From 09cea6195073ee1d0f076d907d9249045757245d Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Fri, 5 Nov 2021 13:39:44 -0700 Subject: [PATCH 001/166] arm64: support page mapping percpu first chunk allocator Percpu embedded first chunk allocator is the firstly option, but it could fails on ARM64, eg, percpu: max_distance=0x5fcfdc640000 too large for vmalloc space 0x781fefff0000 percpu: max_distance=0x600000540000 too large for vmalloc space 0x7dffb7ff0000 percpu: max_distance=0x5fff9adb0000 too large for vmalloc space 0x5dffb7ff0000 then we could get WARNING: CPU: 15 PID: 461 at vmalloc.c:3087 pcpu_get_vm_areas+0x488/0x838 and the system could not boot successfully. Let's implement page mapping percpu first chunk allocator as a fallback to the embedding allocator to increase the robustness of the system. Link: https://lkml.kernel.org/r/20210910053354.26721-3-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: Catalin Marinas Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Greg Kroah-Hartman Cc: Marco Elver Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm64/Kconfig | 4 ++ drivers/base/arch_numa.c | 82 +++++++++++++++++++++++++++++++++++----- 2 files changed, 76 insertions(+), 10 deletions(-) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index fee914c716aa..67f24ee6cf57 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1042,6 +1042,10 @@ config NEED_PER_CPU_EMBED_FIRST_CHUNK def_bool y depends on NUMA +config NEED_PER_CPU_PAGE_FIRST_CHUNK + def_bool y + depends on NUMA + source "kernel/Kconfig.hz" config ARCH_SPARSEMEM_ENABLE diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c index 00fb4120a5b3..28222688ace7 100644 --- a/drivers/base/arch_numa.c +++ b/drivers/base/arch_numa.c @@ -14,6 +14,7 @@ #include #include +#include struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; EXPORT_SYMBOL(node_data); @@ -168,22 +169,83 @@ static void __init pcpu_fc_free(void *ptr, size_t size) memblock_free_early(__pa(ptr), size); } +#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK +static void __init pcpu_populate_pte(unsigned long addr) +{ + pgd_t *pgd = pgd_offset_k(addr); + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + p4d = p4d_offset(pgd, addr); + if (p4d_none(*p4d)) { + pud_t *new; + + new = memblock_alloc(PAGE_SIZE, PAGE_SIZE); + if (!new) + goto err_alloc; + p4d_populate(&init_mm, p4d, new); + } + + pud = pud_offset(p4d, addr); + if (pud_none(*pud)) { + pmd_t *new; + + new = memblock_alloc(PAGE_SIZE, PAGE_SIZE); + if (!new) + goto err_alloc; + pud_populate(&init_mm, pud, new); + } + + pmd = pmd_offset(pud, addr); + if (!pmd_present(*pmd)) { + pte_t *new; + + new = memblock_alloc(PAGE_SIZE, PAGE_SIZE); + if (!new) + goto err_alloc; + pmd_populate_kernel(&init_mm, pmd, new); + } + + return; + +err_alloc: + panic("%s: Failed to allocate %lu bytes align=%lx from=%lx\n", + __func__, PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); +} +#endif + void __init setup_per_cpu_areas(void) { unsigned long delta; unsigned int cpu; - int rc; + int rc = -EINVAL; - /* - * Always reserve area for module percpu variables. That's - * what the legacy allocator did. - */ - rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, - PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, - pcpu_cpu_distance, - pcpu_fc_alloc, pcpu_fc_free); + if (pcpu_chosen_fc != PCPU_FC_PAGE) { + /* + * Always reserve area for module percpu variables. That's + * what the legacy allocator did. + */ + rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, + PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, + pcpu_cpu_distance, + pcpu_fc_alloc, pcpu_fc_free); +#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK + if (rc < 0) + pr_warn("PERCPU: %s allocator failed (%d), falling back to page size\n", + pcpu_fc_names[pcpu_chosen_fc], rc); +#endif + } + +#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK if (rc < 0) - panic("Failed to initialize percpu areas."); + rc = pcpu_page_first_chunk(PERCPU_MODULE_RESERVE, + pcpu_fc_alloc, + pcpu_fc_free, + pcpu_populate_pte); +#endif + if (rc < 0) + panic("Failed to initialize percpu areas (err=%d).", rc); delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start; for_each_possible_cpu(cpu) From 3252b1d8309ea42bc6329d9341072ecf1c9505c0 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Fri, 5 Nov 2021 13:39:47 -0700 Subject: [PATCH 002/166] kasan: arm64: fix pcpu_page_first_chunk crash with KASAN_VMALLOC With KASAN_VMALLOC and NEED_PER_CPU_PAGE_FIRST_CHUNK the kernel crashes: Unable to handle kernel paging request at virtual address ffff7000028f2000 ... swapper pgtable: 64k pages, 48-bit VAs, pgdp=0000000042440000 [ffff7000028f2000] pgd=000000063e7c0003, p4d=000000063e7c0003, pud=000000063e7c0003, pmd=000000063e7b0003, pte=0000000000000000 Internal error: Oops: 96000007 [#1] PREEMPT SMP Modules linked in: CPU: 0 PID: 0 Comm: swapper Not tainted 5.13.0-rc4-00003-gc6e6e28f3f30-dirty #62 Hardware name: linux,dummy-virt (DT) pstate: 200000c5 (nzCv daIF -PAN -UAO -TCO BTYPE=--) pc : kasan_check_range+0x90/0x1a0 lr : memcpy+0x88/0xf4 sp : ffff80001378fe20 ... Call trace: kasan_check_range+0x90/0x1a0 pcpu_page_first_chunk+0x3f0/0x568 setup_per_cpu_areas+0xb8/0x184 start_kernel+0x8c/0x328 The vm area used in vm_area_register_early() has no kasan shadow memory, Let's add a new kasan_populate_early_vm_area_shadow() function to populate the vm area shadow memory to fix the issue. [wangkefeng.wang@huawei.com: fix redefinition of 'kasan_populate_early_vm_area_shadow'] Link: https://lkml.kernel.org/r/20211011123211.3936196-1-wangkefeng.wang@huawei.com Link: https://lkml.kernel.org/r/20210910053354.26721-4-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Acked-by: Marco Elver [KASAN] Acked-by: Andrey Konovalov [KASAN] Acked-by: Catalin Marinas Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Greg Kroah-Hartman Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm64/mm/kasan_init.c | 16 ++++++++++++++++ include/linux/kasan.h | 6 ++++++ mm/kasan/shadow.c | 5 +++++ mm/vmalloc.c | 1 + 4 files changed, 28 insertions(+) diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index 61b52a92b8b6..5b996ca4d996 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -287,6 +287,22 @@ static void __init kasan_init_depth(void) init_task.kasan_depth = 0; } +#ifdef CONFIG_KASAN_VMALLOC +void __init kasan_populate_early_vm_area_shadow(void *start, unsigned long size) +{ + unsigned long shadow_start, shadow_end; + + if (!is_vmalloc_or_module_addr(start)) + return; + + shadow_start = (unsigned long)kasan_mem_to_shadow(start); + shadow_start = ALIGN_DOWN(shadow_start, PAGE_SIZE); + shadow_end = (unsigned long)kasan_mem_to_shadow(start + size); + shadow_end = ALIGN(shadow_end, PAGE_SIZE); + kasan_map_populate(shadow_start, shadow_end, NUMA_NO_NODE); +} +#endif + void __init kasan_init(void) { kasan_init_shadow(); diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 736d7b458996..65487a3b2a71 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -436,6 +436,8 @@ void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, unsigned long free_region_end); +void kasan_populate_early_vm_area_shadow(void *start, unsigned long size); + #else /* CONFIG_KASAN_VMALLOC */ static inline int kasan_populate_vmalloc(unsigned long start, @@ -453,6 +455,10 @@ static inline void kasan_release_vmalloc(unsigned long start, unsigned long free_region_start, unsigned long free_region_end) {} +static inline void kasan_populate_early_vm_area_shadow(void *start, + unsigned long size) +{ } + #endif /* CONFIG_KASAN_VMALLOC */ #if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c index 8d95ee52d019..4a4929b29a23 100644 --- a/mm/kasan/shadow.c +++ b/mm/kasan/shadow.c @@ -254,6 +254,11 @@ core_initcall(kasan_memhotplug_init); #ifdef CONFIG_KASAN_VMALLOC +void __init __weak kasan_populate_early_vm_area_shadow(void *start, + unsigned long size) +{ +} + static int kasan_populate_vmalloc_pte(pte_t *ptep, unsigned long addr, void *unused) { diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 74da45a8beec..75fa100f5424 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2291,6 +2291,7 @@ void __init vm_area_register_early(struct vm_struct *vm, size_t align) vm->addr = (void *)addr; vm->next = *p; *p = vm; + kasan_populate_early_vm_area_shadow(vm->addr, vm->size); } static void vmap_init_free_space(void) From b7d90e7a5ea8d64e668d5685925900d33d3884d5 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 5 Nov 2021 13:39:50 -0700 Subject: [PATCH 003/166] mm/vmalloc: be more explicit about supported gfp flags The core of the vmalloc allocator __vmalloc_area_node doesn't say anything about gfp mask argument. Not all gfp flags are supported though. Be more explicit about constraints. Link: https://lkml.kernel.org/r/20211020082545.4830-1-mhocko@kernel.org Signed-off-by: Michal Hocko Cc: Dave Chinner Cc: Neil Brown Cc: Christoph Hellwig Cc: Uladzislau Rezki Cc: Ilya Dryomov Cc: Jeff Layton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmalloc.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 75fa100f5424..c56720136c45 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2983,8 +2983,16 @@ fail: * @caller: caller's return address * * Allocate enough pages to cover @size from the page level - * allocator with @gfp_mask flags. Map them into contiguous - * kernel virtual space, using a pagetable protection of @prot. + * allocator with @gfp_mask flags. Please note that the full set of gfp + * flags are not supported. GFP_KERNEL would be a preferred allocation mode + * but GFP_NOFS and GFP_NOIO are supported as well. Zone modifiers are not + * supported. From the reclaim modifiers__GFP_DIRECT_RECLAIM is required (aka + * GFP_NOWAIT is not supported) and only __GFP_NOFAIL is supported (aka + * __GFP_NORETRY and __GFP_RETRY_MAYFAIL are not supported). + * __GFP_NOWARN can be used to suppress error messages about failures. + * + * Map them into contiguous kernel virtual space, using a pagetable + * protection of @prot. * * Return: the address of the area or %NULL on failure */ From c00b6b9610991c042ff4c3153daaa3ea8522c210 Mon Sep 17 00:00:00 2001 From: Chen Wandun Date: Fri, 5 Nov 2021 13:39:53 -0700 Subject: [PATCH 004/166] mm/vmalloc: introduce alloc_pages_bulk_array_mempolicy to accelerate memory allocation Commit ffb29b1c255a ("mm/vmalloc: fix numa spreading for large hash tables") can cause significant performance regressions in some situations as Andrew mentioned in [1]. The main situation is vmalloc, vmalloc will allocate pages with NUMA_NO_NODE by default, that will result in alloc page one by one; In order to solve this, __alloc_pages_bulk and mempolicy should be considered at the same time. 1) If node is specified in memory allocation request, it will alloc all pages by __alloc_pages_bulk. 2) If interleaving allocate memory, it will cauculate how many pages should be allocated in each node, and use __alloc_pages_bulk to alloc pages in each node. [1]: https://lore.kernel.org/lkml/CALvZod4G3SzP3kWxQYn0fj+VgG-G3yWXz=gz17+3N57ru1iajw@mail.gmail.com/t/#m750c8e3231206134293b089feaa090590afa0f60 [akpm@linux-foundation.org: coding style fixes] [akpm@linux-foundation.org: make two functions static] [akpm@linux-foundation.org: fix CONFIG_NUMA=n build] Link: https://lkml.kernel.org/r/20211021080744.874701-3-chenwandun@huawei.com Signed-off-by: Chen Wandun Reviewed-by: Uladzislau Rezki (Sony) Cc: Eric Dumazet Cc: Shakeel Butt Cc: Nicholas Piggin Cc: Kefeng Wang Cc: Hanjun Guo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 4 +++ mm/mempolicy.c | 82 +++++++++++++++++++++++++++++++++++++++++++++ mm/vmalloc.c | 20 ++++++++--- 3 files changed, 102 insertions(+), 4 deletions(-) diff --git a/include/linux/gfp.h b/include/linux/gfp.h index fbd4abc33f24..c1b262725dca 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -535,6 +535,10 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, struct list_head *page_list, struct page **page_array); +unsigned long alloc_pages_bulk_array_mempolicy(gfp_t gfp, + unsigned long nr_pages, + struct page **page_array); + /* Bulk allocate order-0 pages */ static inline unsigned long alloc_pages_bulk_list(gfp_t gfp, unsigned long nr_pages, struct list_head *list) diff --git a/mm/mempolicy.c b/mm/mempolicy.c index d12e0608fced..ce722333d9f6 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2196,6 +2196,88 @@ struct page *alloc_pages(gfp_t gfp, unsigned order) } EXPORT_SYMBOL(alloc_pages); +static unsigned long alloc_pages_bulk_array_interleave(gfp_t gfp, + struct mempolicy *pol, unsigned long nr_pages, + struct page **page_array) +{ + int nodes; + unsigned long nr_pages_per_node; + int delta; + int i; + unsigned long nr_allocated; + unsigned long total_allocated = 0; + + nodes = nodes_weight(pol->nodes); + nr_pages_per_node = nr_pages / nodes; + delta = nr_pages - nodes * nr_pages_per_node; + + for (i = 0; i < nodes; i++) { + if (delta) { + nr_allocated = __alloc_pages_bulk(gfp, + interleave_nodes(pol), NULL, + nr_pages_per_node + 1, NULL, + page_array); + delta--; + } else { + nr_allocated = __alloc_pages_bulk(gfp, + interleave_nodes(pol), NULL, + nr_pages_per_node, NULL, page_array); + } + + page_array += nr_allocated; + total_allocated += nr_allocated; + } + + return total_allocated; +} + +static unsigned long alloc_pages_bulk_array_preferred_many(gfp_t gfp, int nid, + struct mempolicy *pol, unsigned long nr_pages, + struct page **page_array) +{ + gfp_t preferred_gfp; + unsigned long nr_allocated = 0; + + preferred_gfp = gfp | __GFP_NOWARN; + preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); + + nr_allocated = __alloc_pages_bulk(preferred_gfp, nid, &pol->nodes, + nr_pages, NULL, page_array); + + if (nr_allocated < nr_pages) + nr_allocated += __alloc_pages_bulk(gfp, numa_node_id(), NULL, + nr_pages - nr_allocated, NULL, + page_array + nr_allocated); + return nr_allocated; +} + +/* alloc pages bulk and mempolicy should be considered at the + * same time in some situation such as vmalloc. + * + * It can accelerate memory allocation especially interleaving + * allocate memory. + */ +unsigned long alloc_pages_bulk_array_mempolicy(gfp_t gfp, + unsigned long nr_pages, struct page **page_array) +{ + struct mempolicy *pol = &default_policy; + + if (!in_interrupt() && !(gfp & __GFP_THISNODE)) + pol = get_task_policy(current); + + if (pol->mode == MPOL_INTERLEAVE) + return alloc_pages_bulk_array_interleave(gfp, pol, + nr_pages, page_array); + + if (pol->mode == MPOL_PREFERRED_MANY) + return alloc_pages_bulk_array_preferred_many(gfp, + numa_node_id(), pol, nr_pages, page_array); + + return __alloc_pages_bulk(gfp, policy_node(gfp, pol, numa_node_id()), + policy_nodemask(gfp, pol), nr_pages, NULL, + page_array); +} + int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) { struct mempolicy *pol = mpol_dup(vma_policy(src)); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index c56720136c45..d2a00ad4e1dd 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2843,7 +2843,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid, * to fails, fallback to a single page allocator that is * more permissive. */ - if (!order && nid != NUMA_NO_NODE) { + if (!order) { while (nr_allocated < nr_pages) { unsigned int nr, nr_pages_request; @@ -2855,8 +2855,20 @@ vm_area_alloc_pages(gfp_t gfp, int nid, */ nr_pages_request = min(100U, nr_pages - nr_allocated); - nr = alloc_pages_bulk_array_node(gfp, nid, - nr_pages_request, pages + nr_allocated); + /* memory allocation should consider mempolicy, we can't + * wrongly use nearest node when nid == NUMA_NO_NODE, + * otherwise memory may be allocated in only one node, + * but mempolcy want to alloc memory by interleaving. + */ + if (IS_ENABLED(CONFIG_NUMA) && nid == NUMA_NO_NODE) + nr = alloc_pages_bulk_array_mempolicy(gfp, + nr_pages_request, + pages + nr_allocated); + + else + nr = alloc_pages_bulk_array_node(gfp, nid, + nr_pages_request, + pages + nr_allocated); nr_allocated += nr; cond_resched(); @@ -2868,7 +2880,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid, if (nr != nr_pages_request) break; } - } else if (order) + } else /* * Compound pages required for remap_vmalloc_page if * high-order pages. From 34b46efd6ec6a6f2d6a57be4216b820c879a0030 Mon Sep 17 00:00:00 2001 From: Changcheng Deng Date: Fri, 5 Nov 2021 13:39:56 -0700 Subject: [PATCH 005/166] lib/test_vmalloc.c: use swap() to make code cleaner Use swap() in order to make code cleaner. Issue found by coccinelle. Link: https://lkml.kernel.org/r/20211028111443.15744-1-deng.changcheng@zte.com.cn Signed-off-by: Changcheng Deng Reported-by: Zeal Robot Reviewed-by: Uladzislau Rezki (Sony) Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/test_vmalloc.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/lib/test_vmalloc.c b/lib/test_vmalloc.c index e14993bc84d2..cf41fd6df42a 100644 --- a/lib/test_vmalloc.c +++ b/lib/test_vmalloc.c @@ -393,7 +393,7 @@ static struct test_driver { static void shuffle_array(int *arr, int n) { unsigned int rnd; - int i, j, x; + int i, j; for (i = n - 1; i > 0; i--) { get_random_bytes(&rnd, sizeof(rnd)); @@ -402,9 +402,7 @@ static void shuffle_array(int *arr, int n) j = rnd % i; /* Swap indexes. */ - x = arr[i]; - arr[i] = arr[j]; - arr[j] = x; + swap(arr[i], arr[j]); } } From 084f7e2377e89ccbc8375b5486c6b4c16682f602 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 5 Nov 2021 13:39:59 -0700 Subject: [PATCH 006/166] mm/large system hash: avoid possible NULL deref in alloc_large_system_hash If __vmalloc() returned NULL, is_vm_area_hugepages(NULL) will fault if CONFIG_HAVE_ARCH_HUGE_VMALLOC=y Link: https://lkml.kernel.org/r/20210915212530.2321545-1-eric.dumazet@gmail.com Fixes: 121e6f3258fe ("mm/vmalloc: hugepage vmalloc mappings") Signed-off-by: Eric Dumazet Reviewed-by: Andrew Morton Cc: Nicholas Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 23d3339ac4e8..133dad9f4669 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -8762,7 +8762,8 @@ void *__init alloc_large_system_hash(const char *tablename, } else if (get_order(size) >= MAX_ORDER || hashdist) { table = __vmalloc(size, gfp_flags); virt = true; - huge = is_vm_area_hugepages(table); + if (table) + huge = is_vm_area_hugepages(table); } else { /* * If bucketsize is not a power-of-two, we may free From ea808b4efd15f6f019e9779617a166c9708856c1 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Fri, 5 Nov 2021 13:40:02 -0700 Subject: [PATCH 007/166] mm/page_alloc.c: remove meaningless VM_BUG_ON() in pindex_to_order() Patch series "Cleanups and fixup for page_alloc", v2. This series contains cleanups to remove meaningless VM_BUG_ON(), use helpers to simplify the code and remove obsolete comment. Also we avoid allocating highmem pages via alloc_pages_exact[_nid]. More details can be found in the respective changelogs. This patch (of 5): It's meaningless to VM_BUG_ON() order != pageblock_order just after setting order to pageblock_order. Remove it. Link: https://lkml.kernel.org/r/20210902121242.41607-1-linmiaohe@huawei.com Link: https://lkml.kernel.org/r/20210902121242.41607-2-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Acked-by: Mel Gorman Reviewed-by: David Hildenbrand Cc: Vlastimil Babka Cc: Stephen Rothwell Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 133dad9f4669..afaa544f129f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -677,10 +677,8 @@ static inline int pindex_to_order(unsigned int pindex) int order = pindex / MIGRATE_PCPTYPES; #ifdef CONFIG_TRANSPARENT_HUGEPAGE - if (order > PAGE_ALLOC_COSTLY_ORDER) { + if (order > PAGE_ALLOC_COSTLY_ORDER) order = pageblock_order; - VM_BUG_ON(order != pageblock_order); - } #else VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER); #endif From ff7ed9e4532d14e0478d192548e77d78d72387e9 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Fri, 5 Nov 2021 13:40:05 -0700 Subject: [PATCH 008/166] mm/page_alloc.c: simplify the code by using macro K() Use helper macro K() to convert the pages to the corresponding size. Minor readability improvement. Link: https://lkml.kernel.org/r/20210902121242.41607-3-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Acked-by: Mel Gorman Reviewed-by: David Hildenbrand Cc: Peter Zijlstra Cc: Stephen Rothwell Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index afaa544f129f..8224c6c302dd 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -8130,8 +8130,7 @@ unsigned long free_reserved_area(void *start, void *end, int poison, const char } if (pages && s) - pr_info("Freeing %s memory: %ldK\n", - s, pages << (PAGE_SHIFT - 10)); + pr_info("Freeing %s memory: %ldK\n", s, K(pages)); return pages; } @@ -8176,14 +8175,13 @@ void __init mem_init_print_info(void) ", %luK highmem" #endif ")\n", - nr_free_pages() << (PAGE_SHIFT - 10), - physpages << (PAGE_SHIFT - 10), + K(nr_free_pages()), K(physpages), codesize >> 10, datasize >> 10, rosize >> 10, (init_data_size + init_code_size) >> 10, bss_size >> 10, - (physpages - totalram_pages() - totalcma_pages) << (PAGE_SHIFT - 10), - totalcma_pages << (PAGE_SHIFT - 10) + K(physpages - totalram_pages() - totalcma_pages), + K(totalcma_pages) #ifdef CONFIG_HIGHMEM - , totalhigh_pages() << (PAGE_SHIFT - 10) + , K(totalhigh_pages()) #endif ); } From 7cba630bd830472f88ada5fdd34bbfd5825d9217 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Fri, 5 Nov 2021 13:40:08 -0700 Subject: [PATCH 009/166] mm/page_alloc.c: fix obsolete comment in free_pcppages_bulk() The second two paragraphs about "all pages pinned" and pages_scanned is obsolete. And There are PAGE_ALLOC_COSTLY_ORDER + 1 + NR_PCP_THP orders in pcp. So the same order assumption is not held now. Link: https://lkml.kernel.org/r/20210902121242.41607-4-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Acked-by: Mel Gorman Cc: David Hildenbrand Cc: Peter Zijlstra Cc: Stephen Rothwell Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8224c6c302dd..c494c9c66f4f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1428,14 +1428,8 @@ static inline void prefetch_buddy(struct page *page) /* * Frees a number of pages from the PCP lists - * Assumes all pages on list are in same zone, and of same order. + * Assumes all pages on list are in same zone. * count is the number of pages to free. - * - * If the zone was previously in an "all pages pinned" state then look to - * see if this freeing clears that state. - * - * And clear the zone's pages_scanned counter, to hold off the "all pages are - * pinned" detection logic. */ static void free_pcppages_bulk(struct zone *zone, int count, struct per_cpu_pages *pcp) From 86fb05b9cc1ac7cdcf37e5408b927dd3ad95db96 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Fri, 5 Nov 2021 13:40:11 -0700 Subject: [PATCH 010/166] mm/page_alloc.c: use helper function zone_spans_pfn() Use helper function zone_spans_pfn() to check whether pfn is within a zone to simplify the code slightly. Link: https://lkml.kernel.org/r/20210902121242.41607-5-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Acked-by: Mel Gorman Reviewed-by: David Hildenbrand Cc: Peter Zijlstra Cc: Stephen Rothwell Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c494c9c66f4f..26aebbbf1f66 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1583,7 +1583,7 @@ static void __meminit init_reserved_page(unsigned long pfn) for (zid = 0; zid < MAX_NR_ZONES; zid++) { struct zone *zone = &pgdat->node_zones[zid]; - if (pfn >= zone->zone_start_pfn && pfn < zone_end_pfn(zone)) + if (zone_spans_pfn(zone, pfn)) break; } __init_single_page(pfn_to_page(pfn), pfn, zid, nid); From ba7f1b9e3fd9a2a64c5da04995919c9eb5bab974 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Fri, 5 Nov 2021 13:40:15 -0700 Subject: [PATCH 011/166] mm/page_alloc.c: avoid allocating highmem pages via alloc_pages_exact[_nid] Don't use with __GFP_HIGHMEM because page_address() cannot represent highmem pages without kmap(). Newly allocated pages would leak as page_address() will return NULL for highmem pages here. But It works now because the callers do not specify __GFP_HIGHMEM now. Link: https://lkml.kernel.org/r/20210902121242.41607-6-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Reviewed-by: David Hildenbrand Cc: Mel Gorman Cc: Peter Zijlstra Cc: Stephen Rothwell Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 26aebbbf1f66..307ad23cb9e9 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5610,8 +5610,8 @@ void *alloc_pages_exact(size_t size, gfp_t gfp_mask) unsigned int order = get_order(size); unsigned long addr; - if (WARN_ON_ONCE(gfp_mask & __GFP_COMP)) - gfp_mask &= ~__GFP_COMP; + if (WARN_ON_ONCE(gfp_mask & (__GFP_COMP | __GFP_HIGHMEM))) + gfp_mask &= ~(__GFP_COMP | __GFP_HIGHMEM); addr = __get_free_pages(gfp_mask, order); return make_alloc_exact(addr, order, size); @@ -5635,8 +5635,8 @@ void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) unsigned int order = get_order(size); struct page *p; - if (WARN_ON_ONCE(gfp_mask & __GFP_COMP)) - gfp_mask &= ~__GFP_COMP; + if (WARN_ON_ONCE(gfp_mask & (__GFP_COMP | __GFP_HIGHMEM))) + gfp_mask &= ~(__GFP_COMP | __GFP_HIGHMEM); p = alloc_pages_node(nid, gfp_mask, order); if (!p) From 6cf253925df72e522c06dac09ede7e81a6e38121 Mon Sep 17 00:00:00 2001 From: Bharata B Rao Date: Fri, 5 Nov 2021 13:40:18 -0700 Subject: [PATCH 012/166] mm/page_alloc: print node fallback order Patch series "Fix NUMA nodes fallback list ordering". For a NUMA system that has multiple nodes at same distance from other nodes, the fallback list generation prefers same node order for them instead of round-robin thereby penalizing one node over others. This series fixes it. More description of the problem and the fix is present in the patch description. This patch (of 2): Print information message about the allocation fallback order for each NUMA node during boot. No functional changes here. This makes it easier to illustrate the problem in the node fallback list generation, which the next patch fixes. Link: https://lkml.kernel.org/r/20210830121603.1081-1-bharata@amd.com Link: https://lkml.kernel.org/r/20210830121603.1081-2-bharata@amd.com Signed-off-by: Bharata B Rao Acked-by: Mel Gorman Reviewed-by: Anshuman Khandual Cc: KAMEZAWA Hiroyuki Cc: Lee Schermerhorn Cc: Krupa Ramakrishnan Cc: Sadagopan Srinivasan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 307ad23cb9e9..163f60dcac47 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6262,6 +6262,10 @@ static void build_zonelists(pg_data_t *pgdat) build_zonelists_in_node_order(pgdat, node_order, nr_nodes); build_thisnode_zonelists(pgdat); + pr_info("Fallback order for Node %d: ", local_node); + for (node = 0; node < nr_nodes; node++) + pr_cont("%d ", node_order[node]); + pr_cont("\n"); } #ifdef CONFIG_HAVE_MEMORYLESS_NODES From 54d032ced98378bcb9d32dd5e378b7e402b36ad8 Mon Sep 17 00:00:00 2001 From: Krupa Ramakrishnan Date: Fri, 5 Nov 2021 13:40:21 -0700 Subject: [PATCH 013/166] mm/page_alloc: use accumulated load when building node fallback list In build_zonelists(), when the fallback list is built for the nodes, the node load gets reinitialized during each iteration. This results in nodes with same distances occupying the same slot in different node fallback lists rather than appearing in the intended round- robin manner. This results in one node getting picked for allocation more compared to other nodes with the same distance. As an example, consider a 4 node system with the following distance matrix. Node 0 1 2 3 ---------------- 0 10 12 32 32 1 12 10 32 32 2 32 32 10 12 3 32 32 12 10 For this case, the node fallback list gets built like this: Node Fallback list --------------------- 0 0 1 2 3 1 1 0 3 2 2 2 3 0 1 3 3 2 0 1 <-- Unexpected fallback order In the fallback list for nodes 2 and 3, the nodes 0 and 1 appear in the same order which results in more allocations getting satisfied from node 0 compared to node 1. The effect of this on remote memory bandwidth as seen by stream benchmark is shown below: Case 1: Bandwidth from cores on nodes 2 & 3 to memory on nodes 0 & 1 (numactl -m 0,1 ./stream_lowOverhead ... --cores ) Case 2: Bandwidth from cores on nodes 0 & 1 to memory on nodes 2 & 3 (numactl -m 2,3 ./stream_lowOverhead ... --cores ) ---------------------------------------- BANDWIDTH (MB/s) TEST Case 1 Case 2 ---------------------------------------- COPY 57479.6 110791.8 SCALE 55372.9 105685.9 ADD 50460.6 96734.2 TRIADD 50397.6 97119.1 ---------------------------------------- The bandwidth drop in Case 1 occurs because most of the allocations get satisfied by node 0 as it appears first in the fallback order for both nodes 2 and 3. This can be fixed by accumulating the node load in build_zonelists() rather than reinitializing it during each iteration. With this the nodes with the same distance rightly get assigned in the round robin manner. In fact this was how it was originally until commit f0c0b2b808f2 ("change zonelist order: zonelist order selection logic") dropped the load accumulation and resorted to initializing the load during each iteration. While zonelist ordering was removed by commit c9bff3eebc09 ("mm, page_alloc: rip out ZONELIST_ORDER_ZONE"), the change to the node load accumulation in build_zonelists() remained. So essentially this patch reverts back to the accumulated node load logic. After this fix, the fallback order gets built like this: Node Fallback list ------------------ 0 0 1 2 3 1 1 0 3 2 2 2 3 0 1 3 3 2 1 0 <-- Note the change here The bandwidth in Case 1 improves and matches Case 2 as shown below. ---------------------------------------- BANDWIDTH (MB/s) TEST Case 1 Case 2 ---------------------------------------- COPY 110438.9 110107.2 SCALE 105930.5 105817.5 ADD 97005.1 96159.8 TRIADD 97441.5 96757.1 ---------------------------------------- The correctness of the fallback list generation has been verified for the above node configuration where the node 3 starts as memory-less node and comes up online only during memory hotplug. [bharata@amd.com: Added changelog, review, test validation] Link: https://lkml.kernel.org/r/20210830121603.1081-3-bharata@amd.com Fixes: f0c0b2b808f2 ("change zonelist order: zonelist order selection logic") Signed-off-by: Krupa Ramakrishnan Co-developed-by: Sadagopan Srinivasan Signed-off-by: Sadagopan Srinivasan Signed-off-by: Bharata B Rao Acked-by: Mel Gorman Reviewed-by: Anshuman Khandual Cc: KAMEZAWA Hiroyuki Cc: Lee Schermerhorn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 163f60dcac47..1eab16b4006d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6253,7 +6253,7 @@ static void build_zonelists(pg_data_t *pgdat) */ if (node_distance(local_node, node) != node_distance(local_node, prev_node)) - node_load[node] = load; + node_load[node] += load; node_order[nr_nodes++] = node; prev_node = node; From 61bb6cd2f765b90cfc5f0f91696889c366a6a13d Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 5 Nov 2021 13:40:24 -0700 Subject: [PATCH 014/166] mm: move node_reclaim_distance to fix NUMA without SMP Patch series "Fix NUMA without SMP". SuperH is the only architecture which still supports NUMA without SMP, for good reasons (various memories scattered around the address space, each with varying latencies). This series fixes two build errors due to variables and functions used by the NUMA code being provided by SMP-only source files or sections. This patch (of 2): If CONFIG_NUMA=y, but CONFIG_SMP=n (e.g. sh/migor_defconfig): sh4-linux-gnu-ld: mm/page_alloc.o: in function `get_page_from_freelist': page_alloc.c:(.text+0x2c24): undefined reference to `node_reclaim_distance' Fix this by moving the declaration of node_reclaim_distance from an SMP-only to a generic file. Link: https://lkml.kernel.org/r/cover.1631781495.git.geert+renesas@glider.be Link: https://lkml.kernel.org/r/6432666a648dde85635341e6c918cee97c97d264.1631781495.git.geert+renesas@glider.be Fixes: a55c7454a8c887b2 ("sched/topology: Improve load balancing on AMD EPYC systems") Signed-off-by: Geert Uytterhoeven Suggested-by: Matt Fleming Acked-by: Mel Gorman Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Juri Lelli Cc: Vincent Guittot Cc: Vlastimil Babka Cc: Yoshinori Sato Cc: Rich Felker Cc: Gon Solo Cc: Geert Uytterhoeven Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sched/topology.c | 1 - mm/page_alloc.c | 2 ++ 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 4e8698e62f07..738ee7fa7972 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1481,7 +1481,6 @@ static int sched_domains_curr_level; int sched_max_numa_distance; static int *sched_domains_numa_distance; static struct cpumask ***sched_domains_numa_masks; -int __read_mostly node_reclaim_distance = RECLAIM_DISTANCE; static unsigned long __read_mostly *sched_numa_onlined_nodes; #endif diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 1eab16b4006d..e4aef907abe9 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3960,6 +3960,8 @@ bool zone_watermark_ok_safe(struct zone *z, unsigned int order, } #ifdef CONFIG_NUMA +int __read_mostly node_reclaim_distance = RECLAIM_DISTANCE; + static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) { return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <= From ebeac3ea995b59e823510937ab92825004e3fbaa Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 5 Nov 2021 13:40:28 -0700 Subject: [PATCH 015/166] mm: move fold_vm_numa_events() to fix NUMA without SMP If CONFIG_NUMA=y, but CONFIG_SMP=n (e.g. sh/migor_defconfig): sh4-linux-gnu-ld: mm/vmstat.o: in function `vmstat_start': vmstat.c:(.text+0x97c): undefined reference to `fold_vm_numa_events' sh4-linux-gnu-ld: drivers/base/node.o: in function `node_read_vmstat': node.c:(.text+0x140): undefined reference to `fold_vm_numa_events' sh4-linux-gnu-ld: drivers/base/node.o: in function `node_read_numastat': node.c:(.text+0x1d0): undefined reference to `fold_vm_numa_events' Fix this by moving fold_vm_numa_events() outside the SMP-only section. Link: https://lkml.kernel.org/r/9d16ccdd9ef32803d7100c84f737de6a749314fb.1631781495.git.geert+renesas@glider.be Fixes: f19298b9516c1a03 ("mm/vmstat: convert NUMA statistics to basic NUMA counters") Signed-off-by: Geert Uytterhoeven Acked-by: Mel Gorman Cc: Gon Solo Cc: Ingo Molnar Cc: Juri Lelli Cc: Matt Fleming Cc: Peter Zijlstra Cc: Rich Felker Cc: Vincent Guittot Cc: Vlastimil Babka Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmstat.c | 56 ++++++++++++++++++++++++++--------------------------- 1 file changed, 28 insertions(+), 28 deletions(-) diff --git a/mm/vmstat.c b/mm/vmstat.c index 8ce2620344b2..5db54581feab 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -165,6 +165,34 @@ atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS] __cacheline_aligned_in_smp; EXPORT_SYMBOL(vm_zone_stat); EXPORT_SYMBOL(vm_node_stat); +#ifdef CONFIG_NUMA +static void fold_vm_zone_numa_events(struct zone *zone) +{ + unsigned long zone_numa_events[NR_VM_NUMA_EVENT_ITEMS] = { 0, }; + int cpu; + enum numa_stat_item item; + + for_each_online_cpu(cpu) { + struct per_cpu_zonestat *pzstats; + + pzstats = per_cpu_ptr(zone->per_cpu_zonestats, cpu); + for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++) + zone_numa_events[item] += xchg(&pzstats->vm_numa_event[item], 0); + } + + for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++) + zone_numa_event_add(zone_numa_events[item], zone, item); +} + +void fold_vm_numa_events(void) +{ + struct zone *zone; + + for_each_populated_zone(zone) + fold_vm_zone_numa_events(zone); +} +#endif + #ifdef CONFIG_SMP int calculate_pressure_threshold(struct zone *zone) @@ -771,34 +799,6 @@ static int fold_diff(int *zone_diff, int *node_diff) return changes; } -#ifdef CONFIG_NUMA -static void fold_vm_zone_numa_events(struct zone *zone) -{ - unsigned long zone_numa_events[NR_VM_NUMA_EVENT_ITEMS] = { 0, }; - int cpu; - enum numa_stat_item item; - - for_each_online_cpu(cpu) { - struct per_cpu_zonestat *pzstats; - - pzstats = per_cpu_ptr(zone->per_cpu_zonestats, cpu); - for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++) - zone_numa_events[item] += xchg(&pzstats->vm_numa_event[item], 0); - } - - for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++) - zone_numa_event_add(zone_numa_events[item], zone, item); -} - -void fold_vm_numa_events(void) -{ - struct zone *zone; - - for_each_populated_zone(zone) - fold_vm_zone_numa_events(zone); -} -#endif - /* * Update the zone counters for the current cpu. * From 8446b59baaf45e83e1187cdb174ac78ac5d7d0ae Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 5 Nov 2021 13:40:31 -0700 Subject: [PATCH 016/166] mm/page_alloc.c: do not acquire zone lock in is_free_buddy_page() Grabbing zone lock in is_free_buddy_page() gives a wrong sense of safety, and has potential performance implications when zone is experiencing lock contention. In any case, if a caller needs a stable result, it should grab zone lock before calling this function. Link: https://lkml.kernel.org/r/20210922152833.4023972-1-eric.dumazet@gmail.com Signed-off-by: Eric Dumazet Acked-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index e4aef907abe9..e891560e0a80 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -9356,21 +9356,21 @@ void __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) } #endif +/* + * This function returns a stable result only if called under zone lock. + */ bool is_free_buddy_page(struct page *page) { - struct zone *zone = page_zone(page); unsigned long pfn = page_to_pfn(page); - unsigned long flags; unsigned int order; - spin_lock_irqsave(&zone->lock, flags); for (order = 0; order < MAX_ORDER; order++) { struct page *page_head = page - (pfn & ((1 << order) - 1)); - if (PageBuddy(page_head) && buddy_order(page_head) >= order) + if (PageBuddy(page_head) && + buddy_order_unsafe(page_head) >= order) break; } - spin_unlock_irqrestore(&zone->lock, flags); return order < MAX_ORDER; } From 8ca1b5a49885f0c0c486544da46a9e0ac790831d Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Fri, 5 Nov 2021 13:40:34 -0700 Subject: [PATCH 017/166] mm/page_alloc: detect allocation forbidden by cpuset and bail out early There was a report that starting an Ubuntu in docker while using cpuset to bind it to movable nodes (a node only has movable zone, like a node for hotplug or a Persistent Memory node in normal usage) will fail due to memory allocation failure, and then OOM is involved and many other innocent processes got killed. It can be reproduced with command: $ docker run -it --rm --cpuset-mems 4 ubuntu:latest bash -c "grep Mems_allowed /proc/self/status" (where node 4 is a movable node) runc:[2:INIT] invoked oom-killer: gfp_mask=0x500cc2(GFP_HIGHUSER|__GFP_ACCOUNT), order=0, oom_score_adj=0 CPU: 8 PID: 8291 Comm: runc:[2:INIT] Tainted: G W I E 5.8.2-0.g71b519a-default #1 openSUSE Tumbleweed (unreleased) Hardware name: Dell Inc. PowerEdge R640/0PHYDR, BIOS 2.6.4 04/09/2020 Call Trace: dump_stack+0x6b/0x88 dump_header+0x4a/0x1e2 oom_kill_process.cold+0xb/0x10 out_of_memory.part.0+0xaf/0x230 out_of_memory+0x3d/0x80 __alloc_pages_slowpath.constprop.0+0x954/0xa20 __alloc_pages_nodemask+0x2d3/0x300 pipe_write+0x322/0x590 new_sync_write+0x196/0x1b0 vfs_write+0x1c3/0x1f0 ksys_write+0xa7/0xe0 do_syscall_64+0x52/0xd0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Mem-Info: active_anon:392832 inactive_anon:182 isolated_anon:0 active_file:68130 inactive_file:151527 isolated_file:0 unevictable:2701 dirty:0 writeback:7 slab_reclaimable:51418 slab_unreclaimable:116300 mapped:45825 shmem:735 pagetables:2540 bounce:0 free:159849484 free_pcp:73 free_cma:0 Node 4 active_anon:1448kB inactive_anon:0kB active_file:0kB inactive_file:0kB unevictable:0kB isolated(anon):0kB isolated(file):0kB mapped:0kB dirty:0kB writeback:0kB shmem:0kB shmem_thp: 0kB shmem_pmdmapped: 0kB anon_thp: 0kB writeback_tmp:0kB all_unreclaimable? no Node 4 Movable free:130021408kB min:9140kB low:139160kB high:269180kB reserved_highatomic:0KB active_anon:1448kB inactive_anon:0kB active_file:0kB inactive_file:0kB unevictable:0kB writepending:0kB present:130023424kB managed:130023424kB mlocked:0kB kernel_stack:0kB pagetables:0kB bounce:0kB free_pcp:292kB local_pcp:84kB free_cma:0kB lowmem_reserve[]: 0 0 0 0 0 Node 4 Movable: 1*4kB (M) 0*8kB 0*16kB 1*32kB (M) 0*64kB 0*128kB 1*256kB (M) 1*512kB (M) 1*1024kB (M) 0*2048kB 31743*4096kB (M) = 130021156kB oom-kill:constraint=CONSTRAINT_CPUSET,nodemask=(null),cpuset=docker-9976a269caec812c134fa317f27487ee36e1129beba7278a463dd53e5fb9997b.scope,mems_allowed=4,global_oom,task_memcg=/system.slice/containerd.service,task=containerd,pid=4100,uid=0 Out of memory: Killed process 4100 (containerd) total-vm:4077036kB, anon-rss:51184kB, file-rss:26016kB, shmem-rss:0kB, UID:0 pgtables:676kB oom_score_adj:0 oom_reaper: reaped process 8248 (docker), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB oom_reaper: reaped process 2054 (node_exporter), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB oom_reaper: reaped process 1452 (systemd-journal), now anon-rss:0kB, file-rss:8564kB, shmem-rss:4kB oom_reaper: reaped process 2146 (munin-node), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB oom_reaper: reaped process 8291 (runc:[2:INIT]), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB The reason is that in this case, the target cpuset nodes only have movable zone, while the creation of an OS in docker sometimes needs to allocate memory in non-movable zones (dma/dma32/normal) like GFP_HIGHUSER, and the cpuset limit forbids the allocation, then out-of-memory killing is involved even when normal nodes and movable nodes both have many free memory. The OOM killer cannot help to resolve the situation as there is no usable memory for the request in the cpuset scope. The only reasonable measure to take is to fail the allocation right away and have the caller to deal with it. So add a check for cases like this in the slowpath of allocation, and bail out early returning NULL for the allocation. As page allocation is one of the hottest path in kernel, this check will hurt all users with sane cpuset configuration, add a static branch check and detect the abnormal config in cpuset memory binding setup so that the extra check cost in page allocation is not paid by everyone. [thanks to Micho Hocko and David Rientjes for suggesting not handling it inside OOM code, adding cpuset check, refining comments] Link: https://lkml.kernel.org/r/1632481657-68112-1-git-send-email-feng.tang@intel.com Signed-off-by: Feng Tang Suggested-by: Michal Hocko Acked-by: Michal Hocko Cc: David Rientjes Cc: Tejun Heo Cc: Zefan Li Cc: Johannes Weiner Cc: Mel Gorman Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpuset.h | 17 +++++++++++++++++ include/linux/mmzone.h | 22 ++++++++++++++++++++++ kernel/cgroup/cpuset.c | 23 +++++++++++++++++++++++ mm/page_alloc.c | 13 +++++++++++++ 4 files changed, 75 insertions(+) diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index d2b9c41c8edf..d58e0476ee8e 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -34,6 +34,8 @@ */ extern struct static_key_false cpusets_pre_enable_key; extern struct static_key_false cpusets_enabled_key; +extern struct static_key_false cpusets_insane_config_key; + static inline bool cpusets_enabled(void) { return static_branch_unlikely(&cpusets_enabled_key); @@ -51,6 +53,19 @@ static inline void cpuset_dec(void) static_branch_dec_cpuslocked(&cpusets_pre_enable_key); } +/* + * This will get enabled whenever a cpuset configuration is considered + * unsupportable in general. E.g. movable only node which cannot satisfy + * any non movable allocations (see update_nodemask). Page allocator + * needs to make additional checks for those configurations and this + * check is meant to guard those checks without any overhead for sane + * configurations. + */ +static inline bool cpusets_insane_config(void) +{ + return static_branch_unlikely(&cpusets_insane_config_key); +} + extern int cpuset_init(void); extern void cpuset_init_smp(void); extern void cpuset_force_rebuild(void); @@ -167,6 +182,8 @@ static inline void set_mems_allowed(nodemask_t nodemask) static inline bool cpusets_enabled(void) { return false; } +static inline bool cpusets_insane_config(void) { return false; } + static inline int cpuset_init(void) { return 0; } static inline void cpuset_init_smp(void) {} diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 832aa49d0d8e..fb36a29e3aae 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1220,6 +1220,28 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, #define for_each_zone_zonelist(zone, z, zlist, highidx) \ for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, NULL) +/* Whether the 'nodes' are all movable nodes */ +static inline bool movable_only_nodes(nodemask_t *nodes) +{ + struct zonelist *zonelist; + struct zoneref *z; + int nid; + + if (nodes_empty(*nodes)) + return false; + + /* + * We can chose arbitrary node from the nodemask to get a + * zonelist as they are interlinked. We just need to find + * at least one zone that can satisfy kernel allocations. + */ + nid = first_node(*nodes); + zonelist = &NODE_DATA(nid)->node_zonelists[ZONELIST_FALLBACK]; + z = first_zones_zonelist(zonelist, ZONE_NORMAL, nodes); + return (!z->zone) ? true : false; +} + + #ifdef CONFIG_SPARSEMEM #include #endif diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 2a9695ccb65f..d0e163a02099 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -69,6 +69,13 @@ DEFINE_STATIC_KEY_FALSE(cpusets_pre_enable_key); DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key); +/* + * There could be abnormal cpuset configurations for cpu or memory + * node binding, add this key to provide a quick low-cost judgement + * of the situation. + */ +DEFINE_STATIC_KEY_FALSE(cpusets_insane_config_key); + /* See "Frequency meter" comments, below. */ struct fmeter { @@ -372,6 +379,17 @@ static DECLARE_WORK(cpuset_hotplug_work, cpuset_hotplug_workfn); static DECLARE_WAIT_QUEUE_HEAD(cpuset_attach_wq); +static inline void check_insane_mems_config(nodemask_t *nodes) +{ + if (!cpusets_insane_config() && + movable_only_nodes(nodes)) { + static_branch_enable(&cpusets_insane_config_key); + pr_info("Unsupported (movable nodes only) cpuset configuration detected (nmask=%*pbl)!