From 800977f6f32e452cba6b04ef21d2f5383ca29209 Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Fri, 14 Jan 2022 14:02:52 -0800 Subject: kthread: add the helper function kthread_run_on_cpu() Add a new helper function kthread_run_on_cpu(), which includes kthread_create_on_cpu/wake_up_process(). In some cases, use kthread_run_on_cpu() directly instead of kthread_create_on_node/kthread_bind/wake_up_process() or kthread_create_on_cpu/wake_up_process() or kthreadd_create/kthread_bind/wake_up_process() to simplify the code. [akpm@linux-foundation.org: export kthread_create_on_cpu to modules] Link: https://lkml.kernel.org/r/20211022025711.3673-2-caihuoqing@baidu.com Signed-off-by: Cai Huoqing Cc: Bernard Metzler Cc: Cai Huoqing Cc: Daniel Bristot de Oliveira Cc: Davidlohr Bueso Cc: Doug Ledford Cc: Ingo Molnar Cc: Jason Gunthorpe Cc: Joel Fernandes (Google) Cc: Josh Triplett Cc: Lai Jiangshan Cc: Mathieu Desnoyers Cc: "Paul E . McKenney" Cc: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kthread.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 346b0f269161..db47aae7c481 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -56,6 +56,31 @@ bool kthread_is_per_cpu(struct task_struct *k); __k; \ }) +/** + * kthread_run_on_cpu - create and wake a cpu bound thread. + * @threadfn: the function to run until signal_pending(current). + * @data: data ptr for @threadfn. + * @cpu: The cpu on which the thread should be bound, + * @namefmt: printf-style name for the thread. Format is restricted + * to "name.*%u". Code fills in cpu number. + * + * Description: Convenient wrapper for kthread_create_on_cpu() + * followed by wake_up_process(). Returns the kthread or + * ERR_PTR(-ENOMEM). + */ +static inline struct task_struct * +kthread_run_on_cpu(int (*threadfn)(void *data), void *data, + unsigned int cpu, const char *namefmt) +{ + struct task_struct *p; + + p = kthread_create_on_cpu(threadfn, data, cpu, namefmt); + if (!IS_ERR(p)) + wake_up_process(p); + + return p; +} + void free_kthread_struct(struct task_struct *k); void kthread_bind(struct task_struct *k, unsigned int cpu); void kthread_bind_mask(struct task_struct *k, const struct cpumask *mask); -- cgit v1.2.3 From 60115fa54ad7b913b7cb5844e6b7ffeb842d55f2 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Fri, 14 Jan 2022 14:04:11 -0800 Subject: mm: defer kmemleak object creation of module_alloc() Yongqiang reports a kmemleak panic when module insmod/rmmod with KASAN enabled(without KASAN_VMALLOC) on x86[1]. When the module area allocates memory, it's kmemleak_object is created successfully, but the KASAN shadow memory of module allocation is not ready, so when kmemleak scan the module's pointer, it will panic due to no shadow memory with KASAN check. module_alloc __vmalloc_node_range kmemleak_vmalloc kmemleak_scan update_checksum kasan_module_alloc kmemleak_ignore Note, there is no problem if KASAN_VMALLOC enabled, the modules area entire shadow memory is preallocated. Thus, the bug only exits on ARCH which supports dynamic allocation of module area per module load, for now, only x86/arm64/s390 are involved. Add a VM_DEFER_KMEMLEAK flags, defer vmalloc'ed object register of kmemleak in module_alloc() to fix this issue. [1] https://lore.kernel.org/all/6d41e2b9-4692-5ec4-b1cd-cbe29ae89739@huawei.com/ [wangkefeng.wang@huawei.com: fix build] Link: https://lkml.kernel.org/r/20211125080307.27225-1-wangkefeng.wang@huawei.com [akpm@linux-foundation.org: simplify ifdefs, per Andrey] Link: https://lkml.kernel.org/r/CA+fCnZcnwJHUQq34VuRxpdoY6_XbJCDJ-jopksS5Eia4PijPzw@mail.gmail.com Link: https://lkml.kernel.org/r/20211124142034.192078-1-wangkefeng.wang@huawei.com Fixes: 793213a82de4 ("s390/kasan: dynamic shadow mem allocation for modules") Fixes: 39d114ddc682 ("arm64: add KASAN support") Fixes: bebf56a1b176 ("kasan: enable instrumentation of global variables") Signed-off-by: Kefeng Wang Reported-by: Yongqiang Liu Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Catalin Marinas Cc: Will Deacon Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: Alexander Gordeev Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: Alexander Potapenko Cc: Kefeng Wang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm64/kernel/module.c | 4 ++-- arch/s390/kernel/module.c | 5 +++-- arch/x86/kernel/module.c | 7 ++++--- include/linux/kasan.h | 4 ++-- include/linux/vmalloc.h | 7 +++++++ mm/kasan/shadow.c | 9 +++++++-- mm/vmalloc.c | 3 ++- 7 files changed, 27 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index b5ec010c481f..309a27553c87 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -36,7 +36,7 @@ void *module_alloc(unsigned long size) module_alloc_end = MODULES_END; p = __vmalloc_node_range(size, MODULE_ALIGN, module_alloc_base, - module_alloc_end, gfp_mask, PAGE_KERNEL, 0, + module_alloc_end, gfp_mask, PAGE_KERNEL, VM_DEFER_KMEMLEAK, NUMA_NO_NODE, __builtin_return_address(0)); if (!p && IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) && @@ -58,7 +58,7 @@ void *module_alloc(unsigned long size) PAGE_KERNEL, 0, NUMA_NO_NODE, __builtin_return_address(0)); - if (p && (kasan_module_alloc(p, size) < 0)) { + if (p && (kasan_module_alloc(p, size, gfp_mask) < 0)) { vfree(p); return NULL; } diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index b01ba460b7ca..d52d85367bf7 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -37,14 +37,15 @@ void *module_alloc(unsigned long size) { + gfp_t gfp_mask = GFP_KERNEL; void *p; if (PAGE_ALIGN(size) > MODULES_LEN) return NULL; p = __vmalloc_node_range(size, MODULE_ALIGN, MODULES_VADDR, MODULES_END, - GFP_KERNEL, PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE, + gfp_mask, PAGE_KERNEL_EXEC, VM_DEFER_KMEMLEAK, NUMA_NO_NODE, __builtin_return_address(0)); - if (p && (kasan_module_alloc(p, size) < 0)) { + if (p && (kasan_module_alloc(p, size, gfp_mask) < 0)) { vfree(p); return NULL; } diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 169fb6f4cd2e..95fa745e310a 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -67,6 +67,7 @@ static unsigned long int get_module_load_offset(void) void *module_alloc(unsigned long size) { + gfp_t gfp_mask = GFP_KERNEL; void *p; if (PAGE_ALIGN(size) > MODULES_LEN) @@ -74,10 +75,10 @@ void *module_alloc(unsigned long size) p = __vmalloc_node_range(size, MODULE_ALIGN, MODULES_VADDR + get_module_load_offset(), - MODULES_END, GFP_KERNEL, - PAGE_KERNEL, 0, NUMA_NO_NODE, + MODULES_END, gfp_mask, + PAGE_KERNEL, VM_DEFER_KMEMLEAK, NUMA_NO_NODE, __builtin_return_address(0)); - if (p && (kasan_module_alloc(p, size) < 0)) { + if (p && (kasan_module_alloc(p, size, gfp_mask) < 0)) { vfree(p); return NULL; } diff --git a/include/linux/kasan.h b/include/linux/kasan.h index d8783b682669..89c99e5e67de 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -474,12 +474,12 @@ static inline void kasan_populate_early_vm_area_shadow(void *start, * allocations with real shadow memory. With KASAN vmalloc, the special * case is unnecessary, as the work is handled in the generic case. */ -int kasan_module_alloc(void *addr, size_t size); +int kasan_module_alloc(void *addr, size_t size, gfp_t gfp_mask); void kasan_free_shadow(const struct vm_struct *vm); #else /* (CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS) && !CONFIG_KASAN_VMALLOC */ -static inline int kasan_module_alloc(void *addr, size_t size) { return 0; } +static inline int kasan_module_alloc(void *addr, size_t size, gfp_t gfp_mask) { return 0; } static inline void kasan_free_shadow(const struct vm_struct *vm) {} #endif /* (CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS) && !CONFIG_KASAN_VMALLOC */ diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 6e022cc712e6..880227b9f044 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -28,6 +28,13 @@ struct notifier_block; /* in notifier.h */ #define VM_MAP_PUT_PAGES 0x00000200 /* put pages and free array in vfree */ #define VM_NO_HUGE_VMAP 0x00000400 /* force PAGE_SIZE pte mapping */ +#if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ + !defined(CONFIG_KASAN_VMALLOC) +#define VM_DEFER_KMEMLEAK 0x00000800 /* defer kmemleak object creation */ +#else +#define VM_DEFER_KMEMLEAK 0 +#endif + /* * VM_KASAN is used slightly differently depending on CONFIG_KASAN_VMALLOC. * diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c index 4a4929b29a23..94136f84b449 100644 --- a/mm/kasan/shadow.c +++ b/mm/kasan/shadow.c @@ -498,7 +498,7 @@ void kasan_release_vmalloc(unsigned long start, unsigned long end, #else /* CONFIG_KASAN_VMALLOC */ -int kasan_module_alloc(void *addr, size_t size) +int kasan_module_alloc(void *addr, size_t size, gfp_t gfp_mask) { void *ret; size_t scaled_size; @@ -520,9 +520,14 @@ int kasan_module_alloc(void *addr, size_t size) __builtin_return_address(0)); if (ret) { + struct vm_struct *vm = find_vm_area(addr); __memset(ret, KASAN_SHADOW_INIT, shadow_size); - find_vm_area(addr)->flags |= VM_KASAN; + vm->flags |= VM_KASAN; kmemleak_ignore(ret); + + if (vm->flags & VM_DEFER_KMEMLEAK) + kmemleak_vmalloc(vm, size, gfp_mask); + return 0; } diff --git a/mm/vmalloc.c b/mm/vmalloc.c index d2a00ad4e1dd..bf3c2fe8f528 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -3074,7 +3074,8 @@ again: clear_vm_uninitialized_flag(area); size = PAGE_ALIGN(size); - kmemleak_vmalloc(area, size, gfp_mask); + if (!(vm_flags & VM_DEFER_KMEMLEAK)) + kmemleak_vmalloc(area, size, gfp_mask); return addr; -- cgit v1.2.3 From c4386bd8ee3a921c3c799b7197dc898ade76a453 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Fri, 14 Jan 2022 14:04:22 -0800 Subject: mm/memremap: add ZONE_DEVICE support for compound pages Add a new @vmemmap_shift property for struct dev_pagemap which specifies that a devmap is composed of a set of compound pages of order @vmemmap_shift, instead of base pages. When a compound page devmap is requested, all but the first page are initialised as tail pages instead of order-0 pages. For certain ZONE_DEVICE users like device-dax which have a fixed page size, this creates an opportunity to optimize GUP and GUP-fast walkers, treating it the same way as THP or hugetlb pages. Additionally, commit 7118fc2906e2 ("hugetlb: address ref count racing in prep_compound_gigantic_page") removed set_page_count() because the setting of page ref count to zero was redundant. devmap pages don't come from page allocator though and only head page refcount is used for compound pages, hence initialize tail page count to zero. Link: https://lkml.kernel.org/r/20211202204422.26777-5-joao.m.martins@oracle.com Signed-off-by: Joao Martins Reviewed-by: Dan Williams Cc: Christoph Hellwig Cc: Dave Jiang Cc: Jane Chu Cc: Jason Gunthorpe Cc: Jason Gunthorpe Cc: John Hubbard Cc: Jonathan Corbet Cc: Matthew Wilcox (Oracle) Cc: Mike Kravetz Cc: Muchun Song Cc: Naoya Horiguchi Cc: Vishal Verma Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memremap.h | 11 +++++++++++ mm/memremap.c | 18 ++++++++++++------ mm/page_alloc.c | 38 +++++++++++++++++++++++++++++++++++++- 3 files changed, 60 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index c0e9d35889e8..61a6a0e27359 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -99,6 +99,11 @@ struct dev_pagemap_ops { * @done: completion for @internal_ref * @type: memory type: see MEMORY_* in memory_hotplug.h * @flags: PGMAP_* flags to specify defailed behavior + * @vmemmap_shift: structural definition of how the vmemmap page metadata + * is populated, specifically the metadata page order. + * A zero value (default) uses base pages as the vmemmap metadata + * representation. A bigger value will set up compound struct pages + * of the requested order value. * @ops: method table * @owner: an opaque pointer identifying the entity that manages this * instance. Used by various helpers to make sure that no @@ -114,6 +119,7 @@ struct dev_pagemap { struct completion done; enum memory_type type; unsigned int flags; + unsigned long vmemmap_shift; const struct dev_pagemap_ops *ops; void *owner; int nr_range; @@ -130,6 +136,11 @@ static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap) return NULL; } +static inline unsigned long pgmap_vmemmap_nr(struct dev_pagemap *pgmap) +{ + return 1 << pgmap->vmemmap_shift; +} + #ifdef CONFIG_ZONE_DEVICE void *memremap_pages(struct dev_pagemap *pgmap, int nid); void memunmap_pages(struct dev_pagemap *pgmap); diff --git a/mm/memremap.c b/mm/memremap.c index 5a66a71ab591..a2869d8519a2 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -102,15 +102,22 @@ static unsigned long pfn_end(struct dev_pagemap *pgmap, int range_id) return (range->start + range_len(range)) >> PAGE_SHIFT; } -static unsigned long pfn_next(unsigned long pfn) +static unsigned long pfn_next(struct dev_pagemap *pgmap, unsigned long pfn) { - if (pfn % 1024 == 0) + if (pfn % (1024 << pgmap->vmemmap_shift)) cond_resched(); - return pfn + 1; + return pfn + pgmap_vmemmap_nr(pgmap); +} + +static unsigned long pfn_len(struct dev_pagemap *pgmap, unsigned long range_id) +{ + return (pfn_end(pgmap, range_id) - + pfn_first(pgmap, range_id)) >> pgmap->vmemmap_shift; } #define for_each_device_pfn(pfn, map, i) \ - for (pfn = pfn_first(map, i); pfn < pfn_end(map, i); pfn = pfn_next(pfn)) + for (pfn = pfn_first(map, i); pfn < pfn_end(map, i); \ + pfn = pfn_next(map, pfn)) static void dev_pagemap_kill(struct dev_pagemap *pgmap) { @@ -295,8 +302,7 @@ static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params, memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE], PHYS_PFN(range->start), PHYS_PFN(range_len(range)), pgmap); - percpu_ref_get_many(pgmap->ref, pfn_end(pgmap, range_id) - - pfn_first(pgmap, range_id)); + percpu_ref_get_many(pgmap->ref, pfn_len(pgmap, range_id)); return 0; err_add_memory: diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 23045a2a1339..d59023a676ed 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6612,6 +6612,35 @@ static void __ref __init_zone_device_page(struct page *page, unsigned long pfn, } } +static void __ref memmap_init_compound(struct page *head, + unsigned long head_pfn, + unsigned long zone_idx, int nid, + struct dev_pagemap *pgmap, + unsigned long nr_pages) +{ + unsigned long pfn, end_pfn = head_pfn + nr_pages; + unsigned int order = pgmap->vmemmap_shift; + + __SetPageHead(head); + for (pfn = head_pfn + 1; pfn < end_pfn; pfn++) { + struct page *page = pfn_to_page(pfn); + + __init_zone_device_page(page, pfn, zone_idx, nid, pgmap); + prep_compound_tail(head, pfn - head_pfn); + set_page_count(page, 0); + + /* + * The first tail page stores compound_mapcount_ptr() and + * compound_order() and the second tail page stores + * compound_pincount_ptr(). Call prep_compound_head() after + * the first and second tail pages have been initialized to + * not have the data overwritten. + */ + if (pfn == head_pfn + 2) + prep_compound_head(head, order); + } +} + void __ref memmap_init_zone_device(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages, @@ -6620,6 +6649,7 @@ void __ref memmap_init_zone_device(struct zone *zone, unsigned long pfn, end_pfn = start_pfn + nr_pages; struct pglist_data *pgdat = zone->zone_pgdat; struct vmem_altmap *altmap = pgmap_altmap(pgmap); + unsigned int pfns_per_compound = pgmap_vmemmap_nr(pgmap); unsigned long zone_idx = zone_idx(zone); unsigned long start = jiffies; int nid = pgdat->node_id; @@ -6637,10 +6667,16 @@ void __ref memmap_init_zone_device(struct zone *zone, nr_pages = end_pfn - start_pfn; } - for (pfn = start_pfn; pfn < end_pfn; pfn++) { + for (pfn = start_pfn; pfn < end_pfn; pfn += pfns_per_compound) { struct page *page = pfn_to_page(pfn); __init_zone_device_page(page, pfn, zone_idx, nid, pgmap); + + if (pfns_per_compound == 1) + continue; + + memmap_init_compound(page, pfn, zone_idx, nid, pgmap, + pfns_per_compound); } pr_info("%s initialised %lu pages in %ums\n", __func__, -- cgit v1.2.3 From 3e9d80a891df3b1a5d77db47fa7fdf33ba71e5cb Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 14 Jan 2022 14:05:04 -0800 Subject: mm,fs: split dump_mapping() out from dump_page() dump_mapping() is a big chunk of dump_page(), and it'd be handy to be able to call it when we don't have a struct page. Split it out and move it to fs/inode.c. Take the opportunity to simplify some of the debug messages a little. Link: https://lkml.kernel.org/r/20211121121056.2870061-1-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: William Kucharski Acked-by: Michal Hocko Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/inode.c | 49 +++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/fs.h | 1 + mm/debug.c | 52 ++-------------------------------------------------- 3 files changed, 52 insertions(+), 50 deletions(-) (limited to 'include/linux') diff --git a/fs/inode.c b/fs/inode.c index 6b80a51129d5..980e7b7a5460 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -526,6 +526,55 @@ void __remove_inode_hash(struct inode *inode) } EXPORT_SYMBOL(__remove_inode_hash); +void dump_mapping(const struct address_space *mapping) +{ + struct inode *host; + const struct address_space_operations *a_ops; + struct hlist_node *dentry_first; + struct dentry *dentry_ptr; + struct dentry dentry; + unsigned long ino; + + /* + * If mapping is an invalid pointer, we don't want to crash + * accessing it, so probe everything depending on it carefully. + */ + if (get_kernel_nofault(host, &mapping->host) || + get_kernel_nofault(a_ops, &mapping->a_ops)) { + pr_warn("invalid mapping:%px\n", mapping); + return; + } + + if (!host) { + pr_warn("aops:%ps\n", a_ops); + return; + } + + if (get_kernel_nofault(dentry_first, &host->i_dentry.first) || + get_kernel_nofault(ino, &host->i_ino)) { + pr_warn("aops:%ps invalid inode:%px\n", a_ops, host); + return; + } + + if (!dentry_first) { + pr_warn("aops:%ps ino:%lx\n", a_ops, ino); + return; + } + + dentry_ptr = container_of(dentry_first, struct dentry, d_u.d_alias); + if (get_kernel_nofault(dentry, dentry_ptr)) { + pr_warn("aops:%ps ino:%lx invalid dentry:%px\n", + a_ops, ino, dentry_ptr); + return; + } + + /* + * if dentry is corrupted, the %pd handler may still crash, + * but it's unlikely that we reach here with a corrupt mapping + */ + pr_warn("aops:%ps ino:%lx dentry name:\"%pd\"\n", a_ops, ino, &dentry); +} + void clear_inode(struct inode *inode) { /* diff --git a/include/linux/fs.h b/include/linux/fs.h index bbf812ce89a8..5315fa68f751 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3152,6 +3152,7 @@ extern void unlock_new_inode(struct inode *); extern void discard_new_inode(struct inode *); extern unsigned int get_next_ino(void); extern void evict_inodes(struct super_block *sb); +void dump_mapping(const struct address_space *); /* * Userspace may rely on the the inode number being non-zero. For example, glibc diff --git a/mm/debug.c b/mm/debug.c index a05a39ff8fe4..bc9ac87f0e08 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -112,56 +112,8 @@ static void __dump_page(struct page *page) type = "ksm "; else if (PageAnon(page)) type = "anon "; - else if (mapping) { - struct inode *host; - const struct address_space_operations *a_ops; - struct hlist_node *dentry_first; - struct dentry *dentry_ptr; - struct dentry dentry; - unsigned long ino; - - /* - * mapping can be invalid pointer and we don't want to crash - * accessing it, so probe everything depending on it carefully - */ - if (get_kernel_nofault(host, &mapping->host) || - get_kernel_nofault(a_ops, &mapping->a_ops)) { - pr_warn("failed to read mapping contents, not a valid kernel address?\n"); - goto out_mapping; - } - - if (!host) { - pr_warn("aops:%ps\n", a_ops); - goto out_mapping; - } - - if (get_kernel_nofault(dentry_first, &host->i_dentry.first) || - get_kernel_nofault(ino, &host->i_ino)) { - pr_warn("aops:%ps with invalid host inode %px\n", - a_ops, host); - goto out_mapping; - } - - if (!dentry_first) { - pr_warn("aops:%ps ino:%lx\n", a_ops, ino); - goto out_mapping; - } - - dentry_ptr = container_of(dentry_first, struct dentry, d_u.d_alias); - if (get_kernel_nofault(dentry, dentry_ptr)) { - pr_warn("aops:%ps ino:%lx with invalid dentry %px\n", - a_ops, ino, dentry_ptr); - } else { - /* - * if dentry is corrupted, the %pd handler may still - * crash, but it's unlikely that we reach here with a - * corrupted struct page - */ - pr_warn("aops:%ps ino:%lx dentry name:\"%pd\"\n", - a_ops, ino, &dentry); - } - } -out_mapping: + else if (mapping) + dump_mapping(mapping); BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS + 1); pr_warn("%sflags: %pGp%s\n", type, &head->flags, -- cgit v1.2.3 From b6bf9abb0aa44e53ffe9c1e6e1d32568f5b25e4a Mon Sep 17 00:00:00 2001 From: Dan Schatzberg Date: Fri, 14 Jan 2022 14:05:35 -0800 Subject: mm/memcg: add oom_group_kill memory event Our container agent wants to know when a container exits if it was OOM killed or not to report to the user. We use memory.oom.group = 1 to ensure that OOM kills within the container's cgroup kill everything. Existing memory.events are insufficient for knowing if this triggered: 1) Our current approach reads memory.events oom_kill and reports the container was killed if the value is non-zero. This is erroneous in some cases where containers create their children cgroups with memory.oom.group=1 as such OOM kills will get counted against the container cgroup's oom_kill counter despite not actually OOM killing the entire container. 2) Reading memory.events.local will fail to identify OOM kills in leaf cgroups (that don't set memory.oom.group) within the container cgroup. This patch adds a new oom_group_kill event when memory.oom.group triggers to allow userspace to cleanly identify when an entire cgroup is oom killed. [schatzberg.dan@gmail.com: changes from Johannes and Chris] Link: https://lkml.kernel.org/r/20211213162511.2492267-1-schatzberg.dan@gmail.com Link: https://lkml.kernel.org/r/20211203162426.3375036-1-schatzberg.dan@gmail.com Signed-off-by: Dan Schatzberg Reviewed-by: Roman Gushchin Acked-by: Johannes Weiner Acked-by: Chris Down Reviewed-by: Shakeel Butt Acked-by: Michal Hocko Cc: Tejun Heo Cc: Zefan Li Cc: Jonathan Corbet Cc: Vladimir Davydov Cc: Matthew Wilcox (Oracle) Cc: Muchun Song Cc: Alex Shi Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/cgroup-v2.rst | 3 +++ include/linux/memcontrol.h | 1 + mm/memcontrol.c | 2 ++ mm/oom_kill.c | 1 + 4 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 2aeb7ae8b393..8269bfa240f4 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1268,6 +1268,9 @@ PAGE_SIZE multiple when read back. The number of processes belonging to this cgroup killed by any kind of OOM killer. + oom_group_kill + The number of times a group OOM has occurred. + memory.events.local Similar to memory.events but the fields in the file are local to the cgroup i.e. not hierarchical. The file modified event diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 0c5c403f4be6..951f24f42147 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -42,6 +42,7 @@ enum memcg_memory_event { MEMCG_MAX, MEMCG_OOM, MEMCG_OOM_KILL, + MEMCG_OOM_GROUP_KILL, MEMCG_SWAP_HIGH, MEMCG_SWAP_MAX, MEMCG_SWAP_FAIL, diff --git a/mm/memcontrol.c b/mm/memcontrol.c index bfe9bdec192b..2d39d58baccf 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6318,6 +6318,8 @@ static void __memory_events_show(struct seq_file *m, atomic_long_t *events) seq_printf(m, "oom %lu\n", atomic_long_read(&events[MEMCG_OOM])); seq_printf(m, "oom_kill %lu\n", atomic_long_read(&events[MEMCG_OOM_KILL])); + seq_printf(m, "oom_group_kill %lu\n", + atomic_long_read(&events[MEMCG_OOM_GROUP_KILL])); } static int memory_events_show(struct seq_file *m, void *v) diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 1ddabefcfb5a..e52ce0b1465d 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -994,6 +994,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message) * If necessary, kill all tasks in the selected memory cgroup. */ if (oom_group) { + memcg_memory_event(oom_group, MEMCG_OOM_GROUP_KILL); mem_cgroup_print_oom_group(oom_group); mem_cgroup_scan_tasks(oom_group, oom_kill_memcg_member, (void *)message); -- cgit v1.2.3 From 4e5aa1f4c2b489bc6f3ab5ca54747b18a847289d Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Fri, 14 Jan 2022 14:05:45 -0800 Subject: memcg: add per-memcg vmalloc stat The kvmalloc* allocation functions can fallback to vmalloc allocations and more often on long running machines. In addition the kernel does have __GFP_ACCOUNT kvmalloc* calls. So, often on long running machines, the memory.stat does not tell the complete picture which type of memory is charged to the memcg. So add a per-memcg vmalloc stat. [shakeelb@google.com: page_memcg() within rcu lock, per Muchun] Link: https://lkml.kernel.org/r/20211222052457.1960701-1-shakeelb@google.com [akpm@linux-foundation.org: remove cast, per Muchun] [shakeelb@google.com: remove area->page[0] checks and move to page by page accounting per Michal] Link: https://lkml.kernel.org/r/20220104222341.3972772-1-shakeelb@google.com Link: https://lkml.kernel.org/r/20211221215336.1922823-1-shakeelb@google.com Signed-off-by: Shakeel Butt Acked-by: Roman Gushchin Reviewed-by: Muchun Song Acked-by: Michal Hocko Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/cgroup-v2.rst | 3 +++ include/linux/memcontrol.h | 21 +++++++++++++++++++++ mm/memcontrol.c | 1 + mm/vmalloc.c | 13 +++++++++++-- 4 files changed, 36 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 8269bfa240f4..4f400b03dddf 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1314,6 +1314,9 @@ PAGE_SIZE multiple when read back. sock (npn) Amount of memory used in network transmission buffers + vmalloc (npn) + Amount of memory used for vmap backed memory. + shmem Amount of cached filesystem data that is swap-backed, such as tmpfs, shm segments, shared anonymous mmap()s diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 951f24f42147..0131e5574c88 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -33,6 +33,7 @@ enum memcg_stat_item { MEMCG_SWAP = NR_VM_NODE_STAT_ITEMS, MEMCG_SOCK, MEMCG_PERCPU_B, + MEMCG_VMALLOC, MEMCG_NR_STAT, }; @@ -992,6 +993,21 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg, local_irq_restore(flags); } +static inline void mod_memcg_page_state(struct page *page, + int idx, int val) +{ + struct mem_cgroup *memcg; + + if (mem_cgroup_disabled()) + return; + + rcu_read_lock(); + memcg = page_memcg(page); + if (memcg) + mod_memcg_state(memcg, idx, val); + rcu_read_unlock(); +} + static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { return READ_ONCE(memcg->vmstats.state[idx]); @@ -1447,6 +1463,11 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg, { } +static inline void mod_memcg_page_state(struct page *page, + int idx, int val) +{ +} + static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { return 0; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 88e1be912aa7..c9ddd02dc5de 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1375,6 +1375,7 @@ static const struct memory_stat memory_stats[] = { { "pagetables", NR_PAGETABLE }, { "percpu", MEMCG_PERCPU_B }, { "sock", MEMCG_SOCK }, + { "vmalloc", MEMCG_VMALLOC }, { "shmem", NR_SHMEM }, { "file_mapped", NR_FILE_MAPPED }, { "file_dirty", NR_FILE_DIRTY }, diff --git a/mm/vmalloc.c b/mm/vmalloc.c index bf3c2fe8f528..80c6de4c425f 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include #include @@ -2623,12 +2624,13 @@ static void __vunmap(const void *addr, int deallocate_pages) if (deallocate_pages) { unsigned int page_order = vm_area_page_order(area); - int i; + int i, step = 1U << page_order; - for (i = 0; i < area->nr_pages; i += 1U << page_order) { + for (i = 0; i < area->nr_pages; i += step) { struct page *page = area->pages[i]; BUG_ON(!page); + mod_memcg_page_state(page, MEMCG_VMALLOC, -step); __free_pages(page, page_order); cond_resched(); } @@ -2955,6 +2957,13 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, page_order, nr_small_pages, area->pages); atomic_long_add(area->nr_pages, &nr_vmalloc_pages); + if (gfp_mask & __GFP_ACCOUNT) { + int i, step = 1U << page_order; + + for (i = 0; i < area->nr_pages; i += step) + mod_memcg_page_state(area->pages[i], MEMCG_VMALLOC, + step); + } /* * If not enough pages were obtained to accomplish an -- cgit v1.2.3 From 9a10064f5625d5572c3626c1516e0bebc6c9fe9b Mon Sep 17 00:00:00 2001 From: Colin Cross Date: Fri, 14 Jan 2022 14:05:59 -0800 Subject: mm: add a field to store names for private anonymous memory In many userspace applications, and especially in VM based applications like Android uses heavily, there are multiple different allocators in use. At a minimum there is libc malloc and the stack, and in many cases there are libc malloc, the stack, direct syscalls to mmap anonymous memory, and multiple VM heaps (one for small objects, one for big objects, etc.). Each of these layers usually has its own tools to inspect its usage; malloc by compiling a debug version, the VM through heap inspection tools, and for direct syscalls there is usually no way to track them. On Android we heavily use a set of tools that use an extended version of the logic covered in Documentation/vm/pagemap.txt to walk all pages mapped in userspace and slice their usage by process, shared (COW) vs. unique mappings, backing, etc. This can account for real physical memory usage even in cases like fork without exec (which Android uses heavily to share as many private COW pages as possible between processes), Kernel SamePage Merging, and clean zero pages. It produces a measurement of the pages that only exist in that process (USS, for unique), and a measurement of the physical memory usage of that process with the cost of shared pages being evenly split between processes that share them (PSS). If all anonymous memory is indistinguishable then figuring out the real physical memory usage (PSS) of each heap requires either a pagemap walking tool that can understand the heap debugging of every layer, or for every layer's heap debugging tools to implement the pagemap walking logic, in which case it is hard to get a consistent view of memory across the whole system. Tracking the information in userspace leads to all sorts of problems. It either needs to be stored inside the process, which means every process has to have an API to export its current heap information upon request, or it has to be stored externally in a filesystem that somebody needs to clean up on crashes. It needs to be readable while the process is still running, so it has to have some sort of synchronization with every layer of userspace. Efficiently tracking the ranges requires reimplementing something like the kernel vma trees, and linking to it from every layer of userspace. It requires more memory, more syscalls, more runtime cost, and more complexity to separately track regions that the kernel is already tracking. This patch adds a field to /proc/pid/maps and /proc/pid/smaps to show a userspace-provided name for anonymous vmas. The names of named anonymous vmas are shown in /proc/pid/maps and /proc/pid/smaps as [anon:]. Userspace can set the name for a region of memory by calling prctl(PR_SET_VMA, PR_SET_VMA_ANON_NAME, start, len, (unsigned long)name) Setting the name to NULL clears it. The name length limit is 80 bytes including NUL-terminator and is checked to contain only printable ascii characters (including space), except '[',']','\','$' and '`'. Ascii strings are being used to have a descriptive identifiers for vmas, which can be understood by the users reading /proc/pid/maps or /proc/pid/smaps. Names can be standardized for a given system and they can include some variable parts such as the name of the allocator or a library, tid of the thread using it, etc. The name is stored in a pointer in the shared union in vm_area_struct that points to a null terminated string. Anonymous vmas with the same name (equivalent strings) and are otherwise mergeable will be merged. The name pointers are not shared between vmas even if they contain the same name. The name pointer is stored in a union with fields that are only used on file-backed mappings, so it does not increase memory usage. CONFIG_ANON_VMA_NAME kernel configuration is introduced to enable this feature. It keeps the feature disabled by default to prevent any additional memory overhead and to avoid confusing procfs parsers on systems which are not ready to support named anonymous vmas. The patch is based on the original patch developed by Colin Cross, more specifically on its latest version [1] posted upstream by Sumit Semwal. It used a userspace pointer to store vma names. In that design, name pointers could be shared between vmas. However during the last upstreaming attempt, Kees Cook raised concerns [2] about this approach and suggested to copy the name into kernel memory space, perform validity checks [3] and store as a string referenced from vm_area_struct. One big concern is about fork() performance which would need to strdup anonymous vma names. Dave Hansen suggested experimenting with worst-case scenario of forking a process with 64k vmas having longest possible names [4]. I ran this experiment on an ARM64 Android device and recorded a worst-case regression of almost 40% when forking such a process. This regression is addressed in the followup patch which replaces the pointer to a name with a refcounted structure that allows sharing the name pointer between vmas of the same name. Instead of duplicating the string during fork() or when splitting a vma it increments the refcount. [1] https://lore.kernel.org/linux-mm/20200901161459.11772-4-sumit.semwal@linaro.org/ [2] https://lore.kernel.org/linux-mm/202009031031.D32EF57ED@keescook/ [3] https://lore.kernel.org/linux-mm/202009031022.3834F692@keescook/ [4] https://lore.kernel.org/linux-mm/5d0358ab-8c47-2f5f-8e43-23b89d6a8e95@intel.com/ Changes for prctl(2) manual page (in the options section): PR_SET_VMA Sets an attribute specified in arg2 for virtual memory areas starting from the address specified in arg3 and spanning the size specified in arg4. arg5 specifies the value of the attribute to be set. Note that assigning an attribute to a virtual memory area might prevent it from being merged with adjacent virtual memory areas due to the difference in that attribute's value. Currently, arg2 must be one of: PR_SET_VMA_ANON_NAME Set a name for anonymous virtual memory areas. arg5 should be a pointer to a null-terminated string containing the name. The name length including null byte cannot exceed 80 bytes. If arg5 is NULL, the name of the appropriate anonymous virtual memory areas will be reset. The name can contain only printable ascii characters (including space), except '[',']','\','$' and '`'. This feature is available only if the kernel is built with the CONFIG_ANON_VMA_NAME option enabled. [surenb@google.com: docs: proc.rst: /proc/PID/maps: fix malformed table] Link: https://lkml.kernel.org/r/20211123185928.2513763-1-surenb@google.com [surenb: rebased over v5.15-rc6, replaced userpointer with a kernel copy, added input sanitization and CONFIG_ANON_VMA_NAME config. The bulk of the work here was done by Colin Cross, therefore, with his permission, keeping him as the author] Link: https://lkml.kernel.org/r/20211019215511.3771969-2-surenb@google.com Signed-off-by: Colin Cross Signed-off-by: Suren Baghdasaryan Reviewed-by: Kees Cook Cc: Stephen Rothwell Cc: Al Viro Cc: Cyrill Gorcunov Cc: Dave Hansen Cc: David Rientjes Cc: "Eric W. Biederman" Cc: Hugh Dickins Cc: Ingo Molnar Cc: Jan Glauber Cc: Johannes Weiner Cc: John Stultz Cc: Mel Gorman Cc: Minchan Kim Cc: Oleg Nesterov Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Rob Landley Cc: "Serge E. Hallyn" Cc: Shaohua Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/proc.rst | 6 +- fs/proc/task_mmu.c | 12 +++- fs/userfaultfd.c | 7 +- include/linux/mm.h | 13 +++- include/linux/mm_types.h | 64 ++++++++++++++++-- include/uapi/linux/prctl.h | 3 + kernel/fork.c | 2 + kernel/sys.c | 63 ++++++++++++++++++ mm/Kconfig | 14 ++++ mm/madvise.c | 129 +++++++++++++++++++++++++++++++++++-- mm/mempolicy.c | 3 +- mm/mlock.c | 2 +- mm/mmap.c | 38 ++++++----- mm/mprotect.c | 2 +- 14 files changed, 324 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst index 8d7f141c6fc7..061744c436d9 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -426,12 +426,14 @@ with the memory region, as the case would be with BSS (uninitialized data). The "pathname" shows the name associated file for this mapping. If the mapping is not associated with a file: - ======= ==================================== + ============= ==================================== [heap] the heap of the program [stack] the stack of the main process [vdso] the "virtual dynamic shared object", the kernel system call handler - ======= ==================================== + [anon:] an anonymous mapping that has been + named by userspace + ============= ==================================== or if empty, the mapping is anonymous. diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index ad667dbc96f5..e6998652fd67 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -308,6 +308,8 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma) name = arch_vma_name(vma); if (!name) { + const char *anon_name; + if (!mm) { name = "[vdso]"; goto done; @@ -319,8 +321,16 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma) goto done; } - if (is_stack(vma)) + if (is_stack(vma)) { name = "[stack]"; + goto done; + } + + anon_name = vma_anon_name(vma); + if (anon_name) { + seq_pad(m, ' '); + seq_printf(m, "[anon:%s]", anon_name); + } } done: diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 22bf14ab2d16..5b2af7b82776 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -877,7 +877,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file) new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), - NULL_VM_UFFD_CTX); + NULL_VM_UFFD_CTX, vma_anon_name(vma)); if (prev) vma = prev; else @@ -1436,7 +1436,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, prev = vma_merge(mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), - ((struct vm_userfaultfd_ctx){ ctx })); + ((struct vm_userfaultfd_ctx){ ctx }), + vma_anon_name(vma)); if (prev) { vma = prev; goto next; @@ -1613,7 +1614,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, prev = vma_merge(mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), - NULL_VM_UFFD_CTX); + NULL_VM_UFFD_CTX, vma_anon_name(vma)); if (prev) { vma = prev; goto next; diff --git a/include/linux/mm.h b/include/linux/mm.h index a7e4a9e7d807..7000442984b9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2658,7 +2658,7 @@ static inline int vma_adjust(struct vm_area_struct *vma, unsigned long start, extern struct vm_area_struct *vma_merge(struct mm_struct *, struct vm_area_struct *prev, unsigned long addr, unsigned long end, unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t, - struct mempolicy *, struct vm_userfaultfd_ctx); + struct mempolicy *, struct vm_userfaultfd_ctx, const char *); extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *); extern int __split_vma(struct mm_struct *, struct vm_area_struct *, unsigned long addr, int new_below); @@ -3391,5 +3391,16 @@ static inline int seal_check_future_write(int seals, struct vm_area_struct *vma) return 0; } +#ifdef CONFIG_ANON_VMA_NAME +int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, + unsigned long len_in, const char *name); +#else +static inline int +madvise_set_anon_name(struct mm_struct *mm, unsigned long start, + unsigned long len_in, const char *name) { + return 0; +} +#endif + #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index c3a6e6209600..799e2ee626b2 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -426,11 +426,19 @@ struct vm_area_struct { /* * For areas with an address space and backing store, * linkage into the address_space->i_mmap interval tree. + * + * For private anonymous mappings, a pointer to a null terminated string + * containing the name given to the vma, or NULL if unnamed. */ - struct { - struct rb_node rb; - unsigned long rb_subtree_last; - } shared; + + union { + struct { + struct rb_node rb; + unsigned long rb_subtree_last; + } shared; + /* Serialized by mmap_sem. */ + char *anon_name; + }; /* * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma @@ -875,4 +883,52 @@ typedef struct { unsigned long val; } swp_entry_t; +#ifdef CONFIG_ANON_VMA_NAME +/* + * mmap_lock should be read-locked when calling vma_anon_name() and while using + * the returned pointer. + */ +extern const char *vma_anon_name(struct vm_area_struct *vma); + +/* + * mmap_lock should be read-locked for orig_vma->vm_mm. + * mmap_lock should be write-locked for new_vma->vm_mm or new_vma should be + * isolated. + */ +extern void dup_vma_anon_name(struct vm_area_struct *orig_vma, + struct vm_area_struct *new_vma); + +/* + * mmap_lock should be write-locked or vma should have been isolated under + * write-locked mmap_lock protection. + */ +extern void free_vma_anon_name(struct vm_area_struct *vma); + +/* mmap_lock should be read-locked */ +static inline bool is_same_vma_anon_name(struct vm_area_struct *vma, + const char *name) +{ + const char *vma_name = vma_anon_name(vma); + + /* either both NULL, or pointers to same string */ + if (vma_name == name) + return true; + + return name && vma_name && !strcmp(name, vma_name); +} +#else /* CONFIG_ANON_VMA_NAME */ +static inline const char *vma_anon_name(struct vm_area_struct *vma) +{ + return NULL; +} +static inline void dup_vma_anon_name(struct vm_area_struct *orig_vma, + struct vm_area_struct *new_vma) {} +static inline void free_vma_anon_name(struct vm_area_struct *vma) {} +static inline bool is_same_vma_anon_name(struct vm_area_struct *vma, + const char *name) +{ + return true; +} +#endif /* CONFIG_ANON_VMA_NAME */ + #endif /* _LINUX_MM_TYPES_H */ diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index bb73e9a0b24f..e998764f0262 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -272,4 +272,7 @@ struct prctl_mm_map { # define PR_SCHED_CORE_SCOPE_THREAD_GROUP 1 # define PR_SCHED_CORE_SCOPE_PROCESS_GROUP 2 +#define PR_SET_VMA 0x53564d41 +# define PR_SET_VMA_ANON_NAME 0 + #endif /* _LINUX_PRCTL_H */ diff --git a/kernel/fork.c b/kernel/fork.c index 3244cc56b697..4cf20b5f2da3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -365,12 +365,14 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) *new = data_race(*orig); INIT_LIST_HEAD(&new->anon_vma_chain); new->vm_next = new->vm_prev = NULL; + dup_vma_anon_name(orig, new); } return new; } void vm_area_free(struct vm_area_struct *vma) { + free_vma_anon_name(vma); kmem_cache_free(vm_area_cachep, vma); } diff --git a/kernel/sys.c b/kernel/sys.c index 8fdac0d90504..2450a9f33cb0 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2261,6 +2261,66 @@ int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which, #define PR_IO_FLUSHER (PF_MEMALLOC_NOIO | PF_LOCAL_THROTTLE) +#ifdef CONFIG_ANON_VMA_NAME + +#define ANON_VMA_NAME_MAX_LEN 80 +#define ANON_VMA_NAME_INVALID_CHARS "\\`$[]" + +static inline bool is_valid_name_char(char ch) +{ + /* printable ascii characters, excluding ANON_VMA_NAME_INVALID_CHARS */ + return ch > 0x1f && ch < 0x7f && + !strchr(ANON_VMA_NAME_INVALID_CHARS, ch); +} + +static int prctl_set_vma(unsigned long opt, unsigned long addr, + unsigned long size, unsigned long arg) +{ + struct mm_struct *mm = current->mm; + const char __user *uname; + char *name, *pch; + int error; + + switch (opt) { + case PR_SET_VMA_ANON_NAME: + uname = (const char __user *)arg; + if (uname) { + name = strndup_user(uname, ANON_VMA_NAME_MAX_LEN); + + if (IS_ERR(name)) + return PTR_ERR(name); + + for (pch = name; *pch != '\0'; pch++) { + if (!is_valid_name_char(*pch)) { + kfree(name); + return -EINVAL; + } + } + } else { + /* Reset the name */ + name = NULL; + } + + mmap_write_lock(mm); + error = madvise_set_anon_name(mm, addr, size, name); + mmap_write_unlock(mm); + kfree(name); + break; + default: + error = -EINVAL; + } + + return error; +} + +#else /* CONFIG_ANON_VMA_NAME */ +static int prctl_set_vma(unsigned long opt, unsigned long start, + unsigned long size, unsigned long arg) +{ + return -EINVAL; +} +#endif /* CONFIG_ANON_VMA_NAME */ + SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5) { @@ -2530,6 +2590,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, error = sched_core_share_pid(arg2, arg3, arg4, arg5); break; #endif + case PR_SET_VMA: + error = prctl_set_vma(arg2, arg3, arg4, arg5); + break; default: error = -EINVAL; break; diff --git a/mm/Kconfig b/mm/Kconfig index 356f4f2c779e..53d7485fc38f 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -900,6 +900,20 @@ config IO_MAPPING config SECRETMEM def_bool ARCH_HAS_SET_DIRECT_MAP && !EMBEDDED +config ANON_VMA_NAME + bool "Anonymous VMA name support" + depends on PROC_FS && ADVISE_SYSCALLS && MMU + + help + Allow naming anonymous virtual memory areas. + + This feature allows assigning names to virtual memory areas. Assigned + names can be later retrieved from /proc/pid/maps and /proc/pid/smaps + and help identifying individual anonymous memory areas. + Assigning a name to anonymous virtual memory area might prevent that + area from being merged with adjacent virtual memory areas due to the + difference in their name. + source "mm/damon/Kconfig" endmenu diff --git a/mm/madvise.c b/mm/madvise.c index 4b9c5509990c..413bbc6e40a0 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -62,19 +63,84 @@ static int madvise_need_mmap_write(int behavior) } } +#ifdef CONFIG_ANON_VMA_NAME +static inline bool has_vma_anon_name(struct vm_area_struct *vma) +{ + return !vma->vm_file && vma->anon_name; +} + +const char *vma_anon_name(struct vm_area_struct *vma) +{ + if (!has_vma_anon_name(vma)) + return NULL; + + mmap_assert_locked(vma->vm_mm); + + return vma->anon_name; +} + +void dup_vma_anon_name(struct vm_area_struct *orig_vma, + struct vm_area_struct *new_vma) +{ + if (!has_vma_anon_name(orig_vma)) + return; + + new_vma->anon_name = kstrdup(orig_vma->anon_name, GFP_KERNEL); +} + +void free_vma_anon_name(struct vm_area_struct *vma) +{ + if (!has_vma_anon_name(vma)) + return; + + kfree(vma->anon_name); + vma->anon_name = NULL; +} + +/* mmap_lock should be write-locked */ +static int replace_vma_anon_name(struct vm_area_struct *vma, const char *name) +{ + if (!name) { + free_vma_anon_name(vma); + return 0; + } + + if (vma->anon_name) { + /* Same name, nothing to do here */ + if (!strcmp(name, vma->anon_name)) + return 0; + + free_vma_anon_name(vma); + } + vma->anon_name = kstrdup(name, GFP_KERNEL); + if (!vma->anon_name) + return -ENOMEM; + + return 0; +} +#else /* CONFIG_ANON_VMA_NAME */ +static int replace_vma_anon_name(struct vm_area_struct *vma, const char *name) +{ + if (name) + return -EINVAL; + + return 0; +} +#endif /* CONFIG_ANON_VMA_NAME */ /* * Update the vm_flags on region of a vma, splitting it or merging it as * necessary. Must be called with mmap_sem held for writing; */ static int madvise_update_vma(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, - unsigned long end, unsigned long new_flags) + unsigned long end, unsigned long new_flags, + const char *name) { struct mm_struct *mm = vma->vm_mm; int error; pgoff_t pgoff; - if (new_flags == vma->vm_flags) { + if (new_flags == vma->vm_flags && is_same_vma_anon_name(vma, name)) { *prev = vma; return 0; } @@ -82,7 +148,7 @@ static int madvise_update_vma(struct vm_area_struct *vma, pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); *prev = vma_merge(mm, *prev, start, end, new_flags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx); + vma->vm_userfaultfd_ctx, name); if (*prev) { vma = *prev; goto success; @@ -111,6 +177,11 @@ success: * vm_flags is protected by the mmap_lock held in write mode. */ vma->vm_flags = new_flags; + if (!vma->vm_file) { + error = replace_vma_anon_name(vma, name); + if (error) + return error; + } return 0; } @@ -938,7 +1009,8 @@ static int madvise_vma_behavior(struct vm_area_struct *vma, break; } - error = madvise_update_vma(vma, prev, start, end, new_flags); + error = madvise_update_vma(vma, prev, start, end, new_flags, + vma_anon_name(vma)); out: /* @@ -1118,6 +1190,55 @@ int madvise_walk_vmas(struct mm_struct *mm, unsigned long start, return unmapped_error; } +#ifdef CONFIG_ANON_VMA_NAME +static int madvise_vma_anon_name(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start, unsigned long end, + unsigned long name) +{ + int error; + + /* Only anonymous mappings can be named */ + if (vma->vm_file) + return -EBADF; + + error = madvise_update_vma(vma, prev, start, end, vma->vm_flags, + (const char *)name); + + /* + * madvise() returns EAGAIN if kernel resources, such as + * slab, are temporarily unavailable. + */ + if (error == -ENOMEM) + error = -EAGAIN; + return error; +} + +int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, + unsigned long len_in, const char *name) +{ + unsigned long end; + unsigned long len; + + if (start & ~PAGE_MASK) + return -EINVAL; + len = (len_in + ~PAGE_MASK) & PAGE_MASK; + + /* Check to see whether len was rounded up from small -ve to zero */ + if (len_in && !len) + return -EINVAL; + + end = start + len; + if (end < start) + return -EINVAL; + + if (end == start) + return 0; + + return madvise_walk_vmas(mm, start, end, (unsigned long)name, + madvise_vma_anon_name); +} +#endif /* CONFIG_ANON_VMA_NAME */ /* * The madvise(2) system call. * diff --git a/mm/mempolicy.c b/mm/mempolicy.c index f6248affaf38..679f47b3a079 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -810,7 +810,8 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, ((vmstart - vma->vm_start) >> PAGE_SHIFT); prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags, vma->anon_vma, vma->vm_file, pgoff, - new_pol, vma->vm_userfaultfd_ctx); + new_pol, vma->vm_userfaultfd_ctx, + vma_anon_name(vma)); if (prev) { vma = prev; next = vma->vm_next; diff --git a/mm/mlock.c b/mm/mlock.c index e263d62ae2d0..8f584eddd305 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -512,7 +512,7 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev, pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); *prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx); + vma->vm_userfaultfd_ctx, vma_anon_name(vma)); if (*prev) { vma = *prev; goto success; diff --git a/mm/mmap.c b/mm/mmap.c index bfb0ea164a90..85edb0011453 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1029,7 +1029,8 @@ again: */ static inline int is_mergeable_vma(struct vm_area_struct *vma, struct file *file, unsigned long vm_flags, - struct vm_userfaultfd_ctx vm_userfaultfd_ctx) + struct vm_userfaultfd_ctx vm_userfaultfd_ctx, + const char *anon_name) { /* * VM_SOFTDIRTY should not prevent from VMA merging, if we @@ -1047,6 +1048,8 @@ static inline int is_mergeable_vma(struct vm_area_struct *vma, return 0; if (!is_mergeable_vm_userfaultfd_ctx(vma, vm_userfaultfd_ctx)) return 0; + if (!is_same_vma_anon_name(vma, anon_name)) + return 0; return 1; } @@ -1079,9 +1082,10 @@ static int can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff, - struct vm_userfaultfd_ctx vm_userfaultfd_ctx) + struct vm_userfaultfd_ctx vm_userfaultfd_ctx, + const char *anon_name) { - if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx) && + if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { if (vma->vm_pgoff == vm_pgoff) return 1; @@ -1100,9 +1104,10 @@ static int can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff, - struct vm_userfaultfd_ctx vm_userfaultfd_ctx) + struct vm_userfaultfd_ctx vm_userfaultfd_ctx, + const char *anon_name) { - if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx) && + if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { pgoff_t vm_pglen; vm_pglen = vma_pages(vma); @@ -1113,9 +1118,9 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, } /* - * Given a mapping request (addr,end,vm_flags,file,pgoff), figure out - * whether that can be merged with its predecessor or its successor. - * Or both (it neatly fills a hole). + * Given a mapping request (addr,end,vm_flags,file,pgoff,anon_name), + * figure out whether that can be merged with its predecessor or its + * successor. Or both (it neatly fills a hole). * * In most cases - when called for mmap, brk or mremap - [addr,end) is * certain not to be mapped by the time vma_merge is called; but when @@ -1160,7 +1165,8 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, unsigned long end, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t pgoff, struct mempolicy *policy, - struct vm_userfaultfd_ctx vm_userfaultfd_ctx) + struct vm_userfaultfd_ctx vm_userfaultfd_ctx, + const char *anon_name) { pgoff_t pglen = (end - addr) >> PAGE_SHIFT; struct vm_area_struct *area, *next; @@ -1190,7 +1196,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, mpol_equal(vma_policy(prev), policy) && can_vma_merge_after(prev, vm_flags, anon_vma, file, pgoff, - vm_userfaultfd_ctx)) { + vm_userfaultfd_ctx, anon_name)) { /* * OK, it can. Can we now merge in the successor as well? */ @@ -1199,7 +1205,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, can_vma_merge_before(next, vm_flags, anon_vma, file, pgoff+pglen, - vm_userfaultfd_ctx) && + vm_userfaultfd_ctx, anon_name) && is_mergeable_anon_vma(prev->anon_vma, next->anon_vma, NULL)) { /* cases 1, 6 */ @@ -1222,7 +1228,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, mpol_equal(policy, vma_policy(next)) && can_vma_merge_before(next, vm_flags, anon_vma, file, pgoff+pglen, - vm_userfaultfd_ctx)) { + vm_userfaultfd_ctx, anon_name)) { if (prev && addr < prev->vm_end) /* case 4 */ err = __vma_adjust(prev, prev->vm_start, addr, prev->vm_pgoff, NULL, next); @@ -1754,7 +1760,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, * Can we just expand an old mapping? */ vma = vma_merge(mm, prev, addr, addr + len, vm_flags, - NULL, file, pgoff, NULL, NULL_VM_UFFD_CTX); + NULL, file, pgoff, NULL, NULL_VM_UFFD_CTX, NULL); if (vma) goto out; @@ -1803,7 +1809,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, */ if (unlikely(vm_flags != vma->vm_flags && prev)) { merge = vma_merge(mm, prev, vma->vm_start, vma->vm_end, vma->vm_flags, - NULL, vma->vm_file, vma->vm_pgoff, NULL, NULL_VM_UFFD_CTX); + NULL, vma->vm_file, vma->vm_pgoff, NULL, NULL_VM_UFFD_CTX, NULL); if (merge) { /* ->mmap() can change vma->vm_file and fput the original file. So * fput the vma->vm_file here or we would add an extra fput for file @@ -3056,7 +3062,7 @@ static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long fla /* Can we just expand an old private anonymous mapping? */ vma = vma_merge(mm, prev, addr, addr + len, flags, - NULL, NULL, pgoff, NULL, NULL_VM_UFFD_CTX); + NULL, NULL, pgoff, NULL, NULL_VM_UFFD_CTX, NULL); if (vma) goto out; @@ -3249,7 +3255,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, return NULL; /* should never get here */ new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx); + vma->vm_userfaultfd_ctx, vma_anon_name(vma)); if (new_vma) { /* * Source vma may have been merged into new_vma diff --git a/mm/mprotect.c b/mm/mprotect.c index e552f5e0ccbd..0138dfcdb1d8 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -464,7 +464,7 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); *pprev = vma_merge(mm, *pprev, start, end, newflags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx); + vma->vm_userfaultfd_ctx, vma_anon_name(vma)); if (*pprev) { vma = *pprev; VM_WARN_ON((vma->vm_flags ^ newflags) & ~VM_SOFTDIRTY); -- cgit v1.2.3 From 78db3412833dc9c479cd17412035f216cfd01a29 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Fri, 14 Jan 2022 14:06:03 -0800 Subject: mm: add anonymous vma name refcounting While forking a process with high number (64K) of named anonymous vmas the overhead caused by strdup() is noticeable. Experiments with ARM64 Android device show up to 40% performance regression when forking a process with 64k unpopulated anonymous vmas using the max name lengths vs the same process with the same number of anonymous vmas having no name. Introduce anon_vma_name refcounted structure to avoid the overhead of copying vma names during fork() and when splitting named anonymous vmas. When a vma is duplicated, instead of copying the name we increment the refcount of this structure. Multiple vmas can point to the same anon_vma_name as long as they increment the refcount. The name member of anon_vma_name structure is assigned at structure allocation time and is never changed. If vma name changes then the refcount of the original structure is dropped, a new anon_vma_name structure is allocated to hold the new name and the vma pointer is updated to point to the new structure. With this approach the fork() performance regressions is reduced 3-4x times and with usecases using more reasonable number of VMAs (a few thousand) the regressions is not measurable. Link: https://lkml.kernel.org/r/20211019215511.3771969-3-surenb@google.com Signed-off-by: Suren Baghdasaryan Reviewed-by: Kees Cook Cc: Al Viro Cc: Colin Cross Cc: Cyrill Gorcunov Cc: Dave Hansen Cc: David Rientjes Cc: "Eric W. Biederman" Cc: Hugh Dickins Cc: Ingo Molnar Cc: Jan Glauber Cc: Johannes Weiner Cc: John Stultz Cc: Mel Gorman Cc: Minchan Kim Cc: Oleg Nesterov Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Rob Landley Cc: "Serge E. Hallyn" Cc: Shaohua Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 9 ++++++++- mm/madvise.c | 42 ++++++++++++++++++++++++++++++++++++------ 2 files changed, 44 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 799e2ee626b2..449b6eafc695 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -5,6 +5,7 @@ #include #include +#include #include #include #include @@ -386,6 +387,12 @@ struct vm_userfaultfd_ctx { struct vm_userfaultfd_ctx {}; #endif /* CONFIG_USERFAULTFD */ +struct anon_vma_name { + struct kref kref; + /* The name needs to be at the end because it is dynamically sized. */ + char name[]; +}; + /* * This struct describes a virtual memory area. There is one of these * per VM-area/task. A VM area is any part of the process virtual memory @@ -437,7 +444,7 @@ struct vm_area_struct { unsigned long rb_subtree_last; } shared; /* Serialized by mmap_sem. */ - char *anon_name; + struct anon_vma_name *anon_name; }; /* diff --git a/mm/madvise.c b/mm/madvise.c index 413bbc6e40a0..c63aacbbfa78 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -64,6 +64,29 @@ static int madvise_need_mmap_write(int behavior) } #ifdef CONFIG_ANON_VMA_NAME +static struct anon_vma_name *anon_vma_name_alloc(const char *name) +{ + struct anon_vma_name *anon_name; + size_t count; + + /* Add 1 for NUL terminator at the end of the anon_name->name */ + count = strlen(name) + 1; + anon_name = kmalloc(struct_size(anon_name, name, count), GFP_KERNEL); + if (anon_name) { + kref_init(&anon_name->kref); + memcpy(anon_name->name, name, count); + } + + return anon_name; +} + +static void vma_anon_name_free(struct kref *kref) +{ + struct anon_vma_name *anon_name = + container_of(kref, struct anon_vma_name, kref); + kfree(anon_name); +} + static inline bool has_vma_anon_name(struct vm_area_struct *vma) { return !vma->vm_file && vma->anon_name; @@ -76,7 +99,7 @@ const char *vma_anon_name(struct vm_area_struct *vma) mmap_assert_locked(vma->vm_mm); - return vma->anon_name; + return vma->anon_name->name; } void dup_vma_anon_name(struct vm_area_struct *orig_vma, @@ -85,34 +108,41 @@ void dup_vma_anon_name(struct vm_area_struct *orig_vma, if (!has_vma_anon_name(orig_vma)) return; - new_vma->anon_name = kstrdup(orig_vma->anon_name, GFP_KERNEL); + kref_get(&orig_vma->anon_name->kref); + new_vma->anon_name = orig_vma->anon_name; } void free_vma_anon_name(struct vm_area_struct *vma) { + struct anon_vma_name *anon_name; + if (!has_vma_anon_name(vma)) return; - kfree(vma->anon_name); + anon_name = vma->anon_name; vma->anon_name = NULL; + kref_put(&anon_name->kref, vma_anon_name_free); } /* mmap_lock should be write-locked */ static int replace_vma_anon_name(struct vm_area_struct *vma, const char *name) { + const char *anon_name; + if (!name) { free_vma_anon_name(vma); return 0; } - if (vma->anon_name) { + anon_name = vma_anon_name(vma); + if (anon_name) { /* Same name, nothing to do here */ - if (!strcmp(name, vma->anon_name)) + if (!strcmp(name, anon_name)) return 0; free_vma_anon_name(vma); } - vma->anon_name = kstrdup(name, GFP_KERNEL); + vma->anon_name = anon_vma_name_alloc(name); if (!vma->anon_name) return -ENOMEM; -- cgit v1.2.3 From 17fca131cee21724ee953a17c185c14e9533af5b Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 14 Jan 2022 14:06:07 -0800 Subject: mm: move anon_vma declarations to linux/mm_inline.h The patch to add anonymous vma names causes a build failure in some configurations: include/linux/mm_types.h: In function 'is_same_vma_anon_name': include/linux/mm_types.h:924:37: error: implicit declaration of function 'strcmp' [-Werror=implicit-function-declaration] 924 | return name && vma_name && !strcmp(name, vma_name); | ^~~~~~ include/linux/mm_types.h:22:1: note: 'strcmp' is defined in header ''; did you forget to '#include '? This should not really be part of linux/mm_types.h in the first place, as that header is meant to only contain structure defintions and need a minimum set of indirect includes itself. While the header clearly includes more than it should at this point, let's not make it worse by including string.h as well, which would pull in the expensive (compile-speed wise) fortify-string logic. Move the new functions into a separate header that only needs to be included in a couple of locations. Link: https://lkml.kernel.org/r/20211207125710.2503446-1-arnd@kernel.org Fixes: "mm: add a field to store names for private anonymous memory" Signed-off-by: Arnd Bergmann Cc: Al Viro Cc: Colin Cross Cc: Eric Biederman Cc: Kees Cook Cc: Matthew Wilcox (Oracle) Cc: Peter Xu Cc: Peter Zijlstra (Intel) Cc: Stephen Rothwell Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Yu Zhao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 1 + fs/userfaultfd.c | 1 + include/linux/mm_inline.h | 50 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/mm_types.h | 48 --------------------------------------------- kernel/fork.c | 1 + mm/madvise.c | 1 + mm/mmap.c | 1 + 7 files changed, 55 insertions(+), 48 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index e6998652fd67..18f8c3acbb85 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include #include +#include #include #include #include diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 5b2af7b82776..e26b10132d47 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index e2ec68b0515c..47d96d2647ca 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -4,6 +4,7 @@ #include #include +#include /** * folio_is_file_lru - Should the folio be on a file LRU or anon LRU? @@ -135,4 +136,53 @@ static __always_inline void del_page_from_lru_list(struct page *page, { lruvec_del_folio(lruvec, page_folio(page)); } + +#ifdef CONFIG_ANON_VMA_NAME +/* + * mmap_lock should be read-locked when calling vma_anon_name() and while using + * the returned pointer. + */ +extern const char *vma_anon_name(struct vm_area_struct *vma); + +/* + * mmap_lock should be read-locked for orig_vma->vm_mm. + * mmap_lock should be write-locked for new_vma->vm_mm or new_vma should be + * isolated. + */ +extern void dup_vma_anon_name(struct vm_area_struct *orig_vma, + struct vm_area_struct *new_vma); + +/* + * mmap_lock should be write-locked or vma should have been isolated under + * write-locked mmap_lock protection. + */ +extern void free_vma_anon_name(struct vm_area_struct *vma); + +/* mmap_lock should be read-locked */ +static inline bool is_same_vma_anon_name(struct vm_area_struct *vma, + const char *name) +{ + const char *vma_name = vma_anon_name(vma); + + /* either both NULL, or pointers to same string */ + if (vma_name == name) + return true; + + return name && vma_name && !strcmp(name, vma_name); +} +#else /* CONFIG_ANON_VMA_NAME */ +static inline const char *vma_anon_name(struct vm_area_struct *vma) +{ + return NULL; +} +static inline void dup_vma_anon_name(struct vm_area_struct *orig_vma, + struct vm_area_struct *new_vma) {} +static inline void free_vma_anon_name(struct vm_area_struct *vma) {} +static inline bool is_same_vma_anon_name(struct vm_area_struct *vma, + const char *name) +{ + return true; +} +#endif /* CONFIG_ANON_VMA_NAME */ + #endif diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 449b6eafc695..4d5fb84eed5e 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -890,52 +890,4 @@ typedef struct { unsigned long val; } swp_entry_t; -#ifdef CONFIG_ANON_VMA_NAME -/* - * mmap_lock should be read-locked when calling vma_anon_name() and while using - * the returned pointer. - */ -extern const char *vma_anon_name(struct vm_area_struct *vma); - -/* - * mmap_lock should be read-locked for orig_vma->vm_mm. - * mmap_lock should be write-locked for new_vma->vm_mm or new_vma should be - * isolated. - */ -extern void dup_vma_anon_name(struct vm_area_struct *orig_vma, - struct vm_area_struct *new_vma); - -/* - * mmap_lock should be write-locked or vma should have been isolated under - * write-locked mmap_lock protection. - */ -extern void free_vma_anon_name(struct vm_area_struct *vma); - -/* mmap_lock should be read-locked */ -static inline bool is_same_vma_anon_name(struct vm_area_struct *vma, - const char *name) -{ - const char *vma_name = vma_anon_name(vma); - - /* either both NULL, or pointers to same string */ - if (vma_name == name) - return true; - - return name && vma_name && !strcmp(name, vma_name); -} -#else /* CONFIG_ANON_VMA_NAME */ -static inline const char *vma_anon_name(struct vm_area_struct *vma) -{ - return NULL; -} -static inline void dup_vma_anon_name(struct vm_area_struct *orig_vma, - struct vm_area_struct *new_vma) {} -static inline void free_vma_anon_name(struct vm_area_struct *vma) {} -static inline bool is_same_vma_anon_name(struct vm_area_struct *vma, - const char *name) -{ - return true; -} -#endif /* CONFIG_ANON_VMA_NAME */ - #endif /* _LINUX_MM_TYPES_H */ diff --git a/kernel/fork.c b/kernel/fork.c index 4cf20b5f2da3..75737e566441 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include #include diff --git a/mm/madvise.c b/mm/madvise.c index c63aacbbfa78..5604064df464 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include diff --git a/mm/mmap.c b/mm/mmap.c index 85edb0011453..77733b113c40 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3 From 36090def7bad06a6346f86a7cfdbfda2d138cb64 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 14 Jan 2022 14:06:10 -0800 Subject: mm: move tlb_flush_pending inline helpers to mm_inline.h linux/mm_types.h should only define structure definitions, to make it cheap to include elsewhere. The atomic_t helper function definitions are particularly large, so it's better to move the helpers using those into the existing linux/mm_inline.h and only include that where needed. As a follow-up, we may want to go through all the indirect includes in mm_types.h and reduce them as much as possible. Link: https://lkml.kernel.org/r/20211207125710.2503446-2-arnd@kernel.org Signed-off-by: Arnd Bergmann Cc: Al Viro Cc: Stephen Rothwell Cc: Suren Baghdasaryan Cc: Colin Cross Cc: Kees Cook Cc: Peter Xu Cc: Peter Zijlstra (Intel) Cc: Yu Zhao Cc: Vlastimil Babka Cc: Matthew Wilcox (Oracle) Cc: Eric Biederman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/include/asm/pgtable.h | 2 +- include/linux/mm.h | 45 -------------- include/linux/mm_inline.h | 86 +++++++++++++++++++++++++++ include/linux/mm_types.h | 129 ++++++++++++++--------------------------- mm/ksm.c | 1 + mm/mapping_dirty_helpers.c | 1 + mm/memory.c | 1 + mm/mmu_gather.c | 1 + mm/pgtable-generic.c | 1 + 9 files changed, 137 insertions(+), 130 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 448cd01eb3ec..5196958aa6ac 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -752,7 +752,7 @@ static inline bool pte_accessible(struct mm_struct *mm, pte_t a) return true; if ((pte_flags(a) & _PAGE_PROTNONE) && - mm_tlb_flush_pending(mm)) + atomic_read(&mm->tlb_flush_pending)) return true; return false; diff --git a/include/linux/mm.h b/include/linux/mm.h index 7000442984b9..c17e5cfc1e47 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -424,51 +424,6 @@ extern unsigned int kobjsize(const void *objp); */ extern pgprot_t protection_map[16]; -/** - * enum fault_flag - Fault flag definitions. - * @FAULT_FLAG_WRITE: Fault was a write fault. - * @FAULT_FLAG_MKWRITE: Fault was mkwrite of existing PTE. - * @FAULT_FLAG_ALLOW_RETRY: Allow to retry the fault if blocked. - * @FAULT_FLAG_RETRY_NOWAIT: Don't drop mmap_lock and wait when retrying. - * @FAULT_FLAG_KILLABLE: The fault task is in SIGKILL killable region. - * @FAULT_FLAG_TRIED: The fault has been tried once. - * @FAULT_FLAG_USER: The fault originated in userspace. - * @FAULT_FLAG_REMOTE: The fault is not for current task/mm. - * @FAULT_FLAG_INSTRUCTION: The fault was during an instruction fetch. - * @FAULT_FLAG_INTERRUPTIBLE: The fault can be interrupted by non-fatal signals. - * - * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify - * whether we would allow page faults to retry by specifying these two - * fault flags correctly. Currently there can be three legal combinations: - * - * (a) ALLOW_RETRY and !TRIED: this means the page fault allows retry, and - * this is the first try - * - * (b) ALLOW_RETRY and TRIED: this means the page fault allows retry, and - * we've already tried at least once - * - * (c) !ALLOW_RETRY and !TRIED: this means the page fault does not allow retry - * - * The unlisted combination (!ALLOW_RETRY && TRIED) is illegal and should never - * be used. Note that page faults can be allowed to retry for multiple times, - * in which case we'll have an initial fault with flags (a) then later on - * continuous faults with flags (b). We should always try to detect pending - * signals before a retry to make sure the continuous page faults can still be - * interrupted if necessary. - */ -enum fault_flag { - FAULT_FLAG_WRITE = 1 << 0, - FAULT_FLAG_MKWRITE = 1 << 1, - FAULT_FLAG_ALLOW_RETRY = 1 << 2, - FAULT_FLAG_RETRY_NOWAIT = 1 << 3, - FAULT_FLAG_KILLABLE = 1 << 4, - FAULT_FLAG_TRIED = 1 << 5, - FAULT_FLAG_USER = 1 << 6, - FAULT_FLAG_REMOTE = 1 << 7, - FAULT_FLAG_INSTRUCTION = 1 << 8, - FAULT_FLAG_INTERRUPTIBLE = 1 << 9, -}; - /* * The default fault flags that should be used by most of the * arch-specific page fault handlers. diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 47d96d2647ca..b725839dfe71 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -2,6 +2,7 @@ #ifndef LINUX_MM_INLINE_H #define LINUX_MM_INLINE_H +#include #include #include #include @@ -185,4 +186,89 @@ static inline bool is_same_vma_anon_name(struct vm_area_struct *vma, } #endif /* CONFIG_ANON_VMA_NAME */ +static inline void init_tlb_flush_pending(struct mm_struct *mm) +{ + atomic_set(&mm->tlb_flush_pending, 0); +} + +static inline void inc_tlb_flush_pending(struct mm_struct *mm) +{ + atomic_inc(&mm->tlb_flush_pending); + /* + * The only time this value is relevant is when there are indeed pages + * to flush. And we'll only flush pages after changing them, which + * requires the PTL. + * + * So the ordering here is: + * + * atomic_inc(&mm->tlb_flush_pending); + * spin_lock(&ptl); + * ... + * set_pte_at(); + * spin_unlock(&ptl); + * + * spin_lock(&ptl) + * mm_tlb_flush_pending(); + * .... + * spin_unlock(&ptl); + * + * flush_tlb_range(); + * atomic_dec(&mm->tlb_flush_pending); + * + * Where the increment if constrained by the PTL unlock, it thus + * ensures that the increment is visible if the PTE modification is + * visible. After all, if there is no PTE modification, nobody cares + * about TLB flushes either. + * + * This very much relies on users (mm_tlb_flush_pending() and + * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and + * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc + * locks (PPC) the unlock of one doesn't order against the lock of + * another PTL. + * + * The decrement is ordered by the flush_tlb_range(), such that + * mm_tlb_flush_pending() will not return false unless all flushes have + * completed. + */ +} + +static inline void dec_tlb_flush_pending(struct mm_struct *mm) +{ + /* + * See inc_tlb_flush_pending(). + * + * This cannot be smp_mb__before_atomic() because smp_mb() simply does + * not order against TLB invalidate completion, which is what we need. + * + * Therefore we must rely on tlb_flush_*() to guarantee order. + */ + atomic_dec(&mm->tlb_flush_pending); +} + +static inline bool mm_tlb_flush_pending(struct mm_struct *mm) +{ + /* + * Must be called after having acquired the PTL; orders against that + * PTLs release and therefore ensures that if we observe the modified + * PTE we must also observe the increment from inc_tlb_flush_pending(). + * + * That is, it only guarantees to return true if there is a flush + * pending for _this_ PTL. + */ + return atomic_read(&mm->tlb_flush_pending); +} + +static inline bool mm_tlb_flush_nested(struct mm_struct *mm) +{ + /* + * Similar to mm_tlb_flush_pending(), we must have acquired the PTL + * for which there is a TLB flush pending in order to guarantee + * we've seen both that PTE modification and the increment. + * + * (no requirement on actually still holding the PTL, that is irrelevant) + */ + return atomic_read(&mm->tlb_flush_pending) > 1; +} + + #endif diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 4d5fb84eed5e..6a89f128c990 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -692,90 +692,6 @@ extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm); extern void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm); extern void tlb_finish_mmu(struct mmu_gather *tlb); -static inline void init_tlb_flush_pending(struct mm_struct *mm) -{ - atomic_set(&mm->tlb_flush_pending, 0); -} - -static inline void inc_tlb_flush_pending(struct mm_struct *mm) -{ - atomic_inc(&mm->tlb_flush_pending); - /* - * The only time this value is relevant is when there are indeed pages - * to flush. And we'll only flush pages after changing them, which - * requires the PTL. - * - * So the ordering here is: - * - * atomic_inc(&mm->tlb_flush_pending); - * spin_lock(&ptl); - * ... - * set_pte_at(); - * spin_unlock(&ptl); - * - * spin_lock(&ptl) - * mm_tlb_flush_pending(); - * .... - * spin_unlock(&ptl); - * - * flush_tlb_range(); - * atomic_dec(&mm->tlb_flush_pending); - * - * Where the increment if constrained by the PTL unlock, it thus - * ensures that the increment is visible if the PTE modification is - * visible. After all, if there is no PTE modification, nobody cares - * about TLB flushes either. - * - * This very much relies on users (mm_tlb_flush_pending() and - * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and - * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc - * locks (PPC) the unlock of one doesn't order against the lock of - * another PTL. - * - * The decrement is ordered by the flush_tlb_range(), such that - * mm_tlb_flush_pending() will not return false unless all flushes have - * completed. - */ -} - -static inline void dec_tlb_flush_pending(struct mm_struct *mm) -{ - /* - * See inc_tlb_flush_pending(). - * - * This cannot be smp_mb__before_atomic() because smp_mb() simply does - * not order against TLB invalidate completion, which is what we need. - * - * Therefore we must rely on tlb_flush_*() to guarantee order. - */ - atomic_dec(&mm->tlb_flush_pending); -} - -static inline bool mm_tlb_flush_pending(struct mm_struct *mm) -{ - /* - * Must be called after having acquired the PTL; orders against that - * PTLs release and therefore ensures that if we observe the modified - * PTE we must also observe the increment from inc_tlb_flush_pending(). - * - * That is, it only guarantees to return true if there is a flush - * pending for _this_ PTL. - */ - return atomic_read(&mm->tlb_flush_pending); -} - -static inline bool mm_tlb_flush_nested(struct mm_struct *mm) -{ - /* - * Similar to mm_tlb_flush_pending(), we must have acquired the PTL - * for which there is a TLB flush pending in order to guarantee - * we've seen both that PTE modification and the increment. - * - * (no requirement on actually still holding the PTL, that is irrelevant) - */ - return atomic_read(&mm->tlb_flush_pending) > 1; -} - struct vm_fault; /** @@ -890,4 +806,49 @@ typedef struct { unsigned long val; } swp_entry_t; +/** + * enum fault_flag - Fault flag definitions. + * @FAULT_FLAG_WRITE: Fault was a write fault. + * @FAULT_FLAG_MKWRITE: Fault was mkwrite of existing PTE. + * @FAULT_FLAG_ALLOW_RETRY: Allow to retry the fault if blocked. + * @FAULT_FLAG_RETRY_NOWAIT: Don't drop mmap_lock and wait when retrying. + * @FAULT_FLAG_KILLABLE: The fault task is in SIGKILL killable region. + * @FAULT_FLAG_TRIED: The fault has been tried once. + * @FAULT_FLAG_USER: The fault originated in userspace. + * @FAULT_FLAG_REMOTE: The fault is not for current task/mm. + * @FAULT_FLAG_INSTRUCTION: The fault was during an instruction fetch. + * @FAULT_FLAG_INTERRUPTIBLE: The fault can be interrupted by non-fatal signals. + * + * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify + * whether we would allow page faults to retry by specifying these two + * fault flags correctly. Currently there can be three legal combinations: + * + * (a) ALLOW_RETRY and !TRIED: this means the page fault allows retry, and + * this is the first try + * + * (b) ALLOW_RETRY and TRIED: this means the page fault allows retry, and + * we've already tried at least once + * + * (c) !ALLOW_RETRY and !TRIED: this means the page fault does not allow retry + * + * The unlisted combination (!ALLOW_RETRY && TRIED) is illegal and should never + * be used. Note that page faults can be allowed to retry for multiple times, + * in which case we'll have an initial fault with flags (a) then later on + * continuous faults with flags (b). We should always try to detect pending + * signals before a retry to make sure the continuous page faults can still be + * interrupted if necessary. + */ +enum fault_flag { + FAULT_FLAG_WRITE = 1 << 0, + FAULT_FLAG_MKWRITE = 1 << 1, + FAULT_FLAG_ALLOW_RETRY = 1 << 2, + FAULT_FLAG_RETRY_NOWAIT = 1 << 3, + FAULT_FLAG_KILLABLE = 1 << 4, + FAULT_FLAG_TRIED = 1 << 5, + FAULT_FLAG_USER = 1 << 6, + FAULT_FLAG_REMOTE = 1 << 7, + FAULT_FLAG_INSTRUCTION = 1 << 8, + FAULT_FLAG_INTERRUPTIBLE = 1 << 9, +}; + #endif /* _LINUX_MM_TYPES_H */ diff --git a/mm/ksm.c b/mm/ksm.c index 0662093237e4..f34476ac0a41 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -15,6 +15,7 @@ #include #include +#include #include #include #include diff --git a/mm/mapping_dirty_helpers.c b/mm/mapping_dirty_helpers.c index ea734f248fce..1b0ab8fcfd8b 100644 --- a/mm/mapping_dirty_helpers.c +++ b/mm/mapping_dirty_helpers.c @@ -3,6 +3,7 @@ #include #include #include +#include #include #include diff --git a/mm/memory.c b/mm/memory.c index 8f1de811a1dc..bc80d4effac9 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -41,6 +41,7 @@ #include #include +#include #include #include #include diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index 1b9837419bf9..afb7185ffdc4 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -3,6 +3,7 @@ #include #include #include +#include #include #include #include diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index 4e640baf9794..6523fda274e5 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -10,6 +10,7 @@ #include #include #include +#include #include /* -- cgit v1.2.3 From cc6dcfee72509868271d42919a3c1081b6b0dc7e Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Fri, 14 Jan 2022 14:06:18 -0800 Subject: mm: document locking restrictions for vm_operations_struct::close Add comments for vm_operations_struct::close documenting locking requirements for this callback and its callers. Link: https://lkml.kernel.org/r/20211209191325.3069345-2-surenb@google.com Signed-off-by: Suren Baghdasaryan Acked-by: Michal Hocko Cc: Andrea Arcangeli Cc: Andy Lutomirski Cc: Christian Brauner Cc: Christian Brauner Cc: Christoph Hellwig Cc: David Hildenbrand Cc: David Rientjes Cc: Florian Weimer Cc: Jan Engelhardt Cc: Jann Horn Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Matthew Wilcox Cc: Minchan Kim Cc: Oleg Nesterov Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Tim Murray Cc: Jason Gunthorpe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index c17e5cfc1e47..4d7245e6802a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -532,6 +532,10 @@ enum page_entry_size { */ struct vm_operations_struct { void (*open)(struct vm_area_struct * area); + /** + * @close: Called when the VMA is being removed from the MM. + * Context: User context. May sleep. Caller holds mmap_lock. + */ void (*close)(struct vm_area_struct * area); /* Called any time before splitting to check if it's allowed */ int (*may_split)(struct vm_area_struct *area, unsigned long addr); -- cgit v1.2.3 From 08d5b29eac7dd5e6c79b66d390ecbb9219e05931 Mon Sep 17 00:00:00 2001 From: Pasha Tatashin Date: Fri, 14 Jan 2022 14:06:33 -0800 Subject: mm: ptep_clear() page table helper We have ptep_get_and_clear() and ptep_get_and_clear_full() helpers to clear PTE from user page tables, but there is no variant for simple clear of a present PTE from user page tables without using a low level pte_clear() which can be either native or para-virtualised. Add a new ptep_clear() that can be used in common code to clear PTEs from page table. We will need this call later in order to add a hook for page table check. Link: https://lkml.kernel.org/r/20211221154650.1047963-3-pasha.tatashin@soleen.com Signed-off-by: Pasha Tatashin Cc: Aneesh Kumar K.V Cc: Dave Hansen Cc: David Rientjes Cc: Frederic Weisbecker Cc: Greg Thelen Cc: "H. Peter Anvin" Cc: Hugh Dickins Cc: Ingo Molnar Cc: Jiri Slaby Cc: Jonathan Corbet Cc: Kees Cook Cc: Masahiro Yamada Cc: Mike Rapoport Cc: Muchun Song Cc: Paul Turner Cc: Peter Zijlstra Cc: Sami Tolvanen Cc: Thomas Gleixner Cc: Wei Xu Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/vm/arch_pgtable_helpers.rst | 6 ++++-- include/linux/pgtable.h | 8 ++++++++ mm/debug_vm_pgtable.c | 2 +- mm/khugepaged.c | 12 ++---------- 4 files changed, 15 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/Documentation/vm/arch_pgtable_helpers.rst b/Documentation/vm/arch_pgtable_helpers.rst index b3166c33db39..f8b225fc9190 100644 --- a/Documentation/vm/arch_pgtable_helpers.rst +++ b/Documentation/vm/arch_pgtable_helpers.rst @@ -66,9 +66,11 @@ PTE Page Table Helpers +---------------------------+--------------------------------------------------+ | pte_mknotpresent | Invalidates a mapped PTE | +---------------------------+--------------------------------------------------+ -| ptep_get_and_clear | Clears a PTE | +| ptep_clear | Clears a PTE | +---------------------------+--------------------------------------------------+ -| ptep_get_and_clear_full | Clears a PTE | +| ptep_get_and_clear | Clears and returns PTE | ++---------------------------+--------------------------------------------------+ +| ptep_get_and_clear_full | Clears and returns PTE (batched PTE unmap) | +---------------------------+--------------------------------------------------+ | ptep_test_and_clear_young | Clears young from a PTE | +---------------------------+--------------------------------------------------+ diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index e24d2c992b11..bc8713a76e03 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -258,6 +258,14 @@ static inline int pmdp_clear_flush_young(struct vm_area_struct *vma, #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif +#ifndef __HAVE_ARCH_PTEP_CLEAR +static inline void ptep_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + pte_clear(mm, addr, ptep); +} +#endif + #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long address, diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c index 2a2b24e87877..a7ac97c76762 100644 --- a/mm/debug_vm_pgtable.c +++ b/mm/debug_vm_pgtable.c @@ -652,7 +652,7 @@ static void __init pte_clear_tests(struct pgtable_debug_args *args) set_pte_at(args->mm, args->vaddr, args->ptep, pte); flush_dcache_page(page); barrier(); - pte_clear(args->mm, args->vaddr, args->ptep); + ptep_clear(args->mm, args->vaddr, args->ptep); pte = ptep_get(args->ptep); WARN_ON(!pte_none(pte)); } diff --git a/mm/khugepaged.c b/mm/khugepaged.c index e99101162f1a..9d40dd8890e5 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -756,11 +756,7 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page, * ptl mostly unnecessary. */ spin_lock(ptl); - /* - * paravirt calls inside pte_clear here are - * superfluous. - */ - pte_clear(vma->vm_mm, address, _pte); + ptep_clear(vma->vm_mm, address, _pte); spin_unlock(ptl); } } else { @@ -774,11 +770,7 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page, * inside page_remove_rmap(). */ spin_lock(ptl); - /* - * paravirt calls inside pte_clear here are - * superfluous. - */ - pte_clear(vma->vm_mm, address, _pte); + ptep_clear(vma->vm_mm, address, _pte); page_remove_rmap(src_page, false); spin_unlock(ptl); free_page_and_swap_cache(src_page); -- cgit v1.2.3 From df4e817b710809425d899340dbfa8504a3ca4ba5 Mon Sep 17 00:00:00 2001 From: Pasha Tatashin Date: Fri, 14 Jan 2022 14:06:37 -0800 Subject: mm: page table check Check user page table entries at the time they are added and removed. Allows to synchronously catch memory corruption issues related to double mapping. When a pte for an anonymous page is added into page table, we verify that this pte does not already point to a file backed page, and vice versa if this is a file backed page that is being added we verify that this page does not have an anonymous mapping We also enforce that read-only sharing for anonymous pages is allowed (i.e. cow after fork). All other sharing must be for file pages. Page table check allows to protect and debug cases where "struct page" metadata became corrupted for some reason. For example, when refcnt or mapcount become invalid. Link: https://lkml.kernel.org/r/20211221154650.1047963-4-pasha.tatashin@soleen.com Signed-off-by: Pasha Tatashin Cc: Aneesh Kumar K.V Cc: Dave Hansen Cc: David Rientjes Cc: Frederic Weisbecker Cc: Greg Thelen Cc: "H. Peter Anvin" Cc: Hugh Dickins Cc: Ingo Molnar Cc: Jiri Slaby Cc: Jonathan Corbet Cc: Kees Cook Cc: Masahiro Yamada Cc: Mike Rapoport Cc: Muchun Song Cc: Paul Turner Cc: Peter Zijlstra Cc: Sami Tolvanen Cc: Thomas Gleixner Cc: Wei Xu Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/vm/index.rst | 1 + Documentation/vm/page_table_check.rst | 56 +++++++ MAINTAINERS | 9 ++ arch/Kconfig | 3 + include/linux/page_table_check.h | 147 ++++++++++++++++++ mm/Kconfig.debug | 24 +++ mm/Makefile | 1 + mm/page_alloc.c | 4 + mm/page_ext.c | 4 + mm/page_table_check.c | 270 ++++++++++++++++++++++++++++++++++ 10 files changed, 519 insertions(+) create mode 100644 Documentation/vm/page_table_check.rst create mode 100644 include/linux/page_table_check.h create mode 100644 mm/page_table_check.c (limited to 'include/linux') diff --git a/Documentation/vm/index.rst b/Documentation/vm/index.rst index b1826ca2c576..932440805453 100644 --- a/Documentation/vm/index.rst +++ b/Documentation/vm/index.rst @@ -31,6 +31,7 @@ algorithms. If you are looking for advice on simply allocating memory, see the page_migration page_frags page_owner + page_table_check remap_file_pages slub split_page_table_lock diff --git a/Documentation/vm/page_table_check.rst b/Documentation/vm/page_table_check.rst new file mode 100644 index 000000000000..81f521ff7ea7 --- /dev/null +++ b/Documentation/vm/page_table_check.rst @@ -0,0 +1,56 @@ +.. SPDX-License-Identifier: GPL-2.0 + +.. _page_table_check: + +================ +Page Table Check +================ + +Introduction +============ + +Page table check allows to hardern the kernel by ensuring that some types of +the memory corruptions are prevented. + +Page table check performs extra verifications at the time when new pages become +accessible from the userspace by getting their page table entries (PTEs PMDs +etc.) added into the table. + +In case of detected corruption, the kernel is crashed. There is a small +performance and memory overhead associated with the page table check. Therefore, +it is disabled by default, but can be optionally enabled on systems where the +extra hardening outweighs the performance costs. Also, because page table check +is synchronous, it can help with debugging double map memory corruption issues, +by crashing kernel at the time wrong mapping occurs instead of later which is +often the case with memory corruptions bugs. + +Double mapping detection logic +============================== + ++-------------------+-------------------+-------------------+------------------+ +| Current Mapping | New mapping | Permissions | Rule | ++===================+===================+===================+==================+ +| Anonymous | Anonymous | Read | Allow | ++-------------------+-------------------+-------------------+------------------+ +| Anonymous | Anonymous | Read / Write | Prohibit | ++-------------------+-------------------+-------------------+------------------+ +| Anonymous | Named | Any | Prohibit | ++-------------------+-------------------+-------------------+------------------+ +| Named | Anonymous | Any | Prohibit | ++-------------------+-------------------+-------------------+------------------+ +| Named | Named | Any | Allow | ++-------------------+-------------------+-------------------+------------------+ + +Enabling Page Table Check +========================= + +Build kernel with: + +- PAGE_TABLE_CHECK=y + Note, it can only be enabled on platforms where ARCH_SUPPORTS_PAGE_TABLE_CHECK + is available. + +- Boot with 'page_table_check=on' kernel parameter. + +Optionally, build kernel with PAGE_TABLE_CHECK_ENFORCED in order to have page +table support without extra kernel parameter. diff --git a/MAINTAINERS b/MAINTAINERS index dd36acc87ce6..fbdb860c0b8b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14387,6 +14387,15 @@ F: include/net/page_pool.h F: include/trace/events/page_pool.h F: net/core/page_pool.c +PAGE TABLE CHECK +M: Pasha Tatashin +M: Andrew Morton +L: linux-mm@kvack.org +S: Maintained +F: Documentation/vm/page_table_check.rst +F: include/linux/page_table_check.h +F: mm/page_table_check.c + PANASONIC LAPTOP ACPI EXTRAS DRIVER M: Kenneth Chan L: platform-driver-x86@vger.kernel.org diff --git a/arch/Kconfig b/arch/Kconfig index d3c4ab249e9c..4568b6b70b5d 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -1297,6 +1297,9 @@ config HAVE_ARCH_PFN_VALID config ARCH_SUPPORTS_DEBUG_PAGEALLOC bool +config ARCH_SUPPORTS_PAGE_TABLE_CHECK + bool + config ARCH_SPLIT_ARG64 bool help diff --git a/include/linux/page_table_check.h b/include/linux/page_table_check.h new file mode 100644 index 000000000000..38cace1da7b6 --- /dev/null +++ b/include/linux/page_table_check.h @@ -0,0 +1,147 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Copyright (c) 2021, Google LLC. + * Pasha Tatashin + */ +#ifndef __LINUX_PAGE_TABLE_CHECK_H +#define __LINUX_PAGE_TABLE_CHECK_H + +#ifdef CONFIG_PAGE_TABLE_CHECK +#include + +extern struct static_key_true page_table_check_disabled; +extern struct page_ext_operations page_table_check_ops; + +void __page_table_check_zero(struct page *page, unsigned int order); +void __page_table_check_pte_clear(struct mm_struct *mm, unsigned long addr, + pte_t pte); +void __page_table_check_pmd_clear(struct mm_struct *mm, unsigned long addr, + pmd_t pmd); +void __page_table_check_pud_clear(struct mm_struct *mm, unsigned long addr, + pud_t pud); +void __page_table_check_pte_set(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte); +void __page_table_check_pmd_set(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp, pmd_t pmd); +void __page_table_check_pud_set(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, pud_t pud); + +static inline void page_table_check_alloc(struct page *page, unsigned int order) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_zero(page, order); +} + +static inline void page_table_check_free(struct page *page, unsigned int order) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_zero(page, order); +} + +static inline void page_table_check_pte_clear(struct mm_struct *mm, + unsigned long addr, pte_t pte) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_pte_clear(mm, addr, pte); +} + +static inline void page_table_check_pmd_clear(struct mm_struct *mm, + unsigned long addr, pmd_t pmd) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_pmd_clear(mm, addr, pmd); +} + +static inline void page_table_check_pud_clear(struct mm_struct *mm, + unsigned long addr, pud_t pud) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_pud_clear(mm, addr, pud); +} + +static inline void page_table_check_pte_set(struct mm_struct *mm, + unsigned long addr, pte_t *ptep, + pte_t pte) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_pte_set(mm, addr, ptep, pte); +} + +static inline void page_table_check_pmd_set(struct mm_struct *mm, + unsigned long addr, pmd_t *pmdp, + pmd_t pmd) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_pmd_set(mm, addr, pmdp, pmd); +} + +static inline void page_table_check_pud_set(struct mm_struct *mm, + unsigned long addr, pud_t *pudp, + pud_t pud) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_pud_set(mm, addr, pudp, pud); +} + +#else + +static inline void page_table_check_alloc(struct page *page, unsigned int order) +{ +} + +static inline void page_table_check_free(struct page *page, unsigned int order) +{ +} + +static inline void page_table_check_pte_clear(struct mm_struct *mm, + unsigned long addr, pte_t pte) +{ +} + +static inline void page_table_check_pmd_clear(struct mm_struct *mm, + unsigned long addr, pmd_t pmd) +{ +} + +static inline void page_table_check_pud_clear(struct mm_struct *mm, + unsigned long addr, pud_t pud) +{ +} + +static inline void page_table_check_pte_set(struct mm_struct *mm, + unsigned long addr, pte_t *ptep, + pte_t pte) +{ +} + +static inline void page_table_check_pmd_set(struct mm_struct *mm, + unsigned long addr, pmd_t *pmdp, + pmd_t pmd) +{ +} + +static inline void page_table_check_pud_set(struct mm_struct *mm, + unsigned long addr, pud_t *pudp, + pud_t pud) +{ +} + +#endif /* CONFIG_PAGE_TABLE_CHECK */ +#endif /* __LINUX_PAGE_TABLE_CHECK_H */ diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug index 1e73717802f8..5bd5bb097252 100644 --- a/mm/Kconfig.debug +++ b/mm/Kconfig.debug @@ -62,6 +62,30 @@ config PAGE_OWNER If unsure, say N. +config PAGE_TABLE_CHECK + bool "Check for invalid mappings in user page tables" + depends on ARCH_SUPPORTS_PAGE_TABLE_CHECK + select PAGE_EXTENSION + help + Check that anonymous page is not being mapped twice with read write + permissions. Check that anonymous and file pages are not being + erroneously shared. Since the checking is performed at the time + entries are added and removed to user page tables, leaking, corruption + and double mapping problems are detected synchronously. + + If unsure say "n". + +config PAGE_TABLE_CHECK_ENFORCED + bool "Enforce the page table checking by default" + depends on PAGE_TABLE_CHECK + help + Always enable page table checking. By default the page table checking + is disabled, and can be optionally enabled via page_table_check=on + kernel parameter. This config enforces that page table check is always + enabled. + + If unsure say "n". + config PAGE_POISONING bool "Poison pages after freeing" help diff --git a/mm/Makefile b/mm/Makefile index d6c0042e3aa0..5c5a3a480fa6 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -112,6 +112,7 @@ obj-$(CONFIG_GENERIC_EARLY_IOREMAP) += early_ioremap.o obj-$(CONFIG_CMA) += cma.o obj-$(CONFIG_MEMORY_BALLOON) += balloon_compaction.o obj-$(CONFIG_PAGE_EXTENSION) += page_ext.o +obj-$(CONFIG_PAGE_TABLE_CHECK) += page_table_check.o obj-$(CONFIG_CMA_DEBUGFS) += cma_debug.o obj-$(CONFIG_SECRETMEM) += secretmem.o obj-$(CONFIG_CMA_SYSFS) += cma_sysfs.o diff --git a/mm/page_alloc.c b/mm/page_alloc.c index d59023a676ed..806f317c2e7e 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -63,6 +63,7 @@ #include #include #include +#include #include #include #include @@ -1307,6 +1308,7 @@ static __always_inline bool free_pages_prepare(struct page *page, if (memcg_kmem_enabled() && PageMemcgKmem(page)) __memcg_kmem_uncharge_page(page, order); reset_page_owner(page, order); + page_table_check_free(page, order); return false; } @@ -1346,6 +1348,7 @@ static __always_inline bool free_pages_prepare(struct page *page, page_cpupid_reset_last(page); page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; reset_page_owner(page, order); + page_table_check_free(page, order); if (!PageHighMem(page)) { debug_check_no_locks_freed(page_address(page), @@ -2420,6 +2423,7 @@ inline void post_alloc_hook(struct page *page, unsigned int order, } set_page_owner(page, order, gfp_flags); + page_table_check_alloc(page, order); } static void prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags, diff --git a/mm/page_ext.c b/mm/page_ext.c index 6242afb24d84..bee3240604dc 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -8,6 +8,7 @@ #include #include #include +#include /* * struct page extension @@ -75,6 +76,9 @@ static struct page_ext_operations *page_ext_ops[] = { #if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) &page_idle_ops, #endif +#ifdef CONFIG_PAGE_TABLE_CHECK + &page_table_check_ops, +#endif }; unsigned long page_ext_size = sizeof(struct page_ext); diff --git a/mm/page_table_check.c b/mm/page_table_check.c new file mode 100644 index 000000000000..7504e7caa2a1 --- /dev/null +++ b/mm/page_table_check.c @@ -0,0 +1,270 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright (c) 2021, Google LLC. + * Pasha Tatashin + */ +#include +#include + +#undef pr_fmt +#define pr_fmt(fmt) "page_table_check: " fmt + +struct page_table_check { + atomic_t anon_map_count; + atomic_t file_map_count; +}; + +static bool __page_table_check_enabled __initdata = + IS_ENABLED(CONFIG_PAGE_TABLE_CHECK_ENFORCED); + +DEFINE_STATIC_KEY_TRUE(page_table_check_disabled); +EXPORT_SYMBOL(page_table_check_disabled); + +static int __init early_page_table_check_param(char *buf) +{ + if (!buf) + return -EINVAL; + + if (strcmp(buf, "on") == 0) + __page_table_check_enabled = true; + else if (strcmp(buf, "off") == 0) + __page_table_check_enabled = false; + + return 0; +} + +early_param("page_table_check", early_page_table_check_param); + +static bool __init need_page_table_check(void) +{ + return __page_table_check_enabled; +} + +static void __init init_page_table_check(void) +{ + if (!__page_table_check_enabled) + return; + static_branch_disable(&page_table_check_disabled); +} + +struct page_ext_operations page_table_check_ops = { + .size = sizeof(struct page_table_check), + .need = need_page_table_check, + .init = init_page_table_check, +}; + +static struct page_table_check *get_page_table_check(struct page_ext *page_ext) +{ + BUG_ON(!page_ext); + return (void *)(page_ext) + page_table_check_ops.offset; +} + +static inline bool pte_user_accessible_page(pte_t pte) +{ + return (pte_val(pte) & _PAGE_PRESENT) && (pte_val(pte) & _PAGE_USER); +} + +static inline bool pmd_user_accessible_page(pmd_t pmd) +{ + return pmd_leaf(pmd) && (pmd_val(pmd) & _PAGE_PRESENT) && + (pmd_val(pmd) & _PAGE_USER); +} + +static inline bool pud_user_accessible_page(pud_t pud) +{ + return pud_leaf(pud) && (pud_val(pud) & _PAGE_PRESENT) && + (pud_val(pud) & _PAGE_USER); +} + +/* + * An enty is removed from the page table, decrement the counters for that page + * verify that it is of correct type and counters do not become negative. + */ +static void page_table_check_clear(struct mm_struct *mm, unsigned long addr, + unsigned long pfn, unsigned long pgcnt) +{ + struct page_ext *page_ext; + struct page *page; + bool anon; + int i; + + if (!pfn_valid(pfn)) + return; + + page = pfn_to_page(pfn); + page_ext = lookup_page_ext(page); + anon = PageAnon(page); + + for (i = 0; i < pgcnt; i++) { + struct page_table_check *ptc = get_page_table_check(page_ext); + + if (anon) { + BUG_ON(atomic_read(&ptc->file_map_count)); + BUG_ON(atomic_dec_return(&ptc->anon_map_count) < 0); + } else { + BUG_ON(atomic_read(&ptc->anon_map_count)); + BUG_ON(atomic_dec_return(&ptc->file_map_count) < 0); + } + page_ext = page_ext_next(page_ext); + } +} + +/* + * A new enty is added to the page table, increment the counters for that page + * verify that it is of correct type and is not being mapped with a different + * type to a different process. + */ +static void page_table_check_set(struct mm_struct *mm, unsigned long addr, + unsigned long pfn, unsigned long pgcnt, + bool rw) +{ + struct page_ext *page_ext; + struct page *page; + bool anon; + int i; + + if (!pfn_valid(pfn)) + return; + + page = pfn_to_page(pfn); + page_ext = lookup_page_ext(page); + anon = PageAnon(page); + + for (i = 0; i < pgcnt; i++) { + struct page_table_check *ptc = get_page_table_check(page_ext); + + if (anon) { + BUG_ON(atomic_read(&ptc->file_map_count)); + BUG_ON(atomic_inc_return(&ptc->anon_map_count) > 1 && rw); + } else { + BUG_ON(atomic_read(&ptc->anon_map_count)); + BUG_ON(atomic_inc_return(&ptc->file_map_count) < 0); + } + page_ext = page_ext_next(page_ext); + } +} + +/* + * page is on free list, or is being allocated, verify that counters are zeroes + * crash if they are not. + */ +void __page_table_check_zero(struct page *page, unsigned int order) +{ + struct page_ext *page_ext = lookup_page_ext(page); + int i; + + BUG_ON(!page_ext); + for (i = 0; i < (1 << order); i++) { + struct page_table_check *ptc = get_page_table_check(page_ext); + + BUG_ON(atomic_read(&ptc->anon_map_count)); + BUG_ON(atomic_read(&ptc->file_map_count)); + page_ext = page_ext_next(page_ext); + } +} + +void __page_table_check_pte_clear(struct mm_struct *mm, unsigned long addr, + pte_t pte) +{ + if (&init_mm == mm) + return; + + if (pte_user_accessible_page(pte)) { + page_table_check_clear(mm, addr, pte_pfn(pte), + PAGE_SIZE >> PAGE_SHIFT); + } +} +EXPORT_SYMBOL(__page_table_check_pte_clear); + +void __page_table_check_pmd_clear(struct mm_struct *mm, unsigned long addr, + pmd_t pmd) +{ + if (&init_mm == mm) + return; + + if (pmd_user_accessible_page(pmd)) { + page_table_check_clear(mm, addr, pmd_pfn(pmd), + PMD_PAGE_SIZE >> PAGE_SHIFT); + } +} +EXPORT_SYMBOL(__page_table_check_pmd_clear); + +void __page_table_check_pud_clear(struct mm_struct *mm, unsigned long addr, + pud_t pud) +{ + if (&init_mm == mm) + return; + + if (pud_user_accessible_page(pud)) { + page_table_check_clear(mm, addr, pud_pfn(pud), + PUD_PAGE_SIZE >> PAGE_SHIFT); + } +} +EXPORT_SYMBOL(__page_table_check_pud_clear); + +void __page_table_check_pte_set(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte) +{ + pte_t old_pte; + + if (&init_mm == mm) + return; + + old_pte = *ptep; + if (pte_user_accessible_page(old_pte)) { + page_table_check_clear(mm, addr, pte_pfn(old_pte), + PAGE_SIZE >> PAGE_SHIFT); + } + + if (pte_user_accessible_page(pte)) { + page_table_check_set(mm, addr, pte_pfn(pte), + PAGE_SIZE >> PAGE_SHIFT, + pte_write(pte)); + } +} +EXPORT_SYMBOL(__page_table_check_pte_set); + +void __page_table_check_pmd_set(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp, pmd_t pmd) +{ + pmd_t old_pmd; + + if (&init_mm == mm) + return; + + old_pmd = *pmdp; + if (pmd_user_accessible_page(old_pmd)) { + page_table_check_clear(mm, addr, pmd_pfn(old_pmd), + PMD_PAGE_SIZE >> PAGE_SHIFT); + } + + if (pmd_user_accessible_page(pmd)) { + page_table_check_set(mm, addr, pmd_pfn(pmd), + PMD_PAGE_SIZE >> PAGE_SHIFT, + pmd_write(pmd)); + } +} +EXPORT_SYMBOL(__page_table_check_pmd_set); + +void __page_table_check_pud_set(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, pud_t pud) +{ + pud_t old_pud; + + if (&init_mm == mm) + return; + + old_pud = *pudp; + if (pud_user_accessible_page(old_pud)) { + page_table_check_clear(mm, addr, pud_pfn(old_pud), + PUD_PAGE_SIZE >> PAGE_SHIFT); + } + + if (pud_user_accessible_page(pud)) { + page_table_check_set(mm, addr, pud_pfn(pud), + PUD_PAGE_SIZE >> PAGE_SHIFT, + pud_write(pud)); + } +} +EXPORT_SYMBOL(__page_table_check_pud_set); -- cgit v1.2.3 From 020e87650af9f43683546729f959fdc78422a4b7 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 14 Jan 2022 14:06:44 -0800 Subject: mm: remove last argument of reuse_swap_page() None of the callers care about the total_map_swapcount() any more. Link: https://lkml.kernel.org/r/20211220205943.456187-1-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Linus Torvalds Reviewed-by: William Kucharski Reviewed-by: David Hildenbrand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 6 +++--- mm/huge_memory.c | 2 +- mm/khugepaged.c | 2 +- mm/memory.c | 2 +- mm/swapfile.c | 8 +------- 5 files changed, 7 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index d1ea44b31f19..bdccbf1efa61 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -514,7 +514,7 @@ extern int __swp_swapcount(swp_entry_t entry); extern int swp_swapcount(swp_entry_t entry); extern struct swap_info_struct *page_swap_info(struct page *); extern struct swap_info_struct *swp_swap_info(swp_entry_t entry); -extern bool reuse_swap_page(struct page *, int *); +extern bool reuse_swap_page(struct page *); extern int try_to_free_swap(struct page *); struct backing_dev_info; extern int init_swap_address_space(unsigned int type, unsigned long nr_pages); @@ -680,8 +680,8 @@ static inline int swp_swapcount(swp_entry_t entry) return 0; } -#define reuse_swap_page(page, total_map_swapcount) \ - (page_trans_huge_mapcount(page, total_map_swapcount) == 1) +#define reuse_swap_page(page) \ + (page_trans_huge_mapcount(page, NULL) == 1) static inline int try_to_free_swap(struct page *page) { diff --git a/mm/huge_memory.c b/mm/huge_memory.c index e5483347291c..b61fbe95c856 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1322,7 +1322,7 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) * We can only reuse the page if nobody else maps the huge page or it's * part. */ - if (reuse_swap_page(page, NULL)) { + if (reuse_swap_page(page)) { pmd_t entry; entry = pmd_mkyoung(orig_pmd); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 9d40dd8890e5..698ea19775ac 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -681,7 +681,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, goto out; } if (!pte_write(pteval) && PageSwapCache(page) && - !reuse_swap_page(page, NULL)) { + !reuse_swap_page(page)) { /* * Page is in the swap cache and cannot be re-used. * It cannot be collapsed into a THP. diff --git a/mm/memory.c b/mm/memory.c index 5fea331b1560..571d02f419ba 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3627,7 +3627,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); dec_mm_counter_fast(vma->vm_mm, MM_SWAPENTS); pte = mk_pte(page, vma->vm_page_prot); - if ((vmf->flags & FAULT_FLAG_WRITE) && reuse_swap_page(page, NULL)) { + if ((vmf->flags & FAULT_FLAG_WRITE) && reuse_swap_page(page)) { pte = maybe_mkwrite(pte_mkdirty(pte), vma); vmf->flags &= ~FAULT_FLAG_WRITE; ret |= VM_FAULT_WRITE; diff --git a/mm/swapfile.c b/mm/swapfile.c index e64207e2ef1d..31d13a393cf0 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1668,12 +1668,8 @@ static int page_trans_huge_map_swapcount(struct page *page, int *total_mapcount, * to it. And as a side-effect, free up its swap: because the old content * on disk will never be read, and seeking back there to write new content * later would only waste time away from clustering. - * - * NOTE: total_map_swapcount should not be relied upon by the caller if - * reuse_swap_page() returns false, but it may be always overwritten - * (see the other implementation for CONFIG_SWAP=n). */ -bool reuse_swap_page(struct page *page, int *total_map_swapcount) +bool reuse_swap_page(struct page *page) { int count, total_mapcount, total_swapcount; @@ -1682,8 +1678,6 @@ bool reuse_swap_page(struct page *page, int *total_map_swapcount) return false; count = page_trans_huge_map_swapcount(page, &total_mapcount, &total_swapcount); - if (total_map_swapcount) - *total_map_swapcount = total_mapcount + total_swapcount; if (count == 1 && PageSwapCache(page) && (likely(!PageTransCompound(page)) || /* The remaining swap count will be freed soon */ -- cgit v1.2.3 From d08d2b62510e2407cf939e693aefd179dc114913 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 14 Jan 2022 14:06:51 -0800 Subject: mm: remove the total_mapcount argument from page_trans_huge_mapcount() All callers pass NULL, so we can stop calculating the value we would store in it. Link: https://lkml.kernel.org/r/20211220205943.456187-3-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: William Kucharski Acked-by: Linus Torvalds Cc: David Hildenbrand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 10 +++------- include/linux/swap.h | 2 +- mm/huge_memory.c | 30 ++++++++++-------------------- mm/swapfile.c | 2 +- 4 files changed, 15 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 4d7245e6802a..cef65f9cbdf2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -799,19 +799,15 @@ static inline int page_mapcount(struct page *page) #ifdef CONFIG_TRANSPARENT_HUGEPAGE int total_mapcount(struct page *page); -int page_trans_huge_mapcount(struct page *page, int *total_mapcount); +int page_trans_huge_mapcount(struct page *page); #else static inline int total_mapcount(struct page *page) { return page_mapcount(page); } -static inline int page_trans_huge_mapcount(struct page *page, - int *total_mapcount) +static inline int page_trans_huge_mapcount(struct page *page) { - int mapcount = page_mapcount(page); - if (total_mapcount) - *total_mapcount = mapcount; - return mapcount; + return page_mapcount(page); } #endif diff --git a/include/linux/swap.h b/include/linux/swap.h index bdccbf1efa61..1d38d9475c4d 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -681,7 +681,7 @@ static inline int swp_swapcount(swp_entry_t entry) } #define reuse_swap_page(page) \ - (page_trans_huge_mapcount(page, NULL) == 1) + (page_trans_huge_mapcount(page) == 1) static inline int try_to_free_swap(struct page *page) { diff --git