November 2017 - Linux-stable-mirror

[Linux-stable-mirror] FAILED: patch "[PATCH] ACPI / APEI: Replace ioremap_page_range() with fixmap" failed to apply to 3.18-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 3.18-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 4f89fa286f6729312e227e7c2d764e8e7b9d340e Mon Sep 17 00:00:00 2001 From: James Morse <james.morse(a)arm.com> Date: Mon, 6 Nov 2017 18:44:24 +0000 Subject: [PATCH] ACPI / APEI: Replace ioremap_page_range() with fixmap Replace ghes_io{re,un}map_pfn_{nmi,irq}()s use of ioremap_page_range() with __set_fixmap() as ioremap_page_range() may sleep to allocate a new level of page-table, even if its passed an existing final-address to use in the mapping. The GHES driver can only be enabled for architectures that select HAVE_ACPI_APEI: Add fixmap entries to both x86 and arm64. clear_fixmap() does the TLB invalidation in __set_fixmap() for arm64 and __set_pte_vaddr() for x86. In each case its the same as the respective arch_apei_flush_tlb_one(). Reported-by: Fengguang Wu <fengguang.wu(a)intel.com> Suggested-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: James Morse <james.morse(a)arm.com> Reviewed-by: Borislav Petkov <bp(a)suse.de> Tested-by: Tyler Baicar <tbaicar(a)codeaurora.org> Tested-by: Toshi Kani <toshi.kani(a)hpe.com> [ For the arm64 bits: ] Acked-by: Will Deacon <will.deacon(a)arm.com> [ For the x86 bits: ] Acked-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com> Cc: All applicable <stable(a)vger.kernel.org> diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h index caf86be815ba..4052ec39e8db 100644 --- a/arch/arm64/include/asm/fixmap.h +++ b/arch/arm64/include/asm/fixmap.h @@ -51,6 +51,13 @@ enum fixed_addresses { FIX_EARLYCON_MEM_BASE, FIX_TEXT_POKE0, + +#ifdef CONFIG_ACPI_APEI_GHES + /* Used for GHES mapping from assorted contexts */ + FIX_APEI_GHES_IRQ, + FIX_APEI_GHES_NMI, +#endif /* CONFIG_ACPI_APEI_GHES */ + __end_of_permanent_fixed_addresses, /* diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index dcd9fb55e679..b0c505fe9a95 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -104,6 +104,12 @@ enum fixed_addresses { FIX_GDT_REMAP_BEGIN, FIX_GDT_REMAP_END = FIX_GDT_REMAP_BEGIN + NR_CPUS - 1, +#ifdef CONFIG_ACPI_APEI_GHES + /* Used for GHES mapping from assorted contexts */ + FIX_APEI_GHES_IRQ, + FIX_APEI_GHES_NMI, +#endif + __end_of_permanent_fixed_addresses, /* diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index cb7aceae3553..572b6c7303ed 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -51,6 +51,7 @@ #include <acpi/actbl1.h> #include <acpi/ghes.h> #include <acpi/apei.h> +#include <asm/fixmap.h> #include <asm/tlbflush.h> #include <ras/ras_event.h> @@ -112,7 +113,7 @@ static DEFINE_MUTEX(ghes_list_mutex); * Because the memory area used to transfer hardware error information * from BIOS to Linux can be determined only in NMI, IRQ or timer * handler, but general ioremap can not be used in atomic context, so - * a special version of atomic ioremap is implemented for that. + * the fixmap is used instead. */ /* @@ -126,8 +127,8 @@ static DEFINE_MUTEX(ghes_list_mutex); /* virtual memory area for atomic ioremap */ static struct vm_struct *ghes_ioremap_area; /* - * These 2 spinlock is used to prevent atomic ioremap virtual memory - * area from being mapped simultaneously. + * These 2 spinlocks are used to prevent the fixmap entries from being used + * simultaneously. */ static DEFINE_RAW_SPINLOCK(ghes_ioremap_lock_nmi); static DEFINE_SPINLOCK(ghes_ioremap_lock_irq); @@ -159,53 +160,36 @@ static void ghes_ioremap_exit(void) static void __iomem *ghes_ioremap_pfn_nmi(u64 pfn) { - unsigned long vaddr; phys_addr_t paddr; pgprot_t prot; - vaddr = (unsigned long)GHES_IOREMAP_NMI_PAGE(ghes_ioremap_area->addr); - paddr = pfn << PAGE_SHIFT; prot = arch_apei_get_mem_attribute(paddr); - ioremap_page_range(vaddr, vaddr + PAGE_SIZE, paddr, prot); + __set_fixmap(FIX_APEI_GHES_NMI, paddr, prot); - return (void __iomem *)vaddr; + return (void __iomem *) fix_to_virt(FIX_APEI_GHES_NMI); } static void __iomem *ghes_ioremap_pfn_irq(u64 pfn) { - unsigned long vaddr; phys_addr_t paddr; pgprot_t prot; - vaddr = (unsigned long)GHES_IOREMAP_IRQ_PAGE(ghes_ioremap_area->addr); - paddr = pfn << PAGE_SHIFT; prot = arch_apei_get_mem_attribute(paddr); + __set_fixmap(FIX_APEI_GHES_IRQ, paddr, prot); - ioremap_page_range(vaddr, vaddr + PAGE_SIZE, paddr, prot); - - return (void __iomem *)vaddr; + return (void __iomem *) fix_to_virt(FIX_APEI_GHES_IRQ); } -static void ghes_iounmap_nmi(void __iomem *vaddr_ptr) +static void ghes_iounmap_nmi(void) { - unsigned long vaddr = (unsigned long __force)vaddr_ptr; - void *base = ghes_ioremap_area->addr; - - BUG_ON(vaddr != (unsigned long)GHES_IOREMAP_NMI_PAGE(base)); - unmap_kernel_range_noflush(vaddr, PAGE_SIZE); - arch_apei_flush_tlb_one(vaddr); + clear_fixmap(FIX_APEI_GHES_NMI); } -static void ghes_iounmap_irq(void __iomem *vaddr_ptr) +static void ghes_iounmap_irq(void) { - unsigned long vaddr = (unsigned long __force)vaddr_ptr; - void *base = ghes_ioremap_area->addr; - - BUG_ON(vaddr != (unsigned long)GHES_IOREMAP_IRQ_PAGE(base)); - unmap_kernel_range_noflush(vaddr, PAGE_SIZE); - arch_apei_flush_tlb_one(vaddr); + clear_fixmap(FIX_APEI_GHES_IRQ); } static int ghes_estatus_pool_init(void) @@ -361,10 +345,10 @@ static void ghes_copy_tofrom_phys(void *buffer, u64 paddr, u32 len, paddr += trunk; buffer += trunk; if (in_nmi) { - ghes_iounmap_nmi(vaddr); + ghes_iounmap_nmi(); raw_spin_unlock(&ghes_ioremap_lock_nmi); } else { - ghes_iounmap_irq(vaddr); + ghes_iounmap_irq(); spin_unlock_irqrestore(&ghes_ioremap_lock_irq, flags); } }