\n" + "Cpuset allocations might fail even with a lot of memory available.\n", + nodemask_pr_args(nodes)); + } +} + /* * Cgroup v2 behavior is used on the "cpus" and "mems" control files when * on default hierarchy or when the cpuset_v2_mode flag is set by mounting @@ -1870,6 +1888,8 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs, if (retval < 0) goto done; + check_insane_mems_config(&trialcs->mems_allowed); + spin_lock_irq(&callback_lock); cs->mems_allowed = trialcs->mems_allowed; spin_unlock_irq(&callback_lock); @@ -3173,6 +3193,9 @@ update_tasks: cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus); mems_updated = !nodes_equal(new_mems, cs->effective_mems); + if (mems_updated) + check_insane_mems_config(&new_mems); + if (is_in_v2_mode()) hotplug_update_tasks(cs, &new_cpus, &new_mems, cpus_updated, mems_updated); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index e891560e0a80..e493d7da2614 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4910,6 +4910,19 @@ retry_cpuset: if (!ac->preferred_zoneref->zone) goto nopage; + /* + * Check for insane configurations where the cpuset doesn't contain + * any suitable zone to satisfy the request - e.g. non-movable + * GFP_HIGHUSER allocations from MOVABLE nodes only. + */ + if (cpusets_insane_config() && (gfp_mask & __GFP_HARDWALL)) { + struct zoneref *z = first_zones_zonelist(ac->zonelist, + ac->highest_zoneidx, + &cpuset_current_mems_allowed); + if (!z->zone) + goto nopage; + } + if (alloc_flags & ALLOC_KSWAPD) wake_all_kswapds(order, gfp_mask, ac); From a6ea8b5b9f1ce3403a1c8516035d653006741e80 Mon Sep 17 00:00:00 2001 From: Liangcai Fan Date: Fri, 5 Nov 2021 13:40:37 -0700 Subject: [PATCH 018/166] mm/page_alloc.c: show watermark_boost of zone in zoneinfo min/low/high_wmark_pages(z) is defined as (z->_watermark[WMARK_MIN/LOW/HIGH] + z->watermark_boost) If kswapd is frequently woken up due to the increase of min/low/high_wmark_pages, printing watermark_boost can quickly locate whether watermark_boost or _watermark[WMARK_MIN/LOW/HIGH] caused min/low/high_wmark_pages to increase. Link: https://lkml.kernel.org/r/1632472566-12246-1-git-send-email-liangcaifan19@gmail.com Signed-off-by: Liangcai Fan Cc: Chunyan Zhang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 2 ++ mm/vmstat.c | 2 ++ 2 files changed, 4 insertions(+) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index e493d7da2614..6714039cddf4 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5993,6 +5993,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) printk(KERN_CONT "%s" " free:%lukB" + " boost:%lukB" " min:%lukB" " low:%lukB" " high:%lukB" @@ -6013,6 +6014,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) "\n", zone->name, K(zone_page_state(zone, NR_FREE_PAGES)), + K(zone->watermark_boost), K(min_wmark_pages(zone)), K(low_wmark_pages(zone)), K(high_wmark_pages(zone)), diff --git a/mm/vmstat.c b/mm/vmstat.c index 5db54581feab..ae87c90e0b4e 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1656,6 +1656,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, } seq_printf(m, "\n pages free %lu" + "\n boost %lu" "\n min %lu" "\n low %lu" "\n high %lu" @@ -1664,6 +1665,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, "\n managed %lu" "\n cma %lu", zone_page_state(zone, NR_FREE_PAGES), + zone->watermark_boost, min_wmark_pages(zone), low_wmark_pages(zone), high_wmark_pages(zone), From d2635f2012a44e3d469ab9a4022162dbe0e53f21 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 5 Nov 2021 13:40:40 -0700 Subject: [PATCH 019/166] mm: create a new system state and fix core_kernel_text() core_kernel_text() considers that until system_state in at least SYSTEM_RUNNING, init memory is valid. But init memory is freed a few lines before setting SYSTEM_RUNNING, so we have a small period of time when core_kernel_text() is wrong. Create an intermediate system state called SYSTEM_FREEING_INIT that is set before starting freeing init memory, and use it in core_kernel_text() to report init memory invalid earlier. Link: https://lkml.kernel.org/r/9ecfdee7dd4d741d172cb93ff1d87f1c58127c9a.1633001016.git.christophe.leroy@csgroup.eu Signed-off-by: Christophe Leroy Cc: Gerald Schaefer Cc: Kefeng Wang Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Heiko Carstens Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 1 + init/main.c | 2 ++ kernel/extable.c | 2 +- 3 files changed, 4 insertions(+), 1 deletion(-) diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 2776423a587e..471bc0593679 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -248,6 +248,7 @@ extern bool early_boot_irqs_disabled; extern enum system_states { SYSTEM_BOOTING, SYSTEM_SCHEDULING, + SYSTEM_FREEING_INITMEM, SYSTEM_RUNNING, SYSTEM_HALT, SYSTEM_POWER_OFF, diff --git a/init/main.c b/init/main.c index 3c4054a95545..767ee2672176 100644 --- a/init/main.c +++ b/init/main.c @@ -1506,6 +1506,8 @@ static int __ref kernel_init(void *unused) kernel_init_freeable(); /* need to finish all async __init code before freeing the memory */ async_synchronize_full(); + + system_state = SYSTEM_FREEING_INITMEM; kprobe_free_init_mem(); ftrace_free_init_mem(); kgdb_free_init_mem(); diff --git a/kernel/extable.c b/kernel/extable.c index b0ea5eb0c3b4..290661f68e6b 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -76,7 +76,7 @@ int notrace core_kernel_text(unsigned long addr) addr < (unsigned long)_etext) return 1; - if (system_state < SYSTEM_RUNNING && + if (system_state < SYSTEM_FREEING_INITMEM && init_kernel_text(addr)) return 1; return 0; From e5ae3728327fda5209454d738eebdb20443fdfac Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 5 Nov 2021 13:40:43 -0700 Subject: [PATCH 020/166] mm: make generic arch_is_kernel_initmem_freed() do what it says Commit 7a5da02de8d6 ("locking/lockdep: check for freed initmem in static_obj()") added arch_is_kernel_initmem_freed() which is supposed to report whether an object is part of already freed init memory. For the time being, the generic version of arch_is_kernel_initmem_freed() always reports 'false', allthough free_initmem() is generically called on all architectures. Therefore, change the generic version of arch_is_kernel_initmem_freed() to check whether free_initmem() has been called. If so, then check if a given address falls into init memory. To ease the use of system_state, move it out of line into its only caller which is lockdep.c Link: https://lkml.kernel.org/r/1d40783e676e07858be97d881f449ee7ea8adfb1.1633001016.git.christophe.leroy@csgroup.eu Signed-off-by: Christophe Leroy Cc: Gerald Schaefer Cc: Kefeng Wang Cc: Benjamin Herrenschmidt Cc: Heiko Carstens Cc: Paul Mackerras Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/sections.h | 14 -------------- kernel/locking/lockdep.c | 15 +++++++++++++++ 2 files changed, 15 insertions(+), 14 deletions(-) diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h index d16302d3eb59..596ab2092289 100644 --- a/include/asm-generic/sections.h +++ b/include/asm-generic/sections.h @@ -80,20 +80,6 @@ static inline int arch_is_kernel_data(unsigned long addr) } #endif -/* - * Check if an address is part of freed initmem. This is needed on architectures - * with virt == phys kernel mapping, for code that wants to check if an address - * is part of a static object within [_stext, _end]. After initmem is freed, - * memory can be allocated from it, and such allocations would then have - * addresses within the range [_stext, _end]. - */ -#ifndef arch_is_kernel_initmem_freed -static inline int arch_is_kernel_initmem_freed(unsigned long addr) -{ - return 0; -} -#endif - /** * memory_contains - checks if an object is contained within a memory region * @begin: virtual address of the beginning of the memory region diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index bf1c00c881e4..8e118caf835e 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -788,6 +788,21 @@ static int very_verbose(struct lock_class *class) * Is this the address of a static object: */ #ifdef __KERNEL__ +/* + * Check if an address is part of freed initmem. After initmem is freed, + * memory can be allocated from it, and such allocations would then have + * addresses within the range [_stext, _end]. + */ +#ifndef arch_is_kernel_initmem_freed +static int arch_is_kernel_initmem_freed(unsigned long addr) +{ + if (system_state < SYSTEM_FREEING_INITMEM) + return 0; + + return init_section_contains((void *)addr, 1); +} +#endif + static int static_obj(const void *obj) { unsigned long start = (unsigned long) &_stext, From e012a25d81a12fb332e862b51bfb59321acf96e4 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 5 Nov 2021 13:40:46 -0700 Subject: [PATCH 021/166] powerpc: use generic version of arch_is_kernel_initmem_freed() The generic version of arch_is_kernel_initmem_freed() now does the same as powerpc version. Remove the powerpc version. Link: https://lkml.kernel.org/r/c53764eb45d41491e2b21da2e7812239897dbebb.1633001016.git.christophe.leroy@csgroup.eu Signed-off-by: Christophe Leroy Cc: Kefeng Wang Cc: Benjamin Herrenschmidt Cc: Gerald Schaefer Cc: Heiko Carstens Cc: Paul Mackerras Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/include/asm/sections.h | 13 ------------- 1 file changed, 13 deletions(-) diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h index 6e4af4492a14..79cb7a25a5fb 100644 --- a/arch/powerpc/include/asm/sections.h +++ b/arch/powerpc/include/asm/sections.h @@ -6,21 +6,8 @@ #include #include -#define arch_is_kernel_initmem_freed arch_is_kernel_initmem_freed - #include -extern bool init_mem_is_free; - -static inline int arch_is_kernel_initmem_freed(unsigned long addr) -{ - if (!init_mem_is_free) - return 0; - - return addr >= (unsigned long)__init_begin && - addr < (unsigned long)__init_end; -} - extern char __head_end[]; #ifdef __powerpc64__ From 564f6ea1a689b06284641c12e164f3c5b57f3aaf Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 5 Nov 2021 13:40:49 -0700 Subject: [PATCH 022/166] s390: use generic version of arch_is_kernel_initmem_freed() The generic version of arch_is_kernel_initmem_freed() now does the same as s390 version. Remove the s390 version. Link: https://lkml.kernel.org/r/b6feb5dfe611a322de482762fc2df3a9eece70c7.1633001016.git.christophe.leroy@csgroup.eu Signed-off-by: Christophe Leroy Acked-by: Heiko Carstens Cc: Gerald Schaefer Cc: Kefeng Wang Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/s390/include/asm/sections.h | 12 ------------ arch/s390/mm/init.c | 3 --- 2 files changed, 15 deletions(-) diff --git a/arch/s390/include/asm/sections.h b/arch/s390/include/asm/sections.h index 85881dd48022..3fecaa4e8b74 100644 --- a/arch/s390/include/asm/sections.h +++ b/arch/s390/include/asm/sections.h @@ -2,20 +2,8 @@ #ifndef _S390_SECTIONS_H #define _S390_SECTIONS_H -#define arch_is_kernel_initmem_freed arch_is_kernel_initmem_freed - #include -extern bool initmem_freed; - -static inline int arch_is_kernel_initmem_freed(unsigned long addr) -{ - if (!initmem_freed) - return 0; - return addr >= (unsigned long)__init_begin && - addr < (unsigned long)__init_end; -} - /* * .boot.data section contains variables "shared" between the decompressor and * the decompressed kernel. The decompressor will store values in them, and diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index a04faf49001a..8c6f258a6183 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -58,8 +58,6 @@ unsigned long empty_zero_page, zero_page_mask; EXPORT_SYMBOL(empty_zero_page); EXPORT_SYMBOL(zero_page_mask); -bool initmem_freed; - static void __init setup_zero_pages(void) { unsigned int order; @@ -214,7 +212,6 @@ void __init mem_init(void) void free_initmem(void) { - initmem_freed = true; __set_memory((unsigned long)_sinittext, (unsigned long)(_einittext - _sinittext) >> PAGE_SHIFT, SET_MEMORY_RW | SET_MEMORY_NX); From 9c25cbfcb38462803a3d68f5d88e66a587f5f045 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 5 Nov 2021 13:40:52 -0700 Subject: [PATCH 023/166] mm: page_alloc: use migrate_disable() in drain_local_pages_wq() drain_local_pages_wq() disables preemption to avoid CPU migration during CPU hotplug and can't use cpus_read_lock(). Using migrate_disable() works here, too. The scheduler won't take the CPU offline until the task left the migrate-disable section. The problem with disabled preemption here is that drain_local_pages() acquires locks which are turned into sleeping locks on PREEMPT_RT and can't be acquired with disabled preemption. Use migrate_disable() in drain_local_pages_wq(). Link: https://lkml.kernel.org/r/20211015210933.viw6rjvo64qtqxn4@linutronix.de Signed-off-by: Sebastian Andrzej Siewior Cc: Thomas Gleixner Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6714039cddf4..2aafc337d068 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3141,9 +3141,9 @@ static void drain_local_pages_wq(struct work_struct *work) * cpu which is alright but we also have to make sure to not move to * a different one. */ - preempt_disable(); + migrate_disable(); drain_local_pages(drain->zone); - preempt_enable(); + migrate_enable(); } /* From 59d336bdf6931a6a8c2ba41e533267d1cc799fc9 Mon Sep 17 00:00:00 2001 From: Wang ShaoBo Date: Fri, 5 Nov 2021 13:40:55 -0700 Subject: [PATCH 024/166] mm/page_alloc: use clamp() to simplify code This patch uses clamp() to simplify code in init_per_zone_wmark_min(). Link: https://lkml.kernel.org/r/20211021034830.1049150-1-bobo.shaobowang@huawei.com Signed-off-by: Wang ShaoBo Reviewed-by: David Hildenbrand Cc: Wei Yongjun Cc: Li Bin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 2aafc337d068..a7035467bf6d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -8477,16 +8477,12 @@ int __meminit init_per_zone_wmark_min(void) lowmem_kbytes = nr_free_buffer_pages() * (PAGE_SIZE >> 10); new_min_free_kbytes = int_sqrt(lowmem_kbytes * 16); - if (new_min_free_kbytes > user_min_free_kbytes) { - min_free_kbytes = new_min_free_kbytes; - if (min_free_kbytes < 128) - min_free_kbytes = 128; - if (min_free_kbytes > 262144) - min_free_kbytes = 262144; - } else { + if (new_min_free_kbytes > user_min_free_kbytes) + min_free_kbytes = clamp(new_min_free_kbytes, 128, 262144); + else pr_warn("min_free_kbytes is not updated to %d because user defined value %d is preferred\n", new_min_free_kbytes, user_min_free_kbytes); - } + setup_per_zone_wmarks(); refresh_zone_stat_thresholds(); setup_per_zone_lowmem_reserve(); From 477d01fce8dacb41cae9363136ea56812e8baa59 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 5 Nov 2021 13:40:58 -0700 Subject: [PATCH 025/166] mm: fix data race in PagePoisoned() PagePoisoned() accesses page->flags which can be updated concurrently: | BUG: KCSAN: data-race in next_uptodate_page / unlock_page | | write (marked) to 0xffffea00050f37c0 of 8 bytes by task 1872 on cpu 1: | instrument_atomic_write include/linux/instrumented.h:87 [inline] | clear_bit_unlock_is_negative_byte include/asm-generic/bitops/instrumented-lock.h:74 [inline] | unlock_page+0x102/0x1b0 mm/filemap.c:1465 | filemap_map_pages+0x6c6/0x890 mm/filemap.c:3057 | ... | read to 0xffffea00050f37c0 of 8 bytes by task 1873 on cpu 0: | PagePoisoned include/linux/page-flags.h:204 [inline] | PageReadahead include/linux/page-flags.h:382 [inline] | next_uptodate_page+0x456/0x830 mm/filemap.c:2975 | ... | CPU: 0 PID: 1873 Comm: systemd-udevd Not tainted 5.11.0-rc4-00001-gf9ce0be71d1f #1 To avoid the compiler tearing or otherwise optimizing the access, use READ_ONCE() to access flags. Link: https://lore.kernel.org/all/20210826144157.GA26950@xsang-OptiPlex-9020/ Link: https://lkml.kernel.org/r/20210913113542.2658064-1-elver@google.com Reported-by: kernel test robot Signed-off-by: Marco Elver Acked-by: Kirill A. Shutemov Acked-by: Will Deacon Cc: Marco Elver Cc: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index fbfd3fad48f2..dd80cf0bb579 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -215,7 +215,7 @@ static __always_inline int PageCompound(struct page *page) #define PAGE_POISON_PATTERN -1l static inline int PagePoisoned(const struct page *page) { - return page->flags == PAGE_POISON_PATTERN; + return READ_ONCE(page->flags) == PAGE_POISON_PATTERN; } #ifdef CONFIG_DEBUG_VM From ba9eb3cef9e699e259f9ceefdbcd3ee83d3529e2 Mon Sep 17 00:00:00 2001 From: Rikard Falkeborn Date: Fri, 5 Nov 2021 13:41:01 -0700 Subject: [PATCH 026/166] mm/memory_failure: constify static mm_walk_ops The only usage of hwp_walk_ops is to pass its address to walk_page_range() which takes a pointer to const mm_walk_ops as argument. Make it const to allow the compiler to put it in read-only memory. Link: https://lkml.kernel.org/r/20211014075042.17174-3-rikard.falkeborn@gmail.com Signed-off-by: Rikard Falkeborn Acked-by: Naoya Horiguchi Reviewed-by: Anshuman Khandual Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 8376cfe0efce..54a5d28ea601 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -674,7 +674,7 @@ static int hwpoison_hugetlb_range(pte_t *ptep, unsigned long hmask, #define hwpoison_hugetlb_range NULL #endif -static struct mm_walk_ops hwp_walk_ops = { +static const struct mm_walk_ops hwp_walk_ops = { .pmd_entry = hwpoison_pte_range, .hugetlb_entry = hwpoison_hugetlb_range, }; From e0f43fa50605f89d45708bce3b94e408ef5c4342 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 5 Nov 2021 13:41:04 -0700 Subject: [PATCH 027/166] mm: filemap: coding style cleanup for filemap_map_pmd() Patch series "Solve silent data loss caused by poisoned page cache (shmem/tmpfs)", v5. When discussing the patch that splits page cache THP in order to offline the poisoned page, Noaya mentioned there is a bigger problem [1] that prevents this from working since the page cache page will be truncated if uncorrectable errors happen. By looking this deeper it turns out this approach (truncating poisoned page) may incur silent data loss for all non-readonly filesystems if the page is dirty. It may be worse for in-memory filesystem, e.g. shmem/tmpfs since the data blocks are actually gone. To solve this problem we could keep the poisoned dirty page in page cache then notify the users on any later access, e.g. page fault, read/write, etc. The clean page could be truncated as is since they can be reread from disk later on. The consequence is the filesystems may find poisoned page and manipulate it as healthy page since all the filesystems actually don't check if the page is poisoned or not in all the relevant paths except page fault. In general, we need make the filesystems be aware of poisoned page before we could keep the poisoned page in page cache in order to solve the data loss problem. To make filesystems be aware of poisoned page we should consider: - The page should be not written back: clearing dirty flag could prevent from writeback. - The page should not be dropped (it shows as a clean page) by drop caches or other callers: the refcount pin from hwpoison could prevent from invalidating (called by cache drop, inode cache shrinking, etc), but it doesn't avoid invalidation in DIO path. - The page should be able to get truncated/hole punched/unlinked: it works as it is. - Notify users when the page is accessed, e.g. read/write, page fault and other paths (compression, encryption, etc). The scope of the last one is huge since almost all filesystems need do it once a page is returned from page cache lookup. There are a couple of options to do it: 1. Check hwpoison flag for every path, the most straightforward way. 2. Return NULL for poisoned page from page cache lookup, the most callsites check if NULL is returned, this should have least work I think. But the error handling in filesystems just return -ENOMEM, the error code will incur confusion to the users obviously. 3. To improve #2, we could return error pointer, e.g. ERR_PTR(-EIO), but this will involve significant amount of code change as well since all the paths need check if the pointer is ERR or not just like option #1. I did prototypes for both #1 and #3, but it seems #3 may require more changes than #1. For #3 ERR_PTR will be returned so all the callers need to check the return value otherwise invalid pointer may be dereferenced, but not all callers really care about the content of the page, for example, partial truncate which just sets the truncated range in one page to 0. So for such paths it needs additional modification if ERR_PTR is returned. And if the callers have their own way to handle the problematic pages we need to add a new FGP flag to tell FGP functions to return the pointer to the page. It may happen very rarely, but once it happens the consequence (data corruption) could be very bad and it is very hard to debug. It seems this problem had been slightly discussed before, but seems no action was taken at that time. [2] As the aforementioned investigation, it needs huge amount of work to solve the potential data loss for all filesystems. But it is much easier for in-memory filesystems and such filesystems actually suffer more than others since even the data blocks are gone due to truncating. So this patchset starts from shmem/tmpfs by taking option #1. TODO: * The unpoison has been broken since commit 0ed950d1f281 ("mm,hwpoison: make get_hwpoison_page() call get_any_page()"), and this patch series make refcount check for unpoisoning shmem page fail. * Expand to other filesystems. But I haven't heard feedback from filesystem developers yet. Patch breakdown: Patch #1: cleanup, depended by patch #2 Patch #2: fix THP with hwpoisoned subpage(s) PMD map bug Patch #3: coding style cleanup Patch #4: refactor and preparation. Patch #5: keep the poisoned page in page cache and handle such case for all the paths. Patch #6: the previous patches unblock page cache THP split, so this patch add page cache THP split support. This patch (of 4): A minor cleanup to the indent. Link: https://lkml.kernel.org/r/20211020210755.23964-1-shy828301@gmail.com Link: https://lkml.kernel.org/r/20211020210755.23964-4-shy828301@gmail.com Signed-off-by: Yang Shi Reviewed-by: Naoya Horiguchi Cc: Hugh Dickins Cc: Kirill A. Shutemov Cc: Matthew Wilcox Cc: Oscar Salvador Cc: Peter Xu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/mm/filemap.c b/mm/filemap.c index d05f8013a4f0..6f2c4bd6a571 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3203,12 +3203,12 @@ static bool filemap_map_pmd(struct vm_fault *vmf, struct page *page) } if (pmd_none(*vmf->pmd) && PageTransHuge(page)) { - vm_fault_t ret = do_set_pmd(vmf, page); - if (!ret) { - /* The page is mapped successfully, reference consumed. */ - unlock_page(page); - return true; - } + vm_fault_t ret = do_set_pmd(vmf, page); + if (!ret) { + /* The page is mapped successfully, reference consumed. */ + unlock_page(page); + return true; + } } if (pmd_none(*vmf->pmd)) From dd0f230a0a80ff396c7ce587f16429f2a8131344 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 5 Nov 2021 13:41:07 -0700 Subject: [PATCH 028/166] mm: hwpoison: refactor refcount check handling Memory failure will report failure if the page still has extra pinned refcount other than from hwpoison after the handler is done. Actually the check is not necessary for all handlers, so move the check into specific handlers. This would make the following keeping shmem page in page cache patch easier. There may be expected extra pin for some cases, for example, when the page is dirty and in swapcache. Link: https://lkml.kernel.org/r/20211020210755.23964-5-shy828301@gmail.com Signed-off-by: Yang Shi Signed-off-by: Naoya Horiguchi Suggested-by: Naoya Horiguchi Cc: Hugh Dickins Cc: Kirill A. Shutemov Cc: Matthew Wilcox Cc: Oscar Salvador Cc: Peter Xu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 93 +++++++++++++++++++++++++++++++-------------- 1 file changed, 64 insertions(+), 29 deletions(-) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 54a5d28ea601..bbd433e96790 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -807,12 +807,44 @@ static int truncate_error_page(struct page *p, unsigned long pfn, return ret; } +struct page_state { + unsigned long mask; + unsigned long res; + enum mf_action_page_type type; + + /* Callback ->action() has to unlock the relevant page inside it. */ + int (*action)(struct page_state *ps, struct page *p); +}; + +/* + * Return true if page is still referenced by others, otherwise return + * false. + * + * The extra_pins is true when one extra refcount is expected. + */ +static bool has_extra_refcount(struct page_state *ps, struct page *p, + bool extra_pins) +{ + int count = page_count(p) - 1; + + if (extra_pins) + count -= 1; + + if (count > 0) { + pr_err("Memory failure: %#lx: %s still referenced by %d users\n", + page_to_pfn(p), action_page_types[ps->type], count); + return true; + } + + return false; +} + /* * Error hit kernel page. * Do nothing, try to be lucky and not touch this instead. For a few cases we * could be more sophisticated. */ -static int me_kernel(struct page *p, unsigned long pfn) +static int me_kernel(struct page_state *ps, struct page *p) { unlock_page(p); return MF_IGNORED; @@ -821,9 +853,9 @@ static int me_kernel(struct page *p, unsigned long pfn) /* * Page in unknown state. Do nothing. */ -static int me_unknown(struct page *p, unsigned long pfn) +static int me_unknown(struct page_state *ps, struct page *p) { - pr_err("Memory failure: %#lx: Unknown page state\n", pfn); + pr_err("Memory failure: %#lx: Unknown page state\n", page_to_pfn(p)); unlock_page(p); return MF_FAILED; } @@ -831,7 +863,7 @@ static int me_unknown(struct page *p, unsigned long pfn) /* * Clean (or cleaned) page cache page. */ -static int me_pagecache_clean(struct page *p, unsigned long pfn) +static int me_pagecache_clean(struct page_state *ps, struct page *p) { int ret; struct address_space *mapping; @@ -868,9 +900,13 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) * * Open: to take i_rwsem or not for this? Right now we don't. */ - ret = truncate_error_page(p, pfn, mapping); + ret = truncate_error_page(p, page_to_pfn(p), mapping); out: unlock_page(p); + + if (has_extra_refcount(ps, p, false)) + ret = MF_FAILED; + return ret; } @@ -879,7 +915,7 @@ out: * Issues: when the error hit a hole page the error is not properly * propagated. */ -static int me_pagecache_dirty(struct page *p, unsigned long pfn) +static int me_pagecache_dirty(struct page_state *ps, struct page *p) { struct address_space *mapping = page_mapping(p); @@ -923,7 +959,7 @@ static int me_pagecache_dirty(struct page *p, unsigned long pfn) mapping_set_error(mapping, -EIO); } - return me_pagecache_clean(p, pfn); + return me_pagecache_clean(ps, p); } /* @@ -945,9 +981,10 @@ static int me_pagecache_dirty(struct page *p, unsigned long pfn) * Clean swap cache pages can be directly isolated. A later page fault will * bring in the known good data from disk. */ -static int me_swapcache_dirty(struct page *p, unsigned long pfn) +static int me_swapcache_dirty(struct page_state *ps, struct page *p) { int ret; + bool extra_pins = false; ClearPageDirty(p); /* Trigger EIO in shmem: */ @@ -955,10 +992,17 @@ static int me_swapcache_dirty(struct page *p, unsigned long pfn) ret = delete_from_lru_cache(p) ? MF_FAILED : MF_DELAYED; unlock_page(p); + + if (ret == MF_DELAYED) + extra_pins = true; + + if (has_extra_refcount(ps, p, extra_pins)) + ret = MF_FAILED; + return ret; } -static int me_swapcache_clean(struct page *p, unsigned long pfn) +static int me_swapcache_clean(struct page_state *ps, struct page *p) { int ret; @@ -966,6 +1010,10 @@ static int me_swapcache_clean(struct page *p, unsigned long pfn) ret = delete_from_lru_cache(p) ? MF_FAILED : MF_RECOVERED; unlock_page(p); + + if (has_extra_refcount(ps, p, false)) + ret = MF_FAILED; + return ret; } @@ -975,7 +1023,7 @@ static int me_swapcache_clean(struct page *p, unsigned long pfn) * - Error on hugepage is contained in hugepage unit (not in raw page unit.) * To narrow down kill region to one page, we need to break up pmd. */ -static int me_huge_page(struct page *p, unsigned long pfn) +static int me_huge_page(struct page_state *ps, struct page *p) { int res; struct page *hpage = compound_head(p); @@ -986,7 +1034,7 @@ static int me_huge_page(struct page *p, unsigned long pfn) mapping = page_mapping(hpage); if (mapping) { - res = truncate_error_page(hpage, pfn, mapping); + res = truncate_error_page(hpage, page_to_pfn(p), mapping); unlock_page(hpage); } else { res = MF_FAILED; @@ -1004,6 +1052,9 @@ static int me_huge_page(struct page *p, unsigned long pfn) } } + if (has_extra_refcount(ps, p, false)) + res = MF_FAILED; + return res; } @@ -1029,14 +1080,7 @@ static int me_huge_page(struct page *p, unsigned long pfn) #define slab (1UL << PG_slab) #define reserved (1UL << PG_reserved) -static struct page_state { - unsigned long mask; - unsigned long res; - enum mf_action_page_type type; - - /* Callback ->action() has to unlock the relevant page inside it. */ - int (*action)(struct page *p, unsigned long pfn); -} error_states[] = { +static struct page_state error_states[] = { { reserved, reserved, MF_MSG_KERNEL, me_kernel }, /* * free pages are specially detected outside this table: @@ -1096,19 +1140,10 @@ static int page_action(struct page_state *ps, struct page *p, unsigned long pfn) { int result; - int count; /* page p should be unlocked after returning from ps->action(). */ - result = ps->action(p, pfn); + result = ps->action(ps, p); - count = page_count(p) - 1; - if (ps->action == me_swapcache_dirty && result == MF_DELAYED) - count--; - if (count > 0) { - pr_err("Memory failure: %#lx: %s still referenced by %d users\n", - pfn, action_page_types[ps->type], count); - result = MF_FAILED; - } action_result(pfn, ps->type, result); /* Could do more checks here if page looks ok */ From b9d02f1bdd98f38e6e5ecacc9786a8f58f3f8b2c Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 5 Nov 2021 13:41:10 -0700 Subject: [PATCH 029/166] mm: shmem: don't truncate page if memory failure happens The current behavior of memory failure is to truncate the page cache regardless of dirty or clean. If the page is dirty the later access will get the obsolete data from disk without any notification to the users. This may cause silent data loss. It is even worse for shmem since shmem is in-memory filesystem, truncating page cache means discarding data blocks. The later read would return all zero. The right approach is to keep the corrupted page in page cache, any later access would return error for syscalls or SIGBUS for page fault, until the file is truncated, hole punched or removed. The regular storage backed filesystems would be more complicated so this patch is focused on shmem. This also unblock the support for soft offlining shmem THP. [arnd@arndb.de: fix uninitialized variable use in me_pagecache_clean()] Link: https://lkml.kernel.org/r/20211022064748.4173718-1-arnd@kernel.org Link: https://lkml.kernel.org/r/20211020210755.23964-6-shy828301@gmail.com Signed-off-by: Yang Shi Signed-off-by: Arnd Bergmann Cc: Hugh Dickins Cc: Kirill A. Shutemov Cc: Matthew Wilcox Cc: Naoya Horiguchi Cc: Oscar Salvador Cc: Peter Xu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 14 +++++++++++--- mm/shmem.c | 38 +++++++++++++++++++++++++++++++++++--- mm/userfaultfd.c | 5 +++++ 3 files changed, 51 insertions(+), 6 deletions(-) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index bbd433e96790..952a41d568c4 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -58,6 +58,7 @@ #include #include #include +#include #include "internal.h" #include "ras/ras_event.h" @@ -867,6 +868,7 @@ static int me_pagecache_clean(struct page_state *ps, struct page *p) { int ret; struct address_space *mapping; + bool extra_pins; delete_from_lru_cache(p); @@ -895,18 +897,24 @@ static int me_pagecache_clean(struct page_state *ps, struct page *p) goto out; } + /* + * The shmem page is kept in page cache instead of truncating + * so is expected to have an extra refcount after error-handling. + */ + extra_pins = shmem_mapping(mapping); + /* * Truncation is a bit tricky. Enable it per file system for now. * * Open: to take i_rwsem or not for this? Right now we don't. */ ret = truncate_error_page(p, page_to_pfn(p), mapping); + if (has_extra_refcount(ps, p, extra_pins)) + ret = MF_FAILED; + out: unlock_page(p); - if (has_extra_refcount(ps, p, false)) - ret = MF_FAILED; - return ret; } diff --git a/mm/shmem.c b/mm/shmem.c index df2f0288b9ca..6a7bb46019e2 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2454,6 +2454,7 @@ shmem_write_begin(struct file *file, struct address_space *mapping, struct inode *inode = mapping->host; struct shmem_inode_info *info = SHMEM_I(inode); pgoff_t index = pos >> PAGE_SHIFT; + int ret = 0; /* i_rwsem is held by caller */ if (unlikely(info->seals & (F_SEAL_GROW | @@ -2464,7 +2465,15 @@ shmem_write_begin(struct file *file, struct address_space *mapping, return -EPERM; } - return shmem_getpage(inode, index, pagep, SGP_WRITE); + ret = shmem_getpage(inode, index, pagep, SGP_WRITE); + + if (*pagep && PageHWPoison(*pagep)) { + unlock_page(*pagep); + put_page(*pagep); + ret = -EIO; + } + + return ret; } static int @@ -2551,6 +2560,12 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) if (sgp == SGP_CACHE) set_page_dirty(page); unlock_page(page); + + if (PageHWPoison(page)) { + put_page(page); + error = -EIO; + break; + } } /* @@ -3112,7 +3127,8 @@ static const char *shmem_get_link(struct dentry *dentry, page = find_get_page(inode->i_mapping, 0); if (!page) return ERR_PTR(-ECHILD); - if (!PageUptodate(page)) { + if (PageHWPoison(page) || + !PageUptodate(page)) { put_page(page); return ERR_PTR(-ECHILD); } @@ -3120,6 +3136,11 @@ static const char *shmem_get_link(struct dentry *dentry, error = shmem_getpage(inode, 0, &page, SGP_READ); if (error) return ERR_PTR(error); + if (page && PageHWPoison(page)) { + unlock_page(page); + put_page(page); + return ERR_PTR(-ECHILD); + } unlock_page(page); } set_delayed_call(done, shmem_put_link, page); @@ -3770,6 +3791,13 @@ static void shmem_destroy_inodecache(void) kmem_cache_destroy(shmem_inode_cachep); } +/* Keep the page in page cache instead of truncating it */ +static int shmem_error_remove_page(struct address_space *mapping, + struct page *page) +{ + return 0; +} + const struct address_space_operations shmem_aops = { .writepage = shmem_writepage, .set_page_dirty = __set_page_dirty_no_writeback, @@ -3780,7 +3808,7 @@ const struct address_space_operations shmem_aops = { #ifdef CONFIG_MIGRATION .migratepage = migrate_page, #endif - .error_remove_page = generic_error_remove_page, + .error_remove_page = shmem_error_remove_page, }; EXPORT_SYMBOL(shmem_aops); @@ -4191,6 +4219,10 @@ struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, page = ERR_PTR(error); else unlock_page(page); + + if (PageHWPoison(page)) + page = ERR_PTR(-EIO); + return page; #else /* diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index caf6dfff2a60..77fce86371a9 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -232,6 +232,11 @@ static int mcontinue_atomic_pte(struct mm_struct *dst_mm, goto out; } + if (PageHWPoison(page)) { + ret = -EIO; + goto out_release; + } + ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr, page, false, wp_copy); if (ret) From 4966455d9100236fd6dd72b0cd00818435fdb25d Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 5 Nov 2021 13:41:14 -0700 Subject: [PATCH 030/166] mm: hwpoison: handle non-anonymous THP correctly Currently hwpoison doesn't handle non-anonymous THP, but since v4.8 THP support for tmpfs and read-only file cache has been added. They could be offlined by split THP, just like anonymous THP. Link: https://lkml.kernel.org/r/20211020210755.23964-7-shy828301@gmail.com Signed-off-by: Yang Shi Acked-by: Naoya Horiguchi Cc: Hugh Dickins Cc: Kirill A. Shutemov Cc: Matthew Wilcox Cc: Oscar Salvador Cc: Peter Xu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 952a41d568c4..f38b7b42a508 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1444,14 +1444,11 @@ static int identify_page_state(unsigned long pfn, struct page *p, static int try_to_split_thp_page(struct page *page, const char *msg) { lock_page(page); - if (!PageAnon(page) || unlikely(split_huge_page(page))) { + if (unlikely(split_huge_page(page))) { unsigned long pfn = page_to_pfn(page); unlock_page(page); - if (!PageAnon(page)) - pr_info("%s: %#lx: non anonymous thp\n", msg, pfn); - else - pr_info("%s: %#lx: thp split failed\n", msg, pfn); + pr_info("%s: %#lx: thp split failed\n", msg, pfn); put_page(page); return -EBUSY; } From 73c54763482b841d9c14bad87eec98f80f700e0b Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Fri, 5 Nov 2021 13:41:17 -0700 Subject: [PATCH 031/166] mm/hugetlb: drop __unmap_hugepage_range definition from hugetlb.h Remove __unmap_hugepage_range() from the header file, because it is only used in hugetlb.c. Link: https://lkml.kernel.org/r/20210917165108.9341-1-peterx@redhat.com Signed-off-by: Peter Xu Suggested-by: Mike Kravetz Reviewed-by: Mike Kravetz Reviewed-by: John Hubbard Reviewed-by: Muchun Song Reviewed-by: David Hildenbrand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 10 ---------- mm/hugetlb.c | 6 +++--- 2 files changed, 3 insertions(+), 13 deletions(-) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 1faebe1cd0ed..3cbf60464398 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -143,9 +143,6 @@ void __unmap_hugepage_range_final(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page); -void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, - unsigned long start, unsigned long end, - struct page *ref_page); void hugetlb_report_meminfo(struct seq_file *); int hugetlb_report_node_meminfo(char *buf, int len, int nid); void hugetlb_show_meminfo(void); @@ -385,13 +382,6 @@ static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb, BUG(); } -static inline void __unmap_hugepage_range(struct mmu_gather *tlb, - struct vm_area_struct *vma, unsigned long start, - unsigned long end, struct page *ref_page) -{ - BUG(); -} - static inline vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 95dc7b83381f..d394d9545c4e 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4426,9 +4426,9 @@ again: return ret; } -void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, - unsigned long start, unsigned long end, - struct page *ref_page) +static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, + unsigned long start, unsigned long end, + struct page *ref_page) { struct mm_struct *mm = vma->vm_mm; unsigned long address; From 79dfc695525f60c8410015362b8aa4eb5c57210c Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Fri, 5 Nov 2021 13:41:20 -0700 Subject: [PATCH 032/166] hugetlb: add demote hugetlb page sysfs interfaces Patch series "hugetlb: add demote/split page functionality", v4. The concurrent use of multiple hugetlb page sizes on a single system is becoming more common. One of the reasons is better TLB support for gigantic page sizes on x86 hardware. In addition, hugetlb pages are being used to back VMs in hosting environments. When using hugetlb pages to back VMs, it is often desirable to preallocate hugetlb pools. This avoids the delay and uncertainty of allocating hugetlb pages at VM startup. In addition, preallocating huge pages minimizes the issue of memory fragmentation that increases the longer the system is up and running. In such environments, a combination of larger and smaller hugetlb pages are preallocated in anticipation of backing VMs of various sizes. Over time, the preallocated pool of smaller hugetlb pages may become depleted while larger hugetlb pages still remain. In such situations, it is desirable to convert larger hugetlb pages to smaller hugetlb pages. Converting larger to smaller hugetlb pages can be accomplished today by first freeing the larger page to the buddy allocator and then allocating the smaller pages. For example, to convert 50 GB pages on x86: gb_pages=`cat .../hugepages-1048576kB/nr_hugepages` m2_pages=`cat .../hugepages-2048kB/nr_hugepages` echo $(($gb_pages - 50)) > .../hugepages-1048576kB/nr_hugepages echo $(($m2_pages + 25600)) > .../hugepages-2048kB/nr_hugepages On an idle system this operation is fairly reliable and results are as expected. The number of 2MB pages is increased as expected and the time of the operation is a second or two. However, when there is activity on the system the following issues arise: 1) This process can take quite some time, especially if allocation of the smaller pages is not immediate and requires migration/compaction. 