslav Dubeyko Acked-by: Hin-Tak Leung Cc: Anton Altaparmakov Cc: Al Viro Cc: Christoph Hellwig Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hfsplus/brec.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/fs/hfsplus/brec.c b/fs/hfsplus/brec.c index 6e560d56094b..754fdf8c6356 100644 --- a/fs/hfsplus/brec.c +++ b/fs/hfsplus/brec.c @@ -131,13 +131,16 @@ int hfs_brec_insert(struct hfs_find_data *fd, void *entry, int entry_len) hfs_bnode_write(node, entry, data_off + key_len, entry_len); hfs_bnode_dump(node); - if (new_node) { - /* update parent key if we inserted a key - * at the start of the first node - */ - if (!rec && new_node != node) - hfs_brec_update_parent(fd); + /* + * update parent key if we inserted a key + * at the start of the node and it is not the new node + */ + if (!rec && new_node != node) { + hfs_bnode_read_key(node, fd->search_key, data_off + size); + hfs_brec_update_parent(fd); + } + if (new_node) { hfs_bnode_put(fd->bnode); if (!new_node->parent) { hfs_btree_inc_height(tree); @@ -168,9 +171,6 @@ int hfs_brec_insert(struct hfs_find_data *fd, void *entry, int entry_len) goto again; } - if (!rec) - hfs_brec_update_parent(fd); - return 0; } @@ -370,6 +370,8 @@ static int hfs_brec_update_parent(struct hfs_find_data *fd) if (IS_ERR(parent)) return PTR_ERR(parent); __hfs_brec_find(parent, fd, hfs_find_rec_by_key); + if (fd->record < 0) + return -ENOENT; hfs_bnode_dump(parent); rec = fd->record; From bea66fbd11af1ca98ae26855eea41eda8582923e Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 25 Mar 2015 15:55:37 -0700 Subject: [PATCH 111/170] mm: numa: group related processes based on VMA flags instead of page table flags These are three follow-on patches based on the xfsrepair workload Dave Chinner reported was problematic in 4.0-rc1 due to changes in page table management -- https://lkml.org/lkml/2015/3/1/226. Much of the problem was reduced by commit 53da3bc2ba9e ("mm: fix up numa read-only thread grouping logic") and commit ba68bc0115eb ("mm: thp: Return the correct value for change_huge_pmd"). It was known that the performance in 3.19 was still better even if is far less safe. This series aims to restore the performance without compromising on safety. For the test of this mail, I'm comparing 3.19 against 4.0-rc4 and the three patches applied on top autonumabench 3.19.0 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 vanilla vanilla vmwrite-v5r8 preserve-v5r8 slowscan-v5r8 Time System-NUMA01 124.00 ( 0.00%) 161.86 (-30.53%) 107.13 ( 13.60%) 103.13 ( 16.83%) 145.01 (-16.94%) Time System-NUMA01_THEADLOCAL 115.54 ( 0.00%) 107.64 ( 6.84%) 131.87 (-14.13%) 83.30 ( 27.90%) 92.35 ( 20.07%) Time System-NUMA02 9.35 ( 0.00%) 10.44 (-11.66%) 8.95 ( 4.28%) 10.72 (-14.65%) 8.16 ( 12.73%) Time System-NUMA02_SMT 3.87 ( 0.00%) 4.63 (-19.64%) 4.57 (-18.09%) 3.99 ( -3.10%) 3.36 ( 13.18%) Time Elapsed-NUMA01 570.06 ( 0.00%) 567.82 ( 0.39%) 515.78 ( 9.52%) 517.26 ( 9.26%) 543.80 ( 4.61%) Time Elapsed-NUMA01_THEADLOCAL 393.69 ( 0.00%) 384.83 ( 2.25%) 384.10 ( 2.44%) 384.31 ( 2.38%) 380.73 ( 3.29%) Time Elapsed-NUMA02 49.09 ( 0.00%) 49.33 ( -0.49%) 48.86 ( 0.47%) 48.78 ( 0.63%) 50.94 ( -3.77%) Time Elapsed-NUMA02_SMT 47.51 ( 0.00%) 47.15 ( 0.76%) 47.98 ( -0.99%) 48.12 ( -1.28%) 49.56 ( -4.31%) 3.19.0 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 vanilla vanillavmwrite-v5r8preserve-v5r8slowscan-v5r8 User 46334.60 46391.94 44383.95 43971.89 44372.12 System 252.84 284.66 252.61 201.24 249.00 Elapsed 1062.14 1050.96 998.68 1000.94 1026.78 Overall the system CPU usage is comparable and the test is naturally a bit variable. The slowing of the scanner hurts numa01 but on this machine it is an adverse workload and patches that dramatically help it often hurt absolutely everything else. Due to patch 2, the fault activity is interesting 3.19.0 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 vanilla vanillavmwrite-v5r8preserve-v5r8slowscan-v5r8 Minor Faults 2097811 2656646 2597249 1981230 1636841 Major Faults 362 450 365 364 365 Note the impact preserving the write bit across protection updates and fault reduces faults. NUMA alloc hit 1229008 1217015 1191660 1178322 1199681 NUMA alloc miss 0 0 0 0 0 NUMA interleave hit 0 0 0 0 0 NUMA alloc local 1228514 1216317 1190871 1177448 1199021 NUMA base PTE updates 245706197 240041607 238195516 244704842 115012800 NUMA huge PMD updates 479530 468448 464868 477573 224487 NUMA page range updates 491225557 479886983 476207932 489222218 229950144 NUMA hint faults 659753 656503 641678 656926 294842 NUMA hint local faults 381604 373963 360478 337585 186249 NUMA hint local percent 57 56 56 51 63 NUMA pages migrated 5412140 6374899 6266530 5277468 5755096 AutoNUMA cost 5121% 5083% 4994% 5097% 2388% Here the impact of slowing the PTE scanner on migratrion failures is obvious as "NUMA base PTE updates" and "NUMA huge PMD updates" are massively reduced even though the headline performance is very similar. As xfsrepair was the reported workload here is the impact of the series on it. xfsrepair 3.19.0 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 vanilla vanilla vmwrite-v5r8 preserve-v5r8 slowscan-v5r8 Min real-fsmark 1183.29 ( 0.00%) 1165.73 ( 1.48%) 1152.78 ( 2.58%) 1153.64 ( 2.51%) 1177.62 ( 0.48%) Min syst-fsmark 4107.85 ( 0.00%) 4027.75 ( 1.95%) 3986.74 ( 2.95%) 3979.16 ( 3.13%) 4048.76 ( 1.44%) Min real-xfsrepair 441.51 ( 0.00%) 463.96 ( -5.08%) 449.50 ( -1.81%) 440.08 ( 0.32%) 439.87 ( 0.37%) Min syst-xfsrepair 195.76 ( 0.00%) 278.47 (-42.25%) 262.34 (-34.01%) 203.70 ( -4.06%) 143.64 ( 26.62%) Amean real-fsmark 1188.30 ( 0.00%) 1177.34 ( 0.92%) 1157.97 ( 2.55%) 1158.21 ( 2.53%) 1182.22 ( 0.51%) Amean syst-fsmark 4111.37 ( 0.00%) 4055.70 ( 1.35%) 3987.19 ( 3.02%) 3998.72 ( 2.74%) 4061.69 ( 1.21%) Amean real-xfsrepair 450.88 ( 0.00%) 468.32 ( -3.87%) 454.14 ( -0.72%) 442.36 ( 1.89%) 440.59 ( 2.28%) Amean syst-xfsrepair 199.66 ( 0.00%) 290.60 (-45.55%) 277.20 (-38.84%) 204.68 ( -2.51%) 150.55 ( 24.60%) Stddev real-fsmark 4.12 ( 0.00%) 10.82 (-162.29%) 4.14 ( -0.28%) 5.98 (-45.05%) 4.60 (-11.53%) Stddev syst-fsmark 2.63 ( 0.00%) 20.32 (-671.82%) 0.37 ( 85.89%) 16.47 (-525.59%) 15.05 (-471.79%) Stddev real-xfsrepair 6.87 ( 0.00%) 4.55 ( 33.75%) 3.46 ( 49.58%) 1.78 ( 74.12%) 0.52 ( 92.50%) Stddev syst-xfsrepair 3.02 ( 0.00%) 10.30 (-241.37%) 13.17 (-336.37%) 0.71 ( 76.63%) 5.00 (-65.61%) CoeffVar real-fsmark 0.35 ( 0.00%) 0.92 (-164.73%) 0.36 ( -2.91%) 0.52 (-48.82%) 0.39 (-12.10%) CoeffVar syst-fsmark 0.06 ( 0.00%) 0.50 (-682.41%) 0.01 ( 85.45%) 0.41 (-543.22%) 0.37 (-478.78%) CoeffVar real-xfsrepair 1.52 ( 0.00%) 0.97 ( 36.21%) 0.76 ( 49.94%) 0.40 ( 73.62%) 0.12 ( 92.33%) CoeffVar syst-xfsrepair 1.51 ( 0.00%) 3.54 (-134.54%) 4.75 (-214.31%) 0.34 ( 77.20%) 3.32 (-119.63%) Max real-fsmark 1193.39 ( 0.00%) 1191.77 ( 0.14%) 1162.90 ( 2.55%) 1166.66 ( 2.24%) 1188.50 ( 0.41%) Max syst-fsmark 4114.18 ( 0.00%) 4075.45 ( 0.94%) 3987.65 ( 3.08%) 4019.45 ( 2.30%) 4082.80 ( 0.76%) Max real-xfsrepair 457.80 ( 0.00%) 474.60 ( -3.67%) 457.82 ( -0.00%) 444.42 ( 2.92%) 441.03 ( 3.66%) Max syst-xfsrepair 203.11 ( 0.00%) 303.65 (-49.50%) 294.35 (-44.92%) 205.33 ( -1.09%) 155.28 ( 23.55%) The really relevant lines as syst-xfsrepair which is the system CPU usage when running xfsrepair. Note that on my machine the overhead was 45% higher on 4.0-rc4 which may be part of what Dave is seeing. Once we preserve the write bit across faults, it's only 2.51% higher on average. With the full series applied, system CPU usage is 24.6% lower on average. Again, the impact of preserving the write bit on minor faults is obvious and the impact of slowing scanning after migration failures is obvious on the PTE updates. Note also that the number of pages migrated is much reduced even though the headline performance is comparable. 3.19.0 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 vanilla vanillavmwrite-v5r8preserve-v5r8slowscan-v5r8 Minor Faults 153466827 254507978 249163829 153501373 105737890 Major Faults 610 702 690 649 724 NUMA base PTE updates 217735049 210756527 217729596 216937111 144344993 NUMA huge PMD updates 129294 85044 106921 127246 79887 NUMA pages migrated 21938995 29705270 28594162 22687324 16258075 3.19.0 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 vanilla vanillavmwrite-v5r8preserve-v5r8slowscan-v5r8 Mean sdb-avgqusz 13.47 2.54 2.55 2.47 2.49 Mean sdb-avgrqsz 202.32 140.22 139.50 139.02 138.12 Mean sdb-await 25.92 5.09 5.33 5.02 5.22 Mean sdb-r_await 4.71 0.19 0.83 0.51 0.11 Mean sdb-w_await 104.13 5.21 5.38 5.05 5.32 Mean sdb-svctm 0.59 0.13 0.14 0.13 0.14 Mean sdb-rrqm 0.16 0.00 0.00 0.00 0.00 Mean sdb-wrqm 3.59 1799.43 1826.84 1812.21 1785.67 Max sdb-avgqusz 111.06 12.13 14.05 11.66 15.60 Max sdb-avgrqsz 255.60 190.34 190.01 187.33 191.78 Max sdb-await 168.24 39.28 49.22 44.64 65.62 Max sdb-r_await 660.00 52.00 280.00 76.00 12.00 Max sdb-w_await 7804.00 39.28 49.22 44.64 65.62 Max sdb-svctm 4.00 2.82 2.86 1.98 2.84 Max sdb-rrqm 8.30 0.00 0.00 0.00 0.00 Max sdb-wrqm 34.20 5372.80 5278.60 5386.60 5546.15 FWIW, I also checked SPECjbb in different configurations but it's similar observations -- minor faults lower, PTE update activity lower and performance is roughly comparable against 3.19. This patch (of 3): Threads that share writable data within pages are grouped together as related tasks. This decision is based on whether the PTE is marked dirty which is subject to timing races between the PTE scanner update and when the application writes the page. If the page is file-backed, then background flushes and sync also affect placement. This is unpredictable behaviour which is impossible to reason about so this patch makes grouping decisions based on the VMA flags. Signed-off-by: Mel Gorman Reported-by: Dave Chinner Tested-by: Dave Chinner Cc: Ingo Molnar Cc: Aneesh Kumar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/huge_memory.c | 13 ++----------- mm/memory.c | 19 +++++++++++-------- 2 files changed, 13 insertions(+), 19 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 626e93db28ba..2f12e9fcf1a2 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1291,17 +1291,8 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, flags |= TNF_FAULT_LOCAL; } - /* - * Avoid grouping on DSO/COW pages in specific and RO pages - * in general, RO pages shouldn't hurt as much anyway since - * they can be in shared cache state. - * - * FIXME! This checks "pmd_dirty()" as an approximation of - * "is this a read-only page", since checking "pmd_write()" - * is even more broken. We haven't actually turned this into - * a writable page, so pmd_write() will always be false. - */ - if (!pmd_dirty(pmd)) + /* See similar comment in do_numa_page for explanation */ + if (!(vma->vm_flags & VM_WRITE)) flags |= TNF_NO_GROUP; /* diff --git a/mm/memory.c b/mm/memory.c index 411144f977b1..20beb6647dba 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3069,16 +3069,19 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, } /* - * Avoid grouping on DSO/COW pages in specific and RO pages - * in general, RO pages shouldn't hurt as much anyway since - * they can be in shared cache state. + * Avoid grouping on RO pages in general. RO pages shouldn't hurt as + * much anyway since they can be in shared cache state. This misses + * the case where a mapping is writable but the process never writes + * to it but pte_write gets cleared during protection updates and + * pte_dirty has unpredictable behaviour between PTE scan updates, + * background writeback, dirty balancing and application behaviour. * - * FIXME! This checks "pmd_dirty()" as an approximation of - * "is this a read-only page", since checking "pmd_write()" - * is even more broken. We haven't actually turned this into - * a writable page, so pmd_write() will always be false. + * TODO: Note that the ideal here would be to avoid a situation where a + * NUMA fault is taken immediately followed by a write fault in + * some cases which would have lower overhead overall but would be + * invasive as the fault paths would need to be unified. */ - if (!pte_dirty(pte)) + if (!(vma->vm_flags & VM_WRITE)) flags |= TNF_NO_GROUP; /* From b191f9b106ea1a24a711dbebb2925d3313da5852 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 25 Mar 2015 15:55:40 -0700 Subject: [PATCH 112/170] mm: numa: preserve PTE write permissions across a NUMA hinting fault Protecting a PTE to trap a NUMA hinting fault clears the writable bit and further faults are needed after trapping a NUMA hinting fault to set the writable bit again. This patch preserves the writable bit when trapping NUMA hinting faults. The impact is obvious from the number of minor faults trapped during the basis balancing benchmark and the system CPU usage; autonumabench 4.0.0-rc4 4.0.0-rc4 baseline preserve Time System-NUMA01 107.13 ( 0.00%) 103.13 ( 3.73%) Time System-NUMA01_THEADLOCAL 131.87 ( 0.00%) 83.30 ( 36.83%) Time System-NUMA02 8.95 ( 0.00%) 10.72 (-19.78%) Time System-NUMA02_SMT 4.57 ( 0.00%) 3.99 ( 12.69%) Time Elapsed-NUMA01 515.78 ( 0.00%) 517.26 ( -0.29%) Time Elapsed-NUMA01_THEADLOCAL 384.10 ( 0.00%) 384.31 ( -0.05%) Time Elapsed-NUMA02 48.86 ( 0.00%) 48.78 ( 0.16%) Time Elapsed-NUMA02_SMT 47.98 ( 0.00%) 48.12 ( -0.29%) 4.0.0-rc4 4.0.0-rc4 baseline preserve User 44383.95 43971.89 System 252.61 201.24 Elapsed 998.68 1000.94 Minor Faults 2597249 1981230 Major Faults 365 364 There is a similar drop in system CPU usage using Dave Chinner's xfsrepair workload 4.0.0-rc4 4.0.0-rc4 baseline preserve Amean real-xfsrepair 454.14 ( 0.00%) 442.36 ( 2.60%) Amean syst-xfsrepair 277.20 ( 0.00%) 204.68 ( 26.16%) The patch looks hacky but the alternatives looked worse. The tidest was to rewalk the page tables after a hinting fault but it was more complex than this approach and the performance was worse. It's not generally safe to just mark the page writable during the fault if it's a write fault as it may have been read-only for COW so that approach was discarded. Signed-off-by: Mel Gorman Reported-by: Dave Chinner Tested-by: Dave Chinner Cc: Ingo Molnar Cc: Aneesh Kumar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/huge_memory.c | 9 ++++++++- mm/memory.c | 8 +++----- mm/mprotect.c | 3 +++ 3 files changed, 14 insertions(+), 6 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 2f12e9fcf1a2..0a42d1521aa4 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1260,6 +1260,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, int target_nid, last_cpupid = -1; bool page_locked; bool migrated = false; + bool was_writable; int flags = 0; /* A PROT_NONE fault should not end up here */ @@ -1354,7 +1355,10 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, goto out; clear_pmdnuma: BUG_ON(!PageLocked(page)); + was_writable = pmd_write(pmd); pmd = pmd_modify(pmd, vma->vm_page_prot); + if (was_writable) + pmd = pmd_mkwrite(pmd); set_pmd_at(mm, haddr, pmdp, pmd); update_mmu_cache_pmd(vma, addr, pmdp); unlock_page(page); @@ -1478,6 +1482,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { pmd_t entry; + bool preserve_write = prot_numa && pmd_write(*pmd); ret = 1; /* @@ -1493,9 +1498,11 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, if (!prot_numa || !pmd_protnone(*pmd)) { entry = pmdp_get_and_clear_notify(mm, addr, pmd); entry = pmd_modify(entry, newprot); + if (preserve_write) + entry = pmd_mkwrite(entry); ret = HPAGE_PMD_NR; set_pmd_at(mm, addr, pmd, entry); - BUG_ON(pmd_write(entry)); + BUG_ON(!preserve_write && pmd_write(entry)); } spin_unlock(ptl); } diff --git a/mm/memory.c b/mm/memory.c index 20beb6647dba..d20e12da3a3c 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3035,6 +3035,7 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, int last_cpupid; int target_nid; bool migrated = false; + bool was_writable = pte_write(pte); int flags = 0; /* A PROT_NONE fault should not end up here */ @@ -3059,6 +3060,8 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, /* Make it present again */ pte = pte_modify(pte, vma->vm_page_prot); pte = pte_mkyoung(pte); + if (was_writable) + pte = pte_mkwrite(pte); set_pte_at(mm, addr, ptep, pte); update_mmu_cache(vma, addr, ptep); @@ -3075,11 +3078,6 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, * to it but pte_write gets cleared during protection updates and * pte_dirty has unpredictable behaviour between PTE scan updates, * background writeback, dirty balancing and application behaviour. - * - * TODO: Note that the ideal here would be to avoid a situation where a - * NUMA fault is taken immediately followed by a write fault in - * some cases which would have lower overhead overall but would be - * invasive as the fault paths would need to be unified. */ if (!