7 years, 1 month

1
0
0 0

[Linux-stable-mirror] FAILED: patch "[PATCH] ACPI / APEI: Replace ioremap_page_range() with fixmap" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 4f89fa286f6729312e227e7c2d764e8e7b9d340e Mon Sep 17 00:00:00 2001 From: James Morse <james.morse(a)arm.com> Date: Mon, 6 Nov 2017 18:44:24 +0000 Subject: [PATCH] ACPI / APEI: Replace ioremap_page_range() with fixmap Replace ghes_io{re,un}map_pfn_{nmi,irq}()s use of ioremap_page_range() with __set_fixmap() as ioremap_page_range() may sleep to allocate a new level of page-table, even if its passed an existing final-address to use in the mapping. The GHES driver can only be enabled for architectures that select HAVE_ACPI_APEI: Add fixmap entries to both x86 and arm64. clear_fixmap() does the TLB invalidation in __set_fixmap() for arm64 and __set_pte_vaddr() for x86. In each case its the same as the respective arch_apei_flush_tlb_one(). Reported-by: Fengguang Wu <fengguang.wu(a)intel.com> Suggested-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: James Morse <james.morse(a)arm.com> Reviewed-by: Borislav Petkov <bp(a)suse.de> Tested-by: Tyler Baicar <tbaicar(a)codeaurora.org> Tested-by: Toshi Kani <toshi.kani(a)hpe.com> [ For the arm64 bits: ] Acked-by: Will Deacon <will.deacon(a)arm.com> [ For the x86 bits: ] Acked-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com> Cc: All applicable <stable(a)vger.kernel.org> diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h index caf86be815ba..4052ec39e8db 100644 --- a/arch/arm64/include/asm/fixmap.h +++ b/arch/arm64/include/asm/fixmap.h @@ -51,6 +51,13 @@ enum fixed_addresses { FIX_EARLYCON_MEM_BASE, FIX_TEXT_POKE0, + +#ifdef CONFIG_ACPI_APEI_GHES + /* Used for GHES mapping from assorted contexts */ + FIX_APEI_GHES_IRQ, + FIX_APEI_GHES_NMI, +#endif /* CONFIG_ACPI_APEI_GHES */ + __end_of_permanent_fixed_addresses, /* diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index dcd9fb55e679..b0c505fe9a95 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -104,6 +104,12 @@ enum fixed_addresses { FIX_GDT_REMAP_BEGIN, FIX_GDT_REMAP_END = FIX_GDT_REMAP_BEGIN + NR_CPUS - 1, +#ifdef CONFIG_ACPI_APEI_GHES + /* Used for GHES mapping from assorted contexts */ + FIX_APEI_GHES_IRQ, + FIX_APEI_GHES_NMI, +#endif + __end_of_permanent_fixed_addresses, /* diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index cb7aceae3553..572b6c7303ed 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -51,6 +51,7 @@ #include <acpi/actbl1.h> #include <acpi/ghes.h> #include <acpi/apei.h> +#include <asm/fixmap.h> #include <asm/tlbflush.h> #include <ras/ras_event.h> @@ -112,7 +113,7 @@ static DEFINE_MUTEX(ghes_list_mutex); * Because the memory area used to transfer hardware error information * from BIOS to Linux can be determined only in NMI, IRQ or timer * handler, but general ioremap can not be used in atomic context, so - * a special version of atomic ioremap is implemented for that. + * the fixmap is used instead. */ /* @@ -126,8 +127,8 @@ static DEFINE_MUTEX(ghes_list_mutex); /* virtual memory area for atomic ioremap */ static struct vm_struct *ghes_ioremap_area; /* - * These 2 spinlock is used to prevent atomic ioremap virtual memory - * area from being mapped simultaneously. + * These 2 spinlocks are used to prevent the fixmap entries from being used + * simultaneously. */ static DEFINE_RAW_SPINLOCK(ghes_ioremap_lock_nmi); static DEFINE_SPINLOCK(ghes_ioremap_lock_irq); @@ -159,53 +160,36 @@ static void ghes_ioremap_exit(void) static void __iomem *ghes_ioremap_pfn_nmi(u64 pfn) { - unsigned long vaddr; phys_addr_t paddr; pgprot_t prot; - vaddr = (unsigned long)GHES_IOREMAP_NMI_PAGE(ghes_ioremap_area->addr); - paddr = pfn << PAGE_SHIFT; prot = arch_apei_get_mem_attribute(paddr); - ioremap_page_range(vaddr, vaddr + PAGE_SIZE, paddr, prot); + __set_fixmap(FIX_APEI_GHES_NMI, paddr, prot); - return (void __iomem *)vaddr; + return (void __iomem *) fix_to_virt(FIX_APEI_GHES_NMI); } static void __iomem *ghes_ioremap_pfn_irq(u64 pfn) { - unsigned long vaddr; phys_addr_t paddr; pgprot_t prot; - vaddr = (unsigned long)GHES_IOREMAP_IRQ_PAGE(ghes_ioremap_area->addr); - paddr = pfn << PAGE_SHIFT; prot = arch_apei_get_mem_attribute(paddr); + __set_fixmap(FIX_APEI_GHES_IRQ, paddr, prot); - ioremap_page_range(vaddr, vaddr + PAGE_SIZE, paddr, prot); - - return (void __iomem *)vaddr; + return (void __iomem *) fix_to_virt(FIX_APEI_GHES_IRQ); } -static void ghes_iounmap_nmi(void __iomem *vaddr_ptr) +static void ghes_iounmap_nmi(void) { - unsigned long vaddr = (unsigned long __force)vaddr_ptr; - void *base = ghes_ioremap_area->addr; - - BUG_ON(vaddr != (unsigned long)GHES_IOREMAP_NMI_PAGE(base)); - unmap_kernel_range_noflush(vaddr, PAGE_SIZE); - arch_apei_flush_tlb_one(vaddr); + clear_fixmap(FIX_APEI_GHES_NMI); } -static void ghes_iounmap_irq(void __iomem *vaddr_ptr) +static void ghes_iounmap_irq(void) { - unsigned long vaddr = (unsigned long __force)vaddr_ptr; - void *base = ghes_ioremap_area->addr; - - BUG_ON(vaddr != (unsigned long)GHES_IOREMAP_IRQ_PAGE(base)); - unmap_kernel_range_noflush(vaddr, PAGE_SIZE); - arch_apei_flush_tlb_one(vaddr); + clear_fixmap(FIX_APEI_GHES_IRQ); } static int ghes_estatus_pool_init(void) @@ -361,10 +345,10 @@ static void ghes_copy_tofrom_phys(void *buffer, u64 paddr, u32 len, paddr += trunk; buffer += trunk; if (in_nmi) { - ghes_iounmap_nmi(vaddr); + ghes_iounmap_nmi(); raw_spin_unlock(&ghes_ioremap_lock_nmi); } else { - ghes_iounmap_irq(vaddr); + ghes_iounmap_irq(); spin_unlock_irqrestore(&ghes_ioremap_lock_irq, flags); } }

