From 4d80d6ca5d77fde9880da8466e5b64f250e5bf82 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 18 May 2021 11:17:26 +0200 Subject: genirq: Export affinity setter for modules Perf modules abuse irq_set_affinity_hint() to set the affinity of system PMU interrupts just because irq_set_affinity() was not exported. The fact that irq_set_affinity_hint() actually sets the affinity is a non-documented side effect and the name is clearly saying it's a hint. To clean this up, export the real affinity setter. Signed-off-by: Thomas Gleixner Acked-by: Mark Rutland Link: https://lore.kernel.org/r/20210518093117.968251441@linutronix.de --- include/linux/interrupt.h | 35 ++--------------------------------- 1 file changed, 2 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 4777850a6dc7..35a374241515 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -319,39 +319,8 @@ struct irq_affinity_desc { extern cpumask_var_t irq_default_affinity; -/* Internal implementation. Use the helpers below */ -extern int __irq_set_affinity(unsigned int irq, const struct cpumask *cpumask, - bool force); - -/** - * irq_set_affinity - Set the irq affinity of a given irq - * @irq: Interrupt to set affinity - * @cpumask: cpumask - * - * Fails if cpumask does not contain an online CPU - */ -static inline int -irq_set_affinity(unsigned int irq, const struct cpumask *cpumask) -{ - return __irq_set_affinity(irq, cpumask, false); -} - -/** - * irq_force_affinity - Force the irq affinity of a given irq - * @irq: Interrupt to set affinity - * @cpumask: cpumask - * - * Same as irq_set_affinity, but without checking the mask against - * online cpus. - * - * Solely for low level cpu hotplug code, where we need to make per - * cpu interrupts affine before the cpu becomes online. - */ -static inline int -irq_force_affinity(unsigned int irq, const struct cpumask *cpumask) -{ - return __irq_set_affinity(irq, cpumask, true); -} +extern int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask); +extern int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask); extern int irq_can_set_affinity(unsigned int irq); extern int irq_select_affinity(unsigned int irq); -- cgit v1.2.3 From 3fdc0cb59d97f87e2cc708d424f1538e31744286 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 18 May 2021 17:36:18 +0100 Subject: arm64: smccc: Add support for SMCCCv1.2 extended input/output registers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit SMCCC v1.2 allows x8-x17 to be used as parameter registers and x4—x17 to be used as result registers in SMC64/HVC64. Arm Firmware Framework for Armv8-A specification makes use of x0-x7 as parameter and result registers. There are other users like Hyper-V who intend to use beyond x0-x7 as well. Current SMCCC interface in the kernel just use x0-x7 as parameter and x0-x3 as result registers as required by SMCCCv1.0. Let us add new interface to support this extended set of input/output registers namely x0-x17 as both parameter and result registers. Acked-by: Mark Rutland Tested-by: Michael Kelley Reviewed-by: Michael Kelley Cc: Will Deacon Cc: Catalin Marinas Signed-off-by: Sudeep Holla Reviewed-by: Mark Brown Link: https://lore.kernel.org/r/20210518163618.43950-1-sudeep.holla@arm.com Signed-off-by: Will Deacon --- include/linux/arm-smccc.h | 55 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+) (limited to 'include') diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 6861489a1890..5cef2b8b0479 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -227,6 +227,61 @@ struct arm_smccc_res { unsigned long a3; }; +#ifdef CONFIG_ARM64 +/** + * struct arm_smccc_1_2_regs - Arguments for or Results from SMC/HVC call + * @a0-a17 argument values from registers 0 to 17 + */ +struct arm_smccc_1_2_regs { + unsigned long a0; + unsigned