2) There is no guarantee that the total size of smaller pages allocated will match the size of the larger page which was freed. This is because the area freed by the larger page could quickly be fragmented. In a test environment with a load that continually fills the page cache with clean pages, results such as the following can be observed: Unexpected number of 2MB pages allocated: Expected 25600, have 19944 real 0m42.092s user 0m0.008s sys 0m41.467s To address these issues, introduce the concept of hugetlb page demotion. Demotion provides a means of 'in place' splitting of a hugetlb page to pages of a smaller size. This avoids freeing pages to buddy and then trying to allocate from buddy. Page demotion is controlled via sysfs files that reside in the per-hugetlb page size and per node directories. - demote_size Target page size for demotion, a smaller huge page size. File can be written to chose a smaller huge page size if multiple are available. - demote Writable number of hugetlb pages to be demoted To demote 50 GB huge pages, one would: cat .../hugepages-1048576kB/free_hugepages /* optional, verify free pages */ cat .../hugepages-1048576kB/demote_size /* optional, verify target size */ echo 50 > .../hugepages-1048576kB/demote Only hugetlb pages which are free at the time of the request can be demoted. Demotion does not add to the complexity of surplus pages and honors reserved huge pages. Therefore, when a value is written to the sysfs demote file, that value is only the maximum number of pages which will be demoted. It is possible fewer will actually be demoted. The recently introduced per-hstate mutex is used to synchronize demote operations with other operations that modify hugetlb pools. Real world use cases -------------------- The above scenario describes a real world use case where hugetlb pages are used to back VMs on x86. Both issues of long allocation times and not necessarily getting the expected number of smaller huge pages after a free and allocate cycle have been experienced. The occurrence of these issues is dependent on other activity within the host and can not be predicted. This patch (of 5): Two new sysfs files are added to demote hugtlb pages. These files are both per-hugetlb page size and per node. Files are: demote_size - The size in Kb that pages are demoted to. (read-write) demote - The number of huge pages to demote. (write-only) By default, demote_size is the next smallest huge page size. Valid huge page sizes less than huge page size may be written to this file. When huge pages are demoted, they are demoted to this size. Writing a value to demote will result in an attempt to demote that number of hugetlb pages to an appropriate number of demote_size pages. NOTE: Demote interfaces are only provided for huge page sizes if there is a smaller target demote huge page size. For example, on x86 1GB huge pages will have demote interfaces. 2MB huge pages will not have demote interfaces. This patch does not provide full demote functionality. It only provides the sysfs interfaces. It also provides documentation for the new interfaces. [mike.kravetz@oracle.com: n_mask initialization does not need to be protected by the mutex] Link: https://lkml.kernel.org/r/0530e4ef-2492-5186-f919-5db68edea654@oracle.com Link: https://lkml.kernel.org/r/20211007181918.136982-2-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Reviewed-by: Oscar Salvador Cc: David Hildenbrand Cc: Michal Hocko Cc: Zi Yan Cc: Muchun Song Cc: Naoya Horiguchi Cc: David Rientjes Cc: "Aneesh Kumar K . V" Cc: Nghia Le Cc: Mike Kravetz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/mm/hugetlbpage.rst | 30 +++- include/linux/hugetlb.h | 1 + mm/hugetlb.c | 155 ++++++++++++++++++- 3 files changed, 183 insertions(+), 3 deletions(-) diff --git a/Documentation/admin-guide/mm/hugetlbpage.rst b/Documentation/admin-guide/mm/hugetlbpage.rst index 8abaeb144e44..bb90de3885d1 100644 --- a/Documentation/admin-guide/mm/hugetlbpage.rst +++ b/Documentation/admin-guide/mm/hugetlbpage.rst @@ -234,8 +234,12 @@ will exist, of the form:: hugepages-${size}kB -Inside each of these directories, the same set of files will exist:: +Inside each of these directories, the set of files contained in ``/proc`` +will exist. In addition, two additional interfaces for demoting huge +pages may exist:: + demote + demote_size nr_hugepages nr_hugepages_mempolicy nr_overcommit_hugepages @@ -243,7 +247,29 @@ Inside each of these directories, the same set of files will exist:: resv_hugepages surplus_hugepages -which function as described above for the default huge page-sized case. +The demote interfaces provide the ability to split a huge page into +smaller huge pages. For example, the x86 architecture supports both +1GB and 2MB huge pages sizes. A 1GB huge page can be split into 512 +2MB huge pages. Demote interfaces are not available for the smallest +huge page size. The demote interfaces are: + +demote_size + is the size of demoted pages. When a page is demoted a corresponding + number of huge pages of demote_size will be created. By default, + demote_size is set to the next smaller huge page size. If there are + multiple smaller huge page sizes, demote_size can be set to any of + these smaller sizes. Only huge page sizes less than the current huge + pages size are allowed. + +demote + is used to demote a number of huge pages. A user with root privileges + can write to this file. It may not be possible to demote the + requested number of huge pages. To determine how many pages were + actually demoted, compare the value of nr_hugepages before and after + writing to the demote interface. demote is a write only interface. + +The interfaces which are the same as in ``/proc`` (all except demote and +demote_size) function as described above for the default huge page-sized case. .. _mem_policy_and_hp_alloc: diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 3cbf60464398..2bddd6c38204 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -586,6 +586,7 @@ struct hstate { int next_nid_to_alloc; int next_nid_to_free; unsigned int order; + unsigned int demote_order; unsigned long mask; unsigned long max_huge_pages; unsigned long nr_huge_pages; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index d394d9545c4e..1a18ff2f0001 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2986,7 +2986,7 @@ free: static void __init hugetlb_init_hstates(void) { - struct hstate *h; + struct hstate *h, *h2; for_each_hstate(h) { if (minimum_order > huge_page_order(h)) @@ -2995,6 +2995,22 @@ static void __init hugetlb_init_hstates(void) /* oversize hugepages were init'ed in early boot */ if (!hstate_is_gigantic(h)) hugetlb_hstate_alloc_pages(h); + + /* + * Set demote order for each hstate. Note that + * h->demote_order is initially 0. + * - We can not demote gigantic pages if runtime freeing + * is not supported, so skip this. + */ + if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) + continue; + for_each_hstate(h2) { + if (h2 == h) + continue; + if (h2->order < h->order && + h2->order > h->demote_order) + h->demote_order = h2->order; + } } VM_BUG_ON(minimum_order == UINT_MAX); } @@ -3235,9 +3251,31 @@ out: return 0; } +static int demote_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed) + __must_hold(&hugetlb_lock) +{ + int rc = 0; + + lockdep_assert_held(&hugetlb_lock); + + /* We should never get here if no demote order */ + if (!h->demote_order) { + pr_warn("HugeTLB: NULL demote order passed to demote_pool_huge_page.\n"); + return -EINVAL; /* internal error */ + } + + /* + * TODO - demote fucntionality will be added in subsequent patch + */ + return rc; +} + #define HSTATE_ATTR_RO(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) +#define HSTATE_ATTR_WO(_name) \ + static struct kobj_attribute _name##_attr = __ATTR_WO(_name) + #define HSTATE_ATTR(_name) \ static struct kobj_attribute _name##_attr = \ __ATTR(_name, 0644, _name##_show, _name##_store) @@ -3433,6 +3471,105 @@ static ssize_t surplus_hugepages_show(struct kobject *kobj, } HSTATE_ATTR_RO(surplus_hugepages); +static ssize_t demote_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t len) +{ + unsigned long nr_demote; + unsigned long nr_available; + nodemask_t nodes_allowed, *n_mask; + struct hstate *h; + int err = 0; + int nid; + + err = kstrtoul(buf, 10, &nr_demote); + if (err) + return err; + h = kobj_to_hstate(kobj, &nid); + + if (nid != NUMA_NO_NODE) { + init_nodemask_of_node(&nodes_allowed, nid); + n_mask = &nodes_allowed; + } else { + n_mask = &node_states[N_MEMORY]; + } + + /* Synchronize with other sysfs operations modifying huge pages */ + mutex_lock(&h->resize_lock); + spin_lock_irq(&hugetlb_lock); + + while (nr_demote) { + /* + * Check for available pages to demote each time thorough the + * loop as demote_pool_huge_page will drop hugetlb_lock. + * + * NOTE: demote_pool_huge_page does not yet drop hugetlb_lock + * but will when full demote functionality is added in a later + * patch. + */ + if (nid != NUMA_NO_NODE) + nr_available = h->free_huge_pages_node[nid]; + else + nr_available = h->free_huge_pages; + nr_available -= h->resv_huge_pages; + if (!nr_available) + break; + + err = demote_pool_huge_page(h, n_mask); + if (err) + break; + + nr_demote--; + } + + spin_unlock_irq(&hugetlb_lock); + mutex_unlock(&h->resize_lock); + + if (err) + return err; + return len; +} +HSTATE_ATTR_WO(demote); + +static ssize_t demote_size_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + int nid; + struct hstate *h = kobj_to_hstate(kobj, &nid); + unsigned long demote_size = (PAGE_SIZE << h->demote_order) / SZ_1K; + + return sysfs_emit(buf, "%lukB\n", demote_size); +} + +static ssize_t demote_size_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct hstate *h, *demote_hstate; + unsigned long demote_size; + unsigned int demote_order; + int nid; + + demote_size = (unsigned long)memparse(buf, NULL); + + demote_hstate = size_to_hstate(demote_size); + if (!demote_hstate) + return -EINVAL; + demote_order = demote_hstate->order; + + /* demote order must be smaller than hstate order */ + h = kobj_to_hstate(kobj, &nid); + if (demote_order >= h->order) + return -EINVAL; + + /* resize_lock synchronizes access to demote size and writes */ + mutex_lock(&h->resize_lock); + h->demote_order = demote_order; + mutex_unlock(&h->resize_lock); + + return count; +} +HSTATE_ATTR(demote_size); + static struct attribute *hstate_attrs[] = { &nr_hugepages_attr.attr, &nr_overcommit_hugepages_attr.attr, @@ -3449,6 +3586,16 @@ static const struct attribute_group hstate_attr_group = { .attrs = hstate_attrs, }; +static struct attribute *hstate_demote_attrs[] = { + &demote_size_attr.attr, + &demote_attr.attr, + NULL, +}; + +static const struct attribute_group hstate_demote_attr_group = { + .attrs = hstate_demote_attrs, +}; + static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent, struct kobject **hstate_kobjs, const struct attribute_group *hstate_attr_group) @@ -3466,6 +3613,12 @@ static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent, hstate_kobjs[hi] = NULL; } + if (h->demote_order) { + if (sysfs_create_group(hstate_kobjs[hi], + &hstate_demote_attr_group)) + pr_warn("HugeTLB unable to create demote interfaces for %s\n", h->name); + } + return retval; } From 9871e2ded6c1ff61a59988d7a0e975f012105d52 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Fri, 5 Nov 2021 13:41:23 -0700 Subject: [PATCH 033/166] mm/cma: add cma_pages_valid to determine if pages are in CMA Add new interface cma_pages_valid() which indicates if the specified pages are part of a CMA region. This interface will be used in a subsequent patch by hugetlb code. In order to keep the same amount of DEBUG information, a pr_debug() call was added to cma_pages_valid(). In the case where the page passed to cma_release is not in cma region, the debug message will be printed from cma_pages_valid as opposed to cma_release. Link: https://lkml.kernel.org/r/20211007181918.136982-3-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Acked-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: "Aneesh Kumar K . V" Cc: David Rientjes Cc: Michal Hocko Cc: Muchun Song Cc: Naoya Horiguchi Cc: Nghia Le Cc: Zi Yan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cma.h | 1 + mm/cma.c | 24 ++++++++++++++++++++---- 2 files changed, 21 insertions(+), 4 deletions(-) diff --git a/include/linux/cma.h b/include/linux/cma.h index 53fd8c3cdbd0..bd801023504b 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -46,6 +46,7 @@ extern int cma_init_reserved_mem(phys_addr_t base, phys_addr_t size, struct cma **res_cma); extern struct page *cma_alloc(struct cma *cma, unsigned long count, unsigned int align, bool no_warn); +extern bool cma_pages_valid(struct cma *cma, const struct page *pages, unsigned long count); extern bool cma_release(struct cma *cma, const struct page *pages, unsigned long count); extern int cma_for_each_area(int (*it)(struct cma *cma, void *data), void *data); diff --git a/mm/cma.c b/mm/cma.c index 995e15480937..11152c3fb23c 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -524,6 +524,25 @@ out: return page; } +bool cma_pages_valid(struct cma *cma, const struct page *pages, + unsigned long count) +{ + unsigned long pfn; + + if (!cma || !pages) + return false; + + pfn = page_to_pfn(pages); + + if (pfn < cma->base_pfn || pfn >= cma->base_pfn + cma->count) { + pr_debug("%s(page %p, count %lu)\n", __func__, + (void *)pages, count); + return false; + } + + return true; +} + /** * cma_release() - release allocated pages * @cma: Contiguous memory region for which the allocation is performed. @@ -539,16 +558,13 @@ bool cma_release(struct cma *cma, const struct page *pages, { unsigned long pfn; - if (!cma || !pages) + if (!cma_pages_valid(cma, pages, count)) return false; pr_debug("%s(page %p, count %lu)\n", __func__, (void *)pages, count); pfn = page_to_pfn(pages); - if (pfn < cma->base_pfn || pfn >= cma->base_pfn + cma->count) - return false; - VM_BUG_ON(pfn + count > cma->base_pfn + cma->count); free_contig_range(pfn, count); From a01f43901cfb93b7b63f2739774b80469b21128d Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Fri, 5 Nov 2021 13:41:27 -0700 Subject: [PATCH 034/166] hugetlb: be sure to free demoted CMA pages to CMA When huge page demotion is fully implemented, gigantic pages can be demoted to a smaller huge page size. For example, on x86 a 1G page can be demoted to 512 2M pages. However, gigantic pages can potentially be allocated from CMA. If a gigantic page which was allocated from CMA is demoted, the corresponding demoted pages needs to be returned to CMA. Use the new interface cma_pages_valid() to determine if a non-gigantic hugetlb page should be freed to CMA. Also, clear mapping field of these pages as expected by cma_release. This also requires a change to CMA region creation for gigantic pages. CMA uses a per-region bit map to track allocations. When setting up the region, you specify how many pages each bit represents. Currently, only gigantic pages are allocated/freed from CMA so the region is set up such that one bit represents a gigantic page size allocation. With demote, a gigantic page (allocation) could be split into smaller size pages. And, these smaller size pages will be freed to CMA. So, since the per-region bit map needs to be set up to represent the smallest allocation/free size, it now needs to be set to the smallest huge page size which can be freed to CMA. Unfortunately, we set up the CMA region for huge pages before we set up huge pages sizes (hstates). So, technically we do not know the smallest huge page size as this can change via command line options and architecture specific code. Therefore, at region setup time we use HUGETLB_PAGE_ORDER as the smallest possible huge page size that can be given back to CMA. It is possible that this value is sub-optimal for some architectures/config options. If needed, this can be addressed in follow on work. Link: https://lkml.kernel.org/r/20211007181918.136982-4-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Cc: "Aneesh Kumar K . V" Cc: David Hildenbrand Cc: David Rientjes Cc: Michal Hocko Cc: Muchun Song Cc: Naoya Horiguchi Cc: Nghia Le Cc: Oscar Salvador Cc: Zi Yan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 41 +++++++++++++++++++++++++++++++++++++++-- 1 file changed, 39 insertions(+), 2 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 1a18ff2f0001..6662a99e6dab 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -50,6 +50,16 @@ struct hstate hstates[HUGE_MAX_HSTATE]; #ifdef CONFIG_CMA static struct cma *hugetlb_cma[MAX_NUMNODES]; +static bool hugetlb_cma_page(struct page *page, unsigned int order) +{ + return cma_pages_valid(hugetlb_cma[page_to_nid(page)], page, + 1 << order); +} +#else +static bool hugetlb_cma_page(struct page *page, unsigned int order) +{ + return false; +} #endif static unsigned long hugetlb_cma_size __initdata; @@ -1272,6 +1282,7 @@ static void destroy_compound_gigantic_page(struct page *page, atomic_set(compound_pincount_ptr(page), 0); for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) { + p->mapping = NULL; clear_compound_head(p); set_page_refcounted(p); } @@ -1476,7 +1487,13 @@ static void __update_and_free_page(struct hstate *h, struct page *page) 1 << PG_active | 1 << PG_private | 1 << PG_writeback); } - if (hstate_is_gigantic(h)) { + + /* + * Non-gigantic pages demoted from CMA allocated gigantic pages + * need to be given back to CMA in free_gigantic_page. + */ + if (hstate_is_gigantic(h) || + hugetlb_cma_page(page, huge_page_order(h))) { destroy_compound_gigantic_page(page, huge_page_order(h)); free_gigantic_page(page, huge_page_order(h)); } else { @@ -3001,9 +3018,13 @@ static void __init hugetlb_init_hstates(void) * h->demote_order is initially 0. * - We can not demote gigantic pages if runtime freeing * is not supported, so skip this. + * - If CMA allocation is possible, we can not demote + * HUGETLB_PAGE_ORDER or smaller size pages. */ if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) continue; + if (hugetlb_cma_size && h->order <= HUGETLB_PAGE_ORDER) + continue; for_each_hstate(h2) { if (h2 == h) continue; @@ -3555,6 +3576,8 @@ static ssize_t demote_size_store(struct kobject *kobj, if (!demote_hstate) return -EINVAL; demote_order = demote_hstate->order; + if (demote_order < HUGETLB_PAGE_ORDER) + return -EINVAL; /* demote order must be smaller than hstate order */ h = kobj_to_hstate(kobj, &nid); @@ -6543,6 +6566,7 @@ void __init hugetlb_cma_reserve(int order) if (hugetlb_cma_size < (PAGE_SIZE << order)) { pr_warn("hugetlb_cma: cma area should be at least %lu MiB\n", (PAGE_SIZE << order) / SZ_1M); + hugetlb_cma_size = 0; return; } @@ -6563,7 +6587,13 @@ void __init hugetlb_cma_reserve(int order) size = round_up(size, PAGE_SIZE << order); snprintf(name, sizeof(name), "hugetlb%d", nid); - res = cma_declare_contiguous_nid(0, size, 0, PAGE_SIZE << order, + /* + * Note that 'order per bit' is based on smallest size that + * may be returned to CMA allocator in the case of + * huge page demotion. + */ + res = cma_declare_contiguous_nid(0, size, 0, + PAGE_SIZE << HUGETLB_PAGE_ORDER, 0, false, name, &hugetlb_cma[nid], nid); if (res) { @@ -6579,6 +6609,13 @@ void __init hugetlb_cma_reserve(int order) if (reserved >= hugetlb_cma_size) break; } + + if (!reserved) + /* + * hugetlb_cma_size is used to determine if allocations from + * cma are possible. Set to zero if no cma regions are set up. + */ + hugetlb_cma_size = 0; } void __init hugetlb_cma_check(void) From 34d9e35b13d5607d6d5105b263adaaba90bdafeb Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Fri, 5 Nov 2021 13:41:30 -0700 Subject: [PATCH 035/166] hugetlb: add demote bool to gigantic page routines The routines remove_hugetlb_page and destroy_compound_gigantic_page will remove a gigantic page and make the set of base pages ready to be returned to a lower level allocator. In the process of doing this, they make all base pages reference counted. The routine prep_compound_gigantic_page creates a gigantic page from a set of base pages. It assumes that all these base pages are reference counted. During demotion, a gigantic page will be split into huge pages of a smaller size. This logically involves use of the routines, remove_hugetlb_page, and destroy_compound_gigantic_page followed by prep_compound*_page for each smaller huge page. When pages are reference counted (ref count >= 0), additional speculative ref counts could be taken as described in previous commits [1] and [2]. This could result in errors while demoting a huge page. Quite a bit of code would need to be created to handle all possible issues. Instead of dealing with the possibility of speculative ref counts, avoid the possibility by keeping ref counts at zero during the demote process. Add a boolean 'demote' to the routines remove_hugetlb_page, destroy_compound_gigantic_page and prep_compound_gigantic_page. If the boolean is set, the remove and destroy routines will not reference count pages and the prep routine will not expect reference counted pages. '*_for_demote' wrappers of the routines will be added in a subsequent patch where this functionality is used. [1] https://lore.kernel.org/linux-mm/20210622021423.154662-3-mike.kravetz@oracle.com/ [2] https://lore.kernel.org/linux-mm/20210809184832.18342-3-mike.kravetz@oracle.com/ Link: https://lkml.kernel.org/r/20211007181918.136982-5-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Reviewed-by: Oscar Salvador Cc: "Aneesh Kumar K . V" Cc: David Hildenbrand Cc: David Rientjes Cc: Michal Hocko Cc: Muchun Song Cc: Naoya Horiguchi Cc: Nghia Le Cc: Zi Yan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 54 +++++++++++++++++++++++++++++++++++++++++----------- 1 file changed, 43 insertions(+), 11 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 6662a99e6dab..c00dd2d1e5f4 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1271,8 +1271,8 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) nr_nodes--) #ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE -static void destroy_compound_gigantic_page(struct page *page, - unsigned int order) +static void __destroy_compound_gigantic_page(struct page *page, + unsigned int order, bool demote) { int i; int nr_pages = 1 << order; @@ -1284,7 +1284,8 @@ static void destroy_compound_gigantic_page(struct page *page, for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) { p->mapping = NULL; clear_compound_head(p); - set_page_refcounted(p); + if (!demote) + set_page_refcounted(p); } set_compound_order(page, 0); @@ -1292,6 +1293,12 @@ static void destroy_compound_gigantic_page(struct page *page, __ClearPageHead(page); } +static void destroy_compound_gigantic_page(struct page *page, + unsigned int order) +{ + __destroy_compound_gigantic_page(page, order, false); +} + static void free_gigantic_page(struct page *page, unsigned int order) { /* @@ -1364,12 +1371,15 @@ static inline void destroy_compound_gigantic_page(struct page *page, /* * Remove hugetlb page from lists, and update dtor so that page appears - * as just a compound page. A reference is held on the page. + * as just a compound page. + * + * A reference is held on the page, except in the case of demote. * * Must be called with hugetlb lock held. */ -static void remove_hugetlb_page(struct hstate *h, struct page *page, - bool adjust_surplus) +static void __remove_hugetlb_page(struct hstate *h, struct page *page, + bool adjust_surplus, + bool demote) { int nid = page_to_nid(page); @@ -1407,8 +1417,12 @@ static void remove_hugetlb_page(struct hstate *h, struct page *page, * * This handles the case where more than one ref is held when and * after update_and_free_page is called. + * + * In the case of demote we do not ref count the page as it will soon + * be turned into a page of smaller size. */ - set_page_refcounted(page); + if (!demote) + set_page_refcounted(page); if (hstate_is_gigantic(h)) set_compound_page_dtor(page, NULL_COMPOUND_DTOR); else @@ -1418,6 +1432,12 @@ static void remove_hugetlb_page(struct hstate *h, struct page *page, h->nr_huge_pages_node[nid]--; } +static void remove_hugetlb_page(struct hstate *h, struct page *page, + bool adjust_surplus) +{ + __remove_hugetlb_page(h, page, adjust_surplus, false); +} + static void add_hugetlb_page(struct hstate *h, struct page *page, bool adjust_surplus) { @@ -1681,7 +1701,8 @@ static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) spin_unlock_irq(&hugetlb_lock); } -static bool prep_compound_gigantic_page(struct page *page, unsigned int order) +static bool __prep_compound_gigantic_page(struct page *page, unsigned int order, + bool demote) { int i, j; int nr_pages = 1 << order; @@ -1719,10 +1740,16 @@ static bool prep_compound_gigantic_page(struct page *page, unsigned int order) * the set of pages can not be converted to a gigantic page. * The caller who allocated the pages should then discard the * pages using the appropriate free interface. + * + * In the case of demote, the ref count will be zero. */ - if (!page_ref_freeze(p, 1)) { - pr_warn("HugeTLB page can not be used due to unexpected inflated ref count\n"); - goto out_error; + if (!demote) { + if (!page_ref_freeze(p, 1)) { + pr_warn("HugeTLB page can not be used due to unexpected inflated ref count\n"); + goto out_error; + } + } else { + VM_BUG_ON_PAGE(page_count(p), p); } set_page_count(p, 0); set_compound_head(p, page); @@ -1747,6 +1774,11 @@ out_error: return false; } +static bool prep_compound_gigantic_page(struct page *page, unsigned int order) +{ + return __prep_compound_gigantic_page(page, order, false); +} + /* * PageHuge() only returns true for hugetlbfs pages, but not for normal or * transparent huge pages. See the PageTransHuge() documentation for more From 8531fc6f52f5fc201f43d8c36c2606e25748b1c4 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Fri, 5 Nov 2021 13:41:33 -0700 Subject: [PATCH 036/166] hugetlb: add hugetlb demote page support Demote page functionality will split a huge page into a number of huge pages of a smaller size. For example, on x86 a 1GB huge page can be demoted into 512 2M huge pages. Demotion is done 'in place' by simply splitting the huge page. Added '*_for_demote' wrappers for remove_hugetlb_page, destroy_compound_hugetlb_page and prep_compound_gigantic_page for use by demote code. [mike.kravetz@oracle.com: v4] Link: https://lkml.kernel.org/r/6ca29b8e-527c-d6ec-900e-e6a43e4f8b73@oracle.com Link: https://lkml.kernel.org/r/20211007181918.136982-6-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Reviewed-by: Oscar Salvador Cc: "Aneesh Kumar K . V" Cc: David Hildenbrand Cc: David Rientjes Cc: Michal Hocko Cc: Muchun Song Cc: Naoya Horiguchi Cc: Nghia Le Cc: Zi Yan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 100 ++++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 92 insertions(+), 8 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index c00dd2d1e5f4..1835d548fecc 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1270,7 +1270,7 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) ((node = hstate_next_node_to_free(hs, mask)) || 1); \ nr_nodes--) -#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE +/* used to demote non-gigantic_huge pages as well */ static void __destroy_compound_gigantic_page(struct page *page, unsigned int order, bool demote) { @@ -1293,6 +1293,13 @@ static void __destroy_compound_gigantic_page(struct page *page, __ClearPageHead(page); } +static void destroy_compound_hugetlb_page_for_demote(struct page *page, + unsigned int order) +{ + __destroy_compound_gigantic_page(page, order, true); +} + +#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE static void destroy_compound_gigantic_page(struct page *page, unsigned int order) { @@ -1438,6 +1445,12 @@ static void remove_hugetlb_page(struct hstate *h, struct page *page, __remove_hugetlb_page(h, page, adjust_surplus, false); } +static void remove_hugetlb_page_for_demote(struct hstate *h, struct page *page, + bool adjust_surplus) +{ + __remove_hugetlb_page(h, page, adjust_surplus, true); +} + static void add_hugetlb_page(struct hstate *h, struct page *page, bool adjust_surplus) { @@ -1779,6 +1792,12 @@ static bool prep_compound_gigantic_page(struct page *page, unsigned int order) return __prep_compound_gigantic_page(page, order, false); } +static bool prep_compound_gigantic_page_for_demote(struct page *page, + unsigned int order) +{ + return __prep_compound_gigantic_page(page, order, true); +} + /* * PageHuge() only returns true for hugetlbfs pages, but not for normal or * transparent huge pages. See the PageTransHuge() documentation for more @@ -3304,9 +3323,72 @@ out: return 0; } +static int demote_free_huge_page(struct hstate *h, struct page *page) +{ + int i, nid = page_to_nid(page); + struct hstate *target_hstate; + int rc = 0; + + target_hstate = size_to_hstate(PAGE_SIZE << h->demote_order); + + remove_hugetlb_page_for_demote(h, page, false); + spin_unlock_irq(&hugetlb_lock); + + rc = alloc_huge_page_vmemmap(h, page); + if (rc) { + /* Allocation of vmemmmap failed, we can not demote page */ + spin_lock_irq(&hugetlb_lock); + set_page_refcounted(page); + add_hugetlb_page(h, page, false); + return rc; + } + + /* + * Use destroy_compound_hugetlb_page_for_demote for all huge page + * sizes as it will not ref count pages. + */ + destroy_compound_hugetlb_page_for_demote(page, huge_page_order(h)); + + /* + * Taking target hstate mutex synchronizes with set_max_huge_pages. + * Without the mutex, pages added to target hstate could be marked + * as surplus. + * + * Note that we already hold h->resize_lock. To prevent deadlock, + * use the convention of always taking larger size hstate mutex first. + */ + mutex_lock(&target_hstate->resize_lock); + for (i = 0; i < pages_per_huge_page(h); + i += pages_per_huge_page(target_hstate)) { + if (hstate_is_gigantic(target_hstate)) + prep_compound_gigantic_page_for_demote(page + i, + target_hstate->order); + else + prep_compound_page(page + i, target_hstate->order); + set_page_private(page + i, 0); + set_page_refcounted(page + i); + prep_new_huge_page(target_hstate, page + i, nid); + put_page(page + i); + } + mutex_unlock(&target_hstate->resize_lock); + + spin_lock_irq(&hugetlb_lock); + + /* + * Not absolutely necessary, but for consistency update max_huge_pages + * based on pool changes for the demoted page. + */ + h->max_huge_pages--; + target_hstate->max_huge_pages += pages_per_huge_page(h); + + return rc; +} + static int demote_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed) __must_hold(&hugetlb_lock) { + int nr_nodes, node; + struct page *page; int rc = 0; lockdep_assert_held(&hugetlb_lock); @@ -3317,9 +3399,15 @@ static int demote_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed) return -EINVAL; /* internal error */ } - /* - * TODO - demote fucntionality will be added in subsequent patch - */ + for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { + if (!list_empty(&h->hugepage_freelists[node])) { + page = list_entry(h->hugepage_freelists[node].next, + struct page, lru); + rc = demote_free_huge_page(h, page); + break; + } + } + return rc; } @@ -3554,10 +3642,6 @@ static ssize_t demote_store(struct kobject *kobj, /* * Check for available pages to demote each time thorough the * loop as demote_pool_huge_page will drop hugetlb_lock. - * - * NOTE: demote_pool_huge_page does not yet drop hugetlb_lock - * but will when full demote functionality is added in a later - * patch. */ if (nid != NUMA_NO_NODE) nr_available = h->free_huge_pages_node[nid]; From bd3400ea173fb611cdf2030d03620185ff6c0b0e Mon Sep 17 00:00:00 2001 From: Liangcai Fan Date: Fri, 5 Nov 2021 13:41:36 -0700 Subject: [PATCH 037/166] mm: khugepaged: recalculate min_free_kbytes after stopping khugepaged When initializing transparent huge pages, min_free_kbytes would be calculated according to what khugepaged expected. So when transparent huge pages get disabled, min_free_kbytes should be recalculated instead of the higher value set by khugepaged. Link: https://lkml.kernel.org/r/1633937809-16558-1-git-send-email-liangcaifan19@gmail.com Signed-off-by: Liangcai Fan Signed-off-by: Chunyan Zhang Cc: Mike Kravetz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + mm/khugepaged.c | 10 ++++++++-- mm/page_alloc.c | 7 ++++++- 3 files changed, 15 insertions(+), 3 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 6e29deb1e0d4..7e37c726b9db 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2453,6 +2453,7 @@ extern void memmap_init_range(unsigned long, int, unsigned long, unsigned long, unsigned long, enum meminit_context, struct vmem_altmap *, int migratetype); extern void setup_per_zone_wmarks(void); +extern void calculate_min_free_kbytes(void); extern int __meminit init_per_zone_wmark_min(void); extern void mem_init(void); extern void __init mmap_init(void); diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 8a8b3aa92937..629961966854 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -2299,6 +2299,11 @@ static void set_recommended_min_free_kbytes(void) int nr_zones = 0; unsigned long recommended_min; + if (!khugepaged_enabled()) { + calculate_min_free_kbytes(); + goto update_wmarks; + } + for_each_populated_zone(zone) { /* * We don't need to worry about fragmentation of @@ -2334,6 +2339,8 @@ static void set_recommended_min_free_kbytes(void) min_free_kbytes = recommended_min; } + +update_wmarks: setup_per_zone_wmarks(); } @@ -2355,12 +2362,11 @@ int start_stop_khugepaged(void) if (!list_empty(&khugepaged_scan.mm_head)) wake_up_interruptible(&khugepaged_wait); - - set_recommended_min_free_kbytes(); } else if (khugepaged_thread) { kthread_stop(khugepaged_thread); khugepaged_thread = NULL; } + set_recommended_min_free_kbytes(); fail: mutex_unlock(&khugepaged_mutex); return err; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index a7035467bf6d..09a0f1c5d5d2 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -8469,7 +8469,7 @@ void setup_per_zone_wmarks(void) * 8192MB: 11584k * 16384MB: 16384k */ -int __meminit init_per_zone_wmark_min(void) +void calculate_min_free_kbytes(void) { unsigned long lowmem_kbytes; int new_min_free_kbytes; @@ -8483,6 +8483,11 @@ int __meminit init_per_zone_wmark_min(void) pr_warn("min_free_kbytes is not updated to %d because user defined value %d is preferred\n", new_min_free_kbytes, user_min_free_kbytes); +} + +int __meminit init_per_zone_wmark_min(void) +{ + calculate_min_free_kbytes(); setup_per_zone_wmarks(); refresh_zone_stat_thresholds(); setup_per_zone_lowmem_reserve(); From 550a7d60bd5e35a56942dba6d8a26752beb26c9f Mon Sep 17 00:00:00 2001 From: Mina Almasry Date: Fri, 5 Nov 2021 13:41:40 -0700 Subject: [PATCH 038/166] mm, hugepages: add mremap() support for hugepage backed vma Support mremap() for hugepage backed vma segment by simply repositioning page table entries. The page table entries are repositioned to the new virtual address on mremap(). Hugetlb mremap() support is of course generic; my motivating use case is a library (hugepage_text), which reloads the ELF text of executables in hugepages. This significantly increases the execution performance of said executables. Restrict the mremap operation on hugepages to up to the size of the original mapping as the underlying hugetlb reservation is not yet capable of handling remapping to a larger size. During the mremap() operation we detect pmd_share'd mappings and we unshare those during the mremap(). On access and fault the sharing is established again. Link: https://lkml.kernel.org/r/20211013195825.3058275-1-almasrymina@google.com Signed-off-by: Mina Almasry Reviewed-by: Mike Kravetz Cc: Ken Chen Cc: Chris Kennelly Cc: Michal Hocko Cc: Vlastimil Babka Cc: Kirill Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 19 +++++++ mm/hugetlb.c | 111 +++++++++++++++++++++++++++++++++++++--- mm/mremap.c | 36 +++++++++++-- 3 files changed, 157 insertions(+), 9 deletions(-) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 2bddd6c38204..c0a20781b28e 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -124,6 +124,7 @@ struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, void hugepage_put_subpool(struct hugepage_subpool *spool); void reset_vma_resv_huge_pages(struct vm_area_struct *vma); +void clear_vma_resv_huge_pages(struct vm_area_struct *vma); int hugetlb_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int hugetlb_overcommit_handler(struct ctl_table *, int, void *, size_t *, loff_t *); @@ -132,6 +133,10 @@ int hugetlb_treat_movable_handler(struct ctl_table *, int, void *, size_t *, int hugetlb_mempolicy_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); +int move_hugetlb_page_tables(struct vm_area_struct *vma, + struct vm_area_struct *new_vma, + unsigned long old_addr, unsigned long new_addr, + unsigned long len); int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *); long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, @@ -215,6 +220,10 @@ static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma) { } +static inline void clear_vma_resv_huge_pages(struct vm_area_struct *vma) +{ +} + static inline unsigned long hugetlb_total_pages(void) { return 0; @@ -262,6 +271,16 @@ static inline int copy_hugetlb_page_range(struct mm_struct *dst, return 0; } +static inline int move_hugetlb_page_tables(struct vm_area_struct *vma, + struct vm_area_struct *new_vma, + unsigned long old_addr, + unsigned long new_addr, + unsigned long len) +{ + BUG(); + return 0; +} + static inline void hugetlb_report_meminfo(struct seq_file *m) { } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 1835d548fecc..8028fb7677eb 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1014,6 +1014,35 @@ void reset_vma_resv_huge_pages(struct vm_area_struct *vma) vma->vm_private_data = (void *)0; } +/* + * Reset and decrement one ref on hugepage private reservation. + * Called with mm->mmap_sem writer semaphore held. + * This function should be only used by move_vma() and operate on + * same sized vma. It should never come here with last ref on the + * reservation. + */ +void clear_vma_resv_huge_pages(struct vm_area_struct *vma) +{ + /* + * Clear the old hugetlb private page reservation. + * It has already been transferred to new_vma. + * + * During a mremap() operation of a hugetlb vma we call move_vma() + * which copies vma into new_vma and unmaps vma. After the copy + * operation both new_vma and vma share a reference to the resv_map + * struct, and at that point vma is about to be unmapped. We don't + * want to return the reservation to the pool at unmap of vma because + * the reservation still lives on in new_vma, so simply decrement the + * ref here and remove the resv_map reference from this vma. + */ + struct resv_map *reservations = vma_resv_map(vma); + + if (reservations && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) + kref_put(&reservations->refs, resv_map_release); + + reset_vma_resv_huge_pages(vma); +} + /* Returns true if the VMA has associated reserve pages */ static bool vma_has_reserves(struct vm_area_struct *vma, long chg) { @@ -4718,6 +4747,82 @@ again: return ret; } +static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr, + unsigned long new_addr, pte_t *src_pte) +{ + struct hstate *h = hstate_vma(vma); + struct mm_struct *mm = vma->vm_mm; + pte_t *dst_pte, pte; + spinlock_t *src_ptl, *dst_ptl; + + dst_pte = huge_pte_offset(mm, new_addr, huge_page_size(h)); + dst_ptl = huge_pte_lock(h, mm, dst_pte); + src_ptl = huge_pte_lockptr(h, mm, src_pte); + + /* + * We don't have to worry about the ordering of src and dst ptlocks + * because exclusive mmap_sem (or the i_mmap_lock) prevents deadlock. + */ + if (src_ptl != dst_ptl) + spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); + + pte = huge_ptep_get_and_clear(mm, old_addr, src_pte); + set_huge_pte_at(mm, new_addr, dst_pte, pte); + + if (src_ptl != dst_ptl) + spin_unlock(src_ptl); + spin_unlock(dst_ptl); +} + +int move_hugetlb_page_tables(struct vm_area_struct *vma, + struct vm_area_struct *new_vma, + unsigned long old_addr, unsigned long new_addr, + unsigned long len) +{ + struct hstate *h = hstate_vma(vma); + struct address_space *mapping = vma->vm_file->f_mapping; + unsigned long sz = huge_page_size(h); + struct mm_struct *mm = vma->vm_mm; + unsigned long old_end = old_addr + len; + unsigned long old_addr_copy; + pte_t *src_pte, *dst_pte; + struct mmu_notifier_range range; + + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, old_addr, + old_end); + adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); + mmu_notifier_invalidate_range_start(&range); + /* Prevent race with file truncation */ + i_mmap_lock_write(mapping); + for (; old_addr < old_end; old_addr += sz, new_addr += sz) { + src_pte = huge_pte_offset(mm, old_addr, sz); + if (!src_pte) + continue; + if (huge_pte_none(huge_ptep_get(src_pte))) + continue; + + /* old_addr arg to huge_pmd_unshare() is a pointer and so the + * arg may be modified. Pass a copy instead to preserve the + * value in old_addr. + */ + old_addr_copy = old_addr; + + if (huge_pmd_unshare(mm, vma, &old_addr_copy, src_pte)) + continue; + + dst_pte = huge_pte_alloc(mm, new_vma, new_addr, sz); + if (!dst_pte) + break; + + move_huge_pte(vma, old_addr, new_addr, src_pte); + } + i_mmap_unlock_write(mapping); + flush_tlb_range(vma, old_end - len, old_end); + mmu_notifier_invalidate_range_end(&range); + + return len + old_addr - old_end; +} + static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page) @@ -6257,12 +6362,6 @@ void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, * sharing is possible. For hugetlbfs, this prevents removal of any page * table entries associated with the address space. This is important as we * are setting up sharing based on existing page table entries (mappings). - * - * NOTE: This routine is only called from huge_pte_alloc. Some callers of - * huge_pte_alloc know that sharing is not possible and do not take - * i_mmap_rwsem as a performance optimization. This is handled by the - * if !vma_shareable check at the beginning of the routine. i_mmap_rwsem is - * only required for subsequent processing. */ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pud_t *pud) diff --git a/mm/mremap.c b/mm/mremap.c index c0b6c41b7b78..002eec83e91e 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -489,6 +489,10 @@ unsigned long move_page_tables(struct vm_area_struct *vma, old_end = old_addr + len; flush_cache_range(vma, old_addr, old_end); + if (is_vm_hugetlb_page(vma)) + return move_hugetlb_page_tables(vma, new_vma, old_addr, + new_addr, len); + mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm, old_addr, old_end); mmu_notifier_invalidate_range_start(&range); @@ -646,6 +650,10 @@ static unsigned long move_vma(struct vm_area_struct *vma, mremap_userfaultfd_prep(new_vma, uf); } + if (is_vm_hugetlb_page(vma)) { + clear_vma_resv_huge_pages(vma); + } + /* Conceal VM_ACCOUNT so old reservation is not undone */ if (vm_flags & VM_ACCOUNT && !