7 years, 1 month

1
0
0 0

[Linux-stable-mirror] FAILED: patch "[PATCH] ACPI / APEI: Replace ioremap_page_range() with fixmap" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 4f89fa286f6729312e227e7c2d764e8e7b9d340e Mon Sep 17 00:00:00 2001 From: James Morse <james.morse(a)arm.com> Date: Mon, 6 Nov 2017 18:44:24 +0000 Subject: [PATCH] ACPI / APEI: Replace ioremap_page_range() with fixmap Replace ghes_io{re,un}map_pfn_{nmi,irq}()s use of ioremap_page_range() with __set_fixmap() as ioremap_page_range() may sleep to allocate a new level of page-table, even if its passed an existing final-address to use in the mapping. The GHES driver can only be enabled for architectures that select HAVE_ACPI_APEI: Add fixmap entries to both x86 and arm64. clear_fixmap() does the TLB invalidation in __set_fixmap() for arm64 and __set_pte_vaddr() for x86. In each case its the same as the respective arch_apei_flush_tlb_one(). Reported-by: Fengguang Wu <fengguang.wu(a)intel.com> Suggested-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: James Morse <james.morse(a)arm.com> Reviewed-by: Borislav Petkov <bp(a)suse.de> Tested-by: Tyler Baicar <tbaicar(a)codeaurora.org> Tested-by: Toshi Kani <toshi.kani(a)hpe.com> [ For the arm64 bits: ] Acked-by: Will Deacon <will.deacon(a)arm.com> [ For the x86 bits: ] Acked-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com> Cc: All applicable <stable(a)vger.kernel.org> diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h index caf86be815ba..4052ec39e8db 100644 --- a/arch/arm64/include/asm/fixmap.h +++ b/arch/arm64/include/asm/fixmap.h @@ -51,6 +51,13 @@ enum fixed_addresses { FIX_EARLYCON_MEM_BASE, FIX_TEXT_POKE0, + +#ifdef CONFIG_ACPI_APEI_GHES + /* Used for GHES mapping from assorted contexts */ + FIX_APEI_GHES_IRQ, + FIX_APEI_GHES_NMI, +#endif /* CONFIG_ACPI_APEI_GHES */ + __end_of_permanent_fixed_addresses, /* diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index dcd9fb55e679..b0c505fe9a95 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -104,6 +104,12 @@ enum fixed_addresses { FIX_GDT_REMAP_BEGIN, FIX_GDT_REMAP_END = FIX_GDT_REMAP_BEGIN + NR_CPUS - 1, +#ifdef CONFIG_ACPI_APEI_GHES + /* Used for GHES mapping from assorted contexts */ + FIX_APEI_GHES_IRQ, + FIX_APEI_GHES_NMI, +#endif + __end_of_permanent_fixed_addresses, /* diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index cb7aceae3553..572b6c7303ed 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -51,6 +51,7 @@ #include <acpi/actbl1.h> #include <acpi/ghes.h> #include <acpi/apei.h> +#include <asm/fixmap.h> #include <asm/tlbflush.h> #include <ras/ras_event.h> @@ -112,7 +113,7 @@ static DEFINE_MUTEX(ghes_list_mutex); * Because the memory area used to transfer hardware error information * from BIOS to Linux can be determined only in NMI, IRQ or timer * handler, but general ioremap can not be used in atomic context, so - * a special version of atomic ioremap is implemented for that. + * the fixmap is used instead. */ /* @@ -126,8 +127,8 @@ static DEFINE_MUTEX(ghes_list_mutex); /* virtual memory area for atomic ioremap */ static struct vm_struct *ghes_ioremap_area; /* - * These 2 spinlock is used to prevent atomic ioremap virtual memory - * area from being mapped simultaneously. + * These 2 spinlocks are used to prevent the fixmap entries from being used + * simultaneously. */ static DEFINE_RAW_SPINLOCK(ghes_ioremap_lock_nmi); static DEFINE_SPINLOCK(ghes_ioremap_lock_irq); @@ -159,53 +160,36 @@ static void ghes_ioremap_exit(void) static void __iomem *ghes_ioremap_pfn_nmi(u64 pfn) { - unsigned long vaddr; phys_addr_t paddr; pgprot_t prot; - vaddr = (unsigned long)GHES_IOREMAP_NMI_PAGE(ghes_ioremap_area->addr); - paddr = pfn << PAGE_SHIFT; prot = arch_apei_get_mem_attribute(paddr); - ioremap_page_range(vaddr, vaddr + PAGE_SIZE, paddr, prot); + __set_fixmap(FIX_APEI_GHES_NMI, paddr, prot); - return (void __iomem *)vaddr; + return (void __iomem *) fix_to_virt(FIX_APEI_GHES_NMI); } static void __iomem *ghes_ioremap_pfn_irq(u64 pfn) { - unsigned long vaddr; phys_addr_t paddr; pgprot_t prot; - vaddr = (unsigned long)GHES_IOREMAP_IRQ_PAGE(ghes_ioremap_area->addr); - paddr = pfn << PAGE_SHIFT; prot = arch_apei_get_mem_attribute(paddr); + __set_fixmap(FIX_APEI_GHES_IRQ, paddr, prot); - ioremap_page_range(vaddr, vaddr + PAGE_SIZE, paddr, prot); - - return (void __iomem *)vaddr; + return (void __iomem *) fix_to_virt(FIX_APEI_GHES_IRQ); } -static void ghes_iounmap_nmi(void __iomem *vaddr_ptr) +static void ghes_iounmap_nmi(void) { - unsigned long vaddr = (unsigned long __force)vaddr_ptr; - void *base = ghes_ioremap_area->addr; - - BUG_ON(vaddr != (unsigned long)GHES_IOREMAP_NMI_PAGE(base)); - unmap_kernel_range_noflush(vaddr, PAGE_SIZE); - arch_apei_flush_tlb_one(vaddr); + clear_fixmap(FIX_APEI_GHES_NMI); } -static void ghes_iounmap_irq(void __iomem *vaddr_ptr) +static void ghes_iounmap_irq(void) { - unsigned long vaddr = (unsigned long __force)vaddr_ptr; - void *base = ghes_ioremap_area->addr; - - BUG_ON(vaddr != (unsigned long)GHES_IOREMAP_IRQ_PAGE(base)); - unmap_kernel_range_noflush(vaddr, PAGE_SIZE); - arch_apei_flush_tlb_one(vaddr); + clear_fixmap(FIX_APEI_GHES_IRQ); } static int ghes_estatus_pool_init(void) @@ -361,10 +345,10 @@ static void ghes_copy_tofrom_phys(void *buffer, u64 paddr, u32 len, paddr += trunk; buffer += trunk; if (in_nmi) { - ghes_iounmap_nmi(vaddr); + ghes_iounmap_nmi(); raw_spin_unlock(&ghes_ioremap_lock_nmi); } else { - ghes_iounmap_irq(vaddr); + ghes_iounmap_irq(); spin_unlock_irqrestore(&ghes_ioremap_lock_irq, flags); } }