(vma->vm_flags & VM_WRITE)) flags |= TNF_NO_GROUP; diff --git a/mm/mprotect.c b/mm/mprotect.c index 44727811bf4c..88584838e704 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -75,6 +75,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, oldpte = *pte; if (pte_present(oldpte)) { pte_t ptent; + bool preserve_write = prot_numa && pte_write(oldpte); /* * Avoid trapping faults against the zero or KSM @@ -94,6 +95,8 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, ptent = ptep_modify_prot_start(mm, addr, pte); ptent = pte_modify(ptent, newprot); + if (preserve_write) + ptent = pte_mkwrite(ptent); /* Avoid taking write faults for known dirty pages */ if (dirty_accountable && pte_dirty(ptent) && From 074c238177a75f5e79af3b2cb6a84e54823ef950 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 25 Mar 2015 15:55:42 -0700 Subject: [PATCH 113/170] mm: numa: slow PTE scan rate if migration failures occur Dave Chinner reported the following on https://lkml.org/lkml/2015/3/1/226 Across the board the 4.0-rc1 numbers are much slower, and the degradation is far worse when using the large memory footprint configs. Perf points straight at the cause - this is from 4.0-rc1 on the "-o bhash=101073" config: - 56.07% 56.07% [kernel] [k] default_send_IPI_mask_sequence_phys - default_send_IPI_mask_sequence_phys - 99.99% physflat_send_IPI_mask - 99.37% native_send_call_func_ipi smp_call_function_many - native_flush_tlb_others - 99.85% flush_tlb_page ptep_clear_flush try_to_unmap_one rmap_walk try_to_unmap migrate_pages migrate_misplaced_page - handle_mm_fault - 99.73% __do_page_fault trace_do_page_fault do_async_page_fault + async_page_fault 0.63% native_send_call_func_single_ipi generic_exec_single smp_call_function_single This is showing excessive migration activity even though excessive migrations are meant to get throttled. Normally, the scan rate is tuned on a per-task basis depending on the locality of faults. However, if migrations fail for any reason then the PTE scanner may scan faster if the faults continue to be remote. This means there is higher system CPU overhead and fault trapping at exactly the time we know that migrations cannot happen. This patch tracks when migration failures occur and slows the PTE scanner. Signed-off-by: Mel Gorman Reported-by: Dave Chinner Tested-by: Dave Chinner Cc: Ingo Molnar Cc: Aneesh Kumar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 9 +++++---- kernel/sched/fair.c | 8 ++++++-- mm/huge_memory.c | 3 ++- mm/memory.c | 3 ++- 4 files changed, 15 insertions(+), 8 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 6d77432e14ff..a419b65770d6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1625,11 +1625,11 @@ struct task_struct { /* * numa_faults_locality tracks if faults recorded during the last - * scan window were remote/local. The task scan period is adapted - * based on the locality of the faults with different weights - * depending on whether they were shared or private faults + * scan window were remote/local or failed to migrate. The task scan + * period is adapted based on the locality of the faults with different + * weights depending on whether they were shared or private faults */ - unsigned long numa_faults_locality[2]; + unsigned long numa_faults_locality[3]; unsigned long numa_pages_migrated; #endif /* CONFIG_NUMA_BALANCING */ @@ -1719,6 +1719,7 @@ struct task_struct { #define TNF_NO_GROUP 0x02 #define TNF_SHARED 0x04 #define TNF_FAULT_LOCAL 0x08 +#define TNF_MIGRATE_FAIL 0x10 #ifdef CONFIG_NUMA_BALANCING extern void task_numa_fault(int last_node, int node, int pages, int flags); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 7ce18f3c097a..bcfe32088b37 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1609,9 +1609,11 @@ static void update_task_scan_period(struct task_struct *p, /* * If there were no record hinting faults then either the task is * completely idle or all activity is areas that are not of interest - * to automatic numa balancing. Scan slower + * to automatic numa balancing. Related to that, if there were failed + * migration then it implies we are migrating too quickly or the local + * node is overloaded. In either case, scan slower */ - if (local + shared == 0) { + if (local + shared == 0 || p->numa_faults_locality[2]) { p->numa_scan_period = min(p->numa_scan_period_max, p->numa_scan_period << 1); @@ -2080,6 +2082,8 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) if (migrated) p->numa_pages_migrated += pages; + if (flags & TNF_MIGRATE_FAIL) + p->numa_faults_locality[2] += pages; p->numa_faults[task_faults_idx(NUMA_MEMBUF, mem_node, priv)] += pages; p->numa_faults[task_faults_idx(NUMA_CPUBUF, cpu_node, priv)] += pages; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 0a42d1521aa4..51b3e7c64622 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1350,7 +1350,8 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, if (migrated) { flags |= TNF_MIGRATED; page_nid = target_nid; - } + } else + flags |= TNF_MIGRATE_FAIL; goto out; clear_pmdnuma: diff --git a/mm/memory.c b/mm/memory.c index d20e12da3a3c..97839f5c8c30 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3103,7 +3103,8 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, if (migrated) { page_nid = target_nid; flags |= TNF_MIGRATED; - } + } else + flags |= TNF_MIGRATE_FAIL; out: if (page_nid != -1) From b7b04004ecd9e58cdc6c6ff92f251d5ac5c0adb2 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 25 Mar 2015 15:55:45 -0700 Subject: [PATCH 114/170] mm: numa: mark huge PTEs young when clearing NUMA hinting faults Base PTEs are marked young when the NUMA hinting information is cleared but the same does not happen for huge pages which this patch addresses. Note that migrated pages are not marked young as the base page migration code does not assume that migrated pages have been referenced. This could be addressed but beyond the scope of this series which is aimed at Dave Chinners shrink workload that is unlikely to be affected by this issue. Signed-off-by: Mel Gorman Cc: Dave Chinner Cc: Ingo Molnar Cc: Aneesh Kumar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/huge_memory.c | 1 + 1 file changed, 1 insertion(+) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 51b3e7c64622..6817b0350c71 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1358,6 +1358,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, BUG_ON(!PageLocked(page)); was_writable = pmd_write(pmd); pmd = pmd_modify(pmd, vma->vm_page_prot); + pmd = pmd_mkyoung(pmd); if (was_writable) pmd = pmd_mkwrite(pmd); set_pmd_at(mm, haddr, pmdp, pmd); From c5952338bfc234e54deda45b7228f610a545e28a Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 23 Mar 2015 10:53:42 -0400 Subject: [PATCH 115/170] nfsd: return correct openowner when there is a race to put one in the hash alloc_init_open_stateowner can return an already freed entry if there is a race to put openowners in the hashtable. In commit 7ffb588086e9, we changed it so that we allocate and initialize an openowner, and then check to see if a matching one got stuffed into the hashtable in the meantime. If it did, then we free the one we just allocated and take a reference on the one already there. There is a bug here though. The code will then return the pointer to the one that was allocated (and has now been freed). This wasn't evident before as this race almost never occurred. The Linux kernel client used to serialize requests for a single openowner. That has changed now with v4.0 kernels, and this race can now easily occur. Fixes: 7ffb588086e9 Cc: # v3.17+ Cc: Trond Myklebust Reported-by: Christoph Hellwig Reviewed-by: Christoph Hellwig Signed-off-by: Jeff Layton Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index d2f2c37dc2db..cf29d1a698b3 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -3221,7 +3221,7 @@ alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open, } else nfs4_free_openowner(&oo->oo_owner); spin_unlock(&clp->cl_lock); - return oo; + return ret; } static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp, struct nfsd4_open *open) { From 340f0ba1c6c8412aa35fd6476044836b84361ea6 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Mon, 23 Mar 2015 11:02:30 -0400 Subject: [PATCH 116/170] nfsd: return correct lockowner when there is a race on hash insert alloc_init_lock_stateowner can return an already freed entry if there is a race to put openowners in the hashtable. Noticed by inspection after Jeff Layton fixed the same bug for open owners. Depending on client behavior, this one may be trickier to trigger in practice. Fixes: c58c6610ec24 "nfsd: Protect adding/removing lock owners using client_lock" Cc: Cc: Trond Myklebust Acked-by: Jeff Layton Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index cf29d1a698b3..8ba1d888f1e6 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -5062,7 +5062,7 @@ alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp, } else nfs4_free_lockowner(&lo->lo_owner); spin_unlock(&clp->cl_lock); - return lo; + return ret; } static void From 853695230e9847445ad42c330d023fca2324fd56 Mon Sep 17 00:00:00 2001 From: Kinglong Mee Date: Sun, 22 Mar 2015 22:16:40 +0800 Subject: [PATCH 117/170] NFSD: Printk blocklayout length and offset as format 0x%llx When testing pnfs with nfsd_debug on, nfsd print a negative number of layout length and foff in nfsd4_block_proc_layoutget as, "GET: -xxxx:-xxx 2" Signed-off-by: Kinglong Mee Reviewed-by: Christoph Hellwig Signed-off-by: J. Bruce Fields --- fs/nfsd/blocklayout.c | 2 +- fs/nfsd/blocklayoutxdr.c | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index cdbc78c72542..03d647bf195d 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -137,7 +137,7 @@ nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp, seg->offset = iomap.offset; seg->length = iomap.length; - dprintk("GET: %lld:%lld %d\n", bex->foff, bex->len, bex->es); + dprintk("GET: 0x%llx:0x%llx %d\n", bex->foff, bex->len, bex->es); return 0; out_error: diff --git a/fs/nfsd/blocklayoutxdr.c b/fs/nfsd/blocklayoutxdr.c index 9da89fddab33..9aa2796da90d 100644 --- a/fs/nfsd/blocklayoutxdr.c +++ b/fs/nfsd/blocklayoutxdr.c @@ -122,19 +122,19 @@ nfsd4_block_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp, p = xdr_decode_hyper(p, &bex.foff); if (bex.foff & (block_size - 1)) { - dprintk("%s: unaligned offset %lld\n", + dprintk("%s: unaligned offset 0x%llx\n", __func__, bex.foff); goto fail; } p = xdr_decode_hyper(p, &bex.len); if (bex.len & (block_size - 1)) { - dprintk("%s: unaligned length %lld\n", + dprintk("%s: unaligned length 0x%llx\n", __func__, bex.foff); goto fail; } p = xdr_decode_hyper(p, &bex.soff); if (bex.soff & (block_size - 1)) { - dprintk("%s: unaligned disk offset %lld\n", + dprintk("%s: unaligned disk offset 0x%llx\n", __func__, bex.soff); goto fail; } From 376675daeac3dc0e39b84ca90f0bdc41a9d44d46 Mon Sep 17 00:00:00 2001 From: Kinglong Mee Date: Sun, 22 Mar 2015 22:17:10 +0800 Subject: [PATCH 118/170] NFSD: Take care the return value from nfsd4_encode_stateid Signed-off-by: Kinglong Mee Reviewed-by: Christoph Hellwig Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4xdr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index c76654c3605f..5fb7e78169a6 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -4135,7 +4135,7 @@ nfsd4_encode_layoutreturn(struct nfsd4_compoundres *resp, __be32 nfserr, return nfserr_resource; *p++ = cpu_to_be32(lrp->lrs_present); if (lrp->lrs_present) - nfsd4_encode_stateid(xdr, &lrp->lr_sid); + return nfsd4_encode_stateid(xdr, &lrp->lr_sid); return nfs_ok; } #endif /* CONFIG_NFSD_PNFS */ From 7890203da2cb9b861dae9bdb88f882f3e03baec9 Mon Sep 17 00:00:00 2001 From: Kinglong Mee Date: Sun, 22 Mar 2015 22:17:20 +0800 Subject: [PATCH 119/170] NFSD: Fix bad update of layout in nfsd4_return_file_layout With return layout as, (seg is return layout, lo is record layout) seg->offset <= lo->offset and layout_end(seg) < layout_end(lo), nfsd should update lo's offset to seg's end, and, seg->offset > lo->offset and layout_end(seg) >= layout_end(lo), nfsd should update lo's end to seg's offset. Fixes: 9cf514ccfa ("nfsd: implement pNFS operations") Signed-off-by: Kinglong Mee Reviewed-by: Christoph Hellwig Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4layouts.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 6964613bad90..80e236bf79fc 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -440,15 +440,14 @@ nfsd4_return_file_layout(struct nfs4_layout *lp, struct nfsd4_layout_seg *seg, list_move_tail(&lp->lo_perstate, reaplist); return; } - end = seg->offset; + lo->offset = layout_end(seg); } else { /* retain the whole layout segment on a split. */ if (layout_end(seg) < end) { dprintk("%s: split not supported\n", __func__); return; } - - lo->offset = layout_end(seg); + end = seg->offset; } layout_update_len(lo, end); From 6914e1e3f63caa829431160f0f7093292daef2d5 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Thu, 26 Mar 2015 09:25:44 +0530 Subject: [PATCH 120/170] ARC: SA_SIGINFO ucontext regs off-by-one The regfile provided to SA_SIGINFO signal handler as ucontext was off by one due to pt_regs gutter cleanups in 2013. Before handling signal, user pt_regs are copied onto user_regs_struct and copied back later. Both structs are binary compatible. This was all fine until commit 2fa919045b72 (ARC: pt_regs update #2) which removed the empty stack slot at top of pt_regs (corresponding to first pad) and made the corresponding fixup in struct user_regs_struct (the pad in there was moved out of @scratch - not removed altogether as it is part of ptrace ABI) struct user_regs_struct { + long pad; struct { - long pad; long bta, lp_start, lp_end,.... } scratch; ... } This meant that now user_regs_struct was off by 1 reg w.r.t pt_regs and signal code needs to user_regs_struct.scratch to reflect it as pt_regs, which is what this commit does. This problem was hidden for 2 years, because both save/restore, despite using wrong location, were using the same location. Only an interim inspection (reproducer below) exposed the issue. void handle_segv(int signo, siginfo_t *info, void *context) { ucontext_t *uc = context; struct user_regs_struct *regs = &(uc->uc_mcontext.regs); printf("regs %x %x\n", <=== prints 7 8 (vs. 8 9) regs->scratch.r8, regs->scratch.r9); } int main() { struct sigaction sa; sa.sa_sigaction = handle_segv; sa.sa_flags = SA_SIGINFO; sigemptyset(&sa.sa_mask); sigaction(SIGSEGV, &sa, NULL); asm volatile( "mov r7, 7 \n" "mov r8, 8 \n" "mov r9, 9 \n" "mov r10, 10 \n" :::"r7","r8","r9","r10"); *((unsigned int*)0x10) = 0; } Fixes: 2fa919045b72ec892e "ARC: pt_regs update #2: Remove unused gutter at start of pt_regs" CC: Signed-off-by: Vineet Gupta --- arch/arc/kernel/signal.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c index 114234e83caa..fdd3c98dfb0f 100644 --- a/arch/arc/kernel/signal.c +++ b/arch/arc/kernel/signal.c @@ -67,7 +67,7 @@ stash_usr_regs(struct rt_sigframe __user *sf, struct pt_regs *regs, sigset_t *set) { int err; - err = __copy_to_user(&(sf->uc.uc_mcontext.regs), regs, + err = __copy_to_user(&(sf->uc.uc_mcontext.regs.scratch), regs, sizeof(sf->uc.uc_mcontext.regs.scratch)); err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(sigset_t)); @@ -83,7 +83,7 @@ static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf) if (!err) set_current_blocked(&set); - err |= __copy_from_user(regs, &(sf->uc.uc_mcontext.regs), + err |= __copy_from_user(regs, &(sf->uc.uc_mcontext.regs.scratch), sizeof(sf->uc.uc_mcontext.regs.scratch)); return err; From e4140819dadc3624accac8294881bca8a3cba4ed Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Thu, 26 Mar 2015 11:14:41 +0530 Subject: [PATCH 121/170] ARC: signal handling robustify A malicious signal handler / restorer can DOS the system by fudging the user regs saved on stack, causing weird things such as sigreturn returning to user mode PC but cpu state still being kernel mode.... Ensure that in sigreturn path status32 always has U bit; any other bogosity (gargbage PC etc) will be taken care of by normal user mode exceptions mechanisms. Reproducer signal handler: void handle_sig(int signo, siginfo_t *info, void *context) { ucontext_t *uc = context; struct user_regs_struct *regs = &(uc->uc_mcontext.regs); regs->scratch.status32 = 0; } Before the fix, kernel would go off to weeds like below: --------->8----------- [ARCLinux]$ ./signal-test Path: /signal-test CPU: 0 PID: 61 Comm: signal-test Not tainted 4.0.0-rc5+ #65 task: 8f177880 ti: 5ffe6000 task.ti: 8f15c000 [ECR ]: 0x00220200 => Invalid Write @ 0x00000010 by insn @ 0x00010698 [EFA ]: 0x00000010 [BLINK ]: 0x2007c1ee [ERET ]: 0x10698 [STAT32]: 0x00000000 : <-------- BTA: 0x00010680 SP: 0x5ffe7e48 FP: 0x00000000 LPS: 0x20003c6c LPE: 0x20003c70 LPC: 0x00000000 ... --------->8----------- Reported-by: Alexey Brodkin Cc: Signed-off-by: Vineet Gupta --- arch/arc/kernel/signal.c | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c index fdd3c98dfb0f..edda76fae83f 100644 --- a/arch/arc/kernel/signal.c +++ b/arch/arc/kernel/signal.c @@ -131,6 +131,15 @@ SYSCALL_DEFINE0(rt_sigreturn) /* Don't restart from sigreturn */ syscall_wont_restart(regs); + /* + * Ensure that sigreturn always returns to user mode (in case the + * regs saved on user stack got fudged between save and sigreturn) + * Otherwise it is easy to panic the kernel with a custom + * signal handler and/or restorer which clobberes the status32/ret + * to return to a bogus location in kernel mode. + */ + regs->status32 |= STATUS_U_MASK; + return regs->r0; badframe: @@ -229,8 +238,11 @@ setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs) /* * handler returns using sigreturn stub provided already by userpsace + * If not, nuke the process right away */ - BUG_ON(!(ksig->ka.sa.sa_flags & SA_RESTORER)); + if(!(ksig->ka.sa.sa_flags & SA_RESTORER)) + return 1; + regs->blink = (unsigned long)ksig->ka.sa.sa_restorer; /* User Stack for signal handler will be above the frame just carved */ @@ -296,12 +308,12 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) { sigset_t *oldset = sigmask_to_save(); - int ret; + int failed; /* Set up the stack frame */ - ret = setup_rt_frame(ksig, oldset, regs); + failed = setup_rt_frame(ksig, oldset, regs); - signal_setup_done(ret, ksig, 0); + signal_setup_done(failed, ksig, 0); } void do_signal(struct pt_regs *regs) From db48abf4367cb1f9e118defee0a37238638c2752 Mon Sep 17 00:00:00 2001 From: Libin Yang Date: Thu, 26 Mar 2015 13:28:39 +0800 Subject: [PATCH 122/170] ALSA: hda_intel: apply the Seperate stream_tag for Sunrise Point The total stream number of Sunrise Point's input and output stream exceeds 15, which will cause some streams do not work because of the overflow on SDxCTL.STRM field if using the legacy stream tag allocation method. This patch uses the new stream tag allocation method by add the flag AZX_DCAPS_SEPARATE_STREAM_TAG for Skylake platform. Signed-off-by: Libin Yang Signed-off-by: Takashi Iwai --- sound/pci/hda/hda_intel.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 4ca3d5d02436..a8a1e14272a1 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -1989,7 +1989,7 @@ static const struct pci_device_id azx_ids[] = { .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH }, /* Sunrise Point */ { PCI_DEVICE(0x8086, 0xa170), - .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH }, + .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE }, /* Sunrise Point-LP */ { PCI_DEVICE(0x8086, 0x9d70), .