From f5b98461cb8167ba362ad9f74c41d126b7becea7 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Fri, 6 Jan 2017 19:32:01 +0100 Subject: random: use chacha20 for get_random_int/long Now that our crng uses chacha20, we can rely on its speedy characteristics for replacing MD5, while simultaneously achieving a higher security guarantee. Before the idea was to use these functions if you wanted random integers that aren't stupidly insecure but aren't necessarily secure either, a vague gray zone, that hopefully was "good enough" for its users. With chacha20, we can strengthen this claim, since either we're using an rdrand-like instruction, or we're using the same crng as /dev/urandom. And it's faster than what was before. We could have chosen to replace this with a SipHash-derived function, which might be slightly faster, but at the cost of having yet another RNG construction in the kernel. By moving to chacha20, we have a single RNG to analyze and verify, and we also already get good performance improvements on all platforms. Implementation-wise, rather than use a generic buffer for both get_random_int/long and memcpy based on the size needs, we use a specific buffer for 32-bit reads and for 64-bit reads. This way, we're guaranteed to always have aligned accesses on all platforms. While slightly more verbose in C, the assembly this generates is a lot simpler than otherwise. Finally, on 32-bit platforms where longs and ints are the same size, we simply alias get_random_int to get_random_long. Signed-off-by: Jason A. Donenfeld Suggested-by: Theodore Ts'o Cc: Theodore Ts'o Cc: Hannes Frederic Sowa Cc: Andy Lutomirski Signed-off-by: Theodore Ts'o --- include/linux/random.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/random.h b/include/linux/random.h index 7bd2403e4fef..16ab429735a7 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -37,7 +37,6 @@ extern void get_random_bytes(void *buf, int nbytes); extern int add_random_ready_callback(struct random_ready_callback *rdy); extern void del_random_ready_callback(struct random_ready_callback *rdy); extern void get_random_bytes_arch(void *buf, int nbytes); -extern int random_int_secret_init(void); #ifndef MODULE extern const struct file_operations random_fops, urandom_fops; -- cgit v1.2.3 From c440408cf6901eeb2c09563397e24a9097907078 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Sun, 22 Jan 2017 16:34:08 +0100 Subject: random: convert get_random_int/long into get_random_u32/u64 Many times, when a user wants a random number, he wants a random number of a guaranteed size. So, thinking of get_random_int and get_random_long in terms of get_random_u32 and get_random_u64 makes it much easier to achieve this. It also makes the code simpler. On 32-bit platforms, get_random_int and get_random_long are both aliased to get_random_u32. On 64-bit platforms, int->u32 and long->u64. Signed-off-by: Jason A. Donenfeld Cc: Greg Kroah-Hartman Cc: Theodore Ts'o Signed-off-by: Theodore Ts'o --- drivers/char/random.c | 55 +++++++++++++++++++++++++------------------------- include/linux/random.h | 17 ++++++++++++++-- 2 files changed, 42 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/drivers/char/random.c b/drivers/char/random.c index b800e5479b7d..066ae125f2c8 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -2018,8 +2018,8 @@ struct ctl_table random_table[] = { struct batched_entropy { union { - unsigned long entropy_long[CHACHA20_BLOCK_SIZE / sizeof(unsigned long)]; - unsigned int entropy_int[CHACHA20_BLOCK_SIZE / sizeof(unsigned int)]; + u64 entropy_u64[CHACHA20_BLOCK_SIZE / sizeof(u64)]; + u32 entropy_u32[CHACHA20_BLOCK_SIZE / sizeof(u32)]; }; unsigned int position; }; @@ -2029,52 +2029,51 @@ struct batched_entropy { * number is either as good as RDRAND or as good as /dev/urandom, with the * goal of being quite fast and not depleting entropy. */ -static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_long); -unsigned long get_random_long(void) +static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u64); +u64 get_random_u64(void) { - unsigned long ret; + u64 ret; struct batched_entropy *batch; - if (arch_get_random_long(&ret)) +#if BITS_PER_LONG == 64 + if (arch_get_random_long((unsigned long *)&ret)) return ret; +#else + if (arch_get_random_long((unsigned long *)&ret) && + arch_get_random_long((unsigned long *)&ret + 1)) + return ret; +#endif - batch = &get_cpu_var(batched_entropy_long); - if (batch->position % ARRAY_SIZE(batch->entropy_long) == 0) { - extract_crng((u8 *)batch->entropy_long); + batch = &get_cpu_var(batched_entropy_u64); + if (batch->position % ARRAY_SIZE(batch->entropy_u64) == 0) { + extract_crng((u8 *)batch->entropy_u64); batch->position = 0; } - ret = batch->entropy_long[batch->position++]; - put_cpu_var(batched_entropy_long); + ret = batch->entropy_u64[batch->position++]; + put_cpu_var(batched_entropy_u64); return ret; } -EXPORT_SYMBOL(get_random_long); +EXPORT_SYMBOL(get_random_u64); -#if BITS_PER_LONG == 32 -unsigned int get_random_int(void) -{ - return get_random_long(); -} -#else -static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_int); -unsigned int get_random_int(void) +static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u32); +u32 get_random_u32(void) { - unsigned int ret; + u32 ret; struct batched_entropy *batch; if (arch_get_random_int(&ret)) return ret; - batch = &get_cpu_var(batched_entropy_int); - if (batch->position % ARRAY_SIZE(batch->entropy_int) == 0) { - extract_crng((u8 *)batch->entropy_int); + batch = &get_cpu_var(batched_entropy_u32); + if (batch->position % ARRAY_SIZE(batch->entropy_u32) == 0) { + extract_crng((u8 *)batch->entropy_u32); batch->position = 0; } - ret = batch->entropy_int[batch->position++]; - put_cpu_var(batched_entropy_int); + ret = batch->entropy_u32[batch->position++]; + put_cpu_var(batched_entropy_u32); return ret; } -#endif -EXPORT_SYMBOL(get_random_int); +EXPORT_SYMBOL(get_random_u32); /** * randomize_page - Generate a random, page aligned address diff --git a/include/linux/random.h b/include/linux/random.h index 16ab429735a7..ed5c3838780d 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -42,8 +42,21 @@ extern void get_random_bytes_arch(void *buf, int nbytes); extern const struct file_operations random_fops, urandom_fops; #endif -unsigned int get_random_int(void); -unsigned long get_random_long(void); +u32 get_random_u32(void); +u64 get_random_u64(void); +static inline unsigned int get_random_int(void) +{ + return get_random_u32(); +} +static inline unsigned long get_random_long(void) +{ +#if BITS_PER_LONG == 64 + return get_random_u64(); +#else + return get_random_u32(); +#endif +} + unsigned long randomize_page(unsigned long start, unsigned long range); u32 prandom_u32(void); -- cgit v1.2.3 From 7807e086a2d1f69cc1a57958cac04fea79fc2112 Mon Sep 17 00:00:00 2001 From: Ladislav Michl Date: Sat, 11 Feb 2017 14:02:49 +0100 Subject: ARM: OMAP2+: gpmc-onenand: propagate error on initialization failure gpmc_probe_onenand_child returns success even on gpmc_onenand_init failure. Fix that. Signed-off-by: Ladislav Michl Acked-by: Roger Quadros Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/gpmc-onenand.c | 10 ++++++---- drivers/memory/omap-gpmc.c | 4 +--- include/linux/omap-gpmc.h | 5 +++-- 3 files changed, 10 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mach-omap2/gpmc-onenand.c b/arch/arm/mach-omap2/gpmc-onenand.c index 8633c703546a..2944af820558 100644 --- a/arch/arm/mach-omap2/gpmc-onenand.c +++ b/arch/arm/mach-omap2/gpmc-onenand.c @@ -367,7 +367,7 @@ static int gpmc_onenand_setup(void __iomem *onenand_base, int *freq_ptr) return ret; } -void gpmc_onenand_init(struct omap_onenand_platform_data *_onenand_data) +int gpmc_onenand_init(struct omap_onenand_platform_data *_onenand_data) { int err; struct device *dev = &gpmc_onenand_device.dev; @@ -393,15 +393,17 @@ void gpmc_onenand_init(struct omap_onenand_platform_data *_onenand_data) if (err < 0) { dev_err(dev, "Cannot request GPMC CS %d, error %d\n", gpmc_onenand_data->cs, err); - return; + return err; } gpmc_onenand_resource.end = gpmc_onenand_resource.start + ONENAND_IO_SIZE - 1; - if (platform_device_register(&gpmc_onenand_device) < 0) { + err = platform_device_register(&gpmc_onenand_device); + if (err) { dev_err(dev, "Unable to register OneNAND device\n"); gpmc_cs_free(gpmc_onenand_data->cs); - return; } + + return err; } diff --git a/drivers/memory/omap-gpmc.c b/drivers/memory/omap-gpmc.c index 5457c361ad58..bf0fe0137dfe 100644 --- a/drivers/memory/omap-gpmc.c +++ b/drivers/memory/omap-gpmc.c @@ -1947,9 +1947,7 @@ static int gpmc_probe_onenand_child(struct platform_device *pdev, if (!of_property_read_u32(child, "dma-channel", &val)) gpmc_onenand_data->dma_channel = val; - gpmc_onenand_init(gpmc_onenand_data); - - return 0; + return gpmc_onenand_init(gpmc_onenand_data); } #else static int gpmc_probe_onenand_child(struct platform_device *pdev, diff --git a/include/linux/omap-gpmc.h b/include/linux/omap-gpmc.h index 35d0fd7a4948..e821a3132a3e 100644 --- a/include/linux/omap-gpmc.h +++ b/include/linux/omap-gpmc.h @@ -88,10 +88,11 @@ static inline int gpmc_nand_init(struct omap_nand_platform_data *d, #endif #if IS_ENABLED(CONFIG_MTD_ONENAND_OMAP2) -extern void gpmc_onenand_init(struct omap_onenand_platform_data *d); +extern int gpmc_onenand_init(struct omap_onenand_platform_data *d); #else #define board_onenand_data NULL -static inline void gpmc_onenand_init(struct omap_onenand_platform_data *d) +static inline int gpmc_onenand_init(struct omap_onenand_platform_data *d) { + return 0; } #endif -- cgit v1.2.3 From ac28e47ccc3ff8dabce1aec6b224760c3e524044 Mon Sep 17 00:00:00 2001 From: Ladislav Michl Date: Tue, 21 Feb 2017 10:44:45 +0100 Subject: ARM: OMAP2+: Remove legacy gpmc-nand.c This code is no longer used and can be removed as we are using device tree. Removing this code also removes a dependency between drivers/mtd and arch/arm/mach-omap2 making furhter driver changes easier. Signed-off-by: Ladislav Michl [tony@atomide.com: removed from header too, updated comments] Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/Makefile | 3 - arch/arm/mach-omap2/gpmc-nand.c | 154 ---------------------------------------- include/linux/omap-gpmc.h | 11 --- 3 files changed, 168 deletions(-) delete mode 100644 arch/arm/mach-omap2/gpmc-nand.c (limited to 'include/linux') diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile index 093458b62c8d..c89757abb0ae 100644 --- a/arch/arm/mach-omap2/Makefile +++ b/arch/arm/mach-omap2/Makefile @@ -241,6 +241,3 @@ obj-$(CONFIG_MACH_OMAP2_TUSB6010) += usb-tusb6010.o onenand-$(CONFIG_MTD_ONENAND_OMAP2) := gpmc-onenand.o obj-y += $(onenand-m) $(onenand-y) - -nand-$(CONFIG_MTD_NAND_OMAP2) := gpmc-nand.o -obj-y += $(nand-m) $(nand-y) diff --git a/arch/arm/mach-omap2/gpmc-nand.c b/arch/arm/mach-omap2/gpmc-nand.c deleted file mode 100644 index f6ac027f3c3b..000000000000 --- a/arch/arm/mach-omap2/gpmc-nand.c +++ /dev/null @@ -1,154 +0,0 @@ -/* - * gpmc-nand.c - * - * Copyright (C) 2009 Texas Instruments - * Vimal Singh - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include -#include -#include -#include -#include -#include - -#include - -#include "soc.h" - -/* minimum size for IO mapping */ -#define NAND_IO_SIZE 4 - -static bool gpmc_hwecc_bch_capable(enum omap_ecc ecc_opt) -{ - /* platforms which support all ECC schemes */ - if (soc_is_am33xx() || soc_is_am43xx() || cpu_is_omap44xx() || - soc_is_omap54xx() || soc_is_dra7xx()) - return 1; - - if (ecc_opt == OMAP_ECC_BCH4_CODE_HW_DETECTION_SW || - ecc_opt == OMAP_ECC_BCH8_CODE_HW_DETECTION_SW) { - if (cpu_is_omap24xx()) - return 0; - else if (cpu_is_omap3630() && (GET_OMAP_REVISION() == 0)) - return 0; - else - return 1; - } - - /* OMAP3xxx do not have ELM engine, so cannot support ECC schemes - * which require H/W based ECC error detection */ - if ((cpu_is_omap34xx() || cpu_is_omap3630()) && - ((ecc_opt == OMAP_ECC_BCH4_CODE_HW) || - (ecc_opt == OMAP_ECC_BCH8_CODE_HW))) - return 0; - - /* legacy platforms support only HAM1 (1-bit Hamming) ECC scheme */ - if (ecc_opt == OMAP_ECC_HAM1_CODE_HW || - ecc_opt == OMAP_ECC_HAM1_CODE_SW) - return 1; - else - return 0; -} - -/* This function will go away once the device-tree convertion is complete */ -static void gpmc_set_legacy(struct omap_nand_platform_data *gpmc_nand_data, - struct gpmc_settings *s) -{ - /* Enable RD PIN Monitoring Reg */ - if (gpmc_nand_data->dev_ready) { - s->wait_on_read = true; - s->wait_on_write = true; - } - - if (gpmc_nand_data->devsize == NAND_BUSWIDTH_16) - s->device_width = GPMC_DEVWIDTH_16BIT; - else - s->device_width = GPMC_DEVWIDTH_8BIT; -} - -int gpmc_nand_init(struct omap_nand_platform_data *gpmc_nand_data, - struct gpmc_timings *gpmc_t) -{ - int err = 0; - struct gpmc_settings s; - struct platform_device *pdev; - struct resource gpmc_nand_res[] = { - { .flags = IORESOURCE_MEM, }, - { .flags = IORESOURCE_IRQ, }, - { .flags = IORESOURCE_IRQ, }, - }; - - BUG_ON(gpmc_nand_data->cs >= GPMC_CS_NUM); - - err = gpmc_cs_request(gpmc_nand_data->cs, NAND_IO_SIZE, - (unsigned long *)&gpmc_nand_res[0].start); - if (err < 0) { - pr_err("omap2-gpmc: Cannot request GPMC CS %d, error %d\n", - gpmc_nand_data->cs, err); - return err; - } - gpmc_nand_res[0].end = gpmc_nand_res[0].start + NAND_IO_SIZE - 1; - gpmc_nand_res[1].start = gpmc_get_client_irq(GPMC_IRQ_FIFOEVENTENABLE); - gpmc_nand_res[2].start = gpmc_get_client_irq(GPMC_IRQ_COUNT_EVENT); - - memset(&s, 0, sizeof(struct gpmc_settings)); - gpmc_set_legacy(gpmc_nand_data, &s); - - s.device_nand = true; - - if (gpmc_t) { - err = gpmc_cs_set_timings(gpmc_nand_data->cs, gpmc_t, &s); - if (err < 0) { - pr_err("omap2-gpmc: Unable to set gpmc timings: %d\n", - err); - return err; - } - } - - err = gpmc_cs_program_settings(gpmc_nand_data->cs, &s); - if (err < 0) - goto out_free_cs; - - err = gpmc_configure(GPMC_CONFIG_WP, 0); - if (err < 0) - goto out_free_cs; - - if (!gpmc_hwecc_bch_capable(gpmc_nand_data->ecc_opt)) { - pr_err("omap2-nand: Unsupported NAND ECC scheme selected\n"); - err = -EINVAL; - goto out_free_cs; - } - - - pdev = platform_device_alloc("omap2-nand", gpmc_nand_data->cs); - if (pdev) { - err = platform_device_add_resources(pdev, gpmc_nand_res, - ARRAY_SIZE(gpmc_nand_res)); - if (!err) - pdev->dev.platform_data = gpmc_nand_data; - } else { - err = -ENOMEM; - } - if (err) - goto out_free_pdev; - - err = platform_device_add(pdev); - if (err) { - dev_err(&pdev->dev, "Unable to register NAND device\n"); - goto out_free_pdev; - } - - return 0; - -out_free_pdev: - platform_device_put(pdev); -out_free_cs: - gpmc_cs_free(gpmc_nand_data->cs); - - return err; -} diff --git a/include/linux/omap-gpmc.h b/include/linux/omap-gpmc.h index e821a3132a3e..fd0de00c0d77 100644 --- a/include/linux/omap-gpmc.h +++ b/include/linux/omap-gpmc.h @@ -76,17 +76,6 @@ struct gpmc_timings; struct omap_nand_platform_data; struct omap_onenand_platform_data; -#if IS_ENABLED(CONFIG_MTD_NAND_OMAP2) -extern int gpmc_nand_init(struct omap_nand_platform_data *d, - struct gpmc_timings *gpmc_t); -#else -static inline int gpmc_nand_init(struct omap_nand_platform_data *d, - struct gpmc_timings *gpmc_t) -{ - return 0; -} -#endif - #if IS_ENABLED(CONFIG_MTD_ONENAND_OMAP2) extern int gpmc_onenand_init(struct omap_onenand_platform_data *d); #else -- cgit v1.2.3 From 0878fff1f42c18e448ab5b8b4f6a3eb32365b5b6 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Sun, 5 Mar 2017 12:34:49 -0800 Subject: net: phy: Do not perform software reset for Generic PHY The Generic PHY driver is a catch-all PHY driver and it should preserve whatever prior initialization has been done by boot loader or firmware agents. For specific PHY device configuration it is expected that a specialized PHY driver would take over that role. Resetting the generic PHY was a bad idea that has lead to several complaints and downstream workarounds e.g: in OpenWrt/LEDE so restore the behavior prior to 87aa9f9c61ad ("net: phy: consolidate PHY reset in phy_init_hw()"). Reported-by: Felix Fietkau Fixes: 87aa9f9c61ad ("net: phy: consolidate PHY reset in phy_init_hw()") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 2 +- include/linux/phy.h | 4 ++++ 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index daec6555f3b1..5198ccfa347f 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1864,7 +1864,7 @@ static struct phy_driver genphy_driver[] = { .phy_id = 0xffffffff, .phy_id_mask = 0xffffffff, .name = "Generic PHY", - .soft_reset = genphy_soft_reset, + .soft_reset = genphy_no_soft_reset, .config_init = genphy_config_init, .features = PHY_GBIT_FEATURES | SUPPORTED_MII | SUPPORTED_AUI | SUPPORTED_FIBRE | diff --git a/include/linux/phy.h b/include/linux/phy.h index 772476028a65..43a774873aa9 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -837,6 +837,10 @@ int genphy_read_status(struct phy_device *phydev); int genphy_suspend(struct phy_device *phydev); int genphy_resume(struct phy_device *phydev); int genphy_soft_reset(struct phy_device *phydev); +static inline int genphy_no_soft_reset(struct phy_device *phydev) +{ + return 0; +} void phy_driver_unregister(struct phy_driver *drv); void phy_drivers_unregister(struct phy_driver *drv, int n); int phy_driver_register(struct phy_driver *new_driver, struct module *owner); -- cgit v1.2.3 From 4dfc050571523ac2bc02cbf948dd47621f7dd83f Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 21 Feb 2017 11:32:47 +0000 Subject: KVM: arm/arm64: vgic-v3: Don't pretend to support IRQ/FIQ bypass Our GICv3 emulation always presents ICC_SRE_EL1 with DIB/DFB set to zero, which implies that there is a way to bypass the GIC and inject raw IRQ/FIQ by driving the CPU pins. Of course, we don't allow that when the GIC is configured, but we fail to indicate that to the guest. The obvious fix is to set these bits (and never let them being changed again). Reported-by: Peter Maydell Acked-by: Christoffer Dall Reviewed-by: Eric Auger Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 2 ++ virt/kvm/arm/vgic/vgic-v3.c | 5 ++++- 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 672cfef72fc8..97cbca19430d 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -373,6 +373,8 @@ #define ICC_IGRPEN0_EL1_MASK (1 << ICC_IGRPEN0_EL1_SHIFT) #define ICC_IGRPEN1_EL1_SHIFT 0 #define ICC_IGRPEN1_EL1_MASK (1 << ICC_IGRPEN1_EL1_SHIFT) +#define ICC_SRE_EL1_DIB (1U << 2) +#define ICC_SRE_EL1_DFB (1U << 1) #define ICC_SRE_EL1_SRE (1U << 0) /* diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index edc6ee2dc852..be0f4c3e0142 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -229,10 +229,13 @@ void vgic_v3_enable(struct kvm_vcpu *vcpu) /* * If we are emulating a GICv3, we do it in an non-GICv2-compatible * way, so we force SRE to 1 to demonstrate this to the guest. + * Also, we don't support any form of IRQ/FIQ bypass. * This goes with the spec allowing the value to be RAO/WI. */ if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { - vgic_v3->vgic_sre = ICC_SRE_EL1_SRE; + vgic_v3->vgic_sre = (ICC_SRE_EL1_DIB | + ICC_SRE_EL1_DFB | + ICC_SRE_EL1_SRE); vcpu->arch.vgic_cpu.pendbaser = INITIAL_PENDBASER_VALUE; } else { vgic_v3->vgic_sre = 0; -- cgit v1.2.3 From b3e228473e6cec7cf83b4025b4570c8066ab2dd8 Mon Sep 17 00:00:00 2001 From: Mian Yousaf Kaukab Date: Thu, 2 Mar 2017 16:11:47 +0100 Subject: irqdomain: Add empty irq_domain_check_msi_remap Fix following build error for s390: drivers/vfio/vfio_iommu_type1.c: In function 'vfio_iommu_type1_attach_group': drivers/vfio/vfio_iommu_type1.c:1290:25: error: implicit declaration of function 'irq_domain_check_msi_remap' Acked-by: Marc Zyngier Reviewed-by: Eric Auger Signed-off-by: Mian Yousaf Kaukab Signed-off-by: Marc Zyngier --- include/linux/irqdomain.