long a1; + unsigned long a2; + unsigned long a3; + unsigned long a4; + unsigned long a5; + unsigned long a6; + unsigned long a7; + unsigned long a8; + unsigned long a9; + unsigned long a10; + unsigned long a11; + unsigned long a12; + unsigned long a13; + unsigned long a14; + unsigned long a15; + unsigned long a16; + unsigned long a17; +}; + +/** + * arm_smccc_1_2_hvc() - make HVC calls + * @args: arguments passed via struct arm_smccc_1_2_regs + * @res: result values via struct arm_smccc_1_2_regs + * + * This function is used to make HVC calls following SMC Calling Convention + * v1.2 or above. The content of the supplied param are copied from the + * structure to registers prior to the HVC instruction. The return values + * are updated with the content from registers on return from the HVC + * instruction. + */ +asmlinkage void arm_smccc_1_2_hvc(const struct arm_smccc_1_2_regs *args, + struct arm_smccc_1_2_regs *res); + +/** + * arm_smccc_1_2_smc() - make SMC calls + * @args: arguments passed via struct arm_smccc_1_2_regs + * @res: result values via struct arm_smccc_1_2_regs + * + * This function is used to make SMC calls following SMC Calling Convention + * v1.2 or above. The content of the supplied param are copied from the + * structure to registers prior to the SMC instruction. The return values + * are updated with the content from registers on return from the SMC + * instruction. + */ +asmlinkage void arm_smccc_1_2_smc(const struct arm_smccc_1_2_regs *args, + struct arm_smccc_1_2_regs *res); +#endif + /** * struct arm_smccc_quirk - Contains quirk information * @id: quirk identification -- cgit v1.2.3 From 92638b4e1b47f97d7269e74465dedf73096f777d Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Wed, 2 Jun 2021 16:52:27 -0700 Subject: mm: arch: remove indirection level in alloc_zeroed_user_highpage_movable() In an upcoming change we would like to add a flag to GFP_HIGHUSER_MOVABLE so that it would no longer be an OR of GFP_HIGHUSER and __GFP_MOVABLE. This poses a problem for alloc_zeroed_user_highpage_movable() which passes __GFP_MOVABLE into an arch-specific __alloc_zeroed_user_highpage() hook which ORs in GFP_HIGHUSER. Since __alloc_zeroed_user_highpage() is only ever called from alloc_zeroed_user_highpage_movable(), we can remove one level of indirection here. Remove __alloc_zeroed_user_highpage(), make alloc_zeroed_user_highpage_movable() the hook, and use GFP_HIGHUSER_MOVABLE in the hook implementations so that they will pick up the new flag that we are going to add. Signed-off-by: Peter Collingbourne Link: https://linux-review.googlesource.com/id/Ic6361c657b2cdcd896adbe0cf7cb5a7fbb1ed7bf Acked-by: Catalin Marinas Link: https://lore.kernel.org/r/20210602235230.3928842-2-pcc@google.com Signed-off-by: Will Deacon --- include/linux/highmem.h | 35 ++++++++--------------------------- 1 file changed, 8 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 832b49b50c7b..54d0643b8fcf 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -152,28 +152,24 @@ static inline void clear_user_highpage(struct page *page, unsigned long vaddr) } #endif -#ifndef __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE +#ifndef __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE /** - * __alloc_zeroed_user_highpage - Allocate a zeroed HIGHMEM page for a VMA with caller-specified movable GFP flags - * @movableflags: The GFP flags related to the pages future ability to move like __GFP_MOVABLE + * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM page for a VMA that the caller knows can move * @vma: The VMA the page is to be allocated for * @vaddr: The virtual address the page will be inserted into * - * This function will allocate a page for a VMA but the caller is expected - * to specify via movableflags whether the page