a/mm/huge_memory.c b/mm/huge_memory.c index b61fbe95c856..6ed86a8f6a5b 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2542,38 +2542,28 @@ int total_mapcount(struct page *page) * need full accuracy to avoid breaking page pinning, because * page_trans_huge_mapcount() is slower than page_mapcount(). */ -int page_trans_huge_mapcount(struct page *page, int *total_mapcount) +int page_trans_huge_mapcount(struct page *page) { - int i, ret, _total_mapcount, mapcount; + int i, ret; /* hugetlbfs shouldn't call it */ VM_BUG_ON_PAGE(PageHuge(page), page); - if (likely(!PageTransCompound(page))) { - mapcount = atomic_read(&page->_mapcount) + 1; - if (total_mapcount) - *total_mapcount = mapcount; - return mapcount; - } + if (likely(!PageTransCompound(page))) + return atomic_read(&page->_mapcount) + 1; page = compound_head(page); - _total_mapcount = ret = 0; + ret = 0; for (i = 0; i < thp_nr_pages(page); i++) { - mapcount = atomic_read(&page[i]._mapcount) + 1; + int mapcount = atomic_read(&page[i]._mapcount) + 1; ret = max(ret, mapcount); - _total_mapcount += mapcount; } - if (PageDoubleMap(page)) { + + if (PageDoubleMap(page)) ret -= 1; - _total_mapcount -= thp_nr_pages(page); - } - mapcount = compound_mapcount(page); - ret += mapcount; - _total_mapcount += mapcount; - if (total_mapcount) - *total_mapcount = _total_mapcount; - return ret; + + return ret + compound_mapcount(page); } /* Racy check whether the huge page can be split */ diff --git a/mm/swapfile.c b/mm/swapfile.c index a93f5b5fc8b6..caa9f81a0d15 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1619,7 +1619,7 @@ static int page_trans_huge_map_swapcount(struct page *page, swapcount = page_swapcount(page); if (total_swapcount) *total_swapcount = swapcount; - return swapcount + page_trans_huge_mapcount(page, NULL); + return swapcount + page_trans_huge_mapcount(page); } page = compound_head(page); -- cgit v1.2.3 From a421ef303008b0ceee2cfc625c3246fa7654b0ca Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 14 Jan 2022 14:07:07 -0800 Subject: mm: allow !GFP_KERNEL allocations for kvmalloc Support for GFP_NO{FS,IO} and __GFP_NOFAIL has been implemented by previous patches so we can allow the support for kvmalloc. This will allow some external users to simplify or completely remove their helpers. GFP_NOWAIT semantic hasn't been supported so far but it hasn't been explicitly documented so let's add a note about that. ceph_kvmalloc is the first helper to be dropped and changed to kvmalloc. Link: https://lkml.kernel.org/r/20211122153233.9924-5-mhocko@kernel.org Signed-off-by: Michal Hocko Reviewed-by: Uladzislau Rezki (Sony) Acked-by: Vlastimil Babka Cc: Christoph Hellwig Cc: Dave Chinner Cc: Ilya Dryomov Cc: Jeff Layton Cc: Neil Brown Cc: Sebastian Andrzej Siewior Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ceph/libceph.h | 1 - mm/util.c | 15 ++++----------- net/ceph/buffer.c | 4 ++-- net/ceph/ceph_common.c | 27 --------------------------- net/ceph/crypto.c | 2 +- net/ceph/messenger.c | 2 +- net/ceph/messenger_v2.c | 2 +- net/ceph/osdmap.c | 12 ++++++------ 8 files changed, 15 insertions(+), 50 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 409d8c29bc4f..309acbcb5a8a 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -295,7 +295,6 @@ extern bool libceph_compatible(void *data); extern const char *ceph_msg_type_name(int type); extern int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid); -extern void *ceph_kvmalloc(size_t size, gfp_t flags); struct fs_parameter; struct fc_log; diff --git a/mm/util.c b/mm/util.c index 741ba32a43ac..7e43369064c8 100644 --- a/mm/util.c +++ b/mm/util.c @@ -549,13 +549,10 @@ EXPORT_SYMBOL(vm_mmap); * Uses kmalloc to get the memory but if the allocation fails then falls back * to the vmalloc allocator. Use kvfree for freeing the memory. * - * Reclaim modifiers - __GFP_NORETRY and __GFP_NOFAIL are not supported. + * GFP_NOWAIT and GFP_ATOMIC are not supported, neither is the __GFP_NORETRY modifier. * __GFP_RETRY_MAYFAIL is supported, and it should be used only if kmalloc is * preferable to the vmalloc fallback, due to visible performance drawbacks. * - * Please note that any use of gfp flags outside of GFP_KERNEL is careful to not - * fall back to vmalloc. - * * Return: pointer to the allocated memory of %NULL in case of failure */ void *kvmalloc_node(size_t size, gfp_t flags, int node) @@ -563,13 +560,6 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node) gfp_t kmalloc_flags = flags; void *ret; - /* - * vmalloc uses GFP_KERNEL for some internal allocations (e.g page tables) - * so the given set of flags has to be compatible. - */ - if ((flags & GFP_KERNEL) != GFP_KERNEL) - return kmalloc_node(size, flags, node); - /* * We want to attempt a large physically contiguous block first because * it is less likely to fragment multiple larger blocks and therefore @@ -582,6 +572,9 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node) if (!(kmalloc_flags & __GFP_RETRY_MAYFAIL)) kmalloc_flags |= __GFP_NORETRY; + + /* nofail semantic is implemented by the vmalloc fallback */ + kmalloc_flags &= ~__GFP_NOFAIL; } ret = kmalloc_node(size, kmalloc_flags, node); diff --git a/net/ceph/buffer.c b/net/ceph/buffer.c index 5622763ad402..7e51f128045d 100644 --- a/net/ceph/buffer.c +++ b/net/ceph/buffer.c @@ -7,7 +7,7 @@ #include #include -#include /* for ceph_kvmalloc */ +#include /* for kvmalloc */ struct ceph_buffer *ceph_buffer_new(size_t len, gfp_t gfp) { @@ -17,7 +17,7 @@ struct ceph_buffer *ceph_buffer_new(size_t len, gfp_t gfp) if (!b) return NULL; - b->vec.iov_base = ceph_kvmalloc(len, gfp); + b->vec.iov_base = kvmalloc(len, gfp); if (!b->vec.iov_base) { kfree(b); return NULL; diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 97d6ea763e32..9441b4a4912b 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -190,33 +190,6 @@ int ceph_compare_options(struct ceph_options *new_opt, } EXPORT_SYMBOL(ceph_compare_options); -/* - * kvmalloc() doesn't fall back to the vmalloc allocator unless flags are - * compatible with (a superset of) GFP_KERNEL. This is because while the - * actual pages are allocated with the specified flags, the page table pages - * are always allocated with GFP_KERNEL. - * - * ceph_kvmalloc() may be called with GFP_KERNEL, GFP_NOFS or GFP_NOIO. - */ -void *ceph_kvmalloc(size_t size, gfp_t flags) -{ - void *p; - - if ((flags & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS)) { - p = kvmalloc(size, flags); - } else if ((flags & (__GFP_IO | __GFP_FS)) == __GFP_IO) { - unsigned int nofs_flag = memalloc_nofs_save(); - p = kvmalloc(size, GFP_KERNEL); - memalloc_nofs_restore(nofs_flag); - } else { - unsigned int noio_flag = memalloc_noio_save(); - p = kvmalloc(size, GFP_KERNEL); - memalloc_noio_restore(noio_flag); - } - - return p; -} - static int parse_fsid(const char *str, struct ceph_fsid *fsid) { int i = 0; diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c index 92d89b331645..051d22c0e4ad 100644 --- a/net/ceph/crypto.c +++ b/net/ceph/crypto.c @@ -147,7 +147,7 @@ void ceph_crypto_key_destroy(struct ceph_crypto_key *key) static const u8 *aes_iv = (u8 *)CEPH_AES_IV; /* - * Should be used for buffers allocated with ceph_kvmalloc(). + * Should be used for buffers allocated with kvmalloc(). * Currently these are encrypt out-buffer (ceph_buffer) and decrypt * in-buffer (msg front). * diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 57d043b382ed..7b891be799d2 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1920,7 +1920,7 @@ struct ceph_msg *ceph_msg_new2(int type, int front_len, int max_data_items, /* front */ if (front_len) { - m->front.iov_base = ceph_kvmalloc(front_len, flags); + m->front.iov_base = kvmalloc(front_len, flags); if (m->front.iov_base == NULL) { dout("ceph_msg_new can't allocate %d bytes\n", front_len); diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c index cc40ce4e02fb..c4099b641b38 100644 --- a/net/ceph/messenger_v2.c +++ b/net/ceph/messenger_v2.c @@ -308,7 +308,7 @@ static void *alloc_conn_buf(struct ceph_connection *con, int len) if (WARN_ON(con->v2.conn_buf_cnt >= ARRAY_SIZE(con->v2.conn_bufs))) return NULL; - buf = ceph_kvmalloc(len, GFP_NOIO); + buf = kvmalloc(len, GFP_NOIO); if (!buf) return NULL; diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 75b738083523..2823bb3cff55 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -980,7 +980,7 @@ static struct crush_work *alloc_workspace(const struct crush_map *c) work_size = crush_work_size(c, CEPH_PG_MAX_SIZE); dout("%s work_size %zu bytes\n", __func__, work_size); - work = ceph_kvmalloc(work_size, GFP_NOIO); + work = kvmalloc(work_size, GFP_NOIO); if (!work) return NULL; @@ -1190,9 +1190,9 @@ static int osdmap_set_max_osd(struct ceph_osdmap *map, u32 max) if (max == map->max_osd) return 0; - state = ceph_kvmalloc(array_size(max, sizeof(*state)), GFP_NOFS); - weight = ceph_kvmalloc(array_size(max, sizeof(*weight)), GFP_NOFS); - addr = ceph_kvmalloc(array_size(max, sizeof(*addr)), GFP_NOFS); + state = kvmalloc(array_size(max, sizeof(*state)), GFP_NOFS); + weight = kvmalloc(array_size(max, sizeof(*weight)), GFP_NOFS); + addr = kvmalloc(array_size(max, sizeof(*addr)), GFP_NOFS); if (!state || !weight || !addr) { kvfree(state); kvfree(weight); @@ -1222,7 +1222,7 @@ static int osdmap_set_max_osd(struct ceph_osdmap *map, u32 max) if (map->osd_primary_affinity) { u32 *affinity; - affinity = ceph_kvmalloc(array_size(max, sizeof(*affinity)), + affinity = kvmalloc(array_size(max, sizeof(*affinity)), GFP_NOFS); if (!affinity) return -ENOMEM; @@ -1503,7 +1503,7 @@ static int set_primary_affinity(struct ceph_osdmap *map, int osd, u32 aff) if (!map->osd_primary_affinity) { int i; - map->osd_primary_affinity = ceph_kvmalloc( + map->osd_primary_affinity = kvmalloc( array_size(map->max_osd, sizeof(*map->osd_primary_affinity)), GFP_NOFS); if (!map->osd_primary_affinity) -- cgit v1.2.3 From 4034247a0d6ab281ba3293798ce67af494d86129 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 14 Jan 2022 14:07:14 -0800 Subject: mm: introduce memalloc_retry_wait() Various places in the kernel - largely in filesystems - respond to a memory allocation failure by looping around and re-trying. Some of these cannot conveniently use __GFP_NOFAIL, for reasons such as: - a GFP_ATOMIC allocation, which __GFP_NOFAIL doesn't work on - a need to check for the process being signalled between failures - the possibility that other recovery actions could be performed - the allocation is quite deep in support code, and passing down an extra flag to say if __GFP_NOFAIL is wanted would be clumsy. Many of these currently use congestion_wait() which (in almost all cases) simply waits the given timeout - congestion isn't tracked for most devices. It isn't clear what the best delay is for loops, but it is clear that the various filesystems shouldn't be responsible for choosing a timeout. This patch introduces memalloc_retry_wait() with takes on that responsibility. Code that wants to retry a memory allocation can call this function passing the GFP flags that were used. It will wait however is appropriate. For now, it only considers __GFP_NORETRY and whatever gfpflags_allow_blocking() tests. If blocking is allowed without __GFP_NORETRY, then alloc_page either made some reclaim progress, or waited for a while, before failing. So there is no need for much further waiting. memalloc_retry_wait() will wait until the current jiffie ends. If this condition is not met, then alloc_page() won't have waited much if at all. In that case memalloc_retry_wait() waits about 200ms. This is the delay that most current loops uses. linux/sched/mm.h needs to be included in some files now, but linux/backing-dev.h does not. Link: https://lkml.kernel.org/r/163754371968.13692.1277530886009912421@noble.neil.brown.name Signed-off-by: NeilBrown Cc: Dave Chinner Cc: Michal Hocko Cc: "Theodore Ts'o" Cc: Jaegeuk Kim Cc: Chao Yu Cc: Darrick J. Wong Cc: Chuck Lever Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ext4/extents.c | 8 +++----- fs/ext4/inline.c | 5 ++--- fs/ext4/page-io.c | 9 +++++---- fs/f2fs/data.c | 4 ++-- fs/f2fs/gc.c | 5 ++--- fs/f2fs/inode.c | 4 ++-- fs/f2fs/node.c | 4 ++-- fs/f2fs/recovery.c | 6 +++--- fs/f2fs/segment.c | 9 +++------ fs/f2fs/super.c | 5 ++--- fs/xfs/kmem.c | 3 +-- fs/xfs/xfs_buf.c | 2 +- include/linux/sched/mm.h | 26 ++++++++++++++++++++++++++ net/sunrpc/svc_xprt.c | 3 ++- 14 files changed, 56 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 0ecf819bf189..5582fba36b44 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -27,8 +27,8 @@ #include #include #include -#include #include +#include #include "ext4_jbd2.h" #include "ext4_extents.h" #include "xattr.h" @@ -4407,8 +4407,7 @@ retry: err = ext4_es_remove_extent(inode, last_block, EXT_MAX_BLOCKS - last_block); if (err == -ENOMEM) { - cond_resched(); - congestion_wait(BLK_RW_ASYNC, HZ/50); + memalloc_retry_wait(GFP_ATOMIC); goto retry; } if (err) @@ -4416,8 +4415,7 @@ retry: retry_remove_space: err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1); if (err == -ENOMEM) { - cond_resched(); - congestion_wait(BLK_RW_ASYNC, HZ/50); + memalloc_retry_wait(GFP_ATOMIC); goto retry_remove_space; } return err; diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 39a1ab129fdc..635bcf68a67e 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -7,7 +7,7 @@ #include #include #include -#include +#include #include "ext4_jbd2.h" #include "ext4.h" @@ -1929,8 +1929,7 @@ int ext4_inline_data_truncate(struct inode *inode, int *has_inline) retry: err = ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS); if (err == -ENOMEM) { - cond_resched(); - congestion_wait(BLK_RW_ASYNC, HZ/50); + memalloc_retry_wait(GFP_ATOMIC); goto retry; } if (err) diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 9cb261714991..1d370364230e 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -24,7 +24,7 @@ #include #include #include -#include +#include #include "ext4_jbd2.h" #include "xattr.h" @@ -523,12 +523,13 @@ int ext4_bio_write_page(struct ext4_io_submit *io, ret = PTR_ERR(bounce_page); if (ret == -ENOMEM && (io->io_bio || wbc->sync_mode == WB_SYNC_ALL)) { - gfp_flags = GFP_NOFS; + gfp_t new_gfp_flags = GFP_NOFS; if (io->io_bio) ext4_io_submit(io); else - gfp_flags |= __GFP_NOFAIL; - congestion_wait(BLK_RW_ASYNC, HZ/50); + new_gfp_flags |= __GFP_NOFAIL; + memalloc_retry_wait(gfp_flags); + gfp_flags = new_gfp_flags; goto retry_encrypt; } diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 9f754aaef558..aacf5e4dcc57 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -8,9 +8,9 @@ #include #include #include +#include #include #include -#include #include #include #include @@ -2542,7 +2542,7 @@ retry_encrypt: /* flush pending IOs and wait for a while in the ENOMEM case */ if (PTR_ERR(fio->encrypted_page) == -ENOMEM) { f2fs_flush_merged_writes(fio->sbi); - congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT); + memalloc_retry_wait(GFP_NOFS); gfp_flags |= __GFP_NOFAIL; goto retry_encrypt; } diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index a946ce0ead34..374bbb5294d9 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -7,7 +7,6 @@ */ #include #include -#include #include #include #include @@ -15,6 +14,7 @@ #include #include #include +#include #include "f2fs.h" #include "node.h" @@ -1375,8 +1375,7 @@ retry: if (err) { clear_page_private_gcing(page); if (err == -ENOMEM) { - congestion_wait(BLK_RW_ASYNC, - DEFAULT_IO_TIMEOUT); + memalloc_retry_wait(GFP_NOFS); goto retry; } if (is_dirty) diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 0f8b2df3e1e0..4c11254a07d4 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -8,8 +8,8 @@ #include #include #include -#include #include +#include #include "f2fs.h" #include "node.h" @@ -562,7 +562,7 @@ retry: inode = f2fs_iget(sb, ino); if (IS_ERR(inode)) { if (PTR_ERR(inode) == -ENOMEM) { - congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT); + memalloc_retry_wait(GFP_NOFS); goto retry; } } diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 556fcd8457f3..219506ca9a97 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -8,7 +8,7 @@ #include #include #include -#include +#include #include #include #include @@ -2750,7 +2750,7 @@ int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page) retry: ipage = f2fs_grab_cache_page(NODE_MAPPING(sbi), ino, false); if (!ipage) { - congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT); + memalloc_retry_wait(GFP_NOFS); goto retry; } diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 6a1b4668d933..d1664a0567ef 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -8,6 +8,7 @@ #include #include #include +#include #include "f2fs.h" #include "node.h" #include "segment.h" @@ -587,7 +588,7 @@ retry_dn: err = f2fs_get_dnode_of_data(&dn, start, ALLOC_NODE); if (err) { if (err == -ENOMEM) { - congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT); + memalloc_retry_wait(GFP_NOFS); goto retry_dn; } goto out; @@ -670,8 +671,7 @@ retry_prev: err = check_index_in_prev_nodes(sbi, dest, &dn); if (err) { if (err == -ENOMEM) { - congestion_wait(BLK_RW_ASYNC, - DEFAULT_IO_TIMEOUT); + memalloc_retry_wait(GFP_NOFS); goto retry_prev; } goto err; diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index df9ed75f0b7a..40fdb4a8daeb 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -245,9 +246,7 @@ retry: LOOKUP_NODE); if (err) { if (err == -ENOMEM) { - congestion_wait(BLK_RW_ASYNC, - DEFAULT_IO_TIMEOUT); - cond_resched(); + memalloc_retry_wait(GFP_NOFS); goto retry; } err = -EAGAIN; @@ -424,9 +423,7 @@ retry: err = f2fs_do_write_data_page(&fio); if (err) { if (err == -ENOMEM) { - congestion_wait(BLK_RW_ASYNC, - DEFAULT_IO_TIMEOUT); - cond_resched(); + memalloc_retry_wait(GFP_NOFS); goto retry; } unlock_page(page); diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 040b6d02e1d8..3bace24f8800 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -8,9 +8,9 @@ #include #include #include +#include #include #include -#include #include #include #include @@ -2415,8 +2415,7 @@ repeat: page = read_cache_page_gfp(mapping, blkidx, GFP_NOFS); if (IS_ERR(page)) { if (PTR_ERR(page) == -ENOMEM) { - congestion_wait(BLK_RW_ASYNC, - DEFAULT_IO_TIMEOUT); + memalloc_retry_wait(GFP_NOFS); goto repeat; } set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c index 6f49bf39183c..c557a030acfe 100644 --- a/fs/xfs/kmem.c +++ b/fs/xfs/kmem.c @@ -4,7 +4,6 @@ * All Rights Reserved. */ #include "xfs.h" -#include #include "xfs_message.h" #include "xfs_trace.h" @@ -26,6 +25,6 @@ kmem_alloc(size_t size, xfs_km_flags_t flags) "%s(%u) possible memory allocation deadlock size %u in %s (mode:0x%x)", current->comm, current->pid, (unsigned int)size, __func__, lflags); - congestion_wait(BLK_RW_ASYNC, HZ/50); + memalloc_retry_wait(lflags); } while (1); } diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 631c5a61d89b..6c45e3fa56f4 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -394,7 +394,7 @@ xfs_buf_alloc_pages( } XFS_STATS_INC(bp->b_mount, xb_page_retries); - congestion_wait(BLK_RW_ASYNC, HZ / 50); + memalloc_retry_wait(gfp_mask); } return 0; } diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index aca874d33fe6..aa5f09ca5bcf 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -214,6 +214,32 @@ static inline void fs_reclaim_acquire(gfp_t gfp_mask) { } static inline void fs_reclaim_release(gfp_t gfp_mask) { } #endif +/* Any memory-allocation retry loop should use + * memalloc_retry_wait(), and pass the flags for the most + * constrained allocation attempt that might have failed. + * This provides useful documentation of where loops are, + * and a central place to fine tune the waiting as the MM + * implementation changes. + */ +static inline void memalloc_retry_wait(gfp_t gfp_flags) +{ + /* We use io_schedule_timeout because waiting for memory + * typically included waiting for dirty pages to be + * written out, which requires IO. + */ + __set_current_state(TASK_UNINTERRUPTIBLE); + gfp_flags = current_gfp_context(gfp_flags); + if (gfpflags_allow_blocking(gfp_flags) && + !(gfp_flags & __GFP_NORETRY)) + /* Probably waited already, no need for much more */ + io_schedule_timeout(1); + else + /* Probably didn't wait, and has now released a lock, + * so now is a good time to wait + */ + io_schedule_timeout(HZ/50); +} + /** * might_alloc - Mark possible allocation sites * @gfp_mask: gfp_t flags that would be used to allocate diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 1e99ba1b9d72..9cb18b822ab2 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -6,6 +6,7 @@ */ #include +#include #include #include #include @@ -688,7 +689,7 @@ static int svc_alloc_arg(struct svc_rqst *rqstp) return -EINTR; } trace_svc_alloc_arg_err(pages); - schedule_timeout(msecs_to_jiffies(500)); + memalloc_retry_wait(GFP_KERNEL); } rqstp->rq_page_end = &rqstp->rq_pages[pages]; rqstp->rq_pages[pages] = NULL; /* this might be seen in nfsd_splice_actor() */ -- cgit v1.2.3 From 1611f74a94ba2e0f2d25b75008ed8e76e122097a Mon Sep 17 00:00:00 2001 From: Changcheng Deng Date: Fri, 14 Jan 2022 14:07:21 -0800 Subject: mm: fix boolreturn.cocci warning Return statements in functions returning bool should use true/false instead of 1/0. Link: https://lkml.kernel.org/r/20211126073327.74815-1-deng.changcheng@zte.com.cn Signed-off-by: Changcheng Deng Reported-by: Zeal Robot Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index b5f14d581113..18423c2157e8 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -383,7 +383,7 @@ static __always_inline int TestClearPage##uname(struct page *page) \ TESTCLEARFLAG(uname, lname, policy) #define TESTPAGEFLAG_FALSE(uname, lname) \ -static inline bool folio_test_##lname(const struct folio *folio) { return 0; } \ +static inline bool folio_test_##lname(const struct folio *folio) { return false; } \ static inline int Page##uname(const struct page *page) { return 0; } #define SETPAGEFLAG_NOOP(uname, lname) \ -- cgit v1.2.3 From be1a13eb51077b2ec5f7f4306f93dfece503a3f1 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 14 Jan 2022 14:07:27 -0800 Subject: mm: drop node from alloc_pages_vma alloc_pages_vma is meant to allocate a page with a vma specific memory policy. The initial node parameter is always a local node so it is pointless to waste a function argument for this. Drop the parameter. Link: https://lkml.kernel.org/r/YaSnlv4QpryEpesG@dhcp22.suse.cz Signed-off-by: Michal Hocko Cc: Aneesh Kumar K.V Cc: Ben Widawsky Cc: Dave Hansen Cc: Feng Tang Cc: Andrea Arcangeli Cc: Mel Gorman Cc: Mike Kravetz Cc: Randy Dunlap Cc: Vlastimil Babka Cc: Andi Kleen Cc: Dan Williams Cc: "Huang, Ying" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 8 ++++---- mm/mempolicy.c | 3 ++- mm/shmem.c | 3 +-- 3 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 8fcc38467af6..78b58448f796 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -598,9 +598,9 @@ struct page *alloc_pages(gfp_t gfp, unsigned int order); struct folio *folio_alloc(gfp_t gfp, unsigned order); extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, - int node, bool hugepage); + bool hugepage); #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ - alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true) + alloc_pages_vma(gfp_mask, order, vma, addr, true) #else static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order) { @@ -610,14 +610,14 @@ static inline struct folio *folio_alloc(gfp_t gfp, unsigned int order) { return __folio_alloc_node(gfp, order, numa_node_id()); } -#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\ +#define alloc_pages_vma(gfp_mask, order, vma, addr, false)\ alloc_pages(gfp_mask, order) #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) #define alloc_page_vma(gfp_mask, vma, addr) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false) + alloc_pages_vma(gfp_mask, 0, vma, addr, false) extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 679f47b3a079..ed7d15acb6a2 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2084,9 +2084,10 @@ static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order, * Return: The page on success or NULL if allocation fails. */ struct page *alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, - unsigned long addr, int node, bool hugepage) + unsigned long addr, bool hugepage) { struct mempolicy *pol; + int node = numa_node_id(); struct page *page; int preferred_nid; nodemask_t *nmask; diff --git a/mm/shmem.c b/mm/shmem.c index 8f940552c182..0700e9acf53b 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1564,8 +1564,7 @@ static struct page *shmem_alloc_hugepage(gfp_t gfp, return NULL; shmem_pseudo_vma_init(&pvma, info, hindex); - page = alloc_pages_vma(gfp, HPAGE_PMD_ORDER, &pvma, 0, numa_node_id(), - true); + page = alloc_pages_vma(gfp, HPAGE_PMD_ORDER, &pvma, 0, true); shmem_pseudo_vma_destroy(&pvma); if (page) prep_transhuge_page(page); -- cgit v1.2.3 From 04a536bfbd0f885338eecc2a4503dfca50ac94dd Mon Sep 17 00:00:00 2001 From: Miles Chen Date: Fri, 14 Jan 2022 14:07:30 -0800 Subject: include/linux/gfp.h: further document GFP_DMA32 kmalloc(..., GFP_DMA32) does not return DMA32 memory because the DMA32 kmalloc cache array is not implemented. (Reason: there is no such user in kernel). Put a short comment about this so people can understand this by reading the comment. [1] https://lists.linuxfoundation.org/pipermail/iommu/2018-December/031696.html Link: https://lkml.kernel.org/r/20211207093610.6406-1-miles.chen@mediatek.com Signed-off-by: Miles Chen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 78b58448f796..80f63c862be5 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -302,7 +302,9 @@ struct vm_area_struct; * lowest zone as a type of emergency reserve. * * %GFP_DMA32 is similar to %GFP_DMA except that the caller requires a 32-bit - * address. + * address. Note that kmalloc(..., GFP_DMA32) does not return DMA32 memory + * because the DMA32 kmalloc cache array is not implemented. + * (Reason: there is no such user in kernel). * * %GFP_HIGHUSER is for userspace allocations that may be mapped to userspace, * do not need to be directly accessible by the kernel but that cannot -- cgit v1.2.3 From 62b3107073646e0946bd97ff926832bafb846d17 Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Fri, 14 Jan 2022 14:07:37 -0800 Subject: mm_zone: add function to check if managed dma zone exists Patch series "Handle warning of allocation failure on DMA zone w/o managed pages", v4. **Problem observed: On x86_64, when crash is triggered and entering into kdump kernel, page allocation failure can always be seen. --------------------------------- DMA: preallocated 128 KiB GFP_KERNEL pool for atomic allocations swapper/0: page allocation failure: order:5, mode:0xcc1(GFP_KERNEL|GFP_DMA), nodemask=(null),cpuset=/,mems_allowed=0 CPU: 0 PID: 1 Comm: swapper/0 Call Trace: dump_stack+0x7f/0xa1 warn_alloc.cold+0x72/0xd6 ...... __alloc_pages+0x24d/0x2c0 ...... dma_atomic_pool_init+0xdb/0x176 do_one_initcall+0x67/0x320 ? rcu_read_lock_sched_held+0x3f/0x80 kernel_init_freeable+0x290/0x2dc ? rest_init+0x24f/0x24f kernel_init+0xa/0x111 ret_from_fork+0x22/0x30 Mem-Info: ------------------------------------ ***Root cause: In the current kernel, it assumes that DMA zone must have managed pages and try to request pages if CONFIG_ZONE_DMA is enabled. While this is not always true. E.g in kdump kernel of x86_64, only low 1M is presented and locked down at very early stage of boot, so that this low 1M won't be added into buddy allocator to become managed pages of DMA