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE }, From 832a3aad1e2927b1684e7369c9f36a370e0b95da Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Wed, 18 Mar 2015 18:19:22 +0000 Subject: [PATCH 123/170] drm/i915: Keep ring->active_list and ring->requests_list consistent If we retire requests last, we may use a later seqno and so clear the requests lists without clearing the active list, leading to confusion. Hence we should retire requests first for consistency with the early return. The order used to be important as the lifecycle for the object on the active list was determined by request->seqno. However, the requests themselves are now reference counted removing the constraint from the order of retirement. Fixes regression from commit 1b5a433a4dd967b125131da42b89b5cc0d5b1f57 Author: John Harrison Date: Mon Nov 24 18:49:42 2014 +0000 drm/i915: Convert 'i915_seqno_passed' calls into 'i915_gem_request_completed ' and a WARNING: CPU: 0 PID: 1383 at drivers/gpu/drm/i915/i915_gem_evict.c:279 i915_gem_evict_vm+0x10c/0x140() WARN_ON(!list_empty(&vm->active_list)) Identified by updating WATCH_LISTS: [drm:i915_verify_lists] *ERROR* blitter ring: active list not empty, but no requests WARNING: CPU: 0 PID: 681 at drivers/gpu/drm/i915/i915_gem.c:2751 i915_gem_retire_requests_ring+0x149/0x230() WARN_ON(i915_verify_lists(ring->dev)) Note that this is only a problem in evict_vm where the following happens after a retire_request has cleaned out all requests, but not all active bo: - intel_ring_idle called from i915_gpu_idle notices that no requests are outstanding and immediately returns. - i915_gem_retire_requests_ring called from i915_gem_retire_requests also immediately returns when there's no request, still leaving the bo on the active list. - evict_vm hits the WARN_ON(!list_empty(&vm->active_list)) after evicting all active objects that there's still stuff left that shouldn't be there. Signed-off-by: Chris Wilson Cc: John Harrison Cc: Daniel Vetter Reviewed-by: Daniel Vetter Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_gem.c | 38 ++++++++++++++++++--------------- 1 file changed, 21 insertions(+), 17 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 5b205863b659..27ea6bdebce7 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2737,24 +2737,11 @@ i915_gem_retire_requests_ring(struct intel_engine_cs *ring) WARN_ON(i915_verify_lists(ring->dev)); - /* Move any buffers on the active list that are no longer referenced - * by the ringbuffer to the flushing/inactive lists as appropriate, - * before we free the context associated with the requests. + /* Retire requests first as we use it above for the early return. + * If we retire requests last, we may use a later seqno and so clear + * the requests lists without clearing the active list, leading to + * confusion. */ - while (!list_empty(&ring->active_list)) { - struct drm_i915_gem_object *obj; - - obj = list_first_entry(&ring->active_list, - struct drm_i915_gem_object, - ring_list); - - if (!i915_gem_request_completed(obj->last_read_req, true)) - break; - - i915_gem_object_move_to_inactive(obj); - } - - while (!list_empty(&ring->request_list)) { struct drm_i915_gem_request *request; struct intel_ringbuffer *ringbuf; @@ -2789,6 +2776,23 @@ i915_gem_retire_requests_ring(struct intel_engine_cs *ring) i915_gem_free_request(request); } + /* Move any buffers on the active list that are no longer referenced + * by the ringbuffer to the flushing/inactive lists as appropriate, + * before we free the context associated with the requests. + */ + while (!list_empty(&ring->active_list)) { + struct drm_i915_gem_object *obj; + + obj = list_first_entry(&ring->active_list, + struct drm_i915_gem_object, + ring_list); + + if (!i915_gem_request_completed(obj->last_read_req, true)) + break; + + i915_gem_object_move_to_inactive(obj); + } + if (unlikely(ring->trace_irq_req && i915_gem_request_completed(ring->trace_irq_req, true))) { ring->irq_put(ring); From 11bc26fe372fa6da81c82c68f755d2795838a640 Mon Sep 17 00:00:00 2001 From: Richard Weinberger Date: Thu, 26 Mar 2015 10:27:06 +0100 Subject: [PATCH 124/170] clocksource/drivers: Fix various !CONFIG_HAS_IOMEM build errors MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix !CONFIG_HAS_IOMEM related build failures in three clocksource drivers. The build failures have the pattern of: drivers/clocksource/sh_cmt.c: In function ‘sh_cmt_map_memory’: drivers/clocksource/sh_cmt.c:920:2: error: implicit declaration of function ‘ioremap_nocache’ [-Werror=implicit-function-declaration] cmt->mapbase = ioremap_nocache(mem->start, resource_size(mem)); Signed-off-by: Richard Weinberger Signed-off-by: Daniel Lezcano Acked-by: Geert Uytterhoeven Cc: maxime.ripard@free-electrons.com Link: http://lkml.kernel.org/r/1427362029-6511-1-git-send-email-daniel.lezcano@linaro.org Signed-off-by: Ingo Molnar --- drivers/clocksource/Kconfig | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index 68161f7a07d6..a0b036ccb118 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -192,6 +192,7 @@ config SYS_SUPPORTS_EM_STI config SH_TIMER_CMT bool "Renesas CMT timer driver" if COMPILE_TEST depends on GENERIC_CLOCKEVENTS + depends on HAS_IOMEM default SYS_SUPPORTS_SH_CMT help This enables build of a clocksource and clockevent driver for @@ -201,6 +202,7 @@ config SH_TIMER_CMT config SH_TIMER_MTU2 bool "Renesas MTU2 timer driver" if COMPILE_TEST depends on GENERIC_CLOCKEVENTS + depends on HAS_IOMEM default SYS_SUPPORTS_SH_MTU2 help This enables build of a clockevent driver for the Multi-Function @@ -210,6 +212,7 @@ config SH_TIMER_MTU2 config SH_TIMER_TMU bool "Renesas TMU timer driver" if COMPILE_TEST depends on GENERIC_CLOCKEVENTS + depends on HAS_IOMEM default SYS_SUPPORTS_SH_TMU help This enables build of a clocksource and clockevent driver for From 6e206020324c50a95486f6b279a53512febed92d Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Thu, 26 Mar 2015 10:27:09 +0100 Subject: [PATCH 125/170] clocksource/drivers/sun5i: Fix cpufreq interaction with sched_clock() The sun5i timer is used as the sched-clock on certain systems, and ever since we started using cpufreq, the cpu clock (that is one of the timer's clock indirect parent) now changes as well, along with the actual sched_clock() rate. This is not accurate and not desirable. We can safely remove the sun5i sched-clock on those systems, since we have other reliable sched_clock() sources in the system. Tested-by: Hans de Goede Signed-off-by: Maxime Ripard Signed-off-by: Daniel Lezcano [ Improved the changelog. ] Cc: richard@nod.at Link: http://lkml.kernel.org/r/1427362029-6511-4-git-send-email-daniel.lezcano@linaro.org Signed-off-by: Ingo Molnar --- drivers/clocksource/timer-sun5i.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/clocksource/timer-sun5i.c b/drivers/clocksource/timer-sun5i.c index 5dcbf90b8015..58597fbcc046 100644 --- a/drivers/clocksource/timer-sun5i.c +++ b/drivers/clocksource/timer-sun5i.c @@ -17,7 +17,6 @@ #include #include #include -#include #include #include #include @@ -137,11 +136,6 @@ static struct irqaction sun5i_timer_irq = { .dev_id = &sun5i_clockevent, }; -static u64 sun5i_timer_sched_read(void) -{ - return ~readl(timer_base + TIMER_CNTVAL_LO_REG(1)); -} - static void __init sun5i_timer_init(struct device_node *node) { struct reset_control *rstc; @@ -172,7 +166,6 @@ static void __init sun5i_timer_init(struct device_node *node) writel(TIMER_CTL_ENABLE | TIMER_CTL_RELOAD, timer_base + TIMER_CTL_REG(1)); - sched_clock_register(sun5i_timer_sched_read, 32, rate); clocksource_mmio_init(timer_base + TIMER_CNTVAL_LO_REG(1), node->name, rate, 340, 32, clocksource_mmio_readl_down); From af95b41426e0b58279f8ff0ebe420df49a4e96b8 Mon Sep 17 00:00:00 2001 From: Hui Wang Date: Thu, 26 Mar 2015 17:14:55 +0800 Subject: [PATCH 126/170] ALSA: hda - Add one more node in the EAPD supporting candidate list We have a HP machine which use the codec node 0x17 connecting the internal speaker, and from the node capability, we saw the EAPD, if we don't set the EAPD on for this node, the internal speaker can't output any sound. Cc: BugLink: https://bugs.launchpad.net/bugs/1436745 Signed-off-by: Hui Wang Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 7b0f72c5c6f1..74382137b9f5 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -396,7 +396,7 @@ static void alc_auto_setup_eapd(struct hda_codec *codec, bool on) { /* We currently only handle front, HP */ static hda_nid_t pins[] = { - 0x0f, 0x10, 0x14, 0x15, 0 + 0x0f, 0x10, 0x14, 0x15, 0x17, 0 }; hda_nid_t *p; for (p = pins; *p; p++) From 3164a803416832d61268b758112e8dfd7e35cdf7 Mon Sep 17 00:00:00 2001 From: Damien Lespiau Date: Thu, 5 Feb 2015 19:24:25 +0000 Subject: [PATCH 127/170] drm/i915: Fix atomic state when reusing the firmware fb Right now, we get a warning when taking over the firmware fb: [drm:drm_atomic_plane_check] FB set but no CRTC with the following backtrace: [] drm_atomic_check_only+0x35d/0x510 [drm] [] drm_atomic_commit+0x17/0x60 [drm] [] drm_atomic_helper_plane_set_property+0x8d/0xd0 [drm_kms_helper] [] drm_mode_plane_set_obj_prop+0x2d/0x90 [drm] [] restore_fbdev_mode+0x6b/0xf0 [drm_kms_helper] [] drm_fb_helper_restore_fbdev_mode_unlocked+0x29/0x80 [drm_kms_helper] [] drm_fb_helper_set_par+0x22/0x50 [drm_kms_helper] [] intel_fbdev_set_par+0x1a/0x60 [i915] [] fbcon_init+0x4f4/0x580 That's because we update the plane state with the fb from the firmware, but we never associate the plane to that CRTC. We don't quite have the full DRM take over from HW state just yet, so fake enough of the plane atomic state to pass the checks. v2: Fix the state on which we set the CRTC in the case we're sharing the initial fb with another pipe. (Matt) Signed-off-by: Damien Lespiau Reviewed-by: Matt Roper Signed-off-by: Daniel Vetter [Jani: backported to drm-intel-fixes for v4.0-rc] Reference: http://mid.gmane.org/CA+5PVA7yXH=U757w8V=Zj2U1URG4nYNav20NpjtQ4svVueyPNw@mail.gmail.com Reference: http://lkml.kernel.org/r/CA+55aFweWR=nDzc2Y=rCtL_H8JfdprQiCimN5dwc+TgyD4Bjsg@mail.gmail.com Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_display.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 1c12262029fb..30faf6c262e5 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -2439,7 +2439,11 @@ intel_find_plane_obj(struct intel_crtc *intel_crtc, return; if (intel_alloc_plane_obj(intel_crtc, plane_config)) { - update_state_fb(intel_crtc->base.primary); + struct drm_plane *primary = intel_crtc->base.primary; + + primary->state->crtc = &intel_crtc->base; + update_state_fb(primary); + return; } @@ -2464,11 +2468,14 @@ intel_find_plane_obj(struct intel_crtc *intel_crtc, continue; if (i915_gem_obj_ggtt_offset(obj) == plane_config->base) { + struct drm_plane *primary = intel_crtc->base.primary; + if (obj->tiling_mode != I915_TILING_NONE) dev_priv->preserve_bios_swizzle = true; drm_framebuffer_reference(c->primary->fb); - intel_crtc->base.primary->fb = c->primary->fb; + primary->fb = c->primary->fb; + primary->state->crtc = &intel_crtc->base; obj->frontbuffer_bits |= INTEL_FRONTBUFFER_PRIMARY(intel_crtc->pipe); break; } From 5f407751b0ca9bd876fe8f15ff28153661c6ba0a Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 25 Mar 2015 18:30:38 +0100 Subject: [PATCH 128/170] drm/i915: Fixup legacy plane->crtc link for initial fb config This is a very similar bug in the load detect code fixed in commit 9128b040eb774e04bc23777b005ace2b66ab2a85 Author: Daniel Vetter Date: Tue Mar 3 17:31:21 2015 +0100 drm/i915: Fix modeset state confusion in the load detect code But this time around it was the initial fb code that forgot to update the plane->crtc pointer. Otherwise it's the exact same bug, with the exact same restrains (any set_config call/ioctl that doesn't disable the pipe papers over the bug for free, so fairly hard to hit in normal testing). So if you want the full explanation just go read that one over there - it's rather long ... Cc: Matt Roper Cc: Linus Torvalds Cc: Chris Wilson Cc: Josh Boyer Cc: Jani Nikula Reported-and-tested-by: Josh Boyer Signed-off-by: Daniel Vetter [Jani: backported to drm-intel-fixes for v4.0-rc] Reference: http://mid.gmane.org/CA+5PVA7ChbtJrknqws1qvZcbrg1CW2pQAFkSMURWWgyASRyGXg@mail.gmail.com Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_display.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 30faf6c262e5..f75173c20f47 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -2442,6 +2442,7 @@ intel_find_plane_obj(struct intel_crtc *intel_crtc, struct drm_plane *primary = intel_crtc->base.primary; primary->state->crtc = &intel_crtc->base; + primary->crtc = &intel_crtc->base; update_state_fb(primary); return; @@ -2476,6 +2477,7 @@ intel_find_plane_obj(struct intel_crtc *intel_crtc, drm_framebuffer_reference(c->primary->fb); primary->fb = c->primary->fb; primary->state->crtc = &intel_crtc->base; + primary->crtc = &intel_crtc->base; obj->frontbuffer_bits |= INTEL_FRONTBUFFER_PRIMARY(intel_crtc->pipe); break; } From 9ffd906d9a6e50c958bd99971d762a426a12a36a Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 11 Feb 2015 13:26:21 +0300 Subject: [PATCH 129/170] watchdog: mtk_wdt: signedness bug in mtk_wdt_start() "ret" should be signed for the error handling to work correctly. This doesn't matter much in real life since mtk_wdt_set_timeout() always succeeds. Signed-off-by: Dan Carpenter Reviewed-by: Matthias Brugger Reviewed-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/mtk_wdt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/watchdog/mtk_wdt.c b/drivers/watchdog/mtk_wdt.c index a87f6df6e85f..938b987de551 100644 --- a/drivers/watchdog/mtk_wdt.c +++ b/drivers/watchdog/mtk_wdt.c @@ -133,7 +133,7 @@ static int mtk_wdt_start(struct watchdog_device *wdt_dev) u32 reg; struct mtk_wdt_dev *mtk_wdt = watchdog_get_drvdata(wdt_dev); void __iomem *wdt_base = mtk_wdt->wdt_base; - u32 ret; + int ret; ret = mtk_wdt_set_timeout(wdt_dev, wdt_dev->timeout); if (ret < 0) From a629c08fdb98ebb184d745553af9dda4f05941bf Mon Sep 17 00:00:00 2001 From: James Hogan Date: Fri, 20 Feb 2015 23:45:44 +0000 Subject: [PATCH 130/170] watchdog: imgpdc: Fix probe NULL pointer dereference The IMG PDC watchdog probe function calls pdc_wdt_stop() prior to watchdog_set_drvdata(), causing a NULL pointer dereference when pdc_wdt_stop() retrieves the struct pdc_wdt_dev pointer using watchdog_get_drvdata() and reads the register base address through it. Fix by moving the watchdog_set_drvdata() call earlier, to where various other pdc_wdt->wdt_dev fields are initialised. Fixes: 93937669e9b5 ("watchdog: ImgTec PDC Watchdog Timer Driver") Signed-off-by: James Hogan Cc: Ezequiel Garcia Cc: Naidu Tellapati Cc: Jude Abraham Cc: linux-watchdog@vger.kernel.org Reviewed-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/imgpdc_wdt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/watchdog/imgpdc_wdt.c b/drivers/watchdog/imgpdc_wdt.c index c8def68d9e4c..32c35eb31e65 100644 --- a/drivers/watchdog/imgpdc_wdt.c +++ b/drivers/watchdog/imgpdc_wdt.c @@ -191,6 +191,7 @@ static int pdc_wdt_probe(struct platform_device *pdev) pdc_wdt->wdt_dev.ops = &pdc_wdt_ops; pdc_wdt->wdt_dev.max_timeout = 1 << PDC_WDT_CONFIG_DELAY_MASK; pdc_wdt->wdt_dev.parent = &pdev->dev; + watchdog_set_drvdata(&pdc_wdt->wdt_dev, pdc_wdt); ret = watchdog_init_timeout(&pdc_wdt->wdt_dev, heartbeat, &pdev->dev); if (ret < 0) { @@ -232,7 +233,6 @@ static int pdc_wdt_probe(struct platform_device *pdev) watchdog_set_nowayout(&pdc_wdt->wdt_dev, nowayout); platform_set_drvdata(pdev, pdc_wdt); - watchdog_set_drvdata(&pdc_wdt->wdt_dev, pdc_wdt); ret = watchdog_register_device(&pdc_wdt->wdt_dev); if (ret) From ae6ee2fd47f76db5a1cd02c23378057bd21c2c8d Mon Sep 17 00:00:00 2001 From: James Hogan Date: Fri, 20 Feb 2015 23:45:45 +0000 Subject: [PATCH 131/170] watchdog: imgpdc: Fix default heartbeat The IMG PDC watchdog driver heartbeat module parameter has no default so it is initialised to zero. This results in the following warning during probe: imgpdc-wdt 2006000.wdt: Initial timeout out of range! setting max timeout The module parameter description implies that the default value should be PDC_WDT_DEF_TIMEOUT, which isn't yet used, so initialise it to that. Also tweak the heartbeat module parameter description for consistency. Fixes: 93937669e9b5 ("watchdog: ImgTec PDC Watchdog Timer Driver") Signed-off-by: James Hogan Cc: Ezequiel Garcia Cc: Naidu Tellapati Cc: Jude Abraham Cc: linux-watchdog@vger.kernel.org Reviewed-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/imgpdc_wdt.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/watchdog/imgpdc_wdt.c b/drivers/watchdog/imgpdc_wdt.c index 32c35eb31e65..0deaa4f971f5 100644 --- a/drivers/watchdog/imgpdc_wdt.c +++ b/drivers/watchdog/imgpdc_wdt.c @@ -42,10 +42,10 @@ #define PDC_WDT_MIN_TIMEOUT 1 #define PDC_WDT_DEF_TIMEOUT 64 -static int heartbeat; +static int heartbeat = PDC_WDT_DEF_TIMEOUT; module_param(heartbeat, int, 0); -MODULE_PARM_DESC(heartbeat, "Watchdog heartbeats in seconds. " - "(default = " __MODULE_STRING(PDC_WDT_DEF_TIMEOUT) ")"); +MODULE_PARM_DESC(heartbeat, "Watchdog heartbeats in seconds " + "(default=" __MODULE_STRING(PDC_WDT_DEF_TIMEOUT) ")"); static bool nowayout = WATCHDOG_NOWAYOUT; module_param(nowayout, bool, 0); From c6ac19dac2683a8b06aebcc10cb1c711b555a949 Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Tue, 24 Mar 2015 20:42:42 +0200 Subject: [PATCH 132/170] gpio: syscon: reduce message level when direction reg offset not in dt Now GPIO syscon driver produces bunch of warnings during the boot of Kesytone 2 SoCs: gpio-syscon soc:keystone_dsp_gpio@02620240: can't read the dir register offset! gpio-syscon soc:keystone_dsp_gpio@2620244: can't read the dir register offset! This message unintentionally was added using dev_err(), but its actual log level is debug, because third cell of "ti,syscon-dev" is optional. Hence change it to dev_dbg() as it should be. This patch fixes commit: 5a3e3f8 ("gpio: syscon: retriave syscon node and regs offsets from dt") Reported-by: Russell King Tested-by: Murali Karicheri Acked-by: Santosh Shilimkar Signed-off-by: Grygorii Strashko Signed-off-by: Linus Walleij --- drivers/gpio/gpio-syscon.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpio/gpio-syscon.c b/drivers/gpio/gpio-syscon.c index 257e2989215c..045a952576c7 100644 --- a/drivers/gpio/gpio-syscon.c +++ b/drivers/gpio/gpio-syscon.c @@ -219,7 +219,7 @@ static int syscon_gpio_probe(struct platform_device *pdev) ret = of_property_read_u32_index(np, "gpio,syscon-dev", 2, &priv->dir_reg_offset); if (ret) - dev_err(dev, "can't read the dir register offset!\n"); + dev_dbg(dev, "can't read the dir register offset!\n"); priv->dir_reg_offset <<= 3; } From a901125c65544aa05c52e1a7388c3900e8af105f Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Fri, 27 Mar 2015 10:34:20 +0800 Subject: [PATCH 133/170] locks: fix file_lock deletion inside loop locks_delete_lock_ctx() is called inside the loop, so we should use list_for_each_entry_safe. Fixes: 8634b51f6ca2 (locks: convert lease handling to file_lock_context) Signed-off-by: "Yan, Zheng" Signed-off-by: Jeff Layton --- fs/locks.