will be movable in the - * future or not + * This function will allocate a page for a VMA that the caller knows will + * be able to migrate in the future using move_pages() or reclaimed * * An architecture may override this function by defining - * __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE and providing their own + * __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE and providing their own * implementation. */ static inline struct page * -__alloc_zeroed_user_highpage(gfp_t movableflags, - struct vm_area_struct *vma, - unsigned long vaddr) +alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma, + unsigned long vaddr) { - struct page *page = alloc_page_vma(GFP_HIGHUSER | movableflags, - vma, vaddr); + struct page *page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr); if (page) clear_user_highpage(page, vaddr); @@ -182,21 +178,6 @@ __alloc_zeroed_user_highpage(gfp_t movableflags, } #endif -/** - * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM page for a VMA that the caller knows can move - * @vma: The VMA the page is to be allocated for - * @vaddr: The virtual address the page will be inserted into - * - * This function will allocate a page for a VMA that the caller knows will - * be able to migrate in the future using move_pages() or reclaimed - */ -static inline struct page * -alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma, - unsigned long vaddr) -{ - return __alloc_zeroed_user_highpage(__GFP_MOVABLE, vma, vaddr); -} - static inline void clear_highpage(struct page *page) { void *kaddr = kmap_atomic(page); -- cgit v1.2.3 From 7a3b835371883558eb63e069d891bd87f562380d Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Wed, 2 Jun 2021 16:52:28 -0700 Subject: kasan: use separate (un)poison implementation for integrated init Currently with integrated init page_alloc.c needs to know whether kasan_alloc_pages() will zero initialize memory, but this will start becoming more complicated once we start adding tag initialization support for user pages. To avoid page_alloc.c needing to know more details of what integrated init will do, move the unpoisoning logic for integrated init into the HW tags implementation. Currently the logic is identical but it will diverge in subsequent patches. For symmetry do the same for poisoning although this logic will be unaffected by subsequent patches. Signed-off-by: Peter Collingbourne Reviewed-by: Andrey Konovalov Link: https://linux-review.googlesource.com/id/I2c550234c6c4a893c48c18ff0c6ce658c7c67056 Link: https://lore.kernel.org/r/20210602235230.3928842-3-pcc@google.com Signed-off-by: Will Deacon --- include/linux/kasan.h | 64 ++++++++++++++++++++++++++++++--------------------- 1 file changed, 38 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index b1678a61e6a7..a1c7ce5f3e4f 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -2,6 +2,7 @@ #ifndef _LINUX_KASAN_H #define _LINUX_KASAN_H +#include #include #include @@ -79,14 +80,6 @@ static inline void kasan_disable_current(void) {} #endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ -#ifdef CONFIG_KASAN - -struct kasan_cache { - int alloc_meta_offset; - int free_meta_offset; - bool is_kmalloc; -}; - #ifdef CONFIG_KASAN_HW_TAGS DECLARE_STATIC_KEY_FALSE(kasan_flag_enabled); @@ -101,11 +94,14 @@ static inline bool kasan_has_integrated_init(void) return kasan_enabled(); } +void kasan_alloc_pages(struct page *page, unsigned int order, gfp_t flags); +void kasan_free_pages(struct page *page, unsigned int order); + #else /* CONFIG_KASAN_HW_TAGS */ static inline bool kasan_enabled(void) { - return true; + return IS_ENABLED(CONFIG_KASAN); } static inline bool kasan_has_integrated_init(void) @@ -113,8 +109,30 @@ static inline bool kasan_has_integrated_init(void) return false; } +static __always_inline void kasan_alloc_pages(struct page *page, + unsigned int order, gfp_t flags) +{ + /* Only available for integrated init. */ + BUILD_BUG(); +} + +static __always_inline void kasan_free_pages(struct page *page, + unsigned int order) +{ + /* Only available for integrated init. */ + BUILD_BUG(); +} + #endif /* CONFIG_KASAN_HW_TAGS */ +#ifdef CONFIG_KASAN + +struct kasan_cache { + int alloc_meta_offset; + int free_meta_offset; + bool is_kmalloc; +}; + slab_flags_t __kasan_never_merge(void); static __always_inline slab_flags_t kasan_never_merge(void) { @@ -130,20 +148,20 @@ static __always_inline void kasan_unpoison_range(const void *addr, size_t size) __kasan_unpoison_range(addr, size); } -void __kasan_alloc_pages(struct page *page, unsigned int order, bool init); -static __always_inline void kasan_alloc_pages(struct page *page, +void __kasan_poison_pages(struct page *page, unsigned int order, bool init); +static __always_inline void kasan_poison_pages(struct page *page, unsigned int order, bool init) { if (kasan_enabled()) - __kasan_alloc_pages(page, order, init); + __kasan_poison_pages(page, order, init); } -void __kasan_free_pages(struct page *page, unsigned int order, bool init); -static __always_inline void kasan_free_pages(struct page *page, - unsigned int order, bool init) +void __kasan_unpoison_pages(struct page *page, unsigned int order, bool init); +static __always_inline void kasan_unpoison_pages(struct page *page, + unsigned int order, bool init) { if (kasan_enabled()) - __kasan_free_pages(page, order, init); + __kasan_unpoison_pages(page, order, init); } void __kasan_cache_create(struct kmem_cache *cache, unsigned int *size, @@ -285,21 +303,15 @@ void kasan_restore_multi_shot(bool enabled); #else /* CONFIG_KASAN */ -static inline bool kasan_enabled(void) -{ - return false; -} -static inline bool kasan_has_integrated_init(void) -{ - return false; -} static inline slab_flags_t kasan_never_merge(void) { return 0; } static inline void kasan_unpoison_range(const void *address, size_t size) {} -static inline void kasan_alloc_pages(struct page *page, unsigned int order, bool init) {} -static inline void kasan_free_pages(struct page *page, unsigned int order, bool init) {} +static inline void kasan_poison_pages(struct page *page, unsigned int order, + bool init) {} +static inline void kasan_unpoison_pages(struct page *page, unsigned int order, + bool init) {} static inline void kasan_cache_create(struct kmem_cache *cache, unsigned int *size, slab_flags_t *flags) {} -- cgit v1.2.3 From 013bb59dbb7cf876449df860946458a595a96d51 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Wed, 2 Jun 2021 16:52:29 -0700 Subject: arm64: mte: handle tags zeroing at page allocation time Currently, on an anonymous page fault, the kernel allocates a zeroed page and maps it in user space. If the mapping is tagged (PROT_MTE), set_pte_at() additionally clears the tags. It is, however, more efficient to clear the tags at the same time as zeroing the data on allocation. To avoid clearing the tags on any page (which may not be mapped as tagged), only do this if the vma flags contain VM_MTE. This requires introducing a new GFP flag that is used to determine whether to clear the tags. The DC GZVA instruction with a 0 top byte (and 0 tag) requires top-byte-ignore. Set the TCR_EL1.