(flags & MREMAP_DONTUNMAP)) { vma->vm_flags &= ~VM_ACCOUNT; @@ -739,9 +747,6 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr, (vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP))) return ERR_PTR(-EINVAL); - if (is_vm_hugetlb_page(vma)) - return ERR_PTR(-EINVAL); - /* We can't remap across vm area boundaries */ if (old_len > vma->vm_end - addr) return ERR_PTR(-EFAULT); @@ -937,6 +942,31 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, if (mmap_write_lock_killable(current->mm)) return -EINTR; + vma = find_vma(mm, addr); + if (!vma || vma->vm_start > addr) { + ret = EFAULT; + goto out; + } + + if (is_vm_hugetlb_page(vma)) { + struct hstate *h __maybe_unused = hstate_vma(vma); + + old_len = ALIGN(old_len, huge_page_size(h)); + new_len = ALIGN(new_len, huge_page_size(h)); + + /* addrs must be huge page aligned */ + if (addr & ~huge_page_mask(h)) + goto out; + if (new_addr & ~huge_page_mask(h)) + goto out; + + /* + * Don't allow remap expansion, because the underlying hugetlb + * reservation is not yet capable to handle split reservation. + */ + if (new_len > old_len) + goto out; + } if (flags & (MREMAP_FIXED | MREMAP_DONTUNMAP)) { ret = mremap_to(addr, old_len, new_addr, new_len, From 12b613206474cea36671d6e3a7be7d1db7eb8741 Mon Sep 17 00:00:00 2001 From: Mina Almasry Date: Fri, 5 Nov 2021 13:41:43 -0700 Subject: [PATCH 039/166] mm, hugepages: add hugetlb vma mremap() test [almasrymina@google.com: v8] Link: https://lkml.kernel.org/r/20211014200542.4126947-2-almasrymina@google.com [wanjiabing@vivo.com: remove duplicated include in hugepage-mremap] Link: https://lkml.kernel.org/r/20211021122944.8857-1-wanjiabing@vivo.com Link: https://lkml.kernel.org/r/20211013195825.3058275-2-almasrymina@google.com Signed-off-by: Mina Almasry Signed-off-by: Wan Jiabing Acked-by: Mike Kravetz Cc: Ken Chen Cc: Chris Kennelly Cc: Michal Hocko Cc: Vlastimil Babka Cc: Kirill Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/testing/selftests/vm/.gitignore | 1 + tools/testing/selftests/vm/Makefile | 1 + tools/testing/selftests/vm/hugepage-mremap.c | 160 +++++++++++++++++++ tools/testing/selftests/vm/run_vmtests.sh | 11 ++ 4 files changed, 173 insertions(+) create mode 100644 tools/testing/selftests/vm/hugepage-mremap.c diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore index b02eac613fdd..2e7e86e85282 100644 --- a/tools/testing/selftests/vm/.gitignore +++ b/tools/testing/selftests/vm/.gitignore @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only hugepage-mmap +hugepage-mremap hugepage-shm khugepaged map_hugetlb diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index d9605bd10f2d..1607322a112c 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -29,6 +29,7 @@ TEST_GEN_FILES = compaction_test TEST_GEN_FILES += gup_test TEST_GEN_FILES += hmm-tests TEST_GEN_FILES += hugepage-mmap +TEST_GEN_FILES += hugepage-mremap TEST_GEN_FILES += hugepage-shm TEST_GEN_FILES += khugepaged TEST_GEN_FILES += madv_populate diff --git a/tools/testing/selftests/vm/hugepage-mremap.c b/tools/testing/selftests/vm/hugepage-mremap.c new file mode 100644 index 000000000000..68b8b8c4b2e6 --- /dev/null +++ b/tools/testing/selftests/vm/hugepage-mremap.c @@ -0,0 +1,160 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * hugepage-mremap: + * + * Example of remapping huge page memory in a user application using the + * mremap system call. Code assumes a hugetlbfs filesystem is mounted + * at './huge'. The code will use 10MB worth of huge pages. + */ + +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include /* Definition of O_* constants */ +#include /* Definition of SYS_* constants */ +#include +#include +#include + +#define LENGTH (1UL * 1024 * 1024 * 1024) + +#define PROTECTION (PROT_READ | PROT_WRITE | PROT_EXEC) +#define FLAGS (MAP_SHARED | MAP_ANONYMOUS) + +static void check_bytes(char *addr) +{ + printf("First hex is %x\n", *((unsigned int *)addr)); +} + +static void write_bytes(char *addr) +{ + unsigned long i; + + for (i = 0; i < LENGTH; i++) + *(addr + i) = (char)i; +} + +static int read_bytes(char *addr) +{ + unsigned long i; + + check_bytes(addr); + for (i = 0; i < LENGTH; i++) + if (*(addr + i) != (char)i) { + printf("Mismatch at %lu\n", i); + return 1; + } + return 0; +} + +static void register_region_with_uffd(char *addr, size_t len) +{ + long uffd; /* userfaultfd file descriptor */ + struct uffdio_api uffdio_api; + struct uffdio_register uffdio_register; + + /* Create and enable userfaultfd object. */ + + uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); + if (uffd == -1) { + perror("userfaultfd"); + exit(1); + } + + uffdio_api.api = UFFD_API; + uffdio_api.features = 0; + if (ioctl(uffd, UFFDIO_API, &uffdio_api) == -1) { + perror("ioctl-UFFDIO_API"); + exit(1); + } + + /* Create a private anonymous mapping. The memory will be + * demand-zero paged--that is, not yet allocated. When we + * actually touch the memory, it will be allocated via + * the userfaultfd. + */ + + addr = mmap(NULL, len, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (addr == MAP_FAILED) { + perror("mmap"); + exit(1); + } + + printf("Address returned by mmap() = %p\n", addr); + + /* Register the memory range of the mapping we just created for + * handling by the userfaultfd object. In mode, we request to track + * missing pages (i.e., pages that have not yet been faulted in). + */ + + uffdio_register.range.start = (unsigned long)addr; + uffdio_register.range.len = len; + uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; + if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) == -1) { + perror("ioctl-UFFDIO_REGISTER"); + exit(1); + } +} + +int main(void) +{ + int ret = 0; + + int fd = open("/huge/test", O_CREAT | O_RDWR, 0755); + + if (fd < 0) { + perror("Open failed"); + exit(1); + } + + /* mmap to a PUD aligned address to hopefully trigger pmd sharing. */ + unsigned long suggested_addr = 0x7eaa40000000; + void *haddr = mmap((void *)suggested_addr, LENGTH, PROTECTION, + MAP_HUGETLB | MAP_SHARED | MAP_POPULATE, fd, 0); + printf("Map haddr: Returned address is %p\n", haddr); + if (haddr == MAP_FAILED) { + perror("mmap1"); + exit(1); + } + + /* mmap again to a dummy address to hopefully trigger pmd sharing. */ + suggested_addr = 0x7daa40000000; + void *daddr = mmap((void *)suggested_addr, LENGTH, PROTECTION, + MAP_HUGETLB | MAP_SHARED | MAP_POPULATE, fd, 0); + printf("Map daddr: Returned address is %p\n", daddr); + if (daddr == MAP_FAILED) { + perror("mmap3"); + exit(1); + } + + suggested_addr = 0x7faa40000000; + void *vaddr = + mmap((void *)suggested_addr, LENGTH, PROTECTION, FLAGS, -1, 0); + printf("Map vaddr: Returned address is %p\n", vaddr); + if (vaddr == MAP_FAILED) { + perror("mmap2"); + exit(1); + } + + register_region_with_uffd(haddr, LENGTH); + + void *addr = mremap(haddr, LENGTH, LENGTH, + MREMAP_MAYMOVE | MREMAP_FIXED, vaddr); + if (addr == MAP_FAILED) { + perror("mremap"); + exit(1); + } + + printf("Mremap: Returned address is %p\n", addr); + check_bytes(addr); + write_bytes(addr); + ret = read_bytes(addr); + + munmap(addr, LENGTH); + + return ret; +} diff --git a/tools/testing/selftests/vm/run_vmtests.sh b/tools/testing/selftests/vm/run_vmtests.sh index 45e803af7c77..a24d30af3094 100755 --- a/tools/testing/selftests/vm/run_vmtests.sh +++ b/tools/testing/selftests/vm/run_vmtests.sh @@ -108,6 +108,17 @@ else echo "[PASS]" fi +echo "-----------------------" +echo "running hugepage-mremap" +echo "-----------------------" +./hugepage-mremap +if [ $? -ne 0 ]; then + echo "[FAIL]" + exitcode=1 +else + echo "[PASS]" +fi + echo "NOTE: The above hugetlb tests provide minimal coverage. Use" echo " https://github.com/libhugetlbfs/libhugetlbfs.git for" echo " hugetlb regression testing." From 38e719ab26735aa2c5d9d422fc4b741cbd36e700 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Fri, 5 Nov 2021 13:41:46 -0700 Subject: [PATCH 040/166] hugetlb: support node specified when using cma for gigantic hugepages Now the size of CMA area for gigantic hugepages runtime allocation is balanced for all online nodes, but we also want to specify the size of CMA per-node, or only one node in some cases, which are similar with patch [1]. For example, on some multi-nodes systems, each node's memory can be different, allocating the same size of CMA for each node is not suitable for the low-memory nodes. Meanwhile some workloads like DPDK mentioned by Zhenguo in patch [1] only need hugepages in one node. On the other hand, we have some machines with multiple types of memory, like DRAM and PMEM (persistent memory). On this system, we may want to specify all the hugepages only on DRAM node, or specify the proportion of DRAM node and PMEM node, to tuning the performance of the workloads. Thus this patch adds node format for 'hugetlb_cma' parameter to support specifying the size of CMA per-node. An example is as follows: hugetlb_cma=0:5G,2:5G which means allocating 5G size of CMA area on node 0 and node 2 respectively. And the users should use the node specific sysfs file to allocate the gigantic hugepages if specified the CMA size on that node. Link: https://lkml.kernel.org/r/20211005054729.86457-1-yaozhenguo1@gmail.com [1] Link: https://lkml.kernel.org/r/bb790775ca60bb8f4b26956bb3f6988f74e075c7.1634261144.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Reviewed-by: Mike Kravetz Cc: Michal Hocko Cc: Roman Gushchin Cc: Jonathan Corbet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- .../admin-guide/kernel-parameters.txt | 6 +- mm/hugetlb.c | 86 +++++++++++++++++-- 2 files changed, 81 insertions(+), 11 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 43dc35fe5bc0..e7f7904edf20 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1587,8 +1587,10 @@ registers. Default set by CONFIG_HPET_MMAP_DEFAULT. hugetlb_cma= [HW,CMA] The size of a CMA area used for allocation - of gigantic hugepages. - Format: nn[KMGTPE] + of gigantic hugepages. Or using node format, the size + of a CMA area per node can be specified. + Format: nn[KMGTPE] or (node format) + :nn[KMGTPE][,:nn[KMGTPE]] Reserve a CMA area of given size and allocate gigantic hugepages using the CMA allocator. If enabled, the diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 8028fb7677eb..b86d27870c54 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -50,6 +50,7 @@ struct hstate hstates[HUGE_MAX_HSTATE]; #ifdef CONFIG_CMA static struct cma *hugetlb_cma[MAX_NUMNODES]; +static unsigned long hugetlb_cma_size_in_node[MAX_NUMNODES] __initdata; static bool hugetlb_cma_page(struct page *page, unsigned int order) { return cma_pages_valid(hugetlb_cma[page_to_nid(page)], page, @@ -6762,7 +6763,38 @@ static bool cma_reserve_called __initdata; static int __init cmdline_parse_hugetlb_cma(char *p) { - hugetlb_cma_size = memparse(p, &p); + int nid, count = 0; + unsigned long tmp; + char *s = p; + + while (*s) { + if (sscanf(s, "%lu%n", &tmp, &count) != 1) + break; + + if (s[count] == ':') { + nid = tmp; + if (nid < 0 || nid >= MAX_NUMNODES) + break; + + s += count + 1; + tmp = memparse(s, &s); + hugetlb_cma_size_in_node[nid] = tmp; + hugetlb_cma_size += tmp; + + /* + * Skip the separator if have one, otherwise + * break the parsing. + */ + if (*s == ',') + s++; + else + break; + } else { + hugetlb_cma_size = memparse(p, &p); + break; + } + } + return 0; } @@ -6771,10 +6803,36 @@ early_param("hugetlb_cma", cmdline_parse_hugetlb_cma); void __init hugetlb_cma_reserve(int order) { unsigned long size, reserved, per_node; + bool node_specific_cma_alloc = false; int nid; cma_reserve_called = true; + if (!hugetlb_cma_size) + return; + + for (nid = 0; nid < MAX_NUMNODES; nid++) { + if (hugetlb_cma_size_in_node[nid] == 0) + continue; + + if (!node_state(nid, N_ONLINE)) { + pr_warn("hugetlb_cma: invalid node %d specified\n", nid); + hugetlb_cma_size -= hugetlb_cma_size_in_node[nid]; + hugetlb_cma_size_in_node[nid] = 0; + continue; + } + + if (hugetlb_cma_size_in_node[nid] < (PAGE_SIZE << order)) { + pr_warn("hugetlb_cma: cma area of node %d should be at least %lu MiB\n", + nid, (PAGE_SIZE << order) / SZ_1M); + hugetlb_cma_size -= hugetlb_cma_size_in_node[nid]; + hugetlb_cma_size_in_node[nid] = 0; + } else { + node_specific_cma_alloc = true; + } + } + + /* Validate the CMA size again in case some invalid nodes specified. */ if (!hugetlb_cma_size) return; @@ -6785,20 +6843,30 @@ void __init hugetlb_cma_reserve(int order) return; } - /* - * If 3 GB area is requested on a machine with 4 numa nodes, - * let's allocate 1 GB on first three nodes and ignore the last one. - */ - per_node = DIV_ROUND_UP(hugetlb_cma_size, nr_online_nodes); - pr_info("hugetlb_cma: reserve %lu MiB, up to %lu MiB per node\n", - hugetlb_cma_size / SZ_1M, per_node / SZ_1M); + if (!node_specific_cma_alloc) { + /* + * If 3 GB area is requested on a machine with 4 numa nodes, + * let's allocate 1 GB on first three nodes and ignore the last one. + */ + per_node = DIV_ROUND_UP(hugetlb_cma_size, nr_online_nodes); + pr_info("hugetlb_cma: reserve %lu MiB, up to %lu MiB per node\n", + hugetlb_cma_size / SZ_1M, per_node / SZ_1M); + } reserved = 0; for_each_node_state(nid, N_ONLINE) { int res; char name[CMA_MAX_NAME]; - size = min(per_node, hugetlb_cma_size - reserved); + if (node_specific_cma_alloc) { + if (hugetlb_cma_size_in_node[nid] == 0) + continue; + + size = hugetlb_cma_size_in_node[nid]; + } else { + size = min(per_node, hugetlb_cma_size - reserved); + } + size = round_up(size, PAGE_SIZE << order); snprintf(name, sizeof(name), "hugetlb%d", nid); From b65c23f72e77f87b31cf978fb0915d80875e26a0 Mon Sep 17 00:00:00 2001 From: Ran Jianping Date: Fri, 5 Nov 2021 13:41:49 -0700 Subject: [PATCH 041/166] mm: remove duplicate include in hugepage-mremap.c Remove duplicate includes 'unistd.h' included in '/tools/testing/selftests/vm/hugepage-mremap.c' is duplicated.It is also included on 23 line. Link: https://lkml.kernel.org/r/20211018102336.869726-1-ran.jianping@zte.com.cn Signed-off-by: Ran Jianping Reported-by: Zeal Robot Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/testing/selftests/vm/hugepage-mremap.c | 1 - 1 file changed, 1 deletion(-) diff --git a/tools/testing/selftests/vm/hugepage-mremap.c b/tools/testing/selftests/vm/hugepage-mremap.c index 68b8b8c4b2e6..257df94697a5 100644 --- a/tools/testing/selftests/vm/hugepage-mremap.c +++ b/tools/testing/selftests/vm/hugepage-mremap.c @@ -15,7 +15,6 @@ #include #include /* Definition of O_* constants */ #include /* Definition of SYS_* constants */ -#include #include #include From df8931c89d2edc143fa7f59e049696dce6b151ef Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Fri, 5 Nov 2021 13:41:52 -0700 Subject: [PATCH 042/166] hugetlb_cgroup: remove unused hugetlb_cgroup_from_counter macro Patch series "Some cleanups and improvements for hugetlb". This patchset does some cleanups and improvements for hugetlb and hugetlb_cgroup. This patch (of 4): Since commit 726b7bbeafd4 ("hugetlb_cgroup: fix illegal access to memory"), the hugetlb_cgroup_from_counter() macro is not used any more, remove it. Link: https://lkml.kernel.org/r/cover.1634797639.git.baolin.wang@linux.alibaba.com Link: https://lkml.kernel.org/r/f03b29b801fa9942466ab15334ec09988e124ae6.1634797639.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Reviewed-by: Mike Kravetz Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb_cgroup.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index 5383023d0cca..79d93534ef1e 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -27,9 +27,6 @@ #define MEMFILE_IDX(val) (((val) >> 16) & 0xffff) #define MEMFILE_ATTR(val) ((val) & 0xffff) -#define hugetlb_cgroup_from_counter(counter, idx) \ - container_of(counter, struct hugetlb_cgroup, hugepage[idx]) - static struct hugetlb_cgroup *root_h_cgroup __read_mostly; static inline struct page_counter * From aa6d2e8cba2dc6f1f3dd39f7a7cc8ac788ad6c1a Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Fri, 5 Nov 2021 13:41:55 -0700 Subject: [PATCH 043/166] hugetlb: replace the obsolete hugetlb_instantiation_mutex in the comments After commit 8382d914ebf7 ("mm, hugetlb: improve page-fault scalability"), the hugetlb_instantiation_mutex lock had been replaced by hugetlb_fault_mutex_table to serializes faults on the same logical page. Thus update the obsolete hugetlb_instantiation_mutex related comments. Link: https://lkml.kernel.org/r/4b3febeae37455ff7b74aa0aad16cc6909cf0926.1634797639.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Reviewed-by: Mike Kravetz Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index b86d27870c54..f9c1ec1180d3 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5014,7 +5014,7 @@ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, /* * Hugetlb_cow() should be called with page lock of the original hugepage held. - * Called with hugetlb_instantiation_mutex held and pte_page locked so we + * Called with hugetlb_fault_mutex_table held and pte_page locked so we * cannot race with other handlers or page migration. * Keep the pte_same checks anyway to make transition from the mutex easier. */ From 0739eb437f3d397eb39b5dc653aa250ee7b453f0 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Fri, 5 Nov 2021 13:41:58 -0700 Subject: [PATCH 044/166] hugetlb: remove redundant validation in has_same_uncharge_info() The callers of has_same_uncharge_info() has accessed the original file_region and new file_region, and they are impossible to be NULL now. So we can remove the file_region validation in has_same_uncharge_info() to simplify the code. Link: https://lkml.kernel.org/r/97fc68d3f8d34f63c204645e10d7a718997e50b7.1634797639.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Reviewed-by: Mike Kravetz Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f9c1ec1180d3..1869ca9f21f3 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -332,8 +332,7 @@ static bool has_same_uncharge_info(struct file_region *rg, struct file_region *org) { #ifdef CONFIG_CGROUP_HUGETLB - return rg && org && - rg->reservation_counter == org->reservation_counter && + return rg->reservation_counter == org->reservation_counter && rg->css == org->css; #else From 76efc67a5e7a3dc1226c4ad1b266a15741347031 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Fri, 5 Nov 2021 13:42:01 -0700 Subject: [PATCH 045/166] hugetlb: remove redundant VM_BUG_ON() in add_reservation_in_range() When calling hugetlb_resv_map_add(), we've guaranteed that the parameter 'to' is always larger than 'from', so it never returns a negative value from hugetlb_resv_map_add(). Thus remove the redundant VM_BUG_ON(). Link: https://lkml.kernel.org/r/2b565552f3d06753da1e8dda439c0d96d6d9a5a3.1634797639.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Reviewed-by: Mike Kravetz Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 1 - 1 file changed, 1 deletion(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 1869ca9f21f3..e304326dba63 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -445,7 +445,6 @@ static long add_reservation_in_range(struct resv_map *resv, long f, long t, add += hugetlb_resv_map_add(resv, rg, last_accounted_offset, t, h, h_cg, regions_needed); - VM_BUG_ON(add < 0); return add; } From 2c0078a7d820e55ce6a176721a94f3c585833436 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Fri, 5 Nov 2021 13:42:04 -0700 Subject: [PATCH 046/166] hugetlb: remove unnecessary set_page_count in prep_compound_gigantic_page In commit 7118fc2906e2 ("hugetlb: address ref count racing in prep_compound_gigantic_page"), page_ref_freeze is used to atomically zero the ref count of tail pages iff they are 1. The unconditional call to set_page_count(0) was left in the code. This call is after page_ref_freeze so it is really a noop. Remove redundant and unnecessary set_page_count call. Link: https://lkml.kernel.org/r/20211026220635.35187-1-mike.kravetz@oracle.com Fixes: 7118fc2906e29 ("hugetlb: address ref count racing in prep_compound_gigantic_page") Signed-off-by: Mike Kravetz Suggested-by: Pasha Tatashin Reviewed-by: Pasha Tatashin Reviewed-by: Matthew Wilcox (Oracle) Reviewed-by: Oscar Salvador Reviewed-by: Muchun Song Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 1 - 1 file changed, 1 deletion(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index e304326dba63..5eab627a170b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1792,7 +1792,6 @@ static bool __prep_compound_gigantic_page(struct page *page, unsigned int order, } else { VM_BUG_ON_PAGE(page_count(p), p); } - set_page_count(p, 0); set_compound_head(p, page); } atomic_set(compound_mapcount_ptr(page), -1); From 1c10e674b35e2c2566b621ceca74064817c249f0 Mon Sep 17 00:00:00 2001 From: Axel Rasmussen Date: Fri, 5 Nov 2021 13:42:07 -0700 Subject: [PATCH 047/166] userfaultfd/selftests: don't rely on GNU extensions for random numbers Patch series "Small userfaultfd selftest fixups", v2. This patch (of 3): Two arguments for doing this: First, and maybe most importantly, the resulting code is significantly shorter / simpler. Then, we avoid using GNU libc extensions. Why does this matter? It makes testing userfaultfd with the selftest easier e.g. on distros which use something other than glibc (e.g., Alpine, which uses musl); basically, it makes the test more portable. Link: https://lkml.kernel.org/r/20210930212309.4001967-2-axelrasmussen@google.com Signed-off-by: Axel Rasmussen Reviewed-by: Peter Xu Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/testing/selftests/vm/userfaultfd.c | 26 ++++-------------------- 1 file changed, 4 insertions(+), 22 deletions(-) diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index 60aa1a4fc69b..d2acab4411cf 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -57,6 +57,7 @@ #include #include #include +#include #include "../kselftest.h" @@ -518,22 +519,10 @@ static void continue_range(int ufd, __u64 start, __u64 len) static void *locking_thread(void *arg) { unsigned long cpu = (unsigned long) arg; - struct random_data rand; unsigned long page_nr = *(&(page_nr)); /* uninitialized warning */ - int32_t rand_nr; unsigned long long count; - char randstate[64]; - unsigned int seed; - if (bounces & BOUNCE_RANDOM) { - seed = (unsigned int) time(NULL) - bounces; - if (!(bounces & BOUNCE_RACINGFAULTS)) - seed += cpu; - bzero(&rand, sizeof(rand)); - bzero(&randstate, sizeof(randstate)); - if (initstate_r(seed, randstate, sizeof(randstate), &rand)) - err("initstate_r failed"); - } else { + if (!(bounces & BOUNCE_RANDOM)) { page_nr = -bounces; if (!(bounces & BOUNCE_RACINGFAULTS)) page_nr += cpu * nr_pages_per_cpu; @@ -541,15 +530,8 @@ static void *locking_thread(void *arg) while (!finished) { if (bounces & BOUNCE_RANDOM) { - if (random_r(&rand, &rand_nr)) - err("random_r failed"); - page_nr = rand_nr; - if (sizeof(page_nr) > sizeof(rand_nr)) { - if (random_r(&rand, &rand_nr)) - err("random_r failed"); - page_nr |= (((unsigned long) rand_nr) << 16) << - 16; - } + if (getrandom(&page_nr, sizeof(page_nr), 0) != sizeof(page_nr)) + err("getrandom failed"); } else page_nr += 1; page_nr %= nr_pages; From 1042a53d0ec3fb617bcff395ce24b0df90d5a99b Mon Sep 17 00:00:00 2001 From: Axel Rasmussen Date: Fri, 5 Nov 2021 13:42:10 -0700 Subject: [PATCH 048/166] userfaultfd/selftests: fix feature support detection Before any tests are run, in set_test_type, we decide what feature(s) we are going to be testing, based upon our command line arguments. However, the supported features are not just a function of the memory type being used, so this is broken. For instance, consider writeprotect support. It is "normally" supported for anonymous memory, but furthermore it requires that the kernel has CONFIG_HAVE_ARCH_USERFAULTFD_WP. So, it is *not* supported at all on aarch64, for example. So, this fixes this by querying the kernel for the set of features it supports in set_test_type, by opening a userfaultfd and issuing a UFFDIO_API ioctl. Based upon the reported features, we toggle what tests are enabled. Link: https://lkml.kernel.org/r/20210930212309.4001967-3-axelrasmussen@google.com Signed-off-by: Axel Rasmussen Reviewed-by: Peter Xu Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/testing/selftests/vm/userfaultfd.c | 54 ++++++++++++++---------- 1 file changed, 31 insertions(+), 23 deletions(-) diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index d2acab4411cf..4efdaff2b563 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -346,6 +346,16 @@ static struct uffd_test_ops hugetlb_uffd_test_ops = { static struct uffd_test_ops *uffd_test_ops; +static inline uint64_t uffd_minor_feature(void) +{ + if (test_type == TEST_HUGETLB && map_shared) + return UFFD_FEATURE_MINOR_HUGETLBFS; + else if (test_type == TEST_SHMEM) + return UFFD_FEATURE_MINOR_SHMEM; + else + return 0; +} + static void userfaultfd_open(uint64_t *features) { struct uffdio_api uffdio_api; @@ -406,7 +416,7 @@ static void uffd_test_ctx_clear(void) munmap_area((void **)&area_dst_alias); } -static void uffd_test_ctx_init_ext(uint64_t *features) +static void uffd_test_ctx_init(uint64_t features) { unsigned long nr, cpu; @@ -415,7 +425,7 @@ static void uffd_test_ctx_init_ext(uint64_t *features) uffd_test_ops->allocate_area((void **)&area_src); uffd_test_ops->allocate_area((void **)&area_dst); - userfaultfd_open(features); + userfaultfd_open(&features); count_verify = malloc(nr_pages * sizeof(unsigned long long)); if (!count_verify) @@ -463,11 +473,6 @@ static void uffd_test_ctx_init_ext(uint64_t *features) err("pipe"); } -static inline void uffd_test_ctx_init(uint64_t features) -{ - uffd_test_ctx_init_ext(&features); -} - static int my_bcmp(char *str1, char *str2, size_t n) { unsigned long i; @@ -1208,7 +1213,6 @@ static int userfaultfd_minor_test(void) void *expected_page; char c; struct uffd_stats stats = { 0 }; - uint64_t req_features, features_out; if (!test_uffdio_minor) return 0; @@ -1216,21 +1220,7 @@ static int userfaultfd_minor_test(void) printf("testing minor faults: "); fflush(stdout); - if (test_type == TEST_HUGETLB) - req_features = UFFD_FEATURE_MINOR_HUGETLBFS; - else if (test_type == TEST_SHMEM) - req_features = UFFD_FEATURE_MINOR_SHMEM; - else - return 1; - - features_out = req_features; - uffd_test_ctx_init_ext(&features_out); - /* If kernel reports required features aren't supported, skip test. */ - if ((features_out & req_features) != req_features) { - printf("skipping test due to lack of feature support\n"); - fflush(stdout); - return 0; - } + uffd_test_ctx_init(uffd_minor_feature()); uffdio_register.range.start = (unsigned long)area_dst_alias; uffdio_register.range.len = nr_pages * page_size; @@ -1591,6 +1581,8 @@ unsigned long default_huge_page_size(void) static void set_test_type(const char *type) { + uint64_t features = UFFD_API_FEATURES; + if (!strcmp(type, "anon")) { test_type = TEST_ANON; uffd_test_ops = &anon_uffd_test_ops; @@ -1624,6 +1616,22 @@ static void set_test_type(const char *type) if ((unsigned long) area_count(NULL, 0) + sizeof(unsigned long long) * 2 > page_size) err("Impossible to run this test"); + + /* + * Whether we can test certain features depends not just on test type, + * but also on whether or not this particular kernel supports the + * feature. + */ + + userfaultfd_open(&features); + + test_uffdio_wp = test_uffdio_wp && + (features & UFFD_FEATURE_PAGEFAULT_FLAG_WP); + test_uffdio_minor = test_uffdio_minor && + (features & uffd_minor_feature()); + + close(uffd); + uffd = -1; } static void sigalrm(int sig) From ad0ce23ed099492d7ed1f87cd8cf39a68b9f20a0 Mon Sep 17 00:00:00 2001 From: Axel Rasmussen Date: Fri, 5 Nov 2021 13:42:13 -0700 Subject: [PATCH 049/166] userfaultfd/selftests: fix calculation of expected ioctls Today, we assert that the ioctls the kernel reports as supported for a registration match a precomputed list. We decide which ioctls are supported by examining the memory type. Then, in several locations we "fix up" this list by adding or removing things this initial decision got wrong. What ioctls the kernel reports is actually a function of several things: - The memory type - Kernel feature support (e.g., no writeprotect on aarch64) - The registration type (e.g., CONTINUE only supported for MINOR mode) So, we can't fully compute this at the start, in set_test_type. It varies per test, depending on what registration mode(s) those tests use. Instead, introduce a new function which computes the correct list. This centralizes the add/remove of ioctls depending on these function inputs in one place, so we don't have to repeat ourselves in various tests. Not only is the resulting code a bit shorter, but it fixes a real bug in the existing code: previously, we would incorrectly require the writeprotect ioctl to be present on aarch64, where it isn't actually supported. Link: https://lkml.kernel.org/r/20210930212309.4001967-4-axelrasmussen@google.com Signed-off-by: Axel Rasmussen Reviewed-by: Peter Xu Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/testing/selftests/vm/userfaultfd.c | 77 ++++++++++++------------ 1 file changed, 38 insertions(+), 39 deletions(-) diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index 4efdaff2b563..8a09057d2f22 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -308,37 +308,24 @@ static void shmem_alias_mapping(__u64 *start, size_t len, unsigned long offset) } struct uffd_test_ops { - unsigned long expected_ioctls; void (*allocate_area)(void **alloc_area); void (*release_pages)(char *rel_area); void (*alias_mapping)(__u64 *start, size_t len, unsigned long offset); }; -#define SHMEM_EXPECTED_IOCTLS ((1 << _UFFDIO_WAKE) | \ - (1 << _UFFDIO_COPY) | \ - (1 << _UFFDIO_ZEROPAGE)) - -#define ANON_EXPECTED_IOCTLS ((1 << _UFFDIO_WAKE) | \ - (1 << _UFFDIO_COPY) | \ - (1 << _UFFDIO_ZEROPAGE) | \ - (1 << _UFFDIO_WRITEPROTECT)) - static struct uffd_test_ops anon_uffd_test_ops = { - .expected_ioctls = ANON_EXPECTED_IOCTLS, .allocate_area = anon_allocate_area, .release_pages = anon_release_pages, .alias_mapping = noop_alias_mapping, }; static struct uffd_test_ops shmem_uffd_test_ops = { - .expected_ioctls = SHMEM_EXPECTED_IOCTLS, .allocate_area = shmem_allocate_area, .release_pages = shmem_release_pages, .alias_mapping = shmem_alias_mapping, }; static struct uffd_test_ops hugetlb_uffd_test_ops = { - .expected_ioctls = UFFD_API_RANGE_IOCTLS_BASIC & ~(1 << _UFFDIO_CONTINUE), .allocate_area = hugetlb_allocate_area, .release_pages = hugetlb_release_pages, .alias_mapping = hugetlb_alias_mapping, @@ -356,6 +343,33 @@ static inline uint64_t uffd_minor_feature(void) return 0; } +static uint64_t get_expected_ioctls(uint64_t mode) +{ + uint64_t ioctls = UFFD_API_RANGE_IOCTLS; + + if (test_type == TEST_HUGETLB) + ioctls &= ~(1 << _UFFDIO_ZEROPAGE); + + if (!((mode & UFFDIO_REGISTER_MODE_WP) && test_uffdio_wp)) + ioctls &= ~(1 << _UFFDIO_WRITEPROTECT); + + if (!((mode & UFFDIO_REGISTER_MODE_MINOR) && test_uffdio_minor)) + ioctls &= ~(1 << _UFFDIO_CONTINUE); + + return ioctls; +} + +static void assert_expected_ioctls_present(uint64_t mode, uint64_t ioctls) +{ + uint64_t expected = get_expected_ioctls(mode); + uint64_t actual = ioctls & expected; + + if (actual != expected) { + err("missing ioctl(s): expected %"PRIx64" actual: %"PRIx64, + expected, actual); + } +} + static void userfaultfd_open(uint64_t *features) { struct uffdio_api uffdio_api; @@ -1017,11 +1031,9 @@ static int __uffdio_zeropage(int ufd, unsigned long offset, bool retry) { struct uffdio_zeropage uffdio_zeropage; int ret; - unsigned long has_zeropage; + bool has_zeropage = get_expected_ioctls(0) & (1 << _UFFDIO_ZEROPAGE); __s64 res; - has_zeropage = uffd_test_ops->expected_ioctls & (1 << _UFFDIO_ZEROPAGE); - if (offset >= nr_pages * page_size) err("unexpected offset %lu", offset); uffdio_zeropage.range.start = (unsigned long) area_dst + offset; @@ -1061,7 +1073,6 @@ static int uffdio_zeropage(int ufd, unsigned long offset) static int userfaultfd_zeropage_test(void) { struct uffdio_register uffdio_register; - unsigned long expected_ioctls; printf("testing UFFDIO_ZEROPAGE: "); fflush(stdout); @@ -1076,9 +1087,8 @@ static int userfaultfd_zeropage_test(void) if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) err("register failure"); - expected_ioctls = uffd_test_ops->expected_ioctls; - if ((uffdio_register.ioctls & expected_ioctls) != expected_ioctls) - err("unexpected missing ioctl for anon memory"); + assert_expected_ioctls_present( + uffdio_register.mode, uffdio_register.ioctls); if (uffdio_zeropage(uffd, 0)) if (my_bcmp(area_dst, zeropage, page_size)) @@ -1091,7 +1101,6 @@ static int userfaultfd_zeropage_test(void) static int userfaultfd_events_test(void) { struct uffdio_register uffdio_register; - unsigned long expected_ioctls; pthread_t uffd_mon; int err, features; pid_t pid; @@ -1115,9 +1124,8 @@ static int userfaultfd_events_test(void) if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) err("register failure"); - expected_ioctls = uffd_test_ops->expected_ioctls; - if ((uffdio_register.ioctls & expected_ioctls) != expected_ioctls) - err("unexpected missing ioctl for anon memory"); + assert_expected_ioctls_present( + uffdio_register.mode, uffdio_register.ioctls); if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats)) err("uffd_poll_thread create"); @@ -1145,7 +1153,6 @@ static int userfaultfd_events_test(void) static int userfaultfd_sig_test(void) { struct uffdio_register uffdio_register; - unsigned long expected_ioctls; unsigned long userfaults; pthread_t uffd_mon; int err, features; @@ -1169,9 +1176,8 @@ static int userfaultfd_sig_test(void) if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) err("register failure"); - expected_ioctls = uffd_test_ops->expected_ioctls; - if ((uffdio_register.ioctls & expected_ioctls) != expected_ioctls) - err("unexpected missing ioctl for anon memory"); + assert_expected_ioctls_present( + uffdio_register.mode, uffdio_register.ioctls); if (faulting_process(1)) err("faulting process failed"); @@ -1206,7 +1212,6 @@ static int userfaultfd_sig_test(void) static int userfaultfd_minor_test(void) { struct uffdio_register uffdio_register; - unsigned long expected_ioctls; unsigned long p; pthread_t uffd_mon; uint8_t expected_byte; @@ -1228,10 +1233,8 @@ static int userfaultfd_minor_test(void) if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) err("register failure"); - expected_ioctls = uffd_test_ops->expected_ioctls; - expected_ioctls |= 1 << _UFFDIO_CONTINUE; - if ((uffdio_register.ioctls & expected_ioctls) != expected_ioctls) - err("unexpected missing ioctl(s)"); + assert_expected_ioctls_present( + uffdio_register.mode, uffdio_register.ioctls); /* * After registering with UFFD, populate the non-UFFD-registered side of @@ -1428,8 +1431,6 @@ static int userfaultfd_stress(void) pthread_attr_setstacksize(&attr, 16*1024*1024); while (bounces--) { - unsigned long expected_ioctls; - printf("bounces: %d, mode:", bounces); if (bounces & BOUNCE_RANDOM) printf(" rnd"); @@ -1457,10 +1458,8 @@ static int userfaultfd_stress(void) uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP; if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) err("register failure"); - expected_ioctls = uffd_test_ops->expected_ioctls; - if ((uffdio_register.ioctls & expected_ioctls) != - expected_ioctls) - err("unexpected missing ioctl for anon memory"); + assert_expected_ioctls_present( + uffdio_register.mode, uffdio_register.ioctls); if (area_dst_alias) { uffdio_register.range.start = (unsigned long) From e1d8c966dbf11afcac1d115f3fca5a29060bba18 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Fri, 5 Nov 2021 13:42:16 -0700 Subject: [PATCH 050/166] mm/page_isolation: fix potential missing call to unset_migratetype_isolate() In start_isolate_page_range() undo path, pfn_to_online_page() just checks the first pfn in a pageblock while __first_valid_page() will traverse the pageblock until the first online pfn is found. So we may miss the call to unset_migratetype_isolate() in undo path and pages will remain isolated unexpectedly. Fix this by calling undo_isolate_page_range() and this will also help to simplify the code further. Note we shouldn't ever trigger it because MAX_ORDER-1 aligned pfn ranges shouldn't contain memory holes now. Link: https://lkml.kernel.org/r/20210914114348.15569-1-linmiaohe@huawei.com Fixes: 2ce13640b3f4 ("mm: __first_valid_page skip over offline pages") Signed-off-by: Miaohe Lin Reviewed-by: David Hildenbrand Cc: Michal Hocko Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_isolation.c | 20 +++----------------- 1 file changed, 3 insertions(+), 17 deletions(-) diff --git a/mm/page_isolation.c b/mm/page_isolation.c index a95c2c6562d0..f93cc63d8fa1 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -183,7 +183,6 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, unsigned migratetype, int flags) { unsigned long pfn; - unsigned long undo_pfn; struct page *page; BUG_ON(!IS_ALIGNED(start_pfn, pageblock_nr_pages)); @@ -193,25 +192,12 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, pfn < end_pfn; pfn += pageblock_nr_pages) { page = __first_valid_page(pfn, pageblock_nr_pages); - if (page) { - if (set_migratetype_isolate(page, migratetype, flags)) { - undo_pfn = pfn; - goto undo; - } + if (page && set_migratetype_isolate(page, migratetype, flags)) { + undo_isolate_page_range(start_pfn, pfn, migratetype); + return -EBUSY; } } return 0; -undo: - for (pfn = start_pfn; - pfn < undo_pfn; - pfn += pageblock_nr_pages) { - struct page *page = pfn_to_online_page(pfn); - if (!page) - continue; - unset_migratetype_isolate(page, migratetype); - } - - return -EBUSY; } /* From a500cb342c84a4c4696850304124bc801331c4a8 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Fri, 5 Nov 2021 13:42:19 -0700 Subject: [PATCH 051/166] mm/page_isolation: guard against possible putback unisolated page Isolating a free page in an isolated pageblock is expected to always work as watermarks don't apply here. But if __isolate_free_page() failed, due to condition changes, the page will be left on the free list. And the page will be put back to free list again via __putback_isolated_page(). This may trigger VM_BUG_ON_PAGE() on page->flags checking in __free_one_page() if PageReported is set. Or we will corrupt the free list because list_add() will be called for pages already on another list. Add a VM_WARN_ON() to complain about this change. Link: https://lkml.kernel.org/r/20210914114508.23725-1-linmiaohe@huawei.com Fixes: 3c605096d315 ("mm/page_alloc: restrict max order of merging on isolated pageblock") Signed-off-by: Miaohe Lin Reviewed-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: John Hubbard Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_isolation.