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 188eced6813e..9f3616085423 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -524,6 +524,10 @@ static inline struct irq_domain *irq_find_matching_fwnode( { return NULL; } +static inline bool irq_domain_check_msi_remap(void) +{ + return false; +} #endif /* !CONFIG_IRQ_DOMAIN */ #endif /* _LINUX_IRQDOMAIN_H */ -- cgit v1.2.3 From 62f8f4d9066c1c6f2474845d1ca7e2891f2ae3fd Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 5 Mar 2017 10:52:16 -0800 Subject: dccp: fix use-after-free in dccp_feat_activate_values Dmitry reported crashes in DCCP stack [1] Problem here is that when I got rid of listener spinlock, I missed the fact that DCCP stores a complex state in struct dccp_request_sock, while TCP does not. Since multiple cpus could access it at the same time, we need to add protection. [1] BUG: KASAN: use-after-free in dccp_feat_activate_values+0x967/0xab0 net/dccp/feat.c:1541 at addr ffff88003713be68 Read of size 8 by task syz-executor2/8457 CPU: 2 PID: 8457 Comm: syz-executor2 Not tainted 4.10.0-rc7+ #127 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:15 [inline] dump_stack+0x292/0x398 lib/dump_stack.c:51 kasan_object_err+0x1c/0x70 mm/kasan/report.c:162 print_address_description mm/kasan/report.c:200 [inline] kasan_report_error mm/kasan/report.c:289 [inline] kasan_report.part.1+0x20e/0x4e0 mm/kasan/report.c:311 kasan_report mm/kasan/report.c:332 [inline] __asan_report_load8_noabort+0x29/0x30 mm/kasan/report.c:332 dccp_feat_activate_values+0x967/0xab0 net/dccp/feat.c:1541 dccp_create_openreq_child+0x464/0x610 net/dccp/minisocks.c:121 dccp_v6_request_recv_sock+0x1f6/0x1960 net/dccp/ipv6.c:457 dccp_check_req+0x335/0x5a0 net/dccp/minisocks.c:186 dccp_v6_rcv+0x69e/0x1d00 net/dccp/ipv6.c:711 ip6_input_finish+0x46d/0x17a0 net/ipv6/ip6_input.c:279 NF_HOOK include/linux/netfilter.h:257 [inline] ip6_input+0xdb/0x590 net/ipv6/ip6_input.c:322 dst_input include/net/dst.h:507 [inline] ip6_rcv_finish+0x289/0x890 net/ipv6/ip6_input.c:69 NF_HOOK include/linux/netfilter.h:257 [inline] ipv6_rcv+0x12ec/0x23d0 net/ipv6/ip6_input.c:203 __netif_receive_skb_core+0x1ae5/0x3400 net/core/dev.c:4190 __netif_receive_skb+0x2a/0x170 net/core/dev.c:4228 process_backlog+0xe5/0x6c0 net/core/dev.c:4839 napi_poll net/core/dev.c:5202 [inline] net_rx_action+0xe70/0x1900 net/core/dev.c:5267 __do_softirq+0x2fb/0xb7d kernel/softirq.c:284 do_softirq_own_stack+0x1c/0x30 arch/x86/entry/entry_64.S:902 do_softirq.part.17+0x1e8/0x230 kernel/softirq.c:328 do_softirq kernel/softirq.c:176 [inline] __local_bh_enable_ip+0x1f2/0x200 kernel/softirq.c:181 local_bh_enable include/linux/bottom_half.h:31 [inline] rcu_read_unlock_bh include/linux/rcupdate.h:971 [inline] ip6_finish_output2+0xbb0/0x23d0 net/ipv6/ip6_output.c:123 ip6_finish_output+0x302/0x960 net/ipv6/ip6_output.c:148 NF_HOOK_COND include/linux/netfilter.h:246 [inline] ip6_output+0x1cb/0x8d0 net/ipv6/ip6_output.c:162 ip6_xmit+0xcdf/0x20d0 include/net/dst.h:501 inet6_csk_xmit+0x320/0x5f0 net/ipv6/inet6_connection_sock.c:179 dccp_transmit_skb+0xb09/0x1120 net/dccp/output.c:141 dccp_xmit_packet+0x215/0x760 net/dccp/output.c:280 dccp_write_xmit+0x168/0x1d0 net/dccp/output.c:362 dccp_sendmsg+0x79c/0xb10 net/dccp/proto.c:796 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:744 sock_sendmsg_nosec net/socket.c:635 [inline] sock_sendmsg+0xca/0x110 net/socket.c:645 SYSC_sendto+0x660/0x810 net/socket.c:1687 SyS_sendto+0x40/0x50 net/socket.c:1655 entry_SYSCALL_64_fastpath+0x1f/0xc2 RIP: 0033:0x4458b9 RSP: 002b:00007f8ceb77bb58 EFLAGS: 00000282 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 0000000000000017 RCX: 00000000004458b9 RDX: 0000000000000023 RSI: 0000000020e60000 RDI: 0000000000000017 RBP: 00000000006e1b90 R08: 00000000200f9fe1 R09: 0000000000000020 R10: 0000000000008010 R11: 0000000000000282 R12: 00000000007080a8 R13: 0000000000000000 R14: 00007f8ceb77c9c0 R15: 00007f8ceb77c700 Object at ffff88003713be50, in cache kmalloc-64 size: 64 Allocated: PID = 8446 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57 save_stack+0x43/0xd0 mm/kasan/kasan.c:502 set_track mm/kasan/kasan.c:514 [inline] kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:605 kmem_cache_alloc_trace+0x82/0x270 mm/slub.c:2738 kmalloc include/linux/slab.h:490 [inline] dccp_feat_entry_new+0x214/0x410 net/dccp/feat.c:467 dccp_feat_push_change+0x38/0x220 net/dccp/feat.c:487 __feat_register_sp+0x223/0x2f0 net/dccp/feat.c:741 dccp_feat_propagate_ccid+0x22b/0x2b0 net/dccp/feat.c:949 dccp_feat_server_ccid_dependencies+0x1b3/0x250 net/dccp/feat.c:1012 dccp_make_response+0x1f1/0xc90 net/dccp/output.c:423 dccp_v6_send_response+0x4ec/0xc20 net/dccp/ipv6.c:217 dccp_v6_conn_request+0xaba/0x11b0 net/dccp/ipv6.c:377 dccp_rcv_state_process+0x51e/0x1650 net/dccp/input.c:606 dccp_v6_do_rcv+0x213/0x350 net/dccp/ipv6.c:632 sk_backlog_rcv include/net/sock.h:893 [inline] __sk_receive_skb+0x36f/0xcc0 net/core/sock.c:479 dccp_v6_rcv+0xba5/0x1d00 net/dccp/ipv6.c:742 ip6_input_finish+0x46d/0x17a0 net/ipv6/ip6_input.c:279 NF_HOOK include/linux/netfilter.h:257 [inline] ip6_input+0xdb/0x590 net/ipv6/ip6_input.c:322 dst_input include/net/dst.h:507 [inline] ip6_rcv_finish+0x289/0x890 net/ipv6/ip6_input.c:69 NF_HOOK include/linux/netfilter.h:257 [inline] ipv6_rcv+0x12ec/0x23d0 net/ipv6/ip6_input.c:203 __netif_receive_skb_core+0x1ae5/0x3400 net/core/dev.c:4190 __netif_receive_skb+0x2a/0x170 net/core/dev.c:4228 process_backlog+0xe5/0x6c0 net/core/dev.c:4839 napi_poll net/core/dev.c:5202 [inline] net_rx_action+0xe70/0x1900 net/core/dev.c:5267 __do_softirq+0x2fb/0xb7d kernel/softirq.c:284 Freed: PID = 15 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57 save_stack+0x43/0xd0 mm/kasan/kasan.c:502 set_track mm/kasan/kasan.c:514 [inline] kasan_slab_free+0x73/0xc0 mm/kasan/kasan.c:578 slab_free_hook mm/slub.c:1355 [inline] slab_free_freelist_hook mm/slub.c:1377 [inline] slab_free mm/slub.c:2954 [inline] kfree+0xe8/0x2b0 mm/slub.c:3874 dccp_feat_entry_destructor.part.4+0x48/0x60 net/dccp/feat.c:418 dccp_feat_entry_destructor net/dccp/feat.c:416 [inline] dccp_feat_list_pop net/dccp/feat.c:541 [inline] dccp_feat_activate_values+0x57f/0xab0 net/dccp/feat.c:1543 dccp_create_openreq_child+0x464/0x610 net/dccp/minisocks.c:121 dccp_v6_request_recv_sock+0x1f6/0x1960 net/dccp/ipv6.c:457 dccp_check_req+0x335/0x5a0 net/dccp/minisocks.c:186 dccp_v6_rcv+0x69e/0x1d00 net/dccp/ipv6.c:711 ip6_input_finish+0x46d/0x17a0 net/ipv6/ip6_input.c:279 NF_HOOK include/linux/netfilter.h:257 [inline] ip6_input+0xdb/0x590 net/ipv6/ip6_input.c:322 dst_input include/net/dst.h:507 [inline] ip6_rcv_finish+0x289/0x890 net/ipv6/ip6_input.c:69 NF_HOOK include/linux/netfilter.h:257 [inline] ipv6_rcv+0x12ec/0x23d0 net/ipv6/ip6_input.c:203 __netif_receive_skb_core+0x1ae5/0x3400 net/core/dev.c:4190 __netif_receive_skb+0x2a/0x170 net/core/dev.c:4228 process_backlog+0xe5/0x6c0 net/core/dev.c:4839 napi_poll net/core/dev.c:5202 [inline] net_rx_action+0xe70/0x1900 net/core/dev.c:5267 __do_softirq+0x2fb/0xb7d kernel/softirq.c:284 Memory state around the buggy address: ffff88003713bd00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff88003713bd80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >ffff88003713be00: fc fc fc fc fc fc fc fc fc fc fb fb fb fb fb fb ^ Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table") Signed-off-by: Eric Dumazet Reported-by: Dmitry Vyukov Tested-by: Dmitry Vyukov Signed-off-by: David S. Miller --- include/linux/dccp.h | 1 + net/dccp/minisocks.c | 24 ++++++++++++++++-------- 2 files changed, 17 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 61d042bbbf60..68449293c4b6 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -163,6 +163,7 @@ struct dccp_request_sock { __u64 dreq_isr; __u64 dreq_gsr; __be32 dreq_service; + spinlock_t dreq_lock; struct list_head dreq_featneg; __u32 dreq_timestamp_echo; __u32 dreq_timestamp_time; diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index e267e6f4c9a5..abd07a443219 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -142,6 +142,13 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, struct dccp_request_sock *dreq = dccp_rsk(req); bool own_req; + /* TCP/DCCP listeners became lockless. + * DCCP stores complex state in its request_sock, so we need + * a protection for them, now this code runs without being protected + * by the parent (listener) lock. + */ + spin_lock_bh(&dreq->dreq_lock); + /* Check for retransmitted REQUEST */ if (dccp_hdr(skb)->dccph_type == DCCP_PKT_REQUEST) { @@ -156,7 +163,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, inet_rtx_syn_ack(sk, req); } /* Network Duplicate, discard packet */ - return NULL; + goto out; } DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_PACKET_ERROR; @@ -182,20 +189,20 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL, req, &own_req); - if (!child) - goto listen_overflow; - - return inet_csk_complete_hashdance(sk, child, req, own_req); + if (child) { + child = inet_csk_complete_hashdance(sk, child, req, own_req); + goto out; + } -listen_overflow: - dccp_pr_debug("listen_overflow!\n"); DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_TOO_BUSY; drop: if (dccp_hdr(skb)->dccph_type != DCCP_PKT_RESET) req->rsk_ops->send_reset(sk, skb); inet_csk_reqsk_queue_drop(sk, req); - return NULL; +out: + spin_unlock_bh(&dreq->dreq_lock); + return child; } EXPORT_SYMBOL_GPL(dccp_check_req); @@ -246,6 +253,7 @@ int dccp_reqsk_init(struct request_sock *req, { struct dccp_request_sock *dreq = dccp_rsk(req); + spin_lock_init(&dreq->dreq_lock); inet_rsk(req)->ir_rmt_port = dccp_hdr(skb)->dccph_sport; inet_rsk(req)->ir_num = ntohs(dccp_hdr(skb)->dccph_dport); inet_rsk(req)->acked = 0; -- cgit v1.2.3 From 4fe8435909fddc97b81472026aa954e06dd192a5 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 7 Mar 2017 20:00:13 -0800 Subject: bpf: convert htab map to hlist_nulls when all map elements are pre-allocated one cpu can delete and reuse htab_elem while another cpu is still walking the hlist. In such case the lookup may miss the element. Convert hlist to hlist_nulls to avoid such scenario. When bucket lock is taken there is no need to take such precautions, so only convert map_lookup and map_get_next to nulls. The race window is extremely small and only reproducible with explicit udelay() inside lookup_nulls_elem_raw() Similar to hlist add hlist_nulls_for_each_entry_safe() and hlist_nulls_entry_safe() helpers. Fixes: 6c9059817432 ("bpf: pre-allocate hash map elements") Reported-by: Jonathan Perry Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/list_nulls.h | 5 +++ include/linux/rculist_nulls.h | 14 +++++++ kernel/bpf/hashtab.c | 94 +++++++++++++++++++++++++++---------------- 3 files changed, 79 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/list_nulls.h b/include/linux/list_nulls.h index b01fe1009084..87ff4f58a2f0 100644 --- a/include/linux/list_nulls.h +++ b/include/linux/list_nulls.h @@ -29,6 +29,11 @@ struct hlist_nulls_node { ((ptr)->first = (struct hlist_nulls_node *) NULLS_MARKER(nulls)) #define hlist_nulls_entry(ptr, type, member) container_of(ptr,type,member) + +#define hlist_nulls_entry_safe(ptr, type, member) \ + ({ typeof(ptr) ____ptr = (ptr); \ + !is_a_nulls(____ptr) ? hlist_nulls_entry(____ptr, type, member) : NULL; \ + }) /** * ptr_is_a_nulls - Test if a ptr is a nulls * @ptr: ptr to be tested diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h index 4ae95f7e8597..a23a33153180 100644 --- a/include/linux/rculist_nulls.h +++ b/include/linux/rculist_nulls.h @@ -156,5 +156,19 @@ static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n, ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1; }); \ pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos))) +/** + * hlist_nulls_for_each_entry_safe - + * iterate over list of given type safe against removal of list entry + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct hlist_nulls_node to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the hlist_nulls_node within the struct. + */ +#define hlist_nulls_for_each_entry_safe(tpos, pos, head, member) \ + for (({barrier();}), \ + pos = rcu_dereference_raw(hlist_nulls_first_rcu(head)); \ + (!is_a_nulls(pos)) && \ + ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); \ + pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos)); 1; });) #endif #endif diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 63c86a7be2a1..afe5bab376c9 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -13,11 +13,12 @@ #include #include #include +#include #include "percpu_freelist.h" #include "bpf_lru_list.h" struct bucket { - struct hlist_head head; + struct hlist_nulls_head head; raw_spinlock_t lock; }; @@ -44,7 +45,7 @@ enum extra_elem_state { /* each htab element is struct htab_elem + key + value */ struct htab_elem { union { - struct hlist_node hash_node; + struct hlist_nulls_node hash_node; struct { void *padding; union { @@ -337,7 +338,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) goto free_htab; for (i = 0; i < htab->n_buckets; i++) { - INIT_HLIST_HEAD(&htab->buckets[i].head); + INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i); raw_spin_lock_init(&htab->buckets[i].lock); } @@ -377,28 +378,52 @@ static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash) return &htab->buckets[hash & (htab->n_buckets - 1)]; } -static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash) +static inline struct hlist_nulls_head *select_bucket(struct bpf_htab *htab, u32 hash) { return &__select_bucket(htab, hash)->head; } -static struct htab_elem *lookup_elem_raw(struct hlist_head *head, u32 hash, +/* this lookup function can only be called with bucket lock taken */ +static struct htab_elem *lookup_elem_raw(struct hlist_nulls_head *head, u32 hash, void *key, u32 key_size) { + struct hlist_nulls_node *n; struct htab_elem *l; - hlist_for_each_entry_rcu(l, head, hash_node) + hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) if (l->hash == hash && !memcmp(&l->key, key, key_size)) return l; return NULL; } +/* can be called without bucket lock. it will repeat the loop in + * the unlikely event when elements moved from one bucket into another + * while link list is being walked + */ +static struct htab_elem *lookup_nulls_elem_raw(struct hlist_nulls_head *head, + u32 hash, void *key, + u32 key_size, u32 n_buckets) +{ + struct hlist_nulls_node *n; + struct htab_elem *l; + +again: + hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) + if (l->hash == hash && !memcmp(&l->key, key, key_size)) + return l; + + if (unlikely(get_nulls_value(n) != (hash & (n_buckets - 1)))) + goto again; + + return NULL; +} + /* Called from syscall or from eBPF program */ static void *__htab_map_lookup_elem(struct bpf_map *map, void *key) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - struct hlist_head *head; + struct hlist_nulls_head *head; struct htab_elem *l; u32 hash, key_size; @@ -411,7 +436,7 @@ static void *__htab_map_lookup_elem(struct bpf_map *map, void *key) head = select_bucket(htab, hash); - l = lookup_elem_raw(head, hash, key, key_size); + l = lookup_nulls_elem_raw(head, hash, key, key_size, htab->n_buckets); return l; } @@ -444,8 +469,9 @@ static void *htab_lru_map_lookup_elem(struct bpf_map *map, void *key) static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node) { struct bpf_htab *htab = (struct bpf_htab *)arg; - struct htab_elem *l, *tgt_l; - struct hlist_head *head; + struct htab_elem *l = NULL, *tgt_l; + struct hlist_nulls_head *head; + struct hlist_nulls_node *n; unsigned long flags; struct bucket *b; @@ -455,9 +481,9 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node) raw_spin_lock_irqsave(&b->lock, flags); - hlist_for_each_entry_rcu(l, head, hash_node) + hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) if (l == tgt_l) { - hlist_del_rcu(&l->hash_node); + hlist_nulls_del_rcu(&l->hash_node); break; } @@ -470,7 +496,7 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node) static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - struct hlist_head *head; + struct hlist_nulls_head *head; struct htab_elem *l, *next_l; u32 hash, key_size; int i; @@ -484,7 +510,7 @@ static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key) head = select_bucket(htab, hash); /* lookup the key */ - l = lookup_elem_raw(head, hash, key, key_size); + l = lookup_nulls_elem_raw(head, hash, key, key_size, htab->n_buckets); if (!l) { i = 0; @@ -492,7 +518,7 @@ static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key) } /* key was found, get next key in the same bucket */ - next_l = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&l->hash_node)), + next_l = hlist_nulls_entry_safe(rcu_dereference_raw(hlist_nulls_next_rcu(&l->hash_node)), struct htab_elem, hash_node); if (next_l) { @@ -511,7 +537,7 @@ find_first_elem: head = select_bucket(htab, i); /* pick first element in the bucket */ - next_l = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)), + next_l = hlist_nulls_entry_safe(rcu_dereference_raw(hlist_nulls_first_rcu(head)), struct htab_elem, hash_node); if (next_l) { /* if it's not empty, just return it */ @@ -676,7 +702,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct htab_elem *l_new = NULL, *l_old; - struct hlist_head *head; + struct hlist_nulls_head *head; unsigned long flags; struct bucket *b; u32 key_size, hash; @@ -715,9 +741,9 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, /* add new element to the head of the list, so that * concurrent search will find it before old elem */ - hlist_add_head_rcu(&l_new->hash_node, head); + hlist_nulls_add_head_rcu(&l_new->hash_node, head); if (l_old) { - hlist_del_rcu(&l_old->hash_node); + hlist_nulls_del_rcu(&l_old->hash_node); free_htab_elem(htab, l_old); } ret = 0; @@ -731,7 +757,7 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct htab_elem *l_new, *l_old = NULL; - struct hlist_head *head; + struct hlist_nulls_head *head; unsigned long flags; struct bucket *b; u32 key_size, hash; @@ -772,10 +798,10 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, /* add new element to the head of the list, so that * concurrent search will find it before old elem */ - hlist_add_head_rcu(&l_new->hash_node, head); + hlist_nulls_add_head_rcu(&l_new->hash_node, head); if (l_old) { bpf_lru_node_set_ref(&l_new->lru_node); - hlist_del_rcu(&l_old->hash_node); + hlist_nulls_del_rcu(&l_old->hash_node); } ret = 0; @@ -796,7 +822,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct htab_elem *l_new = NULL, *l_old; - struct hlist_head *head; + struct hlist_nulls_head *head; unsigned long flags; struct bucket *b; u32 key_size, hash; @@ -835,7 +861,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, ret = PTR_ERR(l_new); goto err; } - hlist_add_head_rcu(&l_new->hash_node, head); + hlist_nulls_add_head_rcu(&l_new->hash_node, head); } ret = 0; err: @@ -849,7 +875,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct htab_elem *l_new = NULL, *l_old; - struct hlist_head *head; + struct hlist_nulls_head *head; unsigned long flags; struct bucket *b; u32 key_size, hash; @@ -897,7 +923,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, } else { pcpu_copy_value(htab, htab_elem_get_ptr(l_new, key_size), value, onallcpus); - hlist_add_head_rcu(&l_new->hash_node, head); + hlist_nulls_add_head_rcu(&l_new->hash_node, head); l_new = NULL; } ret = 0; @@ -925,7 +951,7 @@ static int htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, static int htab_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - struct hlist_head *head; + struct hlist_nulls_head *head; struct bucket *b; struct htab_elem *l; unsigned long flags; @@ -945,7 +971,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key) l = lookup_elem_raw(head, hash, key, key_size); if (l) { - hlist_del_rcu(&l->hash_node); + hlist_nulls_del_rcu(&l->hash_node); free_htab_elem(htab, l); ret = 0; } @@ -957,7 +983,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key) static int htab_lru_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - struct hlist_head *head; + struct hlist_nulls_head *head; struct bucket *b; struct htab_elem *l; unsigned long flags; @@ -977,7 +1003,7 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key) l = lookup_elem_raw(head, hash, key, key_size); if (l) { - hlist_del_rcu(&l->hash_node); + hlist_nulls_del_rcu(&l->hash_node); ret = 0; } @@ -992,12 +1018,12 @@ static void delete_all_elements(struct bpf_htab *htab) int i; for (i = 0; i < htab->n_buckets; i++) { - struct hlist_head *head = select_bucket(htab, i); - struct hlist_node *n; + struct hlist_nulls_head *head = select_bucket(htab, i); + struct hlist_nulls_node *n; struct htab_elem *l; - hlist_for_each_entry_safe(l, n, head, hash_node) { - hlist_del_rcu(&l->hash_node); + hlist_nulls_for_each_entry_safe(l, n, head, hash_node) { + hlist_nulls_del_rcu(&l->hash_node); if (l->state != HTAB_EXTRA_ELEM_USED) htab_elem_free(htab, l); } -- cgit v1.2.3 From cdfbabfb2f0ce983fdaa42f20e5f7842178fc01e Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 9 Mar 2017 08:09:05 +0000 Subject: net: Work around lockdep limitation in sockets that use sockets Lockdep issues a circular dependency warning when AFS issues an operation through AF_RXRPC from a context in which the VFS/VM holds the mmap_sem. The theory lockdep comes up with is as follows: (1) If the pagefault handler decides it needs to read pages from AFS, it calls AFS with mmap_sem held and AFS begins an AF_RXRPC call, but creating a call requires the socket lock: mmap_sem must be taken before sk_lock-AF_RXRPC (2) afs_open_socket() opens an AF_RXRPC socket and binds it. rxrpc_bind() binds the underlying UDP socket whilst holding its socket lock. inet_bind() takes its own socket lock: sk_lock-AF_RXRPC must be taken before sk_lock-AF_INET (3) Reading from a TCP socket into a userspace buffer might cause a fault and thus cause the kernel to take the mmap_sem, but the TCP socket is locked whilst doing this: sk_lock-AF_INET must be taken before mmap_sem However, lockdep's theory is wrong in this instance because it deals only with lock classes and not individual locks. The AF_INET lock in (2) isn't really equivalent to the AF_INET lock in (3) as the former deals with a socket entirely internal to the kernel that never sees userspace. This is a limitation in the design of lockdep. Fix the general case by: (1) Double up all the locking keys used in sockets so that one set are used if the socket is created by userspace and the other set is used if the socket is created by the kernel. (2) Store the kern parameter passed to sk_alloc() in a variable in the sock struct (sk_kern_sock). This informs sock_lock_init(), sock_init_data() and sk_clone_lock() as to the lock keys to be used. Note that the child created by sk_clone_lock() inherits the parent's kern setting. (3) Add a 'kern' parameter to ->accept() that is analogous to the one passed in to ->create() that distinguishes whether kernel_accept() or sys_accept4() was the caller and can be passed to sk_alloc(). Note that a lot of accept functions merely dequeue an already allocated socket. I haven't touched these as the new socket already exists before we get the parameter. Note also that there are a couple of places where I've made the accepted socket unconditionally kernel-based: irda_accept() rds_rcp_accept_one() tcp_accept_from_sock() because they follow a sock_create_kern() and accept off of that. Whilst creating this, I noticed that lustre and ocfs don't create sockets through sock_create_kern() and thus they aren't marked as for-kernel, though they appear to be internal. I wonder if these should do that so that they use the new set of lock keys. Signed-off-by: David Howells Signed-off-by: David S. Miller --- crypto/af_alg.c | 9 ++- crypto/algif_hash.c | 9 ++- drivers/staging/lustre/lnet/lnet/lib-socket.c | 4 +- fs/dlm/lowcomms.c | 2 +- fs/ocfs2/cluster/tcp.c | 2 +- include/crypto/if_alg.h | 2 +- include/linux/net.h | 2 +- include/net/inet_common.h | 3 +- include/net/inet_connection_sock.h | 2 +- include/net/sctp/structs.h | 3 +- include/net/sock.h | 9 ++- net/atm/svc.c | 5 +- net/ax25/af_ax25.c | 3 +- net/bluetooth/l2cap_sock.c | 2 +- net/bluetooth/rfcomm/sock.c | 3 +- net/bluetooth/sco.c | 2 +- net/core/sock.c | 106 ++++++++++++++------------ net/decnet/af_decnet.c | 5 +- net/ipv4/af_inet.c | 5 +- net/ipv4/inet_connection_sock.c | 2 +- net/irda/af_irda.c | 5 +- net/iucv/af_iucv.c | 2 +- net/llc/af_llc.c | 4 +- net/netrom/af_netrom.c | 3 +- net/nfc/llcp_sock.c | 2 +- net/phonet/pep.c | 6 +- net/phonet/socket.c | 4 +- net/rds/tcp_listen.c | 2 +- net/rose/af_rose.c | 3 +- net/sctp/ipv6.c | 5 +- net/sctp/protocol.c | 5 +- net/sctp/socket.c | 4 +- net/smc/af_smc.c | 2 +- net/socket.c | 4 +- net/tipc/socket.c | 8 +- net/unix/af_unix.c | 5 +- net/vmw_vsock/af_vsock.c | 3 +- net/x25/af_x25.c | 3 +- 38 files changed, 142 insertions(+), 108 deletions(-) (limited to 'include/linux') diff --git a/crypto/af_alg.c b/crypto/af_alg.c index f5e18c2a4852..690deca17c35 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -266,7 +266,7 @@ unlock: return err; } -int af_alg_accept(struct sock *sk, struct socket *newsock) +int af_alg_accept(struct sock *sk, struct socket *newsock, bool kern) { struct alg_sock *ask = alg_sk(sk); const struct af_alg_type *type; @@ -281,7 +281,7 @@ int af_alg_accept(struct sock *sk, struct socket *newsock) if (!type) goto unlock; - sk2 = sk_alloc(sock_net(sk), PF_ALG, GFP_KERNEL, &alg_proto, 0); + sk2 = sk_alloc(sock_net(sk), PF_ALG, GFP_KERNEL, &alg_proto, kern); err = -ENOMEM; if (!sk2) goto unlock; @@ -323,9 +323,10 @@ unlock: } EXPORT_SYMBOL_GPL(af_alg_accept); -static int alg_accept(struct socket *sock, struct socket *newsock, int flags) +static int alg_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { - return af_alg_accept(sock->sk, newsock); + return af_alg_accept(sock->sk, newsock, kern); } static const struct proto_ops alg_proto_ops = { diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c index 54fc90e8339c..5e92bd275ef3 100644 --- a/crypto/algif_hash.c +++ b/crypto/algif_hash.c @@ -239,7 +239,8 @@ unlock: return err ?: len; } -static int hash_accept(struct socket *sock, struct socket *newsock, int flags) +static int hash_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); @@ -260,7 +261,7 @@ static int hash_accept(struct socket *sock, struct socket *newsock, int flags) if (err) return err; - err = af_alg_accept(ask->parent, newsock); + err = af_alg_accept(ask->parent, newsock, kern); if (err) return err; @@ -378,7 +379,7 @@ static int hash_recvmsg_nokey(struct socket *sock, struct msghdr *msg, } static int hash_accept_nokey(struct socket *sock, struct socket *newsock, - int flags) + int flags, bool kern) { int err; @@ -386,7 +387,7 @@ static int hash_accept_nokey(struct socket *sock, struct socket *newsock, if (err) return err; - return hash_accept(sock, newsock, flags); + return hash_accept(sock, newsock, flags, kern); } static struct proto_ops algif_hash_ops_nokey = { diff --git a/drivers/staging/lustre/lnet/lnet/lib-socket.c b/drivers/staging/lustre/lnet/lnet/lib-socket.c index b7b87ecefcdf..9fca8d225ee0 100644 --- a/drivers/staging/lustre/lnet/lnet/lib-socket.c +++ b/drivers/staging/lustre/lnet/lnet/lib-socket.c @@ -532,7 +532,7 @@ lnet_sock_accept(struct socket **newsockp, struct socket *sock) newsock->ops = sock->ops; - rc = sock->ops->accept(sock, newsock, O_NONBLOCK); + rc = sock->ops->accept(sock, newsock, O_NONBLOCK, false); if (rc == -EAGAIN) { /* Nothing ready, so wait for activity */ init_waitqueue_entry(&wait, current); @@ -540,7 +540,7 @@ lnet_sock_accept(struct socket **newsockp, struct socket *sock) set_current_state(TASK_INTERRUPTIBLE); schedule(); remove_wait_queue(sk_sleep(sock->sk), &wait); - rc = sock->ops->accept(sock, newsock, O_NONBLOCK); + rc = sock->ops->accept(sock, newsock, O_NONBLOCK, false); } if (rc) diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 7d398d300e97..9382db998ec9 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -743,7 +743,7 @@ static int tcp_accept_from_sock(struct connection *con) newsock->type = con->sock->type; newsock->ops = con->sock->ops; - result = con->sock->ops->accept(con->sock, newsock, O_NONBLOCK); + result = con->sock->ops->accept(con->sock, newsock, O_NONBLOCK, true); if (result < 0) goto accept_err; diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index 4348027384f5..d0ab7e56d0b4 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -1863,7 +1863,7 @@ static int o2net_accept_one(struct socket *sock, int *more) new_sock->type = sock->type; new_sock->ops = sock->ops; - ret = sock->ops->accept(sock, new_sock, O_NONBLOCK); + ret = sock->ops->accept(sock, new_sock, O_NONBLOCK, false); if (ret < 0) goto out; diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h index a2bfd7843f18..e2b9c6fe2714 100644 --- a/include/crypto/if_alg.h +++ b/include/crypto/if_alg.h @@ -73,7 +73,7 @@ int af_alg_unregister_type(const struct af_alg_type *type); int af_alg_release(struct socket *sock); void af_alg_release_parent(struct sock *sk); -int af_alg_accept(struct sock *sk, struct socket *newsock); +int af_alg_accept(struct sock *sk, struct socket *newsock, bool kern); int af_alg_make_sg(struct af_alg_sgl *sgl, struct iov_iter *iter, int len); void af_alg_free_sg(struct af_alg_sgl *sgl); diff --git a/include/linux/net.h b/include/linux/net.h index cd0c8bd0a1de..0620f5e18c96 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -146,7 +146,7 @@ struct proto_ops { int (*socketpair)(struct socket *sock1, struct socket *sock2); int (*accept) (struct socket *sock, - struct socket *newsock, int flags); + struct socket *newsock, int flags, bool kern); int (*getname) (struct socket *sock, struct sockaddr *addr, int *sockaddr_len, int peer); diff --git a/include/net/inet_common.h b/include/net/inet_common.h index b7952d55b9c0..f39ae697347f 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -20,7 +20,8 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags, int is_sendmsg); int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags); -int inet_accept(struct socket *sock, struct socket *newsock, int flags); +int inet_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern); int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size); ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags); diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 826f198374f8..c7a577976bec 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -258,7 +258,7 @@ inet_csk_rto_backoff(const struct inet_connection_sock *icsk, return (unsigned long)min_t(u64, when, max_when); } -struct sock *inet_csk_accept(struct sock *sk, int flags, int *err); +struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern); int inet_csk_get_port(struct sock *sk, unsigned short snum); diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index a244db5e5ff7..07a0b128625a 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -476,7 +476,8 @@ struct sctp_pf { int (*send_verify) (struct sctp_sock *, union sctp_addr *); int (*supported_addrs)(const struct sctp_sock *, __be16 *); struct sock *(*create_accept_sk) (struct sock *sk, - struct sctp_association *asoc); + struct sctp_association *asoc, + bool kern); int (*addr_to_user)(struct sctp_sock *sk, union sctp_addr *addr); void (*to_sk_saddr)(union sctp_addr *, struct sock *sk); void (*to_sk_daddr)(union sctp_addr *, struct sock *sk); diff --git a/include/net/sock.h b/include/net/sock.h index 5e5997654db6..03252d53975d 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -236,6 +236,7 @@ struct sock_common { * @sk_shutdown: mask of %SEND_SHUTDOWN and/or %RCV_SHUTDOWN * @sk_userlocks: %SO_SNDBUF and %SO_RCVBUF settings * @sk_lock: synchronizer + * @sk_kern_sock: True if sock is using kernel lock classes * @sk_rcvbuf: size of receive buffer in bytes * @sk_wq: sock wait queue and async head * @sk_rx_dst: receive input route used by early demux @@ -430,7 +431,8 @@ struct sock { #endif kmemcheck_bitfield_begin(flags); - unsigned int sk_padding : 2, + unsigned int sk_padding : 1, + sk_kern_sock : 1, sk_no_check_tx : 1, sk_no_check_rx : 1, sk_userlocks : 4, @@ -1015,7 +1017,8 @@ struct proto { int addr_len); int (*disconnect)(struct sock *sk, int flags); - struct sock * (*accept)(struct sock *sk, int flags, int *err); + struct sock * (*accept)(struct sock *sk, int flags, int *err, + bool kern); int (*ioctl)(struct sock *sk, int cmd, unsigned long arg); @@ -1573,7 +1576,7 @@ int sock_cmsg_send(struct sock *sk, struct msghdr *msg, int sock_no_bind(struct socket *, struct sockaddr *, int); int sock_no_connect(struct socket *, struct sockaddr *, int, int); int sock_no_socketpair(struct socket *, struct socket *); -int sock_no_accept(struct socket *, struct socket *, int); +int sock_no_accept(struct socket *, struct socket *, int, bool); int sock_no_getname(struct socket *, struct sockaddr *, int *, int); unsigned int sock_no_poll(struct file *, struct socket *, struct poll_table_struct *); diff --git a/net/atm/svc.c b/net/atm/svc.c index db9794ec61d8..5589de7086af 100644 --- a/net/atm/svc.c +++ b/net/atm/svc.c @@ -318,7 +318,8 @@ out: return error; } -static int svc_accept(struct socket *sock, struct socket *newsock, int flags) +static int svc_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk = sock->sk; struct sk_buff *skb; @@ -329,7 +330,7 @@ static int svc_accept(struct socket *sock, struct socket *newsock, int flags) lock_sock(sk); - error = svc_create(sock_net(sk), newsock, 0, 0); + error = svc_create(sock_net(sk), newsock, 0, kern); if (error) goto out; diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index a8e42cedf1db..b7c486752b3a 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -1320,7 +1320,8 @@ out_release: return err; } -static int ax25_accept(struct socket *sock, struct socket *newsock, int flags) +static int ax25_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sk_buff *skb; struct sock *newsk; diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index f307b145ea54..507b80d59dec 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -301,7 +301,7 @@ done: } static int l2cap_sock_accept(struct socket *sock, struct socket *newsock, - int flags) + int flags, bool kern) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sock *sk = sock->sk, *nsk; diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index aa1a814ceddc..ac3c650cb234 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -471,7 +471,8 @@ done: return err; } -static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int flags) +static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sock *sk = sock->sk, *nsk; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index e4e9a2da1e7e..728e0c8dc8e7 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -627,7 +627,7 @@ done: } static int sco_sock_accept(struct socket *sock, struct socket *newsock, - int flags) + int flags, bool kern) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sock *sk = sock->sk, *ch; diff --git a/net/core/sock.c b/net/core/sock.c index f6fd79f33097..a96d5f7a5734 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -197,66 +197,55 @@ EXPORT_SYMBOL(sk_net_capable); /* * Each address family might have different locking rules, so we have - * one slock key per address family: + * one slock key per address family and separate keys for internal and + * userspace sockets. */ static struct lock_class_key af_family_keys[AF_MAX]; +static struct lock_class_key af_family_kern_keys[AF_MAX]; static struct lock_class_key af_family_slock_keys[AF_MAX]; +static struct lock_class_key af_family_kern_slock_keys[AF_MAX]; /* * Make lock validator output more readable. (we pre-construct these * strings build-time, so that runtime initialization of socket * locks is fast): */ + +#define _sock_locks(x) \ + x "AF_UNSPEC", x "AF_UNIX" , x "AF_INET" , \ + x "AF_AX25" , x "AF_IPX" , x "AF_APPLETALK", \ + x "AF_NETROM", x "AF_BRIDGE" , x "AF_ATMPVC" , \ + x "AF_X25" , x "AF_INET6" , x "AF_ROSE" , \ + x "AF_DECnet", x "AF_NETBEUI" , x "AF_SECURITY" , \ + x "AF_KEY" , x "AF_NETLINK" , x "AF_PACKET" , \ + x "AF_ASH" , x "AF_ECONET" , x "AF_ATMSVC" , \ + x "AF_RDS" , x "AF_SNA" , x "AF_IRDA" , \ + x "AF_PPPOX" , x "AF_WANPIPE" , x "AF_LLC" , \ + x "27" , x "28" , x "AF_CAN" , \ + x "AF_TIPC" , x "AF_BLUETOOTH", x "IUCV" , \ + x "AF_RXRPC" , x "AF_ISDN" , x "AF_PHONET" , \ + x "AF_IEEE802154", x "AF_CAIF" , x "AF_ALG" , \ + x "AF_NFC" , x "AF_VSOCK" , x "AF_KCM" , \ + x "AF_QIPCRTR", x "AF_SMC" , x "AF_MAX" + static const char *const af_family_key_strings[AF_MAX+1] = { - "sk_lock-AF_UNSPEC", "sk_lock-AF_UNIX" , "sk_lock-AF_INET" , - "sk_lock-AF_AX25" , "sk_lock-AF_IPX" , "sk_lock-AF_APPLETALK", - "sk_lock-AF_NETROM", "sk_lock-AF_BRIDGE" , "sk_lock-AF_ATMPVC" , - "sk_lock-AF_X25" , "sk_lock-AF_INET6" , "sk_lock-AF_ROSE" , - "sk_lock-AF_DECnet", "sk_lock-AF_NETBEUI" , "sk_lock-AF_SECURITY" , - "sk_lock-AF_KEY" , "sk_lock-AF_NETLINK" , "sk_lock-AF_PACKET" , - "sk_lock-AF_ASH" , "sk_lock-AF_ECONET" , "sk_lock-AF_ATMSVC" , - "sk_lock-AF_RDS" , "sk_lock-AF_SNA" , "sk_lock-AF_IRDA" , - "sk_lock-AF_PPPOX" , "sk_lock-AF_WANPIPE" , "sk_lock-AF_LLC" , - "sk_lock-27" , "sk_lock-28" , "sk_lock-AF_CAN" , - "sk_lock-AF_TIPC" , "sk_lock-AF_BLUETOOTH", "sk_lock-IUCV" , - "sk_lock-AF_RXRPC" , "sk_lock-AF_ISDN" , "sk_lock-AF_PHONET" , - "sk_lock-AF_IEEE802154", "sk_lock-AF_CAIF" , "sk_lock-AF_ALG" , - "sk_lock-AF_NFC" , "sk_lock-AF_VSOCK" , "sk_lock-AF_KCM" , - "sk_lock-AF_QIPCRTR", "sk_lock-AF_SMC" , "sk_lock-AF_MAX" + _sock_locks("sk_lock-") }; static const char *const af_family_slock_key_strings[AF_MAX+1] = { - "slock-AF_UNSPEC", "slock-AF_UNIX" , "slock-AF_INET" , - "slock-AF_AX25" , "slock-AF_IPX" , "slock-AF_APPLETALK", - "slock-AF_NETROM", "slock-AF_BRIDGE" , "slock-AF_ATMPVC" , - "slock-AF_X25" , "slock-AF_INET6" , "slock-AF_ROSE" , - "slock-AF_DECnet", "slock-AF_NETBEUI" , "slock-AF_SECURITY" , - "slock-AF_KEY" , "slock-AF_NETLINK" , "slock-AF_PACKET" , - "slock-AF_ASH" , "slock-AF_ECONET" , "slock-AF_ATMSVC" , - "slock-AF_RDS" , "slock-AF_SNA" , "slock-AF_IRDA" , - "slock-AF_PPPOX" , "slock-AF_WANPIPE" , "slock-AF_LLC" , - "slock-27" , "slock-28" , "slock-AF_CAN" , - "slock-AF_TIPC" , "slock-AF_BLUETOOTH", "slock-AF_IUCV" , - "slock-AF_RXRPC" , "slock-AF_ISDN" , "slock-AF_PHONET" , - "slock-AF_IEEE802154", "slock-AF_CAIF" , "slock-AF_ALG" , - "slock-AF_NFC" , "slock-AF_VSOCK" ,"slock-AF_KCM" , - "slock-AF_QIPCRTR", "slock-AF_SMC" , "slock-AF_MAX" + _sock_locks("slock-") }; static const char *const af_family_clock_key_strings[AF_MAX+1] = { - "clock-AF_UNSPEC", "clock-AF_UNIX" , "clock-AF_INET" , - "clock-AF_AX25" , "clock-AF_IPX" , "clock-AF_APPLETALK", - "clock-AF_NETROM", "clock-AF_BRIDGE" , "clock-AF_ATMPVC" , - "clock-AF_X25" , "clock-AF_INET6" , "clock-AF_ROSE" , - "clock-AF_DECnet", "clock-AF_NETBEUI" , "clock-AF_SECURITY" , - "clock-AF_KEY" , "clock-AF_NETLINK" , "clock-AF_PACKET" , - "clock-AF_ASH" , "clock-AF_ECONET" , "clock-AF_ATMSVC" , - "clock-AF_RDS" , "clock-AF_SNA" , "clock-AF_IRDA" , - "clock-AF_PPPOX" , "clock-AF_WANPIPE" , "clock-AF_LLC" , - "clock-27" , "clock-28" , "clock-AF_CAN" , - "clock-AF_TIPC" , "clock-AF_BLUETOOTH", "clock-AF_IUCV" , - "clock-AF_RXRPC" , "clock-AF_ISDN" , "clock-AF_PHONET" , - "clock-AF_IEEE802154", "clock-AF_CAIF" , "clock-AF_ALG" , - "clock-AF_NFC" , "clock-AF_VSOCK" , "clock-AF_KCM" , - "clock-AF_QIPCRTR", "clock-AF_SMC" , "clock-AF_MAX" + _sock_locks("clock-") +}; + +static const char *const af_family_kern_key_strings[AF_MAX+1] = { + _sock_locks("k-sk_lock-") +}; +static const char *const af_family_kern_slock_key_strings[AF_MAX+1] = { + _sock_locks("k-slock-") +}; +static const char *const af_family_kern_clock_key_strings[AF_MAX+1] = { + _sock_locks("k-clock-") }; /* @@ -264,6 +253,7 @@ static const char *const af_family_clock_key_strings[AF_MAX+1] = { * so split the lock classes by using a per-AF key: */ static struct lock_class_key af_callback_keys[AF_MAX]; +static struct lock_class_key af_kern_callback_keys[AF_MAX]; /* Take into consideration the size of the struct sk_buff overhead in the * determination of these values, since that is non-constant across @@ -1293,7 +1283,16 @@ lenout: */ static inline void sock_lock_init(struct sock *sk) { - sock_lock_init_class_and_name(sk, + if (sk->sk_kern_sock) + sock_lock_init_class_and_name( + sk, + af_family_kern_slock_key_strings[sk->sk_family], + af_family_kern_slock_keys + sk->sk_family, + af_family_kern_key_strings[sk->sk_family], + af_family_kern_keys + sk->sk_family); + else + sock_lock_init_class_and_name( + sk, af_family_slock_key_strings[sk->sk_family], af_family_slock_keys + sk->sk_family, af_family_key_strings[sk->sk_family], @@ -1399,6 +1398,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, * why we need sk_prot_creator -acme */ sk->sk_prot = sk->sk_prot_creator = prot; + sk->sk_kern_sock = kern; sock_lock_init(sk); sk->sk_net_refcnt = kern ? 