7 years, 1 month

1
0
0 0

[Linux-stable-mirror] FAILED: patch "[PATCH] ACPI / APEI: Replace ioremap_page_range() with fixmap" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 4f89fa286f6729312e227e7c2d764e8e7b9d340e Mon Sep 17 00:00:00 2001 From: James Morse <james.morse(a)arm.com> Date: Mon, 6 Nov 2017 18:44:24 +0000 Subject: [PATCH] ACPI / APEI: Replace ioremap_page_range() with fixmap Replace ghes_io{re,un}map_pfn_{nmi,irq}()s use of ioremap_page_range() with __set_fixmap() as ioremap_page_range() may sleep to allocate a new level of page-table, even if its passed an existing final-address to use in the mapping. The GHES driver can only be enabled for architectures that select HAVE_ACPI_APEI: Add fixmap entries to both x86 and arm64. clear_fixmap() does the TLB invalidation in __set_fixmap() for arm64 and __set_pte_vaddr() for x86. In each case its the same as the respective arch_apei_flush_tlb_one(). Reported-by: Fengguang Wu <fengguang.wu(a)intel.com> Suggested-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: James Morse <james.morse(a)arm.com> Reviewed-by: Borislav Petkov <bp(a)suse.de> Tested-by: Tyler Baicar <tbaicar(a)codeaurora.org> Tested-by: Toshi Kani <toshi.kani(a)hpe.com> [ For the arm64 bits: ] Acked-by: Will Deacon <will.deacon(a)arm.com> [ For the x86 bits: ] Acked-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com> Cc: All applicable <stable(a)vger.kernel.org> diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h index caf86be815ba..4052ec39e8db 100644 --- a/arch/arm64/include/asm/fixmap.h +++ b/arch/arm64/include/asm/fixmap.h @@ -51,6 +51,13 @@ enum fixed_addresses { FIX_EARLYCON_MEM_BASE, FIX_TEXT_POKE0, + +#ifdef CONFIG_ACPI_APEI_GHES + /* Used for GHES mapping from assorted contexts */ + FIX_APEI_GHES_IRQ, + FIX_APEI_GHES_NMI, +#endif /* CONFIG_ACPI_APEI_GHES */ + __end_of_permanent_fixed_addresses, /* diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index dcd9fb55e679..b0c505fe9a95 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -104,6 +104,12 @@ enum fixed_addresses { FIX_GDT_REMAP_BEGIN, FIX_GDT_REMAP_END = FIX_GDT_REMAP_BEGIN + NR_CPUS - 1, +#ifdef CONFIG_ACPI_APEI_GHES + /* Used for GHES mapping from assorted contexts */ + FIX_APEI_GHES_IRQ, + FIX_APEI_GHES_NMI, +#endif + __end_of_permanent_fixed_addresses, /* diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index cb7aceae3553..572b6c7303ed 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -51,6 +51,7 @@ #include <acpi/actbl1.h> #include <acpi/ghes.h> #include <acpi/apei.h> +#include <asm/fixmap.h> #include <asm/tlbflush.h> #include <ras/ras_event.h> @@ -112,7 +113,7 @@ static DEFINE_MUTEX(ghes_list_mutex); * Because the memory area used to transfer hardware error information * from BIOS to Linux can be determined only in NMI, IRQ or timer * handler, but general ioremap can not be used in atomic context, so - * a special version of atomic ioremap is implemented for that. + * the fixmap is used instead. */ /* @@ -126,8 +127,8 @@ static DEFINE_MUTEX(ghes_list_mutex); /* virtual memory area for atomic ioremap */ static struct vm_struct *ghes_ioremap_area; /* - * These 2 spinlock is used to prevent atomic ioremap virtual memory - * area from being mapped simultaneously. + * These 2 spinlocks are used to prevent the fixmap entries from being used + * simultaneously. */ static DEFINE_RAW_SPINLOCK(ghes_ioremap_lock_nmi); static DEFINE_SPINLOCK(ghes_ioremap_lock_irq); @@ -159,53 +160,36 @@ static void ghes_ioremap_exit(void) static void __iomem *ghes_ioremap_pfn_nmi(u64 pfn) { - unsigned long vaddr; phys_addr_t paddr; pgprot_t prot; - vaddr = (unsigned long)GHES_IOREMAP_NMI_PAGE(ghes_ioremap_area->addr); - paddr = pfn << PAGE_SHIFT; prot = arch_apei_get_mem_attribute(paddr); - ioremap_page_range(vaddr, vaddr + PAGE_SIZE, paddr, prot); + __set_fixmap(FIX_APEI_GHES_NMI, paddr, prot); - return (void __iomem *)vaddr; + return (void __iomem *) fix_to_virt(FIX_APEI_GHES_NMI); } static void __iomem *ghes_ioremap_pfn_irq(u64 pfn) { - unsigned long vaddr; phys_addr_t paddr; pgprot_t prot; - vaddr = (unsigned long)GHES_IOREMAP_IRQ_PAGE(ghes_ioremap_area->addr); - paddr = pfn << PAGE_SHIFT; prot = arch_apei_get_mem_attribute(paddr); + __set_fixmap(FIX_APEI_GHES_IRQ, paddr, prot); - ioremap_page_range(vaddr, vaddr + PAGE_SIZE, paddr, prot); - - return (void __iomem *)vaddr; + return (void __iomem *) fix_to_virt(FIX_APEI_GHES_IRQ); } -static void ghes_iounmap_nmi(void __iomem *vaddr_ptr) +static void ghes_iounmap_nmi(void) { - unsigned long vaddr = (unsigned long __force)vaddr_ptr; - void *base = ghes_ioremap_area->addr; - - BUG_ON(vaddr != (unsigned long)GHES_IOREMAP_NMI_PAGE(base)); - unmap_kernel_range_noflush(vaddr, PAGE_SIZE); - arch_apei_flush_tlb_one(vaddr); + clear_fixmap(FIX_APEI_GHES_NMI); } -static void ghes_iounmap_irq(void __iomem *vaddr_ptr) +static void ghes_iounmap_irq(void) { - unsigned long vaddr = (unsigned long __force)vaddr_ptr; - void *base = ghes_ioremap_area->addr; - - BUG_ON(vaddr != (unsigned long)GHES_IOREMAP_IRQ_PAGE(base)); - unmap_kernel_range_noflush(vaddr, PAGE_SIZE); - arch_apei_flush_tlb_one(vaddr); + clear_fixmap(FIX_APEI_GHES_IRQ); } static int ghes_estatus_pool_init(void) @@ -361,10 +345,10 @@ static void ghes_copy_tofrom_phys(void *buffer, u64 paddr, u32 len, paddr += trunk; buffer += trunk; if (in_nmi) { - ghes_iounmap_nmi(vaddr); + ghes_iounmap_nmi(); raw_spin_unlock(&ghes_ioremap_lock_nmi); } else { - ghes_iounmap_irq(vaddr); + ghes_iounmap_irq(); spin_unlock_irqrestore(&ghes_ioremap_lock_irq, flags); } }