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/mm/page_isolation.c b/mm/page_isolation.c index f93cc63d8fa1..f67c4c70f17f 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -94,8 +94,13 @@ static void unset_migratetype_isolate(struct page *page, unsigned migratetype) buddy = page + (buddy_pfn - pfn); if (!is_migrate_isolate_page(buddy)) { - __isolate_free_page(page, order); - isolated_page = true; + isolated_page = !!__isolate_free_page(page, order); + /* + * Isolating a free page in an isolated pageblock + * is expected to always work as watermarks don't + * apply here. + */ + VM_WARN_ON(!isolated_page); } } } From cb75463ca73483e79fbbad60f6fb704ee0489856 Mon Sep 17 00:00:00 2001 From: Kai Song Date: Fri, 5 Nov 2021 13:42:22 -0700 Subject: [PATCH 052/166] mm/vmscan.c: fix -Wunused-but-set-variable warning We fix the following warning when building kernel with W=1: mm/vmscan.c:1362:6: warning: variable 'err' set but not used [-Wunused-but-set-variable] Link: https://lkml.kernel.org/r/20210924181218.21165-1-songkai01@inspur.com Signed-off-by: Kai Song Reviewed-by: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmscan.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index 74296c2d1fed..9483dd6af550 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1337,7 +1337,6 @@ static unsigned int demote_page_list(struct list_head *demote_pages, { int target_nid = next_demotion_node(pgdat->node_id); unsigned int nr_succeeded; - int err; if (list_empty(demote_pages)) return 0; @@ -1346,7 +1345,7 @@ static unsigned int demote_page_list(struct list_head *demote_pages, return 0; /* Demotion ignores all cpuset and mempolicy settings */ - err = migrate_pages(demote_pages, alloc_demote_page, NULL, + migrate_pages(demote_pages, alloc_demote_page, NULL, target_nid, MIGRATE_ASYNC, MR_DEMOTION, &nr_succeeded); From 8cd7c588decf470bf7e14f2be93b709f839a965e Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 5 Nov 2021 13:42:25 -0700 Subject: [PATCH 053/166] mm/vmscan: throttle reclaim until some writeback completes if congested Patch series "Remove dependency on congestion_wait in mm/", v5. This series that removes all calls to congestion_wait in mm/ and deletes wait_iff_congested. It's not a clever implementation but congestion_wait has been broken for a long time [1]. Even if congestion throttling worked, it was never a great idea. While excessive dirty/writeback pages at the tail of the LRU is one possibility that reclaim may be slow, there is also the problem of too many pages being isolated and reclaim failing for other reasons (elevated references, too many pages isolated, excessive LRU contention etc). This series replaces the "congestion" throttling with 3 different types. - If there are too many dirty/writeback pages, sleep until a timeout or enough pages get cleaned - If too many pages are isolated, sleep until enough isolated pages are either reclaimed or put back on the LRU - If no progress is being made, direct reclaim tasks sleep until another task makes progress with acceptable efficiency. This was initially tested with a mix of workloads that used to trigger corner cases that no longer work. A new test case was created called "stutterp" (pagereclaim-stutterp-noreaders in mmtests) using a freshly created XFS filesystem. Note that it may be necessary to increase the timeout of ssh if executing remotely as ssh itself can get throttled and the connection may timeout. stutterp varies the number of "worker" processes from 4 up to NR_CPUS*4 to check the impact as the number of direct reclaimers increase. It has four types of worker. - One "anon latency" worker creates small mappings with mmap() and times how long it takes to fault the mapping reading it 4K at a time - X file writers which is fio randomly writing X files where the total size of the files add up to the allowed dirty_ratio. fio is allowed to run for a warmup period to allow some file-backed pages to accumulate. The duration of the warmup is based on the best-case linear write speed of the storage. - Y file readers which is fio randomly reading small files - Z anon memory hogs which continually map (100-dirty_ratio)% of memory - Total estimated WSS = (100+dirty_ration) percentage of memory X+Y+Z+1 == NR_WORKERS varying from 4 up to NR_CPUS*4 The intent is to maximise the total WSS with a mix of file and anon memory where some anonymous memory must be swapped and there is a high likelihood of dirty/writeback pages reaching the end of the LRU. The test can be configured to have no background readers to stress dirty/writeback pages. The results below are based on having zero readers. The short summary of the results is that the series works and stalls until some event occurs but the timeouts may need adjustment. The test results are not broken down by patch as the series should be treated as one block that replaces a broken throttling mechanism with a working one. Finally, three machines were tested but I'm reporting the worst set of results. The other two machines had much better latencies for example. First the results of the "anon latency" latency stutterp 5.15.0-rc1 5.15.0-rc1 vanilla mm-reclaimcongest-v5r4 Amean mmap-4 31.4003 ( 0.00%) 2661.0198 (-8374.52%) Amean mmap-7 38.1641 ( 0.00%) 149.2891 (-291.18%) Amean mmap-12 60.0981 ( 0.00%) 187.8105 (-212.51%) Amean mmap-21 161.2699 ( 0.00%) 213.9107 ( -32.64%) Amean mmap-30 174.5589 ( 0.00%) 377.7548 (-116.41%) Amean mmap-48 8106.8160 ( 0.00%) 1070.5616 ( 86.79%) Stddev mmap-4 41.3455 ( 0.00%) 27573.9676 (-66591.66%) Stddev mmap-7 53.5556 ( 0.00%) 4608.5860 (-8505.23%) Stddev mmap-12 171.3897 ( 0.00%) 5559.4542 (-3143.75%) Stddev mmap-21 1506.6752 ( 0.00%) 5746.2507 (-281.39%) Stddev mmap-30 557.5806 ( 0.00%) 7678.1624 (-1277.05%) Stddev mmap-48 61681.5718 ( 0.00%) 14507.2830 ( 76.48%) Max-90 mmap-4 31.4243 ( 0.00%) 83.1457 (-164.59%) Max-90 mmap-7 41.0410 ( 0.00%) 41.0720 ( -0.08%) Max-90 mmap-12 66.5255 ( 0.00%) 53.9073 ( 18.97%) Max-90 mmap-21 146.7479 ( 0.00%) 105.9540 ( 27.80%) Max-90 mmap-30 193.9513 ( 0.00%) 64.3067 ( 66.84%) Max-90 mmap-48 277.9137 ( 0.00%) 591.0594 (-112.68%) Max mmap-4 1913.8009 ( 0.00%) 299623.9695 (-15555.96%) Max mmap-7 2423.9665 ( 0.00%) 204453.1708 (-8334.65%) Max mmap-12 6845.6573 ( 0.00%) 221090.3366 (-3129.64%) Max mmap-21 56278.6508 ( 0.00%) 213877.3496 (-280.03%) Max mmap-30 19716.2990 ( 0.00%) 216287.6229 (-997.00%) Max mmap-48 477923.9400 ( 0.00%) 245414.8238 ( 48.65%) For most thread counts, the time to mmap() is unfortunately increased. In earlier versions of the series, this was lower but a large number of throttling events were reaching their timeout increasing the amount of inefficient scanning of the LRU. There is no prioritisation of reclaim tasks making progress based on each tasks rate of page allocation versus progress of reclaim. The variance is also impacted for high worker counts but in all cases, the differences in latency are not statistically significant due to very large maximum outliers. Max-90 shows that 90% of the stalls are comparable but the Max results show the massive outliers which are increased to to stalling. It is expected that this will be very machine dependant. Due to the test design, reclaim is difficult so allocations stall and there are variances depending on whether THPs can be allocated or not. The amount of memory will affect exactly how bad the corner cases are and how often they trigger. The warmup period calculation is not ideal as it's based on linear writes where as fio is randomly writing multiple files from multiple tasks so the start state of the test is variable. For example, these are the latencies on a single-socket machine that had more memory Amean mmap-4 42.2287 ( 0.00%) 49.6838 * -17.65%* Amean mmap-7 216.4326 ( 0.00%) 47.4451 * 78.08%* Amean mmap-12 2412.0588 ( 0.00%) 51.7497 ( 97.85%) Amean mmap-21 5546.2548 ( 0.00%) 51.8862 ( 99.06%) Amean mmap-30 1085.3121 ( 0.00%) 72.1004 ( 93.36%) The overall system CPU usage and elapsed time is as follows 5.15.0-rc3 5.15.0-rc3 vanilla mm-reclaimcongest-v5r4 Duration User 6989.03 983.42 Duration System 7308.12 799.68 Duration Elapsed 2277.67 2092.98 The patches reduce system CPU usage by 89% as the vanilla kernel is rarely stalling. The high-level /proc/vmstats show 5.15.0-rc1 5.15.0-rc1 vanilla mm-reclaimcongest-v5r2 Ops Direct pages scanned 1056608451.00 503594991.00 Ops Kswapd pages scanned 109795048.00 147289810.00 Ops Kswapd pages reclaimed 63269243.00 31036005.00 Ops Direct pages reclaimed 10803973.00 6328887.00 Ops Kswapd efficiency % 57.62 21.07 Ops Kswapd velocity 48204.98 57572.86 Ops Direct efficiency % 1.02 1.26 Ops Direct velocity 463898.83 196845.97 Kswapd scanned less pages but the detailed pattern is different. The vanilla kernel scans slowly over time where as the patches exhibits burst patterns of scan activity. Direct reclaim scanning is reduced by 52% due to stalling. The pattern for stealing pages is also slightly different. Both kernels exhibit spikes but the vanilla kernel when reclaiming shows pages being reclaimed over a period of time where as the patches tend to reclaim in spikes. The difference is that vanilla is not throttling and instead scanning constantly finding some pages over time where as the patched kernel throttles and reclaims in spikes. Ops Percentage direct scans 90.59 77.37 For direct reclaim, vanilla scanned 90.59% of pages where as with the patches, 77.37% were direct reclaim due to throttling Ops Page writes by reclaim 2613590.00 1687131.00 Page writes from reclaim context are reduced. Ops Page writes anon 2932752.00 1917048.00 And there is less swapping. Ops Page reclaim immediate 996248528.00 107664764.00 The number of pages encountered at the tail of the LRU tagged for immediate reclaim but still dirty/writeback is reduced by 89%. Ops Slabs scanned 164284.00 153608.00 Slab scan activity is similar. ftrace was used to gather stall activity Vanilla ------- 1 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=16000 2 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=12000 8 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=8000 29 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=4000 82394 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=0 The fast majority of wait_iff_congested calls do not stall at all. What is likely happening is that cond_resched() reschedules the task for a short period when the BDI is not registering congestion (which it never will in this test setup). 1 writeback_congestion_wait: usec_timeout=100000 usec_delayed=120000 2 writeback_congestion_wait: usec_timeout=100000 usec_delayed=132000 4 writeback_congestion_wait: usec_timeout=100000 usec_delayed=112000 380 writeback_congestion_wait: usec_timeout=100000 usec_delayed=108000 778 writeback_congestion_wait: usec_timeout=100000 usec_delayed=104000 congestion_wait if called always exceeds the timeout as there is no trigger to wake it up. Bottom line: Vanilla will throttle but it's not effective. Patch series ------------ Kswapd throttle activity was always due to scanning pages tagged for immediate reclaim at the tail of the LRU 1 usec_timeout=100000 usect_delayed=72000 reason=VMSCAN_THROTTLE_WRITEBACK 4 usec_timeout=100000 usect_delayed=20000 reason=VMSCAN_THROTTLE_WRITEBACK 5 usec_timeout=100000 usect_delayed=12000 reason=VMSCAN_THROTTLE_WRITEBACK 6 usec_timeout=100000 usect_delayed=16000 reason=VMSCAN_THROTTLE_WRITEBACK 11 usec_timeout=100000 usect_delayed=100000 reason=VMSCAN_THROTTLE_WRITEBACK 11 usec_timeout=100000 usect_delayed=8000 reason=VMSCAN_THROTTLE_WRITEBACK 94 usec_timeout=100000 usect_delayed=0 reason=VMSCAN_THROTTLE_WRITEBACK 112 usec_timeout=100000 usect_delayed=4000 reason=VMSCAN_THROTTLE_WRITEBACK The majority of events did not stall or stalled for a short period. Roughly 16% of stalls reached the timeout before expiry. For direct reclaim, the number of times stalled for each reason were 6624 reason=VMSCAN_THROTTLE_ISOLATED 93246 reason=VMSCAN_THROTTLE_NOPROGRESS 96934 reason=VMSCAN_THROTTLE_WRITEBACK The most common reason to stall was due to excessive pages tagged for immediate reclaim at the tail of the LRU followed by a failure to make forward. A relatively small number were due to too many pages isolated from the LRU by parallel threads For VMSCAN_THROTTLE_ISOLATED, the breakdown of delays was 9 usec_timeout=20000 usect_delayed=4000 reason=VMSCAN_THROTTLE_ISOLATED 12 usec_timeout=20000 usect_delayed=16000 reason=VMSCAN_THROTTLE_ISOLATED 83 usec_timeout=20000 usect_delayed=20000 reason=VMSCAN_THROTTLE_ISOLATED 6520 usec_timeout=20000 usect_delayed=0 reason=VMSCAN_THROTTLE_ISOLATED Most did not stall at all. A small number reached the timeout. For VMSCAN_THROTTLE_NOPROGRESS, the breakdown of stalls were all over the map 1 usec_timeout=500000 usect_delayed=324000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usec_timeout=500000 usect_delayed=332000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usec_timeout=500000 usect_delayed=348000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usec_timeout=500000 usect_delayed=360000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=228000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=260000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=340000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=364000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=372000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=428000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=460000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=464000 reason=VMSCAN_THROTTLE_NOPROGRESS 3 usec_timeout=500000 usect_delayed=244000 reason=VMSCAN_THROTTLE_NOPROGRESS 3 usec_timeout=500000 usect_delayed=252000 reason=VMSCAN_THROTTLE_NOPROGRESS 3 usec_timeout=500000 usect_delayed=272000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=188000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=268000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=328000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=380000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=392000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=432000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=204000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=220000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=412000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=436000 reason=VMSCAN_THROTTLE_NOPROGRESS 6 usec_timeout=500000 usect_delayed=488000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=212000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=300000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=316000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=472000 reason=VMSCAN_THROTTLE_NOPROGRESS 8 usec_timeout=500000 usect_delayed=248000 reason=VMSCAN_THROTTLE_NOPROGRESS 8 usec_timeout=500000 usect_delayed=356000 reason=VMSCAN_THROTTLE_NOPROGRESS 8 usec_timeout=500000 usect_delayed=456000 reason=VMSCAN_THROTTLE_NOPROGRESS 9 usec_timeout=500000 usect_delayed=124000 reason=VMSCAN_THROTTLE_NOPROGRESS 9 usec_timeout=500000 usect_delayed=376000 reason=VMSCAN_THROTTLE_NOPROGRESS 9 usec_timeout=500000 usect_delayed=484000 reason=VMSCAN_THROTTLE_NOPROGRESS 10 usec_timeout=500000 usect_delayed=172000 reason=VMSCAN_THROTTLE_NOPROGRESS 10 usec_timeout=500000 usect_delayed=420000 reason=VMSCAN_THROTTLE_NOPROGRESS 10 usec_timeout=500000 usect_delayed=452000 reason=VMSCAN_THROTTLE_NOPROGRESS 11 usec_timeout=500000 usect_delayed=256000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=112000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=116000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=144000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=152000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=264000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=384000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=424000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=492000 reason=VMSCAN_THROTTLE_NOPROGRESS 13 usec_timeout=500000 usect_delayed=184000 reason=VMSCAN_THROTTLE_NOPROGRESS 13 usec_timeout=500000 usect_delayed=444000 reason=VMSCAN_THROTTLE_NOPROGRESS 14 usec_timeout=500000 usect_delayed=308000 reason=VMSCAN_THROTTLE_NOPROGRESS 14 usec_timeout=500000 usect_delayed=440000 reason=VMSCAN_THROTTLE_NOPROGRESS 14 usec_timeout=500000 usect_delayed=476000 reason=VMSCAN_THROTTLE_NOPROGRESS 16 usec_timeout=500000 usect_delayed=140000 reason=VMSCAN_THROTTLE_NOPROGRESS 17 usec_timeout=500000 usect_delayed=232000 reason=VMSCAN_THROTTLE_NOPROGRESS 17 usec_timeout=500000 usect_delayed=240000 reason=VMSCAN_THROTTLE_NOPROGRESS 17 usec_timeout=500000 usect_delayed=280000 reason=VMSCAN_THROTTLE_NOPROGRESS 18 usec_timeout=500000 usect_delayed=404000 reason=VMSCAN_THROTTLE_NOPROGRESS 20 usec_timeout=500000 usect_delayed=148000 reason=VMSCAN_THROTTLE_NOPROGRESS 20 usec_timeout=500000 usect_delayed=216000 reason=VMSCAN_THROTTLE_NOPROGRESS 20 usec_timeout=500000 usect_delayed=468000 reason=VMSCAN_THROTTLE_NOPROGRESS 21 usec_timeout=500000 usect_delayed=448000 reason=VMSCAN_THROTTLE_NOPROGRESS 23 usec_timeout=500000 usect_delayed=168000 reason=VMSCAN_THROTTLE_NOPROGRESS 23 usec_timeout=500000 usect_delayed=296000 reason=VMSCAN_THROTTLE_NOPROGRESS 25 usec_timeout=500000 usect_delayed=132000 reason=VMSCAN_THROTTLE_NOPROGRESS 25 usec_timeout=500000 usect_delayed=352000 reason=VMSCAN_THROTTLE_NOPROGRESS 26 usec_timeout=500000 usect_delayed=180000 reason=VMSCAN_THROTTLE_NOPROGRESS 27 usec_timeout=500000 usect_delayed=284000 reason=VMSCAN_THROTTLE_NOPROGRESS 28 usec_timeout=500000 usect_delayed=164000 reason=VMSCAN_THROTTLE_NOPROGRESS 29 usec_timeout=500000 usect_delayed=136000 reason=VMSCAN_THROTTLE_NOPROGRESS 30 usec_timeout=500000 usect_delayed=200000 reason=VMSCAN_THROTTLE_NOPROGRESS 30 usec_timeout=500000 usect_delayed=400000 reason=VMSCAN_THROTTLE_NOPROGRESS 31 usec_timeout=500000 usect_delayed=196000 reason=VMSCAN_THROTTLE_NOPROGRESS 32 usec_timeout=500000 usect_delayed=156000 reason=VMSCAN_THROTTLE_NOPROGRESS 33 usec_timeout=500000 usect_delayed=224000 reason=VMSCAN_THROTTLE_NOPROGRESS 35 usec_timeout=500000 usect_delayed=128000 reason=VMSCAN_THROTTLE_NOPROGRESS 35 usec_timeout=500000 usect_delayed=176000 reason=VMSCAN_THROTTLE_NOPROGRESS 36 usec_timeout=500000 usect_delayed=368000 reason=VMSCAN_THROTTLE_NOPROGRESS 36 usec_timeout=500000 usect_delayed=496000 reason=VMSCAN_THROTTLE_NOPROGRESS 37 usec_timeout=500000 usect_delayed=312000 reason=VMSCAN_THROTTLE_NOPROGRESS 38 usec_timeout=500000 usect_delayed=304000 reason=VMSCAN_THROTTLE_NOPROGRESS 40 usec_timeout=500000 usect_delayed=288000 reason=VMSCAN_THROTTLE_NOPROGRESS 43 usec_timeout=500000 usect_delayed=408000 reason=VMSCAN_THROTTLE_NOPROGRESS 55 usec_timeout=500000 usect_delayed=416000 reason=VMSCAN_THROTTLE_NOPROGRESS 56 usec_timeout=500000 usect_delayed=76000 reason=VMSCAN_THROTTLE_NOPROGRESS 58 usec_timeout=500000 usect_delayed=120000 reason=VMSCAN_THROTTLE_NOPROGRESS 59 usec_timeout=500000 usect_delayed=208000 reason=VMSCAN_THROTTLE_NOPROGRESS 61 usec_timeout=500000 usect_delayed=68000 reason=VMSCAN_THROTTLE_NOPROGRESS 71 usec_timeout=500000 usect_delayed=192000 reason=VMSCAN_THROTTLE_NOPROGRESS 71 usec_timeout=500000 usect_delayed=480000 reason=VMSCAN_THROTTLE_NOPROGRESS 79 usec_timeout=500000 usect_delayed=60000 reason=VMSCAN_THROTTLE_NOPROGRESS 82 usec_timeout=500000 usect_delayed=320000 reason=VMSCAN_THROTTLE_NOPROGRESS 82 usec_timeout=500000 usect_delayed=92000 reason=VMSCAN_THROTTLE_NOPROGRESS 85 usec_timeout=500000 usect_delayed=64000 reason=VMSCAN_THROTTLE_NOPROGRESS 85 usec_timeout=500000 usect_delayed=80000 reason=VMSCAN_THROTTLE_NOPROGRESS 88 usec_timeout=500000 usect_delayed=84000 reason=VMSCAN_THROTTLE_NOPROGRESS 90 usec_timeout=500000 usect_delayed=160000 reason=VMSCAN_THROTTLE_NOPROGRESS 90 usec_timeout=500000 usect_delayed=292000 reason=VMSCAN_THROTTLE_NOPROGRESS 94 usec_timeout=500000 usect_delayed=56000 reason=VMSCAN_THROTTLE_NOPROGRESS 118 usec_timeout=500000 usect_delayed=88000 reason=VMSCAN_THROTTLE_NOPROGRESS 119 usec_timeout=500000 usect_delayed=72000 reason=VMSCAN_THROTTLE_NOPROGRESS 126 usec_timeout=500000 usect_delayed=108000 reason=VMSCAN_THROTTLE_NOPROGRESS 146 usec_timeout=500000 usect_delayed=52000 reason=VMSCAN_THROTTLE_NOPROGRESS 148 usec_timeout=500000 usect_delayed=36000 reason=VMSCAN_THROTTLE_NOPROGRESS 148 usec_timeout=500000 usect_delayed=48000 reason=VMSCAN_THROTTLE_NOPROGRESS 159 usec_timeout=500000 usect_delayed=28000 reason=VMSCAN_THROTTLE_NOPROGRESS 178 usec_timeout=500000 usect_delayed=44000 reason=VMSCAN_THROTTLE_NOPROGRESS 183 usec_timeout=500000 usect_delayed=40000 reason=VMSCAN_THROTTLE_NOPROGRESS 237 usec_timeout=500000 usect_delayed=100000 reason=VMSCAN_THROTTLE_NOPROGRESS 266 usec_timeout=500000 usect_delayed=32000 reason=VMSCAN_THROTTLE_NOPROGRESS 313 usec_timeout=500000 usect_delayed=24000 reason=VMSCAN_THROTTLE_NOPROGRESS 347 usec_timeout=500000 usect_delayed=96000 reason=VMSCAN_THROTTLE_NOPROGRESS 470 usec_timeout=500000 usect_delayed=20000 reason=VMSCAN_THROTTLE_NOPROGRESS 559 usec_timeout=500000 usect_delayed=16000 reason=VMSCAN_THROTTLE_NOPROGRESS 964 usec_timeout=500000 usect_delayed=12000 reason=VMSCAN_THROTTLE_NOPROGRESS 2001 usec_timeout=500000 usect_delayed=104000 reason=VMSCAN_THROTTLE_NOPROGRESS 2447 usec_timeout=500000 usect_delayed=8000 reason=VMSCAN_THROTTLE_NOPROGRESS 7888 usec_timeout=500000 usect_delayed=4000 reason=VMSCAN_THROTTLE_NOPROGRESS 22727 usec_timeout=500000 usect_delayed=0 reason=VMSCAN_THROTTLE_NOPROGRESS 51305 usec_timeout=500000 usect_delayed=500000 reason=VMSCAN_THROTTLE_NOPROGRESS The full timeout is often hit but a large number also do not stall at all. The remainder slept a little allowing other reclaim tasks to make progress. While this timeout could be further increased, it could also negatively impact worst-case behaviour when there is no prioritisation of what task should make progress. For VMSCAN_THROTTLE_WRITEBACK, the breakdown was 1 usec_timeout=100000 usect_delayed=44000 reason=VMSCAN_THROTTLE_WRITEBACK 2 usec_timeout=100000 usect_delayed=76000 reason=VMSCAN_THROTTLE_WRITEBACK 3 usec_timeout=100000 usect_delayed=80000 reason=VMSCAN_THROTTLE_WRITEBACK 5 usec_timeout=100000 usect_delayed=48000 reason=VMSCAN_THROTTLE_WRITEBACK 5 usec_timeout=100000 usect_delayed=84000 reason=VMSCAN_THROTTLE_WRITEBACK 6 usec_timeout=100000 usect_delayed=72000 reason=VMSCAN_THROTTLE_WRITEBACK 7 usec_timeout=100000 usect_delayed=88000 reason=VMSCAN_THROTTLE_WRITEBACK 11 usec_timeout=100000 usect_delayed=56000 reason=VMSCAN_THROTTLE_WRITEBACK 12 usec_timeout=100000 usect_delayed=64000 reason=VMSCAN_THROTTLE_WRITEBACK 16 usec_timeout=100000 usect_delayed=92000 reason=VMSCAN_THROTTLE_WRITEBACK 24 usec_timeout=100000 usect_delayed=68000 reason=VMSCAN_THROTTLE_WRITEBACK 28 usec_timeout=100000 usect_delayed=32000 reason=VMSCAN_THROTTLE_WRITEBACK 30 usec_timeout=100000 usect_delayed=60000 reason=VMSCAN_THROTTLE_WRITEBACK 30 usec_timeout=100000 usect_delayed=96000 reason=VMSCAN_THROTTLE_WRITEBACK 32 usec_timeout=100000 usect_delayed=52000 reason=VMSCAN_THROTTLE_WRITEBACK 42 usec_timeout=100000 usect_delayed=40000 reason=VMSCAN_THROTTLE_WRITEBACK 77 usec_timeout=100000 usect_delayed=28000 reason=VMSCAN_THROTTLE_WRITEBACK 99 usec_timeout=100000 usect_delayed=36000 reason=VMSCAN_THROTTLE_WRITEBACK 137 usec_timeout=100000 usect_delayed=24000 reason=VMSCAN_THROTTLE_WRITEBACK 190 usec_timeout=100000 usect_delayed=20000 reason=VMSCAN_THROTTLE_WRITEBACK 339 usec_timeout=100000 usect_delayed=16000 reason=VMSCAN_THROTTLE_WRITEBACK 518 usec_timeout=100000 usect_delayed=12000 reason=VMSCAN_THROTTLE_WRITEBACK 852 usec_timeout=100000 usect_delayed=8000 reason=VMSCAN_THROTTLE_WRITEBACK 3359 usec_timeout=100000 usect_delayed=4000 reason=VMSCAN_THROTTLE_WRITEBACK 7147 usec_timeout=100000 usect_delayed=0 reason=VMSCAN_THROTTLE_WRITEBACK 83962 usec_timeout=100000 usect_delayed=100000 reason=VMSCAN_THROTTLE_WRITEBACK The majority hit the timeout in direct reclaim context although a sizable number did not stall at all. This is very different to kswapd where only a tiny percentage of stalls due to writeback reached the timeout. Bottom line, the throttling appears to work and the wakeup events may limit worst case stalls. There might be some grounds for adjusting timeouts but it's likely futile as the worst-case scenarios depend on the workload, memory size and the speed of the storage. A better approach to improve the series further would be to prioritise tasks based on their rate of allocation with the caveat that it may be very expensive to track. This patch (of 5): Page reclaim throttles on wait_iff_congested under the following conditions: - kswapd is encountering pages under writeback and marked for immediate reclaim implying that pages are cycling through the LRU faster than pages can be cleaned. - Direct reclaim will stall if all dirty pages are backed by congested inodes. wait_iff_congested is almost completely broken with few exceptions. This patch adds a new node-based workqueue and tracks the number of throttled tasks and pages written back since throttling started. If enough pages belonging to the node are written back then the throttled tasks will wake early. If not, the throttled tasks sleeps until the timeout expires. [neilb@suse.de: Uninterruptible sleep and simpler wakeups] [hdanton@sina.com: Avoid race when reclaim starts] [vbabka@suse.cz: vmstat irq-safe api, clarifications] Link: https://lore.kernel.org/linux-mm/45d8b7a6-8548-65f5-cccf-9f451d4ae3d4@kernel.dk/ [1] Link: https://lkml.kernel.org/r/20211022144651.19914-1-mgorman@techsingularity.net Link: https://lkml.kernel.org/r/20211022144651.19914-2-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: NeilBrown Cc: "Theodore Ts'o" Cc: Andreas Dilger Cc: "Darrick J . Wong" Cc: Matthew Wilcox Cc: Michal Hocko Cc: Dave Chinner Cc: Rik van Riel Cc: Johannes Weiner Cc: Jonathan Corbet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/backing-dev.h | 1 - include/linux/mmzone.h | 13 +++++ include/trace/events/vmscan.h | 34 +++++++++++++ include/trace/events/writeback.h | 7 --- mm/backing-dev.c | 48 ------------------- mm/filemap.c | 1 + mm/internal.h | 11 +++++ mm/page_alloc.c | 5 ++ mm/vmscan.c | 82 +++++++++++++++++++++++++++----- mm/vmstat.c | 1 + 10 files changed, 135 insertions(+), 68 deletions(-) diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index ac7f231b8825..9fb1f0ae273c 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -154,7 +154,6 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) } long congestion_wait(int sync, long timeout); -long wait_iff_congested(int sync, long timeout); static inline bool mapping_can_writeback(struct address_space *mapping) { diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index fb36a29e3aae..5a5e19b90dab 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -199,6 +199,7 @@ enum node_stat_item { NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ + NR_THROTTLED_WRITTEN, /* NR_WRITTEN while reclaim throttled */ NR_KERNEL_MISC_RECLAIMABLE, /* reclaimable non-slab kernel pages */ NR_FOLL_PIN_ACQUIRED, /* via: pin_user_page(), gup flag: FOLL_PIN */ NR_FOLL_PIN_RELEASED, /* pages returned via unpin_user_page() */ @@ -272,6 +273,11 @@ enum lru_list { NR_LRU_LISTS }; +enum vmscan_throttle_state { + VMSCAN_THROTTLE_WRITEBACK, + NR_VMSCAN_THROTTLE, +}; + #define for_each_lru(lru) for (lru = 0; lru < NR_LRU_LISTS; lru++) #define for_each_evictable_lru(lru) for (lru = 0; lru <= LRU_ACTIVE_FILE; lru++) @@ -841,6 +847,13 @@ typedef struct pglist_data { int node_id; wait_queue_head_t kswapd_wait; wait_queue_head_t pfmemalloc_wait; + + /* workqueues for throttling reclaim for different reasons. */ + wait_queue_head_t reclaim_wait[NR_VMSCAN_THROTTLE]; + + atomic_t nr_writeback_throttled;/* nr of writeback-throttled tasks */ + unsigned long nr_reclaim_start; /* nr pages written while throttled + * when throttling started. */ struct task_struct *kswapd; /* Protected by mem_hotplug_begin/end() */ int kswapd_order; diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index 88faf2400ec2..c317f9fe0d17 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -27,6 +27,14 @@ {RECLAIM_WB_ASYNC, "RECLAIM_WB_ASYNC"} \ ) : "RECLAIM_WB_NONE" +#define _VMSCAN_THROTTLE_WRITEBACK (1 << VMSCAN_THROTTLE_WRITEBACK) + +#define show_throttle_flags(flags) \ + (flags) ? __print_flags(flags, "|", \ + {_VMSCAN_THROTTLE_WRITEBACK, "VMSCAN_THROTTLE_WRITEBACK"} \ + ) : "VMSCAN_THROTTLE_NONE" + + #define trace_reclaim_flags(file) ( \ (file ? RECLAIM_WB_FILE : RECLAIM_WB_ANON) | \ (RECLAIM_WB_ASYNC) \ @@ -454,6 +462,32 @@ DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_node_reclaim_end, TP_ARGS(nr_reclaimed) ); +TRACE_EVENT(mm_vmscan_throttled, + + TP_PROTO(int nid, int usec_timeout, int usec_delayed, int reason), + + TP_ARGS(nid, usec_timeout, usec_delayed, reason), + + TP_STRUCT__entry( + __field(int, nid) + __field(int, usec_timeout) + __field(int, usec_delayed) + __field(int, reason) + ), + + TP_fast_assign( + __entry->nid = nid; + __entry->usec_timeout = usec_timeout; + __entry->usec_delayed = usec_delayed; + __entry->reason = 1U << reason; + ), + + TP_printk("nid=%d usec_timeout=%d usect_delayed=%d reason=%s", + __entry->nid, + __entry->usec_timeout, + __entry->usec_delayed, + show_throttle_flags(__entry->reason)) +); #endif /* _TRACE_VMSCAN_H */ /* This part must be outside protection */ diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 840d1ba84cf5..3bc759b81897 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -763,13 +763,6 @@ DEFINE_EVENT(writeback_congest_waited_template, writeback_congestion_wait, TP_ARGS(usec_timeout, usec_delayed) ); -DEFINE_EVENT(writeback_congest_waited_template, writeback_wait_iff_congested, - - TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed), - - TP_ARGS(usec_timeout, usec_delayed) -); - DECLARE_EVENT_CLASS(writeback_single_inode_template, TP_PROTO(struct inode *inode, diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 5ccb25089808..3d2983752e24 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -1038,51 +1038,3 @@ long congestion_wait(int sync, long timeout) return ret; } EXPORT_SYMBOL(congestion_wait); - -/** - * wait_iff_congested - Conditionally wait for a backing_dev to become uncongested or a pgdat to complete writes - * @sync: SYNC or ASYNC IO - * @timeout: timeout in jiffies - * - * In the event of a congested backing_dev (any backing_dev) this waits - * for up to @timeout jiffies for either a BDI to exit congestion of the - * given @sync queue or a write to complete. - * - * The return value is 0 if the sleep is for the full timeout. Otherwise, - * it is the number of jiffies that were still remaining when the function - * returned. return_value == timeout implies the function did not sleep. - */ -long wait_iff_congested(int sync, long timeout) -{ - long ret; - unsigned long start = jiffies; - DEFINE_WAIT(wait); - wait_queue_head_t *wqh = &congestion_wqh[sync]; - - /* - * If there is no congestion, yield if necessary instead - * of sleeping on the congestion queue - */ - if (atomic_read(&nr_wb_congested[sync]) == 0) { - cond_resched(); - - /* In case we scheduled, work out time remaining */ - ret = timeout - (jiffies - start); - if (ret < 0) - ret = 0; - - goto out; - } - - /* Sleep until uncongested or a write happens */ - prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); - ret = io_schedule_timeout(timeout); - finish_wait(wqh, &wait); - -out: - trace_writeback_wait_iff_congested(jiffies_to_usecs(timeout), - jiffies_to_usecs(jiffies - start)); - - return ret; -} -EXPORT_SYMBOL(wait_iff_congested); diff --git a/mm/filemap.c b/mm/filemap.c index 6f2c4bd6a571..b6140debc2da 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1612,6 +1612,7 @@ void end_page_writeback(struct page *page) smp_mb__after_atomic(); wake_up_page(page, PG_writeback); + acct_reclaim_writeback(page); put_page(page); } EXPORT_SYMBOL(end_page_writeback); diff --git a/mm/internal.h b/mm/internal.h index 6c3e1a9f8c5a..a59b5626f968 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -34,6 +34,17 @@ void page_writeback_init(void); +void __acct_reclaim_writeback(pg_data_t *pgdat, struct page *page, + int nr_throttled); +static inline void acct_reclaim_writeback(struct page *page) +{ + pg_data_t *pgdat = page_pgdat(page); + int nr_throttled = atomic_read(&pgdat->nr_writeback_throttled); + + if (nr_throttled) + __acct_reclaim_writeback(pgdat, page, nr_throttled); +} + vm_fault_t do_swap_page(struct vm_fault *vmf); void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 09a0f1c5d5d2..0f1f1f353211 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -7408,6 +7408,8 @@ static void pgdat_init_kcompactd(struct pglist_data *pgdat) {} static void __meminit pgdat_init_internals(struct pglist_data *pgdat) { + int i; + pgdat_resize_init(pgdat); pgdat_init_split_queue(pgdat); @@ -7416,6 +7418,9 @@ static void __meminit pgdat_init_internals(struct pglist_data *pgdat) init_waitqueue_head(&pgdat->kswapd_wait); init_waitqueue_head(&pgdat->pfmemalloc_wait); + for (i = 0; i < NR_VMSCAN_THROTTLE; i++) + init_waitqueue_head(&pgdat->reclaim_wait[i]); + pgdat_page_ext_init(pgdat); lruvec_init(&pgdat->__lruvec); } diff --git a/mm/vmscan.c b/mm/vmscan.c index 9483dd6af550..09beeb55546c 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1006,6 +1006,64 @@ static void handle_write_error(struct address_space *mapping, unlock_page(page); } +static void +reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason, + long timeout) +{ + wait_queue_head_t *wqh = &pgdat->reclaim_wait[reason]; + long ret; + DEFINE_WAIT(wait); + + /* + * Do not throttle IO workers, kthreads other than kswapd or + * workqueues. They may be required for reclaim to make + * forward progress (e.g. journalling workqueues or kthreads). + */ + if (!current_is_kswapd() && + current->flags & (PF_IO_WORKER|PF_KTHREAD)) + return; + + if (atomic_inc_return(&pgdat->nr_writeback_throttled) == 1) { + WRITE_ONCE(pgdat->nr_reclaim_start, + node_page_state(pgdat, NR_THROTTLED_WRITTEN)); + } + + prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); + ret = schedule_timeout(timeout); + finish_wait(wqh, &wait); + atomic_dec(&pgdat->nr_writeback_throttled); + + trace_mm_vmscan_throttled(pgdat->node_id, jiffies_to_usecs(timeout), + jiffies_to_usecs(timeout - ret), + reason); +} + +/* + * Account for pages written if tasks are throttled waiting on dirty + * pages to clean. If enough pages have been cleaned since throttling + * started then wakeup the throttled tasks. + */ +void __acct_reclaim_writeback(pg_data_t *pgdat, struct page *page, + int nr_throttled) +{ + unsigned long nr_written; + + inc_node_page_state(page, NR_THROTTLED_WRITTEN); + + /* + * This is an inaccurate read as the per-cpu deltas may not + * be synchronised. However, given that the system is + * writeback throttled, it is not worth taking the penalty + * of getting an accurate count. At worst, the throttle + * timeout guarantees forward progress. + */ + nr_written = node_page_state(pgdat, NR_THROTTLED_WRITTEN) - + READ_ONCE(pgdat->nr_reclaim_start); + + if (nr_written > SWAP_CLUSTER_MAX * nr_throttled) + wake_up(&pgdat->reclaim_wait[VMSCAN_THROTTLE_WRITEBACK]); +} + /* possible outcome of pageout() */ typedef enum { /* failed to write page out, page is locked */ @@ -1411,9 +1469,8 @@ retry: /* * The number of dirty pages determines if a node is marked - * reclaim_congested which affects wait_iff_congested. kswapd - * will stall and start writing pages if the tail of the LRU - * is all dirty unqueued pages. + * reclaim_congested. kswapd will stall and start writing + * pages if the tail of the LRU is all dirty unqueued pages. */ page_check_dirty_writeback(page, &dirty, &writeback); if (dirty || writeback) @@ -3179,19 +3236,19 @@ again: * If kswapd scans pages marked for immediate * reclaim and under writeback (nr_immediate), it * implies that pages are cycling through the LRU - * faster than they are written so also forcibly stall. + * faster than they are written so forcibly stall + * until some pages complete writeback. */ if (sc->nr.immediate) - congestion_wait(BLK_RW_ASYNC, HZ/10); + reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK, HZ/10); } /* - * Tag a node/memcg as congested if all the dirty pages - * scanned were backed by a congested BDI and - * wait_iff_congested will stall. + * Tag a node/memcg as congested if all the dirty pages were marked + * for writeback and immediate reclaim (counted in nr.congested). * * Legacy memcg will stall in page writeback so avoid forcibly - * stalling in wait_iff_congested(). + * stalling in reclaim_throttle(). */ if ((current_is_kswapd() || (cgroup_reclaim(sc) && writeback_throttling_sane(sc))) && @@ -3199,15 +3256,15 @@ again: set_bit(LRUVEC_CONGESTED, &target_lruvec->flags); /* - * Stall direct reclaim for IO completions if underlying BDIs - * and node is congested. Allow kswapd to continue until it + * Stall direct reclaim for IO completions if the lruvec is + * node is congested. Allow kswapd to continue until it * starts encountering unqueued dirty pages or cycling through * the LRU too quickly. */ if (!current_is_kswapd() && current_may_throttle() && !sc->hibernation_mode && test_bit(LRUVEC_CONGESTED, &target_lruvec->flags)) - wait_iff_congested(BLK_RW_ASYNC, HZ/10); + reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK, HZ/10); if (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed, sc)) @@ -4285,6 +4342,7 @@ static int kswapd(void *p) WRITE_ONCE(pgdat->kswapd_order, 0); WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); + atomic_set(&pgdat->nr_writeback_throttled, 0); for ( ; ; ) { bool ret; diff --git a/mm/vmstat.c b/mm/vmstat.c index ae87c90e0b4e..0f4643e5324d 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1225,6 +1225,7 @@ const char * const vmstat_text[] = { "nr_vmscan_immediate_reclaim", "nr_dirtied", "nr_written", + "nr_throttled_written", "nr_kernel_misc_reclaimable", "nr_foll_pin_acquired", "nr_foll_pin_released", From d818fca1cac31b1fc9301bda83e195a46fb4ebaa Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 5 Nov 2021 13:42:29 -0700 Subject: [PATCH 054/166] mm/vmscan: throttle reclaim and compaction when too may pages are isolated Page reclaim throttles on congestion if too many parallel reclaim instances have isolated too many pages. This makes no sense, excessive parallelisation has nothing to do with writeback or congestion. This patch creates an additional workqueue to sleep on when too many pages are isolated. The throttled tasks are woken when the number of isolated pages is reduced or a timeout occurs. There may be some false positive wakeups for GFP_NOIO/GFP_NOFS callers but the tasks will throttle again if necessary. [shy828301@gmail.com: Wake up from compaction context] [vbabka@suse.cz: Account number of throttled tasks only