{TBI1,TBID1} bits irrespective of whether KASAN_HW is enabled. Signed-off-by: Peter Collingbourne Co-developed-by: Catalin Marinas Signed-off-by: Catalin Marinas Link: https://linux-review.googlesource.com/id/Id46dc94e30fe11474f7e54f5d65e7658dbdddb26 Reviewed-by: Catalin Marinas Reviewed-by: Andrey Konovalov Link: https://lore.kernel.org/r/20210602235230.3928842-4-pcc@google.com Signed-off-by: Will Deacon --- include/linux/gfp.h | 9 +++++++-- include/linux/highmem.h | 8 ++++++++ 2 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 11da8af06704..68ba237365dc 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -53,8 +53,9 @@ struct vm_area_struct; #define ___GFP_HARDWALL 0x100000u #define ___GFP_THISNODE 0x200000u #define ___GFP_ACCOUNT 0x400000u +#define ___GFP_ZEROTAGS 0x800000u #ifdef CONFIG_LOCKDEP -#define ___GFP_NOLOCKDEP 0x800000u +#define ___GFP_NOLOCKDEP 0x1000000u #else #define ___GFP_NOLOCKDEP 0 #endif @@ -229,16 +230,20 @@ struct vm_area_struct; * %__GFP_COMP address compound page metadata. * * %__GFP_ZERO returns a zeroed page on success. + * + * %__GFP_ZEROTAGS returns a page with zeroed memory tags on success, if + * __GFP_ZERO is set. */ #define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN) #define __GFP_COMP ((__force gfp_t)___GFP_COMP) #define __GFP_ZERO ((__force gfp_t)___GFP_ZERO) +#define __GFP_ZEROTAGS ((__force gfp_t)___GFP_ZEROTAGS) /* Disable lockdep for GFP context tracking */ #define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP) /* Room for N __GFP_FOO bits */ -#define __GFP_BITS_SHIFT (23 + IS_ENABLED(CONFIG_LOCKDEP)) +#define __GFP_BITS_SHIFT (24 + IS_ENABLED(CONFIG_LOCKDEP)) #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) /** diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 54d0643b8fcf..8c6e8e996c87 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -185,6 +185,14 @@ static inline void clear_highpage(struct page *page) kunmap_atomic(kaddr); } +#ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGE + +static inline void tag_clear_highpage(struct page *page) +{ +} + +#endif + /* * If we pass in a base or tail page, we can zero up to PAGE_SIZE. * If we pass in a head page, we can zero up to the size of the compound page. -- cgit v1.2.3 From c275c5c6d50a0518cdb0584e85905d10e7cefc6e Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Wed, 2 Jun 2021 16:52:30 -0700 Subject: kasan: disable freed user page poisoning with HW tags Poisoning freed pages protects against kernel use-after-free. The likelihood of such a bug involving kernel pages is significantly higher than that for user pages. At the same time, poisoning freed pages can impose a significant performance cost, which cannot always be justified for user pages given the lower probability of finding a bug. Therefore, disable freed user page poisoning when using HW tags. We identify "user" pages via the flag set GFP_HIGHUSER_MOVABLE, which indicates a strong likelihood of not being directly accessible to the kernel. Signed-off-by: Peter Collingbourne Reviewed-by: Andrey Konovalov Link: https://linux-review.googlesource.com/id/I716846e2de8ef179f44e835770df7e6307be96c9 Link: https://lore.kernel.org/r/20210602235230.3928842-5-pcc@google.com Signed-off-by: Will Deacon --- include/linux/gfp.h | 13 ++++++++++--- include/linux/page-flags.h | 9 +++++++++ include/trace/events/mmflags.h | 9 ++++++++- 3 files changed, 27 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 68ba237365dc..e6102dfa4faa 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -54,8 +54,9 @@ struct vm_area_struct; #define ___GFP_THISNODE 0x200000u #define ___GFP_ACCOUNT 0x400000u #define ___GFP_ZEROTAGS 0x800000u +#define ___GFP_SKIP_KASAN_POISON 0x1000000u #ifdef CONFIG_LOCKDEP -#define ___GFP_NOLOCKDEP 0x1000000u +#define ___GFP_NOLOCKDEP 0x2000000u #else #define ___GFP_NOLOCKDEP 0 #endif @@ -233,17 +234,22 @@ struct vm_area_struct; * * %__GFP_ZEROTAGS returns a page with zeroed memory tags on success, if * __GFP_ZERO is set. + * + * %__GFP_SKIP_KASAN_POISON returns a page which does not need to be poisoned + * on deallocation. Typically used for userspace pages. Currently only has an + * effect in HW tags mode. */ #define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN) #define __GFP_COMP ((__force gfp_t)___GFP_COMP) #define __GFP_ZERO ((__force gfp_t)___GFP_ZERO) #define __GFP_ZEROTAGS ((__force gfp_t)___GFP_ZEROTAGS) +#define __GFP_SKIP_KASAN_POISON ((__force gfp_t)___GFP_SKIP_KASAN_POISON) /* Disable lockdep for GFP context tracking */ #define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP) /* Room for N __GFP_FOO bits */ -#define __GFP_BITS_SHIFT (24 + IS_ENABLED(CONFIG_LOCKDEP)) +#define __GFP_BITS_SHIFT (25 + IS_ENABLED(CONFIG_LOCKDEP)) #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) /** @@ -324,7 +330,8 @@ struct vm_area_struct; #define GFP_DMA __GFP_DMA #define GFP_DMA32 __GFP_DMA32 #define GFP_HIGHUSER (GFP_USER | __GFP_HIGHMEM) -#define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE) +#define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE | \ + __GFP_SKIP_KASAN_POISON) #define GFP_TRANSHUGE_LIGHT ((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \ __GFP_NOMEMALLOC | __GFP_NOWARN) & ~__GFP_RECLAIM) #define GFP_TRANSHUGE (GFP_TRANSHUGE_LIGHT | __GFP_DIRECT_RECLAIM) diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 04a34c08e0a6..40e2c5000585 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -137,6 +137,9 @@ enum pageflags { #endif #ifdef CONFIG_64BIT PG_arch_2, +#endif +#ifdef CONFIG_KASAN_HW_TAGS + PG_skip_kasan_poison, #endif __NR_PAGEFLAGS, @@ -443,6 +446,12 @@ TESTCLEARFLAG(Young, young, PF_ANY) PAGEFLAG(Idle, idle, PF_ANY) #endif +#ifdef CONFIG_KASAN_HW_TAGS +PAGEFLAG(SkipKASanPoison, skip_kasan_poison, PF_HEAD) +#else +PAGEFLAG_FALSE(SkipKASanPoison) +#endif + /* * PageReported() is used to track reported free pages within the Buddy * allocator. We can use the non-atomic version of the test and set diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index 629c7a0eaff2..390270e00a1d 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -85,6 +85,12 @@ #define IF_HAVE_PG_ARCH_2(flag,string) #endif +#ifdef CONFIG_KASAN_HW_TAGS +#define IF_HAVE_PG_SKIP_KASAN_POISON(flag,string) ,{1UL << flag, string} +#else +#define IF_HAVE_PG_SKIP_KASAN_POISON(flag,string) +#endif + #define __def_pageflag_names \ {1UL << PG_locked, "locked" }, \ {1UL << PG_waiters, "waiters" }, \ @@ -112,7 +118,8 @@ IF_HAVE_PG_UNCACHED(PG_uncached, "uncached" ) \ IF_HAVE_PG_HWPOISON(PG_hwpoison, "hwpoison" ) \ IF_HAVE_PG_IDLE(PG_young, "young" ) \ IF_HAVE_PG_IDLE(PG_idle, "idle" ) \ -IF_HAVE_PG_ARCH_2(PG_arch_2, "arch_2" ) +IF_HAVE_PG_ARCH_2(PG_arch_2, "arch_2" ) \ +IF_HAVE_PG_SKIP_KASAN_POISON(PG_skip_kasan_poison, "skip_kasan_poison") #define show_page_flags(flags) \ (flags) ? __print_flags(flags, "|", \ -- cgit v1.2.3 From cfa7ff959a789a953eac40c8ac793e2cfc2db931 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 3 Jun 2021 19:41:18 +0100 Subject: arm64: smccc: Support SMCCC v1.3 SVE register saving hint SMCCC v1.2 requires that all SVE state be preserved over SMC calls which introduces substantial overhead in the common case where there is no SVE state in the registers. To avoid this SMCCC v1.3 introduces a flag which allows the caller to say that there is no state that needs to be preserved in the registers. Make use of this flag, setting it if the SMCCC version indicates support for it and the TIF_ flags indicate that there is no live SVE state in the registers, this avoids placing any constraints on when SMCCC calls can be done or triggering extra saving and reloading of SVE register state in the kernel. This would be straightforward enough except for the rather entertaining inline assembly we use to do SMCCC v1.1 calls to allow us to take advantage of the limited number of registers it clobbers. Deal with this by having a function which we call immediately before issuing the SMCCC call to make our checks and set the flag. Using alternatives the overhead