7 years, 1 month

1
0
0 0

[Linux-stable-mirror] FAILED: patch "[PATCH] ACPI / APEI: Remove ghes_ioremap_area" failed to apply to 3.18-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 3.18-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 520e18a5080d2c444a03280d99c8a35cb667d321 Mon Sep 17 00:00:00 2001 From: James Morse <james.morse(a)arm.com> Date: Mon, 6 Nov 2017 18:44:25 +0000 Subject: [PATCH] ACPI / APEI: Remove ghes_ioremap_area Now that nothing is using the ghes_ioremap_area pages, rip them out. Signed-off-by: James Morse <james.morse(a)arm.com> Reviewed-by: Borislav Petkov <bp(a)suse.de> Tested-by: Tyler Baicar <tbaicar(a)codeaurora.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com> Cc: All applicable <stable(a)vger.kernel.org> diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 572b6c7303ed..f14695e744d0 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -114,19 +114,7 @@ static DEFINE_MUTEX(ghes_list_mutex); * from BIOS to Linux can be determined only in NMI, IRQ or timer * handler, but general ioremap can not be used in atomic context, so * the fixmap is used instead. - */ - -/* - * Two virtual pages are used, one for IRQ/PROCESS context, the other for - * NMI context (optionally). - */ -#define GHES_IOREMAP_PAGES 2 -#define GHES_IOREMAP_IRQ_PAGE(base) (base) -#define GHES_IOREMAP_NMI_PAGE(base) ((base) + PAGE_SIZE) - -/* virtual memory area for atomic ioremap */ -static struct vm_struct *ghes_ioremap_area; -/* + * * These 2 spinlocks are used to prevent the fixmap entries from being used * simultaneously. */ @@ -141,23 +129,6 @@ static atomic_t ghes_estatus_cache_alloced; static int ghes_panic_timeout __read_mostly = 30; -static int ghes_ioremap_init(void) -{ - ghes_ioremap_area = __get_vm_area(PAGE_SIZE * GHES_IOREMAP_PAGES, - VM_IOREMAP, VMALLOC_START, VMALLOC_END); - if (!ghes_ioremap_area) { - pr_err(GHES_PFX "Failed to allocate virtual memory area for atomic ioremap.\n"); - return -ENOMEM; - } - - return 0; -} - -static void ghes_ioremap_exit(void) -{ - free_vm_area(ghes_ioremap_area); -} - static void __iomem *ghes_ioremap_pfn_nmi(u64 pfn) { phys_addr_t paddr; @@ -1247,13 +1218,9 @@ static int __init ghes_init(void) ghes_nmi_init_cxt(); - rc = ghes_ioremap_init(); - if (rc) - goto err; - rc = ghes_estatus_pool_init(); if (rc) - goto err_ioremap_exit; + goto err; rc = ghes_estatus_pool_expand(GHES_ESTATUS_CACHE_AVG_SIZE * GHES_ESTATUS_CACHE_ALLOCED_MAX); @@ -1277,8 +1244,6 @@ static int __init ghes_init(void) return 0; err_pool_exit: ghes_estatus_pool_exit(); -err_ioremap_exit: - ghes_ioremap_exit(); err: return rc; }

7 years, 1 month

1
0
0 0

[Linux-stable-mirror] FAILED: patch "[PATCH] ACPI / APEI: Remove ghes_ioremap_area" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 520e18a5080d2c444a03280d99c8a35cb667d321 Mon Sep 17 00:00:00 2001 From: James Morse <james.morse(a)arm.com> Date: Mon, 6 Nov 2017 18:44:25 +0000 Subject: [PATCH] ACPI / APEI: Remove ghes_ioremap_area Now that nothing is using the ghes_ioremap_area pages, rip them out. Signed-off-by: James Morse <james.morse(a)arm.com> Reviewed-by: Borislav Petkov <bp(a)suse.de> Tested-by: Tyler Baicar <tbaicar(a)codeaurora.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com> Cc: All applicable <stable(a)vger.kernel.org> diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 572b6c7303ed..f14695e744d0 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -114,19 +114,7 @@ static DEFINE_MUTEX(ghes_list_mutex); * from BIOS to Linux can be determined only in NMI, IRQ or timer * handler, but general ioremap can not be used in atomic context, so * the fixmap is used instead. - */ - -/* - * Two virtual pages are used, one for IRQ/PROCESS context, the other for - * NMI context (optionally). - */ -#define GHES_IOREMAP_PAGES 2 -#define GHES_IOREMAP_IRQ_PAGE(base) (base) -#define GHES_IOREMAP_NMI_PAGE(base) ((base) + PAGE_SIZE) - -/* virtual memory area for atomic ioremap */ -static struct vm_struct *ghes_ioremap_area; -/* + * * These 2 spinlocks are used to prevent the fixmap entries from being used * simultaneously. */ @@ -141,23 +129,6 @@ static atomic_t ghes_estatus_cache_alloced; static int ghes_panic_timeout __read_mostly = 30; -static int ghes_ioremap_init(void) -{ - ghes_ioremap_area = __get_vm_area(PAGE_SIZE * GHES_IOREMAP_PAGES, - VM_IOREMAP, VMALLOC_START, VMALLOC_END); - if (!ghes_ioremap_area) { - pr_err(GHES_PFX "Failed to allocate virtual memory area for atomic ioremap.\n"); - return -ENOMEM; - } - - return 0; -} - -static void ghes_ioremap_exit(void) -{ - free_vm_area(ghes_ioremap_area); -} - static void __iomem *ghes_ioremap_pfn_nmi(u64 pfn) { phys_addr_t paddr; @@ -1247,13 +1218,9 @@ static int __init ghes_init(void) ghes_nmi_init_cxt(); - rc = ghes_ioremap_init(); - if (rc) - goto err; - rc = ghes_estatus_pool_init(); if (rc) - goto err_ioremap_exit; + goto err; rc = ghes_estatus_pool_expand(GHES_ESTATUS_CACHE_AVG_SIZE * GHES_ESTATUS_CACHE_ALLOCED_MAX); @@ -1277,8 +1244,6 @@ static int __init ghes_init(void) return 0; err_pool_exit: ghes_estatus_pool_exit(); -err_ioremap_exit: - ghes_ioremap_exit(); err: return rc; }

7 years, 1 month

1
0
0 0

[Linux-stable-mirror] FAILED: patch "[PATCH] ACPI / APEI: Remove ghes_ioremap_area" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 520e18a5080d2c444a03280d99c8a35cb667d321 Mon Sep 17 00:00:00 2001 From: James Morse <james.morse(a)arm.com> Date: Mon, 6 Nov 2017 18:44:25 +0000 Subject: [PATCH] ACPI / APEI: Remove ghes_ioremap_area Now that nothing is using the ghes_ioremap_area pages, rip them out. Signed-off-by: James Morse <james.morse(a)arm.com> Reviewed-by: Borislav Petkov <bp(a)suse.de> Tested-by: Tyler Baicar <tbaicar(a)codeaurora.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com> Cc: All applicable <stable(a)vger.kernel.org> diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 572b6c7303ed..f14695e744d0 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -114,19 +114,7 @@ static DEFINE_MUTEX(ghes_list_mutex); * from BIOS to Linux can be determined only in NMI, IRQ or timer * handler, but general ioremap can not be used in atomic context, so * the fixmap is used instead. - */ - -/* - * Two virtual pages are used, one for IRQ/PROCESS context, the other for - * NMI context (optionally). - */ -#define GHES_IOREMAP_PAGES 2 -#define GHES_IOREMAP_IRQ_PAGE(base) (base) -#define GHES_IOREMAP_NMI_PAGE(base) ((base) + PAGE_SIZE) - -/* virtual memory area for atomic ioremap */ -static struct vm_struct *ghes_ioremap_area; -/* + * * These 2 spinlocks are used to prevent the fixmap entries from being used * simultaneously. */ @@ -141,23 +129,6 @@ static atomic_t ghes_estatus_cache_alloced; static int ghes_panic_timeout __read_mostly = 30; -static int ghes_ioremap_init(void) -{ - ghes_ioremap_area = __get_vm_area(PAGE_SIZE * GHES_IOREMAP_PAGES, - VM_IOREMAP, VMALLOC_START, VMALLOC_END); - if (!ghes_ioremap_area) { - pr_err(GHES_PFX "Failed to allocate virtual memory area for atomic ioremap.\n"); - return -ENOMEM; - } - - return 0; -} - -static void ghes_ioremap_exit(void) -{ - free_vm_area(ghes_ioremap_area); -} - static void __iomem *ghes_ioremap_pfn_nmi(u64 pfn) { phys_addr_t paddr; @@ -1247,13 +1218,9 @@ static int __init ghes_init(void) ghes_nmi_init_cxt(); - rc = ghes_ioremap_init(); - if (rc) - goto err; - rc = ghes_estatus_pool_init(); if (rc) - goto err_ioremap_exit; + goto err; rc = ghes_estatus_pool_expand(GHES_ESTATUS_CACHE_AVG_SIZE * GHES_ESTATUS_CACHE_ALLOCED_MAX); @@ -1277,8 +1244,6 @@ static int __init ghes_init(void) return 0; err_pool_exit: ghes_estatus_pool_exit(); -err_ioremap_exit: - ghes_ioremap_exit(); err: return rc; }