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/locks.c b/fs/locks.c index 528fedfda15e..40bc384728c0 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1388,9 +1388,8 @@ any_leases_conflict(struct inode *inode, struct file_lock *breaker) int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) { int error = 0; - struct file_lock *new_fl; struct file_lock_context *ctx = inode->i_flctx; - struct file_lock *fl; + struct file_lock *new_fl, *fl, *tmp; unsigned long break_time; int want_write = (mode & O_ACCMODE) != O_RDONLY; LIST_HEAD(dispose); @@ -1420,7 +1419,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) break_time++; /* so that 0 means no break time */ } - list_for_each_entry(fl, &ctx->flc_lease, fl_list) { + list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) { if (!leases_conflict(fl, new_fl)) continue; if (want_write) { From ff7f53fb82a7801a778e5902bdbbc5e195ab0de0 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Fri, 27 Mar 2015 15:17:20 -0400 Subject: [PATCH 134/170] libata: Update Crucial/Micron blacklist Micron has released an updated firmware (MU02) for M510/M550/MX100 drives to fix the issues with queued TRIM. Queued TRIM remains broken on M500 but is working fine on later drives such as M600 and MX200. Tweak our blacklist to reflect the above. Link: https://bugzilla.kernel.org/show_bug.cgi?id=71371 Signed-off-by: Martin K. Petersen Cc: stable@vger.kernel.org Signed-off-by: Tejun Heo --- drivers/ata/libata-core.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index ef150ebb4c30..86374df28b10 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4204,9 +4204,16 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "PIONEER DVD-RW DVR-216D", NULL, ATA_HORKAGE_NOSETXFER }, /* devices that don't properly handle queued TRIM commands */ - { "Micron_M[56]*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | + { "Micron_M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | + ATA_HORKAGE_ZERO_AFTER_TRIM, }, + { "Crucial_CT*M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | + ATA_HORKAGE_ZERO_AFTER_TRIM, }, + { "Micron_M5[15]0*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | + ATA_HORKAGE_ZERO_AFTER_TRIM, }, + { "Crucial_CT*M550*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | + ATA_HORKAGE_ZERO_AFTER_TRIM, }, + { "Crucial_CT*MX100*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, - { "Crucial_CT*SSD*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, /* * As defined, the DRAT (Deterministic Read After Trim) and RZAT @@ -4226,6 +4233,8 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { */ { "INTEL*SSDSC2MH*", NULL, 0, }, + { "Micron*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, + { "Crucial*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "INTEL*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "SSD*INTEL*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Samsung*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, From 6fc4d97a4987c5d247655a157a9377996626221a Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Fri, 27 Mar 2015 15:17:21 -0400 Subject: [PATCH 135/170] libata: Blacklist queued TRIM on Samsung SSD 850 Pro Blacklist queued TRIM on this drive for now. Reported-by: Stefan Keller Signed-off-by: Martin K. Petersen CC: stable@vger.kernel.org Signed-off-by: Tejun Heo --- drivers/ata/libata-core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 86374df28b10..23dac3babfe3 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4214,6 +4214,8 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Crucial_CT*MX100*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, + { "Samsung SSD 850 PRO*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | + ATA_HORKAGE_ZERO_AFTER_TRIM, }, /* * As defined, the DRAT (Deterministic Read After Trim) and RZAT From 1e9e39f4a29857a396ac7b669d109f697f66695e Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Thu, 26 Feb 2015 19:34:37 +0000 Subject: [PATCH 136/170] usbnet: Fix tx_packets stat for FLAG_MULTI_FRAME drivers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently the usbnet core does not update the tx_packets statistic for drivers with FLAG_MULTI_PACKET and there is no hook in the TX completion path where they could do this. cdc_ncm and dependent drivers are bumping tx_packets stat on the transmit path while asix and sr9800 aren't updating it at all. Add a packet count in struct skb_data so these drivers can fill it in, initialise it to 1 for other drivers, and add the packet count to the tx_packets statistic on completion. Signed-off-by: Ben Hutchings Tested-by: Bjørn Mork Signed-off-by: David S. Miller --- drivers/net/usb/asix_common.c | 2 ++ drivers/net/usb/cdc_ncm.c | 3 ++- drivers/net/usb/sr9800.c | 1 + drivers/net/usb/usbnet.c | 5 +++-- include/linux/usb/usbnet.h | 12 ++++++++++++ 5 files changed, 20 insertions(+), 3 deletions(-) diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c index 5c55f11572ba..724a9b50df7a 100644 --- a/drivers/net/usb/asix_common.c +++ b/drivers/net/usb/asix_common.c @@ -188,6 +188,8 @@ struct sk_buff *asix_tx_fixup(struct usbnet *dev, struct sk_buff *skb, memcpy(skb_tail_pointer(skb), &padbytes, sizeof(padbytes)); skb_put(skb, sizeof(padbytes)); } + + usbnet_set_skb_tx_stats(skb, 1); return skb; } diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index 80a844e0ae03..70cbea551139 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -1172,7 +1172,6 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign) /* return skb */ ctx->tx_curr_skb = NULL; - dev->net->stats.tx_packets += ctx->tx_curr_frame_num; /* keep private stats: framing overhead and number of NTBs */ ctx->tx_overhead += skb_out->len - ctx->tx_curr_frame_payload; @@ -1184,6 +1183,8 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign) */ dev->net->stats.tx_bytes -= skb_out->len - ctx->tx_curr_frame_payload; + usbnet_set_skb_tx_stats(skb_out, n); + return skb_out; exit_no_skb: diff --git a/drivers/net/usb/sr9800.c b/drivers/net/usb/sr9800.c index b94a0fbb8b3b..7650cdc8fe6b 100644 --- a/drivers/net/usb/sr9800.c +++ b/drivers/net/usb/sr9800.c @@ -144,6 +144,7 @@ static struct sk_buff *sr_tx_fixup(struct usbnet *dev, struct sk_buff *skb, skb_put(skb, sizeof(padbytes)); } + usbnet_set_skb_tx_stats(skb, 1); return skb; } diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 449835f4331e..0f3ff285f6a1 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1188,8 +1188,7 @@ static void tx_complete (struct urb *urb) struct usbnet *dev = entry->dev; if (urb->status == 0) { - if (!(dev->driver_info->flags & FLAG_MULTI_PACKET)) - dev->net->stats.tx_packets++; + dev->net->stats.tx_packets += entry->packets; dev->net->stats.tx_bytes += entry->length; } else { dev->net->stats.tx_errors++; @@ -1348,6 +1347,8 @@ netdev_tx_t usbnet_start_xmit (struct sk_buff *skb, urb->transfer_flags |= URB_ZERO_PACKET; } entry->length = urb->transfer_buffer_length = length; + if (!(info->flags & FLAG_MULTI_PACKET)) + usbnet_set_skb_tx_stats(skb, 1); spin_lock_irqsave(&dev->txq.lock, flags); retval = usb_autopm_get_interface_async(dev->intf); diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index d9a4905e01d0..ff3fb2bd0e90 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -228,8 +228,20 @@ struct skb_data { /* skb->cb is one of these */ struct usbnet *dev; enum skb_state state; size_t length; + unsigned long packets; }; +/* Drivers that set FLAG_MULTI_PACKET must call this in their + * tx_fixup method before returning an skb. + */ +static inline void +usbnet_set_skb_tx_stats(struct sk_buff *skb, unsigned long packets) +{ + struct skb_data *entry = (struct skb_data *) skb->cb; + + entry->packets = packets; +} + extern int usbnet_open(struct net_device *net); extern int usbnet_stop(struct net_device *net); extern netdev_tx_t usbnet_start_xmit(struct sk_buff *skb, From 7a1e890e2168e33fb62d84528e996b8b4b478fea Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Wed, 25 Mar 2015 21:41:33 +0100 Subject: [PATCH 137/170] usbnet: Fix tx_bytes statistic running backward in cdc_ncm MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit cdc_ncm disagrees with usbnet about how much framing overhead should be counted in the tx_bytes statistics, and tries 'fix' this by decrementing tx_bytes on the transmit path. But statistics must never be decremented except due to roll-over; this will thoroughly confuse user-space. Also, tx_bytes is only incremented by usbnet in the completion path. Fix this by requiring drivers that set FLAG_MULTI_FRAME to set a tx_bytes delta along with the tx_packets count. Fixes: beeecd42c3b4 ("net: cdc_ncm/cdc_mbim: adding NCM protocol statistics") Signed-off-by: Ben Hutchings Signed-off-by: Bjørn Mork --- drivers/net/usb/asix_common.c | 2 +- drivers/net/usb/cdc_ncm.c | 7 +++---- drivers/net/usb/sr9800.c | 2 +- drivers/net/usb/usbnet.c | 16 +++++++++++++--- include/linux/usb/usbnet.h | 6 ++++-- 5 files changed, 22 insertions(+), 11 deletions(-) diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c index 724a9b50df7a..75d6f26729a3 100644 --- a/drivers/net/usb/asix_common.c +++ b/drivers/net/usb/asix_common.c @@ -189,7 +189,7 @@ struct sk_buff *asix_tx_fixup(struct usbnet *dev, struct sk_buff *skb, skb_put(skb, sizeof(padbytes)); } - usbnet_set_skb_tx_stats(skb, 1); + usbnet_set_skb_tx_stats(skb, 1, 0); return skb; } diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index 70cbea551139..c3e4da9e79ca 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -1177,13 +1177,12 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign) ctx->tx_overhead += skb_out->len - ctx->tx_curr_frame_payload; ctx->tx_ntbs++; - /* usbnet has already counted all the framing overhead. + /* usbnet will count all the framing overhead by default. * Adjust the stats so that the tx_bytes counter show real * payload data instead. */ - dev->net->stats.tx_bytes -= skb_out->len - ctx->tx_curr_frame_payload; - - usbnet_set_skb_tx_stats(skb_out, n); + usbnet_set_skb_tx_stats(skb_out, n, + ctx->tx_curr_frame_payload - skb_out->len); return skb_out; diff --git a/drivers/net/usb/sr9800.c b/drivers/net/usb/sr9800.c index 7650cdc8fe6b..953de13267df 100644 --- a/drivers/net/usb/sr9800.c +++ b/drivers/net/usb/sr9800.c @@ -144,7 +144,7 @@ static struct sk_buff *sr_tx_fixup(struct usbnet *dev, struct sk_buff *skb, skb_put(skb, sizeof(padbytes)); } - usbnet_set_skb_tx_stats(skb, 1); + usbnet_set_skb_tx_stats(skb, 1, 0); return skb; } diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 0f3ff285f6a1..777757ae1973 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1346,9 +1346,19 @@ netdev_tx_t usbnet_start_xmit (struct sk_buff *skb, } else urb->transfer_flags |= URB_ZERO_PACKET; } - entry->length = urb->transfer_buffer_length = length; - if (!(info->flags & FLAG_MULTI_PACKET)) - usbnet_set_skb_tx_stats(skb, 1); + urb->transfer_buffer_length = length; + + if (info->flags & FLAG_MULTI_PACKET) { + /* Driver has set number of packets and a length delta. + * Calculate the complete length and ensure that it's + * positive. + */ + entry->length += length; + if (WARN_ON_ONCE(entry->length <= 0)) + entry->length = length; + } else { + usbnet_set_skb_tx_stats(skb, 1, length); + } spin_lock_irqsave(&dev->txq.lock, flags); retval = usb_autopm_get_interface_async(dev->intf); diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index ff3fb2bd0e90..6e0ce8c7b8cb 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -227,7 +227,7 @@ struct skb_data { /* skb->cb is one of these */ struct urb *urb; struct usbnet *dev; enum skb_state state; - size_t length; + long length; unsigned long packets; }; @@ -235,11 +235,13 @@ struct skb_data { /* skb->cb is one of these */ * tx_fixup method before returning an skb. */ static inline void -usbnet_set_skb_tx_stats(struct sk_buff *skb, unsigned long packets) +usbnet_set_skb_tx_stats(struct sk_buff *skb, + unsigned long packets, long bytes_delta) { struct skb_data *entry = (struct skb_data *) skb->cb; entry->packets = packets; + entry->length = bytes_delta; } extern int usbnet_open(struct net_device *net); From f243e5a7859a24d10975afb9a1708cac624ba6f1 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Wed, 25 Mar 2015 14:45:03 -0700 Subject: [PATCH 138/170] ipmr,ip6mr: call ip6mr_free_table() on failure path Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/ipv4/ipmr.c | 2 +- net/ipv6/ip6mr.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 9d78427652d2..92825443fad6 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -268,7 +268,7 @@ static int __net_init ipmr_rules_init(struct net *net) return 0; err2: - kfree(mrt); + ipmr_free_table(mrt); err1: fib_rules_unregister(ops); return err; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 34b682617f50..52028f449a89 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -252,7 +252,7 @@ static int __net_init ip6mr_rules_init(struct net *net) return 0; err2: - kfree(mrt); + ip6mr_free_table(mrt); err1: fib_rules_unregister(ops); return err; From 4b8e27a86d209063d8aacfb918668bbb75e56019 Mon Sep 17 00:00:00 2001 From: Hariprasad Shenai Date: Thu, 26 Mar 2015 10:04:25 +0530 Subject: [PATCH 139/170] cxgb4: Allocate dynamic mem. for egress and ingress queue maps QIDs (egress/ingress) from firmware in FW_*_CMD.alloc command can be anywhere in the range from EQ(IQFLINT)_START to EQ(IQFLINT)_END. For eg, in the first load eqid can be from 100 to 300. In the next load it can be from 301 to 500 (assume eq_start is 100 and eq_end is 1000). The driver was assuming them to always start from EQ(IQFLINT)_START till MAX_EGRQ(INGQ). This was causing stack overflow and subsequent crash. Fixed it by dynamically allocating memory (of qsize (x_END - x_START + 1)) for these structures. Based on original work by Santosh Rastapur Signed-off-by: Hariprasad Shenai Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/cxgb4.h | 12 +-- .../net/ethernet/chelsio/cxgb4/cxgb4_main.c | 79 +++++++++++++++++-- drivers/net/ethernet/chelsio/cxgb4/sge.c | 7 +- 3 files changed, 83 insertions(+), 15 deletions(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 97842d03675b..8816c645de7d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -376,8 +376,6 @@ enum { enum { INGQ_EXTRAS = 2, /* firmware event queue and */ /* forwarded interrupts */ - MAX_EGRQ = MAX_ETH_QSETS*2 + MAX_OFLD_QSETS*2 - + MAX_CTRL_QUEUES + MAX_RDMA_QUEUES + MAX_ISCSI_QUEUES, MAX_INGQ = MAX_ETH_QSETS + MAX_OFLD_QSETS + MAX_RDMA_QUEUES + MAX_RDMA_CIQS + MAX_ISCSI_QUEUES + INGQ_EXTRAS, }; @@ -616,11 +614,13 @@ struct sge { unsigned int idma_qid[2]; /* SGE IDMA Hung Ingress Queue ID */ unsigned int egr_start; + unsigned int egr_sz; unsigned int ingr_start; - void *egr_map[MAX_EGRQ]; /* qid->queue egress queue map */ - struct sge_rspq *ingr_map[MAX_INGQ]; /* qid->queue ingress queue map */ - DECLARE_BITMAP(starving_fl, MAX_EGRQ); - DECLARE_BITMAP(txq_maperr, MAX_EGRQ); + unsigned int ingr_sz; + void **egr_map; /* qid->queue egress queue map */ + struct sge_rspq **ingr_map; /* qid->queue ingress queue map */ + unsigned long *starving_fl; + unsigned long *txq_maperr; struct timer_list rx_timer; /* refills starving FLs */ struct timer_list tx_timer; /* checks Tx queues */ }; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index a22cf932ca35..b9b5a7b1a116 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -920,7 +920,7 @@ static void quiesce_rx(struct adapter *adap) { int i; - for (i = 0; i < ARRAY_SIZE(adap->sge.ingr_map); i++) { + for (i = 0; i < adap->sge.ingr_sz; i++) { struct sge_rspq *q = adap->sge.ingr_map[i]; if (q && q->handler) { @@ -941,7 +941,7 @@ static void enable_rx(struct adapter *adap) { int i; - for (i = 0; i < ARRAY_SIZE(adap->sge.ingr_map); i++) { + for (i = 0; i < adap->sge.ingr_sz; i++) { struct sge_rspq *q = adap->sge.ingr_map[i]; if (!q) @@ -970,8 +970,8 @@ static int setup_sge_queues(struct adapter *adap) int err, msi_idx, i, j; struct sge *s = &adap->sge; - bitmap_zero(s->starving_fl, MAX_EGRQ); - bitmap_zero(s->txq_maperr, MAX_EGRQ); + bitmap_zero(s->starving_fl, s->egr_sz); + bitmap_zero(s->txq_maperr, s->egr_sz); if (adap->flags & USING_MSIX) msi_idx = 1; /* vector 0 is for non-queue interrupts */ @@ -983,6 +983,19 @@ static int setup_sge_queues(struct adapter *adap) msi_idx = -((int)s->intrq.abs_id + 1); } + /* NOTE: If you add/delete any Ingress/Egress Queue allocations in here, + * don't forget to update the following which need to be + * synchronized to and changes here. + * + * 1. The calculations of MAX_INGQ in cxgb4.h. + * + * 2. Update enable_msix/name_msix_vecs/request_msix_queue_irqs + * to accommodate any new/deleted Ingress Queues + * which need MSI-X Vectors. + * + * 3. Update sge_qinfo_show() to include information on the + * new/deleted queues. + */ err = t4_sge_alloc_rxq(adap, &s->fw_evtq, true, adap->port[0], msi_idx, NULL, fwevtq_handler); if (err) { @@ -4733,8 +4746,9 @@ static int adap_init1(struct adapter *adap, struct fw_caps_config_cmd *c) if (ret < 0) return ret; - ret = t4_cfg_pfvf(adap, adap->fn, adap->fn, 0, MAX_EGRQ, 64, MAX_INGQ, - 0, 0, 4, 0xf, 0xf, 16, FW_CMD_CAP_PF, FW_CMD_CAP_PF); + ret = t4_cfg_pfvf(adap, adap->fn, adap->fn, 0, adap->sge.egr_sz, 64, + MAX_INGQ, 0, 0, 4, 0xf, 0xf, 16, FW_CMD_CAP_PF, + FW_CMD_CAP_PF); if (ret < 0) return ret; @@ -5293,6 +5307,51 @@ static int adap_init0(struct adapter *adap) adap->tids.nftids = val[4] - val[3] + 1; adap->sge.ingr_start = val[5]; + /* qids (ingress/egress) returned from firmware can be anywhere + * in the range from EQ(IQFLINT)_START to EQ(IQFLINT)_END. + * Hence driver needs to allocate memory for this range to + * store the queue info. Get the highest IQFLINT/EQ index returned + * in FW_EQ_*_CMD.alloc command. + */ + params[0] = FW_PARAM_PFVF(EQ_END); + params[1] = FW_PARAM_PFVF(IQFLINT_END); + ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 2, params, val); + if (ret < 0) + goto bye; + adap->sge.egr_sz = val[0] - adap->sge.egr_start + 1; + adap->sge.ingr_sz = val[1] - adap->sge.ingr_start + 1; + + adap->sge.egr_map = kcalloc(adap->sge.egr_sz, + sizeof(*adap->sge.egr_map), GFP_KERNEL); + if (!adap->sge.egr_map) { + ret = -ENOMEM; + goto