0 : 1; if (likely(sk->sk_net_refcnt)) @@ -2277,7 +2277,8 @@ int sock_no_socketpair(struct socket *sock1, struct socket *sock2) } EXPORT_SYMBOL(sock_no_socketpair); -int sock_no_accept(struct socket *sock, struct socket *newsock, int flags) +int sock_no_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { return -EOPNOTSUPP; } @@ -2481,7 +2482,14 @@ void sock_init_data(struct socket *sock, struct sock *sk) } rwlock_init(&sk->sk_callback_lock); - lockdep_set_class_and_name(&sk->sk_callback_lock, + if (sk->sk_kern_sock) + lockdep_set_class_and_name( + &sk->sk_callback_lock, + af_kern_callback_keys + sk->sk_family, + af_family_kern_clock_key_strings[sk->sk_family]); + else + lockdep_set_class_and_name( + &sk->sk_callback_lock, af_callback_keys + sk->sk_family, af_family_clock_key_strings[sk->sk_family]); diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index e6e79eda9763..7de5b40a5d0d 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -1070,7 +1070,8 @@ static struct sk_buff *dn_wait_for_connect(struct sock *sk, long *timeo) return skb == NULL ? ERR_PTR(err) : skb; } -static int dn_accept(struct socket *sock, struct socket *newsock, int flags) +static int dn_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk = sock->sk, *newsk; struct sk_buff *skb = NULL; @@ -1099,7 +1100,7 @@ static int dn_accept(struct socket *sock, struct socket *newsock, int flags) cb = DN_SKB_CB(skb); sk->sk_ack_backlog--; - newsk = dn_alloc_sock(sock_net(sk), newsock, sk->sk_allocation, 0); + newsk = dn_alloc_sock(sock_net(sk), newsock, sk->sk_allocation, kern); if (newsk == NULL) { release_sock(sk); kfree_skb(skb); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 5091f46826fa..6b1fc6e4278e 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -689,11 +689,12 @@ EXPORT_SYMBOL(inet_stream_connect); * Accept a pending connection. The TCP layer now gives BSD semantics. */ -int inet_accept(struct socket *sock, struct socket *newsock, int flags) +int inet_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk1 = sock->sk; int err = -EINVAL; - struct sock *sk2 = sk1->sk_prot->accept(sk1, flags, &err); + struct sock *sk2 = sk1->sk_prot->accept(sk1, flags, &err, kern); if (!sk2) goto do_err; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index b4d5980ade3b..5e313c1ac94f 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -424,7 +424,7 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo) /* * This will accept the next outstanding connection. */ -struct sock *inet_csk_accept(struct sock *sk, int flags, int *err) +struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern) { struct inet_connection_sock *icsk = inet_csk(sk); struct request_sock_queue *queue = &icsk->icsk_accept_queue; diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index 81adc29a448d..8d77ad5cadaf 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -828,7 +828,8 @@ out: * Wait for incoming connection * */ -static int irda_accept(struct socket *sock, struct socket *newsock, int flags) +static int irda_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk = sock->sk; struct irda_sock *new, *self = irda_sk(sk); @@ -836,7 +837,7 @@ static int irda_accept(struct socket *sock, struct socket *newsock, int flags) struct sk_buff *skb = NULL; int err; - err = irda_create(sock_net(sk), newsock, sk->sk_protocol, 0); + err = irda_create(sock_net(sk), newsock, sk->sk_protocol, kern); if (err) return err; diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 89bbde1081ce..84de7b6326dc 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -938,7 +938,7 @@ done: /* Accept a pending connection */ static int iucv_sock_accept(struct socket *sock, struct socket *newsock, - int flags) + int flags, bool kern) { DECLARE_WAITQUEUE(wait, current); struct sock *sk = sock->sk, *nsk; diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 06186d608a27..cb4fff785cbf 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -641,11 +641,13 @@ static void llc_cmsg_rcv(struct msghdr *msg, struct sk_buff *skb) * @sock: Socket which connections arrive on. * @newsock: Socket to move incoming connection to. * @flags: User specified operational flags. + * @kern: If the socket is kernel internal * * Accept a new incoming connection. * Returns 0 upon success, negative otherwise. */ -static int llc_ui_accept(struct socket *sock, struct socket *newsock, int flags) +static int llc_ui_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk = sock->sk, *newsk; struct llc_sock *llc, *newllc; diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 4bbf4526b885..ebf16f7f9089 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -765,7 +765,8 @@ out_release: return err; } -static int nr_accept(struct socket *sock, struct socket *newsock, int flags) +static int nr_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sk_buff *skb; struct sock *newsk; diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index 879885b31cce..2ffb18e73df6 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -441,7 +441,7 @@ struct sock *nfc_llcp_accept_dequeue(struct sock *parent, } static int llcp_sock_accept(struct socket *sock, struct socket *newsock, - int flags) + int flags, bool kern) { DECLARE_WAITQUEUE(wait, current); struct sock *sk = sock->sk, *new_sk; diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 222bedcd9575..e81537991ddf 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -772,7 +772,8 @@ static void pep_sock_close(struct sock *sk, long timeout) sock_put(sk); } -static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp) +static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp, + bool kern) { struct pep_sock *pn = pep_sk(sk), *newpn; struct sock *newsk = NULL; @@ -846,7 +847,8 @@ static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp) } /* Create a new to-be-accepted sock */ - newsk = sk_alloc(sock_net(sk), PF_PHONET, GFP_KERNEL, sk->sk_prot, 0); + newsk = sk_alloc(sock_net(sk), PF_PHONET, GFP_KERNEL, sk->sk_prot, + kern); if (!newsk) { pep_reject_conn(sk, skb, PN_PIPE_ERR_OVERLOAD, GFP_KERNEL); err = -ENOBUFS; diff --git a/net/phonet/socket.c b/net/phonet/socket.c index a6c8da3ee893..64634e3ec2fc 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -305,7 +305,7 @@ out: } static int pn_socket_accept(struct socket *sock, struct socket *newsock, - int flags) + int flags, bool kern) { struct sock *sk = sock->sk; struct sock *newsk; @@ -314,7 +314,7 @@ static int pn_socket_accept(struct socket *sock, struct socket *newsock, if (unlikely(sk->sk_state != TCP_LISTEN)) return -EINVAL; - newsk = sk->sk_prot->accept(sk, flags, &err); + newsk = sk->sk_prot->accept(sk, flags, &err, kern); if (!newsk) return err; diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 2c69a508a693..507678853e6c 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -133,7 +133,7 @@ int rds_tcp_accept_one(struct socket *sock) new_sock->type = sock->type; new_sock->ops = sock->ops; - ret = sock->ops->accept(sock, new_sock, O_NONBLOCK); + ret = sock->ops->accept(sock, new_sock, O_NONBLOCK, true); if (ret < 0) goto out; diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index b8a1df2c9785..4a9729257023 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -871,7 +871,8 @@ out_release: return err; } -static int rose_accept(struct socket *sock, struct socket *newsock, int flags) +static int rose_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sk_buff *skb; struct sock *newsk; diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 063baac5b9fe..961ee59f696a 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -640,14 +640,15 @@ static sctp_scope_t sctp_v6_scope(union sctp_addr *addr) /* Create and initialize a new sk for the socket to be returned by accept(). */ static struct sock *sctp_v6_create_accept_sk(struct sock *sk, - struct sctp_association *asoc) + struct sctp_association *asoc, + bool kern) { struct sock *newsk; struct ipv6_pinfo *newnp, *np = inet6_sk(sk); struct sctp6_sock *newsctp6sk; struct ipv6_txoptions *opt; - newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot, 0); + newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot, kern); if (!newsk) goto out; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 1b6d4574d2b0..989a900383b5 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -575,10 +575,11 @@ static int sctp_v4_is_ce(const struct sk_buff *skb) /* Create and initialize a new sk for the socket returned by accept(). */ static struct sock *sctp_v4_create_accept_sk(struct sock *sk, - struct sctp_association *asoc) + struct sctp_association *asoc, + bool kern) { struct sock *newsk = sk_alloc(sock_net(sk), PF_INET, GFP_KERNEL, - sk->sk_prot, 0); + sk->sk_prot, kern); struct inet_sock *newinet; if (!newsk) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 6f0a9be50f50..0f378ea2ae38 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4116,7 +4116,7 @@ static int sctp_disconnect(struct sock *sk, int flags) * descriptor will be returned from accept() to represent the newly * formed association. */ -static struct sock *sctp_accept(struct sock *sk, int flags, int *err) +static struct sock *sctp_accept(struct sock *sk, int flags, int *err, bool kern) { struct sctp_sock *sp; struct sctp_endpoint *ep; @@ -4151,7 +4151,7 @@ static struct sock *sctp_accept(struct sock *sk, int flags, int *err) */ asoc = list_entry(ep->asocs.next, struct sctp_association, asocs); - newsk = sp->pf->create_accept_sk(sk, asoc); + newsk = sp->pf->create_accept_sk(sk, asoc, kern); if (!newsk) { error = -ENOMEM; goto out; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 85837ab90e89..093803786eac 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -944,7 +944,7 @@ out: } static int smc_accept(struct socket *sock, struct socket *new_sock, - int flags) + int flags, bool kern) { struct sock *sk = sock->sk, *nsk; DECLARE_WAITQUEUE(wait, current); diff --git a/net/socket.c b/net/socket.c index e0757e648c0c..e034fe4164be 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1506,7 +1506,7 @@ SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr, if (err) goto out_fd; - err = sock->ops->accept(sock, newsock, sock->file->f_flags); + err = sock->ops->accept(sock, newsock, sock->file->f_flags, false); if (err < 0) goto out_fd; @@ -3239,7 +3239,7 @@ int kernel_accept(struct socket *sock, struct socket **newsock, int flags) if (err < 0) goto done; - err = sock->ops->accept(sock, *newsock, flags); + err = sock->ops->accept(sock, *newsock, flags, true); if (err < 0) { sock_release(*newsock); *newsock = NULL; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 43e4045e72bc..7130e73bd42c 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -115,7 +115,8 @@ static void tipc_data_ready(struct sock *sk); static void tipc_write_space(struct sock *sk); static void tipc_sock_destruct(struct sock *sk); static int tipc_release(struct socket *sock); -static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags); +static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags, + bool kern); static void tipc_sk_timeout(unsigned long data); static int tipc_sk_publish(struct tipc_sock *tsk, uint scope, struct tipc_name_seq const *seq); @@ -2029,7 +2030,8 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo) * * Returns 0 on success, errno otherwise */ -static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags) +static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags, + bool kern) { struct sock *new_sk, *sk = sock->sk; struct sk_buff *buf; @@ -2051,7 +2053,7 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags) buf = skb_peek(&sk->sk_receive_queue); - res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, 0); + res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, kern); if (res) goto exit; security_sk_clone(sock->sk, new_sock->sk); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index ee37b390260a..928691c43408 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -636,7 +636,7 @@ static int unix_bind(struct socket *, struct sockaddr *, int); static int unix_stream_connect(struct socket *, struct sockaddr *, int addr_len, int flags); static int unix_socketpair(struct socket *, struct socket *); -static int unix_accept(struct socket *, struct socket *, int); +static int unix_accept(struct socket *, struct socket *, int, bool); static int unix_getname(struct socket *, struct sockaddr *, int *, int); static unsigned int unix_poll(struct file *, struct socket *, poll_table *); static unsigned int unix_dgram_poll(struct file *, struct socket *, @@ -1402,7 +1402,8 @@ static void unix_sock_inherit_flags(const struct socket *old, set_bit(SOCK_PASSSEC, &new->flags); } -static int unix_accept(struct socket *sock, struct socket *newsock, int flags) +static int unix_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk = sock->sk; struct sock *tsk; diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 9192ead66751..9f770f33c100 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1250,7 +1250,8 @@ out: return err; } -static int vsock_accept(struct socket *sock, struct socket *newsock, int flags) +static int vsock_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *listener; int err; diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index fd28a49dbe8f..8b911c29860e 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -852,7 +852,8 @@ static int x25_wait_for_data(struct sock *sk, long timeout) return rc; } -static int x25_accept(struct socket *sock, struct socket *newsock, int flags) +static int x25_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk = sock->sk; struct sock *newsk; -- cgit v1.2.3 From 40c50c1fecdf012a3bf055ec813f0ef2eda2749c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 10 Mar 2017 13:17:18 +0100 Subject: kexec, x86/purgatory: Unbreak it and clean it up The purgatory code defines global variables which are referenced via a symbol lookup in the kexec code (core and arch). A recent commit addressing sparse warnings made these static and thereby broke kexec_file. Why did this happen? Simply because the whole machinery is undocumented and lacks any form of forward declarations. The variable names are unspecific and lack a prefix, so adding forward declarations creates shadow variables in the core code. Aside of that the code relies on magic constants and duplicate struct definitions with no way to ensure that these things stay in sync. The section placement of the purgatory variables happened by chance and not by design. Unbreak kexec and cleanup the mess: - Add proper forward declarations and document the usage - Use common struct definition - Use the proper common defines instead of magic constants - Add a purgatory_ prefix to have a proper name space - Use ARRAY_SIZE() instead of a homebrewn reimplementation - Add proper sections to the purgatory variables [ From Mike ] Fixes: 72042a8c7b01 ("x86/purgatory: Make functions and variables static") Reported-by: Mike Galbraith < Signed-off-by: Thomas Gleixner Cc: Nicholas Mc Guire Cc: Borislav Petkov Cc: Vivek Goyal Cc: "Tobin C. Harding" Link: http://lkml.kernel.org/r/alpine.DEB.2.20.1703101315140.3681@nanos Signed-off-by: Thomas Gleixner --- arch/powerpc/purgatory/trampoline.S | 12 ++++++------ arch/x86/include/asm/purgatory.h | 20 ++++++++++++++++++++ arch/x86/kernel/machine_kexec_64.c | 9 ++++++--- arch/x86/purgatory/purgatory.c | 35 +++++++++++++++++------------------ arch/x86/purgatory/purgatory.h | 8 -------- arch/x86/purgatory/setup-x86_64.S | 2 +- arch/x86/purgatory/sha256.h | 1 - include/linux/purgatory.h | 23 +++++++++++++++++++++++ kernel/kexec_file.c | 8 ++++---- kernel/kexec_internal.h | 6 +----- 10 files changed, 78 insertions(+), 46 deletions(-) create mode 100644 arch/x86/include/asm/purgatory.h delete mode 100644 arch/x86/purgatory/purgatory.h create mode 100644 include/linux/purgatory.h (limited to 'include/linux') diff --git a/arch/powerpc/purgatory/trampoline.S b/arch/powerpc/purgatory/trampoline.S index f9760ccf4032..3696ea6c4826 100644 --- a/arch/powerpc/purgatory/trampoline.S +++ b/arch/powerpc/purgatory/trampoline.S @@ -116,13 +116,13 @@ dt_offset: .data .balign 8 -.globl sha256_digest -sha256_digest: +.globl purgatory_sha256_digest +purgatory_sha256_digest: .skip 32 - .size sha256_digest, . - sha256_digest + .size purgatory_sha256_digest, . - purgatory_sha256_digest .balign 8 -.globl sha_regions -sha_regions: +.globl purgatory_sha_regions +purgatory_sha_regions: .skip 8 * 2 * 16 - .size sha_regions, . - sha_regions + .size purgatory_sha_regions, . - purgatory_sha_regions diff --git a/arch/x86/include/asm/purgatory.h b/arch/x86/include/asm/purgatory.h new file mode 100644 index 000000000000..d7da2729903d --- /dev/null +++ b/arch/x86/include/asm/purgatory.h @@ -0,0 +1,20 @@ +#ifndef _ASM_X86_PURGATORY_H +#define _ASM_X86_PURGATORY_H + +#ifndef __ASSEMBLY__ +#include + +extern void purgatory(void); +/* + * These forward declarations serve two purposes: + * + * 1) Make sparse happy when checking arch/purgatory + * 2) Document that these are required to be global so the symbol + * lookup in kexec works + */ +extern unsigned long purgatory_backup_dest; +extern unsigned long purgatory_backup_src; +extern unsigned long purgatory_backup_sz; +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_PURGATORY_H */ diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 307b1f4543de..857cdbd02867 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -194,19 +194,22 @@ static int arch_update_purgatory(struct kimage *image) /* Setup copying of backup region */ if (image->type == KEXEC_TYPE_CRASH) { - ret = kexec_purgatory_get_set_symbol(image, "backup_dest", + ret = kexec_purgatory_get_set_symbol(image, + "purgatory_backup_dest", &image->arch.backup_load_addr, sizeof(image->arch.backup_load_addr), 0); if (ret) return ret; - ret = kexec_purgatory_get_set_symbol(image, "backup_src", + ret = kexec_purgatory_get_set_symbol(image, + "purgatory_backup_src", &image->arch.backup_src_start, sizeof(image->arch.backup_src_start), 0); if (ret) return ret; - ret = kexec_purgatory_get_set_symbol(image, "backup_sz", + ret = kexec_purgatory_get_set_symbol(image, + "purgatory_backup_sz", &image->arch.backup_src_sz, sizeof(image->arch.backup_src_sz), 0); if (ret) diff --git a/arch/x86/purgatory/purgatory.c b/arch/x86/purgatory/purgatory.c index b6d5c8946e66..470edad96bb9 100644 --- a/arch/x86/purgatory/purgatory.c +++ b/arch/x86/purgatory/purgatory.c @@ -10,22 +10,19 @@ * Version 2. See the file COPYING for more details. */ +#include +#include + #include "sha256.h" -#include "purgatory.h" #include "../boot/string.h" -struct sha_region { - unsigned long start; - unsigned long len; -}; - -static unsigned long backup_dest; -static unsigned long backup_src; -static unsigned long backup_sz; +unsigned long purgatory_backup_dest __section(.kexec-purgatory); +unsigned long purgatory_backup_src __section(.kexec-purgatory); +unsigned long purgatory_backup_sz __section(.kexec-purgatory); -static u8 sha256_digest[SHA256_DIGEST_SIZE] = { 0 }; +u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE] __section(.kexec-purgatory); -struct sha_region sha_regions[16] = {}; +struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX] __section(.kexec-purgatory); /* * On x86, second kernel requries first 640K of memory to boot. Copy @@ -34,26 +31,28 @@ struct sha_region sha_regions[16] = {}; */ static int copy_backup_region(void) { - if (backup_dest) - memcpy((void *)backup_dest, (void *)backup_src, backup_sz); - + if (purgatory_backup_dest) { + memcpy((void *)purgatory_backup_dest, + (void *)purgatory_backup_src, purgatory_backup_sz); + } return 0; } static int verify_sha256_digest(void) { - struct sha_region *ptr, *end; + struct kexec_sha_region *ptr, *end; u8 digest[SHA256_DIGEST_SIZE]; struct sha256_state sctx; sha256_init(&sctx); - end = &sha_regions[sizeof(sha_regions)/sizeof(sha_regions[0])]; - for (ptr = sha_regions; ptr < end; ptr++) + end = purgatory_sha_regions + ARRAY_SIZE(purgatory_sha_regions); + + for (ptr = purgatory_sha_regions; ptr < end; ptr++) sha256_update(&sctx, (uint8_t *)(ptr->start), ptr->len); sha256_final(&sctx, digest); - if (memcmp(digest, sha256_digest, sizeof(digest))) + if (memcmp(digest, purgatory_sha256_digest, sizeof(digest))) return 1; return 0; diff --git a/arch/x86/purgatory/purgatory.h b/arch/x86/purgatory/purgatory.h deleted file mode 100644 index e2e365a6c192..000000000000 --- a/arch/x86/purgatory/purgatory.h +++ /dev/null @@ -1,8 +0,0 @@ -#ifndef PURGATORY_H -#define PURGATORY_H - -#ifndef __ASSEMBLY__ -extern void purgatory(void); -#endif /* __ASSEMBLY__ */ - -#endif /* PURGATORY_H */ diff --git a/arch/x86/purgatory/setup-x86_64.S b/arch/x86/purgatory/setup-x86_64.S index f90e9dfa90bb..dfae9b9e60b5 100644 --- a/arch/x86/purgatory/setup-x86_64.S +++ b/arch/x86/purgatory/setup-x86_64.S @@ -9,7 +9,7 @@ * This source code is licensed under the GNU General Public License, * Version 2. See the file COPYING for more details. */ -#include "purgatory.h" +#include .text .globl purgatory_start diff --git a/arch/x86/purgatory/sha256.h b/arch/x86/purgatory/sha256.h index bd15a4127735..2867d9825a57 100644 --- a/arch/x86/purgatory/sha256.h +++ b/arch/x86/purgatory/sha256.h @@ -10,7 +10,6 @@ #ifndef SHA256_H #define SHA256_H - #include #include diff --git a/include/linux/purgatory.h b/include/linux/purgatory.h new file mode 100644 index 000000000000..d60d4e278609 --- /dev/null +++ b/include/linux/purgatory.h @@ -0,0 +1,23 @@ +#ifndef _LINUX_PURGATORY_H +#define _LINUX_PURGATORY_H + +#include +#include +#include + +struct kexec_sha_region { + unsigned long start; + unsigned long len; +}; + +/* + * These forward declarations serve two purposes: + * + * 1) Make sparse happy when checking arch/purgatory + * 2) Document that these are required to be global so the symbol + * lookup in kexec works + */ +extern struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX]; +extern u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE]; + +#endif diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index b56a558e406d..b118735fea9d 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -614,13 +614,13 @@ static int kexec_calculate_store_digests(struct kimage *image) ret = crypto_shash_final(desc, digest); if (ret) goto out_free_digest; - ret = kexec_purgatory_get_set_symbol(image, "sha_regions", - sha_regions, sha_region_sz, 0); + ret = kexec_purgatory_get_set_symbol(image, "purgatory_sha_regions", + sha_regions, sha_region_sz, 0); if (ret) goto out_free_digest; - ret = kexec_purgatory_get_set_symbol(image, "sha256_digest", - digest, SHA256_DIGEST_SIZE, 0); + ret = kexec_purgatory_get_set_symbol(image, "purgatory_sha256_digest", + digest, SHA256_DIGEST_SIZE, 0); if (ret) goto out_free_digest; } diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h index 4cef7e4706b0..799a8a452187 100644 --- a/kernel/kexec_internal.h +++ b/kernel/kexec_internal.h @@ -15,11 +15,7 @@ int kimage_is_destination_range(struct kimage *image, extern struct mutex kexec_mutex; #ifdef CONFIG_KEXEC_FILE -struct kexec_sha_region { - unsigned long start; - unsigned long len; -}; - +#include void kimage_file_post_load_cleanup(struct kimage *image); #else /* CONFIG_KEXEC_FILE */ static inline void kimage_file_post_load_cleanup(struct kimage *image) { } -- cgit v1.2.3 From c962cff17dfa11f4a8227ac16de2b28aea3312e4 Mon Sep 17 00:00:00 2001 From: Dou Liyang Date: Fri, 3 Mar 2017 16:02:23 +0800 Subject: Revert "x86/acpi: Set persistent cpuid <-> nodeid mapping when booting" Revert: dc6db24d2476 ("x86/acpi: Set persistent cpuid <-> nodeid mapping when booting") The mapping of "cpuid <-> nodeid" is established at boot time via ACPI tables to keep associations of workqueues and other node related items consistent across cpu hotplug. But, ACPI tables are unreliable and failures with that boot time mapping have been reported on machines where the ACPI table and the physical information which is retrieved at actual hotplug is inconsistent. Revert the mapping implementation so it can be replaced with a less error prone approach. Signed-off-by: Dou Liyang Tested-by: Xiaolong Ye Cc: rjw@rjwysocki.net Cc: linux-acpi@vger.kernel.org Cc: guzheng1@huawei.com Cc: izumi.taku@jp.fujitsu.com Cc: lenb@kernel.org Link: http://lkml.kernel.org/r/1488528147-2279-2-git-send-email-douly.fnst@cn.fujitsu.com Signed-off-by: Thomas Gleixner --- arch/x86/kernel/acpi/boot.c | 2 +- drivers/acpi/acpi_processor.c | 5 --- drivers/acpi/bus.c | 1 - drivers/acpi/processor_core.c | 73 ------------------------------------------- include/linux/acpi.h | 3 -- 5 files changed, 1 insertion(+), 83 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index ae32838cac5f..f6b0e87d2388 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -710,7 +710,7 @@ static void __init acpi_set_irq_model_ioapic(void) #ifdef CONFIG_ACPI_HOTPLUG_CPU #include -int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) +static int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) { #ifdef CONFIG_ACPI_NUMA int nid; diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c index 4467a8089ab8..5d208a99d0c9 100644 --- a/drivers/acpi/acpi_processor.c +++ b/drivers/acpi/acpi_processor.c @@ -182,11 +182,6 @@ int __weak arch_register_cpu(int cpu) void __weak arch_unregister_cpu(int cpu) {} -int __weak acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) -{ - return -ENODEV; -} - static int acpi_processor_hotadd_init(struct acpi_processor *pr) { unsigned long long sta; diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index 80cb5eb75b63..34fbe027e73a 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -1249,7 +1249,6 @@ static int __init acpi_init(void) acpi_wakeup_device_init(); acpi_debugger_init(); acpi_setup_sb_notify_handler(); - acpi_set_processor_mapping(); return 0; } diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c index 611a5585a902..a84386204659 100644 --- a/drivers/acpi/processor_core.c +++ b/drivers/acpi/processor_core.c @@ -278,79 +278,6 @@ int acpi_get_cpuid(acpi_handle handle, int type, u32 acpi_id) } EXPORT_SYMBOL_GPL(acpi_get_cpuid); -#ifdef CONFIG_ACPI_HOTPLUG_CPU -static bool __init -map_processor(acpi_handle handle, phys_cpuid_t *phys_id, int *cpuid) -{ - int type, id; - u32 acpi_id; - acpi_status status; - acpi_object_type acpi_type; - unsigned long long tmp; - union acpi_object object = { 0 }; - struct acpi_buffer buffer = { sizeof(union acpi_object), &object }; - - status = acpi_get_type(handle, &acpi_type); - if (ACPI_FAILURE(status)) - return false; - - switch (acpi_type) { - case ACPI_TYPE_PROCESSOR: - status = acpi_evaluate_object(handle, NULL, NULL, &buffer); - if (ACPI_FAILURE(status)) - return false; - acpi_id = object.processor.proc_id; - - /* validate the acpi_id */ - if(acpi_processor_validate_proc_id(acpi_id)) - return false; - break; - case ACPI_TYPE_DEVICE: - status = acpi_evaluate_integer(handle, "_UID", NULL, &tmp); - if (ACPI_FAILURE(status)) - return false; - acpi_id = tmp; - break; - default: - return false; - } - - type = (acpi_type == ACPI_TYPE_DEVICE) ? 1 : 0; - - *phys_id = __acpi_get_phys_id(handle, type, acpi_id, false); - id = acpi_map_cpuid(*phys_id, acpi_id); - - if (id < 0) - return false; - *cpuid = id; - return true; -} - -static acpi_status __init -set_processor_node_mapping(acpi_handle handle, u32 lvl, void *context, - void **rv) -{ - phys_cpuid_t phys_id; - int cpu_id; - - if (!map_processor(handle, &phys_id, &cpu_id)) - return AE_ERROR; - - acpi_map_cpu2node(handle, cpu_id, phys_id); - return AE_OK; -} - -void __init acpi_set_processor_mapping(void) -{ - /* Set persistent cpu <-> node mapping for all processors. */ - acpi_walk_namespace(ACPI_TYPE_PROCESSOR, ACPI_ROOT_OBJECT, - ACPI_UINT32_MAX, set_processor_node_mapping, - NULL, NULL, NULL); -} -#else -void __init acpi_set_processor_mapping(void) {} -#endif /* CONFIG_ACPI_HOTPLUG_CPU */ - #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC static int get_ioapic_id(struct acpi_subtable_header *entry, u32 gsi_base, u64 *phys_addr, int *ioapic_id) diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 673acda012af..63a7519b00cc 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -294,11 +294,8 @@ bool acpi_processor_validate_proc_id(int proc_id); int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id, int *pcpu); int acpi_unmap_cpu(int cpu); -int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid); #endif /* CONFIG_ACPI_HOTPLUG_CPU */ -void acpi_set_processor_mapping(void); - #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC int acpi_get_ioapic_id(acpi_handle handle, u32 gsi_base, u64 *phys_addr); #endif -- cgit v1.2.3 From a77d6cd968497792e072b74dff45b891ba778ddb Mon Sep 17 00:00:00 2001 From: Dou Liyang Date: Fri, 3 Mar 2017 16:02:27 +0800 Subject: acpi/processor: Check for duplicate processor ids at hotplug time The check for duplicate processor ids happens at boot time based on the ACPI table contents, but the final sanity checks for a processor happen at hotplug time. At hotplug time, where the physical information is available, which might differ from the ACPI table information, a check for duplicate processor ids is missing. Add it to the hotplug checks and rename the function so it better reflects its purpose. Signed-off-by: Dou Liyang Tested-by: Xiaolong Ye Cc: rjw@rjwysocki.net Cc: linux-acpi@vger.kernel.org Cc: guzheng1@huawei.com Cc: izumi.taku@jp.fujitsu.com Cc: lenb@kernel.org Link: http://lkml.kernel.org/r/1488528147-2279-6-git-send-email-douly.fnst@cn.fujitsu.com Signed-off-by: Thomas Gleixner --- drivers/acpi/acpi_processor.c | 13 ++++++++++--- include/linux/acpi.h | 2 +- 2 files changed, 11 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c index 9a98d7e00200..0143135b3abe 100644 --- a/drivers/acpi/acpi_processor.c +++ b/drivers/acpi/acpi_processor.c @@ -280,6 +280,13 @@ static int acpi_processor_get_info(struct acpi_device *device) pr->acpi_id = value; } + if (acpi_duplicate_processor_id(pr->acpi_id)) { + dev_err(&device->dev, + "Failed to get unique processor _UID (0x%x)\n", + pr->acpi_id); + return -ENODEV; + } + pr->phys_id = acpi_get_phys_id(pr->handle, device_declaration, pr->acpi_id); if (invalid_phys_cpuid(pr->phys_id)) @@ -580,7 +587,7 @@ static struct acpi_scan_handler processor_container_handler = { static int nr_unique_ids __initdata; /* The number of the duplicate processor IDs */ -static int nr_duplicate_ids __initdata; +static int nr_duplicate_ids; /* Used to store the unique processor IDs */ static int unique_processor_ids[] __initdata = { @@ -588,7 +595,7 @@ static int unique_processor_ids[] __initdata = { }; /* Used to store the duplicate processor IDs */ -static int duplicate_processor_ids[] __initdata = { +static int duplicate_processor_ids[] = { [0 ... NR_CPUS - 1] = -1, }; @@ -679,7 +686,7 @@ void __init acpi_processor_check_duplicates(void) NULL, NULL); } -bool __init acpi_processor_validate_proc_id(int proc_id) +bool acpi_duplicate_processor_id(int proc_id) { int i; diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 63a7519b00cc..9b05886f9773 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -287,7 +287,7 @@ static inline bool invalid_phys_cpuid(phys_cpuid_t phys_id) } /* Validate the processor object's proc_id */ -bool acpi_processor_validate_proc_id(int proc_id); +bool acpi_duplicate_processor_id(int proc_id); #ifdef CONFIG_ACPI_HOTPLUG_CPU /* Arch dependent functions for cpu hotplug support */ -- cgit v1.2.3 From 65869a47f3488253f5fd88cc4f14e0a4e2601a55 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 11 Mar 2017 16:55:49 +0100 Subject: bpf: improve read-only handling Improve bpf_{prog,jit_binary}_{un,}lock_ro() by throwing a one-time warning in case of an error when the image couldn't be set read-only, and also mark struct bpf_prog as locked when bpf_prog_lock_ro() was called. Reason for the latter is that bpf_prog_unlock_ro() is called from various places including error paths, and we shouldn't mess with page attributes when really not needed. For bpf_jit_binary_unlock_ro() this is not needed as jited flag implicitly indicates this, thus for archs with ARCH_HAS_SET_MEMORY we're guaranteed to have a previously locked image. Overall, this should also help us to identify any further potential issues with set_memory_*() helpers. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/filter.h | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 0c167fdee5f7..fbf7b39e8103 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -409,6 +409,7 @@ struct bpf_prog { u16 pages; /* Number of allocated pages */ kmemcheck_bitfield_begin(meta); u16 jited:1, /* Is our filter JIT'ed? */ + locked:1, /* Program image locked? */ gpl_compatible:1, /* Is filter GPL compatible? */ cb_access:1, /* Is control block accessed? */ dst_needed:1, /* Do we need dst entry? */ @@ -554,22 +555,29 @@ static inline bool bpf_prog_was_classic(const struct bpf_prog *prog) #ifdef CONFIG_ARCH_HAS_SET_MEMORY static inline void bpf_prog_lock_ro(struct bpf_prog *fp) { - set_memory_ro((unsigned long)fp, fp->pages); + fp->locked = 1; + WARN_ON_ONCE(set_memory_ro((unsigned long)fp, fp->pages)); } static inline void bpf_prog_unlock_ro(struct bpf_prog *fp) { - set_memory_rw((unsigned long)fp, fp->pages); + if (fp->locked) { + WARN_ON_ONCE(set_memory_rw((unsigned long)fp, fp->pages)); + /* In case set_memory_rw() fails, we want to be the first + * to crash here instead of some random place later on. + */ + fp->locked = 0; + } } static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { - set_memory_ro((unsigned long)hdr, hdr->pages); + WARN_ON_ONCE(set_memory_ro((unsigned long)hdr, hdr->pages)); } static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr) { - set_memory_rw((unsigned long)hdr, hdr->pages); + WARN_ON_ONCE(set_memory_rw((unsigned long)hdr, hdr->pages)); } #else static inline void bpf_prog_lock_ro(struct bpf_prog *fp) -- cgit v1.2.3 From c42f8218610aa09d7d3795e5810387673c1f84b6 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Thu, 9 Mar 2017 17:20:04 +0100 Subject: iio: sw-device: Fix config group initialization Use the IS_ENABLED() helper macro to ensure that the configfs group is initialized either when configfs is built-in or when configfs is built as a module. Otherwise software device creation will result in undefined behaviour when configfs is built as a module since the configfs group for the device not properly initialized. Similar to commit b2f0c09664b7 ("iio: sw-trigger: Fix config group initialization"). Fixes: 0f3a8c3f34f7 ("iio: Add support for creating IIO devices via configfs") Reported-by: Miguel Robles Signed-off-by: Lars-Peter Clausen Acked-by: Daniel Baluta Cc: Signed-off-by: Jonathan Cameron --- include/linux/iio/sw_device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/sw_device.h b/include/linux/iio/sw_device.h index 23ca41515527..fa7931933067 100644 --- a/include/linux/iio/sw_device.h +++ b/include/linux/iio/sw_device.h @@ -62,7 +62,7 @@ void iio_swd_group_init_type_name(struct iio_sw_device *d, const char *name, struct config_item_type *type) { -#ifdef CONFIG_CONFIGFS_FS +#if IS_ENABLED(CONFIG_CONFIGFS_FS) config_group_init_type_name(&d->group, name, type); #endif } -- cgit v1.2.3 From 3243367b209faed5c320a4e5f9a565ee2a2ba958 Mon Sep 17 00:00:00 2001 From: Samuel Thibault Date: Mon, 13 Mar 2017 20:50:08 +0100 Subject: usb-core: Add LINEAR_FRAME_INTR_BINTERVAL USB quirk Some USB 2.0 devices erroneously report millisecond values in bInterval. The generic config code manages to catch most of them, but in some cases it's not completely enough. The case at stake here is a USB 2.0 braille device, which wants to announce 10ms and thus sets bInterval to 10, but with the USB 2.0 computation that yields to 64ms. It happens that one can type fast enough to reach this interval and get the device buffers overflown, leading to problematic latencies. The generic config code does not catch this case because the 64ms is considered a sane enough value. This change thus adds a USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL quirk to mark devices which actually report milliseconds in bInterval, and marks Vario Ultra devices as needing it. Signed-off-by: Samuel Thibault Acked-by: Alan Stern Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/config.c | 10 ++++++++++ drivers/usb/core/quirks.c | 8 ++++++++ include/linux/usb/quirks.h | 6 ++++++ 3 files changed, 24 insertions(+) (limited to 'include/linux') diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index 25dbd8c7aec7..4be52c602e9b 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -280,6 +280,16 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum, /* * Adjust bInterval for quirked devices. + */ + /* + * This quirk fixes bIntervals reported in ms. + */ + if (to_usb_device(ddev)->quirks & + USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL) { + n = clamp(fls(d->bInterval) + 3, i, j); + i = j = n; + } + /* * This quirk fixes bIntervals reported in * linear microframes. */ diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 24f9f98968a5..96b21b0dac1e 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -170,6 +170,14 @@ static const struct usb_device_id usb_quirk_list[] = { /* M-Systems Flash Disk Pioneers */ { USB_DEVICE(0x08ec, 0x1000), .driver_info = USB_QUIRK_RESET_RESUME }, + /* Baum Vario Ultra */ + { USB_DEVICE(0x0904, 0x6101), .driver_info = + USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL }, + { USB_DEVICE(0x0904, 0x6102), .driver_info = + USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL }, + { USB_DEVICE(0x0904, 0x6103), .driver_info = + USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL }, + /* Keytouch QWERTY Panel keyboard */ { USB_DEVICE(0x0926, 0x3333), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index 1d0043dc34e4..de2a722fe3cf 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -50,4 +50,10 @@ /* device can't handle Link Power Management */ #define USB_QUIRK_NO_LPM BIT(10) +/* + * Device reports its bInterval as linear frames instead of the + * USB 2.0 calculation. + */ +#define USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL BIT(11) + #endif /* __LINUX_USB_QUIRKS_H */ -- cgit v1.2.3 From 0043c1dfbec7b6e2427409059b05347d6f51aa9f Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Wed, 8 Feb 2017 09:24:25 +0000 Subject: serial: st-asc: Use new GPIOD API to obtain RTS pin The commits mentioned below adapt the GPIO API to allow more information to be passed directly through devm_get_gpiod_from_child() in the first instance. This facilitates the removal of subsequent calls, such as gpiod_direction_output(). This patch firstly moves to utilise the new API and secondly removes the now superfluous call do set the direction. Reported-by: Stephen Rothwell Suggested-by: Boris Brezillon Signed-off-by: Lee Jones [Also drop the header file dummies that only this driver was using] Acked-by: Greg Kroah-Hartman Signed-off-by: Linus Walleij --- drivers/tty/serial/st-asc.c | 11 ++++++----- include/linux/gpio/consumer.h | 16 ---------------- 2 files changed, 6 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/serial/st-asc.c b/drivers/tty/serial/st-asc.c index bcf1d33e6ffe..c334bcc59c64 100644 --- a/drivers/tty/serial/st-asc.c +++ b/drivers/tty/serial/st-asc.c @@ -575,12 +575,13 @@ static void asc_set_termios(struct uart_port *port, struct ktermios *termios, pinctrl_select_state(ascport->pinctrl, ascport->states[NO_HW_FLOWCTRL]); - gpiod = devm_get_gpiod_from_child(port->dev, "rts", - &np->fwnode); - if (!IS_ERR(gpiod)) { - gpiod_direction_output(gpiod, 0); + gpiod = devm_fwnode_get_gpiod_from_child(port->dev, + "rts", + &np->fwnode, + GPIOD_OUT_LOW, + np->name); + if (!IS_ERR(gpiod)) ascport->rts = gpiod; - } } } diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 2484b2fcc6eb..933d93656605 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -143,15 +143,6 @@ struct gpio_desc *devm_fwnode_get_index_gpiod_from_child(struct device *dev, struct fwnode_handle *child, enum gpiod_flags flags, const char *label); -/* FIXME: delete this helper when users are switched over */ -static inline struct gpio_desc *devm_get_gpiod_from_child(struct device *dev, - const char *con_id, struct fwnode_handle *child) -{ - return devm_fwnode_get_index_gpiod_from_child(dev, con_id, - 0, child, - GPIOD_ASIS, - "?"); -} #else /* CONFIG_GPIOLIB */ @@ -444,13 +435,6 @@ struct gpio_desc *devm_fwnode_get_index_gpiod_from_child(struct device *dev, return ERR_PTR(-ENOSYS); } -/* FIXME: delete this when all users are switched over */ -static inline struct gpio_desc *devm_get_gpiod_from_child(struct device *dev, - const char *con_id, struct fwnode_handle *child) -{ - return ERR_PTR(-ENOSYS); -} - #endif /* CONFIG_GPIOLIB */ static inline -- cgit v1.2.3 From 94840e3c802daa1a62985957f36ac48faf8ceedd Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 22 Feb 2017 13:25:14 -0800 Subject: fscrypt: eliminate ->prepare_context() operation The only use of the ->prepare_context() fscrypt operation was to allow ext4 to evict inline data from the inode before ->set_context(). However, there is no reason why this cannot be done as simply the first step in ->set_context(), and in fact it makes more sense to do it that way because then the policy modes and flags get validated before any real work is done. Therefore, merge ext4_prepare_context() into ext4_set_context(), and remove ->prepare_context(). Signed-off-by: Eric Biggers Signed-off-by: Theodore Ts'o --- fs/crypto/policy.c | 7 ------- fs/ext4/super.c | 10 ++++------ include/linux/fscrypt_common.h | 1 - 3 files changed, 4 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index 14b76da71269..4908906d54d5 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -33,17 +33,10 @@ static int create_encryption_context_from_policy(struct inode *inode, const struct fscrypt_policy *policy) { struct fscrypt_context ctx; - int res; if (!inode->i_sb->s_cop->set_context) return -EOPNOTSUPP; - if (inode->i_sb->s_cop->prepare_context) { - res = inode->i_sb->s_cop->prepare_context(inode); - if (res) - return res; - } - ctx.format = FS_ENCRYPTION_CONTEXT_FORMAT_V1; memcpy(ctx.master_key_descriptor, policy->master_key_descriptor, FS_KEY_DESCRIPTOR_SIZE); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 2e03a0a88d92..a9448db1cf7e 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1120,17 +1120,16 @@ static int ext4_get_context(struct inode *inode, void *ctx, size_t len) EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx, len); } -static int ext4_prepare_context(struct inode *inode) -{ - return ext4_convert_inline_data(inode); -} - static int ext4_set_context(struct inode *inode, const void *ctx, size_t len, void *fs_data) { handle_t *handle = fs_data; int res, res2, retries = 0; + res = ext4_convert_inline_data(inode); + if (res) + return res; + /* * If a journal handle was specified, then the encryption context is * being set on a new inode via inheritance and is part of a larger @@ -1196,7 +1195,6 @@ static unsigned ext4_max_namelen(struct inode *inode) static const struct fscrypt_operations ext4_cryptops = { .key_prefix = "ext4:", .get_context = ext4_get_context, - .prepare_context = ext4_prepare_context, .set_context = ext4_set_context, .dummy_context = ext4_dummy_context, .is_encrypted = ext4_encrypted_inode, diff --git a/include/linux/fscrypt_common.h b/include/linux/fscrypt_common.h index 547f81592ba1..10c1abfbac6c 100644 --- a/include/linux/fscrypt_common.h +++ b/include/linux/fscrypt_common.h @@ -87,7 +87,6 @@ struct fscrypt_operations { unsigned int flags; const char *key_prefix; int (*get_context)(struct inode *, void *, size_t); - int (*prepare_context)(struct inode *); int (*set_context)(struct inode *, const void *, size_t, void *); int (*dummy_context)(struct inode *); bool (*is_encrypted)(struct inode *); -- cgit v1.2.3 From 8200f2085abe7f29a016381f3122000cc7b2a760 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Sat, 4 Mar 2017 18:13:57 -0700 Subject: vmbus: use rcu for per-cpu channel list The per-cpu channel list is now referred to in the interrupt routine. This is mostly safe since the host will not normally generate an interrupt when channel is being deleted but if it did then there would be a use after free problem. To solve, this use RCU protection on ther per-cpu list. Fixes: 631e63a9f346 ("vmbus: change to per channel tasklet") Signed-off-by: Stephen Hemminger Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- drivers/hv/channel_mgmt.c | 7 ++++--- drivers/hv/vmbus_drv.c | 6 +++++- include/linux/hyperv.h | 7 +++++++ 3 files changed, 16 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index f33465d78a02..d2cfa3eb71a2 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -350,7 +350,8 @@ static struct vmbus_channel *alloc_channel(void) static void free_channel(struct vmbus_channel *channel) { tasklet_kill(&channel->callback_event); - kfree(channel); + + kfree_rcu(channel, rcu); } static void percpu_channel_enq(void *arg) @@ -359,14 +360,14 @@ static void percpu_channel_enq(void *arg) struct hv_per_cpu_context *hv_cpu = this_cpu_ptr(hv_context.cpu_context); - list_add_tail(&channel->percpu_list, &hv_cpu->chan_list); + list_add_tail_rcu(&channel->percpu_list, &hv_cpu->chan_list); } static void percpu_channel_deq(void *arg) { struct vmbus_channel *channel = arg; - list_del(&channel->percpu_list); + list_del_rcu(&channel->percpu_list); } diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index da6b59ba5940..8370b9dc6037 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -939,8 +939,10 @@ static void vmbus_chan_sched(struct hv_per_cpu_context *hv_cpu) if (relid == 0) continue; + rcu_read_lock(); + /* Find channel based on relid */ - list_for_each_entry(channel, &hv_cpu->chan_list, percpu_list) { + list_for_each_entry_rcu(channel, &hv_cpu->chan_list, percpu_list) { if (channel->offermsg.child_relid != relid) continue; @@ -956,6 +958,8 @@ static void vmbus_chan_sched(struct hv_per_cpu_context *hv_cpu) tasklet_schedule(&channel->callback_event); } } + + rcu_read_unlock(); } } diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 62bbf3c1aa4a..c4c7ae91f9d1 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -845,6 +845,13 @@ struct vmbus_channel { * link up channels based on their CPU affinity. */ struct list_head percpu_list; + + /* + * Defer freeing channel until after all cpu's have + * gone through grace period. + */ + struct rcu_head rcu; + /* * For performance critical channels (storage, networking * etc,), Hyper-V has a mechanism to enhance the throughput -- cgit v1.2.3 From dad72a1d28442b03aac86836a42de2d00a1014ab Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Sat, 4 Mar 2017 18:13:58 -0700 Subject: vmbus: remove hv_event_tasklet_disable/enable With the recent introduction of per-channel tasklet, we need to update the way we handle the 3 concurrency issues: 1. hv_process_channel_removal -> percpu_channel_deq vs. vmbus_chan_sched -> list_for_each_entry(..., percpu_list); 2. vmbus_process_offer -> percpu_channel_enq/deq vs. vmbus_chan_sched. 3. vmbus_close_internal vs. the per-channel tasklet vmbus_on_event; The first 2 issues can be handled by Stephen's recent patch "vmbus: use rcu for per-cpu channel list", and the third issue can be handled by calling tasklet_disable in vmbus_close_internal here. We don't need the original hv_event_tasklet_disable/enable since we now use per-channel tasklet instead of the previous per-CPU tasklet, and actually we must remove them due to the side effect now: vmbus_process_offer -> hv_event_tasklet_enable -> tasklet_schedule will start the per-channel callback prematurely, cauing NULL dereferencing (the channel may haven't been properly configured to run the callback yet). Fixes: 631e63a9f346 ("vmbus: change to per channel tasklet") Signed-off-by: Dexuan Cui Cc: "K. Y. Srinivasan" Cc: Haiyang Zhang Cc: Stephen Hemminger Tested-by: Vitaly Kuznetsov Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- drivers/hv/channel.c | 12 ++++-------- drivers/hv/channel_mgmt.c | 19 ------------------- include/linux/hyperv.h | 3 --- 3 files changed, 4 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index bd0d1988feb2..57b2958205c7 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -530,15 +530,13 @@ static int vmbus_close_internal(struct vmbus_channel *channel) int ret; /* - * vmbus_on_event(), running in the tasklet, can race + * vmbus_on_event(), running in the per-channel tasklet, can race * with vmbus_close_internal() in the case of SMP guest, e.g., when * the former is accessing channel->inbound.ring_buffer, the latter - * could be freeing the ring_buffer pages. - * - * To resolve the race, we can serialize them by disabling the - * tasklet when the latter is running here. + * could be freeing the ring_buffer pages, so here we must stop it + * first. */ - hv_event_tasklet_disable(channel); + tasklet_disable(&channel->callback_event); /* * In case a device driver's probe() fails (e.g., @@ -605,8 +603,6 @@ static int vmbus_close_internal(struct vmbus_channel *channel) get_order(channel->ringbuffer_pagecount * PAGE_SIZE)); out: - hv_event_tasklet_enable(channel); - return ret; } diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index d2cfa3eb71a2..bf846d078d85 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -382,19 +382,6 @@ static void vmbus_release_relid(u32 relid) true); } -void hv_event_tasklet_disable(struct vmbus_channel *channel) -{ - tasklet_disable(&channel->callback_event); -} - -void hv_event_tasklet_enable(struct vmbus_channel *channel) -{ - tasklet_enable(&channel->callback_event); - - /* In case there is any pending event */ - tasklet_schedule(&channel->callback_event); -} - void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid) { unsigned long flags; @@ -403,7 +390,6 @@ void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid) BUG_ON(!channel->rescind); BUG_ON(!mutex_is_locked(&vmbus_connection.channel_mutex)); - hv_event_tasklet_disable(channel); if (channel->target_cpu != get_cpu()) { put_cpu(); smp_call_function_single(channel->target_cpu, @@ -412,7 +398,6 @@ void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid) percpu_channel_deq(channel); put_cpu(); } - hv_event_tasklet_enable(channel); if (channel->primary_channel == NULL) { list_del(&channel->listentry); @@ -506,7 +491,6 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel) init_vp_index(newchannel, dev_type); - hv_event_tasklet_disable(newchannel); if (newchannel->target_cpu != get_cpu()) { put_cpu(); smp_call_function_single(newchannel->target_cpu, @@ -516,7 +500,6 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel) percpu_channel_enq(newchannel); put_cpu(); } - hv_event_tasklet_enable(newchannel); /* * This state is used to indicate a successful open @@ -566,7 +549,6 @@ err_deq_chan: list_del(&newchannel->listentry); mutex_unlock(&vmbus_connection.channel_mutex); - hv_event_tasklet_disable(newchannel); if (newchannel->target_cpu != get_cpu()) { put_cpu(); smp_call_function_single(newchannel->target_cpu, @@ -575,7 +557,6 @@ err_deq_chan: percpu_channel_deq(newchannel); put_cpu(); } - hv_event_tasklet_enable(newchannel); vmbus_release_relid(newchannel->offermsg.child_relid); diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index c4c7ae91f9d1..970771a5f739 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1437,9 +1437,6 @@ extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, u8 *buf, const int *srv_version, int srv_vercnt, int *nego_fw_version, int *nego_srv_version); -void hv_event_tasklet_disable(struct vmbus_channel *channel); -void hv_event_tasklet_enable(struct vmbus_channel *channel); - void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid); void vmbus_setevent(struct vmbus_channel *channel); -- cgit v1.2.3 From 7c468447f40645fbf2a033dfdaa92b1957130d50 Mon Sep 17 00:00:00 2001 From: Gary R Hook Date: Fri, 10 Mar 2017 12:28:18 -0600 Subject: crypto: ccp - Assign DMA commands to the channel's CCP The CCP driver generally uses a round-robin approach when assigning operations to available CCPs. For the DMA engine, however, the DMA mappings of the SGs are associated with a specific CCP. When an IOMMU is enabled, the IOMMU is programmed based on this specific device. If the DMA operations are not performed by that specific CCP then addressing errors and I/O page faults will occur. Update the CCP driver to allow a specific CCP device to be requested for an operation and use this in the DMA engine support. Cc: # 4.9.x- Signed-off-by: Gary R Hook Signed-off-by: Herbert Xu --- drivers/crypto/ccp/ccp-dev.c | 5 ++++- drivers/crypto/ccp/ccp-dmaengine.c | 1 + include/linux/ccp.h | 2 +- 3 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/crypto/ccp/ccp-dev.c b/drivers/crypto/ccp/ccp-dev.c index 511ab042b5e7..92d1c6959f08 100644 --- a/drivers/crypto/ccp/ccp-dev.c +++ b/drivers/crypto/ccp/ccp-dev.c @@ -283,11 +283,14 @@ EXPORT_SYMBOL_GPL(ccp_version); */ int ccp_enqueue_cmd(struct ccp_cmd *cmd) { - struct ccp_device *ccp = ccp_get_device(); + struct ccp_device *ccp; unsigned long flags; unsigned int i; int ret; + /* Some commands might need to be sent to a specific device */ + ccp = cmd->ccp ? cmd->ccp : ccp_get_device(); + if (!ccp) return -ENODEV; diff --git a/drivers/crypto/ccp/ccp-dmaengine.c b/drivers/crypto/ccp/ccp-dmaengine.c index e5d9278f4019..8d0eeb46d4a2 100644 --- a/drivers/crypto/ccp/ccp-dmaengine.c +++ b/drivers/crypto/ccp/ccp-dmaengine.c @@ -390,6 +390,7 @@ static struct ccp_dma_desc *ccp_create_desc(struct dma_chan *dma_chan, goto err; ccp_cmd = &cmd->ccp_cmd; + ccp_cmd->ccp = chan->ccp; ccp_pt = &ccp_cmd->u.passthru_nomap; ccp_cmd->flags = CCP_CMD_MAY_BACKLOG; ccp_cmd->flags |= CCP_CMD_PASSTHRU_NO_DMA_MAP; diff --git a/include/linux/ccp.h b/include/linux/ccp.h index c71dd8fa5764..c41b8d99dd0e 100644 --- a/include/linux/ccp.h +++ b/include/linux/ccp.h @@ -556,7 +556,7 @@ enum ccp_engine { * struct ccp_cmd - CCP operation request * @entry: list element (ccp driver use only) * @work: work element used for callbacks (ccp driver use only) - * @ccp: CCP device to be run on (ccp driver use only) + * @ccp: CCP device to be run on * @ret: operation return code (ccp driver use only) * @flags: cmd processing flags * @engine: CCP operation to perform -- cgit v1.2.3 From 5be9b730b09c45c358bbfe7f51d254e306cccc07 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 16 Mar 2017 16:40:21 -0700 Subject: kasan: add a prototype of task_struct to avoid warning Add a prototype of task_struct to fix below warning on arm64. In file included from arch/arm64/kernel/probes/kprobes.c:19:0: include/linux/kasan.h:81:132: error: 'struct task_struct' declared inside parameter list will not be visible outside of this definition or declaration [-Werror] static inline void kasan_unpoison_task_stack(struct task_struct *task) {} As same as other types (kmem_cache, page, and vm_struct) this adds a prototype of task_struct data structure on top of kasan.h. [arnd] A related warning was fixed before, but now appears in a different line in the same file in v4.11-rc2. The patch from Masami Hiramatsu still seems appropriate, so let's take his version. Fixes: 71af2ed5eeea ("kasan, sched/headers: Remove from ") Link: https://patchwork.kernel.org/patch/9569839/ Link: http://lkml.kernel.org/r/20170313141517.3397802-1-arnd@arndb.de Signed-off-by: Arnd Bergmann Signed-off-by: Masami Hiramatsu Acked-by: Alexander Potapenko Acked-by: Andrey Ryabinin Cc: Dmitry Vyukov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 1c823bef4c15..5734480c9590 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -6,6 +6,7 @@ struct kmem_cache; struct page; struct vm_struct; +struct task_struct; #ifdef CONFIG_KASAN -- cgit v1.2.3 From 15c9e10d9ad4d41d076148bbff1de7f659f68852 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Thu, 16 Mar 2017 16:40:33 -0700 Subject: drivers core: remove assert_held_device_hotplug() The last caller of assert_held_device_hotplug() is gone, so remove it again. Link: http://lkml.kernel.org/r/20170314125226.16779-3-heiko.carstens@de.ibm.com Signed-off-by: Heiko Carstens Acked-by: Dan Williams Cc: Michal Hocko Cc: "Rafael J. Wysocki" Cc: Vladimir Davydov Cc: Ben Hutchings Cc: Gerald Schaefer Cc: Martin Schwidefsky Cc: Sebastian Ott Cc: Greg Kroah-Hartman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/core.c | 5 ----- include/linux/device.h | 1 - 2 files changed, 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/core.c b/drivers/base/core.c index 684bda4d14a1..6bb60fb6a30b 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -639,11 +639,6 @@ int lock_device_hotplug_sysfs(void) return restart_syscall(); } -void assert_held_device_hotplug(void) -{ - lockdep_assert_held(&device_hotplug_lock); -} - #ifdef CONFIG_BLOCK static inline int device_is_not_partition(struct device *dev) { diff --git a/include/linux/device.h b/include/linux/device.h index 30c4570e928d..9ef518af5515 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1140,7 +1140,6 @@ static inline bool device_supports_offline(struct device *dev) extern void lock_device_hotplug(void); extern void unlock_device_hotplug(void); extern int lock_device_hotplug_sysfs(void); -void assert_held_device_hotplug(void); extern int device_offline(struct device *dev); extern int device_online(struct device *dev); extern void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode); -- cgit v1.2.3 From 4cbe4dac82e423ecc9a0ba46af24a860853259f4 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Mon, 13 Mar 2017 19:29:08 +0200 Subject: net/mlx4_core: Avoid delays during VF driver device shutdown Some Hypervisors detach VFs from VMs by instantly causing an FLR event to be generated for a VF. In the mlx4 case, this will cause that VF's comm channel to be disabled before the VM has an opportunity to invoke the VF device's "shutdown" method. For such Hypervisors, there is a race condition between the VF's shutdown method and its internal-error detection/reset thread. The internal-error detection/reset thread (which runs every 5 seconds) also detects a disabled comm channel. If the internal-error detection/reset flow wins the race, we still get delays (while that flow tries repeatedly to detect comm-channel recovery). The cited commit fixed the command timeout problem when the internal-error detection/reset flow loses the race. This commit avoids the unneeded delays when the internal-error detection/reset flow wins. Fixes: d585df1c5ccf ("net/mlx4_core: Avoid command timeouts during VF driver device shutdown") Signed-off-by: Jack Morgenstein Reported-by: Simon Xiao Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/cmd.c | 11 +++++++++++ drivers/net/ethernet/mellanox/mlx4/main.c | 11 +++++++++++ include/linux/mlx4/device.h | 1 + 3 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index e8c105164931..0e0fa7030565 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -2305,6 +2305,17 @@ static int sync_toggles(struct mlx4_dev *dev) rd_toggle = swab32(readl(&priv->mfunc.comm->slave_read)); if (wr_toggle == 0xffffffff || rd_toggle == 0xffffffff) { /* PCI might be offline */ + + /* If device removal has been requested, + * do not continue retrying. + */ + if (dev->persist->interface_state & + MLX4_INTERFACE_STATE_NOWAIT) { + mlx4_warn(dev, + "communication channel is offline\n"); + return -EIO; + } + msleep(100); wr_toggle = swab32(readl(&priv->mfunc.comm-> slave_write)); diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 21377c315083..703205475524 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -1940,6 +1940,14 @@ static int mlx4_comm_check_offline(struct mlx4_dev *dev) (u32)(1 << COMM_CHAN_OFFLINE_OFFSET)); if (!offline_bit) return 0; + + /* If device removal has been requested, + * do not continue retrying. + */ + if (dev->persist->interface_state & + MLX4_INTERFACE_STATE_NOWAIT) + break; + /* There are cases as part of AER/Reset flow that PF needs * around 100 msec to load. We therefore sleep for 100 msec * to allow other tasks to make use of that CPU during this @@ -3955,6 +3963,9 @@ static void mlx4_remove_one(struct pci_dev *pdev) struct devlink *devlink = priv_to_devlink(priv); int active_vfs = 0; + if (mlx4_is_slave(dev)) + persist->interface_state |= MLX4_INTERFACE_STATE_NOWAIT; + mutex_lock(&persist->interface_state_mutex); persist->interface_state |= MLX4_INTERFACE_STATE_DELETION; mutex_unlock(&persist->interface_state_mutex); diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 7e66e4f62858..1beb1ec2fbdf 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -476,6 +476,7 @@ enum { enum { MLX4_INTERFACE_STATE_UP = 1 << 0, MLX4_INTERFACE_STATE_DELETION = 1 << 1, + MLX4_INTERFACE_STATE_NOWAIT = 1 << 2, }; #define MSTR_SM_CHANGE_MASK (MLX4_EQ_PORT_INFO_MSTR_SM_SL_CHANGE_MASK | \ -- cgit v1.2.3 From 0ca10b60ceeb5372da01798ca68c116ae45a6eb6 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Mon, 20 Mar 2017 11:25:16 +0100 Subject: reset: fix optional reset_control_get stubs to return NULL When RESET_CONTROLLER is not enabled, the optional reset_control_get stubs should now also return NULL. Since it is now valid for reset_control_assert/deassert/reset/status/put to be called unconditionally, with NULL as an argument for optional resets, the stubs are not allowed to warn anymore. Fixes: bb475230b8e5 ("reset: make optional functions really optional") Reported-by: Andrzej Hajda Tested-by: Andrzej Hajda Reviewed-by: Andrzej Hajda Cc: Ramiro Oliveira Signed-off-by: Philipp Zabel --- include/linux/reset.h | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/reset.h b/include/linux/reset.h index 86b4ed75359e..96fb139bdd08 100644 --- a/include/linux/reset.h +++ b/include/linux/reset.h @@ -31,31 +31,26 @@ static inline int device_reset_optional(struct device *dev) static inline int reset_control_reset(struct reset_control *rstc) { - WARN_ON(1); return 0; } static inline int reset_control_assert(struct reset_control *rstc) { - WARN_ON(1); return 0; } static inline int reset_control_deassert(struct reset_control *rstc) { - WARN_ON(1); return 0; } static inline int reset_control_status(struct reset_control *rstc) { - WARN_ON(1); return 0; } static inline void reset_control_put(struct reset_control *rstc) { - WARN_ON(1); } static inline int __must_check device_reset(struct device *dev) @@ -74,14 +69,14 @@ static inline struct reset_control *__of_reset_control_get( const char *id, int index, bool shared, bool optional) { - return ERR_PTR(-ENOTSUPP); + return optional ? NULL : ERR_PTR(-ENOTSUPP); } static inline struct reset_control *__devm_reset_control_get( struct device *dev, const char *id, int index, bool shared, bool optional) { - return ERR_PTR(-ENOTSUPP); + return optional ? NULL : ERR_PTR(-ENOTSUPP); } #endif /* CONFIG_RESET_CONTROLLER */ -- cgit v1.2.3 From 36d277bac8080202684e67162ebb157f16631581 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Wed, 15 Mar 2017 09:32:14 +0800 Subject: vsock: track pkt owner vsock So that we can cancel a queued pkt later if necessary. Signed-off-by: Peng Tao Signed-off-by: David S. Miller --- include/linux/virtio_vsock.h | 3 +++ net/vmw_vsock/virtio_transport_common.c | 7 +++++++ 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 9638bfeb0d1f..584f9a647ad4 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -48,6 +48,8 @@ struct virtio_vsock_pkt { struct virtio_vsock_hdr hdr; struct work_struct work; struct list_head list; + /* socket refcnt not held, only use for cancellation */ + struct vsock_sock *vsk; void *buf; u32 len; u32 off; @@ -56,6 +58,7 @@ struct virtio_vsock_pkt { struct virtio_vsock_pkt_info { u32 remote_cid, remote_port; + struct vsock_sock *vsk; struct msghdr *msg; u32 pkt_len; u16 type; diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 8d592a45b597..af087b44ceea 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -58,6 +58,7 @@ virtio_transport_alloc_pkt(struct virtio_vsock_pkt_info *info, pkt->len = len; pkt->hdr.len = cpu_to_le32(len); pkt->reply = info->reply; + pkt->vsk = info->vsk; if (info->msg && len > 0) { pkt->buf = kmalloc(len, GFP_KERNEL); @@ -180,6 +181,7 @@ static int virtio_transport_send_credit_update(struct vsock_sock *vsk, struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_CREDIT_UPDATE, .type = type, + .vsk = vsk, }; return virtio_transport_send_pkt_info(vsk, &info); @@ -519,6 +521,7 @@ int virtio_transport_connect(struct vsock_sock *vsk) struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_REQUEST, .type = VIRTIO_VSOCK_TYPE_STREAM, + .vsk = vsk, }; return virtio_transport_send_pkt_info(vsk, &info); @@ -534,6 +537,7 @@ int virtio_transport_shutdown(struct vsock_sock *vsk, int mode) VIRTIO_VSOCK_SHUTDOWN_RCV : 0) | (mode & SEND_SHUTDOWN ? VIRTIO_VSOCK_SHUTDOWN_SEND : 0), + .vsk = vsk, }; return virtio_transport_send_pkt_info(vsk, &info); @@ -560,6 +564,7 @@ virtio_transport_stream_enqueue(struct vsock_sock *vsk, .type = VIRTIO_VSOCK_TYPE_STREAM, .msg = msg, .pkt_len = len, + .vsk = vsk, }; return virtio_transport_send_pkt_info(vsk, &info); @@ -581,6 +586,7 @@ static int virtio_transport_reset(struct vsock_sock *vsk, .op = VIRTIO_VSOCK_OP_RST, .type = VIRTIO_VSOCK_TYPE_STREAM, .reply = !!pkt, + .vsk = vsk, }; /* Send RST only if the original pkt is not a RST pkt */ @@ -826,6 +832,7 @@ virtio_transport_send_response(struct vsock_sock *vsk, .remote_cid = le64_to_cpu(pkt->hdr.src_cid), .remote_port = le32_to_cpu(pkt->hdr.src_port), .reply = true, + .vsk = vsk, }; return virtio_transport_send_pkt_info(vsk, &info); -- cgit v1.2.3 From 4ef1b2869447411ad3ef91ad7d4891a83c1a509a Mon Sep 17 00:00:00 2001 From: Soheil Hassas Yeganeh Date: Sat, 18 Mar 2017 17:03:00 -0400 Subject: tcp: mark skbs with SCM_TIMESTAMPING_OPT_STATS SOF_TIMESTAMPING_OPT_STATS can be enabled and disabled while packets are collected on the error queue. So, checking SOF_TIMESTAMPING_OPT_STATS in sk->sk_tsflags is not enough to safely assume that the skb contains OPT_STATS data. Add a bit in sock_exterr_skb to indicate whether the skb contains opt_stats data. Fixes: 1c885808e456 ("tcp: SOF_TIMESTAMPING_OPT_STATS option for SO_TIMESTAMPING") Reported-by: JongHwan Kim Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: Eric Dumazet Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/errqueue.h | 2 ++ net/core/skbuff.c | 17 +++++++++++------ net/socket.c | 2 +- 3 files changed, 14 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/errqueue.h b/include/linux/errqueue.h index 9ca23fcfb5d7..6fdfc884fdeb 100644 --- a/include/linux/errqueue.h +++ b/include/linux/errqueue.h @@ -20,6 +20,8 @@ struct sock_exterr_skb { struct sock_extended_err ee; u16 addr_offset; __be16 port; + u8 opt_stats:1, + unused:7; }; #endif diff --git a/net/core/skbuff.c b/net/core/skbuff.c index b1fbd1958eb6..9f781092fda9 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3793,16 +3793,20 @@ EXPORT_SYMBOL(skb_clone_sk); static void __skb_complete_tx_timestamp(struct sk_buff *skb, struct sock *sk, - int tstype) + int tstype, + bool opt_stats) { struct sock_exterr_skb *serr; int err; + BUILD_BUG_ON(sizeof(struct sock_exterr_skb) > sizeof(skb->cb)); + serr = SKB_EXT_ERR(skb); memset(serr, 0, sizeof(*serr)); serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING; serr->ee.ee_info = tstype; + serr->opt_stats = opt_stats; if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) { serr->ee.ee_data = skb_shinfo(skb)->tskey; if (sk->sk_protocol == IPPROTO_TCP && @@ -3843,7 +3847,7 @@ void skb_complete_tx_timestamp(struct sk_buff *skb, */ if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) { *skb_hwtstamps(skb) = *hwtstamps; - __skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND); + __skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND, false); sock_put(sk); } } @@ -3854,7 +3858,7 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb, struct sock *sk, int tstype) { struct sk_buff *skb; - bool tsonly; + bool tsonly, opt_stats = false; if (!sk) return; @@ -3867,9 +3871,10 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb, #ifdef CONFIG_INET if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS) && sk->sk_protocol == IPPROTO_TCP && - sk->sk_type == SOCK_STREAM) + sk->sk_type == SOCK_STREAM) { skb = tcp_get_timestamping_opt_stats(sk); - else + opt_stats = true; + } else #endif skb = alloc_skb(0, GFP_ATOMIC); } else { @@ -3888,7 +3893,7 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb, else skb->tstamp = ktime_get_real(); - __skb_complete_tx_timestamp(skb, sk, tstype); + __skb_complete_tx_timestamp(skb, sk, tstype, opt_stats); } EXPORT_SYMBOL_GPL(__skb_tstamp_tx); diff --git a/net/socket.c b/net/socket.c index 692d6989d2c2..985ef06792d6 100644 --- a/net/socket.c +++ b/net/socket.c @@ -706,7 +706,7 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, SCM_TIMESTAMPING, sizeof(tss), &tss); if (skb_is_err_queue(skb) && skb->len && - (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS)) + SKB_EXT_ERR(skb)->opt_stats) put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING_OPT_STATS, skb->len, skb->data); } -- cgit v1.2.3 From a5023a99393dab276069cd60dad3e61d57720fda Mon Sep 17 00:00:00 2001 From: Peter Huewe Date: Fri, 17 Mar 2017 00:28:56 +0100 Subject: hwmon: Add missing HWMON_T_ALARM Unfortunately the HWMON_T_ALARM define was missing, although the associated entry was present in hwmon_temp_attributes. This is needed to convert drivers to the new interface which use channel based alarms. Signed-off-by: Peter Huewe Signed-off-by: Guenter Roeck --- include/linux/hwmon.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index 78d59dba563e..88b673749121 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -88,6 +88,7 @@ enum hwmon_temp_attributes { #define HWMON_T_CRIT_HYST BIT(hwmon_temp_crit_hyst) #define HWMON_T_EMERGENCY BIT(hwmon_temp_emergency) #define HWMON_T_EMERGENCY_HYST BIT(hwmon_temp_emergency_hyst) +#define HWMON_T_ALARM BIT(hwmon_temp_alarm) #define HWMON_T_MIN_ALARM BIT(hwmon_temp_min_alarm) #define HWMON_T_MAX_ALARM BIT(hwmon_temp_max_alarm) #define HWMON_T_CRIT_ALARM BIT(hwmon_temp_crit_alarm) -- cgit v1.2.3 From 9d3a4de4cb8db8e71730e36736272ef041836f68 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Thu, 16 Mar 2017 17:00:16 +0000 Subject: iommu: Disambiguate MSI region types The introduction of reserved regions has left a couple of rough edges which we could do with sorting out sooner rather than later. Since we are not yet addressing the potential dynamic aspect of software-managed reservations and presenting them at arbitrary fixed addresses, it is incongruous that we end up displaying hardware vs. software-managed MSI regions to userspace differently, especially since ARM-based systems may actually require one or the other, or even potentially both at once, (which iommu-dma currently has no hope of dealing with at all). Let's resolve the former user-visible inconsistency ASAP before the ABI has been baked into a kernel release, in a way that also lays the groundwork for the latter shortcoming to be addressed by follow-up patches. For clarity, rename the software-managed type to IOMMU_RESV_SW_MSI, use IOMMU_RESV_MSI to describe the hardware type, and document everything a little bit. Since the x86 MSI remapping hardware falls squarely under this meaning of IOMMU_RESV_MSI, apply that type to their regions as well, so that we tell the same story to userspace across all platforms. Secondly, as the various region types require quite different handling, and it really makes little sense to ever try combining them, convert the bitfield-esque #defines to a plain enum in the process before anyone gets the wrong impression. Fixes: d30ddcaa7b02 ("iommu: Add a new type field in iommu_resv_region") Reviewed-by: Eric Auger CC: Alex Williamson CC: David Woodhouse CC: kvm@vger.kernel.org Signed-off-by: Robin Murphy Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu.c | 2 +- drivers/iommu/arm-smmu-v3.c | 2 +- drivers/iommu/arm-smmu.c | 2 +- drivers/iommu/intel-iommu.c | 2 +- drivers/iommu/iommu.c | 5 +++-- drivers/vfio/vfio_iommu_type1.c | 7 +++---- include/linux/iommu.h | 18 +++++++++++++----- 7 files changed, 23 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 98940d1392cb..b17536d6e69b 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -3202,7 +3202,7 @@ static void amd_iommu_get_resv_regions(struct device *dev, region = iommu_alloc_resv_region(MSI_RANGE_START, MSI_RANGE_END - MSI_RANGE_START + 1, - 0, IOMMU_RESV_RESERVED); + 0, IOMMU_RESV_MSI); if (!region) return; list_add_tail(®ion->list, head); diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 5806a6acc94e..591bb96047c9 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -1888,7 +1888,7 @@ static void arm_smmu_get_resv_regions(struct device *dev, int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO; region = iommu_alloc_resv_region(MSI_IOVA_BASE, MSI_IOVA_LENGTH, - prot, IOMMU_RESV_MSI); + prot, IOMMU_RESV_SW_MSI); if (!region) return; diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index abf6496843a6..b493c99e17f7 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -1608,7 +1608,7 @@ static void arm_smmu_get_resv_regions(struct device *dev, int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO; region = iommu_alloc_resv_region(MSI_IOVA_BASE, MSI_IOVA_LENGTH, - prot, IOMMU_RESV_MSI); + prot, IOMMU_RESV_SW_MSI); if (!region) return; diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 91d60493b57c..d412a313a372 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -5249,7 +5249,7 @@ static void intel_iommu_get_resv_regions(struct device *device, reg = iommu_alloc_resv_region(IOAPIC_RANGE_START, IOAPIC_RANGE_END - IOAPIC_RANGE_START + 1, - 0, IOMMU_RESV_RESERVED); + 0, IOMMU_RESV_MSI); if (!reg) return; list_add_tail(®->list, head); diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 8ea14f41a979..3b67144dead2 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -72,6 +72,7 @@ static const char * const iommu_group_resv_type_string[] = { [IOMMU_RESV_DIRECT] = "direct", [IOMMU_RESV_RESERVED] = "reserved", [IOMMU_RESV_MSI] = "msi", + [IOMMU_RESV_SW_MSI] = "msi", }; #define IOMMU_GROUP_ATTR(_name, _mode, _show, _store) \ @@ -1743,8 +1744,8 @@ void iommu_put_resv_regions(struct device *dev, struct list_head *list) } struct iommu_resv_region *iommu_alloc_resv_region(phys_addr_t start, - size_t length, - int prot, int type) + size_t length, int prot, + enum iommu_resv_type type) { struct iommu_resv_region *region; diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index c26fa1f3ed86..32d2633092a3 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -1182,8 +1182,7 @@ static struct vfio_group *find_iommu_group(struct vfio_domain *domain, return NULL; } -static bool vfio_iommu_has_resv_msi(struct iommu_group *group, - phys_addr_t *base) +static bool vfio_iommu_has_sw_msi(struct iommu_group *group, phys_addr_t *base) { struct list_head group_resv_regions; struct iommu_resv_region *region, *next; @@ -1192,7 +1191,7 @@ static bool vfio_iommu_has_resv_msi(struct iommu_group *group, INIT_LIST_HEAD(&group_resv_regions); iommu_get_group_resv_regions(group, &group_resv_regions); list_for_each_entry(region, &group_resv_regions, list) { - if (region->type & IOMMU_RESV_MSI) { + if (region->type == IOMMU_RESV_SW_MSI) { *base = region->start; ret = true; goto out; @@ -1283,7 +1282,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data, if (ret) goto out_domain; - resv_msi = vfio_iommu_has_resv_msi(iommu_group, &resv_msi_base); + resv_msi = vfio_iommu_has_sw_msi(iommu_group, &resv_msi_base); INIT_LIST_HEAD(&domain->group_list); list_add(&group->next, &domain->group_list); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 6a6de187ddc0..2e4de0deee53 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -125,9 +125,16 @@ enum iommu_attr { }; /* These are the possible reserved region types */ -#define IOMMU_RESV_DIRECT (1 << 0) -#define IOMMU_RESV_RESERVED (1 << 1) -#define IOMMU_RESV_MSI (1 << 2) +enum iommu_resv_type { + /* Memory regions which must be mapped 1:1 at all times */ + IOMMU_RESV_DIRECT, + /* Arbitrary "never map this or give it to a device" address ranges */ + IOMMU_RESV_RESERVED, + /* Hardware MSI region (untranslated) */ + IOMMU_RESV_MSI, + /* Software-managed MSI translation window */ + IOMMU_RESV_SW_MSI, +}; /** * struct iommu_resv_region - descriptor for a reserved memory region @@ -142,7 +149,7 @@ struct iommu_resv_region { phys_addr_t start; size_t length; int prot; - int type; + enum iommu_resv_type type; }; #ifdef CONFIG_IOMMU_API @@ -288,7 +295,8 @@ extern void iommu_get_resv_regions(struct device *dev, struct list_head *list); extern void iommu_put_resv_regions(struct device *dev, struct list_head *list); extern int iommu_request_dm_for_dev(struct device *dev); extern struct iommu_resv_region * -iommu_alloc_resv_region(phys_addr_t start, size_t length, int prot, int type); +iommu_alloc_resv_region(phys_addr_t start, size_t length, int prot, + enum iommu_resv_type type); extern int iommu_get_group_resv_regions(struct iommu_group *group, struct list_head *head); -- cgit v1.2.3 From 698eff6355f735d46d1b7113df8b422874cd7988 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 17 Mar 2017 12:48:18 +0100 Subject: sched/clock, x86/perf: Fix "perf test tsc" People reported that commit: 5680d8094ffa ("sched/clock: Provide better clock continuity") broke "perf test tsc". That commit added another offset to the reported clock value; so take that into account when computing the provided offset values. Reported-by: Adrian Hunter Reported-by: Arnaldo Carvalho de Melo Tested-by: Alexander Shishkin Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: 5680d8094ffa ("sched/clock: Provide better clock continuity") Signed-off-by: Ingo Molnar --- arch/x86/events/core.c | 9 ++++++--- arch/x86/include/asm/timer.h | 2 ++ arch/x86/kernel/tsc.c | 4 ++-- include/linux/sched/clock.h | 13 +++++++------ kernel/sched/clock.c | 22 +++++++++++----------- 5 files changed, 28 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 2aa1ad194db2..580b60f5ac83 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2256,6 +2256,7 @@ void arch_perf_update_userpage(struct perf_event *event, struct perf_event_mmap_page *userpg, u64 now) { struct cyc2ns_data *data; + u64 offset; userpg->cap_user_time = 0; userpg->cap_user_time_zero = 0; @@ -2263,11 +2264,13 @@ void arch_perf_update_userpage(struct perf_event *event, !!