7 years, 1 month

1
0
0 0

[Linux-stable-mirror] FAILED: patch "[PATCH] ACPI / APEI: Remove ghes_ioremap_area" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 520e18a5080d2c444a03280d99c8a35cb667d321 Mon Sep 17 00:00:00 2001 From: James Morse <james.morse(a)arm.com> Date: Mon, 6 Nov 2017 18:44:25 +0000 Subject: [PATCH] ACPI / APEI: Remove ghes_ioremap_area Now that nothing is using the ghes_ioremap_area pages, rip them out. Signed-off-by: James Morse <james.morse(a)arm.com> Reviewed-by: Borislav Petkov <bp(a)suse.de> Tested-by: Tyler Baicar <tbaicar(a)codeaurora.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com> Cc: All applicable <stable(a)vger.kernel.org> diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 572b6c7303ed..f14695e744d0 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -114,19 +114,7 @@ static DEFINE_MUTEX(ghes_list_mutex); * from BIOS to Linux can be determined only in NMI, IRQ or timer * handler, but general ioremap can not be used in atomic context, so * the fixmap is used instead. - */ - -/* - * Two virtual pages are used, one for IRQ/PROCESS context, the other for - * NMI context (optionally). - */ -#define GHES_IOREMAP_PAGES 2 -#define GHES_IOREMAP_IRQ_PAGE(base) (base) -#define GHES_IOREMAP_NMI_PAGE(base) ((base) + PAGE_SIZE) - -/* virtual memory area for atomic ioremap */ -static struct vm_struct *ghes_ioremap_area; -/* + * * These 2 spinlocks are used to prevent the fixmap entries from being used * simultaneously. */ @@ -141,23 +129,6 @@ static atomic_t ghes_estatus_cache_alloced; static int ghes_panic_timeout __read_mostly = 30; -static int ghes_ioremap_init(void) -{ - ghes_ioremap_area = __get_vm_area(PAGE_SIZE * GHES_IOREMAP_PAGES, - VM_IOREMAP, VMALLOC_START, VMALLOC_END); - if (!ghes_ioremap_area) { - pr_err(GHES_PFX "Failed to allocate virtual memory area for atomic ioremap.\n"); - return -ENOMEM; - } - - return 0; -} - -static void ghes_ioremap_exit(void) -{ - free_vm_area(ghes_ioremap_area); -} - static void __iomem *ghes_ioremap_pfn_nmi(u64 pfn) { phys_addr_t paddr; @@ -1247,13 +1218,9 @@ static int __init ghes_init(void) ghes_nmi_init_cxt(); - rc = ghes_ioremap_init(); - if (rc) - goto err; - rc = ghes_estatus_pool_init(); if (rc) - goto err_ioremap_exit; + goto err; rc = ghes_estatus_pool_expand(GHES_ESTATUS_CACHE_AVG_SIZE * GHES_ESTATUS_CACHE_ALLOCED_MAX); @@ -1277,8 +1244,6 @@ static int __init ghes_init(void) return 0; err_pool_exit: ghes_estatus_pool_exit(); -err_ioremap_exit: - ghes_ioremap_exit(); err: return rc; }