bye; + } + + adap->sge.ingr_map = kcalloc(adap->sge.ingr_sz, + sizeof(*adap->sge.ingr_map), GFP_KERNEL); + if (!adap->sge.ingr_map) { + ret = -ENOMEM; + goto bye; + } + + /* Allocate the memory for the vaious egress queue bitmaps + * ie starving_fl and txq_maperr. + */ + adap->sge.starving_fl = kcalloc(BITS_TO_LONGS(adap->sge.egr_sz), + sizeof(long), GFP_KERNEL); + if (!adap->sge.starving_fl) { + ret = -ENOMEM; + goto bye; + } + + adap->sge.txq_maperr = kcalloc(BITS_TO_LONGS(adap->sge.egr_sz), + sizeof(long), GFP_KERNEL); + if (!adap->sge.txq_maperr) { + ret = -ENOMEM; + goto bye; + } + params[0] = FW_PARAM_PFVF(CLIP_START); params[1] = FW_PARAM_PFVF(CLIP_END); ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 2, params, val); @@ -5501,6 +5560,10 @@ static int adap_init0(struct adapter *adap) * happened to HW/FW, stop issuing commands. */ bye: + kfree(adap->sge.egr_map); + kfree(adap->sge.ingr_map); + kfree(adap->sge.starving_fl); + kfree(adap->sge.txq_maperr); if (ret != -ETIMEDOUT && ret != -EIO) t4_fw_bye(adap, adap->mbox); return ret; @@ -5912,6 +5975,10 @@ static void free_some_resources(struct adapter *adapter) t4_free_mem(adapter->l2t); t4_free_mem(adapter->tids.tid_tab); + kfree(adapter->sge.egr_map); + kfree(adapter->sge.ingr_map); + kfree(adapter->sge.starving_fl); + kfree(adapter->sge.txq_maperr); disable_msi(adapter); for_each_port(adapter, i) diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index b4b9f6048fe7..b688b32c21fe 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -2171,7 +2171,7 @@ static void sge_rx_timer_cb(unsigned long data) struct adapter *adap = (struct adapter *)data; struct sge *s = &adap->sge; - for (i = 0; i < ARRAY_SIZE(s->starving_fl); i++) + for (i = 0; i < BITS_TO_LONGS(s->egr_sz); i++) for (m = s->starving_fl[i]; m; m &= m - 1) { struct sge_eth_rxq *rxq; unsigned int id = __ffs(m) + i * BITS_PER_LONG; @@ -2259,7 +2259,7 @@ static void sge_tx_timer_cb(unsigned long data) struct adapter *adap = (struct adapter *)data; struct sge *s = &adap->sge; - for (i = 0; i < ARRAY_SIZE(s->txq_maperr); i++) + for (i = 0; i < BITS_TO_LONGS(s->egr_sz); i++) for (m = s->txq_maperr[i]; m; m &= m - 1) { unsigned long id = __ffs(m) + i * BITS_PER_LONG; struct sge_ofld_txq *txq = s->egr_map[id]; @@ -2741,7 +2741,8 @@ void t4_free_sge_resources(struct adapter *adap) free_rspq_fl(adap, &adap->sge.intrq, NULL); /* clear the reverse egress queue map */ - memset(adap->sge.egr_map, 0, sizeof(adap->sge.egr_map)); + memset(adap->sge.egr_map, 0, + adap->sge.egr_sz * sizeof(*adap->sge.egr_map)); } void t4_sge_start(struct adapter *adap) From b37987e8db5faee3fc12baecc4699f9d92bc0695 Mon Sep 17 00:00:00 2001 From: Hariprasad Shenai Date: Thu, 26 Mar 2015 10:04:26 +0530 Subject: [PATCH 140/170] cxgb4: Disable interrupts and napi before unregistering netdev Disable interrupts and quiesce rx before unregistering net device to avoid crash while unloading driver when traffic is flowing through. Based on original work by Shameem Khalid Signed-off-by: Hariprasad Shenai Signed-off-by: David S. Miller --- .../net/ethernet/chelsio/cxgb4/cxgb4_main.c | 25 +++++++++++++------ 1 file changed, 18 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index b9b5a7b1a116..826de7a7f83c 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -934,6 +934,21 @@ static void quiesce_rx(struct adapter *adap) } } +/* Disable interrupt and napi handler */ +static void disable_interrupts(struct adapter *adap) +{ + if (adap->flags & FULL_INIT_DONE) { + t4_intr_disable(adap); + if (adap->flags & USING_MSIX) { + free_msix_queue_irqs(adap); + free_irq(adap->msix_info[0].vec, adap); + } else { + free_irq(adap->pdev->irq, adap); + } + quiesce_rx(adap); + } +} + /* * Enable NAPI scheduling and interrupt generation for all Rx queues. */ @@ -4257,19 +4272,12 @@ static int cxgb_up(struct adapter *adap) static void cxgb_down(struct adapter *adapter) { - t4_intr_disable(adapter); cancel_work_sync(&adapter->tid_release_task); cancel_work_sync(&adapter->db_full_task); cancel_work_sync(&adapter->db_drop_task); adapter->tid_release_task_busy = false; adapter->tid_release_head = NULL; - if (adapter->flags & USING_MSIX) { - free_msix_queue_irqs(adapter); - free_irq(adapter->msix_info[0].vec, adapter); - } else - free_irq(adapter->pdev->irq, adapter); - quiesce_rx(adapter); t4_sge_stop(adapter); t4_free_sge_resources(adapter); adapter->flags &= ~FULL_INIT_DONE; @@ -5591,6 +5599,7 @@ static pci_ers_result_t eeh_err_detected(struct pci_dev *pdev, netif_carrier_off(dev); } spin_unlock(&adap->stats_lock); + disable_interrupts(adap); if (adap->flags & FULL_INIT_DONE) cxgb_down(adap); rtnl_unlock(); @@ -6304,6 +6313,8 @@ static void remove_one(struct pci_dev *pdev) if (is_offload(adapter)) detach_ulds(adapter); + disable_interrupts(adapter); + for_each_port(adapter, i) if (adapter->port[i]->reg_state == NETREG_REGISTERED) unregister_netdev(adapter->port[i]); From 4217291e592da0e4258b652e82e5428639d29acc Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Thu, 26 Mar 2015 17:56:38 +0100 Subject: [PATCH 141/170] netns: don't clear nsid too early on removal With the current code, ids are removed too early. Suppose you have an ipip interface that stands in the netns foo and its link part in the netns bar (so the netns bar has an nsid into the netns foo). Now, you remove the netns bar: - the bar nsid into the netns foo is removed - the netns exit method of ipip is called, thus our ipip iface is removed: => a netlink message is sent in the netns foo to advertise this deletion => this netlink message requests an nsid for bar, thus a new nsid is allocated for bar and never removed. We must remove nsids when we are sure that nobody will refer to netns currently cleaned. Fixes: 0c7aecd4bde4 ("netns: add rtnl cmd to add and get peer netns ids") Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- net/core/net_namespace.c | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index cb5290b8c428..5221f975a4cc 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -349,7 +349,7 @@ static LIST_HEAD(cleanup_list); /* Must hold cleanup_list_lock to touch */ static void cleanup_net(struct work_struct *work) { const struct pernet_operations *ops; - struct net *net, *tmp; + struct net *net, *tmp, *peer; struct list_head net_kill_list; LIST_HEAD(net_exit_list); @@ -365,14 +365,6 @@ static void cleanup_net(struct work_struct *work) list_for_each_entry(net, &net_kill_list, cleanup_list) { list_del_rcu(&net->list); list_add_tail(&net->exit_list, &net_exit_list); - for_each_net(tmp) { - int id = __peernet2id(tmp, net, false); - - if (id >= 0) - idr_remove(&tmp->netns_ids, id); - } - idr_destroy(&net->netns_ids); - } rtnl_unlock(); @@ -398,12 +390,26 @@ static void cleanup_net(struct work_struct *work) */ rcu_barrier(); + rtnl_lock(); /* Finally it is safe to free my network namespace structure */ list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) { + /* Unreference net from all peers (no need to loop over + * net_exit_list because idr_destroy() will be called for each + * element of this list. + */ + for_each_net(peer) { + int id = __peernet2id(peer, net, false); + + if (id >= 0) + idr_remove(&peer->netns_ids, id); + } + idr_destroy(&net->netns_ids); + list_del_init(&net->exit_list); put_user_ns(net->user_ns); net_drop_ns(net); } + rtnl_unlock(); } static DECLARE_WORK(net_cleanup_work, cleanup_net); From 2ff2acf1fb65f1c83c41b67aba990c6d49a2274c Mon Sep 17 00:00:00 2001 From: Hariprasad Shenai Date: Fri, 27 Mar 2015 11:01:18 +0530 Subject: [PATCH 142/170] cxgb4vf: Fix sparse warnings Fixes sparse warnings introduced in commit e85c9a7abfa407ed ("cxgb4/cxgb4vf: Add code to calculate T5 BAR2 Offsets for SGE Queue Registers") and df64e4d38c904dd3 ("cxgb4/cxgb4vf: Use new interfaces to calculate BAR2 SGE Queue Register addresses") and few old ones sparse warnings: >> drivers/net/ethernet/chelsio/cxgb4vf/sge.c:1006:48: sparse: cast removes >> address space of expression >> drivers/net/ethernet/chelsio/cxgb4vf/sge.c:1006:48: sparse: incorrect type in >> initializer (different address space) >> drivers/net/ethernet/chelsio/cxgb4vf/sge.c:1020:40: sparse: incorrect type in >> argument 1 (different base types) Reported-by: Dan Carpenter Reported-by: kbuild test robot Signed-off-by: Hariprasad Shenai Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4vf/sge.c | 12 ++++++++---- drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c | 6 +++--- 2 files changed, 11 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c index 0545f0de1c52..e0d711071afb 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c @@ -1004,7 +1004,7 @@ static inline void ring_tx_db(struct adapter *adapter, struct sge_txq *tq, ? (tq->pidx - 1) : (tq->size - 1)); __be64 *src = (__be64 *)&tq->desc[index]; - __be64 __iomem *dst = (__be64 *)(tq->bar2_addr + + __be64 __iomem *dst = (__be64 __iomem *)(tq->bar2_addr + SGE_UDB_WCDOORBELL); unsigned int count = EQ_UNIT / sizeof(__be64); @@ -1018,7 +1018,11 @@ static inline void ring_tx_db(struct adapter *adapter, struct sge_txq *tq, * DMA. */ while (count) { - writeq(*src, dst); + /* the (__force u64) is because the compiler + * doesn't understand the endian swizzling + * going on + */ + writeq((__force u64)*src, dst); src++; dst++; count--; @@ -1252,8 +1256,8 @@ int t4vf_eth_xmit(struct sk_buff *skb, struct net_device *dev) BUG_ON(DIV_ROUND_UP(ETHTXQ_MAX_HDR, TXD_PER_EQ_UNIT) > 1); wr = (void *)&txq->q.desc[txq->q.pidx]; wr->equiq_to_len16 = cpu_to_be32(wr_mid); - wr->r3[0] = cpu_to_be64(0); - wr->r3[1] = cpu_to_be64(0); + wr->r3[0] = cpu_to_be32(0); + wr->r3[1] = cpu_to_be32(0); skb_copy_from_linear_data(skb, (void *)wr->ethmacdst, fw_hdr_copy_len); end = (u64 *)wr + flits; diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c index 1b5506df35b1..280b4a215849 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c @@ -210,10 +210,10 @@ int t4vf_wr_mbox_core(struct adapter *adapter, const void *cmd, int size, if (rpl) { /* request bit in high-order BE word */ - WARN_ON((be32_to_cpu(*(const u32 *)cmd) + WARN_ON((be32_to_cpu(*(const __be32 *)cmd) & FW_CMD_REQUEST_F) == 0); get_mbox_rpl(adapter, rpl, size, mbox_data); - WARN_ON((be32_to_cpu(*(u32 *)rpl) + WARN_ON((be32_to_cpu(*(__be32 *)rpl) & FW_CMD_REQUEST_F) != 0); } t4_write_reg(adapter, mbox_ctl, @@ -484,7 +484,7 @@ int t4_bar2_sge_qregs(struct adapter *adapter, * o The BAR2 Queue ID. * o The BAR2 Queue ID Offset into the BAR2 page. */ - bar2_page_offset = ((qid >> qpp_shift) << page_shift); + bar2_page_offset = ((u64)(qid >> qpp_shift) << page_shift); bar2_qid = qid & qpp_mask; bar2_qid_offset = bar2_qid * SGE_UDB_SIZE; From 4ad19de8774e2a7b075b3e8ea48db85adcf33fa6 Mon Sep 17 00:00:00 2001 From: Alexey Kodanev Date: Fri, 27 Mar 2015 12:24:22 +0300 Subject: [PATCH 143/170] net: tcp6: fix double call of tcp_v6_fill_cb() tcp_v6_fill_cb() will be called twice if socket's state changes from TCP_TIME_WAIT to TCP_LISTEN. That can result in control buffer data corruption because in the second tcp_v6_fill_cb() call it's not copying IP6CB(skb) anymore, but 'seq', 'end_seq', etc., so we can get weird and unpredictable results. Performance loss of up to 1200% has been observed in LTP/vxlan03 test. This can be fixed by copying inet6_skb_parm to the beginning of 'cb' only if xfrm6_policy_check() and tcp_v6_fill_cb() are going to be called again. Fixes: 2dc49d1680b53 ("tcp6: don't move IP6CB before xfrm6_policy_check()") Signed-off-by: Alexey Kodanev Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv6/tcp_ipv6.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index b283a498f7a4..1f5e62229aaa 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1411,6 +1411,15 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr, TCP_SKB_CB(skb)->sacked = 0; } +static void tcp_v6_restore_cb(struct sk_buff *skb) +{ + /* We need to move header back to the beginning if xfrm6_policy_check() + * and tcp_v6_fill_cb() are going to be called again. + */ + memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6, + sizeof(struct inet6_skb_parm)); +} + static int tcp_v6_rcv(struct sk_buff *skb) { const struct tcphdr *th; @@ -1543,6 +1552,7 @@ static int tcp_v6_rcv(struct sk_buff *skb) inet_twsk_deschedule(tw, &tcp_death_row); inet_twsk_put(tw); sk = sk2; + tcp_v6_restore_cb(skb); goto process; } /* Fall through to ACK */ @@ -1551,6 +1561,7 @@ static int tcp_v6_rcv(struct sk_buff *skb) tcp_v6_timewait_ack(sk, skb); break; case TCP_TW_RST: + tcp_v6_restore_cb(skb); goto no_tcp_socket; case TCP_TW_SUCCESS: ; From 63c607321492c5efc7a31bc4ea734b877f8e7f87 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 27 Mar 2015 11:08:32 +0100 Subject: [PATCH 144/170] net: fec: setup right value for mdio hold time MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The FEC modules used on i.MX28 and newer have a register to tune the MDIO output hold time that should be at least 10 ns. Up to now this value was not explicitly set and so resulted in less hold time if the fec clock was faster than 100 MHz. This was noticed on an i.MX28 machine that uses an input clock of ~150 Mhz which resulted in unreliable communication with a Marvell switch. Signed-off-by: Uwe Kleine-König Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fec_main.c | 30 ++++++++++++++++++++--- 1 file changed, 27 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 78e1ce09b1ab..f6a3a7abd468 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1954,6 +1954,7 @@ static int fec_enet_mii_init(struct platform_device *pdev) struct fec_enet_private *fep = netdev_priv(ndev); struct device_node *node; int err = -ENXIO, i; + u32 mii_speed, holdtime; /* * The i.MX28 dual fec interfaces are not equal. @@ -1991,10 +1992,33 @@ static int fec_enet_mii_init(struct platform_device *pdev) * Reference Manual has an error on this, and gets fixed on i.MX6Q * document. */ - fep->phy_speed = DIV_ROUND_UP(clk_get_rate(fep->clk_ipg), 5000000); + mii_speed = DIV_ROUND_UP(clk_get_rate(fep->clk_ipg), 5000000); if (fep->quirks & FEC_QUIRK_ENET_MAC) - fep->phy_speed--; - fep->phy_speed <<= 1; + mii_speed--; + if (mii_speed > 63) { + dev_err(&pdev->dev, + "fec clock (%lu) to fast to get right mii speed\n", + clk_get_rate(fep->clk_ipg)); + err = -EINVAL; + goto err_out; + } + + /* + * The i.MX28 and i.MX6 types have another filed in the MSCR (aka + * MII_SPEED) register that defines the MDIO output hold time. Earlier + * versions are RAZ there, so just ignore the difference and write the + * register always. + * The minimal hold time according to IEE802.3 (clause 22) is 10 ns. + * HOLDTIME + 1 is the number of clk cycles the fec is holding the + * output. + * The HOLDTIME bitfield takes values between 0 and 7 (inclusive). + * Given that ceil(clkrate / 5000000) <= 64, the calculation for + * holdtime cannot result in a value greater than 3. + */ + holdtime = DIV_ROUND_UP(clk_get_rate(fep->clk_ipg), 100000000) - 1; + + fep->phy_speed = mii_speed << 1 | holdtime << 8; + writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED); fep->mii_bus = mdiobus_alloc(); From 78d84bc3734c2566dbba09baae2414734661ed6a Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Tue, 17 Mar 2015 12:35:41 +0000 Subject: [PATCH 145/170] arm64: juno: Fix misleading name of UART reference clock The UART reference clock speed is 7273.8 kHz, not 72738 kHz. Dots aren't usually used in node names even though ePAPR permits them. However, this can easily be avoided by expressing the frequency in Hz, not kHz. This patch changes the name to refclk7273800hz, reflecting the actual clock speed. Signed-off-by: Dave Martin Acked-by: Liviu Dudau Signed-off-by: Olof Johansson --- arch/arm64/boot/dts/arm/juno-clocks.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/arm/juno-clocks.dtsi b/arch/arm64/boot/dts/arm/juno-clocks.dtsi index ea2b5666a16f..c9b89efe0f56 100644 --- a/arch/arm64/boot/dts/arm/juno-clocks.dtsi +++ b/arch/arm64/boot/dts/arm/juno-clocks.dtsi @@ -8,7 +8,7 @@ */ /* SoC fixed clocks */ - soc_uartclk: refclk72738khz { + soc_uartclk: refclk7273800hz { compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <7273800>; From e42391cd048809d903291d07f86ed3934ce138e9 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 29 Mar 2015 15:26:31 -0700 Subject: [PATCH 146/170] Linux 4.0-rc6 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 14c722f96877..da36a3be7969 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 0 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc6 NAME = Hurr durr I'ma sheep # *DOCUMENTATION* From ca76683930a1c6acb8dd22867eca2bedaab998e3 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Sat, 28 Mar 2015 18:05:44 +0100 Subject: [PATCH 147/170] dmaengine: jz4740: Define capabilities Setup the capabilities of the device/driver, so that users of the DMAengine API can query them. Signed-off-by: Lars-Peter Clausen Signed-off-by: Vinod Koul --- drivers/dma/dma-jz4740.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/dma/dma-jz4740.c b/drivers/dma/dma-jz4740.c index 4527a3ebeac4..84884418fd30 100644 --- a/drivers/dma/dma-jz4740.c +++ b/drivers/dma/dma-jz4740.c @@ -511,6 +511,9 @@ static void jz4740_dma_desc_free(struct virt_dma_desc *vdesc) kfree(container_of(vdesc, struct jz4740_dma_desc, vdesc)); } +#define JZ4740_DMA_BUSWIDTHS (BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \ + BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | BIT(DMA_SLAVE_BUSWIDTH_4_BYTES)) + static int jz4740_dma_probe(struct platform_device *pdev) { struct jz4740_dmaengine_chan *chan; @@ -548,6 +551,10 @@ static int jz4740_dma_probe(struct platform_device *pdev) dd->device_prep_dma_cyclic = jz4740_dma_prep_dma_cyclic; dd->device_config = jz4740_dma_slave_config; dd->device_terminate_all = jz4740_dma_terminate_all; + dd->src_addr_widths = JZ4740_DMA_BUSWIDTHS; + dd->dst_addr_widths = JZ4740_DMA_BUSWIDTHS; + dd->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV); + dd->residue_granularity = DMA_RESIDUE_GRANULARITY_BURST; dd->dev = &pdev->dev; INIT_LIST_HEAD(&dd->channels); From 5ca9e7ce6eebec53362ff779264143860ccf68cd Mon Sep 17 00:00:00 2001 From: Petr Kulhavy Date: Fri, 27 Mar 2015 13:35:51 +0200 Subject: [PATCH 148/170] dmaengine: edma: fix memory leak when terminating running transfers If edma_terminate_all() was called while a transfer was running (i.e. after edma_execute() but before edma_callback()) the echan->edesc was not freed. This was due to the fact that a running transfer is on none of the vchan lists: desc_submitted, desc_issued, desc_completed (edma_execute() removes it from the desc_issued list), so the vchan_dma_desc_free_list() called at the end of edma_terminate_all() didn't find it and didn't free it. This bug was found on an AM1808 based hardware (very similar to da850evm, however using the second MMC/SD controller), where intense operations on the SD card wasted the device 128MB RAM within a couple of days. Peter Ujfalusi: The issue is even more severe since it affects cyclic (audio) transfers as well. In this case starting/stopping audio will results memory leak. Signed-off-by: Petr Kulhavy Signed-off-by: Peter Ujfalusi CC: CC: Signed-off-by: Vinod Koul --- drivers/dma/edma.