zone. This exception will always cause page allocation failure if page is requested from DMA zone. ***Investigation: This failure happens since below commit merged into linus's tree. 1a6a9044b967 x86/setup: Remove CONFIG_X86_RESERVE_LOW and reservelow= options 23721c8e92f7 x86/crash: Remove crash_reserve_low_1M() f1d4d47c5851 x86/setup: Always reserve the first 1M of RAM 7c321eb2b843 x86/kdump: Remove the backup region handling 6f599d84231f x86/kdump: Always reserve the low 1M when the crashkernel option is specified Before them, on x86_64, the low 640K area will be reused by kdump kernel. So in kdump kernel, the content of low 640K area is copied into a backup region for dumping before jumping into kdump. Then except of those firmware reserved region in [0, 640K], the left area will be added into buddy allocator to become available managed pages of DMA zone. However, after above commits applied, in kdump kernel of x86_64, the low 1M is reserved by memblock, but not released to buddy allocator. So any later page allocation requested from DMA zone will fail. At the beginning, if crashkernel is reserved, the low 1M need be locked down because AMD SME encrypts memory making the old backup region mechanims impossible when switching into kdump kernel. Later, it was also observed that there are BIOSes corrupting memory under 1M. To solve this, in commit f1d4d47c5851, the entire region of low 1M is always reserved after the real mode trampoline is allocated. Besides, recently, Intel engineer mentioned their TDX (Trusted domain extensions) which is under development in kernel also needs to lock down the low 1M. So we can't simply revert above commits to fix the page allocation failure from DMA zone as someone suggested. ***Solution: Currently, only DMA atomic pool and dma-kmalloc will initialize and request page allocation with GFP_DMA during bootup. So only initializ DMA atomic pool when DMA zone has available managed pages, otherwise just skip the initialization. For dma-kmalloc(), for the time being, let's mute the warning of allocation failure if requesting pages from DMA zone while no manged pages. Meanwhile, change code to use dma_alloc_xx/dma_map_xx API to replace kmalloc(GFP_DMA), or do not use GFP_DMA when calling kmalloc() if not necessary. Christoph is posting patches to fix those under drivers/scsi/. Finally, we can remove the need of dma-kmalloc() as people suggested. This patch (of 3): In some places of the current kernel, it assumes that dma zone must have managed pages if CONFIG_ZONE_DMA is enabled. While this is not always true. E.g in kdump kernel of x86_64, only low 1M is presented and locked down at very early stage of boot, so that there's no managed pages at all in DMA zone. This exception will always cause page allocation failure if page is requested from DMA zone. Here add function has_managed_dma() and the relevant helper functions to check if there's DMA zone with managed pages. It will be used in later patches. Link: https://lkml.kernel.org/r/20211223094435.248523-1-bhe@redhat.com Link: https://lkml.kernel.org/r/20211223094435.248523-2-bhe@redhat.com Fixes: 6f599d84231f ("x86/kdump: Always reserve the low 1M when the crashkernel option is specified") Signed-off-by: Baoquan He Reviewed-by: David Hildenbrand Acked-by: John Donnelly Cc: Christoph Hellwig Cc: Christoph Lameter Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com> Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Vlastimil Babka Cc: David Laight Cc: Borislav Petkov Cc: Marek Szyprowski Cc: Robin Murphy Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 9 +++++++++ mm/page_alloc.c | 15 +++++++++++++++ 2 files changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 936dc0b6c226..aed44e9b5d89 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1047,6 +1047,15 @@ static inline int is_highmem_idx(enum zone_type idx) #endif } +#ifdef CONFIG_ZONE_DMA +bool has_managed_dma(void); +#else +static inline bool has_managed_dma(void) +{ + return false; +} +#endif + /** * is_highmem - helper function to quickly check if a struct zone is a * highmem zone or not. This is an attempt to keep references diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 3eace0065ecc..e2ad2303f634 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -9518,3 +9518,18 @@ bool take_page_off_buddy(struct page *page) return ret; } #endif + +#ifdef CONFIG_ZONE_DMA +bool has_managed_dma(void) +{ + struct pglist_data *pgdat; + + for_each_online_pgdat(pgdat) { + struct zone *zone = &pgdat->node_zones[ZONE_DMA]; + + if (managed_zone(zone)) + return true; + } + return false; +} +#endif /* CONFIG_ZONE_DMA */ -- cgit v1.2.3 From f47761999052b1cc987dd3e3d3adf47997358fc0 Mon Sep 17 00:00:00 2001 From: Mina Almasry Date: Fri, 14 Jan 2022 14:07:48 -0800 Subject: hugetlb: add hugetlb.*.numa_stat file For hugetlb backed jobs/VMs it's critical to understand the numa information for the memory backing these jobs to deliver optimal performance. Currently this technically can be queried from /proc/self/numa_maps, but there are significant issues with that. Namely: 1. Memory can be mapped or unmapped. 2. numa_maps are per process and need to be aggregated across all processes in the cgroup. For shared memory this is more involved as the userspace needs to make sure it doesn't double count shared mappings. 3. I believe querying numa_maps needs to hold the mmap_lock which adds to the contention on this lock. For these reasons I propose simply adding hugetlb.*.numa_stat file, which shows the numa information of the cgroup similarly to memory.numa_stat. On cgroup-v2: cat /sys/fs/cgroup/unified/test/hugetlb.2MB.numa_stat total=2097152 N0=2097152 N1=0 On cgroup-v1: cat /sys/fs/cgroup/hugetlb/test/hugetlb.2MB.numa_stat total=2097152 N0=2097152 N1=0 hierarichal_total=2097152 N0=2097152 N1=0 This patch was tested manually by allocating hugetlb memory and querying the hugetlb.*.numa_stat file of the cgroup and its parents. [colin.i.king@googlemail.com: fix spelling mistake "hierarichal" -> "hierarchical"] Link: https://lkml.kernel.org/r/20211125090635.23508-1-colin.i.king@gmail.com [keescook@chromium.org: fix copy/paste array assignment] Link: https://lkml.kernel.org/r/20211203065647.2819707-1-keescook@chromium.org Link: https://lkml.kernel.org/r/20211123001020.4083653-1-almasrymina@google.com Signed-off-by: Mina Almasry Signed-off-by: Colin Ian King Signed-off-by: Kees Cook Reviewed-by: Shakeel Butt Reviewed-by: Muchun Song Reviewed-by: Mike Kravetz Cc: Shuah Khan Cc: Miaohe Lin Cc: Oscar Salvador Cc: Michal Hocko Cc: David Rientjes Cc: Jue Wang Cc: Yang Yao Cc: Joanna Li Cc: Cannon Matthews Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/cgroup-v1/hugetlb.rst | 4 + Documentation/admin-guide/cgroup-v2.rst | 5 + include/linux/hugetlb.h | 4 +- include/linux/hugetlb_cgroup.h | 7 ++ mm/hugetlb_cgroup.c | 133 ++++++++++++++++++++++-- 5 files changed, 141 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/cgroup-v1/hugetlb.rst b/Documentation/admin-guide/cgroup-v1/hugetlb.rst index 338f2c7d7a1c..0fa724d82abb 100644 --- a/Documentation/admin-guide/cgroup-v1/hugetlb.rst +++ b/Documentation/admin-guide/cgroup-v1/hugetlb.rst @@ -29,12 +29,14 @@ Brief summary of control files:: hugetlb..max_usage_in_bytes # show max "hugepagesize" hugetlb usage recorded hugetlb..usage_in_bytes # show current usage for "hugepagesize" hugetlb hugetlb..failcnt # show the number of allocation failure due to HugeTLB usage limit + hugetlb..numa_stat # show the numa information of the hugetlb memory charged to this cgroup For a system supporting three hugepage sizes (64k, 32M and 1G), the control files include:: hugetlb.1GB.limit_in_bytes hugetlb.1GB.max_usage_in_bytes + hugetlb.1GB.numa_stat hugetlb.1GB.usage_in_bytes hugetlb.1GB.failcnt hugetlb.1GB.rsvd.limit_in_bytes @@ -43,6 +45,7 @@ files include:: hugetlb.1GB.rsvd.failcnt hugetlb.64KB.limit_in_bytes hugetlb.64KB.max_usage_in_bytes + hugetlb.64KB.numa_stat hugetlb.64KB.usage_in_bytes hugetlb.64KB.failcnt hugetlb.64KB.rsvd.limit_in_bytes @@ -51,6 +54,7 @@ files include:: hugetlb.64KB.rsvd.failcnt hugetlb.32MB.limit_in_bytes hugetlb.32MB.max_usage_in_bytes + hugetlb.32MB.numa_stat hugetlb.32MB.usage_in_bytes hugetlb.32MB.failcnt hugetlb.32MB.rsvd.limit_in_bytes diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 4f400b03dddf..5aa368d165da 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -2266,6 +2266,11 @@ HugeTLB Interface Files are local to the cgroup i.e. not hierarchical. The file modified event generated on this file reflects only the local events. + hugetlb..numa_stat + Similar to memory.numa_stat, it shows the numa information of the + hugetlb pages of in this cgroup. Only active in + use hugetlb pages are included. The per-node values are in bytes. + Misc ---- diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 00351ccb49a3..d1897a69c540 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -622,8 +622,8 @@ struct hstate { #endif #ifdef CONFIG_CGROUP_HUGETLB /* cgroup control files */ - struct cftype cgroup_files_dfl[7]; - struct cftype cgroup_files_legacy[9]; + struct cftype cgroup_files_dfl[8]; + struct cftype cgroup_files_legacy[10]; #endif char name[HSTATE_NAME_LEN]; }; diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h index ba025ae27882..379344828e78 100644 --- a/include/linux/hugetlb_cgroup.h +++ b/include/linux/hugetlb_cgroup.h @@ -36,6 +36,11 @@ enum hugetlb_memory_event { HUGETLB_NR_MEMORY_EVENTS, }; +struct hugetlb_cgroup_per_node { + /* hugetlb usage in pages over all hstates. */ + unsigned long usage[HUGE_MAX_HSTATE]; +}; + struct hugetlb_cgroup { struct cgroup_subsys_state css; @@ -57,6 +62,8 @@ struct hugetlb_cgroup { /* Handle for "hugetlb.events.local" */ struct cgroup_file events_local_file[HUGE_MAX_HSTATE]; + + struct hugetlb_cgroup_per_node *nodeinfo[]; }; static inline struct hugetlb_cgroup * diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index 79d93534ef1e..f9942841df18 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -123,29 +123,58 @@ static void hugetlb_cgroup_init(struct hugetlb_cgroup *h_cgroup, } } +static void hugetlb_cgroup_free(struct hugetlb_cgroup *h_cgroup) +{ + int node; + + for_each_node(node) + kfree(h_cgroup->nodeinfo[node]); + kfree(h_cgroup); +} + static struct cgroup_subsys_state * hugetlb_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) { struct hugetlb_cgroup *parent_h_cgroup = hugetlb_cgroup_from_css(parent_css); struct hugetlb_cgroup *h_cgroup; + int node; + + h_cgroup = kzalloc(struct_size(h_cgroup, nodeinfo, nr_node_ids), + GFP_KERNEL); - h_cgroup = kzalloc(sizeof(*h_cgroup), GFP_KERNEL); if (!h_cgroup) return ERR_PTR(-ENOMEM); if (!parent_h_cgroup) root_h_cgroup = h_cgroup; + /* + * TODO: this routine can waste much memory for nodes which will + * never be onlined. It's better to use memory hotplug callback + * function. + */ + for_each_node(node) { + /* Set node_to_alloc to -1 for offline nodes. */ + int node_to_alloc = + node_state(node, N_NORMAL_MEMORY) ? node : -1; + h_cgroup->nodeinfo[node] = + kzalloc_node(sizeof(struct hugetlb_cgroup_per_node), + GFP_KERNEL, node_to_alloc); + if (!h_cgroup->nodeinfo[node]) + goto fail_alloc_nodeinfo; + } + hugetlb_cgroup_init(h_cgroup, parent_h_cgroup); return &h_cgroup->css; + +fail_alloc_nodeinfo: + hugetlb_cgroup_free(h_cgroup); + return ERR_PTR(-ENOMEM); } static void hugetlb_cgroup_css_free(struct cgroup_subsys_state *css) { - struct hugetlb_cgroup *h_cgroup; - - h_cgroup = hugetlb_cgroup_from_css(css); - kfree(h_cgroup); + hugetlb_cgroup_free(hugetlb_cgroup_from_css(css)); } /* @@ -289,7 +318,17 @@ static void __hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, return; __set_hugetlb_cgroup(page, h_cg, rsvd); - return; + if (!rsvd) { + unsigned long usage = + h_cg->nodeinfo[page_to_nid(page)]->usage[idx]; + /* + * This write is not atomic due to fetching usage and writing + * to it, but that's fine because we call this with + * hugetlb_lock held anyway. + */ + WRITE_ONCE(h_cg->nodeinfo[page_to_nid(page)]->usage[idx], + usage + nr_pages); + } } void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, @@ -328,8 +367,17 @@ static void __hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, if (rsvd) css_put(&h_cg->css); - - return; + else { + unsigned long usage = + h_cg->nodeinfo[page_to_nid(page)]->usage[idx]; + /* + * This write is not atomic due to fetching usage and writing + * to it, but that's fine because we call this with + * hugetlb_lock held anyway. + */ + WRITE_ONCE(h_cg->nodeinfo[page_to_nid(page)]->usage[idx], + usage - nr_pages); + } } void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, @@ -418,6 +466,59 @@ enum { RES_RSVD_FAILCNT, }; +static int hugetlb_cgroup_read_numa_stat(struct seq_file *seq, void *dummy) +{ + int nid; + struct cftype *cft = seq_cft(seq); + int idx = MEMFILE_IDX(cft->private); + bool legacy = MEMFILE_ATTR(cft->private); + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(seq_css(seq)); + struct cgroup_subsys_state *css; + unsigned long usage; + + if (legacy) { + /* Add up usage across all nodes for the non-hierarchical total. */ + usage = 0; + for_each_node_state(nid, N_MEMORY) + usage += READ_ONCE(h_cg->nodeinfo[nid]->usage[idx]); + seq_printf(seq, "total=%lu", usage * PAGE_SIZE); + + /* Simply print the per-node usage for the non-hierarchical total. */ + for_each_node_state(nid, N_MEMORY) + seq_printf(seq, " N%d=%lu", nid, + READ_ONCE(h_cg->nodeinfo[nid]->usage[idx]) * + PAGE_SIZE); + seq_putc(seq, '\n'); + } + + /* + * The hierarchical total is pretty much the value recorded by the + * counter, so use that. + */ + seq_printf(seq, "%stotal=%lu", legacy ? "hierarchical_" : "", + page_counter_read(&h_cg->hugepage[idx]) * PAGE_SIZE); + + /* + * For each node, transverse the css tree to obtain the hierarchical + * node usage. + */ + for_each_node_state(nid, N_MEMORY) { + usage = 0; + rcu_read_lock(); + css_for_each_descendant_pre(css, &h_cg->css) { + usage += READ_ONCE(hugetlb_cgroup_from_css(css) + ->nodeinfo[nid] + ->usage[idx]); + } + rcu_read_unlock(); + seq_printf(seq, " N%d=%lu", nid, usage * PAGE_SIZE); + } + + seq_putc(seq, '\n'); + + return 0; +} + static u64 hugetlb_cgroup_read_u64(struct cgroup_subsys_state *css, struct cftype *cft) { @@ -668,8 +769,14 @@ static void __init __hugetlb_cgroup_file_dfl_init(int idx) events_local_file[idx]); cft->flags = CFTYPE_NOT_ON_ROOT; - /* NULL terminate the last cft */ + /* Add the numa stat file */ cft = &h->cgroup_files_dfl[6]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.numa_stat", buf); + cft->seq_show = hugetlb_cgroup_read_numa_stat; + cft->flags = CFTYPE_NOT_ON_ROOT; + + /* NULL terminate the last cft */ + cft = &h->cgroup_files_dfl[7]; memset(cft, 0, sizeof(*cft)); WARN_ON(cgroup_add_dfl_cftypes(&hugetlb_cgrp_subsys, @@ -739,8 +846,14 @@ static void __init __hugetlb_cgroup_file_legacy_init(int idx) cft->write = hugetlb_cgroup_reset; cft->read_u64 = hugetlb_cgroup_read_u64; - /* NULL terminate the last cft */ + /* Add the numa stat file */ cft = &h->cgroup_files_legacy[8]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.numa_stat", buf); + cft->private = MEMFILE_PRIVATE(idx, 1); + cft->seq_show = hugetlb_cgroup_read_numa_stat; + + /* NULL terminate the last cft */ + cft = &h->cgroup_files_legacy[9]; memset(cft, 0, sizeof(*cft)); WARN_ON(cgroup_add_legacy_cftypes(&hugetlb_cgrp_subsys, -- cgit v1.2.3 From e9ea874a8ffb0f8ebed4f4981531a32c5b663d79 Mon Sep 17 00:00:00 2001 From: Yang Yang Date: Fri, 14 Jan 2022 14:07:55 -0800 Subject: mm/vmstat: add events for THP max_ptes_* exceeds There are interfaces to adjust max_ptes_none, max_ptes_swap, max_ptes_shared values, see /sys/kernel/mm/transparent_hugepage/khugepaged/. But system administrator may not know which value is the best. So Add those events to support adjusting max_ptes_* to suitable values. For example, if default max_ptes_swap value causes too much failures, and system uses zram whose IO is fast, administrator could increase max_ptes_swap until THP_SCAN_EXCEED_SWAP_PTE not increase anymore. Link: https://lkml.kernel.org/r/20211225094036.574157-1-yang.yang29@zte.com.cn Signed-off-by: Yang Yang Cc: "Huang, Ying" Cc: Dave Hansen Cc: Minchan Kim Cc: Saravanan D Cc: Mike Kravetz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vm_event_item.h | 3 +++ mm/khugepaged.c | 7 +++++++ mm/vmstat.c | 3 +++ 3 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index a185cc75ff52..7b2363388bfa 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -98,6 +98,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, THP_SPLIT_PAGE_FAILED, THP_DEFERRED_SPLIT_PAGE, THP_SPLIT_PMD, + THP_SCAN_EXCEED_NONE_PTE, + THP_SCAN_EXCEED_SWAP_PTE, + THP_SCAN_EXCEED_SHARED_PTE, #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD THP_SPLIT_PUD, #endif diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 698ea19775ac..02071f213c58 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -618,6 +618,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, continue; } else { result = SCAN_EXCEED_NONE_PTE; + count_vm_event(THP_SCAN_EXCEED_NONE_PTE); goto out; } } @@ -636,6 +637,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, if (page_mapcount(page) > 1 && ++shared > khugepaged_max_ptes_shared) { result = SCAN_EXCEED_SHARED_PTE; + count_vm_event(THP_SCAN_EXCEED_SHARED_PTE); goto out; } @@ -1253,6 +1255,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, continue; } else { result = SCAN_EXCEED_SWAP_PTE; + count_vm_event(THP_SCAN_EXCEED_SWAP_PTE); goto out_unmap; } } @@ -1262,6 +1265,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, continue; } else { result = SCAN_EXCEED_NONE_PTE; + count_vm_event(THP_SCAN_EXCEED_NONE_PTE); goto out_unmap; } } @@ -1290,6 +1294,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, if (page_mapcount(page) > 1 && ++shared > khugepaged_max_ptes_shared) { result = SCAN_EXCEED_SHARED_PTE; + count_vm_event(THP_SCAN_EXCEED_SHARED_PTE); goto out_unmap; } @@ -2000,6 +2005,7 @@ static void khugepaged_scan_file(struct mm_struct *mm, if (xa_is_value(page)) { if (++swap > khugepaged_max_ptes_swap) { result = SCAN_EXCEED_SWAP_PTE; + count_vm_event(THP_SCAN_EXCEED_SWAP_PTE); break; } continue; @@ -2046,6 +2052,7 @@ static void khugepaged_scan_file(struct mm_struct *mm, if (result == SCAN_SUCCEED) { if (present < HPAGE_PMD_NR - khugepaged_max_ptes_none) { result = SCAN_EXCEED_NONE_PTE; + count_vm_event(THP_SCAN_EXCEED_NONE_PTE); } else { node = khugepaged_find_target_node(); collapse_file(mm, file, start, hpage, node); diff --git a/mm/vmstat.c b/mm/vmstat.c index d701c335628c..4057372745d0 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1353,6 +1353,9 @@ const char * const vmstat_text[] = { "thp_split_page_failed", "thp_deferred_split_page", "thp_split_pmd", + "thp_scan_exceed_none_pte", + "thp_scan_exceed_swap_pte", + "thp_scan_exceed_share_pte", #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD "thp_split_pud", #endif -- cgit v1.2.3 From e4b424b7ec8791087375bb1f2480a3ba05d21e0b Mon Sep 17 00:00:00 2001 From: Gang Li Date: Fri, 14 Jan 2022 14:08:07 -0800 Subject: vmscan: make drop_slab_node static drop_slab_node is only used in drop_slab. So remove it's declaration from header file and add keyword static for it's definition. Link: https://lkml.kernel.org/r/20211111062445.5236-1-ligang.bdlg@bytedance.com Signed-off-by: Gang Li Reviewed-by: David Hildenbrand Reviewed-by: Muchun Song Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 - mm/vmscan.c | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index cef65f9cbdf2..eb67eb699b78 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3122,7 +3122,6 @@ int drop_caches_sysctl_handler(struct ctl_table *, int, void *, size_t *, #endif void drop_slab(void); -void drop_slab_node(int nid); #ifndef CONFIG_MMU #define randomize_va_space 0 diff --git a/mm/vmscan.c b/mm/vmscan.c index 700434db5735..090bfb605ecf 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -951,7 +951,7 @@ out: return freed; } -void drop_slab_node(int nid) +static void drop_slab_node(int nid) { unsigned long freed; int shift = 0; -- cgit v1.2.3 From c6018b4b254971863bd0ad36bb5e7d0fa0f0ddb0 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Fri, 14 Jan 2022 14:08:17 -0800 Subject: mm/mempolicy: add set_mempolicy_home_node syscall This syscall can be used to set a home node for the MPOL_BIND and MPOL_PREFERRED_MANY memory policy. Users should use this syscall after setting up a memory policy for the specified range as shown below. mbind(p, nr_pages * page_size, MPOL_BIND, new_nodes->maskp, new_nodes->size + 1, 0); sys_set_mempolicy_home_node((unsigned long)p, nr_pages * page_size, home_node, 0); The syscall allows specifying a home node/preferred node from which kernel will fulfill memory allocation requests first. For address range with MPOL_BIND memory policy, if nodemask specifies more than one node, page allocations will come from the node in the nodemask with sufficient free memory that is closest to the home node/preferred node. For MPOL_PREFERRED_MANY if the nodemask specifies more than one node, page allocation will come from the node in the nodemask with sufficient free memory that is closest to the home node/preferred node. If there is not enough memory in all the nodes specified in the nodemask, the allocation will be attempted from the closest numa node to the home node in the system. This helps applications to hint at a memory allocation preference node and fallback to _only_ a set of nodes if the memory is not available on the preferred node. Fallback allocation is attempted from the node which is nearest to the preferred node. This helps applications to have control on memory allocation numa nodes and avoids default fallback to slow memory NUMA nodes. For example a system with NUMA nodes 1,2 and 3 with DRAM memory and 10, 11 and 12 of slow memory new_nodes = numa_bitmask_alloc(nr_nodes); numa_bitmask_setbit(new_nodes, 1); numa_bitmask_setbit(new_nodes, 2); numa_bitmask_setbit(new_nodes, 3); p = mmap(NULL, nr_pages * page_size, protflag, mapflag, -1, 0); mbind(p, nr_pages * page_size, MPOL_BIND, new_nodes->maskp, new_nodes->size + 1, 0); sys_set_mempolicy_home_node(p, nr_pages * page_size, 2, 0); This will allocate from nodes closer to node 2 and will make sure the kernel will only allocate from nodes 1, 2, and 3. Memory will not be allocated from slow memory nodes 10, 11, and 12. This differs from default MPOL_BIND behavior in that with default MPOL_BIND the allocation will be attempted from node closer to the local node. One of the reasons to specify a home node is to allow allocations from cpu less NUMA node and its nearby NUMA nodes. With MPOL_PREFERRED_MANY on the other hand will first try to allocate from the closest node to node 2 from the node list 1, 2 and 3. If those nodes don't have enough memory, kernel will allocate from slow memory node 10, 11 and 12 which ever is closer to node 2. Link: https://lkml.kernel.org/r/20211202123810.267175-3-aneesh.kumar@linux.ibm.com Signed-off-by: Aneesh Kumar K.V Cc: Ben Widawsky Cc: Dave Hansen Cc: Feng Tang Cc: Michal Hocko Cc: Andrea Arcangeli Cc: Mel Gorman Cc: Mike Kravetz Cc: Randy Dunlap Cc: Vlastimil Babka Cc: Andi Kleen Cc: Dan Williams Cc: Huang Ying Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- .../admin-guide/mm/numa_memory_policy.rst | 16 ++++- include/linux/mempolicy.h | 1 + mm/mempolicy.c | 79 ++++++++++++++++++++++ 3 files changed, 95 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/mm/numa_memory_policy.rst b/Documentation/admin-guide/mm/numa_memory_policy.rst index 64fd0ba0d057..5a6afecbb0d0 100644 --- a/Documentation/admin-guide/mm/numa_memory_policy.rst +++ b/Documentation/admin-guide/mm/numa_memory_policy.rst @@ -408,7 +408,7 @@ follows: Memory Policy APIs ================== -Linux supports 3 system calls for controlling memory policy. These APIS +Linux supports 4 system calls for controlling memory policy. These APIS always affect only the calling task, the calling task's address space, or some shared object mapped into the calling task's address space. @@ -460,6 +460,20 @@ requested via the 'flags' argument. See the mbind(2) man page for more details. +Set home node for a Range of Task's Address Spacec:: + + long sys_set_mempolicy_home_node(unsigned long start, unsigned long len, + unsigned long home_node, + unsigned long flags); + +sys_set_mempolicy_home_node set the home node for a VMA policy present in the +task's address range. The system call updates the home node only for the existing +mempolicy range. Other address ranges are ignored. A home node is the NUMA node +closest to which page allocation will come from. Specifying the home node override +the default allocation policy to allocate memory close to the local node for an +executing CPU. + + Memory Policy Command Line Interface ==================================== diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 3c7595e81150..668389b4b53d 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -46,6 +46,7 @@ struct mempolicy { unsigned short mode; /* See MPOL_* above */ unsigned short flags; /* See set_mempolicy() MPOL_F_* above */ nodemask_t nodes; /* interleave/bind/perfer */ + int home_node; /* Home node to use for MPOL_BIND and MPOL_PREFERRED_MANY */ union { nodemask_t cpuset_mems_allowed; /* relative to these nodes */ diff --git a/mm/mempolicy.c b/mm/mempolicy.c index de70f119984a..fc6cae7926f3 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -296,6 +296,7 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, atomic_set(&policy->refcnt, 1); policy->mode = mode; policy->flags = flags; + policy->home_node = NUMA_NO_NODE; return policy; } @@ -1478,6 +1479,77 @@ static long kernel_mbind(unsigned long start, unsigned long len, return do_mbind(start, len, lmode, mode_flags, &nodes, flags); } +SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, len, + unsigned long, home_node, unsigned long, flags) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + struct mempolicy *new; + unsigned long vmstart; + unsigned long vmend; + unsigned long end; + int err = -ENOENT; + + start = untagged_addr(start); + if (start & ~PAGE_MASK) + return -EINVAL; + /* + * flags is used for future extension if any. + */ + if (flags != 0) + return -EINVAL; + + /* + * Check home_node is online to avoid accessing uninitialized + * NODE_DATA. + */ + if (home_node >= MAX_NUMNODES || !node_online(home_node)) + return -EINVAL; + + len = (len + PAGE_SIZE - 1) & PAGE_MASK; + end = start + len; + + if (end < start) + return -EINVAL; + if (end == start) + return 0; + mmap_write_lock(mm); + vma = find_vma(mm, start); + for (; vma && vma->vm_start < end; vma = vma->vm_next) { + + vmstart = max(start, vma->vm_start); + vmend = min(end, vma->vm_end); + new = mpol_dup(vma_policy(vma)); + if (IS_ERR(new)) { + err = PTR_ERR(new); + break; + } + /* + * Only update home node if there is an existing vma policy + */ + if (!new) + continue; + + /* + * If any vma in the range got policy other than MPOL_BIND + * or MPOL_PREFERRED_MANY we return error. We don't reset + * the home node for vmas we already updated before. + */ + if (new->mode != MPOL_BIND && new->mode != MPOL_PREFERRED_MANY) { + err = -EOPNOTSUPP; + break; + } + + new->home_node = home_node; + err = mbind_range(mm, vmstart, vmend, new); + mpol_put(new); + if (err) + break; + } + mmap_write_unlock(mm); + return err; +} + SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, unsigned long, mode, const