7 years, 1 month

1
0
0 0

[Linux-stable-mirror] FAILED: patch "[PATCH] ACPI / PM: Fix acpi_pm_notifier_lock vs flush_workqueue()" failed to apply to 3.18-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 3.18-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From ff1656790b3a4caca94505c52fd0250f981ea187 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala(a)linux.intel.com> Date: Tue, 7 Nov 2017 23:08:10 +0200 Subject: [PATCH] ACPI / PM: Fix acpi_pm_notifier_lock vs flush_workqueue() deadlock MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit acpi_remove_pm_notifier() ends up calling flush_workqueue() while holding acpi_pm_notifier_lock, and that same lock is taken by by the work via acpi_pm_notify_handler(). This can deadlock. To fix the problem let's split the single lock into two: one to protect the dev->wakeup between the work vs. add/remove, and another one to handle notifier installation vs. removal. After commit a1d14934ea4b "workqueue/lockdep: 'Fix' flush_work() annotation" I was able to kill the machine (Intel Braswell) very easily with 'powertop --auto-tune', runtime suspending i915, and trying to wake it up via the USB keyboard. The cases when it didn't die are presumably explained by lockdep getting disabled by something else (cpu hotplug locking issues usually). Fortunately I still got a lockdep report over netconsole (trickling in very slowly), even though the machine was otherwise practically dead: [ 112.179806] ====================================================== [ 114.670858] WARNING: possible circular locking dependency detected [ 117.155663] 4.13.0-rc6-bsw-bisect-00169-ga1d14934ea4b #119 Not tainted [ 119.658101] ------------------------------------------------------ [ 121.310242] xhci_hcd 0000:00:14.0: xHCI host not responding to stop endpoint command. [ 121.313294] xhci_hcd 0000:00:14.0: xHCI host controller not responding, assume dead [ 121.313346] xhci_hcd 0000:00:14.0: HC died; cleaning up [ 121.313485] usb 1-6: USB disconnect, device number 3 [ 121.313501] usb 1-6.2: USB disconnect, device number 4 [ 134.747383] kworker/0:2/47 is trying to acquire lock: [ 137.220790] (acpi_pm_notifier_lock){+.+.}, at: [<ffffffff813cafdf>] acpi_pm_notify_handler+0x2f/0x80 [ 139.721524] [ 139.721524] but task is already holding lock: [ 144.672922] ((&dpc->work)){+.+.}, at: [<ffffffff8109ce90>] process_one_work+0x160/0x720 [ 147.184450] [ 147.184450] which lock already depends on the new lock. [ 147.184450] [ 154.604711] [ 154.604711] the existing dependency chain (in reverse order) is: [ 159.447888] [ 159.447888] -> #2 ((&dpc->work)){+.+.}: [ 164.183486] __lock_acquire+0x1255/0x13f0 [ 166.504313] lock_acquire+0xb5/0x210 [ 168.778973] process_one_work+0x1b9/0x720 [ 171.030316] worker_thread+0x4c/0x440 [ 173.257184] kthread+0x154/0x190 [ 175.456143] ret_from_fork+0x27/0x40 [ 177.624348] [ 177.624348] -> #1 ("kacpi_notify"){+.+.}: [ 181.850351] __lock_acquire+0x1255/0x13f0 [ 183.941695] lock_acquire+0xb5/0x210 [ 186.046115] flush_workqueue+0xdd/0x510 [ 190.408153] acpi_os_wait_events_complete+0x31/0x40 [ 192.625303] acpi_remove_notify_handler+0x133/0x188 [ 194.820829] acpi_remove_pm_notifier+0x56/0x90 [ 196.989068] acpi_dev_pm_detach+0x5f/0xa0 [ 199.145866] dev_pm_domain_detach+0x27/0x30 [ 201.285614] i2c_device_probe+0x100/0x210 [ 203.411118] driver_probe_device+0x23e/0x310 [ 205.522425] __driver_attach+0xa3/0xb0 [ 207.634268] bus_for_each_dev+0x69/0xa0 [ 209.714797] driver_attach+0x1e/0x20 [ 211.778258] bus_add_driver+0x1bc/0x230 [ 213.837162] driver_register+0x60/0xe0 [ 215.868162] i2c_register_driver+0x42/0x70 [ 217.869551] 0xffffffffa0172017 [ 219.863009] do_one_initcall+0x45/0x170 [ 221.843863] do_init_module+0x5f/0x204 [ 223.817915] load_module+0x225b/0x29b0 [ 225.757234] SyS_finit_module+0xc6/0xd0 [ 227.661851] do_syscall_64+0x5c/0x120 [ 229.536819] return_from_SYSCALL_64+0x0/0x7a [ 231.392444] [ 231.392444] -> #0 (acpi_pm_notifier_lock){+.+.}: [ 235.124914] check_prev_add+0x44e/0x8a0 [ 237.024795] __lock_acquire+0x1255/0x13f0 [ 238.937351] lock_acquire+0xb5/0x210 [ 240.840799] __mutex_lock+0x75/0x940 [ 242.709517] mutex_lock_nested+0x1c/0x20 [ 244.551478] acpi_pm_notify_handler+0x2f/0x80 [ 246.382052] acpi_ev_notify_dispatch+0x44/0x5c [ 248.194412] acpi_os_execute_deferred+0x14/0x30 [ 250.003925] process_one_work+0x1ec/0x720 [ 251.803191] worker_thread+0x4c/0x440 [ 253.605307] kthread+0x154/0x190 [ 255.387498] ret_from_fork+0x27/0x40 [ 257.153175] [ 257.153175] other info that might help us debug this: [ 257.153175] [ 262.324392] Chain exists of: [ 262.324392] acpi_pm_notifier_lock --> "kacpi_notify" --> (&dpc->work) [ 262.324392] [ 267.391997] Possible unsafe locking scenario: [ 267.391997] [ 270.758262] CPU0 CPU1 [ 272.431713] ---- ---- [ 274.060756] lock((&dpc->work)); [ 275.646532] lock("kacpi_notify"); [ 277.260772] lock((&dpc->work)); [ 278.839146] lock(acpi_pm_notifier_lock); [ 280.391902] [ 280.391902] *** DEADLOCK *** [ 280.391902] [ 284.986385] 2 locks held by kworker/0:2/47: [ 286.524895] #0: ("kacpi_notify"){+.+.}, at: [<ffffffff8109ce90>] process_one_work+0x160/0x720 [ 288.112927] #1: ((&dpc->work)){+.+.}, at: [<ffffffff8109ce90>] process_one_work+0x160/0x720 [ 289.727725] Fixes: c072530f391e (ACPI / PM: Revork the handling of ACPI device wakeup notifications) Signed-off-by: Ville Syrjälä <ville.syrjala(a)linux.intel.com> Cc: 3.17+ <stable(a)vger.kernel.org> # 3.17+ Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com> diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index 17e8eb93a76c..69ffd1dc1de7 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -387,6 +387,7 @@ EXPORT_SYMBOL(acpi_bus_power_manageable); #ifdef CONFIG_PM static DEFINE_MUTEX(acpi_pm_notifier_lock); +static DEFINE_MUTEX(acpi_pm_notifier_install_lock); void acpi_pm_wakeup_event(struct device *dev) { @@ -443,24 +444,25 @@ acpi_status acpi_add_pm_notifier(struct acpi_device *adev, struct device *dev, if (!dev && !func) return AE_BAD_PARAMETER; - mutex_lock(&acpi_pm_notifier_lock); + mutex_lock(&acpi_pm_notifier_install_lock); if (adev->wakeup.flags.notifier_present) goto out; - adev->wakeup.ws = wakeup_source_register(dev_name(&adev->dev)); - adev->wakeup.context.dev = dev; - adev->wakeup.context.func = func; - status = acpi_install_notify_handler(adev->handle, ACPI_SYSTEM_NOTIFY, acpi_pm_notify_handler, NULL); if (ACPI_FAILURE(status)) goto out; + mutex_lock(&acpi_pm_notifier_lock); + adev->wakeup.ws = wakeup_source_register(dev_name(&adev->dev)); + adev->wakeup.context.dev = dev; + adev->wakeup.context.func = func; adev->wakeup.flags.notifier_present = true; + mutex_unlock(&acpi_pm_notifier_lock); out: - mutex_unlock(&acpi_pm_notifier_lock); + mutex_unlock(&acpi_pm_notifier_install_lock); return status; } @@ -472,7 +474,7 @@ acpi_status acpi_remove_pm_notifier(struct acpi_device *adev) { acpi_status status = AE_BAD_PARAMETER; - mutex_lock(&acpi_pm_notifier_lock); + mutex_lock(&acpi_pm_notifier_install_lock); if (!adev->wakeup.flags.notifier_present) goto out; @@ -483,14 +485,15 @@ acpi_status acpi_remove_pm_notifier(struct acpi_device *adev) if (ACPI_FAILURE(status)) goto out; + mutex_lock(&acpi_pm_notifier_lock); adev->wakeup.context.func = NULL; adev->wakeup.context.dev = NULL; wakeup_source_unregister(adev->wakeup.ws); - adev->wakeup.flags.notifier_present = false; + mutex_unlock(&acpi_pm_notifier_lock); out: - mutex_unlock(&acpi_pm_notifier_lock); + mutex_unlock(&acpi_pm_notifier_install_lock); return status; }