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c index 276157f22612..53dbd3b3384c 100644 --- a/drivers/dma/edma.c +++ b/drivers/dma/edma.c @@ -260,6 +260,13 @@ static int edma_terminate_all(struct dma_chan *chan) */ if (echan->edesc) { int cyclic = echan->edesc->cyclic; + + /* + * free the running request descriptor + * since it is not in any of the vdesc lists + */ + edma_desc_free(&echan->edesc->vdesc); + echan->edesc = NULL; edma_stop(echan->ch_num); /* Move the cyclic channel back to default queue */ From 02d88b735f5a60f04dbf6d051b76e1877a0d0844 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Fri, 27 Mar 2015 13:35:52 +0200 Subject: [PATCH 149/170] dmaengine: omap-dma: Fix memory leak when terminating running transfer In omap_dma_start_desc the vdesc->node is removed from the virt-dma framework managed lists (to be precise from the desc_issued list). If a terminate_all comes before the transfer finishes the omap_desc will not be freed up because it is not in any of the lists and we stopped the DMA channel so the transfer will not going to complete. There is no special sequence for leaking memory when using cyclic (audio) transfer: with every start and stop of a cyclic transfer the driver leaks struct omap_desc worth of memory. Free up the allocated memory directly in omap_dma_terminate_all() since the framework will not going to do that for us. Signed-off-by: Peter Ujfalusi CC: CC: Signed-off-by: Vinod Koul --- drivers/dma/omap-dma.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/dma/omap-dma.c b/drivers/dma/omap-dma.c index 7dd6dd121681..167dbaf65742 100644 --- a/drivers/dma/omap-dma.c +++ b/drivers/dma/omap-dma.c @@ -981,6 +981,7 @@ static int omap_dma_terminate_all(struct dma_chan *chan) * c->desc is NULL and exit.) */ if (c->desc) { + omap_dma_desc_free(&c->desc->vd); c->desc = NULL; /* Avoid stopping the dma twice */ if (!c->paused) From f93178291712772983845700b12fc1c8b32f2eb1 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Fri, 27 Mar 2015 13:35:53 +0200 Subject: [PATCH 150/170] dmaengine: bcm2835-dma: Fix memory leak when stopping a running transfer The vd->node is removed from the lists when the transfer started so the vchan_get_all_descriptors() will not find it. This results memory leak. Signed-off-by: Peter Ujfalusi Acked-by: Stephen Warren Signed-off-by: Vinod Koul --- drivers/dma/bcm2835-dma.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c index 0723096fb50a..c92d6a70ccf3 100644 --- a/drivers/dma/bcm2835-dma.c +++ b/drivers/dma/bcm2835-dma.c @@ -475,6 +475,7 @@ static int bcm2835_dma_terminate_all(struct dma_chan *chan) * c->desc is NULL and exit.) */ if (c->desc) { + bcm2835_dma_desc_free(&c->desc->vd); c->desc = NULL; bcm2835_dma_abort(c->chan_base); From fbef403aa7b377eb238dc6cade21213c315bc1a7 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Fri, 27 Mar 2015 13:35:55 +0200 Subject: [PATCH 151/170] dmaengine: moxart-dma: Fix memory leak when stopping a running transfer The vd->node is removed from the lists when the transfer started so the vchan_get_all_descriptors() will not find it. This results memory leak. Signed-off-by: Peter Ujfalusi Signed-off-by: Vinod Koul --- drivers/dma/moxart-dma.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/dma/moxart-dma.c b/drivers/dma/moxart-dma.c index 15cab7d79525..b4634109e010 100644 --- a/drivers/dma/moxart-dma.c +++ b/drivers/dma/moxart-dma.c @@ -193,8 +193,10 @@ static int moxart_terminate_all(struct dma_chan *chan) spin_lock_irqsave(&ch->vc.lock, flags); - if (ch->desc) + if (ch->desc) { + moxart_dma_desc_free(&ch->desc->vd); ch->desc = NULL; + } ctrl = readl(ch->base + REG_OFF_CTRL); ctrl &= ~(APB_DMA_ENABLE | APB_DMA_FIN_INT_EN | APB_DMA_ERR_INT_EN); From f3f03330dee0526d82f2a0fd1a79d207ed1ac439 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 30 Mar 2015 18:46:29 +0200 Subject: [PATCH 152/170] nfsd: require an explicit option to enable pNFS Turns out sending out layouts to any client is a bad idea if they can't get at the storage device, so require explicit admin action to enable pNFS. Signed-off-by: Christoph Hellwig Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4layouts.c | 2 +- include/uapi/linux/nfsd/export.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 80e236bf79fc..6904213a4363 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -118,7 +118,7 @@ void nfsd4_setup_layout_type(struct svc_export *exp) { struct super_block *sb = exp->ex_path.mnt->mnt_sb; - if (exp->ex_flags & NFSEXP_NOPNFS) + if (!(exp->ex_flags & NFSEXP_PNFS)) return; if (sb->s_export_op->get_uuid && diff --git a/include/uapi/linux/nfsd/export.h b/include/uapi/linux/nfsd/export.h index 4742f2cb42f2..d3bd6ffec041 100644 --- a/include/uapi/linux/nfsd/export.h +++ b/include/uapi/linux/nfsd/export.h @@ -47,7 +47,7 @@ * exported filesystem. */ #define NFSEXP_V4ROOT 0x10000 -#define NFSEXP_NOPNFS 0x20000 +#define NFSEXP_PNFS 0x20000 /* All flags that we claim to support. (Note we don't support NOACL.) */ #define NFSEXP_ALLFLAGS 0x3FE7F From 27705f7085ce2e124fac4c280ce824962cc90bb6 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Sat, 28 Mar 2015 19:13:22 +0100 Subject: [PATCH 153/170] ipvlan: fix addr hash list corruption When ipvlan interface with IP addresses attached is brought down and then deleted, the assigned addresses are deleted twice from the address hash list, first on the interface down and second on the link deletion. Similarly, when an address is added while the interface is down, it is added second time once the interface is brought up. When the interface is down, the addresses should be kept off the hash list for performance reasons. Ensure this is true, which also fixes the double add problem. To fix the double free, check whether the address is hashed before removing it. Reported-by: Dan Williams Signed-off-by: Jiri Benc Signed-off-by: Mahesh Bandewar Signed-off-by: David S. Miller --- drivers/net/ipvlan/ipvlan_core.c | 5 +++-- drivers/net/ipvlan/ipvlan_main.c | 12 ++++++++++-- 2 files changed, 13 insertions(+), 4 deletions(-) diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 2a175006028b..8a542b9340c4 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -81,12 +81,13 @@ void ipvlan_ht_addr_add(struct ipvl_dev *ipvlan, struct ipvl_addr *addr) hash = (addr->atype == IPVL_IPV6) ? ipvlan_get_v6_hash(&addr->ip6addr) : ipvlan_get_v4_hash(&addr->ip4addr); - hlist_add_head_rcu(&addr->hlnode, &port->hlhead[hash]); + if (hlist_unhashed(&addr->hlnode)) + hlist_add_head_rcu(&addr->hlnode, &port->hlhead[hash]); } void ipvlan_ht_addr_del(struct ipvl_addr *addr, bool sync) { - hlist_del_rcu(&addr->hlnode); + hlist_del_init_rcu(&addr->hlnode); if (sync) synchronize_rcu(); } diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 4f4099d5603d..1eb3f33e11cc 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -622,7 +622,11 @@ static int ipvlan_add_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr) addr->atype = IPVL_IPV6; list_add_tail_rcu(&addr->anode, &ipvlan->addrs); ipvlan->ipv6cnt++; - ipvlan_ht_addr_add(ipvlan, addr); + /* If the interface is not up, the address will be added to the hash + * list by ipvlan_open. + */ + if (netif_running(ipvlan->dev)) + ipvlan_ht_addr_add(ipvlan, addr); return 0; } @@ -690,7 +694,11 @@ static int ipvlan_add_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr) addr->atype = IPVL_IPV4; list_add_tail_rcu(&addr->anode, &ipvlan->addrs); ipvlan->ipv4cnt++; - ipvlan_ht_addr_add(ipvlan, addr); + /* If the interface is not up, the address will be added to the hash + * list by ipvlan_open. + */ + if (netif_running(ipvlan->dev)) + ipvlan_ht_addr_add(ipvlan, addr); ipvlan_set_broadcast_mac_filter(ipvlan, true); return 0; From 2afa650ce297bc2048bc3d059774be9c39734565 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Sat, 28 Mar 2015 19:13:23 +0100 Subject: [PATCH 154/170] ipvlan: protect against concurrent link removal Adding and removing to the 'ipvlans' list is already done using _rcu list operations. Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- drivers/net/ipvlan/ipvlan_core.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 8a542b9340c4..568628f95aa2 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -193,7 +193,8 @@ static void ipvlan_multicast_frame(struct ipvl_port *port, struct sk_buff *skb, if (skb->protocol == htons(ETH_P_PAUSE)) return; - list_for_each_entry(ipvlan, &port->ipvlans, pnode) { + rcu_read_lock(); + list_for_each_entry_rcu(ipvlan, &port->ipvlans, pnode) { if (local && (ipvlan == in_dev)) continue; @@ -220,6 +221,7 @@ static void ipvlan_multicast_frame(struct ipvl_port *port, struct sk_buff *skb, mcast_acct: ipvlan_count_rx(ipvlan, len, ret == NET_RX_SUCCESS, true); } + rcu_read_unlock(); /* Locally generated? ...Forward a copy to the main-device as * well. On the RX side we'll ignore it (wont give it to any From 40891e8ad630558caae26788d37bf50137b6d5d2 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Sat, 28 Mar 2015 19:13:24 +0100 Subject: [PATCH 155/170] ipvlan: do not use rcu operations for address list All accesses to ipvlan->addrs are under rtnl. Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- drivers/net/ipvlan/ipvlan_main.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 1eb3f33e11cc..aaa005bd21ce 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -505,7 +505,7 @@ static void ipvlan_link_delete(struct net_device *dev, struct list_head *head) if (ipvlan->ipv6cnt > 0 || ipvlan->ipv4cnt > 0) { list_for_each_entry_safe(addr, next, &ipvlan->addrs, anode) { ipvlan_ht_addr_del(addr, !dev->dismantle); - list_del_rcu(&addr->anode); + list_del(&addr->anode); } } list_del_rcu(&ipvlan->pnode); @@ -620,7 +620,7 @@ static int ipvlan_add_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr) addr->master = ipvlan; memcpy(&addr->ip6addr, ip6_addr, sizeof(struct in6_addr)); addr->atype = IPVL_IPV6; - list_add_tail_rcu(&addr->anode, &ipvlan->addrs); + list_add_tail(&addr->anode, &ipvlan->addrs); ipvlan->ipv6cnt++; /* If the interface is not up, the address will be added to the hash * list by ipvlan_open. @@ -640,7 +640,7 @@ static void ipvlan_del_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr) return; ipvlan_ht_addr_del(addr, true); - list_del_rcu(&addr->anode); + list_del(&addr->anode); ipvlan->ipv6cnt--; WARN_ON(ipvlan->ipv6cnt < 0); kfree_rcu(addr, rcu); @@ -692,7 +692,7 @@ static int ipvlan_add_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr) addr->master = ipvlan; memcpy(&addr->ip4addr, ip4_addr, sizeof(struct in_addr)); addr->atype = IPVL_IPV4; - list_add_tail_rcu(&addr->anode, &ipvlan->addrs); + list_add_tail(&addr->anode, &ipvlan->addrs); ipvlan->ipv4cnt++; /* If the interface is not up, the address will be added to the hash * list by ipvlan_open. @@ -713,7 +713,7 @@ static void ipvlan_del_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr) return; ipvlan_ht_addr_del(addr, true); - list_del_rcu(&addr->anode); + list_del(&addr->anode); ipvlan->ipv4cnt--; WARN_ON(ipvlan->ipv4cnt < 0); if (!ipvlan->ipv4cnt) From e9997c2938b23d792528da1597b3aea9b0f2a324 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Sat, 28 Mar 2015 19:13:25 +0100 Subject: [PATCH 156/170] ipvlan: fix check for IP addresses in control path When an ipvlan interface is down, its addresses are not on the hash list. Fix checks for existence of addresses not to depend on the hash list, walk through all interface addresses instead. Signed-off-by: Jiri Benc Acked-by: Mahesh Bandewar Signed-off-by: David S. Miller --- drivers/net/ipvlan/ipvlan.h | 4 +++- drivers/net/ipvlan/ipvlan_core.c | 21 +++++++++++++++------ drivers/net/ipvlan/ipvlan_main.c | 8 ++++---- 3 files changed, 22 insertions(+), 11 deletions(-) diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h index 924ea98bd531..54549a6223dd 100644 --- a/drivers/net/ipvlan/ipvlan.h +++ b/drivers/net/ipvlan/ipvlan.h @@ -114,7 +114,9 @@ unsigned int ipvlan_mac_hash(const unsigned char *addr); rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb); int ipvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev); void ipvlan_ht_addr_add(struct ipvl_dev *ipvlan, struct ipvl_addr *addr); -bool ipvlan_addr_busy(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6); +struct ipvl_addr *ipvlan_find_addr(const struct ipvl_dev *ipvlan, + const void *iaddr, bool is_v6); +bool ipvlan_addr_busy(struct ipvl_port *port, void *iaddr, bool is_v6); struct ipvl_addr *ipvlan_ht_addr_lookup(const struct ipvl_port *port, const void *iaddr, bool is_v6); void ipvlan_ht_addr_del(struct ipvl_addr *addr, bool sync); diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 568628f95aa2..b7877a194cfe 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -92,9 +92,9 @@ void ipvlan_ht_addr_del(struct ipvl_addr *addr, bool sync) synchronize_rcu(); } -bool ipvlan_addr_busy(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6) +struct ipvl_addr *ipvlan_find_addr(const struct ipvl_dev *ipvlan, + const void *iaddr, bool is_v6) { - struct ipvl_port *port = ipvlan->port; struct ipvl_addr *addr; list_for_each_entry(addr, &ipvlan->addrs, anode) { @@ -102,12 +102,21 @@ bool ipvlan_addr_busy(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6) ipv6_addr_equal(&addr->ip6addr, iaddr)) || (!is_v6 && addr->atype == IPVL_IPV4 && addr->ip4addr.s_addr == ((struct in_addr *)iaddr)->s_addr)) + return addr; + } + return NULL; +} + +bool ipvlan_addr_busy(struct ipvl_port *port, void *iaddr, bool is_v6) +{ + struct ipvl_dev *ipvlan; + + ASSERT_RTNL(); + + list_for_each_entry(ipvlan, &port->ipvlans, pnode) { + if (ipvlan_find_addr(ipvlan, iaddr, is_v6)) return true; } - - if (ipvlan_ht_addr_lookup(port, iaddr, is_v6)) - return true; - return false; } diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index aaa005bd21ce..4fa14208d799 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -607,7 +607,7 @@ static int ipvlan_add_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr) { struct ipvl_addr *addr; - if (ipvlan_addr_busy(ipvlan, ip6_addr, true)) { + if (ipvlan_addr_busy(ipvlan->port, ip6_addr, true)) { netif_err(ipvlan, ifup, ipvlan->dev, "Failed to add IPv6=%pI6c addr for %s intf\n", ip6_addr, ipvlan->dev->name); @@ -635,7 +635,7 @@ static void ipvlan_del_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr) { struct ipvl_addr *addr; - addr = ipvlan_ht_addr_lookup(ipvlan->port, ip6_addr, true); + addr = ipvlan_find_addr(ipvlan, ip6_addr, true); if (!addr) return; @@ -679,7 +679,7 @@ static int ipvlan_add_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr) { struct ipvl_addr *addr; - if (ipvlan_addr_busy(ipvlan, ip4_addr, false)) { + if (ipvlan_addr_busy(ipvlan->port, ip4_addr, false)) { netif_err(ipvlan, ifup, ipvlan->dev, "Failed to add IPv4=%pI4 on %s intf.\n", ip4_addr, ipvlan->dev->name); @@ -708,7 +708,7 @@ static void ipvlan_del_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr) { struct ipvl_addr *addr; - addr = ipvlan_ht_addr_lookup(ipvlan->port, ip4_addr, false); + addr = ipvlan_find_addr(ipvlan, ip4_addr, false); if (!addr) return; From f5e2dc5d7fe78fe4d8748d217338f4f7b6a5d7ea Mon Sep 17 00:00:00 2001 From: Anton Nayshtut Date: Sun, 29 Mar 2015 14:20:25 +0300 Subject: [PATCH 157/170] bonding: Bonding Overriding Configuration logic restored. Before commit 3900f29021f0bc7fe9815aa32f1a993b7dfdd402 ("bonding: slight optimizztion for bond_slave_override()") the override logic was to send packets with non-zero queue_id through the slave with corresponding queue_id, under two conditions only - if the slave can transmit and it's up. The above mentioned commit changed this logic by introducing an additional condition - whether the bond is active (indirectly, using the slave_can_tx and later - bond_is_active_slave), that prevents the user from implementing more complex policies according to the Documentation/networking/bonding.txt. Signed-off-by: Anton Nayshtut Signed-off-by: Alexey Bogoslavsky Signed-off-by: Andy Gospodarek Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index b979c265fc51..089a4028859d 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3850,7 +3850,8 @@ static inline int bond_slave_override(struct bonding *bond, /* Find out if any slaves have the same mapping as this skb. */ bond_for_each_slave_rcu(bond, slave, iter) { if (slave->queue_id == skb->queue_mapping) { - if (bond_slave_can_tx(slave)) { + if (bond_slave_is_up(slave) && + slave->link == BOND_LINK_UP) { bond_dev_queue_xmit(bond, skb, slave->dev); return 0; } From 5899f0478528b59ea9ced201eacb3e56ca406c39 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Sun, 29 Mar 2015 16:05:28 +0200 Subject: [PATCH 158/170] netlink: pad nla_memcpy dest buffer with zeroes This is especially important in cases where the kernel allocs a new structure and expects a field to be set from a netlink attribute. If such attribute is shorter than expected, the rest of the field is left containing previous data. When such field is read back by the user space, kernel memory content is leaked. Signed-off-by: Jiri Benc Acked-by: Thomas Graf Signed-off-by: David S. Miller --- lib/nlattr.