unsigned long __user *, nmask, unsigned long, maxnode, unsigned int, flags) @@ -1802,6 +1874,11 @@ static int policy_node(gfp_t gfp, struct mempolicy *policy, int nd) WARN_ON_ONCE(policy->mode == MPOL_BIND && (gfp & __GFP_THISNODE)); } + if ((policy->mode == MPOL_BIND || + policy->mode == MPOL_PREFERRED_MANY) && + policy->home_node != NUMA_NO_NODE) + return policy->home_node; + return nd; } @@ -2344,6 +2421,8 @@ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b) return false; if (a->flags != b->flags) return false; + if (a->home_node != b->home_node) + return false; if (mpol_store_user_nodemask(a)) if (!nodes_equal(a->w.user_nodemask, b->w.user_nodemask)) return false; -- cgit v1.2.3 From 21b084fdf2a49ca1634e8e360e9ab6f9ff0dee11 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Fri, 14 Jan 2022 14:08:21 -0800 Subject: mm/mempolicy: wire up syscall set_mempolicy_home_node Link: https://lkml.kernel.org/r/20211202123810.267175-4-aneesh.kumar@linux.ibm.com Signed-off-by: Aneesh Kumar K.V Cc: Ben Widawsky Cc: Dave Hansen Cc: Feng Tang Cc: Michal Hocko Cc: Andrea Arcangeli Cc: Mel Gorman Cc: Mike Kravetz Cc: Randy Dunlap Cc: Vlastimil Babka Cc: Andi Kleen Cc: Dan Williams Cc: Huang Ying Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/kernel/syscalls/syscall.tbl | 1 + arch/arm/tools/syscall.tbl | 1 + arch/arm64/include/asm/unistd.h | 2 +- arch/arm64/include/asm/unistd32.h | 2 ++ arch/ia64/kernel/syscalls/syscall.tbl | 1 + arch/m68k/kernel/syscalls/syscall.tbl | 1 + arch/microblaze/kernel/syscalls/syscall.tbl | 1 + arch/mips/kernel/syscalls/syscall_n32.tbl | 1 + arch/mips/kernel/syscalls/syscall_n64.tbl | 1 + arch/mips/kernel/syscalls/syscall_o32.tbl | 1 + arch/parisc/kernel/syscalls/syscall.tbl | 1 + arch/powerpc/kernel/syscalls/syscall.tbl | 1 + arch/s390/kernel/syscalls/syscall.tbl | 1 + arch/sh/kernel/syscalls/syscall.tbl | 1 + arch/sparc/kernel/syscalls/syscall.tbl | 1 + arch/x86/entry/syscalls/syscall_32.tbl | 1 + arch/x86/entry/syscalls/syscall_64.tbl | 1 + arch/xtensa/kernel/syscalls/syscall.tbl | 1 + include/linux/syscalls.h | 3 +++ include/uapi/asm-generic/unistd.h | 5 ++++- kernel/sys_ni.c | 1 + 21 files changed, 27 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index ca5a32228cd6..3515bc4f16a4 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -489,3 +489,4 @@ # 557 reserved for memfd_secret 558 common process_mrelease sys_process_mrelease 559 common futex_waitv sys_futex_waitv +560 common set_mempolicy_home_node sys_ni_syscall diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index 543100151f2b..ac964612d8b0 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -463,3 +463,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 6bdb5f5db438..4e65da3445c7 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -38,7 +38,7 @@ #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5) #define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800) -#define __NR_compat_syscalls 450 +#define __NR_compat_syscalls 451 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 41ea1195e44b..604a2053d006 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -905,6 +905,8 @@ __SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self) __SYSCALL(__NR_process_mrelease, sys_process_mrelease) #define __NR_futex_waitv 449 __SYSCALL(__NR_futex_waitv, sys_futex_waitv) +#define __NR_set_mempolicy_home_node 450 +__SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node) /* * Please add new compat syscalls above this comment and update diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl index 707ae121f6d3..78b1d03e86e1 100644 --- a/arch/ia64/kernel/syscalls/syscall.tbl +++ b/arch/ia64/kernel/syscalls/syscall.tbl @@ -370,3 +370,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 45bc32a41b90..b1f3940bc298 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -449,3 +449,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index 2204bde3ce4a..820145e47350 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -455,3 +455,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index 72d02d363f36..253ff994ed2e 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -388,3 +388,4 @@ # 447 reserved for memfd_secret 448 n32 process_mrelease sys_process_mrelease 449 n32 futex_waitv sys_futex_waitv +450 n32 set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index e2c481fcede6..3f1886ad9d80 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -364,3 +364,4 @@ # 447 reserved for memfd_secret 448 n64 process_mrelease sys_process_mrelease 449 n64 futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 3714c97b2643..8f243e35a7b2 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -437,3 +437,4 @@ # 447 reserved for memfd_secret 448 o32 process_mrelease sys_process_mrelease 449 o32 futex_waitv sys_futex_waitv +450 o32 set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index 358c00000755..68b46fe2f17c 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -447,3 +447,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 15109af9d075..2600b4237292 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -529,3 +529,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 nospu set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index ed9c5c2eafad..799147658dee 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -452,3 +452,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index d9539d28bdaa..2de85c977f54 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -452,3 +452,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index 46adabcb1720..4398cc6fb68d 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -495,3 +495,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 7e25543693de..320480a8db4f 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -454,3 +454,4 @@ 447 i386 memfd_secret sys_memfd_secret 448 i386 process_mrelease sys_process_mrelease 449 i386 futex_waitv sys_futex_waitv +450 i386 set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index fe8f8dd157b4..c84d12608cd2 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -371,6 +371,7 @@ 447 common memfd_secret sys_memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node # # Due to a historical design error, certain syscalls are numbered differently diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index 3e3e1a506bed..52c94ab5c205 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -420,3 +420,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 528a478dbda8..819c0cb00b6d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1057,6 +1057,9 @@ asmlinkage long sys_landlock_add_rule(int ruleset_fd, enum landlock_rule_type ru const void __user *rule_attr, __u32 flags); asmlinkage long sys_landlock_restrict_self(int ruleset_fd, __u32 flags); asmlinkage long sys_memfd_secret(unsigned int flags); +asmlinkage long sys_set_mempolicy_home_node(unsigned long start, unsigned long len, + unsigned long home_node, + unsigned long flags); /* * Architecture-specific system calls diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 4557a8b6086f..1c48b0ae3ba3 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -883,8 +883,11 @@ __SYSCALL(__NR_process_mrelease, sys_process_mrelease) #define __NR_futex_waitv 449 __SYSCALL(__NR_futex_waitv, sys_futex_waitv) +#define __NR_set_mempolicy_home_node 450 +__SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node) + #undef __NR_syscalls -#define __NR_syscalls 450 +#define __NR_syscalls 451 /* * 32 bit systems traditionally used different diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index d1944258cfc0..a492f159624f 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -297,6 +297,7 @@ COND_SYSCALL(get_mempolicy); COND_SYSCALL(set_mempolicy); COND_SYSCALL(migrate_pages); COND_SYSCALL(move_pages); +COND_SYSCALL(set_mempolicy_home_node); COND_SYSCALL(perf_event_open); COND_SYSCALL(accept4); -- cgit v1.2.3 From c9fdc4d5487a16bd1f003fc8b66e91f88efb50e6 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 14 Jan 2022 14:09:06 -0800 Subject: mm/hwpoison: remove MF_MSG_BUDDY_2ND and MF_MSG_POISONED_HUGE These action_page_types are no longer used, so remove them. Link: https://lkml.kernel.org/r/20211115084006.3728254-3-naoya.horiguchi@linux.dev Signed-off-by: Naoya Horiguchi Acked-by: Yang Shi Cc: "Aneesh Kumar K.V" Cc: David Hildenbrand Cc: Ding Hui Cc: Miaohe Lin Cc: Michal Hocko Cc: Oscar Salvador Cc: Peter Xu Cc: Tony Luck Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 -- include/ras/ras_event.h | 2 -- mm/memory-failure.c | 2 -- 3 files changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index eb67eb699b78..7f594da84aca 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3201,7 +3201,6 @@ enum mf_action_page_type { MF_MSG_KERNEL_HIGH_ORDER, MF_MSG_SLAB, MF_MSG_DIFFERENT_COMPOUND, - MF_MSG_POISONED_HUGE, MF_MSG_HUGE, MF_MSG_FREE_HUGE, MF_MSG_NON_PMD_HUGE, @@ -3216,7 +3215,6 @@ enum mf_action_page_type { MF_MSG_CLEAN_LRU, MF_MSG_TRUNCATED_LRU, MF_MSG_BUDDY, - MF_MSG_BUDDY_2ND, MF_MSG_DAX, MF_MSG_UNSPLIT_THP, MF_MSG_UNKNOWN, diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h index 0bdbc0d17d2f..d0337a41141c 100644 --- a/include/ras/ras_event.h +++ b/include/ras/ras_event.h @@ -358,7 +358,6 @@ TRACE_EVENT(aer_event, EM ( MF_MSG_KERNEL_HIGH_ORDER, "high-order kernel page" ) \ EM ( MF_MSG_SLAB, "kernel slab page" ) \ EM ( MF_MSG_DIFFERENT_COMPOUND, "different compound page after locking" ) \ - EM ( MF_MSG_POISONED_HUGE, "huge page already hardware poisoned" ) \ EM ( MF_MSG_HUGE, "huge page" ) \ EM ( MF_MSG_FREE_HUGE, "free huge page" ) \ EM ( MF_MSG_NON_PMD_HUGE, "non-pmd-sized huge page" ) \ @@ -373,7 +372,6 @@ TRACE_EVENT(aer_event, EM ( MF_MSG_CLEAN_LRU, "clean LRU page" ) \ EM ( MF_MSG_TRUNCATED_LRU, "already truncated LRU page" ) \ EM ( MF_MSG_BUDDY, "free buddy page" ) \ - EM ( MF_MSG_BUDDY_2ND, "free buddy page (2nd try)" ) \ EM ( MF_MSG_DAX, "dax page" ) \ EM ( MF_MSG_UNSPLIT_THP, "unsplit thp" ) \ EMe ( MF_MSG_UNKNOWN, "unknown page" ) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 607785491a52..810328fe8adb 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -723,7 +723,6 @@ static const char * const action_page_types[] = { [MF_MSG_KERNEL_HIGH_ORDER] = "high-order kernel page", [MF_MSG_SLAB] = "kernel slab page", [MF_MSG_DIFFERENT_COMPOUND] = "different compound page after locking", - [MF_MSG_POISONED_HUGE] = "huge page already hardware poisoned", [MF_MSG_HUGE] = "huge page", [MF_MSG_FREE_HUGE] = "free huge page", [MF_MSG_NON_PMD_HUGE] = "non-pmd-sized huge page", @@ -738,7 +737,6 @@ static const char * const action_page_types[] = { [MF_MSG_CLEAN_LRU] = "clean LRU page", [MF_MSG_TRUNCATED_LRU] = "already truncated LRU page", [MF_MSG_BUDDY] = "free buddy page", - [MF_MSG_BUDDY_2ND] = "free buddy page (2nd try)", [MF_MSG_DAX] = "dax page", [MF_MSG_UNSPLIT_THP] = "unsplit thp", [MF_MSG_UNKNOWN] = "unknown page", -- cgit v1.2.3 From bf181c582588f8f7406d52f2ee228539b465f173 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 14 Jan 2022 14:09:09 -0800 Subject: mm/hwpoison: fix unpoison_memory() After recent soft-offline rework, error pages can be taken off from buddy allocator, but the existing unpoison_memory() does not properly undo the operation. Moreover, due to the recent change on __get_hwpoison_page(), get_page_unless_zero() is hardly called for hwpoisoned pages. So __get_hwpoison_page() highly likely returns -EBUSY (meaning to fail to grab page refcount) and unpoison just clears PG_hwpoison without releasing a refcount. That does not lead to a critical issue like kernel panic, but unpoisoned pages never get back to buddy (leaked permanently), which is not good. To (partially) fix this, we need to identify "taken off" pages from other types of hwpoisoned pages. We can't use refcount or page flags for this purpose, so a pseudo flag is defined by hacking ->private field. Someone might think that put_page() is enough to cancel taken-off pages, but the normal free path contains some operations not suitable for the current purpose, and can fire VM_BUG_ON(). Note that unpoison_memory() is now supposed to be cancel hwpoison events injected only by madvise() or /sys/devices/system/memory/{hard,soft}_offline_page, not by MCE injection, so please don't try to use unpoison when testing with MCE injection. [lkp@intel.com: report build failure for ARCH=i386] Link: https://lkml.kernel.org/r/20211115084006.3728254-4-naoya.horiguchi@linux.dev Signed-off-by: Naoya Horiguchi Reviewed-by: Yang Shi Cc: David Hildenbrand Cc: Oscar Salvador Cc: Michal Hocko Cc: Ding Hui Cc: Tony Luck Cc: "Aneesh Kumar K.V" Cc: Miaohe Lin Cc: Peter Xu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + include/linux/page-flags.h | 4 ++ mm/memory-failure.c | 109 +++++++++++++++++++++++++++++++++++++-------- mm/page_alloc.c | 27 +++++++++++ 4 files changed, 122 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 7f594da84aca..d4fb49a5d60d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3174,6 +3174,7 @@ enum mf_flags { MF_ACTION_REQUIRED = 1 << 1, MF_MUST_KILL = 1 << 2, MF_SOFT_OFFLINE = 1 << 3, + MF_UNPOISON = 1 << 4, }; extern int memory_failure(unsigned long pfn, int flags); extern void memory_failure_queue(unsigned long pfn, int flags); diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 18423c2157e8..7e2b90dc7d3f 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -522,7 +522,11 @@ PAGEFLAG_FALSE(Uncached, uncached) PAGEFLAG(HWPoison, hwpoison, PF_ANY) TESTSCFLAG(HWPoison, hwpoison, PF_ANY) #define __PG_HWPOISON (1UL << PG_hwpoison) +#define MAGIC_HWPOISON 0x48575053U /* HWPS */ +extern void SetPageHWPoisonTakenOff(struct page *page); +extern void ClearPageHWPoisonTakenOff(struct page *page); extern bool take_page_off_buddy(struct page *page); +extern bool put_page_back_buddy(struct page *page); #else PAGEFLAG_FALSE(HWPoison, hwpoison) #define __PG_HWPOISON 0 diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 810328fe8adb..6a2b4b86b679 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1160,6 +1160,22 @@ static int page_action(struct page_state *ps, struct page *p, return (result == MF_RECOVERED || result == MF_DELAYED) ? 0 : -EBUSY; } +static inline bool PageHWPoisonTakenOff(struct page *page) +{ + return PageHWPoison(page) && page_private(page) == MAGIC_HWPOISON; +} + +void SetPageHWPoisonTakenOff(struct page *page) +{ + set_page_private(page, MAGIC_HWPOISON); +} + +void ClearPageHWPoisonTakenOff(struct page *page) +{ + if (PageHWPoison(page)) + set_page_private(page, 0); +} + /* * Return true if a page type of a given page is supported by hwpoison * mechanism (while handling could fail), otherwise false. This function @@ -1262,6 +1278,27 @@ out: return ret; } +static int __get_unpoison_page(struct page *page) +{ + struct page *head = compound_head(page); + int ret = 0; + bool hugetlb = false; + + ret = get_hwpoison_huge_page(head, &hugetlb); + if (hugetlb) + return ret; + + /* + * PageHWPoisonTakenOff pages are not only marked as PG_hwpoison, + * but also isolated from buddy freelist, so need to identify the + * state and have to cancel both operations to unpoison. + */ + if (PageHWPoisonTakenOff(page)) + return -EHWPOISON; + + return get_page_unless_zero(page) ? 1 : 0; +} + /** * get_hwpoison_page() - Get refcount for memory error handling * @p: Raw error page (hit by memory error) @@ -1278,18 +1315,26 @@ out: * extra care for the error page's state (as done in __get_hwpoison_page()), * and has some retry logic in get_any_page(). * + * When called from unpoison_memory(), the caller should already ensure that + * the given page has PG_hwpoison. So it's never reused for other page + * allocations, and __get_unpoison_page() never races with them. + * * Return: 0 on failure, * 1 on success for in-use pages in a well-defined state, * -EIO for pages on which we can not handle memory errors, * -EBUSY when get_hwpoison_page() has raced with page lifecycle - * operations like allocation and free. + * operations like allocation and free, + * -EHWPOISON when the page is hwpoisoned and taken off from buddy. */ static int get_hwpoison_page(struct page *p, unsigned long flags) { int ret; zone_pcp_disable(page_zone(p)); - ret = get_any_page(p, flags); + if (flags & MF_UNPOISON) + ret = __get_unpoison_page(p); + else + ret = get_any_page(p, flags); zone_pcp_enable(page_zone(p)); return ret; @@ -1937,6 +1982,28 @@ core_initcall(memory_failure_init); pr_info(fmt, pfn); \ }) +static inline int clear_page_hwpoison(struct ratelimit_state *rs, struct page *p) +{ + if (TestClearPageHWPoison(p)) { + unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n", + page_to_pfn(p), rs); + num_poisoned_pages_dec(); + return 1; + } + return 0; +} + +static inline int unpoison_taken_off_page(struct ratelimit_state *rs, + struct page *p) +{ + if (put_page_back_buddy(p)) { + unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n", + page_to_pfn(p), rs); + return 0; + } + return -EBUSY; +} + /** * unpoison_memory - Unpoison a previously poisoned page * @pfn: Page number of the to be unpoisoned page @@ -1953,9 +2020,7 @@ int unpoison_memory(unsigned long pfn) { struct page *page; struct page *p; - int freeit = 0; - int ret = 0; - unsigned long flags = 0; + int ret = -EBUSY; static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); @@ -1991,24 +2056,30 @@ int unpoison_memory(unsigned long pfn) goto unlock_mutex; } - if (!get_hwpoison_page(p, flags)) { - if (TestClearPageHWPoison(p)) - num_poisoned_pages_dec(); - unpoison_pr_info("Unpoison: Software-unpoisoned free page %#lx\n", - pfn, &unpoison_rs); + if (PageSlab(page) || PageTable(page)) goto unlock_mutex; - } - if (TestClearPageHWPoison(page)) { - unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n", - pfn, &unpoison_rs); - num_poisoned_pages_dec(); - freeit = 1; - } + ret = get_hwpoison_page(p, MF_UNPOISON); + if (!ret) { + if (clear_page_hwpoison(&unpoison_rs, page)) + ret = 0; + else + ret = -EBUSY; + } else if (ret < 0) { + if (ret == -EHWPOISON) { + ret = unpoison_taken_off_page(&unpoison_rs, p); + } else + unpoison_pr_info("Unpoison: failed to grab page %#lx\n", + pfn, &unpoison_rs); + } else { + int freeit = clear_page_hwpoison(&unpoison_rs, p); - put_page(page); - if (freeit && !(pfn == my_zero_pfn(0) && page_count(p) == 1)) put_page(page); + if (freeit && !(pfn == my_zero_pfn(0) && page_count(p) == 1)) { + put_page(page); + ret = 0; + } + } unlock_mutex: mutex_unlock(&mf_mutex); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 99fc65c532f0..d4205e5e41d1 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -9508,6 +9509,7 @@ bool take_page_off_buddy(struct page *page) del_page_from_free_list(page_head, zone, page_order); break_down_buddy_pages(zone, page_head, page, 0, page_order, migratetype); + SetPageHWPoisonTakenOff(page); if (!is_migrate_isolate(migratetype)) __mod_zone_freepage_state(zone, -1, migratetype); ret = true; @@ -9519,6 +9521,31 @@ bool take_page_off_buddy(struct page *page) spin_unlock_irqrestore(&zone->lock, flags); return ret; } + +/* + * Cancel takeoff done by take_page_off_buddy(). + */ +bool put_page_back_buddy(struct page *page) +{ + struct zone *zone = page_zone(page); + unsigned long pfn = page_to_pfn(page); + unsigned long flags; + int migratetype = get_pfnblock_migratetype(page, pfn); + bool ret = false; + + spin_lock_irqsave(&zone->lock, flags); + if (put_page_testzero(page)) { + ClearPageHWPoisonTakenOff(page); + __free_one_page(page, pfn, zone, 0, migratetype, FPI_NONE); + if (TestClearPageHWPoison(page)) { + num_poisoned_pages_dec(); + ret = true; + } + } + spin_unlock_irqrestore(&zone->lock, flags); + + return ret; +} #endif #ifdef CONFIG_ZONE_DMA -- cgit v1.2.3 From 5ee2fa2f063649570c702164f47a558a3432dd9e Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Fri, 14 Jan 2022 14:09:16 -0800 Subject: mm/rmap: fix potential batched TLB flush race In theory, the following race is possible for batched TLB flushing. CPU0 CPU1 ---- ---- shrink_page_list() unmap zap_pte_range() flush_tlb_batched_pending() flush_tlb_mm() try_to_unmap() set_tlb_ubc_flush_pending() mm->tlb_flush_batched = true mm->tlb_flush_batched = false After the TLB is flushed on CPU1 via flush_tlb_mm() and before mm->tlb_flush_batched is set to false, some PTE is unmapped on CPU0 and the TLB flushing is pended. Then the pended TLB flushing will be lost. Although both set_tlb_ubc_flush_pending() and flush_tlb_batched_pending() are called with PTL locked, different PTL instances may be used. Because the race window is really small, and the lost TLB flushing will cause problem only if a TLB entry is inserted before the unmapping in the race window, the race is only theoretical. But the fix is simple and cheap too. Syzbot has reported this too as follows: ================================================================== BUG: KCSAN: data-race in flush_tlb_batched_pending / try_to_unmap_one write to 0xffff8881072cfbbc of 1 bytes by task 17406 on cpu 1: flush_tlb_batched_pending+0x5f/0x80 mm/rmap.c:691 madvise_free_pte_range+0xee/0x7d0 mm/madvise.c:594 walk_pmd_range mm/pagewalk.c:128 [inline] walk_pud_range mm/pagewalk.c:205 [inline] walk_p4d_range mm/pagewalk.c:240 [inline] walk_pgd_range mm/pagewalk.c:277 [inline] __walk_page_range+0x981/0x1160 mm/pagewalk.c:379 walk_page_range+0x131/0x300 mm/pagewalk.c:475 madvise_free_single_vma mm/madvise.c:734 [inline] madvise_dontneed_free mm/madvise.c:822 [inline] madvise_vma mm/madvise.c:996 [inline] do_madvise+0xe4a/0x1140 mm/madvise.c:1202 __do_sys_madvise mm/madvise.c:1228 [inline] __se_sys_madvise mm/madvise.c:1226 [inline] __x64_sys_madvise+0x5d/0x70 mm/madvise.c:1226 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae write to 0xffff8881072cfbbc of 1 bytes by task 71 on cpu 0: set_tlb_ubc_flush_pending mm/rmap.c:636 [inline] try_to_unmap_one+0x60e/0x1220 mm/rmap.c:1515 rmap_walk_anon+0x2fb/0x470 mm/rmap.c:2301 try_to_unmap+0xec/0x110 shrink_page_list+0xe91/0x2620 mm/vmscan.c:1719 shrink_inactive_list+0x3fb/0x730 mm/vmscan.c:2394 shrink_list mm/vmscan.c:2621 [inline] shrink_lruvec+0x3c9/0x710 mm/vmscan.c:2940 shrink_node_memcgs+0x23e/0x410 mm/vmscan.c:3129 shrink_node+0x8f6/0x1190 mm/vmscan.c:3252 kswapd_shrink_node mm/vmscan.c:4022 [inline] balance_pgdat+0x702/0xd30 mm/vmscan.c:4213 kswapd+0x200/0x340 mm/vmscan.c:4473 kthread+0x2c7/0x2e0 kernel/kthread.c:327 ret_from_fork+0x1f/0x30 value changed: 0x01 -> 0x00 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 71 Comm: kswapd0 Not tainted 5.16.0-rc1-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 ================================================================== [akpm@linux-foundation.org: tweak comments] Link: https://lkml.kernel.org/r/20211201021104.126469-1-ying.huang@intel.com Signed-off-by: "Huang, Ying" Reported-by: syzbot+aa5bebed695edaccf0df@syzkaller.appspotmail.com Cc: Nadav Amit Cc: Mel Gorman Cc: Andrea Arcangeli Cc: Andy Lutomirski Cc: Dave Hansen Cc: Will Deacon Cc: Yu Zhao Cc: Marco Elver Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 2 +- mm/rmap.c | 43 ++++++++++++++++++++++++++++++++++++------- 2 files changed, 37 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6a89f128c990..e3b0476a4fda 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -647,7 +647,7 @@ struct mm_struct { atomic_t tlb_flush_pending; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* See flush_tlb_batched_pending() */ - bool tlb_flush_batched; + atomic_t tlb_flush_batched; #endif struct uprobes_state uprobes_state; #ifdef CONFIG_PREEMPT_RT diff --git a/mm/rmap.c b/mm/rmap.c index 163ac4e6bcee..6a1e8c7f6213 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -621,9 +621,20 @@ void try_to_unmap_flush_dirty(void) try_to_unmap_flush(); } +/* + * Bits 0-14 of mm->tlb_flush_batched record pending generations. + * Bits 16-30 of mm->tlb_flush_batched bit record flushed generations. + */ +#define TLB_FLUSH_BATCH_FLUSHED_SHIFT 16 +#define TLB_FLUSH_BATCH_PENDING_MASK \ + ((1 << (TLB_FLUSH_BATCH_FLUSHED_SHIFT - 1)) - 1) +#define TLB_FLUSH_BATCH_PENDING_LARGE \ + (TLB_FLUSH_BATCH_PENDING_MASK / 2) + static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; + int batch, nbatch; arch_tlbbatch_add_mm(&tlb_ubc->arch, mm); tlb_ubc->flush_required = true; @@ -633,7 +644,22 @@ static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable) * before the PTE is cleared. */ barrier(); - mm->tlb_flush_batched = true; + batch = atomic_read(&mm->tlb_flush_batched); +retry: + if ((batch & TLB_FLUSH_BATCH_PENDING_MASK) > TLB_FLUSH_BATCH_PENDING_LARGE) { + /* + * Prevent `pending' from catching up with `flushed' because of + * overflow. Reset `pending' and `flushed' to be 1 and 0 if + * `pending' becomes large. + */ + nbatch = atomic_cmpxchg(&mm->tlb_flush_batched, batch, 1); + if (nbatch != batch) { + batch = nbatch; + goto retry; + } + } else { + atomic_inc(&mm->tlb_flush_batched); + } /* * If the PTE was dirty then it's best to assume it's writable. The @@ -680,15 +706,18 @@ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) */ void flush_tlb_batched_pending(struct mm_struct *mm) { - if (data_race(mm->tlb_flush_batched)) { - flush_tlb_mm(mm); + int batch = atomic_read(&mm->tlb_flush_batched); + int pending = batch & TLB_FLUSH_BATCH_PENDING_MASK; + int flushed = batch >> TLB_FLUSH_BATCH_FLUSHED_SHIFT; + if (pending != flushed) { + flush_tlb_mm(mm); /* - * Do not allow the compiler to re-order the clearing of - * tlb_flush_batched before the tlb is flushed. + * If the new TLB flushing is pending during flushing, leave + * mm->tlb_flush_batched as is, to avoid losing flushing. */ - barrier(); - mm->tlb_flush_batched = false; + atomic_cmpxchg(&mm->tlb_flush_batched, batch, + pending | (pending << TLB_FLUSH_BATCH_FLUSHED_SHIFT)); } } #else -- cgit v1.2.3 From cab0a7c115546a4865fb7439558af9077a569574 Mon Sep 17 00:00:00 2001 From: Ting Liu Date: Fri, 14 Jan 2022 14:09:28 -0800 Subject: mm: make some vars and functions static or __init "page_idle_ops" as a global var, but its scope of use within this document. So it should be static. "page_ext_ops" is a var used in the kernel initial phase. And other functions are aslo used in the kernel initial phase. So they should be __init or __initdata to reclaim memory. Link: https://lkml.kernel.org/r/20211217095023.67293-1-liuting.0x7c00@bytedance.com Signed-off-by: Ting Liu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_idle.h | 1 - mm/page_ext.c | 4 ++-- mm/page_owner.c | 4 ++-- 3 files changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page_idle.h b/include/linux/page_idle.h index 83abf95e9fa7..4663dfed1293 100644 --- a/include/linux/page_idle.h +++ b/include/linux/page_idle.h @@ -13,7 +13,6 @@ * If there is not enough space to store Idle and Young bits in page flags, use * page ext flags instead. */ -extern struct page_ext_operations page_idle_ops; static inline bool folio_test_young(struct folio *folio) { diff --git a/mm/page_ext.c b/mm/page_ext.c index bee3240604dc..2e66d934d63f 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -64,12 +64,12 @@ static bool need_page_idle(void) { return true; } -struct page_ext_operations page_idle_ops = { +static struct page_ext_operations page_idle_ops __initdata = { .need = need_page_idle, }; #endif -static struct page_ext_operations *page_ext_ops[] = { +static struct page_ext_operations *page_ext_ops[] __initdata = { #ifdef CONFIG_PAGE_OWNER &page_owner_ops, #endif diff --git a/mm/page_owner.c b/mm/page_owner.c index 4f924957ce7a..5eea061bb1e5 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -46,7 +46,7 @@ static