for writeback] Link: https://lkml.kernel.org/r/20211022144651.19914-3-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Andreas Dilger Cc: "Darrick J . Wong" Cc: Dave Chinner Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Michal Hocko Cc: NeilBrown Cc: Rik van Riel Cc: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + include/trace/events/vmscan.h | 4 +++- mm/compaction.c | 10 ++++++++-- mm/internal.h | 11 +++++++++++ mm/vmscan.c | 22 ++++++++++++++++------ 5 files changed, 39 insertions(+), 9 deletions(-) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 5a5e19b90dab..312c1ea9aafa 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -275,6 +275,7 @@ enum lru_list { enum vmscan_throttle_state { VMSCAN_THROTTLE_WRITEBACK, + VMSCAN_THROTTLE_ISOLATED, NR_VMSCAN_THROTTLE, }; diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index c317f9fe0d17..d4905bd9e9c4 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -28,10 +28,12 @@ ) : "RECLAIM_WB_NONE" #define _VMSCAN_THROTTLE_WRITEBACK (1 << VMSCAN_THROTTLE_WRITEBACK) +#define _VMSCAN_THROTTLE_ISOLATED (1 << VMSCAN_THROTTLE_ISOLATED) #define show_throttle_flags(flags) \ (flags) ? __print_flags(flags, "|", \ - {_VMSCAN_THROTTLE_WRITEBACK, "VMSCAN_THROTTLE_WRITEBACK"} \ + {_VMSCAN_THROTTLE_WRITEBACK, "VMSCAN_THROTTLE_WRITEBACK"}, \ + {_VMSCAN_THROTTLE_ISOLATED, "VMSCAN_THROTTLE_ISOLATED"} \ ) : "VMSCAN_THROTTLE_NONE" diff --git a/mm/compaction.c b/mm/compaction.c index bfc93da1c2c7..7359093d8ac0 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -761,6 +761,8 @@ isolate_freepages_range(struct compact_control *cc, /* Similar to reclaim, but different enough that they don't share logic */ static bool too_many_isolated(pg_data_t *pgdat) { + bool too_many; + unsigned long active, inactive, isolated; inactive = node_page_state(pgdat, NR_INACTIVE_FILE) + @@ -770,7 +772,11 @@ static bool too_many_isolated(pg_data_t *pgdat) isolated = node_page_state(pgdat, NR_ISOLATED_FILE) + node_page_state(pgdat, NR_ISOLATED_ANON); - return isolated > (inactive + active) / 2; + too_many = isolated > (inactive + active) / 2; + if (!too_many) + wake_throttle_isolated(pgdat); + + return too_many; } /** @@ -822,7 +828,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, if (cc->mode == MIGRATE_ASYNC) return -EAGAIN; - congestion_wait(BLK_RW_ASYNC, HZ/10); + reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED, HZ/10); if (fatal_signal_pending(current)) return -EINTR; diff --git a/mm/internal.h b/mm/internal.h index a59b5626f968..7dfe74f827bf 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -45,6 +45,15 @@ static inline void acct_reclaim_writeback(struct page *page) __acct_reclaim_writeback(pgdat, page, nr_throttled); } +static inline void wake_throttle_isolated(pg_data_t *pgdat) +{ + wait_queue_head_t *wqh; + + wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_ISOLATED]; + if (waitqueue_active(wqh)) + wake_up(wqh); +} + vm_fault_t do_swap_page(struct vm_fault *vmf); void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, @@ -121,6 +130,8 @@ extern unsigned long highest_memmap_pfn; */ extern int isolate_lru_page(struct page *page); extern void putback_lru_page(struct page *page); +extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason, + long timeout); /* * in mm/rmap.c: diff --git a/mm/vmscan.c b/mm/vmscan.c index 09beeb55546c..7bfd62f81e16 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1006,12 +1006,12 @@ static void handle_write_error(struct address_space *mapping, unlock_page(page); } -static void -reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason, +void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason, long timeout) { wait_queue_head_t *wqh = &pgdat->reclaim_wait[reason]; long ret; + bool acct_writeback = (reason == VMSCAN_THROTTLE_WRITEBACK); DEFINE_WAIT(wait); /* @@ -1023,7 +1023,8 @@ reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason, current->flags & (PF_IO_WORKER|PF_KTHREAD)) return; - if (atomic_inc_return(&pgdat->nr_writeback_throttled) == 1) { + if (acct_writeback && + atomic_inc_return(&pgdat->nr_writeback_throttled) == 1) { WRITE_ONCE(pgdat->nr_reclaim_start, node_page_state(pgdat, NR_THROTTLED_WRITTEN)); } @@ -1031,7 +1032,9 @@ reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason, prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); ret = schedule_timeout(timeout); finish_wait(wqh, &wait); - atomic_dec(&pgdat->nr_writeback_throttled); + + if (acct_writeback) + atomic_dec(&pgdat->nr_writeback_throttled); trace_mm_vmscan_throttled(pgdat->node_id, jiffies_to_usecs(timeout), jiffies_to_usecs(timeout - ret), @@ -2175,6 +2178,7 @@ static int too_many_isolated(struct pglist_data *pgdat, int file, struct scan_control *sc) { unsigned long inactive, isolated; + bool too_many; if (current_is_kswapd()) return 0; @@ -2198,7 +2202,13 @@ static int too_many_isolated(struct pglist_data *pgdat, int file, if ((sc->gfp_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS)) inactive >>= 3; - return isolated > inactive; + too_many = isolated > inactive; + + /* Wake up tasks throttled due to too_many_isolated. */ + if (!too_many) + wake_throttle_isolated(pgdat); + + return too_many; } /* @@ -2307,8 +2317,8 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, return 0; /* wait a bit for the reclaimer. */ - msleep(100); stalled = true; + reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED, HZ/10); /* We are about to die and free our memory. Return now. */ if (fatal_signal_pending(current)) From 69392a403f49e6e33f9dfb1d6edb87c8006f83c2 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 5 Nov 2021 13:42:32 -0700 Subject: [PATCH 055/166] mm/vmscan: throttle reclaim when no progress is being made Memcg reclaim throttles on congestion if no reclaim progress is made. This makes little sense, it might be due to writeback or a host of other factors. For !memcg reclaim, it's messy. Direct reclaim primarily is throttled in the page allocator if it is failing to make progress. Kswapd throttles if too many pages are under writeback and marked for immediate reclaim. This patch explicitly throttles if reclaim is failing to make progress. [vbabka@suse.cz: Remove redundant code] Link: https://lkml.kernel.org/r/20211022144651.19914-4-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Andreas Dilger Cc: "Darrick J . Wong" Cc: Dave Chinner Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Michal Hocko Cc: NeilBrown Cc: Rik van Riel Cc: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + include/trace/events/vmscan.h | 4 +++- mm/memcontrol.c | 10 +--------- mm/vmscan.c | 28 ++++++++++++++++++++++++++++ 4 files changed, 33 insertions(+), 10 deletions(-) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 312c1ea9aafa..58e744b78c2c 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -276,6 +276,7 @@ enum lru_list { enum vmscan_throttle_state { VMSCAN_THROTTLE_WRITEBACK, VMSCAN_THROTTLE_ISOLATED, + VMSCAN_THROTTLE_NOPROGRESS, NR_VMSCAN_THROTTLE, }; diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index d4905bd9e9c4..f25a6149d3ba 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -29,11 +29,13 @@ #define _VMSCAN_THROTTLE_WRITEBACK (1 << VMSCAN_THROTTLE_WRITEBACK) #define _VMSCAN_THROTTLE_ISOLATED (1 << VMSCAN_THROTTLE_ISOLATED) +#define _VMSCAN_THROTTLE_NOPROGRESS (1 << VMSCAN_THROTTLE_NOPROGRESS) #define show_throttle_flags(flags) \ (flags) ? __print_flags(flags, "|", \ {_VMSCAN_THROTTLE_WRITEBACK, "VMSCAN_THROTTLE_WRITEBACK"}, \ - {_VMSCAN_THROTTLE_ISOLATED, "VMSCAN_THROTTLE_ISOLATED"} \ + {_VMSCAN_THROTTLE_ISOLATED, "VMSCAN_THROTTLE_ISOLATED"}, \ + {_VMSCAN_THROTTLE_NOPROGRESS, "VMSCAN_THROTTLE_NOPROGRESS"} \ ) : "VMSCAN_THROTTLE_NONE" diff --git a/mm/memcontrol.c b/mm/memcontrol.c index cf0321d7a784..965b3cf7046b 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3487,19 +3487,11 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg) /* try to free all pages in this cgroup */ while (nr_retries && page_counter_read(&memcg->memory)) { - int progress; - if (signal_pending(current)) return -EINTR; - progress = try_to_free_mem_cgroup_pages(memcg, 1, - GFP_KERNEL, true); - if (!progress) { + if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, true)) nr_retries--; - /* maybe some writeback is necessary */ - congestion_wait(BLK_RW_ASYNC, HZ/10); - } - } return 0; diff --git a/mm/vmscan.c b/mm/vmscan.c index 7bfd62f81e16..7d3fe5938e3b 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3322,6 +3322,33 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) return zone_watermark_ok_safe(zone, 0, watermark, sc->reclaim_idx); } +static void consider_reclaim_throttle(pg_data_t *pgdat, struct scan_control *sc) +{ + /* If reclaim is making progress, wake any throttled tasks. */ + if (sc->nr_reclaimed) { + wait_queue_head_t *wqh; + + wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_NOPROGRESS]; + if (waitqueue_active(wqh)) + wake_up(wqh); + + return; + } + + /* + * Do not throttle kswapd on NOPROGRESS as it will throttle on + * VMSCAN_THROTTLE_WRITEBACK if there are too many pages under + * writeback and marked for immediate reclaim at the tail of + * the LRU. + */ + if (current_is_kswapd()) + return; + + /* Throttle if making no progress at high prioities. */ + if (sc->priority < DEF_PRIORITY - 2) + reclaim_throttle(pgdat, VMSCAN_THROTTLE_NOPROGRESS, HZ/10); +} + /* * This is the direct reclaim path, for page-allocating processes. We only * try to reclaim pages from zones which will satisfy the caller's allocation @@ -3406,6 +3433,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) continue; last_pgdat = zone->zone_pgdat; shrink_node(zone->zone_pgdat, sc); + consider_reclaim_throttle(zone->zone_pgdat, sc); } /* From 8d58802fc9de1b416601d90da794a3feaad1898d Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 5 Nov 2021 13:42:35 -0700 Subject: [PATCH 056/166] mm/writeback: throttle based on page writeback instead of congestion do_writepages throttles on congestion if the writepages() fails due to a lack of memory but congestion_wait() is partially broken as the congestion state is not updated for all BDIs. This patch stalls waiting for a number of pages to complete writeback that located on the local node. The main weakness is that there is no correlation between the location of the inode's pages and locality but that is still better than congestion_wait. Link: https://lkml.kernel.org/r/20211022144651.19914-5-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Andreas Dilger Cc: "Darrick J . Wong" Cc: Dave Chinner Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Michal Hocko Cc: NeilBrown Cc: Rik van Riel Cc: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page-writeback.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 4812a17b288c..f34f54fcd5b4 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2366,8 +2366,15 @@ int do_writepages(struct address_space *mapping, struct writeback_control *wbc) ret = generic_writepages(mapping, wbc); if ((ret != -ENOMEM) || (wbc->sync_mode != WB_SYNC_ALL)) break; - cond_resched(); - congestion_wait(BLK_RW_ASYNC, HZ/50); + + /* + * Lacking an allocation context or the locality or writeback + * state of any of the inode's pages, throttle based on + * writeback activity on the local node. It's as good a + * guess as any. + */ + reclaim_throttle(NODE_DATA(numa_node_id()), + VMSCAN_THROTTLE_WRITEBACK, HZ/50); } /* * Usually few pages are written by now from those we've just submitted From 132b0d21d21f14f74fbe44dd5b8b1848215fff09 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 5 Nov 2021 13:42:38 -0700 Subject: [PATCH 057/166] mm/page_alloc: remove the throttling logic from the page allocator The page allocator stalls based on the number of pages that are waiting for writeback to start but this should now be redundant. shrink_inactive_list() will wake flusher threads if the LRU tail are unqueued dirty pages so the flusher should be active. If it fails to make progress due to pages under writeback not being completed quickly then it should stall on VMSCAN_THROTTLE_WRITEBACK. Link: https://lkml.kernel.org/r/20211022144651.19914-6-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Andreas Dilger Cc: "Darrick J . Wong" Cc: Dave Chinner Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Michal Hocko Cc: NeilBrown Cc: Rik van Riel Cc: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 21 +-------------------- 1 file changed, 1 insertion(+), 20 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 0f1f1f353211..0f74a66bed19 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4791,30 +4791,11 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order, trace_reclaim_retry_zone(z, order, reclaimable, available, min_wmark, *no_progress_loops, wmark); if (wmark) { - /* - * If we didn't make any progress and have a lot of - * dirty + writeback pages then we should wait for - * an IO to complete to slow down the reclaim and - * prevent from pre mature OOM - */ - if (!did_some_progress) { - unsigned long write_pending; - - write_pending = zone_page_state_snapshot(zone, - NR_ZONE_WRITE_PENDING); - - if (2 * write_pending > reclaimable) { - congestion_wait(BLK_RW_ASYNC, HZ/10); - return true; - } - } - ret = true; - goto out; + break; } } -out: /* * Memory allocation/reclaim might be called from a WQ context and the * current implementation of the WQ concurrency control doesn't From c3f4a9a2b082c5392fbff17c6d8551154add5fdb Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 5 Nov 2021 13:42:42 -0700 Subject: [PATCH 058/166] mm/vmscan: centralise timeout values for reclaim_throttle Neil Brown raised concerns about callers of reclaim_throttle specifying a timeout value. The original timeout values to congestion_wait() were probably pulled out of thin air or copy&pasted from somewhere else. This patch centralises the timeout values and selects a timeout based on the reason for reclaim throttling. These figures are also pulled out of the same thin air but better values may be derived Running a workload that is throttling for inappropriate periods and tracing mm_vmscan_throttled can be used to pick a more appropriate value. Excessive throttling would pick a lower timeout where as excessive CPU usage in reclaim context would select a larger timeout. Ideally a large value would always be used and the wakeups would occur before a timeout but that requires careful testing. Link: https://lkml.kernel.org/r/20211022144651.19914-7-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Andreas Dilger Cc: "Darrick J . Wong" Cc: Dave Chinner Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Michal Hocko Cc: NeilBrown Cc: Rik van Riel Cc: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/compaction.c | 2 +- mm/internal.h | 3 +-- mm/page-writeback.c | 2 +- mm/vmscan.c | 50 +++++++++++++++++++++++++++++++++------------ 4 files changed, 40 insertions(+), 17 deletions(-) diff --git a/mm/compaction.c b/mm/compaction.c index 7359093d8ac0..151b04c4dab3 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -828,7 +828,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, if (cc->mode == MIGRATE_ASYNC) return -EAGAIN; - reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED, HZ/10); + reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED); if (fatal_signal_pending(current)) return -EINTR; diff --git a/mm/internal.h b/mm/internal.h index 7dfe74f827bf..f3de3a2f3e30 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -130,8 +130,7 @@ extern unsigned long highest_memmap_pfn; */ extern int isolate_lru_page(struct page *page); extern void putback_lru_page(struct page *page); -extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason, - long timeout); +extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason); /* * in mm/rmap.c: diff --git a/mm/page-writeback.c b/mm/page-writeback.c index f34f54fcd5b4..4b01a6872f9e 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2374,7 +2374,7 @@ int do_writepages(struct address_space *mapping, struct writeback_control *wbc) * guess as any. */ reclaim_throttle(NODE_DATA(numa_node_id()), - VMSCAN_THROTTLE_WRITEBACK, HZ/50); + VMSCAN_THROTTLE_WRITEBACK); } /* * Usually few pages are written by now from those we've just submitted diff --git a/mm/vmscan.c b/mm/vmscan.c index 7d3fe5938e3b..599e5616b123 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1006,12 +1006,10 @@ static void handle_write_error(struct address_space *mapping, unlock_page(page); } -void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason, - long timeout) +void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason) { wait_queue_head_t *wqh = &pgdat->reclaim_wait[reason]; - long ret; - bool acct_writeback = (reason == VMSCAN_THROTTLE_WRITEBACK); + long timeout, ret; DEFINE_WAIT(wait); /* @@ -1023,17 +1021,43 @@ void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason, current->flags & (PF_IO_WORKER|PF_KTHREAD)) return; - if (acct_writeback && - atomic_inc_return(&pgdat->nr_writeback_throttled) == 1) { - WRITE_ONCE(pgdat->nr_reclaim_start, - node_page_state(pgdat, NR_THROTTLED_WRITTEN)); + /* + * These figures are pulled out of thin air. + * VMSCAN_THROTTLE_ISOLATED is a transient condition based on too many + * parallel reclaimers which is a short-lived event so the timeout is + * short. Failing to make progress or waiting on writeback are + * potentially long-lived events so use a longer timeout. This is shaky + * logic as a failure to make progress could be due to anything from + * writeback to a slow device to excessive references pages at the tail + * of the inactive LRU. + */ + switch(reason) { + case VMSCAN_THROTTLE_WRITEBACK: + timeout = HZ/10; + + if (atomic_inc_return(&pgdat->nr_writeback_throttled) == 1) { + WRITE_ONCE(pgdat->nr_reclaim_start, + node_page_state(pgdat, NR_THROTTLED_WRITTEN)); + } + + break; + case VMSCAN_THROTTLE_NOPROGRESS: + timeout = HZ/10; + break; + case VMSCAN_THROTTLE_ISOLATED: + timeout = HZ/50; + break; + default: + WARN_ON_ONCE(1); + timeout = HZ; + break; } prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); ret = schedule_timeout(timeout); finish_wait(wqh, &wait); - if (acct_writeback) + if (reason == VMSCAN_THROTTLE_WRITEBACK) atomic_dec(&pgdat->nr_writeback_throttled); trace_mm_vmscan_throttled(pgdat->node_id, jiffies_to_usecs(timeout), @@ -2318,7 +2342,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, /* wait a bit for the reclaimer. */ stalled = true; - reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED, HZ/10); + reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED); /* We are about to die and free our memory. Return now. */ if (fatal_signal_pending(current)) @@ -3250,7 +3274,7 @@ again: * until some pages complete writeback. */ if (sc->nr.immediate) - reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK, HZ/10); + reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK); } /* @@ -3274,7 +3298,7 @@ again: if (!current_is_kswapd() && current_may_throttle() && !sc->hibernation_mode && test_bit(LRUVEC_CONGESTED, &target_lruvec->flags)) - reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK, HZ/10); + reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK); if (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed, sc)) @@ -3346,7 +3370,7 @@ static void consider_reclaim_throttle(pg_data_t *pgdat, struct scan_control *sc) /* Throttle if making no progress at high prioities. */ if (sc->priority < DEF_PRIORITY - 2) - reclaim_throttle(pgdat, VMSCAN_THROTTLE_NOPROGRESS, HZ/10); + reclaim_throttle(pgdat, VMSCAN_THROTTLE_NOPROGRESS); } /* From a19594ca4a8bfb5980de7bcc6ae6cbce8ff9680e Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 5 Nov 2021 13:42:45 -0700 Subject: [PATCH 059/166] mm/vmscan: increase the timeout if page reclaim is not making progress Tracing of the stutterp workload showed the following delays 1 usect_delayed=124000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usect_delayed=128000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usect_delayed=176000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usect_delayed=536000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usect_delayed=544000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usect_delayed=556000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usect_delayed=624000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usect_delayed=716000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usect_delayed=772000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usect_delayed=512000 reason=VMSCAN_THROTTLE_NOPROGRESS 16 usect_delayed=120000 reason=VMSCAN_THROTTLE_NOPROGRESS 53 usect_delayed=116000 reason=VMSCAN_THROTTLE_NOPROGRESS 116 usect_delayed=112000 reason=VMSCAN_THROTTLE_NOPROGRESS 5907 usect_delayed=108000 reason=VMSCAN_THROTTLE_NOPROGRESS 71741 usect_delayed=104000 reason=VMSCAN_THROTTLE_NOPROGRESS All the throttling hit the full timeout and then there was wakeup delays meaning that the wakeups are premature as no other reclaimer such as kswapd has made progress. This patch increases the maximum timeout. Link: https://lkml.kernel.org/r/20211022144651.19914-8-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Andreas Dilger Cc: "Darrick J . Wong" Cc: Dave Chinner Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Michal Hocko Cc: NeilBrown Cc: Rik van Riel Cc: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmscan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index 599e5616b123..9c125f793bf5 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1042,7 +1042,7 @@ void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason) break; case VMSCAN_THROTTLE_NOPROGRESS: - timeout = HZ/10; + timeout = HZ/2; break; case VMSCAN_THROTTLE_ISOLATED: timeout = HZ/50; From 66ce520bb7c22848bfdf3180d7e760a066dbcfbe Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 5 Nov 2021 13:42:49 -0700 Subject: [PATCH 060/166] mm/vmscan: delay waking of tasks throttled on NOPROGRESS Tracing indicates that tasks throttled on NOPROGRESS are woken prematurely resulting in occasional massive spikes in direct reclaim activity. This patch wakes tasks throttled on NOPROGRESS if reclaim efficiency is at least 12%. Link: https://lkml.kernel.org/r/20211022144651.19914-9-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Andreas Dilger Cc: "Darrick J . Wong" Cc: Dave Chinner Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Michal Hocko Cc: NeilBrown Cc: Rik van Riel Cc: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmscan.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index 9c125f793bf5..41f5f6007c30 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3348,8 +3348,11 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) static void consider_reclaim_throttle(pg_data_t *pgdat, struct scan_control *sc) { - /* If reclaim is making progress, wake any throttled tasks. */ - if (sc->nr_reclaimed) { + /* + * If reclaim is making progress greater than 12% efficiency then + * wake all the NOPROGRESS throttled tasks. + */ + if (sc->nr_reclaimed > (sc->nr_scanned >> 3)) { wait_queue_head_t *wqh; wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_NOPROGRESS]; From 7e6ec49c18988f1b8dab0677271dafde5f8d9a43 Mon Sep 17 00:00:00 2001 From: Yuanzheng Song Date: Fri, 5 Nov 2021 13:42:52 -0700 Subject: [PATCH 061/166] mm/vmpressure: fix data-race with memcg->socket_pressure When reading memcg->socket_pressure in mem_cgroup_under_socket_pressure() and writing memcg->socket_pressure in vmpressure() at the same time, the following data-race occurs: BUG: KCSAN: data-race in __sk_mem_reduce_allocated / vmpressure write to 0xffff8881286f4938 of 8 bytes by task 24550 on cpu 3: vmpressure+0x218/0x230 mm/vmpressure.c:307 shrink_node_memcgs+0x2b9/0x410 mm/vmscan.c:2658 shrink_node+0x9d2/0x11d0 mm/vmscan.c:2769 shrink_zones+0x29f/0x470 mm/vmscan.c:2972 do_try_to_free_pages+0x193/0x6e0 mm/vmscan.c:3027 try_to_free_mem_cgroup_pages+0x1c0/0x3f0 mm/vmscan.c:3345 reclaim_high mm/memcontrol.c:2440 [inline] mem_cgroup_handle_over_high+0x18b/0x4d0 mm/memcontrol.c:2624 tracehook_notify_resume include/linux/tracehook.h:197 [inline] exit_to_user_mode_loop kernel/entry/common.c:164 [inline] exit_to_user_mode_prepare+0x110/0x170 kernel/entry/common.c:191 syscall_exit_to_user_mode+0x16/0x30 kernel/entry/common.c:266 ret_from_fork+0x15/0x30 arch/x86/entry/entry_64.S:289 read to 0xffff8881286f4938 of 8 bytes by interrupt on cpu 1: mem_cgroup_under_socket_pressure include/linux/memcontrol.h:1483 [inline] sk_under_memory_pressure include/net/sock.h:1314 [inline] __sk_mem_reduce_allocated+0x1d2/0x270 net/core/sock.c:2696 __sk_mem_reclaim+0x44/0x50 net/core/sock.c:2711 sk_mem_reclaim include/net/sock.h:1490 [inline] ...... net_rx_action+0x17a/0x480 net/core/dev.c:6864 __do_softirq+0x12c/0x2af kernel/softirq.c:298 run_ksoftirqd+0x13/0x20 kernel/softirq.c:653 smpboot_thread_fn+0x33f/0x510 kernel/smpboot.c:165 kthread+0x1fc/0x220 kernel/kthread.c:292 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:296 Fix it by using READ_ONCE() and WRITE_ONCE() to read and write memcg->socket_pressure. Link: https://lkml.kernel.org/r/20211025082843.671690-1-songyuanzheng@huawei.com Signed-off-by: Yuanzheng Song Reviewed-by: Muchun Song Cc: Shakeel Butt Cc: Roman Gushchin Cc: Johannes Weiner Cc: Michal Hocko Cc: Matthew Wilcox (Oracle) Cc: Alex Shi Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 2 +- mm/vmpressure.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index f207f98bdb76..9d96238d9c21 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1606,7 +1606,7 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_pressure) return true; do { - if (time_before(jiffies, memcg->socket_pressure)) + if (time_before(jiffies, READ_ONCE(memcg->socket_pressure))) return true; } while ((memcg = parent_mem_cgroup(memcg))); return false; diff --git a/mm/vmpressure.c b/mm/vmpressure.c index 76518e4166dc..b52644771cc4 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -308,7 +308,7 @@ void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree, * asserted for a second in which subsequent * pressure events can occur. */ - memcg->socket_pressure = jiffies + HZ; + WRITE_ONCE(memcg->socket_pressure, jiffies + HZ); } } } From f7df2b1cf03af680354bd4300f48f7ea11316ce8 Mon Sep 17 00:00:00 2001 From: Zhenliang Wei Date: Fri, 5 Nov 2021 13:42:55 -0700 Subject: [PATCH 062/166] tools/vm/page_owner_sort.c: count and sort by mem When viewing page owner information, we may be more concerned about the total memory rather than the times of stack appears. Therefore, the following adjustments are made: 1. Added the statistics on the total number of pages. 2. Added the optional parameter "-m" to configure the program to sort by memory (total pages). The general output of page_owner is as follows: Page allocated via order XXX, ... PFN XXX ... // Detailed stack Page allocated via order XXX, ... PFN XXX ... // Detailed stack The original page_owner_sort ignores PFN rows, puts the remaining rows in buf, counts the times of buf, and finally sorts them according to the times. General output: XXX times: Page allocated via order XXX, ... // Detailed stack Now, we use regexp to extract the page order value from the buf, and count the total pages for the buf. General output: XXX times, XXX pages: Page allocated via order XXX, ... // Detailed stack By default, it is still sorted by the times of buf; If you want to sort by the pages nums of buf, use the new -m parameter. Link: https://lkml.kernel.org/r/1631678242-41033-1-git-send-email-weizhenliang@huawei.com Signed-off-by: Zhenliang Wei Cc: Tang Bin Cc: Zhang Shengju Cc: Zhenliang Wei Cc: Xiaoming Ni Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/vm/page_owner.rst | 23 +++++++- tools/vm/page_owner_sort.c | 96 +++++++++++++++++++++++++++++---- 2 files changed, 108 insertions(+), 11 deletions(-) diff --git a/Documentation/vm/page_owner.rst b/Documentation/vm/page_owner.rst index 2175465c9bf2..9837fc8147dd 100644 --- a/Documentation/vm/page_owner.rst +++ b/Documentation/vm/page_owner.rst @@ -85,5 +85,26 @@ Usage cat /sys/kernel/debug/page_owner > page_owner_full.txt ./page_owner_sort page_owner_full.txt sorted_page_owner.txt + The general output of ``page_owner_full.txt`` is as follows: + + Page allocated via order XXX, ... + PFN XXX ... + // Detailed stack + + Page allocated via order XXX, ... + PFN XXX ... + // Detailed stack + + The ``page_owner_sort`` tool ignores ``PFN`` rows, puts the remaining rows + in buf, uses regexp to extract the page order value, counts the times + and pages of buf, and finally sorts them according to the times. + See the result about who allocated each page - in the ``sorted_page_owner.txt``. + in the ``sorted_page_owner.txt``. General output: + + XXX times, XXX pages: + Page allocated via order XXX, ... + // Detailed stack + + By default, ``page_owner_sort`` is sorted according to the times of buf. + If you want to sort by the pages nums of buf, use the ``-m`` parameter. diff --git a/tools/vm/page_owner_sort.c b/tools/vm/page_owner_sort.c index 0e75f22c9475..9ebb84a9c731 100644 --- a/tools/vm/page_owner_sort.c +++ b/tools/vm/page_owner_sort.c @@ -5,6 +5,8 @@ * Example use: * cat /sys/kernel/debug/page_owner > page_owner_full.txt * ./page_owner_sort page_owner_full.txt sorted_page_owner.txt + * Or sort by total memory: + * ./page_owner_sort -m page_owner_full.txt sorted_page_owner.txt * * See Documentation/vm/page_owner.rst */ @@ -16,14 +18,18 @@ #include #include #include +#include +#include struct block_list { char *txt; int len; int num; + int page_num; }; - +static int sort_by_memory; +static regex_t order_pattern; static struct block_list *list; static int list_size; static int max_size; @@ -59,12 +65,50 @@ static int compare_num(const void *p1, const void *p2) return l2->num - l1->num; } +static int compare_page_num(const void *p1, const void *p2) +{ + const struct block_list *l1 = p1, *l2 = p2; + + return l2->page_num - l1->page_num; +} + +static int get_page_num(char *buf) +{ + int err, val_len, order_val; + char order_str[4] = {0}; + char *endptr; + regmatch_t pmatch[2]; + + err = regexec(&order_pattern, buf, 2, pmatch, REG_NOTBOL); + if (err != 0 || pmatch[1].rm_so == -1) { + printf("no order pattern in %s\n", buf); + return 0; + } + val_len = pmatch[1].rm_eo - pmatch[1].rm_so; + if (val_len > 2) /* max_order should not exceed 2 digits */ + goto wrong_order; + + memcpy(order_str, buf + pmatch[1].rm_so, val_len); + + errno = 0; + order_val = strtol(order_str, &endptr, 10); + if (errno != 0 || endptr == order_str || *endptr != '\0') + goto wrong_order; + + return 1 << order_val; + +wrong_order: + printf("wrong order in follow buf:\n%s\n", buf); + return 0; +} + static void add_list(char *buf, int len) { if (list_size != 0 && len == list[list_size-1].len && memcmp(buf, list[list_size-1].txt, len) == 0) { list[list_size-1].num++; + list[list_size-1].page_num += get_page_num(buf); return; } if (list_size == max_size) { @@ -74,6 +118,7 @@ static void add_list(char *buf, int len) list[list_size].txt = malloc(len+1); list[list_size].len = len; list[list_size].num = 1; + list[list_size].page_num = get_page_num(buf); memcpy(list[list_size].txt, buf, len); list[list_size].txt[len] = 0; list_size++; @@ -85,6 +130,13 @@ static void add_list(char *buf, int len) #define BUF_SIZE (128 * 1024) +static void usage(void) +{ + printf("Usage: ./page_owner_sort [-m] \n" + "-m Sort by total memory. If this option is unset, sort by times\n" + ); +} + int main(int argc, char **argv) { FILE *fin, *fout; @@ -92,18 +144,36 @@ int main(int argc, char **argv) int ret, i, count; struct block_list *list2; struct stat st; + int err; + int opt; - if (argc < 3) { - printf("Usage: ./program \n"); + while ((opt = getopt(argc, argv, "m")) != -1) + switch (opt) { + case 'm': + sort_by_memory = 1; + break; + default: + usage(); + exit(1); + } + + if (optind >= (argc - 1)) { + usage(); + exit(1); + } + + fin = fopen(argv[optind], "r"); + fout = fopen(argv[optind + 1], "w"); + if (!fin || !fout) { + usage(); perror("open: "); exit(1); } - fin = fopen(argv[1], "r"); - fout = fopen(argv[2], "w"); - if (!fin || !fout) { - printf("Usage: ./program \n"); - perror("open: "); + err = regcomp(&order_pattern, "order\\s*([0-9]*),", REG_EXTENDED|REG_NEWLINE); + if (err != 0 || order_pattern.re_nsub != 1) { + printf("%s: Invalid pattern 'order\\s*([0-9]*),' code %d\n", + argv[0], err); exit(1); } @@ -145,13 +215,19 @@ int main(int argc, char **argv) list2[count++] = list[i]; } else { list2[count-1].num += list[i].num; + list2[count-1].page_num += list[i].page_num; } } - qsort(list2, count, sizeof(list[0]), compare_num); + if (sort_by_memory) + qsort(list2, count, sizeof(list[0]), compare_page_num); + else + qsort(list2, count, sizeof(list[0]), compare_num); for (i = 0; i < count; i++) - fprintf(fout, "%d times:\n%s\n", list2[i].num, list2[i].txt); + fprintf(fout, "%d times, %d pages:\n%s\n", + list2[i].num, list2[i].page_num, list2[i].txt); + regfree(&order_pattern); return 0; } From a62f5ecbfb70645e1afa281202d989c68f050e0c Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 5 Nov 2021 13:42:58 -0700 Subject: [PATCH 063/166] tools/vm/page-types.c: make walk_file() aware of address range option Patch series "tools/vm/page-types.c: a few improvements". This patchset adds some improvements on tools/vm/page-types.c. Patch 1/3 makes -a option (specify address range) work with -f (file cache mode). Patch 2/3 and 3/3 are to fix minor formatting issues of this tool. These would make life a little easier for the users of this tool. Please see individual patches for more details about specific issues. This patch (of 3): -a|--addr option is used to limit the range of address to be scanned for page status. It works now for physical address space (dafult mode) or for virtual address space (with -p option), but not for file address space (with -f option). So make walk_file() aware of -a option. Link: https://lkml.kernel.org/r/20211004061325.1525902-1-naoya.horiguchi@linux.dev Link: https://lkml.kernel.org/r/20211004061325.1525902-2-naoya.horiguchi@linux.dev Signed-off-by: Naoya Horiguchi Cc: Konstantin Khlebnikov Cc: Christian Hansen Cc: Changbin Du Cc: Bin Wang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/vm/page-types.c | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c index f62f10c988db..b14376af1f16 100644 --- a/tools/vm/page-types.c +++ b/tools/vm/page-types.c @@ -967,22 +967,19 @@ static struct sigaction sigbus_action = { .sa_flags = SA_SIGINFO, }; -static void walk_file(const char *name, const struct stat *st) +static void walk_file_range(const char *name, int fd, + unsigned long off, unsigned long end) { uint8_t vec[PAGEMAP_BATCH]; uint64_t buf[PAGEMAP_BATCH], flags; uint64_t cgroup = 0; uint64_t mapcnt = 0; unsigned long nr_pages, pfn, i; - off_t off, end = st->st_size; - int fd; ssize_t len; void *ptr; int first = 1; - fd = checked_open(name, O_RDONLY|O_NOATIME|O_NOFOLLOW); - - for (off = 0; off < end; off += len) { + for (; off < end; off += len) { nr_pages = (end - off + page_size - 1) / page_size; if (nr_pages > PAGEMAP_BATCH) nr_pages = PAGEMAP_BATCH; @@ -1043,6 +1040,21 @@ got_sigbus: flags, cgroup, mapcnt, buf[i]); } } +} + +static void walk_file(const char *name, const struct stat *st) +{ + int i; + int fd; + + fd = checked_open(name, O_RDONLY|O_NOATIME|O_NOFOLLOW); + + if (!nr_addr_ranges) + add_addr_range(0, st->st_size / page_size); + + for (i = 0; i < nr_addr_ranges; i++) + walk_file_range(name, fd, opt_offset[i] * page_size, + (opt_offset[i] + opt_size[i]) * page_size); close(fd); } From b76901db7b3d28a1ca6f8690642187c56cb50018 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 5 Nov 2021 13:43:01 -0700 Subject: [PATCH 064/166] tools/vm/page-types.c: move show_file() to summary output Currently file info from show_file() is printed out within page list like below, but this is inconvenient a little to utilize the page list from other scripts (maybe needs additional filtering). $ ./page-types -f page-types.c -l foffset offset len flags page-types.c Inode: 15108680 Size: 30953 (8 pages) Modify: Sat Oct 2 23:11:20 2021 (2399 seconds ago) Access: Sat Oct 2 23:11:28 2021 (2391 seconds ago) 0 d9f59e 1 ___U_lA____________________________________ 1 1031eb5 1 __RU_l_____________________________________ 2 13bf717 1 __RU_l_____________________________________ 3 13ac333 1 ___U_lA____________________________________ 4 d9f59f 1 __RU_l_____________________________________ 5 183fd49 1 ___U_lA____________________________________ 6 13cbf69 1 ___U_lA____________________________________ 7 d9ef05 1 ___U_lA____________________________________ flags page-count MB symbolic-flags long-symbolic-flags 0x000000000000002c 3 0 __RU_l_____________________________________ referenced,uptodate,lru 0x0000000000000068 5 0 ___U_lA____________________________________ uptodate,lru,active total 8 0 With this patch file info is printed out in summary part like below: $ ./page-types -f page-types.c -l foffset offset len flags 0 d9f59e 1 ___U_lA_____________________________________ 1 1031eb5 1 __RU_l______________________________________ 2 13bf717 1 __RU_l______________________________________ 3 13ac333 1 ___U_lA_____________________________________ 4 d9f59f 1 __RU_l______________________________________ 5 183fd49 1 ___U_lA_____________________________________ 6 13cbf69 1 ___U_lA_____________________________________ page-types.c Inode: 15108680 Size: 30953 (8 pages) Modify: Sat Oct 2 23:11:20 2021 (2435 seconds ago) Access: Sat Oct 2 23:11:28 2021 (2427 seconds ago) flags page-count MB symbolic-flags long-symbolic-flags 0x000000000000002c 3 0 __RU_l______________________________________ referenced,uptodate,lru 0x0000000000000068 4 0 ___U_lA_____________________________________ uptodate,lru,active total 7 0 Link: https://lkml.kernel.org/r/20211004061325.1525902-3-naoya.horiguchi@linux.dev Signed-off-by: Naoya Horiguchi Cc: Bin Wang Cc: Changbin Du Cc: Christian Hansen Cc: Konstantin Khlebnikov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/vm/page-types.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c index b14376af1f16..fdb1891faf90 100644 --- a/tools/vm/page-types.c +++ b/tools/vm/page-types.c @@ -1034,7 +1034,6 @@ got_sigbus: if (first && opt_list) { first = 0; flush_page_range(); - show_file(name, st); } add_page(off / page_size + i, pfn, flags, cgroup, mapcnt, buf[i]); @@ -1074,10 +1073,10 @@ int walk_tree(const char *name, const struct stat *st, int type, struct FTW *f) return 0; } +struct stat st; + static void walk_page_cache(void) { - struct stat st; - kpageflags_fd = checked_open(opt_kpageflags, O_RDONLY); pagemap_fd = checked_open("/proc/self/pagemap", O_RDONLY); sigaction(SIGBUS, &sigbus_action, NULL); @@ -1374,6 +1373,11 @@ int main(int argc, char *argv[]) if (opt_list) printf("\n\n"); + if (opt_file) { + show_file(opt_file, &st); + printf("\n"); + } + show_summary(); if (opt_list_mapcnt) From 41d4613b378cc10c087d8af621ace891d96d0907 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 5 Nov 2021 13:43:04 -0700 Subject: [PATCH 065/166] tools/vm/page-types.c: print file offset in hexadecimal In page list mode (with -l and -L option), virtual address and physical address are printed in hexadecimal, but file offset is not, which is confusing, so let's align it. Link: https://lkml.kernel.org/r/20211004061325.1525902-4-naoya.horiguchi@linux.dev Signed-off-by: Naoya Horiguchi Cc: Bin Wang Cc: Changbin Du Cc: Christian Hansen Cc: Konstantin Khlebnikov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/vm/page-types.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c index fdb1891faf90..b1ed76d9a979 100644 --- a/tools/vm/page-types.c +++ b/tools/vm/page-types.c @@ -390,7 +390,7 @@ static void show_page_range(unsigned long voffset, unsigned long offset, if (opt_pid) printf("%lx\t", voff); if (opt_file) - printf("%lu\t", voff); + printf("%lx\t", voff); if (opt_list_cgroup) printf("@%llu\t", (unsigned long long)cgroup0); if (opt_list_mapcnt) @@ -418,7 +418,7 @@ static void show_page(unsigned long voffset, unsigned long offset, if (opt_pid) printf("%lx\t", voffset); if (opt_file) - printf("%lu\t", voffset); + printf("%lx\t", voffset); if (opt_list_cgroup) printf("@%llu\t", (unsigned long long)cgroup); if (opt_list_mapcnt) From 5787ea5bed7607cbee26da492e574f94975e4d76 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Fri, 5 Nov 2021 13:43:07 -0700 Subject: [PATCH 066/166] arch_numa: simplify numa_distance allocation Patch series "memblock: cleanup memblock_free interface", v2. This is the fix for memblock freeing APIs mismatch [1]. The first patch is a cleanup of numa_distance allocation in arch_numa I've spotted during the conversion. The second patch is a fix for Xen memory freeing on some of the error paths. [1] https://lore.kernel.org/all/CAHk-=wj9k4LZTz+svCxLYs5Y1=+yKrbAUArH1+ghyG3OLd8VVg@mail.gmail.com This patch (of 6): Memory allocation of numa_distance uses memblock_phys_alloc_range() without actual range limits, converts the returned physical address to virtual and then only uses the virtual address for further initialization. Simplify this by replacing memblock_phys_alloc_range() with memblock_alloc(). Link: https://lkml.kernel.org/r/20210930185031.18648-1-rppt@kernel.org Link: https://lkml.kernel.org/r/20210930185031.18648-2-rppt@kernel.org Signed-off-by: Mike Rapoport Cc: Christophe Leroy Cc: Juergen Gross Cc: Shahab Vahedi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/arch_numa.