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/lib/nlattr.c b/lib/nlattr.c index 76a1b59523ab..f5907d23272d 100644 --- a/lib/nlattr.c +++ b/lib/nlattr.c @@ -279,6 +279,8 @@ int nla_memcpy(void *dest, const struct nlattr *src, int count) int minlen = min_t(int, count, nla_len(src)); memcpy(dest, nla_data(src), minlen); + if (count > minlen) + memset(dest + minlen, 0, count - minlen); return minlen; } From f9c72d10d6fbf949558cd088389a42213ed7b12d Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Tue, 31 Mar 2015 12:03:28 -0400 Subject: [PATCH 159/170] sunrpc: make debugfs file creation failure non-fatal We currently have a problem that SELinux policy is being enforced when creating debugfs files. If a debugfs file is created as a side effect of doing some syscall, then that creation can fail if the SELinux policy for that process prevents it. This seems wrong. We don't do that for files under /proc, for instance, so Bruce has proposed a patch to fix that. While discussing that patch however, Greg K.H. stated: "No kernel code should care / fail if a debugfs function fails, so please fix up the sunrpc code first." This patch converts all of the sunrpc debugfs setup code to be void return functins, and the callers to not look for errors from those functions. This should allow rpc_clnt and rpc_xprt creation to work, even if the kernel fails to create debugfs files for some reason. Symptoms were failing krb5 mounts on systems using gss-proxy and selinux. Fixes: 388f0c776781 "sunrpc: add a debugfs rpc_xprt directory..." Cc: stable@vger.kernel.org Signed-off-by: Jeff Layton Acked-by: Greg Kroah-Hartman Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/debug.h | 18 ++++++------- net/sunrpc/clnt.c | 4 +-- net/sunrpc/debugfs.c | 52 ++++++++++++++++++++---------------- net/sunrpc/sunrpc_syms.c | 7 +---- net/sunrpc/xprt.c | 7 +---- 5 files changed, 41 insertions(+), 47 deletions(-) diff --git a/include/linux/sunrpc/debug.h b/include/linux/sunrpc/debug.h index c57d8ea0716c..59a7889e15db 100644 --- a/include/linux/sunrpc/debug.h +++ b/include/linux/sunrpc/debug.h @@ -60,17 +60,17 @@ struct rpc_xprt; #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) void rpc_register_sysctl(void); void rpc_unregister_sysctl(void); -int sunrpc_debugfs_init(void); +void sunrpc_debugfs_init(void); void sunrpc_debugfs_exit(void); -int rpc_clnt_debugfs_register(struct rpc_clnt *); +void rpc_clnt_debugfs_register(struct rpc_clnt *); void rpc_clnt_debugfs_unregister(struct rpc_clnt *); -int rpc_xprt_debugfs_register(struct rpc_xprt *); +void rpc_xprt_debugfs_register(struct rpc_xprt *); void rpc_xprt_debugfs_unregister(struct rpc_xprt *); #else -static inline int +static inline void sunrpc_debugfs_init(void) { - return 0; + return; } static inline void @@ -79,10 +79,10 @@ sunrpc_debugfs_exit(void) return; } -static inline int +static inline void rpc_clnt_debugfs_register(struct rpc_clnt *clnt) { - return 0; + return; } static inline void @@ -91,10 +91,10 @@ rpc_clnt_debugfs_unregister(struct rpc_clnt *clnt) return; } -static inline int +static inline void rpc_xprt_debugfs_register(struct rpc_xprt *xprt) { - return 0; + return; } static inline void diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 612aa73bbc60..e6ce1517367f 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -303,9 +303,7 @@ static int rpc_client_register(struct rpc_clnt *clnt, struct super_block *pipefs_sb; int err; - err = rpc_clnt_debugfs_register(clnt); - if (err) - return err; + rpc_clnt_debugfs_register(clnt); pipefs_sb = rpc_get_sb_net(net); if (pipefs_sb) { diff --git a/net/sunrpc/debugfs.c b/net/sunrpc/debugfs.c index e811f390f9f6..82962f7e6e88 100644 --- a/net/sunrpc/debugfs.c +++ b/net/sunrpc/debugfs.c @@ -129,48 +129,52 @@ static const struct file_operations tasks_fops = { .release = tasks_release, }; -int +void rpc_clnt_debugfs_register(struct rpc_clnt *clnt) { - int len, err; + int len; char name[24]; /* enough for "../../rpc_xprt/ + 8 hex digits + NULL */ + struct rpc_xprt *xprt; /* Already registered? */ - if (clnt->cl_debugfs) - return 0; + if (clnt->cl_debugfs || !rpc_clnt_dir) + return; len = snprintf(name, sizeof(name), "%x", clnt->cl_clid); if (len >= sizeof(name)) - return -EINVAL; + return; /* make the per-client dir */ clnt->cl_debugfs = debugfs_create_dir(name, rpc_clnt_dir); if (!clnt->cl_debugfs) - return -ENOMEM; + return; /* make tasks file */ - err = -ENOMEM; if (!debugfs_create_file("tasks", S_IFREG | S_IRUSR, clnt->cl_debugfs, clnt, &tasks_fops)) goto out_err; - err = -EINVAL; rcu_read_lock(); + xprt = rcu_dereference(clnt->cl_xprt); + /* no "debugfs" dentry? Don't bother with the symlink. */ + if (!xprt->debugfs) { + rcu_read_unlock(); + return; + } len = snprintf(name, sizeof(name), "../../rpc_xprt/%s", - rcu_dereference(clnt->cl_xprt)->debugfs->d_name.name); + xprt->debugfs->d_name.name); rcu_read_unlock(); + if (len >= sizeof(name)) goto out_err; - err = -ENOMEM; if (!debugfs_create_symlink("xprt", clnt->cl_debugfs, name)) goto out_err; - return 0; + return; out_err: debugfs_remove_recursive(clnt->cl_debugfs); clnt->cl_debugfs = NULL; - return err; } void @@ -226,33 +230,33 @@ static const struct file_operations xprt_info_fops = { .release = xprt_info_release, }; -int +void rpc_xprt_debugfs_register(struct rpc_xprt *xprt) { int len, id; static atomic_t cur_id; char name[9]; /* 8 hex digits + NULL term */ + if (!rpc_xprt_dir) + return; + id = (unsigned int)atomic_inc_return(&cur_id); len = snprintf(name, sizeof(name), "%x", id); if (len >= sizeof(name)) - return -EINVAL; + return; /* make the per-client dir */ xprt->debugfs = debugfs_create_dir(name, rpc_xprt_dir); if (!xprt->debugfs) - return -ENOMEM; + return; /* make tasks file */ if (!debugfs_create_file("info", S_IFREG | S_IRUSR, xprt->debugfs, xprt, &xprt_info_fops)) { debugfs_remove_recursive(xprt->debugfs); xprt->debugfs = NULL; - return -ENOMEM; } - - return 0; } void @@ -266,14 +270,17 @@ void __exit sunrpc_debugfs_exit(void) { debugfs_remove_recursive(topdir); + topdir = NULL; + rpc_clnt_dir = NULL; + rpc_xprt_dir = NULL; } -int __init +void __init sunrpc_debugfs_init(void) { topdir = debugfs_create_dir("sunrpc", NULL); if (!topdir) - goto out; + return; rpc_clnt_dir = debugfs_create_dir("rpc_clnt", topdir); if (!rpc_clnt_dir) @@ -283,10 +290,9 @@ sunrpc_debugfs_init(void) if (!rpc_xprt_dir) goto out_remove; - return 0; + return; out_remove: debugfs_remove_recursive(topdir); topdir = NULL; -out: - return -ENOMEM; + rpc_clnt_dir = NULL; } diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c index e37fbed87956..ee5d3d253102 100644 --- a/net/sunrpc/sunrpc_syms.c +++ b/net/sunrpc/sunrpc_syms.c @@ -98,10 +98,7 @@ init_sunrpc(void) if (err) goto out4; - err = sunrpc_debugfs_init(); - if (err) - goto out5; - + sunrpc_debugfs_init(); #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) rpc_register_sysctl(); #endif @@ -109,8 +106,6 @@ init_sunrpc(void) init_socket_xprt(); /* clnt sock transport */ return 0; -out5: - unregister_rpc_pipefs(); out4: unregister_pernet_subsys(&sunrpc_net_ops); out3: diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index e3015aede0d9..9949722d99ce 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1331,7 +1331,6 @@ static void xprt_init(struct rpc_xprt *xprt, struct net *net) */ struct rpc_xprt *xprt_create_transport(struct xprt_create *args) { - int err; struct rpc_xprt *xprt; struct xprt_class *t; @@ -1372,11 +1371,7 @@ struct rpc_xprt *xprt_create_transport(struct xprt_create *args) return ERR_PTR(-ENOMEM); } - err = rpc_xprt_debugfs_register(xprt); - if (err) { - xprt_destroy(xprt); - return ERR_PTR(err); - } + rpc_xprt_debugfs_register(xprt); dprintk("RPC: created transport %p with %u slots\n", xprt, xprt->max_reqs); From fa2d8ff4e3522b4e05f590575d3eb8087f3a8cdc Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Mon, 30 Mar 2015 13:57:41 +0200 Subject: [PATCH 160/170] openvswitch: Return vport module ref before destruction Return module reference before invoking the respective vport ->destroy() function. This is needed as ovs_vport_del() is not invoked inside an RCU read side critical section so the kfree can occur immediately before returning to ovs_vport_del(). Returning the module reference before ->destroy() is safe because the module unregistration is blocked on ovs_lock which we hold while destroying the datapath. Fixes: 62b9c8d0372d ("ovs: Turn vports with dependencies into separate modules") Reported-by: Pravin Shelar Signed-off-by: Thomas Graf Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- net/openvswitch/vport.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index ec2954ffc690..067a3fff1d2c 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -274,10 +274,8 @@ void ovs_vport_del(struct vport *vport) ASSERT_OVSL(); hlist_del_rcu(&vport->hash_node); - - vport->ops->destroy(vport); - module_put(vport->ops->owner); + vport->ops->destroy(vport); } /** From ed4ac4221776a5103faf71a4032ca00178d6e66b Mon Sep 17 00:00:00 2001 From: Eugene Crosser Date: Mon, 30 Mar 2015 15:40:42 +0200 Subject: [PATCH 161/170] af_iucv: fix AF_IUCV sendmsg() errno When sending over AF_IUCV socket, errno was incorrectly set to ENOMEM even when other values where appropriate, notably EAGAIN. With this patch, error indicator returned by sock_alloc_send_skb() is passed to the caller, rather than being overwritten with ENOMEM. Signed-off-by: Eugene Crosser Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- net/iucv/af_iucv.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 2e9953b2db84..53d931172088 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1114,10 +1114,8 @@ static int iucv_sock_sendmsg(struct kiocb *iocb, struct socket *sock, noblock, &err); else skb = sock_alloc_send_skb(sk, len, noblock, &err); - if (!skb) { - err = -ENOMEM; + if (!skb) goto out; - } if (iucv->transport == AF_IUCV_TRANS_HIPER) skb_reserve(skb, sizeof(struct af_iucv_trans_hdr) + ETH_HLEN); if (memcpy_from_msg(skb_put(skb, len), msg, len)) { From 347eec348a9b0ba6968145cc7b1995d2475ae31b Mon Sep 17 00:00:00 2001 From: Christian Hesse Date: Tue, 31 Mar 2015 14:10:07 +0200 Subject: [PATCH 162/170] net/usb/r8152: add device id for Lenovo TP USB 3.0 Ethernet This device is sold as 'Lenovo Tinkpad USB 3.0 Ethernet 4X90E51405'. Chipset is RTL8153 and works with r8152. Signed-off-by: Christian Hesse Signed-off-by: David S. Miller --- drivers/net/usb/cdc_ether.c | 8 ++++++++ drivers/net/usb/r8152.c | 2 ++ 2 files changed, 10 insertions(+) diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index 9311a08565be..4545e78840b0 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -522,6 +522,7 @@ static const struct driver_info wwan_info = { #define DELL_VENDOR_ID 0x413C #define REALTEK_VENDOR_ID 0x0bda #define SAMSUNG_VENDOR_ID 0x04e8 +#define LENOVO_VENDOR_ID 0x17ef static const struct usb_device_id products[] = { /* BLACKLIST !! @@ -702,6 +703,13 @@ static const struct usb_device_id products[] = { .driver_info = 0, }, +/* Lenovo Thinkpad USB 3.0 Ethernet Adapters (based on Realtek RTL8153) */ +{ + USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0x7205, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), + .driver_info = 0, +}, + /* WHITELIST!!! * * CDC Ether uses two interfaces, not necessarily consecutive. diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 438fc6bcaef1..9f7c0ab3b349 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -492,6 +492,7 @@ enum rtl8152_flags { /* Define these values to match your device */ #define VENDOR_ID_REALTEK 0x0bda #define VENDOR_ID_SAMSUNG 0x04e8 +#define VENDOR_ID_LENOVO 0x17ef #define MCU_TYPE_PLA 0x0100 #define MCU_TYPE_USB 0x0000 @@ -4037,6 +4038,7 @@ static struct usb_device_id rtl8152_table[] = { {REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, 0x8152)}, {REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, 0x8153)}, {REALTEK_USB_DEVICE(VENDOR_ID_SAMSUNG, 0xa101)}, + {REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x7205)}, {} }; From 7e436905780659d6dc12d0581944934bf91a9919 Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Wed, 1 Apr 2015 09:42:50 +0800 Subject: [PATCH 163/170] tipc: fix a slab object leak When remove TIPC module, there is a warning to remind us that a slab object is leaked like: root@localhost:~# rmmod tipc [ 19.056226] ============================================================================= [ 19.057549] BUG TIPC (Not tainted): Objects remaining in TIPC on kmem_cache_close() [ 19.058736] ----------------------------------------------------------------------------- [ 19.058736] [ 19.060287] INFO: Slab 0xffffea0000519a00 objects=23 used=1 fp=0xffff880014668b00 flags=0x100000000004080 [ 19.061915] INFO: Object 0xffff880014668000 @offset=0 [ 19.062717] kmem_cache_destroy TIPC: Slab cache still has objects This is because the listening socket of TIPC topology server is not closed before TIPC proto handler is unregistered with proto_unregister(). However, as the socket is closed in tipc_exit_net() which is called by unregister_pernet_subsys() during unregistering TIPC namespace operation, the warning can be eliminated if calling unregister_pernet_subsys() is moved before calling proto_unregister(). Fixes: e05b31f4bf89 ("tipc: make tipc socket support net namespace") Reviewed-by: Erik Hugne Signed-off-by: Ying Xue Signed-off-by: David S. Miller --- net/tipc/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/tipc/core.c b/net/tipc/core.c index 935205e6bcfe..be1c9fa60b09 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -152,11 +152,11 @@ static int __init tipc_init(void) static void __exit tipc_exit(void) { tipc_bearer_cleanup(); + unregister_pernet_subsys(&tipc_net_ops); tipc_netlink_stop(); tipc_netlink_compat_stop(); tipc_socket_stop(); tipc_unregister_sysctl(); - unregister_pernet_subsys(&tipc_net_ops); pr_info("Deactivated\n"); } From 2f30232481ef39aa1657ac76b16c47d0c0241a69 Mon Sep 17 00:00:00 2001 From: Jeff Kirsher Date: Wed, 25 Mar 2015 17:01:03 -0700 Subject: [PATCH 164/170] MAINTAINERS: Update Intel Wired Ethernet Driver info Update the git tree info with a recent change in tree names. Also add our new mailing list created solely for Linux kernel patches and kernel development, as well as the new patchwork project for tracking patches. Lastly update the list of "reviewers" since a couple of developers have moved on to different projects. Made an update to the section header so that it is more manageable going forward as we add new drivers. Signed-off-by: Jeff Kirsher --- MAINTAINERS | 25 ++++++++++++------------- 1 file changed, 12 insertions(+), 13 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 358eb0105e00..9508870ce2e0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5128,22 +5128,21 @@ M: Deepak Saxena S: Maintained F: drivers/char/hw_random/ixp4xx-rng.c -INTEL ETHERNET DRIVERS (e100/e1000/e1000e/fm10k/igb/igbvf/ixgb/ixgbe/ixgbevf/i40e/i40evf) +INTEL ETHERNET DRIVERS M: Jeff Kirsher -M: Jesse Brandeburg -M: Bruce Allan -M: Carolyn Wyborny -M: Don Skidmore -M: Greg Rose -M: Matthew Vick -M: John Ronciak -M: Mitch Williams -M: Linux NICS -L: e1000-devel@lists.sourceforge.net +R: Jesse Brandeburg +R: Shannon Nelson +R: Carolyn Wyborny +R: Don Skidmore +R: Matthew Vick +R: John Ronciak +R: Mitch Williams +L: intel-wired-lan@lists.osuosl.org W: http://www.intel.com/support/feedback.htm W: http://e1000.sourceforge.net/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net.git -T: git git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-next.git +Q: http://patchwork.ozlabs.org/project/intel-wired-lan/list/ +T: git git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-queue.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue.git S: Supported F: Documentation/networking/e100.txt F: Documentation/networking/e1000.txt From 788211d81bfdf9b6a547d0530f206ba6ee76b107 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 1 Apr 2015 14:20:42 +0200 Subject: [PATCH 165/170] mac80211: fix RX A-MPDU session reorder timer deletion There's an issue with the way the RX A-MPDU reorder timer is deleted that can cause a kernel crash like this: * tid_rx is removed - call_rcu(ieee80211_free_tid_rx) * station is destroyed * reorder timer fires before ieee80211_free_tid_rx() runs, accessing the station, thus potentially crashing due to the use-after-free The station deletion is protected by synchronize_net(), but that isn't enough -- ieee80211_free_tid_rx() need not have run when that returns (it deletes the timer.) We could use rcu_barrier() instead of synchronize_net(), but that's much more expensive. Instead, to fix this, add a field tracking that the session is being deleted. In this case, the only re-arming of the timer happens with the reorder spinlock held, so make that code not rearm it if the session is being deleted and also delete the timer after setting that field. This ensures the timer cannot fire after ___ieee80211_stop_rx_ba_session() returns, which fixes the problem. Cc: stable@vger.kernel.org Signed-off-by: Johannes Berg --- net/mac80211/agg-rx.c | 8 ++++++-- net/mac80211/rx.c | 7 ++++--- net/mac80211/sta_info.h | 2 ++ 3 files changed, 12 insertions(+), 5 deletions(-) diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index a48bad468880..7702978a4c99 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -49,8 +49,6 @@ static void ieee80211_free_tid_rx(struct rcu_head *h) container_of(h, struct tid_ampdu_rx, rcu_head); int i; - del_timer_sync(&tid_rx->reorder_timer); - for (i = 0; i < tid_rx->buf_size; i++) __skb_queue_purge(&tid_rx->reorder_buf[i]); kfree(tid_rx->reorder_buf); @@ -93,6 +91,12 @@ void ___ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, del_timer_sync(&tid_rx->session_timer); + /* make sure ieee80211_sta_reorder_release() doesn't re-arm the timer */ + spin_lock_bh(&tid_rx->reorder_lock); + tid_rx->removed = true; + spin_unlock_bh(&tid_rx->reorder_lock); + del_timer_sync(&tid_rx->reorder_timer); + call_rcu(&tid_rx->rcu_head, ieee80211_free_tid_rx); } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 944bdc04e913..1eb730bf8752 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -873,9 +873,10 @@ static void ieee80211_sta_reorder_release(struct ieee80211_sub_if_data *sdata, set_release_timer: - mod_timer(&tid_agg_rx->reorder_timer, - tid_agg_rx->reorder_time[j] + 1 + - HT_RX_REORDER_BUF_TIMEOUT); + if (!tid_agg_rx->removed) + mod_timer(&tid_agg_rx->reorder_timer, + tid_agg_rx->reorder_time[j] + 1 + + HT_RX_REORDER_BUF_TIMEOUT); } else { del_timer(&tid_agg_rx->reorder_timer); } diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 925e68fe64c7..fb0fc1302a58 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -175,6 +175,7 @@ struct tid_ampdu_tx { * @reorder_lock: serializes access to reorder buffer, see below. * @auto_seq: used for offloaded BA sessions to automatically pick head_seq_and * and ssn. + * @removed: this session is removed (but might have been found due to RCU) * * This structure's lifetime is managed by RCU, assignments to * the array holding it must hold the aggregation mutex. @@ -199,6 +200,7 @@ struct tid_ampdu_rx { u16 timeout; u8 dialog_token; bool auto_seq; + bool removed; }; /** From 3d6b72534a109be4353b161a09a5683b441d0941 Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Wed, 1 Apr 2015 10:02:19 +0300 Subject: [PATCH 166/170] bnx2x: Fix kdump on 4-port device When running in a kdump kernel, it's very likely that due to sync. loss with management firmware the first PCI function to probe and reach the previous unload flow would decide it can reset the chip and continue onward. While doing so, it will only close its own Rx port. On a 4-port device where 2nd port on engine is a 1g-port, the 2nd port would allow ingress traffic after the chip is reset [assuming it was active on the first kernel]. This would later cause a HW attention. This changes driver flow to close both ports' 1g capabilities during the previous driver unload flow prior to the chip reset. Signed-off-by: Yuval Mintz Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- .../net/ethernet/broadcom/bnx2x/bnx2x_main.c | 53 ++++++++++++------- 1 file changed, 35 insertions(+), 18 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index ae571a199f2f..e6dec47fec68 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -129,8 +129,8 @@ struct bnx2x_mac_vals { u32 xmac_val; u32 emac_addr; u32 emac_val; - u32 umac_addr; - u32 umac_val; + u32 umac_addr[2]; + u32 umac_val[2]; u32 bmac_addr; u32 bmac_val[2]; }; @@ -10141,6 +10141,25 @@ static u32 bnx2x_get_pretend_reg(struct bnx2x *bp) return base + (BP_ABS_FUNC(bp)) * stride; } +static bool bnx2x_prev_unload_close_umac(struct bnx2x *bp, + u8 port, u32 reset_reg, + struct bnx2x_mac_vals *vals) +{ + u32 mask = MISC_REGISTERS_RESET_REG_2_UMAC0 << port; + u32 base_addr; + + if (!