7 years, 1 month

1
0
0 0

[Linux-stable-mirror] FAILED: patch "[PATCH] ACPI / PM: Fix acpi_pm_notifier_lock vs flush_workqueue()" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From ff1656790b3a4caca94505c52fd0250f981ea187 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala(a)linux.intel.com> Date: Tue, 7 Nov 2017 23:08:10 +0200 Subject: [PATCH] ACPI / PM: Fix acpi_pm_notifier_lock vs flush_workqueue() deadlock MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit acpi_remove_pm_notifier() ends up calling flush_workqueue() while holding acpi_pm_notifier_lock, and that same lock is taken by by the work via acpi_pm_notify_handler(). This can deadlock. To fix the problem let's split the single lock into two: one to protect the dev->wakeup between the work vs. add/remove, and another one to handle notifier installation vs. removal. After commit a1d14934ea4b "workqueue/lockdep: 'Fix' flush_work() annotation" I was able to kill the machine (Intel Braswell) very easily with 'powertop --auto-tune', runtime suspending i915, and trying to wake it up via the USB keyboard. The cases when it didn't die are presumably explained by lockdep getting disabled by something else (cpu hotplug locking issues usually). Fortunately I still got a lockdep report over netconsole (trickling in very slowly), even though the machine was otherwise practically dead: [ 112.179806] ====================================================== [ 114.670858] WARNING: possible circular locking dependency detected [ 117.155663] 4.13.0-rc6-bsw-bisect-00169-ga1d14934ea4b #119 Not tainted [ 119.658101] ------------------------------------------------------ [ 121.310242] xhci_hcd 0000:00:14.0: xHCI host not responding to stop endpoint command. [ 121.313294] xhci_hcd 0000:00:14.0: xHCI host controller not responding, assume dead [ 121.313346] xhci_hcd 0000:00:14.0: HC died; cleaning up [ 121.313485] usb 1-6: USB disconnect, device number 3 [ 121.313501] usb 1-6.2: USB disconnect, device number 4 [ 134.747383] kworker/0:2/47 is trying to acquire lock: [ 137.220790] (acpi_pm_notifier_lock){+.+.}, at: [<ffffffff813cafdf>] acpi_pm_notify_handler+0x2f/0x80 [ 139.721524] [ 139.721524] but task is already holding lock: [ 144.672922] ((&dpc->work)){+.+.}, at: [<ffffffff8109ce90>] process_one_work+0x160/0x720 [ 147.184450] [ 147.184450] which lock already depends on the new lock. [ 147.184450] [ 154.604711] [ 154.604711] the existing dependency chain (in reverse order) is: [ 159.447888] [ 159.447888] -> #2 ((&dpc->work)){+.+.}: [ 164.183486] __lock_acquire+0x1255/0x13f0 [ 166.504313] lock_acquire+0xb5/0x210 [ 168.778973] process_one_work+0x1b9/0x720 [ 171.030316] worker_thread+0x4c/0x440 [ 173.257184] kthread+0x154/0x190 [ 175.456143] ret_from_fork+0x27/0x40 [ 177.624348] [ 177.624348] -> #1 ("kacpi_notify"){+.+.}: [ 181.850351] __lock_acquire+0x1255/0x13f0 [ 183.941695] lock_acquire+0xb5/0x210 [ 186.046115] flush_workqueue+0xdd/0x510 [ 190.408153] acpi_os_wait_events_complete+0x31/0x40 [ 192.625303] acpi_remove_notify_handler+0x133/0x188 [ 194.820829] acpi_remove_pm_notifier+0x56/0x90 [ 196.989068] acpi_dev_pm_detach+0x5f/0xa0 [ 199.145866] dev_pm_domain_detach+0x27/0x30 [ 201.285614] i2c_device_probe+0x100/0x210 [ 203.411118] driver_probe_device+0x23e/0x310 [ 205.522425] __driver_attach+0xa3/0xb0 [ 207.634268] bus_for_each_dev+0x69/0xa0 [ 209.714797] driver_attach+0x1e/0x20 [ 211.778258] bus_add_driver+0x1bc/0x230 [ 213.837162] driver_register+0x60/0xe0 [ 215.868162] i2c_register_driver+0x42/0x70 [ 217.869551] 0xffffffffa0172017 [ 219.863009] do_one_initcall+0x45/0x170 [ 221.843863] do_init_module+0x5f/0x204 [ 223.817915] load_module+0x225b/0x29b0 [ 225.757234] SyS_finit_module+0xc6/0xd0 [ 227.661851] do_syscall_64+0x5c/0x120 [ 229.536819] return_from_SYSCALL_64+0x0/0x7a [ 231.392444] [ 231.392444] -> #0 (acpi_pm_notifier_lock){+.+.}: [ 235.124914] check_prev_add+0x44e/0x8a0 [ 237.024795] __lock_acquire+0x1255/0x13f0 [ 238.937351] lock_acquire+0xb5/0x210 [ 240.840799] __mutex_lock+0x75/0x940 [ 242.709517] mutex_lock_nested+0x1c/0x20 [ 244.551478] acpi_pm_notify_handler+0x2f/0x80 [ 246.382052] acpi_ev_notify_dispatch+0x44/0x5c [ 248.194412] acpi_os_execute_deferred+0x14/0x30 [ 250.003925] process_one_work+0x1ec/0x720 [ 251.803191] worker_thread+0x4c/0x440 [ 253.605307] kthread+0x154/0x190 [ 255.387498] ret_from_fork+0x27/0x40 [ 257.153175] [ 257.153175] other info that might help us debug this: [ 257.153175] [ 262.324392] Chain exists of: [ 262.324392] acpi_pm_notifier_lock --> "kacpi_notify" --> (&dpc->work) [ 262.324392] [ 267.391997] Possible unsafe locking scenario: [ 267.391997] [ 270.758262] CPU0 CPU1 [ 272.431713] ---- ---- [ 274.060756] lock((&dpc->work)); [ 275.646532] lock("kacpi_notify"); [ 277.260772] lock((&dpc->work)); [ 278.839146] lock(acpi_pm_notifier_lock); [ 280.391902] [ 280.391902] *** DEADLOCK *** [ 280.391902] [ 284.986385] 2 locks held by kworker/0:2/47: [ 286.524895] #0: ("kacpi_notify"){+.+.}, at: [<ffffffff8109ce90>] process_one_work+0x160/0x720 [ 288.112927] #1: ((&dpc->work)){+.+.}, at: [<ffffffff8109ce90>] process_one_work+0x160/0x720 [ 289.727725] Fixes: c072530f391e (ACPI / PM: Revork the handling of ACPI device wakeup notifications) Signed-off-by: Ville Syrjälä <ville.syrjala(a)linux.intel.com> Cc: 3.17+ <stable(a)vger.kernel.org> # 3.17+ Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com> diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index 17e8eb93a76c..69ffd1dc1de7 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -387,6 +387,7 @@ EXPORT_SYMBOL(acpi_bus_power_manageable); #ifdef CONFIG_PM static DEFINE_MUTEX(acpi_pm_notifier_lock); +static DEFINE_MUTEX(acpi_pm_notifier_install_lock); void acpi_pm_wakeup_event(struct device *dev) { @@ -443,24 +444,25 @@ acpi_status acpi_add_pm_notifier(struct acpi_device *adev, struct device *dev, if (!dev && !func) return AE_BAD_PARAMETER; - mutex_lock(&acpi_pm_notifier_lock); + mutex_lock(&acpi_pm_notifier_install_lock); if (adev->wakeup.flags.notifier_present) goto out; - adev->wakeup.ws = wakeup_source_register(dev_name(&adev->dev)); - adev->wakeup.context.dev = dev; - adev->wakeup.context.func = func; - status = acpi_install_notify_handler(adev->handle, ACPI_SYSTEM_NOTIFY, acpi_pm_notify_handler, NULL); if (ACPI_FAILURE(status)) goto out; + mutex_lock(&acpi_pm_notifier_lock); + adev->wakeup.ws = wakeup_source_register(dev_name(&adev->dev)); + adev->wakeup.context.dev = dev; + adev->wakeup.context.func = func; adev->wakeup.flags.notifier_present = true; + mutex_unlock(&acpi_pm_notifier_lock); out: - mutex_unlock(&acpi_pm_notifier_lock); + mutex_unlock(&acpi_pm_notifier_install_lock); return status; } @@ -472,7 +474,7 @@ acpi_status acpi_remove_pm_notifier(struct acpi_device *adev) { acpi_status status = AE_BAD_PARAMETER; - mutex_lock(&acpi_pm_notifier_lock); + mutex_lock(&acpi_pm_notifier_install_lock); if (!adev->wakeup.flags.notifier_present) goto out; @@ -483,14 +485,15 @@ acpi_status acpi_remove_pm_notifier(struct acpi_device *adev) if (ACPI_FAILURE(status)) goto out; + mutex_lock(&acpi_pm_notifier_lock); adev->wakeup.context.func = NULL; adev->wakeup.context.dev = NULL; wakeup_source_unregister(adev->wakeup.ws); - adev->wakeup.flags.notifier_present = false; + mutex_unlock(&acpi_pm_notifier_lock); out: - mutex_unlock(&acpi_pm_notifier_lock); + mutex_unlock(&acpi_pm_notifier_install_lock); return status; }

7 years, 1 month

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror November 2017