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED); userpg->pmc_width = x86_pmu.cntval_bits; - if (!sched_clock_stable()) + if (!using_native_sched_clock() || !sched_clock_stable()) return; data = cyc2ns_read_begin(); + offset = data->cyc2ns_offset + __sched_clock_offset; + /* * Internal timekeeping for enabled/running/stopped times * is always in the local_clock domain. @@ -2275,7 +2278,7 @@ void arch_perf_update_userpage(struct perf_event *event, userpg->cap_user_time = 1; userpg->time_mult = data->cyc2ns_mul; userpg->time_shift = data->cyc2ns_shift; - userpg->time_offset = data->cyc2ns_offset - now; + userpg->time_offset = offset - now; /* * cap_user_time_zero doesn't make sense when we're using a different @@ -2283,7 +2286,7 @@ void arch_perf_update_userpage(struct perf_event *event, */ if (!event->attr.use_clockid) { userpg->cap_user_time_zero = 1; - userpg->time_zero = data->cyc2ns_offset; + userpg->time_zero = offset; } cyc2ns_read_end(data); diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h index a04eabd43d06..27e9f9d769b8 100644 --- a/arch/x86/include/asm/timer.h +++ b/arch/x86/include/asm/timer.h @@ -12,6 +12,8 @@ extern int recalibrate_cpu_khz(void); extern int no_timer_check; +extern bool using_native_sched_clock(void); + /* * We use the full linear equation: f(x) = a + b*x, in order to allow * a continuous function in the face of dynamic freq changes. diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index c73a7f9e881a..714dfba6a1e7 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -328,7 +328,7 @@ unsigned long long sched_clock(void) return paravirt_sched_clock(); } -static inline bool using_native_sched_clock(void) +bool using_native_sched_clock(void) { return pv_time_ops.sched_clock == native_sched_clock; } @@ -336,7 +336,7 @@ static inline bool using_native_sched_clock(void) unsigned long long sched_clock(void) __attribute__((alias("native_sched_clock"))); -static inline bool using_native_sched_clock(void) { return true; } +bool using_native_sched_clock(void) { return true; } #endif int check_tsc_unstable(void) diff --git a/include/linux/sched/clock.h b/include/linux/sched/clock.h index 4a68c6791207..34fe92ce1ebd 100644 --- a/include/linux/sched/clock.h +++ b/include/linux/sched/clock.h @@ -54,15 +54,16 @@ static inline u64 local_clock(void) } #else extern void sched_clock_init_late(void); -/* - * Architectures can set this to 1 if they have specified - * CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig, - * but then during bootup it turns out that sched_clock() - * is reliable after all: - */ extern int sched_clock_stable(void); extern void clear_sched_clock_stable(void); +/* + * When sched_clock_stable(), __sched_clock_offset provides the offset + * between local_clock() and sched_clock(). + */ +extern u64 __sched_clock_offset; + + extern void sched_clock_tick(void); extern void sched_clock_idle_sleep_event(void); extern void sched_clock_idle_wakeup_event(u64 delta_ns); diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index fec0f58c8dee..24a3e01bf8cb 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -96,10 +96,10 @@ static DEFINE_STATIC_KEY_FALSE(__sched_clock_stable); static int __sched_clock_stable_early = 1; /* - * We want: ktime_get_ns() + gtod_offset == sched_clock() + raw_offset + * We want: ktime_get_ns() + __gtod_offset == sched_clock() + __sched_clock_offset */ -static __read_mostly u64 raw_offset; -static __read_mostly u64 gtod_offset; +__read_mostly u64 __sched_clock_offset; +static __read_mostly u64 __gtod_offset; struct sched_clock_data { u64 tick_raw; @@ -131,11 +131,11 @@ static void __set_sched_clock_stable(void) /* * Attempt to make the (initial) unstable->stable transition continuous. */ - raw_offset = (scd->tick_gtod + gtod_offset) - (scd->tick_raw); + __sched_clock_offset = (scd->tick_gtod + __gtod_offset) - (scd->tick_raw); printk(KERN_INFO "sched_clock: Marking stable (%lld, %lld)->(%lld, %lld)\n", - scd->tick_gtod, gtod_offset, - scd->tick_raw, raw_offset); + scd->tick_gtod, __gtod_offset, + scd->tick_raw, __sched_clock_offset); static_branch_enable(&__sched_clock_stable); tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE); @@ -161,11 +161,11 @@ static void __clear_sched_clock_stable(void) * * Still do what we can. */ - gtod_offset = (scd->tick_raw + raw_offset) - (scd->tick_gtod); + __gtod_offset = (scd->tick_raw + __sched_clock_offset) - (scd->tick_gtod); printk(KERN_INFO "sched_clock: Marking unstable (%lld, %lld)<-(%lld, %lld)\n", - scd->tick_gtod, gtod_offset, - scd->tick_raw, raw_offset); + scd->tick_gtod, __gtod_offset, + scd->tick_raw, __sched_clock_offset); tick_dep_set(TICK_DEP_BIT_CLOCK_UNSTABLE); @@ -238,7 +238,7 @@ again: * scd->tick_gtod + TICK_NSEC); */ - clock = scd->tick_gtod + gtod_offset + delta; + clock = scd->tick_gtod + __gtod_offset + delta; min_clock = wrap_max(scd->tick_gtod, old_clock); max_clock = wrap_max(old_clock, scd->tick_gtod + TICK_NSEC); @@ -324,7 +324,7 @@ u64 sched_clock_cpu(int cpu) u64 clock; if (sched_clock_stable()) - return sched_clock() + raw_offset; + return sched_clock() + __sched_clock_offset; if (unlikely(!sched_clock_running)) return 0ull; -- cgit v1.2.3 From 90db10434b163e46da413d34db8d0e77404cc645 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 23 Mar 2017 18:24:19 +0100 Subject: KVM: kvm_io_bus_unregister_dev() should never fail No caller currently checks the return value of kvm_io_bus_unregister_dev(). This is evil, as all callers silently go on freeing their device. A stale reference will remain in the io_bus, getting at least used again, when the iobus gets teared down on kvm_destroy_vm() - leading to use after free errors. There is nothing the callers could do, except retrying over and over again. So let's simply remove the bus altogether, print an error and make sure no one can access this broken bus again (returning -ENOMEM on any attempt to access it). Fixes: e93f8a0f821e ("KVM: convert io_bus to SRCU") Cc: stable@vger.kernel.org # 3.4+ Reported-by: Dmitry Vyukov Reviewed-by: Cornelia Huck Signed-off-by: David Hildenbrand Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 4 ++-- virt/kvm/eventfd.c | 3 ++- virt/kvm/kvm_main.c | 42 +++++++++++++++++++++++++----------------- 3 files changed, 29 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 2c14ad9809da..d0250744507a 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -162,8 +162,8 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, void *val); int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, struct kvm_io_device *dev); -int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, - struct kvm_io_device *dev); +void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, + struct kvm_io_device *dev); struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr); diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index a29786dd9522..4d28a9ddbee0 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -870,7 +870,8 @@ kvm_deassign_ioeventfd_idx(struct kvm *kvm, enum kvm_bus bus_idx, continue; kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev); - kvm->buses[bus_idx]->ioeventfd_count--; + if (kvm->buses[bus_idx]) + kvm->buses[bus_idx]->ioeventfd_count--; ioeventfd_release(p); ret = 0; break; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 7445566fadc1..ef1aa7f1ed7a 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -728,7 +728,8 @@ static void kvm_destroy_vm(struct kvm *kvm) spin_unlock(&kvm_lock); kvm_free_irq_routing(kvm); for (i = 0; i < KVM_NR_BUSES; i++) { - kvm_io_bus_destroy(kvm->buses[i]); + if (kvm->buses[i]) + kvm_io_bus_destroy(kvm->buses[i]); kvm->buses[i] = NULL; } kvm_coalesced_mmio_free(kvm); @@ -3476,6 +3477,8 @@ int kvm_io_bus_write(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, }; bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu); + if (!bus) + return -ENOMEM; r = __kvm_io_bus_write(vcpu, bus, &range, val); return r < 0 ? r : 0; } @@ -3493,6 +3496,8 @@ int kvm_io_bus_write_cookie(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, }; bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu); + if (!bus) + return -ENOMEM; /* First try the device referenced by cookie. */ if ((cookie >= 0) && (cookie < bus->dev_count) && @@ -3543,6 +3548,8 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, }; bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu); + if (!bus) + return -ENOMEM; r = __kvm_io_bus_read(vcpu, bus, &range, val); return r < 0 ? r : 0; } @@ -3555,6 +3562,9 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, struct kvm_io_bus *new_bus, *bus; bus = kvm->buses[bus_idx]; + if (!bus) + return -ENOMEM; + /* exclude ioeventfd which is limited by maximum fd */ if (bus->dev_count - bus->ioeventfd_count > NR_IOBUS_DEVS - 1) return -ENOSPC; @@ -3574,45 +3584,41 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, } /* Caller must hold slots_lock. */ -int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, - struct kvm_io_device *dev) +void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, + struct kvm_io_device *dev) { - int i, r; + int i; struct kvm_io_bus *new_bus, *bus; bus = kvm->buses[bus_idx]; - - /* - * It's possible the bus being released before hand. If so, - * we're done here. - */ if (!bus) - return 0; + return; - r = -ENOENT; for (i = 0; i < bus->dev_count; i++) if (bus->range[i].dev == dev) { - r = 0; break; } - if (r) - return r; + if (i == bus->dev_count) + return; new_bus = kmalloc(sizeof(*bus) + ((bus->dev_count - 1) * sizeof(struct kvm_io_range)), GFP_KERNEL); - if (!new_bus) - return -ENOMEM; + if (!new_bus) { + pr_err("kvm: failed to shrink bus, removing it completely\n"); + goto broken; + } memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range)); new_bus->dev_count--; memcpy(new_bus->range + i, bus->range + i + 1, (new_bus->dev_count - i) * sizeof(struct kvm_io_range)); +broken: rcu_assign_pointer(kvm->buses[bus_idx], new_bus); synchronize_srcu_expedited(&kvm->srcu); kfree(bus); - return r; + return; } struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx, @@ -3625,6 +3631,8 @@ struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx, srcu_idx = srcu_read_lock(&kvm->srcu); bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu); + if (!bus) + goto out_unlock; dev_idx = kvm_io_bus_get_first_dev(bus, addr, 1); if (dev_idx < 0) -- cgit v1.2.3 From 07de36b378a58f1d1426829acf0ab7cf86f651f3 Mon Sep 17 00:00:00 2001 From: Alexander Kochetkov Date: Wed, 22 Mar 2017 17:32:49 +0300 Subject: clockevents: Fix syntax error in clkevt-of macro The patch fix syntax errors introduced by commit 0c8893c9095d ("clockevents: Add a clkevt-of mechanism like clksrc-of"). Fixes: 0c8893c9095d ("clockevents: Add a clkevt-of mechanism like clksrc-of") Signed-off-by: Alexander Kochetkov Signed-off-by: Daniel Lezcano --- drivers/clocksource/clkevt-probe.c | 2 +- include/linux/clockchips.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/clocksource/clkevt-probe.c b/drivers/clocksource/clkevt-probe.c index 8c30fec86094..eb89b502acbd 100644 --- a/drivers/clocksource/clkevt-probe.c +++ b/drivers/clocksource/clkevt-probe.c @@ -17,7 +17,7 @@ #include #include -#include +#include extern struct of_device_id __clkevt_of_table[]; diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 5d3053c34fb3..6d7edc3082f9 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -229,7 +229,7 @@ static inline void tick_setup_hrtimer_broadcast(void) { } #ifdef CONFIG_CLKEVT_PROBE extern int clockevent_probe(void); -#els +#else static inline int clockevent_probe(void) { return 0; } #endif -- cgit v1.2.3 From 597b7305dd8bafdb3aef4957d97128bc90af8e9f Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 31 Mar 2017 15:11:47 -0700 Subject: mm: move mm_percpu_wq initialization earlier Yang Li has reported that drain_all_pages triggers a WARN_ON which means that this function is called earlier than the mm_percpu_wq is initialized on arm64 with CMA configured: WARNING: CPU: 2 PID: 1 at mm/page_alloc.c:2423 drain_all_pages+0x244/0x25c Modules linked in: CPU: 2 PID: 1 Comm: swapper/0 Not tainted 4.11.0-rc1-next-20170310-00027-g64dfbc5 #127 Hardware name: Freescale Layerscape 2088A RDB Board (DT) task: ffffffc07c4a6d00 task.stack: ffffffc07c4a8000 PC is at drain_all_pages+0x244/0x25c LR is at start_isolate_page_range+0x14c/0x1f0 [...] drain_all_pages+0x244/0x25c start_isolate_page_range+0x14c/0x1f0 alloc_contig_range+0xec/0x354 cma_alloc+0x100/0x1fc dma_alloc_from_contiguous+0x3c/0x44 atomic_pool_init+0x7c/0x208 arm64_dma_init+0x44/0x4c do_one_initcall+0x38/0x128 kernel_init_freeable+0x1a0/0x240 kernel_init+0x10/0xfc ret_from_fork+0x10/0x20 Fix this by moving the whole setup_vmstat which is an initcall right now to init_mm_internals which will be called right after the WQ subsystem is initialized. Link: http://lkml.kernel.org/r/20170315164021.28532-1-mhocko@kernel.org Signed-off-by: Michal Hocko Reported-by: Yang Li Tested-by: Yang Li Tested-by: Xiaolong Ye Cc: Mel Gorman Cc: Vlastimil Babka Cc: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ init/main.c | 2 ++ mm/vmstat.c | 4 +--- 3 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 5f01c88f0800..00a8fa7e366a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -32,6 +32,8 @@ struct user_struct; struct writeback_control; struct bdi_writeback; +void init_mm_internals(void); + #ifndef CONFIG_NEED_MULTIPLE_NODES /* Don't use mapnrs, do it properly */ extern unsigned long max_mapnr; diff --git a/init/main.c b/init/main.c index f9c9d9948203..b0c11cbf5ddf 100644 --- a/init/main.c +++ b/init/main.c @@ -1022,6 +1022,8 @@ static noinline void __init kernel_init_freeable(void) workqueue_init(); + init_mm_internals(); + do_pre_smp_initcalls(); lockup_detector_init(); diff --git a/mm/vmstat.c b/mm/vmstat.c index b1947f0cbee2..89f95396ec46 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1764,7 +1764,7 @@ static int vmstat_cpu_dead(unsigned int cpu) #endif -static int __init setup_vmstat(void) +void __init init_mm_internals(void) { #ifdef CONFIG_SMP int ret; @@ -1792,9 +1792,7 @@ static int __init setup_vmstat(void) proc_create("vmstat", S_IRUGO, NULL, &proc_vmstat_file_operations); proc_create("zoneinfo", S_IRUGO, NULL, &proc_zoneinfo_file_operations); #endif - return 0; } -module_init(setup_vmstat) #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_COMPACTION) -- cgit v1.2.3 From 553af430e7c981e6e8fa5007c5b7b5773acc63dd Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 31 Mar 2017 15:11:50 -0700 Subject: mm: rmap: fix huge file mmap accounting in the memcg stats Huge pages are accounted as single units in the memcg's "file_mapped" counter. Account the correct number of base pages, like we do in the corresponding node counter. Link: http://lkml.kernel.org/r/20170322005111.3156-1-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Reviewed-by: Kirill A. Shutemov Acked-by: Michal Hocko Cc: Vladimir Davydov Cc: [4.8+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 6 ++++++ mm/rmap.c | 4 ++-- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 5af377303880..bb7250c45cb8 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -740,6 +740,12 @@ static inline bool mem_cgroup_oom_synchronize(bool wait) return false; } +static inline void mem_cgroup_update_page_stat(struct page *page, + enum mem_cgroup_stat_index idx, + int nr) +{ +} + static inline void mem_cgroup_inc_page_stat(struct page *page, enum mem_cgroup_stat_index idx) { diff --git a/mm/rmap.c b/mm/rmap.c index 49ed681ccc7b..f6838015810f 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1159,7 +1159,7 @@ void page_add_file_rmap(struct page *page, bool compound) goto out; } __mod_node_page_state(page_pgdat(page), NR_FILE_MAPPED, nr); - mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED); + mem_cgroup_update_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED, nr); out: unlock_page_memcg(page); } @@ -1199,7 +1199,7 @@ static void page_remove_file_rmap(struct page *page, bool compound) * pte lock(a spinlock) is held, which implies preemption disabled. */ __mod_node_page_state(page_pgdat(page), NR_FILE_MAPPED, -nr); - mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED); + mem_cgroup_update_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED, -nr); if (unlikely(PageMlocked(page))) clear_page_mlock(page); -- cgit v1.2.3 From b0845ce58379d11dcad4cdb6824a6410de260216 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 31 Mar 2017 15:12:04 -0700 Subject: kasan: report only the first error by default Disable kasan after the first report. There are several reasons for this: - Single bug quite often has multiple invalid memory accesses causing storm in the dmesg. - Write OOB access might corrupt metadata so the next report will print bogus alloc/free stacktraces. - Reports after the first easily could be not bugs by itself but just side effects of the first one. Given that multiple reports usually only do harm, it makes sense to disable kasan after the first one. If user wants to see all the reports, the boot-time parameter kasan_multi_shot must be used. [aryabinin@virtuozzo.com: wrote changelog and doc, added missing include] Link: http://lkml.kernel.org/r/20170323154416.30257-1-aryabinin@virtuozzo.com Signed-off-by: Mark Rutland Signed-off-by: Andrey Ryabinin Cc: Andrey Konovalov Cc: Alexander Potapenko Cc: Dmitry Vyukov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/kernel-parameters.txt | 6 +++++ include/linux/kasan.h | 3 +++ lib/test_kasan.c | 10 +++++++ mm/kasan/kasan.h | 5 ---- mm/kasan/report.c | 36 +++++++++++++++++++++++++ 5 files changed, 55 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 2ba45caabada..facc20a3f962 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1725,6 +1725,12 @@ kernel and module base offset ASLR (Address Space Layout Randomization). + kasan_multi_shot + [KNL] Enforce KASAN (Kernel Address Sanitizer) to print + report on every invalid memory access. Without this + parameter KASAN will print report only for the first + invalid access. + keepinitrd [HW,ARM] kernelcore= [KNL,X86,IA-64,PPC] diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 5734480c9590..a5c7046f26b4 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -76,6 +76,9 @@ size_t ksize(const void *); static inline void kasan_unpoison_slab(const void *ptr) { ksize(ptr); } size_t kasan_metadata_size(struct kmem_cache *cache); +bool kasan_save_enable_multi_shot(void); +void kasan_restore_multi_shot(bool enabled); + #else /* CONFIG_KASAN */ static inline void kasan_unpoison_shadow(const void *address, size_t size) {} diff --git a/lib/test_kasan.c b/lib/test_kasan.c index 0b1d3140fbb8..a25c9763fce1 100644 --- a/lib/test_kasan.c +++ b/lib/test_kasan.c @@ -20,6 +20,7 @@ #include #include #include +#include /* * Note: test functions are marked noinline so that their names appear in @@ -474,6 +475,12 @@ static noinline void __init use_after_scope_test(void) static int __init kmalloc_tests_init(void) { + /* + * Temporarily enable multi-shot mode. Otherwise, we'd only get a + * report for the first case. + */ + bool multishot = kasan_save_enable_multi_shot(); + kmalloc_oob_right(); kmalloc_oob_left(); kmalloc_node_oob_right(); @@ -499,6 +506,9 @@ static int __init kmalloc_tests_init(void) ksize_unpoisons_memory(); copy_user_test(); use_after_scope_test(); + + kasan_restore_multi_shot(multishot); + return -EAGAIN; } diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index 1c260e6b3b3c..dd2dea8eb077 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -96,11 +96,6 @@ static inline const void *kasan_shadow_to_mem(const void *shadow_addr) << KASAN_SHADOW_SCALE_SHIFT); } -static inline bool kasan_report_enabled(void) -{ - return !current->kasan_depth; -} - void kasan_report(unsigned long addr, size_t size, bool is_write, unsigned long ip); void kasan_report_double_free(struct kmem_cache *cache, void *object, diff --git a/mm/kasan/report.c b/mm/kasan/report.c index f479365530b6..ab42a0803f16 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -13,7 +13,9 @@ * */ +#include #include +#include #include #include #include @@ -293,6 +295,40 @@ static void kasan_report_error(struct kasan_access_info *info) kasan_end_report(&flags); } +static unsigned long kasan_flags; + +#define KASAN_BIT_REPORTED 0 +#define KASAN_BIT_MULTI_SHOT 1 + +bool kasan_save_enable_multi_shot(void) +{ + return test_and_set_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags); +} +EXPORT_SYMBOL_GPL(kasan_save_enable_multi_shot); + +void kasan_restore_multi_shot(bool enabled) +{ + if (!enabled) + clear_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags); +} +EXPORT_SYMBOL_GPL(kasan_restore_multi_shot); + +static int __init kasan_set_multi_shot(char *str) +{ + set_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags); + return 1; +} +__setup("kasan_multi_shot", kasan_set_multi_shot); + +static inline bool kasan_report_enabled(void) +{ + if (current->kasan_depth) + return false; + if (test_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags)) + return true; + return !test_and_set_bit(KASAN_BIT_REPORTED, &kasan_flags); +} + void kasan_report(unsigned long addr, size_t size, bool is_write, unsigned long ip) { -- cgit v1.2.3