(mask & reset_reg)) + return false; + + BNX2X_DEV_INFO("Disable umac Rx %02x\n", port); + base_addr = port ? GRCBASE_UMAC1 : GRCBASE_UMAC0; + vals->umac_addr[port] = base_addr + UMAC_REG_COMMAND_CONFIG; + vals->umac_val[port] = REG_RD(bp, vals->umac_addr[port]); + REG_WR(bp, vals->umac_addr[port], 0); + + return true; +} + static void bnx2x_prev_unload_close_mac(struct bnx2x *bp, struct bnx2x_mac_vals *vals) { @@ -10149,10 +10168,7 @@ static void bnx2x_prev_unload_close_mac(struct bnx2x *bp, u8 port = BP_PORT(bp); /* reset addresses as they also mark which values were changed */ - vals->bmac_addr = 0; - vals->umac_addr = 0; - vals->xmac_addr = 0; - vals->emac_addr = 0; + memset(vals, 0, sizeof(*vals)); reset_reg = REG_RD(bp, MISC_REG_RESET_REG_2); @@ -10201,15 +10217,11 @@ static void bnx2x_prev_unload_close_mac(struct bnx2x *bp, REG_WR(bp, vals->xmac_addr, 0); mac_stopped = true; } - mask = MISC_REGISTERS_RESET_REG_2_UMAC0 << port; - if (mask & reset_reg) { - BNX2X_DEV_INFO("Disable umac Rx\n"); - base_addr = BP_PORT(bp) ? GRCBASE_UMAC1 : GRCBASE_UMAC0; - vals->umac_addr = base_addr + UMAC_REG_COMMAND_CONFIG; - vals->umac_val = REG_RD(bp, vals->umac_addr); - REG_WR(bp, vals->umac_addr, 0); - mac_stopped = true; - } + + mac_stopped |= bnx2x_prev_unload_close_umac(bp, 0, + reset_reg, vals); + mac_stopped |= bnx2x_prev_unload_close_umac(bp, 1, + reset_reg, vals); } if (mac_stopped) @@ -10505,8 +10517,11 @@ static int bnx2x_prev_unload_common(struct bnx2x *bp) /* Close the MAC Rx to prevent BRB from filling up */ bnx2x_prev_unload_close_mac(bp, &mac_vals); - /* close LLH filters towards the BRB */ + /* close LLH filters for both ports towards the BRB */ bnx2x_set_rx_filter(&bp->link_params, 0); + bp->link_params.port ^= 1; + bnx2x_set_rx_filter(&bp->link_params, 0); + bp->link_params.port ^= 1; /* Check if the UNDI driver was previously loaded */ if (bnx2x_prev_is_after_undi(bp)) { @@ -10553,8 +10568,10 @@ static int bnx2x_prev_unload_common(struct bnx2x *bp) if (mac_vals.xmac_addr) REG_WR(bp, mac_vals.xmac_addr, mac_vals.xmac_val); - if (mac_vals.umac_addr) - REG_WR(bp, mac_vals.umac_addr, mac_vals.umac_val); + if (mac_vals.umac_addr[0]) + REG_WR(bp, mac_vals.umac_addr[0], mac_vals.umac_val[0]); + if (mac_vals.umac_addr[1]) + REG_WR(bp, mac_vals.umac_addr[1], mac_vals.umac_val[1]); if (mac_vals.emac_addr) REG_WR(bp, mac_vals.emac_addr, mac_vals.emac_val); if (mac_vals.bmac_addr) { From da254fbc6357a66a127e4e4e234b4f9c555d5ed1 Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Wed, 1 Apr 2015 10:02:20 +0300 Subject: [PATCH 167/170] bnx2x: Fix kdump when iommu=on When IOMM-vtd is active, once main kernel crashes unfinished DMAE transactions will be blocked, putting the HW in an error state which will cause further transactions to timeout. Current employed logic uses wrong macros, causing the first function to be the only function that cleanups that error state during its probe/load. This patch allows all the functions to successfully re-load in kdump kernel. Signed-off-by: Yuval Mintz Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- .../net/ethernet/broadcom/bnx2x/bnx2x_main.c | 39 ++++++++----------- 1 file changed, 16 insertions(+), 23 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index e6dec47fec68..1ec635f54994 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -7866,6 +7866,20 @@ int bnx2x_init_hw_func_cnic(struct bnx2x *bp) return 0; } +/* previous driver DMAE transaction may have occurred when pre-boot stage ended + * and boot began, or when kdump kernel was loaded. Either case would invalidate + * the addresses of the transaction, resulting in was-error bit set in the pci + * causing all hw-to-host pcie transactions to timeout. If this happened we want + * to clear the interrupt which detected this from the pglueb and the was done + * bit + */ +static void bnx2x_clean_pglue_errors(struct bnx2x *bp) +{ + if (!CHIP_IS_E1x(bp)) + REG_WR(bp, PGLUE_B_REG_WAS_ERROR_PF_7_0_CLR, + 1 << BP_ABS_FUNC(bp)); +} + static int bnx2x_init_hw_func(struct bnx2x *bp) { int port = BP_PORT(bp); @@ -7958,8 +7972,7 @@ static int bnx2x_init_hw_func(struct bnx2x *bp) bnx2x_init_block(bp, BLOCK_PGLUE_B, init_phase); - if (!CHIP_IS_E1x(bp)) - REG_WR(bp, PGLUE_B_REG_WAS_ERROR_PF_7_0_CLR, func); + bnx2x_clean_pglue_errors(bp); bnx2x_init_block(bp, BLOCK_ATC, init_phase); bnx2x_init_block(bp, BLOCK_DMAE, init_phase); @@ -10588,26 +10601,6 @@ static int bnx2x_prev_unload_common(struct bnx2x *bp) return bnx2x_prev_mcp_done(bp); } -/* previous driver DMAE transaction may have occurred when pre-boot stage ended - * and boot began, or when kdump kernel was loaded. Either case would invalidate - * the addresses of the transaction, resulting in was-error bit set in the pci - * causing all hw-to-host pcie transactions to timeout. If this happened we want - * to clear the interrupt which detected this from the pglueb and the was done - * bit - */ -static void bnx2x_prev_interrupted_dmae(struct bnx2x *bp) -{ - if (!CHIP_IS_E1x(bp)) { - u32 val = REG_RD(bp, PGLUE_B_REG_PGLUE_B_INT_STS); - if (val & PGLUE_B_PGLUE_B_INT_STS_REG_WAS_ERROR_ATTN) { - DP(BNX2X_MSG_SP, - "'was error' bit was found to be set in pglueb upon startup. Clearing\n"); - REG_WR(bp, PGLUE_B_REG_WAS_ERROR_PF_7_0_CLR, - 1 << BP_FUNC(bp)); - } - } -} - static int bnx2x_prev_unload(struct bnx2x *bp) { int time_counter = 10; @@ -10617,7 +10610,7 @@ static int bnx2x_prev_unload(struct bnx2x *bp) /* clear hw from errors which may have resulted from an interrupted * dmae transaction. */ - bnx2x_prev_interrupted_dmae(bp); + bnx2x_clean_pglue_errors(bp); /* Release previously held locks */ hw_lock_reg = (BP_FUNC(bp) <= 5) ? From e1b7c029a31a26e42c76f763b7cd566ecf62cbd2 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 1 Apr 2015 17:03:30 +1030 Subject: [PATCH 168/170] lguest: now needs PCI_DIRECT. Since commit 8e7094694396 ("lguest: add a dummy PCI host bridge.") lguest uses PCI, but it needs you to frob the ports directly. Signed-off-by: Rusty Russell Acked-by: Ingo Molnar Signed-off-by: Linus Torvalds --- drivers/lguest/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/lguest/Kconfig b/drivers/lguest/Kconfig index ee035ec4526b..169172d2ba05 100644 --- a/drivers/lguest/Kconfig +++ b/drivers/lguest/Kconfig @@ -1,6 +1,6 @@ config LGUEST tristate "Linux hypervisor example code" - depends on X86_32 && EVENTFD && TTY + depends on X86_32 && EVENTFD && TTY && PCI_DIRECT select HVC_DRIVER ---help--- This is a very simple module which allows you to run From 7ef65a42111270f343b26673c10e48180871326b Mon Sep 17 00:00:00 2001 From: Hariprasad Shenai Date: Wed, 1 Apr 2015 21:41:15 +0530 Subject: [PATCH 169/170] cxgb4: Firmware macro changes for fw verison 1.13.32.0 Adds new macro and few macro changes for fw version 1.13.32.0 also changes version string in driver to match 1.13.32.0 Signed-off-by: Hariprasad Shenai Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h | 39 ++++++++++++++++++- .../net/ethernet/chelsio/cxgb4/t4fw_version.h | 8 ++-- 2 files changed, 41 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h index 9b353a88cbda..a4a19e0ec7f5 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h @@ -101,7 +101,7 @@ enum fw_wr_opcodes { FW_RI_BIND_MW_WR = 0x18, FW_RI_FR_NSMR_WR = 0x19, FW_RI_INV_LSTAG_WR = 0x1a, - FW_LASTC2E_WR = 0x40 + FW_LASTC2E_WR = 0x70 }; struct fw_wr_hdr { @@ -993,6 +993,7 @@ enum fw_memtype_cf { FW_MEMTYPE_CF_EXTMEM = 0x2, FW_MEMTYPE_CF_FLASH = 0x4, FW_MEMTYPE_CF_INTERNAL = 0x5, + FW_MEMTYPE_CF_EXTMEM1 = 0x6, }; struct fw_caps_config_cmd { @@ -1035,6 +1036,7 @@ enum fw_params_mnem { FW_PARAMS_MNEM_PFVF = 2, /* function params */ FW_PARAMS_MNEM_REG = 3, /* limited register access */ FW_PARAMS_MNEM_DMAQ = 4, /* dma queue params */ + FW_PARAMS_MNEM_CHNET = 5, /* chnet params */ FW_PARAMS_MNEM_LAST }; @@ -3102,7 +3104,8 @@ enum fw_devlog_facility { FW_DEVLOG_FACILITY_FCOE = 0x2E, FW_DEVLOG_FACILITY_FOISCSI = 0x30, FW_DEVLOG_FACILITY_FOFCOE = 0x32, - FW_DEVLOG_FACILITY_MAX = 0x32, + FW_DEVLOG_FACILITY_CHNET = 0x34, + FW_DEVLOG_FACILITY_MAX = 0x34, }; /* log message format */ @@ -3139,4 +3142,36 @@ struct fw_devlog_cmd { (((x) >> FW_DEVLOG_CMD_MEMADDR16_DEVLOG_S) & \ FW_DEVLOG_CMD_MEMADDR16_DEVLOG_M) +/* P C I E F W P F 7 R E G I S T E R */ + +/* PF7 stores the Firmware Device Log parameters which allows Host Drivers to + * access the "devlog" which needing to contact firmware. The encoding is + * mostly the same as that returned by the DEVLOG command except for the size + * which is encoded as the number of entries in multiples-1 of 128 here rather + * than the memory size as is done in the DEVLOG command. Thus, 0 means 128 + * and 15 means 2048. This of course in turn constrains the allowed values + * for the devlog size ... + */ +#define PCIE_FW_PF_DEVLOG 7 + +#define PCIE_FW_PF_DEVLOG_NENTRIES128_S 28 +#define PCIE_FW_PF_DEVLOG_NENTRIES128_M 0xf +#define PCIE_FW_PF_DEVLOG_NENTRIES128_V(x) \ + ((x) << PCIE_FW_PF_DEVLOG_NENTRIES128_S) +#define PCIE_FW_PF_DEVLOG_NENTRIES128_G(x) \ + (((x) >> PCIE_FW_PF_DEVLOG_NENTRIES128_S) & \ + PCIE_FW_PF_DEVLOG_NENTRIES128_M) + +#define PCIE_FW_PF_DEVLOG_ADDR16_S 4 +#define PCIE_FW_PF_DEVLOG_ADDR16_M 0xffffff +#define PCIE_FW_PF_DEVLOG_ADDR16_V(x) ((x) << PCIE_FW_PF_DEVLOG_ADDR16_S) +#define PCIE_FW_PF_DEVLOG_ADDR16_G(x) \ + (((x) >> PCIE_FW_PF_DEVLOG_ADDR16_S) & PCIE_FW_PF_DEVLOG_ADDR16_M) + +#define PCIE_FW_PF_DEVLOG_MEMTYPE_S 0 +#define PCIE_FW_PF_DEVLOG_MEMTYPE_M 0xf +#define PCIE_FW_PF_DEVLOG_MEMTYPE_V(x) ((x) << PCIE_FW_PF_DEVLOG_MEMTYPE_S) +#define PCIE_FW_PF_DEVLOG_MEMTYPE_G(x) \ + (((x) >> PCIE_FW_PF_DEVLOG_MEMTYPE_S) & PCIE_FW_PF_DEVLOG_MEMTYPE_M) + #endif /* _T4FW_INTERFACE_H_ */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h index e2bd3f747858..b9d1cbac0eee 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h @@ -36,13 +36,13 @@ #define __T4FW_VERSION_H__ #define T4FW_VERSION_MAJOR 0x01 -#define T4FW_VERSION_MINOR 0x0C -#define T4FW_VERSION_MICRO 0x19 +#define T4FW_VERSION_MINOR 0x0D +#define T4FW_VERSION_MICRO 0x20 #define T4FW_VERSION_BUILD 0x00 #define T5FW_VERSION_MAJOR 0x01 -#define T5FW_VERSION_MINOR 0x0C -#define T5FW_VERSION_MICRO 0x19 +#define T5FW_VERSION_MINOR 0x0D +#define T5FW_VERSION_MICRO 0x20 #define T5FW_VERSION_BUILD 0x00 #endif From ae469b68a557d1bd538c9122eaf99cf09fc242f2 Mon Sep 17 00:00:00 2001 From: Hariprasad Shenai Date: Wed, 1 Apr 2015 21:41:16 +0530 Subject: [PATCH 170/170] cxgb4: Fix to dump devlog, even if FW is crashed Add new Common Code routines to retrieve Firmware Device Log parameters from PCIE_FW_PF[7]. The firmware initializes its Device Log very early on and stores the parameters for its location/size in that register. Using the parameters from the register allows us to access the Firmware Device Log even when the firmware crashes very early on or we're not attached to the firmware Based on original work by Casey Leedom Signed-off-by: Hariprasad Shenai Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/cxgb4.h | 2 + .../net/ethernet/chelsio/cxgb4/cxgb4_main.c | 33 +++--------- drivers/net/ethernet/chelsio/cxgb4/t4_hw.c | 53 +++++++++++++++++++ drivers/net/ethernet/chelsio/cxgb4/t4_regs.h | 3 ++ 4 files changed, 65 insertions(+), 26 deletions(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 8816c645de7d..c6ff4890d171 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -1136,6 +1136,8 @@ int cxgb4_t4_bar2_sge_qregs(struct adapter *adapter, unsigned int qtimer_val(const struct adapter *adap, const struct sge_rspq *q); + +int t4_init_devlog_params(struct adapter *adapter); int t4_init_sge_params(struct adapter *adapter); int t4_init_tp_params(struct adapter *adap); int t4_filter_field_shift(const struct adapter *adap, int filter_sel); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 826de7a7f83c..d92995138f7e 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -5110,10 +5110,15 @@ static int adap_init0(struct adapter *adap) enum dev_state state; u32 params[7], val[7]; struct fw_caps_config_cmd caps_cmd; - struct fw_devlog_cmd devlog_cmd; - u32 devlog_meminfo; int reset = 1; + /* Grab Firmware Device Log parameters as early as possible so we have + * access to it for debugging, etc. + */ + ret = t4_init_devlog_params(adap); + if (ret < 0) + return ret; + /* Contact FW, advertising Master capability */ ret = t4_fw_hello(adap, adap->mbox, adap->mbox, MASTER_MAY, &state); if (ret < 0) { @@ -5191,30 +5196,6 @@ static int adap_init0(struct adapter *adap) if (ret < 0) goto bye; - /* Read firmware device log parameters. We really need to find a way - * to get these parameters initialized with some default values (which - * are likely to be correct) for the case where we either don't - * attache to the firmware or it's crashed when we probe the adapter. - * That way we'll still be able to perform early firmware startup - * debugging ... If the request to get the Firmware's Device Log - * parameters fails, we'll live so we don't make that a fatal error. - */ - memset(&devlog_cmd, 0, sizeof(devlog_cmd)); - devlog_cmd.op_to_write = htonl(FW_CMD_OP_V(FW_DEVLOG_CMD) | - FW_CMD_REQUEST_F | FW_CMD_READ_F); - devlog_cmd.retval_len16 = htonl(FW_LEN16(devlog_cmd)); - ret = t4_wr_mbox(adap, adap->mbox, &devlog_cmd, sizeof(devlog_cmd), - &devlog_cmd); - if (ret == 0) { - devlog_meminfo = - ntohl(devlog_cmd.memtype_devlog_memaddr16_devlog); - adap->params.devlog.memtype = - FW_DEVLOG_CMD_MEMTYPE_DEVLOG_G(devlog_meminfo); - adap->params.devlog.start = - FW_DEVLOG_CMD_MEMADDR16_DEVLOG_G(devlog_meminfo) << 4; - adap->params.devlog.size = ntohl(devlog_cmd.memsize_devlog); - } - /* * Find out what ports are available to us. Note that we need to do * this before calling adap_init0_no_config() since it needs nports diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 1abdfa123c6c..ee394dc68303 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -4458,6 +4458,59 @@ int cxgb4_t4_bar2_sge_qregs(struct adapter *adapter, return 0; } +/** + * t4_init_devlog_params - initialize adapter->params.devlog + * @adap: the adapter + * + * Initialize various fields of the adapter's Firmware Device Log + * Parameters structure. + */ +int t4_init_devlog_params(struct adapter *adap) +{ + struct devlog_params *dparams = &adap->params.devlog; + u32 pf_dparams; + unsigned int devlog_meminfo; + struct fw_devlog_cmd devlog_cmd; + int ret; + + /* If we're dealing with newer firmware, the Device Log Paramerters + * are stored in a designated register which allows us to access the + * Device Log even if we can't talk to the firmware. + */ + pf_dparams = + t4_read_reg(adap, PCIE_FW_REG(PCIE_FW_PF_A, PCIE_FW_PF_DEVLOG)); + if (pf_dparams) { + unsigned int nentries, nentries128; + + dparams->memtype = PCIE_FW_PF_DEVLOG_MEMTYPE_G(pf_dparams); + dparams->start = PCIE_FW_PF_DEVLOG_ADDR16_G(pf_dparams) << 4; + + nentries128 = PCIE_FW_PF_DEVLOG_NENTRIES128_G(pf_dparams); + nentries = (nentries128 + 1) * 128; + dparams->size = nentries * sizeof(struct fw_devlog_e); + + return 0; + } + + /* Otherwise, ask the firmware for it's Device Log Parameters. + */ + memset(&devlog_cmd, 0, sizeof(devlog_cmd)); + devlog_cmd.op_to_write = htonl(FW_CMD_OP_V(FW_DEVLOG_CMD) | + FW_CMD_REQUEST_F | FW_CMD_READ_F); + devlog_cmd.retval_len16 = htonl(FW_LEN16(devlog_cmd)); + ret = t4_wr_mbox(adap, adap->mbox, &devlog_cmd, sizeof(devlog_cmd), + &devlog_cmd); + if (ret) + return ret; + + devlog_meminfo = ntohl(devlog_cmd.memtype_devlog_memaddr16_devlog); + dparams->memtype = FW_DEVLOG_CMD_MEMTYPE_DEVLOG_G(devlog_meminfo); + dparams->start = FW_DEVLOG_CMD_MEMADDR16_DEVLOG_G(devlog_meminfo) << 4; + dparams->size = ntohl(devlog_cmd.memsize_devlog); + + return 0; +} + /** * t4_init_sge_params - initialize adap->params.sge * @adapter: the adapter diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h index 231a725f6d5d..326674b19983 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h @@ -63,6 +63,8 @@ #define MC_BIST_STATUS_REG(reg_addr, idx) ((reg_addr) + (idx) * 4) #define EDC_BIST_STATUS_REG(reg_addr, idx) ((reg_addr) + (idx) * 4) +#define PCIE_FW_REG(reg_addr, idx) ((reg_addr) + (idx) * 4) + #define SGE_PF_KDOORBELL_A 0x0 #define QID_S 15 @@ -707,6 +709,7 @@ #define PFNUM_V(x) ((x) << PFNUM_S) #define PCIE_FW_A 0x30b8 +#define PCIE_FW_PF_A 0x30bc #define PCIE_CORE_UTL_SYSTEM_BUS_AGENT_STATUS_A 0x5908