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c index 28222688ace7..a6491673dc1f 100644 --- a/drivers/base/arch_numa.c +++ b/drivers/base/arch_numa.c @@ -337,15 +337,13 @@ void __init numa_free_distance(void) static int __init numa_alloc_distance(void) { size_t size; - u64 phys; int i, j; size = nr_node_ids * nr_node_ids * sizeof(numa_distance[0]); - phys = memblock_phys_alloc_range(size, PAGE_SIZE, 0, PFN_PHYS(max_pfn)); - if (WARN_ON(!phys)) + numa_distance = memblock_alloc(size, PAGE_SIZE); + if (WARN_ON(!numa_distance)) return -ENOMEM; - numa_distance = __va(phys); numa_distance_cnt = nr_node_ids; /* fill with the default distances */ From c486514dd40980b2dbb0e15fabddfe1324ed0197 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Fri, 5 Nov 2021 13:43:10 -0700 Subject: [PATCH 067/166] xen/x86: free_p2m_page: use memblock_free_ptr() to free a virtual pointer free_p2m_page() wrongly passes a virtual pointer to memblock_free() that treats it as a physical address. Call memblock_free_ptr() instead that gets a virtual address to free the memory. Link: https://lkml.kernel.org/r/20210930185031.18648-3-rppt@kernel.org Signed-off-by: Mike Rapoport Reviewed-by: Juergen Gross Cc: Christophe Leroy Cc: Shahab Vahedi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/xen/p2m.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 5e6e236977c7..141bb9dbd2fb 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -197,7 +197,7 @@ static void * __ref alloc_p2m_page(void) static void __ref free_p2m_page(void *p) { if (unlikely(!slab_is_available())) { - memblock_free((unsigned long)p, PAGE_SIZE); + memblock_free_ptr(p, PAGE_SIZE); return; } From fa27717110ae51b9b9013ced0b5143888257bb79 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Fri, 5 Nov 2021 13:43:13 -0700 Subject: [PATCH 068/166] memblock: drop memblock_free_early_nid() and memblock_free_early() memblock_free_early_nid() is unused and memblock_free_early() is an alias for memblock_free(). Replace calls to memblock_free_early() with calls to memblock_free() and remove memblock_free_early() and memblock_free_early_nid(). Link: https://lkml.kernel.org/r/20210930185031.18648-4-rppt@kernel.org Signed-off-by: Mike Rapoport Cc: Christophe Leroy Cc: Juergen Gross Cc: Shahab Vahedi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/mips/mm/init.c | 2 +- arch/powerpc/platforms/pseries/svm.c | 3 +-- arch/s390/kernel/smp.c | 2 +- drivers/base/arch_numa.c | 2 +- drivers/s390/char/sclp_early.c | 2 +- include/linux/memblock.h | 12 ------------ kernel/dma/swiotlb.c | 2 +- lib/cpumask.c | 2 +- mm/percpu.c | 8 ++++---- mm/sparse.c | 2 +- 10 files changed, 12 insertions(+), 25 deletions(-) diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 19347dc6bbf8..21a5a7ac0037 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -529,7 +529,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, static void __init pcpu_fc_free(void *ptr, size_t size) { - memblock_free_early(__pa(ptr), size); + memblock_free(__pa(ptr), size); } void __init setup_per_cpu_areas(void) diff --git a/arch/powerpc/platforms/pseries/svm.c b/arch/powerpc/platforms/pseries/svm.c index 87f001b4c4e4..f12229ce7301 100644 --- a/arch/powerpc/platforms/pseries/svm.c +++ b/arch/powerpc/platforms/pseries/svm.c @@ -56,8 +56,7 @@ void __init svm_swiotlb_init(void) return; - memblock_free_early(__pa(vstart), - PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); + memblock_free(__pa(vstart), PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); panic("SVM: Cannot allocate SWIOTLB buffer"); } diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 1a04e5bdf655..066efd6d9345 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -880,7 +880,7 @@ void __init smp_detect_cpus(void) /* Add CPUs present at boot */ __smp_rescan_cpus(info, true); - memblock_free_early((unsigned long)info, sizeof(*info)); + memblock_free((unsigned long)info, sizeof(*info)); } /* diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c index a6491673dc1f..ade8934764f6 100644 --- a/drivers/base/arch_numa.c +++ b/drivers/base/arch_numa.c @@ -166,7 +166,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, static void __init pcpu_fc_free(void *ptr, size_t size) { - memblock_free_early(__pa(ptr), size); + memblock_free(__pa(ptr), size); } #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK diff --git a/drivers/s390/char/sclp_early.c b/drivers/s390/char/sclp_early.c index f3d5c7f4c13d..f01d942e1c1d 100644 --- a/drivers/s390/char/sclp_early.c +++ b/drivers/s390/char/sclp_early.c @@ -139,7 +139,7 @@ int __init sclp_early_get_core_info(struct sclp_core_info *info) } sclp_fill_core_info(info, sccb); out: - memblock_free_early((unsigned long)sccb, length); + memblock_free((unsigned long)sccb, length); return rc; } diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 34de69b3b8ba..fc8183be340c 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -441,18 +441,6 @@ static inline void *memblock_alloc_node(phys_addr_t size, MEMBLOCK_ALLOC_ACCESSIBLE, nid); } -static inline void memblock_free_early(phys_addr_t base, - phys_addr_t size) -{ - memblock_free(base, size); -} - -static inline void memblock_free_early_nid(phys_addr_t base, - phys_addr_t size, int nid) -{ - memblock_free(base, size); -} - static inline void memblock_free_late(phys_addr_t base, phys_addr_t size) { __memblock_free_late(base, size); diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 87c40517e822..430d2f78d540 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -247,7 +247,7 @@ swiotlb_init(int verbose) return; fail_free_mem: - memblock_free_early(__pa(tlb), bytes); + memblock_free(__pa(tlb), bytes); fail: pr_warn("Cannot allocate buffer"); } diff --git a/lib/cpumask.c b/lib/cpumask.c index c3c76b833384..045779446a18 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -188,7 +188,7 @@ EXPORT_SYMBOL(free_cpumask_var); */ void __init free_bootmem_cpumask_var(cpumask_var_t mask) { - memblock_free_early(__pa(mask), cpumask_size()); + memblock_free(__pa(mask), cpumask_size()); } #endif diff --git a/mm/percpu.c b/mm/percpu.c index e0a986818903..f58318cb04c0 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -2472,7 +2472,7 @@ struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, */ void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai) { - memblock_free_early(__pa(ai), ai->__ai_size); + memblock_free(__pa(ai), ai->__ai_size); } /** @@ -3134,7 +3134,7 @@ out_free_areas: out_free: pcpu_free_alloc_info(ai); if (areas) - memblock_free_early(__pa(areas), areas_size); + memblock_free(__pa(areas), areas_size); return rc; } #endif /* BUILD_EMBED_FIRST_CHUNK */ @@ -3256,7 +3256,7 @@ enomem: free_fn(page_address(pages[j]), PAGE_SIZE); rc = -ENOMEM; out_free_ar: - memblock_free_early(__pa(pages), pages_size); + memblock_free(__pa(pages), pages_size); pcpu_free_alloc_info(ai); return rc; } @@ -3286,7 +3286,7 @@ static void * __init pcpu_dfl_fc_alloc(unsigned int cpu, size_t size, static void __init pcpu_dfl_fc_free(void *ptr, size_t size) { - memblock_free_early(__pa(ptr), size); + memblock_free(__pa(ptr), size); } void __init setup_per_cpu_areas(void) diff --git a/mm/sparse.c b/mm/sparse.c index 120bc8ea5293..55fea0c2f927 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -451,7 +451,7 @@ static void *sparsemap_buf_end __meminitdata; static inline void __meminit sparse_buffer_free(unsigned long size) { WARN_ON(!sparsemap_buf || size == 0); - memblock_free_early(__pa(sparsemap_buf), size); + memblock_free(__pa(sparsemap_buf), size); } static void __init sparse_buffer_init(unsigned long size, int nid) From 621d973901cf9fa6c6e31b31bdd36c5c5f3c9c9e Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Fri, 5 Nov 2021 13:43:16 -0700 Subject: [PATCH 069/166] memblock: stop aliasing __memblock_free_late with memblock_free_late memblock_free_late() is a NOP wrapper for __memblock_free_late(), there is no point to keep this indirection. Drop the wrapper and rename __memblock_free_late() to memblock_free_late(). Link: https://lkml.kernel.org/r/20210930185031.18648-5-rppt@kernel.org Signed-off-by: Mike Rapoport Cc: Christophe Leroy Cc: Juergen Gross Cc: Shahab Vahedi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 7 +------ mm/memblock.c | 8 ++++---- 2 files changed, 5 insertions(+), 10 deletions(-) diff --git a/include/linux/memblock.h b/include/linux/memblock.h index fc8183be340c..e25f964fdd60 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -133,7 +133,7 @@ void __next_mem_range_rev(u64 *idx, int nid, enum memblock_flags flags, struct memblock_type *type_b, phys_addr_t *out_start, phys_addr_t *out_end, int *out_nid); -void __memblock_free_late(phys_addr_t base, phys_addr_t size); +void memblock_free_late(phys_addr_t base, phys_addr_t size); #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP static inline void __next_physmem_range(u64 *idx, struct memblock_type *type, @@ -441,11 +441,6 @@ static inline void *memblock_alloc_node(phys_addr_t size, MEMBLOCK_ALLOC_ACCESSIBLE, nid); } -static inline void memblock_free_late(phys_addr_t base, phys_addr_t size) -{ - __memblock_free_late(base, size); -} - /* * Set the allocation direction to bottom-up or top-down. */ diff --git a/mm/memblock.c b/mm/memblock.c index 5096500b2647..849060013d3c 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -366,14 +366,14 @@ void __init memblock_discard(void) addr = __pa(memblock.reserved.regions); size = PAGE_ALIGN(sizeof(struct memblock_region) * memblock.reserved.max); - __memblock_free_late(addr, size); + memblock_free_late(addr, size); } if (memblock.memory.regions != memblock_memory_init_regions) { addr = __pa(memblock.memory.regions); size = PAGE_ALIGN(sizeof(struct memblock_region) * memblock.memory.max); - __memblock_free_late(addr, size); + memblock_free_late(addr, size); } memblock_memory = NULL; @@ -1589,7 +1589,7 @@ void * __init memblock_alloc_try_nid( } /** - * __memblock_free_late - free pages directly to buddy allocator + * memblock_free_late - free pages directly to buddy allocator * @base: phys starting address of the boot memory block * @size: size of the boot memory block in bytes * @@ -1597,7 +1597,7 @@ void * __init memblock_alloc_try_nid( * down, but we are still initializing the system. Pages are released directly * to the buddy allocator. */ -void __init __memblock_free_late(phys_addr_t base, phys_addr_t size) +void __init memblock_free_late(phys_addr_t base, phys_addr_t size) { phys_addr_t cursor, end; From 3ecc68349bbab6bff1d12cbc7951ca6019b2faf6 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Fri, 5 Nov 2021 13:43:19 -0700 Subject: [PATCH 070/166] memblock: rename memblock_free to memblock_phys_free Since memblock_free() operates on a physical range, make its name reflect it and rename it to memblock_phys_free(), so it will be a logical counterpart to memblock_phys_alloc(). The callers are updated with the below semantic patch: @@ expression addr; expression size; @@ - memblock_free(addr, size); + memblock_phys_free(addr, size); Link: https://lkml.kernel.org/r/20210930185031.18648-6-rppt@kernel.org Signed-off-by: Mike Rapoport Cc: Christophe Leroy Cc: Juergen Gross Cc: Shahab Vahedi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/kernel/core_irongate.c | 3 ++- arch/arc/mm/init.c | 2 +- arch/arm/mach-hisi/platmcpm.c | 2 +- arch/arm/mm/init.c | 2 +- arch/arm64/mm/mmu.c | 4 ++-- arch/mips/mm/init.c | 2 +- arch/mips/sgi-ip30/ip30-setup.c | 6 +++--- arch/powerpc/kernel/dt_cpu_ftrs.c | 4 ++-- arch/powerpc/kernel/paca.c | 8 ++++---- arch/powerpc/kernel/setup-common.c | 2 +- arch/powerpc/kernel/setup_64.c | 2 +- arch/powerpc/platforms/powernv/pci-ioda.c | 2 +- arch/powerpc/platforms/pseries/svm.c | 3 ++- arch/riscv/kernel/setup.c | 5 +++-- arch/s390/kernel/setup.c | 8 ++++---- arch/s390/kernel/smp.c | 4 ++-- arch/s390/kernel/uv.c | 2 +- arch/s390/mm/kasan_init.c | 2 +- arch/sh/boards/mach-ap325rxa/setup.c | 2 +- arch/sh/boards/mach-ecovec24/setup.c | 4 ++-- arch/sh/boards/mach-kfr2r09/setup.c | 2 +- arch/sh/boards/mach-migor/setup.c | 2 +- arch/sh/boards/mach-se/7724/setup.c | 4 ++-- arch/sparc/kernel/smp_64.c | 2 +- arch/um/kernel/mem.c | 2 +- arch/x86/kernel/setup.c | 4 ++-- arch/x86/mm/init.c | 2 +- arch/x86/xen/mmu_pv.c | 6 +++--- arch/x86/xen/setup.c | 6 +++--- drivers/base/arch_numa.c | 2 +- drivers/firmware/efi/memmap.c | 2 +- drivers/of/kexec.c | 3 +-- drivers/of/of_reserved_mem.c | 5 +++-- drivers/s390/char/sclp_early.c | 2 +- drivers/usb/early/xhci-dbc.c | 10 +++++----- drivers/xen/swiotlb-xen.c | 2 +- include/linux/memblock.h | 2 +- init/initramfs.c | 2 +- kernel/dma/swiotlb.c | 2 +- lib/cpumask.c | 2 +- mm/cma.c | 2 +- mm/memblock.c | 8 ++++---- mm/memory_hotplug.c | 2 +- mm/percpu.c | 8 ++++---- mm/sparse.c | 2 +- 45 files changed, 79 insertions(+), 76 deletions(-) diff --git a/arch/alpha/kernel/core_irongate.c b/arch/alpha/kernel/core_irongate.c index 72af1e72d833..ee26dcc49418 100644 --- a/arch/alpha/kernel/core_irongate.c +++ b/arch/alpha/kernel/core_irongate.c @@ -233,7 +233,8 @@ albacore_init_arch(void) unsigned long size; size = initrd_end - initrd_start; - memblock_free(__pa(initrd_start), PAGE_ALIGN(size)); + memblock_phys_free(__pa(initrd_start), + PAGE_ALIGN(size)); if (!move_initrd(pci_mem)) printk("irongate_init_arch: initrd too big " "(%ldK)\ndisabling initrd\n", diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index 699ecf119641..59408f6a02d4 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -173,7 +173,7 @@ static void __init highmem_init(void) #ifdef CONFIG_HIGHMEM unsigned long tmp; - memblock_free(high_mem_start, high_mem_sz); + memblock_phys_free(high_mem_start, high_mem_sz); for (tmp = min_high_pfn; tmp < max_high_pfn; tmp++) free_highmem_page(pfn_to_page(tmp)); #endif diff --git a/arch/arm/mach-hisi/platmcpm.c b/arch/arm/mach-hisi/platmcpm.c index 96a484095194..258586e31333 100644 --- a/arch/arm/mach-hisi/platmcpm.c +++ b/arch/arm/mach-hisi/platmcpm.c @@ -339,7 +339,7 @@ err_fabric: err_sysctrl: iounmap(relocation); err_reloc: - memblock_free(hip04_boot_method[0], hip04_boot_method[1]); + memblock_phys_free(hip04_boot_method[0], hip04_boot_method[1]); err: return ret; } diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 6162a070a410..6d0cb0f7bc54 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -158,7 +158,7 @@ phys_addr_t __init arm_memblock_steal(phys_addr_t size, phys_addr_t align) panic("Failed to steal %pa bytes at %pS\n", &size, (void *)_RET_IP_); - memblock_free(phys, size); + memblock_phys_free(phys, size); memblock_remove(phys, size); return phys; diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index cfd9deb347c3..f68c2d953617 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -738,8 +738,8 @@ void __init paging_init(void) cpu_replace_ttbr1(lm_alias(swapper_pg_dir)); init_mm.pgd = swapper_pg_dir; - memblock_free(__pa_symbol(init_pg_dir), - __pa_symbol(init_pg_end) - __pa_symbol(init_pg_dir)); + memblock_phys_free(__pa_symbol(init_pg_dir), + __pa_symbol(init_pg_end) - __pa_symbol(init_pg_dir)); memblock_allow_resize(); } diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 21a5a7ac0037..3be1c29084fa 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -529,7 +529,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, static void __init pcpu_fc_free(void *ptr, size_t size) { - memblock_free(__pa(ptr), size); + memblock_phys_free(__pa(ptr), size); } void __init setup_per_cpu_areas(void) diff --git a/arch/mips/sgi-ip30/ip30-setup.c b/arch/mips/sgi-ip30/ip30-setup.c index 44b1607e964d..75a34684e704 100644 --- a/arch/mips/sgi-ip30/ip30-setup.c +++ b/arch/mips/sgi-ip30/ip30-setup.c @@ -69,10 +69,10 @@ static void __init ip30_mem_init(void) total_mem += size; if (addr >= IP30_REAL_MEMORY_START) - memblock_free(addr, size); + memblock_phys_free(addr, size); else if ((addr + size) > IP30_REAL_MEMORY_START) - memblock_free(IP30_REAL_MEMORY_START, - size - IP30_MAX_PROM_MEMORY); + memblock_phys_free(IP30_REAL_MEMORY_START, + size - IP30_MAX_PROM_MEMORY); } pr_info("Detected %luMB of physical memory.\n", MEM_SHIFT(total_mem)); } diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 358aee7c2d79..42839d6bd486 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -1095,8 +1095,8 @@ static int __init dt_cpu_ftrs_scan_callback(unsigned long node, const char cpufeatures_setup_finished(); - memblock_free(__pa(dt_cpu_features), - sizeof(struct dt_cpu_feature)*nr_dt_cpu_features); + memblock_phys_free(__pa(dt_cpu_features), + sizeof(struct dt_cpu_feature) * nr_dt_cpu_features); return 0; } diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 9bd30cac852b..4208b4044d12 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -322,8 +322,8 @@ void __init free_unused_pacas(void) new_ptrs_size = sizeof(struct paca_struct *) * nr_cpu_ids; if (new_ptrs_size < paca_ptrs_size) - memblock_free(__pa(paca_ptrs) + new_ptrs_size, - paca_ptrs_size - new_ptrs_size); + memblock_phys_free(__pa(paca_ptrs) + new_ptrs_size, + paca_ptrs_size - new_ptrs_size); paca_nr_cpu_ids = nr_cpu_ids; paca_ptrs_size = new_ptrs_size; @@ -331,8 +331,8 @@ void __init free_unused_pacas(void) #ifdef CONFIG_PPC_BOOK3S_64 if (early_radix_enabled()) { /* Ugly fixup, see new_slb_shadow() */ - memblock_free(__pa(paca_ptrs[boot_cpuid]->slb_shadow_ptr), - sizeof(struct slb_shadow)); + memblock_phys_free(__pa(paca_ptrs[boot_cpuid]->slb_shadow_ptr), + sizeof(struct slb_shadow)); paca_ptrs[boot_cpuid]->slb_shadow_ptr = NULL; } #endif diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index b1e43b69a559..5af8993a8e6d 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -825,7 +825,7 @@ static void __init smp_setup_pacas(void) set_hard_smp_processor_id(cpu, cpu_to_phys_id[cpu]); } - memblock_free(__pa(cpu_to_phys_id), nr_cpu_ids * sizeof(u32)); + memblock_phys_free(__pa(cpu_to_phys_id), nr_cpu_ids * sizeof(u32)); cpu_to_phys_id = NULL; } #endif diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index eaa79a0996d1..75bc294ac40d 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -812,7 +812,7 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size, static void __init pcpu_free_bootmem(void *ptr, size_t size) { - memblock_free(__pa(ptr), size); + memblock_phys_free(__pa(ptr), size); } static int pcpu_cpu_distance(unsigned int from, unsigned int to) diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 3dd35c327d1c..b5a9d343b720 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -2981,7 +2981,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, if (!phb->hose) { pr_err(" Can't allocate PCI controller for %pOF\n", np); - memblock_free(__pa(phb), sizeof(struct pnv_phb)); + memblock_phys_free(__pa(phb), sizeof(struct pnv_phb)); return; } diff --git a/arch/powerpc/platforms/pseries/svm.c b/arch/powerpc/platforms/pseries/svm.c index f12229ce7301..b7c017bb40f7 100644 --- a/arch/powerpc/platforms/pseries/svm.c +++ b/arch/powerpc/platforms/pseries/svm.c @@ -56,7 +56,8 @@ void __init svm_swiotlb_init(void) return; - memblock_free(__pa(vstart), PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); + memblock_phys_free(__pa(vstart), + PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); panic("SVM: Cannot allocate SWIOTLB buffer"); } diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index b9620e5f00ba..6ea7c53b82cd 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -230,13 +230,14 @@ static void __init init_resources(void) /* Clean-up any unused pre-allocated resources */ if (res_idx >= 0) - memblock_free(__pa(mem_res), (res_idx + 1) * sizeof(*mem_res)); + memblock_phys_free(__pa(mem_res), + (res_idx + 1) * sizeof(*mem_res)); return; error: /* Better an empty resource tree than an inconsistent one */ release_child_resources(&iomem_resource); - memblock_free(__pa(mem_res), mem_res_sz); + memblock_phys_free(__pa(mem_res), mem_res_sz); } diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 67e5fff96ee0..7fc836e9e194 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -693,7 +693,7 @@ static void __init reserve_crashkernel(void) } if (register_memory_notifier(&kdump_mem_nb)) { - memblock_free(crash_base, crash_size); + memblock_phys_free(crash_base, crash_size); return; } @@ -748,7 +748,7 @@ static void __init free_mem_detect_info(void) get_mem_detect_reserved(&start, &size); if (size) - memblock_free(start, size); + memblock_phys_free(start, size); } static const char * __init get_mem_info_source(void) @@ -793,7 +793,7 @@ static void __init check_initrd(void) if (initrd_data.start && initrd_data.size && !memblock_is_region_memory(initrd_data.start, initrd_data.size)) { pr_err("The initial RAM disk does not fit into the memory\n"); - memblock_free(initrd_data.start, initrd_data.size); + memblock_phys_free(initrd_data.start, initrd_data.size); initrd_start = initrd_end = 0; } #endif @@ -890,7 +890,7 @@ static void __init setup_randomness(void) if (stsi(vmms, 3, 2, 2) == 0 && vmms->count) add_device_randomness(&vmms->vm, sizeof(vmms->vm[0]) * vmms->count); - memblock_free((unsigned long) vmms, PAGE_SIZE); + memblock_phys_free((unsigned long)vmms, PAGE_SIZE); } /* diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 066efd6d9345..78a8ea6fd582 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -723,7 +723,7 @@ void __init smp_save_dump_cpus(void) /* Get the CPU registers */ smp_save_cpu_regs(sa, addr, is_boot_cpu, page); } - memblock_free(page, PAGE_SIZE); + memblock_phys_free(page, PAGE_SIZE); diag_amode31_ops.diag308_reset(); pcpu_set_smt(0); } @@ -880,7 +880,7 @@ void __init smp_detect_cpus(void) /* Add CPUs present at boot */ __smp_rescan_cpus(info, true); - memblock_free((unsigned long)info, sizeof(*info)); + memblock_phys_free((unsigned long)info, sizeof(*info)); } /* diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index 5a656c7b7a67..d57457b16fe5 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -64,7 +64,7 @@ void __init setup_uv(void) } if (uv_init(uv_stor_base, uv_info.uv_base_stor_len)) { - memblock_free(uv_stor_base, uv_info.uv_base_stor_len); + memblock_phys_free(uv_stor_base, uv_info.uv_base_stor_len); goto fail; } diff --git a/arch/s390/mm/kasan_init.c b/arch/s390/mm/kasan_init.c index 3e4735168019..483b9dbe0970 100644 --- a/arch/s390/mm/kasan_init.c +++ b/arch/s390/mm/kasan_init.c @@ -399,5 +399,5 @@ void __init kasan_copy_shadow_mapping(void) void __init kasan_free_early_identity(void) { - memblock_free(pgalloc_pos, pgalloc_freeable - pgalloc_pos); + memblock_phys_free(pgalloc_pos, pgalloc_freeable - pgalloc_pos); } diff --git a/arch/sh/boards/mach-ap325rxa/setup.c b/arch/sh/boards/mach-ap325rxa/setup.c index bac8a058ebd7..c77b5f00a66a 100644 --- a/arch/sh/boards/mach-ap325rxa/setup.c +++ b/arch/sh/boards/mach-ap325rxa/setup.c @@ -560,7 +560,7 @@ static void __init ap325rxa_mv_mem_reserve(void) if (!phys) panic("Failed to allocate CEU memory\n"); - memblock_free(phys, size); + memblock_phys_free(phys, size); memblock_remove(phys, size); ceu_dma_membase = phys; diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c index bab91a99124e..2b22ce792147 100644 --- a/arch/sh/boards/mach-ecovec24/setup.c +++ b/arch/sh/boards/mach-ecovec24/setup.c @@ -1502,7 +1502,7 @@ static void __init ecovec_mv_mem_reserve(void) if (!phys) panic("Failed to allocate CEU0 memory\n"); - memblock_free(phys, size); + memblock_phys_free(phys, size); memblock_remove(phys, size); ceu0_dma_membase = phys; @@ -1510,7 +1510,7 @@ static void __init ecovec_mv_mem_reserve(void) if (!phys) panic("Failed to allocate CEU1 memory\n"); - memblock_free(phys, size); + memblock_phys_free(phys, size); memblock_remove(phys, size); ceu1_dma_membase = phys; } diff --git a/arch/sh/boards/mach-kfr2r09/setup.c b/arch/sh/boards/mach-kfr2r09/setup.c index eeb5ce341efd..20f4db778ed6 100644 --- a/arch/sh/boards/mach-kfr2r09/setup.c +++ b/arch/sh/boards/mach-kfr2r09/setup.c @@ -633,7 +633,7 @@ static void __init kfr2r09_mv_mem_reserve(void) if (!phys) panic("Failed to allocate CEU memory\n"); - memblock_free(phys, size); + memblock_phys_free(phys, size); memblock_remove(phys, size); ceu_dma_membase = phys; diff --git a/arch/sh/boards/mach-migor/setup.c b/arch/sh/boards/mach-migor/setup.c index 6703a2122c0d..f60061283c48 100644 --- a/arch/sh/boards/mach-migor/setup.c +++ b/arch/sh/boards/mach-migor/setup.c @@ -633,7 +633,7 @@ static void __init migor_mv_mem_reserve(void) if (!phys) panic("Failed to allocate CEU memory\n"); - memblock_free(phys, size); + memblock_phys_free(phys, size); memblock_remove(phys, size); ceu_dma_membase = phys; diff --git a/arch/sh/boards/mach-se/7724/setup.c b/arch/sh/boards/mach-se/7724/setup.c index 8d6541ba0186..8bbf5a6aa423 100644 --- a/arch/sh/boards/mach-se/7724/setup.c +++ b/arch/sh/boards/mach-se/7724/setup.c @@ -966,7 +966,7 @@ static void __init ms7724se_mv_mem_reserve(void) if (!phys) panic("Failed to allocate CEU0 memory\n"); - memblock_free(phys, size); + memblock_phys_free(phys, size); memblock_remove(phys, size); ceu0_dma_membase = phys; @@ -974,7 +974,7 @@ static void __init ms7724se_mv_mem_reserve(void) if (!phys) panic("Failed to allocate CEU1 memory\n"); - memblock_free(phys, size); + memblock_phys_free(phys, size); memblock_remove(phys, size); ceu1_dma_membase = phys; } diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 0224d8f19ed6..2507549538df 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1567,7 +1567,7 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size, static void __init pcpu_free_bootmem(void *ptr, size_t size) { - memblock_free(__pa(ptr), size); + memblock_phys_free(__pa(ptr), size); } static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index 8e636ce02949..d1710ebb44f4 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -47,7 +47,7 @@ void __init mem_init(void) */ brk_end = (unsigned long) UML_ROUND_UP(sbrk(0)); map_memory(brk_end, __pa(brk_end), uml_reserved - brk_end, 1, 1, 0); - memblock_free(__pa(brk_end), uml_reserved - brk_end); + memblock_phys_free(__pa(brk_end), uml_reserved - brk_end); uml_reserved = brk_end; /* this will put all low memory onto the freelists */ diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 40ed44ead063..49b596db5631 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -322,7 +322,7 @@ static void __init reserve_initrd(void) relocate_initrd(); - memblock_free(ramdisk_image, ramdisk_end - ramdisk_image); + memblock_phys_free(ramdisk_image, ramdisk_end - ramdisk_image); } #else @@ -521,7 +521,7 @@ static void __init reserve_crashkernel(void) } if (crash_base >= (1ULL << 32) && reserve_crashkernel_low()) { - memblock_free(crash_base, crash_size); + memblock_phys_free(crash_base, crash_size); return; } diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 23a14d82e783..1895986842b9 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -618,7 +618,7 @@ static void __init memory_map_top_down(unsigned long map_start, */ addr = memblock_phys_alloc_range(PMD_SIZE, PMD_SIZE, map_start, map_end); - memblock_free(addr, PMD_SIZE); + memblock_phys_free(addr, PMD_SIZE); real_end = addr + PMD_SIZE; /* step_size need to be small so pgt_buf from BRK could cover it */ diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 3359c23573c5..676d8d292f8a 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1025,7 +1025,7 @@ static void __init xen_free_ro_pages(unsigned long paddr, unsigned long size) for (; vaddr < vaddr_end; vaddr += PAGE_SIZE) make_lowmem_page_readwrite(vaddr); - memblock_free(paddr, size); + memblock_phys_free(paddr, size); } static void __init xen_cleanmfnmap_free_pgtbl(void *pgtbl, bool unpin) @@ -1151,7 +1151,7 @@ static void __init xen_pagetable_p2m_free(void) xen_cleanhighmap(addr, addr + size); size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long)); - memblock_free(__pa(addr), size); + memblock_phys_free(__pa(addr), size); } else { xen_cleanmfnmap(addr); } @@ -1955,7 +1955,7 @@ void __init xen_relocate_p2m(void) pfn_end = p2m_pfn_end; } - memblock_free(PFN_PHYS(pfn), PAGE_SIZE * (pfn_end - pfn)); + memblock_phys_free(PFN_PHYS(pfn), PAGE_SIZE * (pfn_end - pfn)); while (pfn < pfn_end) { if (pfn == p2m_pfn) { pfn = p2m_pfn_end; diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 8bfc10330107..f387fc7e5250 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -153,7 +153,7 @@ static void __init xen_del_extra_mem(unsigned long start_pfn, break; } } - memblock_free(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns)); + memblock_phys_free(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns)); } /* @@ -719,7 +719,7 @@ static void __init xen_reserve_xen_mfnlist(void) return; xen_relocate_p2m(); - memblock_free(start, size); + memblock_phys_free(start, size); } /** @@ -885,7 +885,7 @@ char * __init xen_memory_setup(void) xen_phys_memcpy(new_area, start, size); pr_info("initrd moved from [mem %#010llx-%#010llx] to [mem %#010llx-%#010llx]\n", start, start + size, new_area, new_area + size); - memblock_free(start, size); + memblock_phys_free(start, size); boot_params.hdr.ramdisk_image = new_area; boot_params.ext_ramdisk_image = new_area >> 32; } diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c index ade8934764f6..712edef03929 100644 --- a/drivers/base/arch_numa.c +++ b/drivers/base/arch_numa.c @@ -166,7 +166,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, static void __init pcpu_fc_free(void *ptr, size_t size) { - memblock_free(__pa(ptr), size); + memblock_phys_free(__pa(ptr), size); } #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK diff --git a/drivers/firmware/efi/memmap.c b/drivers/firmware/efi/memmap.c index 2ff1883dc788..4df55a55da84 100644 --- a/drivers/firmware/efi/memmap.c +++ b/drivers/firmware/efi/memmap.c @@ -35,7 +35,7 @@ void __init __efi_memmap_free(u64 phys, unsigned long size, unsigned long flags) if (slab_is_available()) memblock_free_late(phys, size); else - memblock_free(phys, size); + memblock_phys_free(phys, size); } else if (flags & EFI_MEMMAP_SLAB) { struct page *p = pfn_to_page(PHYS_PFN(phys)); unsigned int order = get_order(size); diff --git a/drivers/of/kexec.c b/drivers/of/kexec.c index 053e241f593c..b9bd1cff1793 100644 --- a/drivers/of/kexec.c +++ b/drivers/of/kexec.c @@ -171,8 +171,7 @@ int ima_free_kexec_buffer(void) if (ret) return ret; - return memblock_free(addr, size); - + return memblock_phys_free(addr, size); } /** diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c index 9da8835ba5a5..9c0fb962c22b 100644 --- a/drivers/of/of_reserved_mem.c +++ b/drivers/of/of_reserved_mem.c @@ -46,7 +46,7 @@ static int __init early_init_dt_alloc_reserved_memory_arch(phys_addr_t size, if (nomap) { err = memblock_mark_nomap(base, size); if (err) - memblock_free(base, size); + memblock_phys_free(base, size); kmemleak_ignore_phys(base); } @@ -284,7 +284,8 @@ void __init fdt_init_reserved_mem(void) if (nomap) memblock_clear_nomap(rmem->base, rmem->size); else - memblock_free(rmem->base, rmem->size); + memblock_phys_free(rmem->base, + rmem->size); } } } diff --git a/drivers/s390/char/sclp_early.c b/drivers/s390/char/sclp_early.c index f01d942e1c1d..c0052655fc4f 100644 --- a/drivers/s390/char/sclp_early.c +++ b/drivers/s390/char/sclp_early.c @@ -139,7 +139,7 @@ int __init sclp_early_get_core_info(struct sclp_core_info *info) } sclp_fill_core_info(info, sccb); out: - memblock_free((unsigned long)sccb, length); + memblock_phys_free((unsigned long)sccb, length); return rc; } diff --git a/drivers/usb/early/xhci-dbc.c b/drivers/usb/early/xhci-dbc.c index be4ecbabdd58..933d77ad0a64 100644 --- a/drivers/usb/early/xhci-dbc.c +++ b/drivers/usb/early/xhci-dbc.c @@ -185,7 +185,7 @@ static void __init xdbc_free_ring(struct xdbc_ring *ring) if (!seg) return; - memblock_free(seg->dma, PAGE_SIZE); + memblock_phys_free(seg->dma, PAGE_SIZE); ring->segment = NULL; } @@ -665,10 +665,10 @@ int __init early_xdbc_setup_hardware(void) xdbc_free_ring(&xdbc.in_ring); if (xdbc.table_dma) - memblock_free(xdbc.table_dma, PAGE_SIZE); + memblock_phys_free(xdbc.table_dma, PAGE_SIZE); if (xdbc.out_dma) - memblock_free(xdbc.out_dma, PAGE_SIZE); + memblock_phys_free(xdbc.out_dma, PAGE_SIZE); xdbc.table_base = NULL; xdbc.out_buf = NULL; @@ -987,8 +987,8 @@ free_and_quit: xdbc_free_ring(&xdbc.evt_ring); xdbc_free_ring(&xdbc.out_ring); xdbc_free_ring(&xdbc.in_ring); - memblock_free(xdbc.table_dma, PAGE_SIZE); - memblock_free(xdbc.out_dma, PAGE_SIZE); + memblock_phys_free(xdbc.table_dma, PAGE_SIZE); + memblock_phys_free(xdbc.out_dma, PAGE_SIZE); writel(0, &xdbc.xdbc_reg->control); early_iounmap(xdbc.xhci_base, xdbc.xhci_length); diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index e56a5faac395..4b671cc0a7ea 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -241,7 +241,7 @@ retry: */ rc = xen_swiotlb_fixup(start, nslabs); if (rc) { - memblock_free(__pa(start), PAGE_ALIGN(bytes)); + memblock_phys_free(__pa(start), PAGE_ALIGN(bytes)); if (nslabs > 1024 && repeat--) { /* Min is 2MB */ nslabs = max(1024UL, ALIGN(nslabs >> 1, IO_TLB_SEGSIZE)); diff --git a/include/linux/memblock.h b/include/linux/memblock.h index e25f964fdd60..d32d41709513 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -103,7 +103,7 @@ void memblock_allow_resize(void); int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid); int memblock_add(phys_addr_t base, phys_addr_t size); int memblock_remove(phys_addr_t base, phys_addr_t size); -int memblock_free(phys_addr_t base, phys_addr_t size); +int memblock_phys_free(phys_addr_t base, phys_addr_t size); int memblock_reserve(phys_addr_t base, phys_addr_t size); #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP int memblock_physmem_add(phys_addr_t base, phys_addr_t size); diff --git a/init/initramfs.c b/init/initramfs.c index a842c0544745..1a971f070dd4 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -607,7 +607,7 @@ void __weak __init free_initrd_mem(unsigned long start, unsigned long end) unsigned long aligned_start = ALIGN_DOWN(start, PAGE_SIZE); unsigned long aligned_end = ALIGN(end, PAGE_SIZE); - memblock_free(__pa(aligned_start), aligned_end - aligned_start); + memblock_phys_free(__pa(aligned_start), aligned_end - aligned_start); #endif free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM, diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 430d2f78d540..b9fa173e5e56 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -247,7 +247,7 @@ swiotlb_init(int verbose) return; fail_free_mem: - memblock_free(__pa(tlb), bytes); + memblock_phys_free(__pa(tlb), bytes); fail: pr_warn("Cannot allocate buffer"); } diff --git a/lib/cpumask.c b/lib/cpumask.c index 045779446a18..a90786b77c1c 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -188,7 +188,7 @@ EXPORT_SYMBOL(free_cpumask_var); */ void __init free_bootmem_cpumask_var(cpumask_var_t mask) { - memblock_free(__pa(mask), cpumask_size()); + memblock_phys_free(__pa(mask), cpumask_size()); } #endif diff --git a/mm/cma.c b/mm/cma.c index 11152c3fb23c..bc9ca8f3c487 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -378,7 +378,7 @@ int __init cma_declare_contiguous_nid(phys_addr_t base, return 0; free_mem: - memblock_free(base, size); + memblock_phys_free(base, size); err: pr_err("Failed to reserve %ld MiB\n", (unsigned long)size / SZ_1M); return ret; diff --git a/mm/memblock.c b/mm/memblock.c index 849060013d3c..52e34abc4abe 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -806,18 +806,18 @@ int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size) void __init_memblock memblock_free_ptr(void *ptr, size_t size) { if (ptr) - memblock_free(__pa(ptr), size); + memblock_phys_free(__pa(ptr), size); } /** - * memblock_free - free boot memory block + * memblock_phys_free - free boot memory block * @base: phys starting address of the boot memory block * @size: size of the boot memory block in bytes * * Free boot memory block previously allocated by memblock_alloc_xx() API. * The freeing memory will not be released to the buddy allocator. */ -int __init_memblock memblock_free(phys_addr_t base, phys_addr_t size) +int __init_memblock memblock_phys_free(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; @@ -1937,7 +1937,7 @@ static void __init free_memmap(unsigned long start_pfn, unsigned long end_pfn) * memmap array. */ if (pg < pgend) - memblock_free(pg, pgend - pg); + memblock_phys_free(pg, pgend - pg); } /* diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 9fd0be32a281..feffaa9423fe 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -2204,7 +2204,7 @@ static int __ref try_remove_memory(u64 start, u64 size) arch_remove_memory(start, size, altmap); if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) { - memblock_free(start, size); + memblock_phys_free(start, size); memblock_remove(start, size); } diff --git a/mm/percpu.c b/mm/percpu.c index f58318cb04c0..d65ddf6f2a35 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -2472,7 +2472,7 @@ struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, */ void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai) { - memblock_free(__pa(ai), ai->__ai_size); + memblock_phys_free(__pa(ai), ai->__ai_size); } /** @@ -3134,7 +3134,7 @@ out_free_areas: out_free: pcpu_free_alloc_info(ai); if (areas) - memblock_free(__pa(areas), areas_size); + memblock_phys_free(__pa(areas), areas_size); return rc; } #endif /* BUILD_EMBED_FIRST_CHUNK */ @@ -3256,7 +3256,7 @@ enomem: free_fn(page_address(pages[j]), PAGE_SIZE); rc = -ENOMEM; out_free_ar: - memblock_free(__pa(pages), pages_size); + memblock_phys_free(__pa(pages), pages_size); pcpu_free_alloc_info(ai); return rc; } @@ -3286,7 +3286,7 @@ static void * __init pcpu_dfl_fc_alloc(unsigned int cpu, size_t size, static void __init pcpu_dfl_fc_free(void *ptr, size_t size) { - memblock_free(__pa(ptr), size); + memblock_phys_free(__pa(ptr), size); } void __init setup_per_cpu_areas(void) diff --git a/mm/sparse.c b/mm/sparse.c index 55fea0c2f927..fc3ab8d3b6bc 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -451,7 +451,7 @@ static void *sparsemap_buf_end __meminitdata; static inline void __meminit sparse_buffer_free(unsigned long size) { WARN_ON(!sparsemap_buf || size == 0); - memblock_free(__pa(sparsemap_buf), size); + memblock_phys_free(__pa(sparsemap_buf), size); } static void __init sparse_buffer_init(unsigned long size, int nid) From 4421cca0a3e4833b3bf0f20de98eb580ab8c7290 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Fri, 5 Nov 2021 13:43:22 -0700 Subject: [PATCH 071/166] memblock: use memblock_free for freeing virtual pointers Rename memblock_free_ptr() to memblock_free() and use memblock_free() when freeing a virtual pointer so that memblock_free() will be a counterpart of memblock_alloc() The callers are updated with the below semantic patch and manual addition of (void *) casting to pointers that are represented by unsigned long variables. @@ identifier vaddr; expression size; @@ ( - memblock_phys_free(__pa(vaddr), size); + memblock_free(vaddr, size); | - memblock_free_ptr(vaddr, size); + memblock_free(vaddr, size); ) [sfr@canb.auug.org.au: fixup] Link: https://lkml.kernel.org/r/20211018192940.3d1d532f@canb.auug.org.au Link: https://lkml.kernel.org/r/20210930185031.18648-7-rppt@kernel.org Signed-off-by: Mike Rapoport Signed-off-by: Stephen Rothwell Cc: Christophe Leroy Cc: Juergen Gross Cc: Shahab Vahedi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/kernel/core_irongate.c | 3 +-- arch/mips/mm/init.c | 2 +- arch/powerpc/kernel/dt_cpu_ftrs.c | 4 ++-- arch/powerpc/kernel/setup-common.c | 2 +- arch/powerpc/kernel/setup_64.c | 2 +- arch/powerpc/platforms/powernv/pci-ioda.c | 2 +- arch/powerpc/platforms/pseries/svm.c | 3 +-- arch/riscv/kernel/setup.c | 5 ++--- arch/sparc/kernel/smp_64.c | 2 +- arch/um/kernel/mem.c | 2 +- arch/x86/kernel/setup_percpu.c | 2 +- arch/x86/mm/kasan_init_64.c | 4 ++-- arch/x86/mm/numa.c | 2 +- arch/x86/mm/numa_emulation.c | 2 +- arch/x86/xen/mmu_pv.c | 2 +- arch/x86/xen/p2m.c | 2 +- drivers/base/arch_numa.c | 4 ++-- drivers/macintosh/smu.c | 2 +- drivers/xen/swiotlb-xen.c | 2 +- include/linux/memblock.h | 2 +- init/initramfs.c | 2 +- init/main.c | 4 ++-- kernel/dma/swiotlb.c | 2 +- kernel/printk/printk.c | 4 ++-- lib/bootconfig.c | 2 +- lib/cpumask.c | 2 +- mm/memblock.c | 6 +++--- mm/percpu.c | 8 ++++---- mm/sparse.c | 2 +- 29 files changed, 40 insertions(+), 43 deletions(-) diff --git a/arch/alpha/kernel/core_irongate.c b/arch/alpha/kernel/core_irongate.c index ee26dcc49418..6b8ed12936b6 100644 --- a/arch/alpha/kernel/core_irongate.c +++ b/arch/alpha/kernel/core_irongate.c @@ -233,8 +233,7 @@ albacore_init_arch(void) unsigned long size; size = initrd_end - initrd_start; - memblock_phys_free(__pa(initrd_start), - PAGE_ALIGN(size)); + memblock_free((void *)initrd_start, PAGE_ALIGN(size)); if (!move_initrd(pci_mem)) printk("irongate_init_arch: initrd too big " "(%ldK)\ndisabling initrd\n", diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 3be1c29084fa..325e1552cbea 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -529,7 +529,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, static void __init pcpu_fc_free(void *ptr, size_t size) { - memblock_phys_free(__pa(ptr), size); + memblock_free(ptr, size); } void __init setup_per_cpu_areas(void) diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 42839d6bd486..ba527fb52993 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -1095,8 +1095,8 @@ static int __init dt_cpu_ftrs_scan_callback(unsigned