int __init early_page_owner_param(char *buf) } early_param("page_owner", early_page_owner_param); -static bool need_page_owner(void) +static __init bool need_page_owner(void) { return page_owner_enabled; } @@ -75,7 +75,7 @@ static noinline void register_early_stack(void) early_handle = create_dummy_stack(); } -static void init_page_owner(void) +static __init void init_page_owner(void) { if (!page_owner_enabled) return; -- cgit v1.2.3 From cdeed009f3bceee41f73f0137db785fd29a05cb8 Mon Sep 17 00:00:00 2001 From: Xin Hao Date: Fri, 14 Jan 2022 14:09:44 -0800 Subject: mm/damon: remove some unneeded function definitions in damon.h In damon.h some func definitions about VA & PA can only be used in its own file, so there no need to define in the header file, and the header file will look cleaner. If other files later need these functions, the prototypes can be added to damon.h at that time. [sj@kernel.org: remove unnecessary function prototype position changes] Link: https://lkml.kernel.org/r/20211118114827.20052-1-sj@kernel.org Link: https://lkml.kernel.org/r/45fd5b3ef6cce8e28dbc1c92f9dc845ccfc949d7.1636989871.git.xhao@linux.alibaba.com Signed-off-by: Xin Hao Signed-off-by: SeongJae Park Reviewed-by: SeongJae Park Cc: Muchun Song Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 21 --------------------- mm/damon/paddr.c | 11 ++++++----- mm/damon/vaddr.c | 18 ++++++++++-------- 3 files changed, 16 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index b4d4be3cc987..1d1be348f506 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -461,34 +461,13 @@ int damon_stop(struct damon_ctx **ctxs, int nr_ctxs); #endif /* CONFIG_DAMON */ #ifdef CONFIG_DAMON_VADDR - -/* Monitoring primitives for virtual memory address spaces */ -void damon_va_init(struct damon_ctx *ctx); -void damon_va_update(struct damon_ctx *ctx); -void damon_va_prepare_access_checks(struct damon_ctx *ctx); -unsigned int damon_va_check_accesses(struct damon_ctx *ctx); bool damon_va_target_valid(void *t); -void damon_va_cleanup(struct damon_ctx *ctx); -int damon_va_apply_scheme(struct damon_ctx *context, struct damon_target *t, - struct damon_region *r, struct damos *scheme); -int damon_va_scheme_score(struct damon_ctx *context, struct damon_target *t, - struct damon_region *r, struct damos *scheme); void damon_va_set_primitives(struct damon_ctx *ctx); - #endif /* CONFIG_DAMON_VADDR */ #ifdef CONFIG_DAMON_PADDR - -/* Monitoring primitives for the physical memory address space */ -void damon_pa_prepare_access_checks(struct damon_ctx *ctx); -unsigned int damon_pa_check_accesses(struct damon_ctx *ctx); bool damon_pa_target_valid(void *t); -int damon_pa_apply_scheme(struct damon_ctx *context, struct damon_target *t, - struct damon_region *r, struct damos *scheme); -int damon_pa_scheme_score(struct damon_ctx *context, struct damon_target *t, - struct damon_region *r, struct damos *scheme); void damon_pa_set_primitives(struct damon_ctx *ctx); - #endif /* CONFIG_DAMON_PADDR */ #endif /* _DAMON_H */ diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c index a496d6f203d6..4318134cbc4c 100644 --- a/mm/damon/paddr.c +++ b/mm/damon/paddr.c @@ -73,7 +73,7 @@ static void __damon_pa_prepare_access_check(struct damon_ctx *ctx, damon_pa_mkold(r->sampling_addr); } -void damon_pa_prepare_access_checks(struct damon_ctx *ctx) +static void damon_pa_prepare_access_checks(struct damon_ctx *ctx) { struct damon_target *t; struct damon_region *r; @@ -192,7 +192,7 @@ static void __damon_pa_check_access(struct damon_ctx *ctx, last_addr = r->sampling_addr; } -unsigned int damon_pa_check_accesses(struct damon_ctx *ctx) +static unsigned int damon_pa_check_accesses(struct damon_ctx *ctx) { struct damon_target *t; struct damon_region *r; @@ -213,7 +213,7 @@ bool damon_pa_target_valid(void *t) return true; } -int damon_pa_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, +static int damon_pa_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, struct damon_region *r, struct damos *scheme) { unsigned long addr; @@ -246,8 +246,9 @@ int damon_pa_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, return 0; } -int damon_pa_scheme_score(struct damon_ctx *context, struct damon_target *t, - struct damon_region *r, struct damos *scheme) +static int damon_pa_scheme_score(struct damon_ctx *context, + struct damon_target *t, struct damon_region *r, + struct damos *scheme) { switch (scheme->action) { case DAMOS_PAGEOUT: diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index 73c5d1aafda6..a9d3b4d96e29 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -272,7 +272,7 @@ static void __damon_va_init_regions(struct damon_ctx *ctx, } /* Initialize '->regions_list' of every target (task) */ -void damon_va_init(struct damon_ctx *ctx) +static void damon_va_init(struct damon_ctx *ctx) { struct damon_target *t; @@ -292,7 +292,8 @@ void damon_va_init(struct damon_ctx *ctx) * * Returns true if it is. */ -static bool damon_intersect(struct damon_region *r, struct damon_addr_range *re) +static bool damon_intersect(struct damon_region *r, + struct damon_addr_range *re) { return !(r->ar.end <= re->start || re->end <= r->ar.start); } @@ -356,7 +357,7 @@ static void damon_va_apply_three_regions(struct damon_target *t, /* * Update regions for current memory mappings */ -void damon_va_update(struct damon_ctx *ctx) +static void damon_va_update(struct damon_ctx *ctx) { struct damon_addr_range three_regions[3]; struct damon_target *t; @@ -418,7 +419,7 @@ static void __damon_va_prepare_access_check(struct damon_ctx *ctx, damon_va_mkold(mm, r->sampling_addr); } -void damon_va_prepare_access_checks(struct damon_ctx *ctx) +static void damon_va_prepare_access_checks(struct damon_ctx *ctx) { struct damon_target *t; struct mm_struct *mm; @@ -539,7 +540,7 @@ static void __damon_va_check_access(struct damon_ctx *ctx, last_addr = r->sampling_addr; } -unsigned int damon_va_check_accesses(struct damon_ctx *ctx) +static unsigned int damon_va_check_accesses(struct damon_ctx *ctx) { struct damon_target *t; struct mm_struct *mm; @@ -603,7 +604,7 @@ out: } #endif /* CONFIG_ADVISE_SYSCALLS */ -int damon_va_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, +static int damon_va_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, struct damon_region *r, struct damos *scheme) { int madv_action; @@ -633,8 +634,9 @@ int damon_va_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, return damos_madvise(t, r, madv_action); } -int damon_va_scheme_score(struct damon_ctx *context, struct damon_target *t, - struct damon_region *r, struct damos *scheme) +static int damon_va_scheme_score(struct damon_ctx *context, + struct damon_target *t, struct damon_region *r, + struct damos *scheme) { switch (scheme->action) { -- cgit v1.2.3 From 9b2a38d6ef25c1748e3964b0ff30a89e4ed26583 Mon Sep 17 00:00:00 2001 From: Xin Hao Date: Fri, 14 Jan 2022 14:09:53 -0800 Subject: mm/damon: move damon_rand() definition into damon.h damon_rand() is called in three files:damon/core.c, damon/ paddr.c, damon/vaddr.c, i think there is no need to redefine this twice, So move it to damon.h will be a good choice. Link: https://lkml.kernel.org/r/20211202075859.51341-1-xhao@linux.alibaba.com Signed-off-by: Xin Hao Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 4 ++++ mm/damon/core.c | 4 ---- mm/damon/prmtv-common.h | 4 ---- 3 files changed, 4 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 1d1be348f506..3e91a597a1aa 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -11,12 +11,16 @@ #include #include #include +#include /* Minimal region size. Every damon_region is aligned by this. */ #define DAMON_MIN_REGION PAGE_SIZE /* Max priority score for DAMON-based operation schemes */ #define DAMOS_MAX_SCORE (99) +/* Get a random number in [l, r) */ +#define damon_rand(l, r) (l + prandom_u32_max(r - l)) + /** * struct damon_addr_range - Represents an address region of [@start, @end). * @start: Start address of the region (inclusive). diff --git a/mm/damon/core.c b/mm/damon/core.c index 04b8df7fd9e9..61e844d15b13 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include @@ -23,9 +22,6 @@ #define DAMON_MIN_REGION 1 #endif -/* Get a random number in [l, r) */ -#define damon_rand(l, r) (l + prandom_u32_max(r - l)) - static DEFINE_MUTEX(damon_lock); static int nr_running_ctxs; diff --git a/mm/damon/prmtv-common.h b/mm/damon/prmtv-common.h index 61f27037603e..e790cb5f8fe0 100644 --- a/mm/damon/prmtv-common.h +++ b/mm/damon/prmtv-common.h @@ -6,10 +6,6 @@ */ #include -#include - -/* Get a random number in [l, r) */ -#define damon_rand(l, r) (l + prandom_u32_max(r - l)) struct page *damon_get_page(unsigned long pfn); -- cgit v1.2.3 From 234d68732b6c135087bdebfa0630a43ae8c27758 Mon Sep 17 00:00:00 2001 From: Xin Hao Date: Fri, 14 Jan 2022 14:09:56 -0800 Subject: mm/damon: modify damon_rand() macro to static inline function damon_rand() cannot be implemented as a macro. Example: damon_rand(a++, b); The value of 'a' will be incremented twice, This is obviously unreasonable, So there fix it. Link: https://lkml.kernel.org/r/110ffcd4e420c86c42b41ce2bc9f0fe6a4f32cd3.1638795127.git.xhao@linux.alibaba.com Fixes: b9a6ac4e4ede ("mm/damon: adaptively adjust regions") Signed-off-by: Xin Hao Reported-by: Andrew Morton Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 3e91a597a1aa..e2c8152985b7 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -19,7 +19,10 @@ #define DAMOS_MAX_SCORE (99) /* Get a random number in [l, r) */ -#define damon_rand(l, r) (l + prandom_u32_max(r - l)) +static inline unsigned long damon_rand(unsigned long l, unsigned long r) +{ + return l + prandom_u32_max(r - l); +} /** * struct damon_addr_range - Represents an address region of [@start, @end). -- cgit v1.2.3 From 88f86dcfa454784f7de550966c60fc78a3e95d6d Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 14 Jan 2022 14:09:59 -0800 Subject: mm/damon: convert macro functions to static inline functions Patch series "mm/damon: Misc cleanups". This patchset contains miscellaneous cleanups for DAMON's macro functions and documentation. This patch (of 6): This commit converts macro functions in DAMON to static inline functions, for better type checking, code documentation, etc[1]. [1] https://lore.kernel.org/linux-mm/20211202151213.6ec830863342220da4141bc5@linux-foundation.org/ Link: https://lkml.kernel.org/r/20211209131806.19317-1-sj@kernel.org Link: https://lkml.kernel.org/r/20211209131806.19317-2-sj@kernel.org Signed-off-by: SeongJae Park Cc: Jonathan Corbet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 18 ++++++++++++------ mm/damon/core.c | 5 ++++- mm/damon/vaddr.c | 6 ++++-- 3 files changed, 20 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index e2c8152985b7..2dbc1f545da2 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -399,14 +399,20 @@ struct damon_ctx { struct list_head schemes; }; -#define damon_next_region(r) \ - (container_of(r->list.next, struct damon_region, list)) +static inline struct damon_region *damon_next_region(struct damon_region *r) +{ + return container_of(r->list.next, struct damon_region, list); +} -#define damon_prev_region(r) \ - (container_of(r->list.prev, struct damon_region, list)) +static inline struct damon_region *damon_prev_region(struct damon_region *r) +{ + return container_of(r->list.prev, struct damon_region, list); +} -#define damon_last_region(t) \ - (list_last_entry(&t->regions_list, struct damon_region, list)) +static inline struct damon_region *damon_last_region(struct damon_target *t) +{ + return list_last_entry(&t->regions_list, struct damon_region, list); +} #define damon_for_each_region(r, t) \ list_for_each_entry(r, &t->regions_list, list) diff --git a/mm/damon/core.c b/mm/damon/core.c index 61e844d15b13..4515cf82c433 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -729,7 +729,10 @@ static void kdamond_apply_schemes(struct damon_ctx *c) } } -#define sz_damon_region(r) (r->ar.end - r->ar.start) +static inline unsigned long sz_damon_region(struct damon_region *r) +{ + return r->ar.end - r->ar.start; +} /* * Merge two adjacent regions into one region diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index 78ff2bcb66eb..68d9e4134816 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -26,8 +26,10 @@ * 't->id' should be the pointer to the relevant 'struct pid' having reference * count. Caller must put the returned task, unless it is NULL. */ -#define damon_get_task_struct(t) \ - (get_pid_task((struct pid *)t->id, PIDTYPE_PID)) +static inline struct task_struct *damon_get_task_struct(struct damon_target *t) +{ + return get_pid_task((struct pid *)t->id, PIDTYPE_PID); +} /* * Get the mm_struct of the given target -- cgit v1.2.3 From f4c6d22c6cf282ef7d24a724b9bd978ee2b74fc6 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 14 Jan 2022 14:10:14 -0800 Subject: mm/damon: remove a mistakenly added comment for a future feature Due to a mistake in patches reordering, a comment for a future feature called 'arbitrary monitoring target support'[1], which is still under development, has added. Because it only introduces confusion and we don't have a plan to post the patches soon, this commit removes the mistakenly added part. [1] https://lore.kernel.org/linux-mm/20201215115448.25633-3-sjpark@amazon.com/ Link: https://lkml.kernel.org/r/20211209131806.19317-7-sj@kernel.org Fixes: 1f366e421c8f ("mm/damon/core: implement DAMON-based Operation Schemes (DAMOS)") Signed-off-by: SeongJae Park Cc: Jonathan Corbet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 2dbc1f545da2..97f4a224e950 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -281,7 +281,7 @@ struct damon_ctx; * as an integer in [0, &DAMOS_MAX_SCORE]. * @apply_scheme is called from @kdamond when a region for user provided * DAMON-based operation scheme is found. It should apply the scheme's action - * to the region. This is not used for &DAMON_ARBITRARY_TARGET case. + * to the region. * @target_valid should check whether the target is still valid for the * monitoring. * @cleanup is called from @kdamond just before its termination. -- cgit v1.2.3 From 0e92c2ee9f459542c5384d9cfab24873c3dd6398 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 14 Jan 2022 14:10:17 -0800 Subject: mm/damon/schemes: account scheme actions that successfully applied Patch series "mm/damon/schemes: Extend stats for better online analysis and tuning". To help online access pattern analysis and tuning of DAMON-based Operation Schemes (DAMOS), DAMOS provides simple statistics for each scheme. Introduction of DAMOS time/space quota further made the tuning easier by making the risk management easier. However, that also made understanding of the working schemes a little bit more difficult. For an example, progress of a given scheme can now be throttled by not only the aggressiveness of the target access pattern, but also the time/space quotas. So, when a scheme is showing unexpectedly slow progress, it's difficult to know by what the progress of the scheme is throttled, with currently provided statistics. This patchset extends the statistics to contain some metrics that can be helpful for such online schemes analysis and tuning (patches 1-2), exports those to users (patches 3 and 5), and add documents (patches 4 and 6). This patch (of 6): DAMON-based operation schemes (DAMOS) stats provide only the number and the amount of regions that the action of the scheme has tried to be applied. Because the action could be failed for some reasons, the currently provided information is sometimes not useful or convenient enough for schemes profiling and tuning. To improve this situation, this commit extends the DAMOS stats to provide the number and the amount of regions that the action has successfully applied. Link: https://lkml.kernel.org/r/20211210150016.35349-1-sj@kernel.org Link: https://lkml.kernel.org/r/20211210150016.35349-2-sj@kernel.org Signed-off-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 28 +++++++++++++++++++++------- mm/damon/core.c | 13 ++++++++----- mm/damon/dbgfs.c | 2 +- mm/damon/paddr.c | 13 +++++++------ mm/damon/vaddr.c | 30 ++++++++++++++++-------------- 5 files changed, 53 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 97f4a224e950..e0ad3d9aaeed 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -192,6 +192,20 @@ struct damos_watermarks { bool activated; }; +/** + * struct damos_stat - Statistics on a given scheme. + * @nr_tried: Total number of regions that the scheme is tried to be applied. + * @sz_tried: Total size of regions that the scheme is tried to be applied. + * @nr_applied: Total number of regions that the scheme is applied. + * @sz_applied: Total size of regions that the scheme is applied. + */ +struct damos_stat { + unsigned long nr_tried; + unsigned long sz_tried; + unsigned long nr_applied; + unsigned long sz_applied; +}; + /** * struct damos - Represents a Data Access Monitoring-based Operation Scheme. * @min_sz_region: Minimum size of target regions. @@ -203,8 +217,7 @@ struct damos_watermarks { * @action: &damo_action to be applied to the target regions. * @quota: Control the aggressiveness of this scheme. * @wmarks: Watermarks for automated (in)activation of this scheme. - * @stat_count: Total number of regions that this scheme is applied. - * @stat_sz: Total size of regions that this scheme is applied. + * @stat: Statistics of this scheme. * @list: List head for siblings. * * For each aggregation interval, DAMON finds regions which fit in the @@ -235,8 +248,7 @@ struct damos { enum damos_action action; struct damos_quota quota; struct damos_watermarks wmarks; - unsigned long stat_count; - unsigned long stat_sz; + struct damos_stat stat; struct list_head list; }; @@ -281,7 +293,8 @@ struct damon_ctx; * as an integer in [0, &DAMOS_MAX_SCORE]. * @apply_scheme is called from @kdamond when a region for user provided * DAMON-based operation scheme is found. It should apply the scheme's action - * to the region. + * to the region and return bytes of the region that the action is successfully + * applied. * @target_valid should check whether the target is still valid for the * monitoring. * @cleanup is called from @kdamond just before its termination. @@ -295,8 +308,9 @@ struct damon_primitive { int (*get_scheme_score)(struct damon_ctx *context, struct damon_target *t, struct damon_region *r, struct damos *scheme); - int (*apply_scheme)(struct damon_ctx *context, struct damon_target *t, - struct damon_region *r, struct damos *scheme); + unsigned long (*apply_scheme)(struct damon_ctx *context, + struct damon_target *t, struct damon_region *r, + struct damos *scheme); bool (*target_valid)(void *target); void (*cleanup)(struct damon_ctx *context); }; diff --git a/mm/damon/core.c b/mm/damon/core.c index 4515cf82c433..d745bf28509f 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -102,8 +102,7 @@ struct damos *damon_new_scheme( scheme->min_age_region = min_age_region; scheme->max_age_region = max_age_region; scheme->action = action; - scheme->stat_count = 0; - scheme->stat_sz = 0; + scheme->stat = (struct damos_stat){}; INIT_LIST_HEAD(&scheme->list); scheme->quota.ms = quota->ms; @@ -574,6 +573,7 @@ static void damon_do_apply_schemes(struct damon_ctx *c, struct damos_quota *quota = &s->quota; unsigned long sz = r->ar.end - r->ar.start; struct timespec64 begin, end; + unsigned long sz_applied = 0; if (!s->wmarks.activated) continue; @@ -627,7 +627,7 @@ static void damon_do_apply_schemes(struct damon_ctx *c, damon_split_region_at(c, t, r, sz); } ktime_get_coarse_ts64(&begin); - c->primitive.apply_scheme(c, t, r, s); + sz_applied = c->primitive.apply_scheme(c, t, r, s); ktime_get_coarse_ts64(&end); quota->total_charged_ns += timespec64_to_ns(&end) - timespec64_to_ns(&begin); @@ -641,8 +641,11 @@ static void damon_do_apply_schemes(struct damon_ctx *c, r->age = 0; update_stat: - s->stat_count++; - s->stat_sz += sz; + s->stat.nr_tried++; + s->stat.sz_tried += sz; + if (sz_applied) + s->stat.nr_applied++; + s->stat.sz_applied += sz_applied; } } diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index bf36a2756cfb..9318b52d0b46 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -117,7 +117,7 @@ static ssize_t sprint_schemes(struct damon_ctx *c, char *buf, ssize_t len) s->quota.weight_age, s->wmarks.metric, s->wmarks.interval, s->wmarks.high, s->wmarks.mid, s->wmarks.low, - s->stat_count, s->stat_sz); + s->stat.nr_tried, s->stat.sz_tried); if (!rc) return -ENOMEM; diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c index 4318134cbc4c..5e8244f65a1a 100644 --- a/mm/damon/paddr.c +++ b/mm/damon/paddr.c @@ -213,14 +213,15 @@ bool damon_pa_target_valid(void *t) return true; } -static int damon_pa_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, - struct damon_region *r, struct damos *scheme) +static unsigned long damon_pa_apply_scheme(struct damon_ctx *ctx, + struct damon_target *t, struct damon_region *r, + struct damos *scheme) { - unsigned long addr; + unsigned long addr, applied; LIST_HEAD(page_list); if (scheme->action != DAMOS_PAGEOUT) - return -EINVAL; + return 0; for (addr = r->ar.start; addr < r->ar.end; addr += PAGE_SIZE) { struct page *page = damon_get_page(PHYS_PFN(addr)); @@ -241,9 +242,9 @@ static int damon_pa_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, put_page(page); } } - reclaim_pages(&page_list); + applied = reclaim_pages(&page_list); cond_resched(); - return 0; + return applied * PAGE_SIZE; } static int damon_pa_scheme_score(struct damon_ctx *context, diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index 68d9e4134816..a10df3fd3d02 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -572,32 +572,34 @@ bool damon_va_target_valid(void *target) } #ifndef CONFIG_ADVISE_SYSCALLS -static int damos_madvise(struct damon_target *target, struct damon_region *r, - int behavior) +static unsigned long damos_madvise(struct damon_target *target, + struct damon_region *r, int behavior) { - return -EINVAL; + return 0; } #else -static int damos_madvise(struct damon_target *target, struct damon_region *r, - int behavior) +static unsigned long damos_madvise(struct damon_target *target, + struct damon_region *r, int behavior) { struct mm_struct *mm; - int ret = -ENOMEM; + unsigned long start = PAGE_ALIGN(r->ar.start); + unsigned long len = PAGE_ALIGN(r->ar.end - r->ar.start); + unsigned long applied; mm = damon_get_mm(target); if (!mm) - goto out; + return 0; - ret = do_madvise(mm, PAGE_ALIGN(r->ar.start), - PAGE_ALIGN(r->ar.end - r->ar.start), behavior); + applied = do_madvise(mm, start, len, behavior) ? 0 : len; mmput(mm); -out: - return ret; + + return applied; } #endif /* CONFIG_ADVISE_SYSCALLS */ -static int damon_va_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, - struct damon_region *r, struct damos *scheme) +static unsigned long damon_va_apply_scheme(struct damon_ctx *ctx, + struct damon_target *t, struct damon_region *r, + struct damos *scheme) { int madv_action; @@ -620,7 +622,7 @@ static int damon_va_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, case DAMOS_STAT: return 0; default: - return -EINVAL; + return 0; } return damos_madvise(t, r, madv_action); -- cgit v1.2.3 From 6268eac34ca30af7f6313504d556ec7fcd295621 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 14 Jan 2022 14:10:20 -0800 Subject: mm/damon/schemes: account how many times quota limit has exceeded If the time/space quotas of a given DAMON-based operation scheme is too small, the scheme could show unexpectedly slow progress. However, there is no good way to notice the case in runtime. This commit extends the DAMOS stat to provide how many times the quota limits exceeded so that the users can easily notice the case and tune the scheme. Link: https://lkml.kernel.org/r/20211210150016.35349-3-sj@kernel.org Signed-off-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 2 ++ mm/damon/core.c | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index e0ad3d9aaeed..af648388e759 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -198,12 +198,14 @@ struct damos_watermarks { * @sz_tried: Total size of regions that the scheme is tried to be applied. * @nr_applied: Total number of regions that the scheme is applied. * @sz_applied: Total size of regions that the scheme is applied. + * @qt_exceeds: Total number of times the quota of the scheme has exceeded. */ struct damos_stat { unsigned long nr_tried; unsigned long sz_tried; unsigned long nr_applied; unsigned long sz_applied; + unsigned long qt_exceeds; }; /** diff --git a/mm/damon/core.c b/mm/damon/core.c index d745bf28509f..d5120b326e1b 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -693,6 +693,8 @@ static void kdamond_apply_schemes(struct damon_ctx *c) if (time_after_eq(jiffies, quota->charged_from + msecs_to_jiffies( quota->reset_interval))) { + if (quota->esz && quota->charged_sz >= quota->esz) + s->stat.qt_exceeds++; quota->total_charged_sz += quota->charged_sz; quota->charged_from = jiffies; quota->charged_sz = 0; -- cgit v1.2.3 From 2cd4b8e10cc31eadb5b10b1d73b3f28156f3776c Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Fri, 14 Jan 2022 14:10:38 -0800 Subject: mm/damon: move the implementation of damon_insert_region to damon.h Usually, inline function is declared static since it should sit between storage and type. And implement it in a header file if used by multiple files. And this change also fixes compile issue when backport damon to 5.10. mm/damon/vaddr.c: In function `damon_va_evenly_split_region': ./include/linux/damon.h:425:13: error: inlining failed in call to `always_inline' `damon_insert_region': function body not available 425 | inline void damon_insert_region(struct damon_region *r, | ^~~~~~~~~~~~~~~~~~~ mm/damon/vaddr.c:86:3: note: called from here 86 | damon_insert_region(n, r, next, t); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Link: https://lkml.kernel.org/r/20211223085703.6142-1-guoqing.jiang@linux.dev Signed-off-by: Guoqing Jiang Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 13 +++++++++++-- mm/damon/core.c | 11 ----------- 2 files changed, 11 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index af648388e759..5e1e3a128b77 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -451,9 +451,18 @@ static inline struct damon_region *damon_last_region(struct damon_target *t) #ifdef CONFIG_DAMON struct damon_region *damon_new_region(unsigned long start, unsigned long end); -inline void damon_insert_region(struct damon_region *r, + +/* + * Add a region between two other regions + */ +static inline void damon_insert_region(struct damon_region *r, struct damon_region *prev, struct damon_region *next, - struct damon_target *t); + struct damon_target *t) +{ + __list_add(&r->list, &prev->list, &next->list); + t->nr_regions++; +} + void damon_add_region(struct damon_region *r, struct damon_target *t); void damon_destroy_region(struct damon_region *r, struct damon_target *t); diff --git a/mm/damon/core.c b/mm/damon/core.c index d5120b326e1b..6482d510dcbe 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -49,17 +49,6 @@ struct damon_region *damon_new_region(unsigned long start, unsigned long end) return region; } -/* - * Add a region between two other regions - */ -inline void damon_insert_region(struct damon_region *r, - struct damon_region *prev, struct damon_region *next, - struct damon_target *t) -{ - __list_add(&r->list, &prev->list, &next->list); - t->nr_regions++; -} - void damon_add_region(struct damon_region *r, struct damon_target *t) { list_add_tail(&r->list, &t->regions_list); -- cgit v1.2.3