if SVE is supported but not detected at runtime can be reduced to a single NOP. Signed-off-by: Mark Brown Reviewed-by: Ard Biesheuvel Reviewed-by: Marc Zyngier Link: https://lore.kernel.org/r/20210603184118.15090-1-broonie@kernel.org Signed-off-by: Will Deacon --- include/linux/arm-smccc.h | 33 +++++++++++++++++++++++++++++++-- 1 file changed, 31 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 5cef2b8b0479..7d1cabe15262 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -63,6 +63,9 @@ #define ARM_SMCCC_VERSION_1_0 0x10000 #define ARM_SMCCC_VERSION_1_1 0x10001 #define ARM_SMCCC_VERSION_1_2 0x10002 +#define ARM_SMCCC_VERSION_1_3 0x10003 + +#define ARM_SMCCC_1_3_SVE_HINT 0x10000 #define ARM_SMCCC_VERSION_FUNC_ID \ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ @@ -216,6 +219,8 @@ u32 arm_smccc_get_version(void); void __init arm_smccc_version_init(u32 version, enum arm_smccc_conduit conduit); +extern u64 smccc_has_sve_hint; + /** * struct arm_smccc_res - Result from SMC/HVC call * @a0-a3 result values from registers 0 to 3 @@ -295,6 +300,15 @@ struct arm_smccc_quirk { } state; }; +/** + * __arm_smccc_sve_check() - Set the SVE hint bit when doing SMC calls + * + * Sets the SMCCC hint bit to indicate if there is live state in the SVE + * registers, this modifies x0 in place and should never be called from C + * code. + */ +asmlinkage unsigned long __arm_smccc_sve_check(unsigned long x0); + /** * __arm_smccc_smc() - make SMC calls * @a0-a7: arguments passed in registers 0 to 7 @@ -352,6 +366,20 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, #endif +/* nVHE hypervisor doesn't have a current thread so needs separate checks */ +#if defined(CONFIG_ARM64_SVE) && !defined(__KVM_NVHE_HYPERVISOR__) + +#define SMCCC_SVE_CHECK ALTERNATIVE("nop \n", "bl __arm_smccc_sve_check \n", \ + ARM64_SVE) +#define smccc_sve_clobbers "x16", "x30", "cc", + +#else + +#define SMCCC_SVE_CHECK +#define smccc_sve_clobbers + +#endif + #define ___count_args(_0, _1, _2, _3, _4, _5, _6, _7, _8, x, ...) x #define __count_args(...) \ @@ -419,7 +447,7 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, #define ___constraints(count) \ : __constraint_read_ ## count \ - : "memory" + : smccc_sve_clobbers "memory" #define __constraints(count) ___constraints(count) /* @@ -434,7 +462,8 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, register unsigned long r2 asm("r2"); \ register unsigned long r3 asm("r3"); \ __declare_args(__count_args(__VA_ARGS__), __VA_ARGS__); \ - asm volatile(inst "\n" : \ + asm volatile(SMCCC_SVE_CHECK \ + inst "\n" : \ "=r" (r0), "=r" (r1), "=r" (r2), "=r" (r3) \ __constraints(__count_args(__VA_ARGS__))); \ if (___res) \ -- cgit v1.2.3 From f8e6d24144d1bfbb8714faa9044e135c0c00bd89 Mon Sep 17 00:00:00 2001 From: Qi Liu Date: Wed, 9 Jun 2021 14:40:57 +0800 Subject: perf: Add EVENT_ATTR_ID to simplify event attributes Similar EVENT_ATTR macros are defined in many PMU drivers, like Arm PMU driver, Arm SMMU PMU driver. So add a generic macro to simplify code. Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo Cc: Mark Rutland Cc: Alexander Shishkin Signed-off-by: Qi Liu Link: https://lore.kernel.org/r/1623220863-58233-2-git-send-email-liuqi115@huawei.com Signed-off-by: Will Deacon --- include/linux/perf_event.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index f5a6a2f069ed..2d510ad750ed 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1576,6 +1576,12 @@ static struct perf_pmu_events_attr _var = { \ .event_str = _str, \ }; +#define PMU_EVENT_ATTR_ID(_name, _show, _id) \ + (&((struct perf_pmu_events_attr[]) { \ + { .attr = __ATTR(_name, 0444, _show, NULL), \ + .id = _id, } \ + })[0].attr.attr) + #define PMU_FORMAT_ATTR(_name, _format) \ static ssize_t \ _name##_show(struct device *dev, \ -- cgit v1.2.3