long node, const char cpufeatures_setup_finished(); - memblock_phys_free(__pa(dt_cpu_features), - sizeof(struct dt_cpu_feature) * nr_dt_cpu_features); + memblock_free(dt_cpu_features, + sizeof(struct dt_cpu_feature) * nr_dt_cpu_features); return 0; } diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 5af8993a8e6d..6b1338db8779 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -825,7 +825,7 @@ static void __init smp_setup_pacas(void) set_hard_smp_processor_id(cpu, cpu_to_phys_id[cpu]); } - memblock_phys_free(__pa(cpu_to_phys_id), nr_cpu_ids * sizeof(u32)); + memblock_free(cpu_to_phys_id, nr_cpu_ids * sizeof(u32)); cpu_to_phys_id = NULL; } #endif diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 75bc294ac40d..1777e992b20b 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -812,7 +812,7 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size, static void __init pcpu_free_bootmem(void *ptr, size_t size) { - memblock_phys_free(__pa(ptr), size); + memblock_free(ptr, size); } static int pcpu_cpu_distance(unsigned int from, unsigned int to) diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index b5a9d343b720..004cd6a96c8a 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -2981,7 +2981,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, if (!phb->hose) { pr_err(" Can't allocate PCI controller for %pOF\n", np); - memblock_phys_free(__pa(phb), sizeof(struct pnv_phb)); + memblock_free(phb, sizeof(struct pnv_phb)); return; } diff --git a/arch/powerpc/platforms/pseries/svm.c b/arch/powerpc/platforms/pseries/svm.c index b7c017bb40f7..6332365d2891 100644 --- a/arch/powerpc/platforms/pseries/svm.c +++ b/arch/powerpc/platforms/pseries/svm.c @@ -56,8 +56,7 @@ void __init svm_swiotlb_init(void) return; - memblock_phys_free(__pa(vstart), - PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); + memblock_free(vstart, PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); panic("SVM: Cannot allocate SWIOTLB buffer"); } diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 6ea7c53b82cd..b42bfdc67482 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -230,14 +230,13 @@ static void __init init_resources(void) /* Clean-up any unused pre-allocated resources */ if (res_idx >= 0) - memblock_phys_free(__pa(mem_res), - (res_idx + 1) * sizeof(*mem_res)); + memblock_free(mem_res, (res_idx + 1) * sizeof(*mem_res)); return; error: /* Better an empty resource tree than an inconsistent one */ release_child_resources(&iomem_resource); - memblock_phys_free(__pa(mem_res), mem_res_sz); + memblock_free(mem_res, mem_res_sz); } diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 2507549538df..b98a7bbe6728 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1567,7 +1567,7 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size, static void __init pcpu_free_bootmem(void *ptr, size_t size) { - memblock_phys_free(__pa(ptr), size); + memblock_free(ptr, size); } static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index d1710ebb44f4..0039771eb01c 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -47,7 +47,7 @@ void __init mem_init(void) */ brk_end = (unsigned long) UML_ROUND_UP(sbrk(0)); map_memory(brk_end, __pa(brk_end), uml_reserved - brk_end, 1, 1, 0); - memblock_phys_free(__pa(brk_end), uml_reserved - brk_end); + memblock_free((void *)brk_end, uml_reserved - brk_end); uml_reserved = brk_end; /* this will put all low memory onto the freelists */ diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 5afd98559193..7b65275544b2 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -135,7 +135,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align) static void __init pcpu_fc_free(void *ptr, size_t size) { - memblock_free_ptr(ptr, size); + memblock_free(ptr, size); } static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index ef885370719a..e7b9b464a82f 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -49,7 +49,7 @@ static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr, p = early_alloc(PMD_SIZE, nid, false); if (p && pmd_set_huge(pmd, __pa(p), PAGE_KERNEL)) return; - memblock_free_ptr(p, PMD_SIZE); + memblock_free(p, PMD_SIZE); } p = early_alloc(PAGE_SIZE, nid, true); @@ -85,7 +85,7 @@ static void __init kasan_populate_pud(pud_t *pud, unsigned long addr, p = early_alloc(PUD_SIZE, nid, false); if (p && pud_set_huge(pud, __pa(p), PAGE_KERNEL)) return; - memblock_free_ptr(p, PUD_SIZE); + memblock_free(p, PUD_SIZE); } p = early_alloc(PAGE_SIZE, nid, true); diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 1e9b93b088db..c6b1213086d6 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -355,7 +355,7 @@ void __init numa_reset_distance(void) /* numa_distance could be 1LU marking allocation failure, test cnt */ if (numa_distance_cnt) - memblock_free_ptr(numa_distance, size); + memblock_free(numa_distance, size); numa_distance_cnt = 0; numa_distance = NULL; /* enable table creation */ } diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index e801e30089c4..1a02b791d273 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -517,7 +517,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) } /* free the copied physical distance table */ - memblock_free_ptr(phys_dist, phys_size); + memblock_free(phys_dist, phys_size); return; no_emu: diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 676d8d292f8a..173de1e29bda 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1151,7 +1151,7 @@ static void __init xen_pagetable_p2m_free(void) xen_cleanhighmap(addr, addr + size); size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long)); - memblock_phys_free(__pa(addr), size); + memblock_free((void *)addr, size); } else { xen_cleanmfnmap(addr); } diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 141bb9dbd2fb..58db86f7b384 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -197,7 +197,7 @@ static void * __ref alloc_p2m_page(void) static void __ref free_p2m_page(void *p) { if (unlikely(!slab_is_available())) { - memblock_free_ptr(p, PAGE_SIZE); + memblock_free(p, PAGE_SIZE); return; } diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c index 712edef03929..bc1876915457 100644 --- a/drivers/base/arch_numa.c +++ b/drivers/base/arch_numa.c @@ -166,7 +166,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, static void __init pcpu_fc_free(void *ptr, size_t size) { - memblock_phys_free(__pa(ptr), size); + memblock_free(ptr, size); } #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK @@ -326,7 +326,7 @@ void __init numa_free_distance(void) size = numa_distance_cnt * numa_distance_cnt * sizeof(numa_distance[0]); - memblock_free_ptr(numa_distance, size); + memblock_free(numa_distance, size); numa_distance_cnt = 0; numa_distance = NULL; } diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c index fe63d5ee201b..f62152111236 100644 --- a/drivers/macintosh/smu.c +++ b/drivers/macintosh/smu.c @@ -570,7 +570,7 @@ fail_msg_node: fail_db_node: of_node_put(smu->db_node); fail_bootmem: - memblock_free_ptr(smu, sizeof(struct smu_device)); + memblock_free(smu, sizeof(struct smu_device)); smu = NULL; fail_np: of_node_put(np); diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 4b671cc0a7ea..f083194e2634 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -241,7 +241,7 @@ retry: */ rc = xen_swiotlb_fixup(start, nslabs); if (rc) { - memblock_phys_free(__pa(start), PAGE_ALIGN(bytes)); + memblock_free(start, PAGE_ALIGN(bytes)); if (nslabs > 1024 && repeat--) { /* Min is 2MB */ nslabs = max(1024UL, ALIGN(nslabs >> 1, IO_TLB_SEGSIZE)); diff --git a/include/linux/memblock.h b/include/linux/memblock.h index d32d41709513..484650681bee 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -118,7 +118,7 @@ int memblock_mark_nomap(phys_addr_t base, phys_addr_t size); int memblock_clear_nomap(phys_addr_t base, phys_addr_t size); void memblock_free_all(void); -void memblock_free_ptr(void *ptr, size_t size); +void memblock_free(void *ptr, size_t size); void reset_node_managed_pages(pg_data_t *pgdat); void reset_all_zones_managed_pages(void); diff --git a/init/initramfs.c b/init/initramfs.c index 1a971f070dd4..2f3d96dc3db6 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -607,7 +607,7 @@ void __weak __init free_initrd_mem(unsigned long start, unsigned long end) unsigned long aligned_start = ALIGN_DOWN(start, PAGE_SIZE); unsigned long aligned_end = ALIGN(end, PAGE_SIZE); - memblock_phys_free(__pa(aligned_start), aligned_end - aligned_start); + memblock_free((void *)aligned_start, aligned_end - aligned_start); #endif free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM, diff --git a/init/main.c b/init/main.c index 767ee2672176..f0001af8ebb9 100644 --- a/init/main.c +++ b/init/main.c @@ -382,7 +382,7 @@ static char * __init xbc_make_cmdline(const char *key) ret = xbc_snprint_cmdline(new_cmdline, len + 1, root); if (ret < 0 || ret > len) { pr_err("Failed to print extra kernel cmdline.\n"); - memblock_free_ptr(new_cmdline, len + 1); + memblock_free(new_cmdline, len + 1); return NULL; } @@ -925,7 +925,7 @@ static void __init print_unknown_bootoptions(void) end += sprintf(end, " %s", *p); pr_notice("Unknown command line parameters:%s\n", unknown_options); - memblock_free_ptr(unknown_options, len); + memblock_free(unknown_options, len); } asmlinkage __visible void __init __no_sanitize_address start_kernel(void) diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index b9fa173e5e56..02656d7ccbfd 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -247,7 +247,7 @@ swiotlb_init(int verbose) return; fail_free_mem: - memblock_phys_free(__pa(tlb), bytes); + memblock_free(tlb, bytes); fail: pr_warn("Cannot allocate buffer"); } diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index a8d0a58deebc..2cae1bfa6be7 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1166,9 +1166,9 @@ void __init setup_log_buf(int early) return; err_free_descs: - memblock_free_ptr(new_descs, new_descs_size); + memblock_free(new_descs, new_descs_size); err_free_log_buf: - memblock_free_ptr(new_log_buf, new_log_buf_len); + memblock_free(new_log_buf, new_log_buf_len); } static bool __read_mostly ignore_loglevel; diff --git a/lib/bootconfig.c b/lib/bootconfig.c index 5ae248b29373..547558d80e64 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -792,7 +792,7 @@ void __init xbc_destroy_all(void) xbc_data = NULL; xbc_data_size = 0; xbc_node_num = 0; - memblock_free_ptr(xbc_nodes, sizeof(struct xbc_node) * XBC_NODE_MAX); + memblock_free(xbc_nodes, sizeof(struct xbc_node) * XBC_NODE_MAX); xbc_nodes = NULL; brace_index = 0; } diff --git a/lib/cpumask.c b/lib/cpumask.c index a90786b77c1c..a971a82d2f43 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -188,7 +188,7 @@ EXPORT_SYMBOL(free_cpumask_var); */ void __init free_bootmem_cpumask_var(cpumask_var_t mask) { - memblock_phys_free(__pa(mask), cpumask_size()); + memblock_free(mask, cpumask_size()); } #endif diff --git a/mm/memblock.c b/mm/memblock.c index 52e34abc4abe..fb0c7f48e627 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -472,7 +472,7 @@ static int __init_memblock memblock_double_array(struct memblock_type *type, kfree(old_array); else if (old_array != memblock_memory_init_regions && old_array != memblock_reserved_init_regions) - memblock_free_ptr(old_array, old_alloc_size); + memblock_free(old_array, old_alloc_size); /* * Reserve the new array if that comes from the memblock. Otherwise, we @@ -796,14 +796,14 @@ int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size) } /** - * memblock_free_ptr - free boot memory allocation + * memblock_free - free boot memory allocation * @ptr: starting address of the boot memory allocation * @size: size of the boot memory block in bytes * * Free boot memory block previously allocated by memblock_alloc_xx() API. * The freeing memory will not be released to the buddy allocator. */ -void __init_memblock memblock_free_ptr(void *ptr, size_t size) +void __init_memblock memblock_free(void *ptr, size_t size) { if (ptr) memblock_phys_free(__pa(ptr), size); diff --git a/mm/percpu.c b/mm/percpu.c index d65ddf6f2a35..f5b2c2ea5a54 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -2472,7 +2472,7 @@ struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, */ void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai) { - memblock_phys_free(__pa(ai), ai->__ai_size); + memblock_free(ai, ai->__ai_size); } /** @@ -3134,7 +3134,7 @@ out_free_areas: out_free: pcpu_free_alloc_info(ai); if (areas) - memblock_phys_free(__pa(areas), areas_size); + memblock_free(areas, areas_size); return rc; } #endif /* BUILD_EMBED_FIRST_CHUNK */ @@ -3256,7 +3256,7 @@ enomem: free_fn(page_address(pages[j]), PAGE_SIZE); rc = -ENOMEM; out_free_ar: - memblock_phys_free(__pa(pages), pages_size); + memblock_free(pages, pages_size); pcpu_free_alloc_info(ai); return rc; } @@ -3286,7 +3286,7 @@ static void * __init pcpu_dfl_fc_alloc(unsigned int cpu, size_t size, static void __init pcpu_dfl_fc_free(void *ptr, size_t size) { - memblock_phys_free(__pa(ptr), size); + memblock_free(ptr, size); } void __init setup_per_cpu_areas(void) diff --git a/mm/sparse.c b/mm/sparse.c index fc3ab8d3b6bc..e5c84b0cf0c9 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -451,7 +451,7 @@ static void *sparsemap_buf_end __meminitdata; static inline void __meminit sparse_buffer_free(unsigned long size) { WARN_ON(!sparsemap_buf || size == 0); - memblock_phys_free(__pa(sparsemap_buf), size); + memblock_free(sparsemap_buf, size); } static void __init sparse_buffer_init(unsigned long size, int nid) From 3723929eb0f50e2101de739cdb66458a4f1f4b27 Mon Sep 17 00:00:00 2001 From: Sultan Alsawaf Date: Fri, 5 Nov 2021 13:43:25 -0700 Subject: [PATCH 072/166] mm: mark the OOM reaper thread as freezable The OOM reaper alters user address space which might theoretically alter the snapshot if reaping is allowed to happen after the freezer quiescent state. To this end, the reaper kthread uses wait_event_freezable() while waiting for any work so that it cannot run while the system freezes. However, the current implementation doesn't respect the freezer because all kernel threads are created with the PF_NOFREEZE flag, so they are automatically excluded from freezing operations. This means that the OOM reaper can race with system snapshotting if it has work to do while the system is being frozen. Fix this by adding a set_freezable() call which will clear the PF_NOFREEZE flag and thus make the OOM reaper visible to the freezer. Please note that the OOM reaper altering the snapshot this way is mostly a theoretical concern and has not been observed in practice. Link: https://lkml.kernel.org/r/20210921165758.6154-1-sultan@kerneltoast.com Link: https://lkml.kernel.org/r/20210918233920.9174-1-sultan@kerneltoast.com Fixes: aac453635549 ("mm, oom: introduce oom reaper") Signed-off-by: Sultan Alsawaf Acked-by: Michal Hocko Cc: David Rientjes Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/oom_kill.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/mm/oom_kill.c b/mm/oom_kill.c index bfa9e348c3a3..d365cc84a486 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -641,6 +641,8 @@ done: static int oom_reaper(void *unused) { + set_freezable(); + while (true) { struct task_struct *tsk = NULL; From b5389086ad7be0453c55e0069a89856d1fbdf605 Mon Sep 17 00:00:00 2001 From: Zhenguo Yao Date: Fri, 5 Nov 2021 13:43:28 -0700 Subject: [PATCH 073/166] hugetlbfs: extend the definition of hugepages parameter to support node allocation We can specify the number of hugepages to allocate at boot. But the hugepages is balanced in all nodes at present. In some scenarios, we only need hugepages in one node. For example: DPDK needs hugepages which are in the same node as NIC. If DPDK needs four hugepages of 1G size in node1 and system has 16 numa nodes we must reserve 64 hugepages on the kernel cmdline. But only four hugepages are used. The others should be free after boot. If the system memory is low(for example: 64G), it will be an impossible task. So extend the hugepages parameter to support specifying hugepages on a specific node. For example add following parameter: hugepagesz=1G hugepages=0:1,1:3 It will allocate 1 hugepage in node0 and 3 hugepages in node1. Link: https://lkml.kernel.org/r/20211005054729.86457-1-yaozhenguo1@gmail.com Signed-off-by: Zhenguo Yao Reviewed-by: Mike Kravetz Cc: Zhenguo Yao Cc: Dan Carpenter Cc: Nathan Chancellor Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Jonathan Corbet Cc: Mike Rapoport Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- .../admin-guide/kernel-parameters.txt | 8 +- Documentation/admin-guide/mm/hugetlbpage.rst | 12 +- arch/powerpc/mm/hugetlbpage.c | 9 +- include/linux/hugetlb.h | 6 +- mm/hugetlb.c | 153 +++++++++++++++--- 5 files changed, 155 insertions(+), 33 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index e7f7904edf20..02eeda2a11ad 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1601,9 +1601,11 @@ the number of pages of hugepagesz to be allocated. If this is the first HugeTLB parameter on the command line, it specifies the number of pages to allocate for - the default huge page size. See also - Documentation/admin-guide/mm/hugetlbpage.rst. - Format: + the default huge page size. If using node format, the + number of pages to allocate per-node can be specified. + See also Documentation/admin-guide/mm/hugetlbpage.rst. + Format: or (node format) + :[,:] hugepagesz= [HW] The size of the HugeTLB pages. This is used in diff --git a/Documentation/admin-guide/mm/hugetlbpage.rst b/Documentation/admin-guide/mm/hugetlbpage.rst index bb90de3885d1..0166f9de3428 100644 --- a/Documentation/admin-guide/mm/hugetlbpage.rst +++ b/Documentation/admin-guide/mm/hugetlbpage.rst @@ -128,7 +128,9 @@ hugepages implicitly specifies the number of huge pages of default size to allocate. If the number of huge pages of default size is implicitly specified, it can not be overwritten by a hugepagesz,hugepages - parameter pair for the default size. + parameter pair for the default size. This parameter also has a + node format. The node format specifies the number of huge pages + to allocate on specific nodes. For example, on an architecture with 2M default huge page size:: @@ -138,6 +140,14 @@ hugepages indicating that the hugepages=512 parameter is ignored. If a hugepages parameter is preceded by an invalid hugepagesz parameter, it will be ignored. + + Node format example:: + + hugepagesz=2M hugepages=0:1,1:2 + + It will allocate 1 2M hugepage on node0 and 2 2M hugepages on node1. + If the node number is invalid, the parameter will be ignored. + default_hugepagesz Specify the default huge page size. This parameter can only be specified once on the command line. default_hugepagesz can diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 9a75ba078e1b..82d8b368ca6d 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -229,17 +229,22 @@ static int __init pseries_alloc_bootmem_huge_page(struct hstate *hstate) m->hstate = hstate; return 1; } + +bool __init hugetlb_node_alloc_supported(void) +{ + return false; +} #endif -int __init alloc_bootmem_huge_page(struct hstate *h) +int __init alloc_bootmem_huge_page(struct hstate *h, int nid) { #ifdef CONFIG_PPC_BOOK3S_64 if (firmware_has_feature(FW_FEATURE_LPAR) && !radix_enabled()) return pseries_alloc_bootmem_huge_page(h); #endif - return __alloc_bootmem_huge_page(h); + return __alloc_bootmem_huge_page(h, nid); } #ifndef CONFIG_PPC_BOOK3S_64 diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index c0a20781b28e..44c2ab0dfa59 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -615,6 +615,7 @@ struct hstate { unsigned long nr_overcommit_huge_pages; struct list_head hugepage_activelist; struct list_head hugepage_freelists[MAX_NUMNODES]; + unsigned int max_huge_pages_node[MAX_NUMNODES]; unsigned int nr_huge_pages_node[MAX_NUMNODES]; unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; @@ -647,8 +648,9 @@ void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, unsigned long address, struct page *page); /* arch callback */ -int __init __alloc_bootmem_huge_page(struct hstate *h); -int __init alloc_bootmem_huge_page(struct hstate *h); +int __init __alloc_bootmem_huge_page(struct hstate *h, int nid); +int __init alloc_bootmem_huge_page(struct hstate *h, int nid); +bool __init hugetlb_node_alloc_supported(void); void __init hugetlb_add_hstate(unsigned order); bool __init arch_hugetlb_valid_size(unsigned long size); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 5eab627a170b..24543dab9c4b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -77,6 +77,7 @@ static struct hstate * __initdata parsed_hstate; static unsigned long __initdata default_hstate_max_huge_pages; static bool __initdata parsed_valid_hugepagesz = true; static bool __initdata parsed_default_hugepagesz; +static unsigned int default_hugepages_in_node[MAX_NUMNODES] __initdata; /* * Protects updates to hugepage_freelists, hugepage_activelist, nr_huge_pages, @@ -2963,33 +2964,39 @@ out_subpool_put: return ERR_PTR(-ENOSPC); } -int alloc_bootmem_huge_page(struct hstate *h) +int alloc_bootmem_huge_page(struct hstate *h, int nid) __attribute__ ((weak, alias("__alloc_bootmem_huge_page"))); -int __alloc_bootmem_huge_page(struct hstate *h) +int __alloc_bootmem_huge_page(struct hstate *h, int nid) { - struct huge_bootmem_page *m; + struct huge_bootmem_page *m = NULL; /* initialize for clang */ int nr_nodes, node; + if (nid >= nr_online_nodes) + return 0; + /* do node specific alloc */ + if (nid != NUMA_NO_NODE) { + m = memblock_alloc_try_nid_raw(huge_page_size(h), huge_page_size(h), + 0, MEMBLOCK_ALLOC_ACCESSIBLE, nid); + if (!m) + return 0; + goto found; + } + /* allocate from next node when distributing huge pages */ for_each_node_mask_to_alloc(h, nr_nodes, node, &node_states[N_MEMORY]) { - void *addr; - - addr = memblock_alloc_try_nid_raw( + m = memblock_alloc_try_nid_raw( huge_page_size(h), huge_page_size(h), 0, MEMBLOCK_ALLOC_ACCESSIBLE, node); - if (addr) { - /* - * Use the beginning of the huge page to store the - * huge_bootmem_page struct (until gather_bootmem - * puts them into the mem_map). - */ - m = addr; - goto found; - } + /* + * Use the beginning of the huge page to store the + * huge_bootmem_page struct (until gather_bootmem + * puts them into the mem_map). + */ + if (!m) + return 0; + goto found; } - return 0; found: - BUG_ON(!IS_ALIGNED(virt_to_phys(m), huge_page_size(h))); /* Put them into a private list first because mem_map is not up yet */ INIT_LIST_HEAD(&m->list); list_add(&m->list, &huge_boot_pages); @@ -3029,12 +3036,61 @@ static void __init gather_bootmem_prealloc(void) cond_resched(); } } +static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid) +{ + unsigned long i; + char buf[32]; + + for (i = 0; i < h->max_huge_pages_node[nid]; ++i) { + if (hstate_is_gigantic(h)) { + if (!alloc_bootmem_huge_page(h, nid)) + break; + } else { + struct page *page; + gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; + + page = alloc_fresh_huge_page(h, gfp_mask, nid, + &node_states[N_MEMORY], NULL); + if (!page) + break; + put_page(page); /* free it into the hugepage allocator */ + } + cond_resched(); + } + if (i == h->max_huge_pages_node[nid]) + return; + + string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); + pr_warn("HugeTLB: allocating %u of page size %s failed node%d. Only allocated %lu hugepages.\n", + h->max_huge_pages_node[nid], buf, nid, i); + h->max_huge_pages -= (h->max_huge_pages_node[nid] - i); + h->max_huge_pages_node[nid] = i; +} static void __init hugetlb_hstate_alloc_pages(struct hstate *h) { unsigned long i; nodemask_t *node_alloc_noretry; + bool node_specific_alloc = false; + /* skip gigantic hugepages allocation if hugetlb_cma enabled */ + if (hstate_is_gigantic(h) && hugetlb_cma_size) { + pr_warn_once("HugeTLB: hugetlb_cma is enabled, skip boot time allocation\n"); + return; + } + + /* do node specific alloc */ + for (i = 0; i < nr_online_nodes; i++) { + if (h->max_huge_pages_node[i] > 0) { + hugetlb_hstate_alloc_pages_onenode(h, i); + node_specific_alloc = true; + } + } + + if (node_specific_alloc) + return; + + /* below will do all node balanced alloc */ if (!hstate_is_gigantic(h)) { /* * Bit mask controlling how hard we retry per-node allocations. @@ -3055,11 +3111,7 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h) for (i = 0; i < h->max_huge_pages; ++i) { if (hstate_is_gigantic(h)) { - if (hugetlb_cma_size) { - pr_warn_once("HugeTLB: hugetlb_cma is enabled, skip boot time allocation\n"); - goto free; - } - if (!alloc_bootmem_huge_page(h)) + if (!alloc_bootmem_huge_page(h, NUMA_NO_NODE)) break; } else if (!alloc_pool_huge_page(h, &node_states[N_MEMORY], @@ -3075,7 +3127,6 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h) h->max_huge_pages, buf, i); h->max_huge_pages = i; } -free: kfree(node_alloc_noretry); } @@ -3990,6 +4041,10 @@ static int __init hugetlb_init(void) } default_hstate.max_huge_pages = default_hstate_max_huge_pages; + + for (i = 0; i < nr_online_nodes; i++) + default_hstate.max_huge_pages_node[i] = + default_hugepages_in_node[i]; } } @@ -4050,6 +4105,10 @@ void __init hugetlb_add_hstate(unsigned int order) parsed_hstate = h; } +bool __init __weak hugetlb_node_alloc_supported(void) +{ + return true; +} /* * hugepages command line processing * hugepages normally follows a valid hugepagsz or default_hugepagsz @@ -4061,6 +4120,10 @@ static int __init hugepages_setup(char *s) { unsigned long *mhp; static unsigned long *last_mhp; + int node = NUMA_NO_NODE; + int count; + unsigned long tmp; + char *p = s; if (!parsed_valid_hugepagesz) { pr_warn("HugeTLB: hugepages=%s does not follow a valid hugepagesz, ignoring\n", s); @@ -4084,8 +4147,40 @@ static int __init hugepages_setup(char *s) return 0; } - if (sscanf(s, "%lu", mhp) <= 0) - *mhp = 0; + while (*p) { + count = 0; + if (sscanf(p, "%lu%n", &tmp, &count) != 1) + goto invalid; + /* Parameter is node format */ + if (p[count] == ':') { + if (!hugetlb_node_alloc_supported()) { + pr_warn("HugeTLB: architecture can't support node specific alloc, ignoring!\n"); + return 0; + } + node = tmp; + p += count + 1; + if (node < 0 || node >= nr_online_nodes) + goto invalid; + /* Parse hugepages */ + if (sscanf(p, "%lu%n", &tmp, &count) != 1) + goto invalid; + if (!hugetlb_max_hstate) + default_hugepages_in_node[node] = tmp; + else + parsed_hstate->max_huge_pages_node[node] = tmp; + *mhp += tmp; + /* Go to parse next node*/ + if (p[count] == ',') + p += count + 1; + else + break; + } else { + if (p != s) + goto invalid; + *mhp = tmp; + break; + } + } /* * Global state is always initialized later in hugetlb_init. @@ -4098,6 +4193,10 @@ static int __init hugepages_setup(char *s) last_mhp = mhp; return 1; + +invalid: + pr_warn("HugeTLB: Invalid hugepages parameter %s\n", p); + return 0; } __setup("hugepages=", hugepages_setup); @@ -4159,6 +4258,7 @@ __setup("hugepagesz=", hugepagesz_setup); static int __init default_hugepagesz_setup(char *s) { unsigned long size; + int i; parsed_valid_hugepagesz = false; if (parsed_default_hugepagesz) { @@ -4187,6 +4287,9 @@ static int __init default_hugepagesz_setup(char *s) */ if (default_hstate_max_huge_pages) { default_hstate.max_huge_pages = default_hstate_max_huge_pages; + for (i = 0; i < nr_online_nodes; i++) + default_hstate.max_huge_pages_node[i] = + default_hugepages_in_node[i]; if (hstate_is_gigantic(&default_hstate)) hugetlb_hstate_alloc_pages(&default_hstate); default_hstate_max_huge_pages = 0; From 8eb42beac8d369f5443addd469879d152422a28d Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Fri, 5 Nov 2021 13:43:32 -0700 Subject: [PATCH 074/166] mm/migrate: de-duplicate migrate_reason strings In order to remove the need to manually keep three different files in synch, provide a common definition of the mapping between enum migrate_reason, and the associated strings for each enum item. 1. Use the tracing system's mapping of enums to strings, by redefining and reusing the MIGRATE_REASON and supporting macros, and using that to populate the string array in mm/debug.c. 2. Move enum migrate_reason to migrate_mode.h. This is not strictly necessary for this patch, but migrate mode and migrate reason go together, so this will slightly clarify things. Link: https://lkml.kernel.org/r/20210922041755.141817-2-jhubbard@nvidia.com Signed-off-by: John Hubbard Reviewed-by: Weizhao Ouyang Cc: "Huang, Ying" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 19 +------------------ include/linux/migrate_mode.h | 13 +++++++++++++ mm/debug.c | 20 +++++++++++--------- 3 files changed, 25 insertions(+), 27 deletions(-) diff --git a/include/linux/migrate.h b/include/linux/migrate.h index c8077e936691..3d154fe03c96 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -19,24 +19,7 @@ struct migration_target_control; */ #define MIGRATEPAGE_SUCCESS 0 -/* - * Keep sync with: - * - macro MIGRATE_REASON in include/trace/events/migrate.h - * - migrate_reason_names[MR_TYPES] in mm/debug.c - */ -enum migrate_reason { - MR_COMPACTION, - MR_MEMORY_FAILURE, - MR_MEMORY_HOTPLUG, - MR_SYSCALL, /* also applies to cpusets */ - MR_MEMPOLICY_MBIND, - MR_NUMA_MISPLACED, - MR_CONTIG_RANGE, - MR_LONGTERM_PIN, - MR_DEMOTION, - MR_TYPES -}; - +/* Defined in mm/debug.c: */ extern const char *migrate_reason_names[MR_TYPES]; #ifdef CONFIG_MIGRATION diff --git a/include/linux/migrate_mode.h b/include/linux/migrate_mode.h index 883c99249033..f37cc03f9369 100644 --- a/include/linux/migrate_mode.h +++ b/include/linux/migrate_mode.h @@ -19,4 +19,17 @@ enum migrate_mode { MIGRATE_SYNC_NO_COPY, }; +enum migrate_reason { + MR_COMPACTION, + MR_MEMORY_FAILURE, + MR_MEMORY_HOTPLUG, + MR_SYSCALL, /* also applies to cpusets */ + MR_MEMPOLICY_MBIND, + MR_NUMA_MISPLACED, + MR_CONTIG_RANGE, + MR_LONGTERM_PIN, + MR_DEMOTION, + MR_TYPES +}; + #endif /* MIGRATE_MODE_H_INCLUDED */ diff --git a/mm/debug.c b/mm/debug.c index fae0f81ad831..4333b6784a20 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -16,17 +16,19 @@ #include #include "internal.h" +#include + +/* + * Define EM() and EMe() so that MIGRATE_REASON from trace/events/migrate.h can + * be used to populate migrate_reason_names[]. + */ +#undef EM +#undef EMe +#define EM(a, b) b, +#define EMe(a, b) b const char *migrate_reason_names[MR_TYPES] = { - "compaction", - "memory_failure", - "memory_hotplug", - "syscall_or_cpuset", - "mempolicy_mbind", - "numa_misplaced", - "contig_range", - "longterm_pin", - "demotion", + MIGRATE_REASON }; const struct trace_print_flags pageflag_names[] = { From 20f9ba4f995247bb79e243741b8fdddbd76dd923 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 5 Nov 2021 13:43:35 -0700 Subject: [PATCH 075/166] mm: migrate: make demotion knob depend on migration The memory demotion needs to call migrate_pages() to do the jobs. And it is controlled by a knob, however, the knob doesn't depend on CONFIG_MIGRATION. The knob could be truned on even though MIGRATION is disabled, this will not cause any crash since migrate_pages() would just return -ENOSYS. But it is definitely not optimal to go through demotion path then retry regular swap every time. And it doesn't make too much sense to have the knob visible to the users when !MIGRATION. Move the related code from mempolicy.[h|c] to migrate.[h|c]. Link: https://lkml.kernel.org/r/20211015005559.246709-1-shy828301@gmail.com Signed-off-by: Yang Shi Acked-by: "Huang, Ying" Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 4 --- include/linux/migrate.h | 4 +++ mm/mempolicy.c | 61 --------------------------------------- mm/migrate.c | 61 +++++++++++++++++++++++++++++++++++++++ 4 files changed, 65 insertions(+), 65 deletions(-) diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 097bbbb37493..3c7595e81150 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -183,8 +183,6 @@ extern bool vma_migratable(struct vm_area_struct *vma); extern int mpol_misplaced(struct page *, struct vm_area_struct *, unsigned long); extern void mpol_put_task_policy(struct task_struct *); -extern bool numa_demotion_enabled; - static inline bool mpol_is_preferred_many(struct mempolicy *pol) { return (pol->mode == MPOL_PREFERRED_MANY); @@ -300,8 +298,6 @@ static inline nodemask_t *policy_nodemask_current(gfp_t gfp) return NULL; } -#define numa_demotion_enabled false - static inline bool mpol_is_preferred_many(struct mempolicy *pol) { return false; diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 3d154fe03c96..2d8130e05dc0 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -40,6 +40,8 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page); extern int migrate_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page, int extra_count); + +extern bool numa_demotion_enabled; #else static inline void putback_movable_pages(struct list_head *l) {} @@ -65,6 +67,8 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping, { return -ENOSYS; } + +#define numa_demotion_enabled false #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_COMPACTION diff --git a/mm/mempolicy.c b/mm/mempolicy.c index ce722333d9f6..f1080e0a566a 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -3057,64 +3057,3 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) p += scnprintf(p, buffer + maxlen - p, ":%*pbl", nodemask_pr_args(&nodes)); } - -bool numa_demotion_enabled = false; - -#ifdef CONFIG_SYSFS -static ssize_t numa_demotion_enabled_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) -{ - return sysfs_emit(buf, "%s\n", - numa_demotion_enabled? "true" : "false"); -} - -static ssize_t numa_demotion_enabled_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count) -{ - if (!strncmp(buf, "true", 4) || !strncmp(buf, "1", 1)) - numa_demotion_enabled = true; - else if (!strncmp(buf, "false", 5) || !strncmp(buf, "0", 1)) - numa_demotion_enabled = false; - else - return -EINVAL; - - return count; -} - -static struct kobj_attribute numa_demotion_enabled_attr = - __ATTR(demotion_enabled, 0644, numa_demotion_enabled_show, - numa_demotion_enabled_store); - -static struct attribute *numa_attrs[] = { - &numa_demotion_enabled_attr.attr, - NULL, -}; - -static const struct attribute_group numa_attr_group = { - .attrs = numa_attrs, -}; - -static int __init numa_init_sysfs(void) -{ - int err; - struct kobject *numa_kobj; - - numa_kobj = kobject_create_and_add("numa", mm_kobj); - if (!numa_kobj) { - pr_err("failed to create numa kobject\n"); - return -ENOMEM; - } - err = sysfs_create_group(numa_kobj, &numa_attr_group); - if (err) { - pr_err("failed to register numa group\n"); - goto delete_obj; - } - return 0; - -delete_obj: - kobject_put(numa_kobj); - return err; -} -subsys_initcall(numa_init_sysfs); -#endif diff --git a/mm/migrate.c b/mm/migrate.c index 1852d787e6ab..51e310a94516 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -3306,3 +3306,64 @@ static int __init migrate_on_reclaim_init(void) } late_initcall(migrate_on_reclaim_init); #endif /* CONFIG_HOTPLUG_CPU */ + +bool numa_demotion_enabled = false; + +#ifdef CONFIG_SYSFS +static ssize_t numa_demotion_enabled_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%s\n", + numa_demotion_enabled ? "true" : "false"); +} + +static ssize_t numa_demotion_enabled_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + if (!strncmp(buf, "true", 4) || !strncmp(buf, "1", 1)) + numa_demotion_enabled = true; + else if (!strncmp(buf, "false", 5) || !strncmp(buf, "0", 1)) + numa_demotion_enabled = false; + else + return -EINVAL; + + return count; +} + +static struct kobj_attribute numa_demotion_enabled_attr = + __ATTR(demotion_enabled, 0644, numa_demotion_enabled_show, + numa_demotion_enabled_store); + +static struct attribute *numa_attrs[] = { + &numa_demotion_enabled_attr.attr, + NULL, +}; + +static const struct attribute_group numa_attr_group = { + .attrs = numa_attrs, +}; + +static int __init numa_init_sysfs(void) +{ + int err; + struct kobject *numa_kobj; + + numa_kobj = kobject_create_and_add("numa", mm_kobj); + if (!numa_kobj) { + pr_err("failed to create numa kobject\n"); + return -ENOMEM; + } + err = sysfs_create_group(numa_kobj, &numa_attr_group); + if (err) { + pr_err("failed to register numa group\n"); + goto delete_obj; + } + return 0; + +delete_obj: + kobject_put(numa_kobj); + return err; +} +subsys_initcall(numa_init_sysfs); +#endif From 39cad8878a058070c79f3a824436de2de095672a Mon Sep 17 00:00:00 2001 From: "George G. Davis" Date: Fri, 5 Nov 2021 13:43:38 -0700 Subject: [PATCH 076/166] selftests/vm/transhuge-stress: fix ram size thinko When executing transhuge-stress with an argument to specify the virtual memory size for testing, the ram size is reported as 0, e.g. transhuge-stress 384 thp-mmap: allocate 192 transhuge pages, using 384 MiB virtual memory and 0 MiB of ram thp-mmap: 0.184 s/loop, 0.957 ms/page, 2090.265 MiB/s 192 succeed, 0 failed This appears to be due to a thinko in commit 0085d61fe05e ("selftests/vm/transhuge-stress: stress test for memory compaction"), where, at a guess, the intent was to base "xyz MiB of ram" on `ram` size. Here are results after using `ram` size: thp-mmap: allocate 192 transhuge pages, using 384 MiB virtual memory and 14 MiB of ram Link: https://lkml.kernel.org/r/20210825135843.29052-1-george_davis@mentor.com Fixes: 0085d61fe05e ("selftests/vm/transhuge-stress: stress test for memory compaction") Signed-off-by: George G. Davis Cc: Konstantin Khlebnikov Cc: Eugeniu Rosca Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/testing/selftests/vm/transhuge-stress.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/vm/transhuge-stress.c b/tools/testing/selftests/vm/transhuge-stress.c index fd7f1b4a96f9..5e4c036f6ad3 100644 --- a/tools/testing/selftests/vm/transhuge-stress.c +++ b/tools/testing/selftests/vm/transhuge-stress.c @@ -79,7 +79,7 @@ int main(int argc, char **argv) warnx("allocate %zd transhuge pages, using %zd MiB virtual memory" " and %zd MiB of ram", len >> HPAGE_SHIFT, len >> 20, - len >> (20 + HPAGE_SHIFT - PAGE_SHIFT - 1)); + ram >> (20 + HPAGE_SHIFT - PAGE_SHIFT - 1)); pagemap_fd = open("/proc/self/pagemap", O_RDONLY); if (pagemap_fd < 0) From 55fc0d91746759c71bc165bba62a2db64ac98e35 Mon Sep 17 00:00:00 2001 From: Rongwei Wang Date: Fri, 5 Nov 2021 13:43:41 -0700 Subject: [PATCH 077/166] mm, thp: lock filemap when truncating page cache Patch series "fix two bugs for file THP". This patch (of 2): Transparent huge page has supported read-only non-shmem files. The file- backed THP is collapsed by khugepaged and truncated when written (for shared libraries). However, there is a race when multiple writers truncate the same page cache concurrently. In that case, subpage(s) of file THP can be revealed by find_get_entry in truncate_inode_pages_range, which will trigger PageTail BUG_ON in truncate_inode_page, as follows: page:000000009e420ff2 refcount:1 mapcount:0 mapping:0000000000000000 index:0x7ff pfn:0x50c3ff head:0000000075ff816d order:9 compound_mapcount:0 compound_pincount:0 flags: 0x37fffe0000010815(locked|uptodate|lru|arch_1|head) raw: 37fffe0000000000 fffffe0013108001 dead000000000122 dead000000000400 raw: 0000000000000001 0000000000000000 00000000ffffffff 0000000000000000 head: 37fffe0000010815 fffffe001066bd48 ffff000404183c20 0000000000000000 head: 0000000000000600 0000000000000000 00000001ffffffff ffff000c0345a000 page dumped because: VM_BUG_ON_PAGE(PageTail(page)) ------------[ cut here ]------------ kernel BUG at mm/truncate.c:213! Internal error: Oops - BUG: 0 [#1] SMP Modules linked in: xfs(E) libcrc32c(E) rfkill(E) ... CPU: 14 PID: 11394 Comm: check_madvise_d Kdump: ... Hardware name: ECS, BIOS 0.0.0 02/06/2015 pstate: 60400005 (nZCv daif +PAN -UAO -TCO BTYPE=--) Call trace: truncate_inode_page+0x64/0x70 truncate_inode_pages_range+0x550/0x7e4 truncate_pagecache+0x58/0x80 do_dentry_open+0x1e4/0x3c0 vfs_open+0x38/0x44 do_open+0x1f0/0x310 path_openat+0x114/0x1dc do_filp_open+0x84/0x134 do_sys_openat2+0xbc/0x164 __arm64_sys_openat+0x74/0xc0 el0_svc_common.constprop.0+0x88/0x220 do_el0_svc+0x30/0xa0 el0_svc+0x20/0x30 el0_sync_handler+0x1a4/0x1b0 el0_sync+0x180/0x1c0 Code: aa0103e0 900061e1 910ec021 9400d300 (d4210000) This patch mainly to lock filemap when one enter truncate_pagecache(), avoiding truncating the same page cache concurrently. Link: https://lkml.kernel.org/r/20211025092134.18562-1-rongwei.wang@linux.alibaba.com Link: https://lkml.kernel.org/r/20211025092134.18562-2-rongwei.wang@linux.alibaba.com Fixes: eb6ecbed0aa2 ("mm, thp: relax the VM_DENYWRITE constraint on file-backed THPs") Signed-off-by: Xu Yu Signed-off-by: Rongwei Wang Suggested-by: Matthew Wilcox (Oracle) Tested-by: Song Liu Cc: Collin Fijalkovich Cc: Hugh Dickins Cc: Mike Kravetz Cc: William Kucharski Cc: Yang Shi Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/open.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/open.c b/fs/open.c index daa324606a41..9ec3cfca3b1a 100644 --- a/fs/open.c +++ b/fs/open.c @@ -856,8 +856,11 @@ static int do_dentry_open(struct file *f, * of THPs into the page cache will fail. */ smp_mb(); - if (filemap_nr_thps(inode->i_mapping)) + if (filemap_nr_thps(inode->i_mapping)) { + filemap_invalidate_lock(inode->i_mapping); truncate_pagecache(inode, 0); + filemap_invalidate_unlock(inode->i_mapping); + } } return 0; From 8468e937df1f31411d1e127fa38db064af051fe5 Mon Sep 17 00:00:00 2001 From: Rongwei Wang Date: Fri, 5 Nov 2021 13:43:44 -0700 Subject: [PATCH 078/166] mm, thp: fix incorrect unmap behavior for private pages When truncating pagecache on file THP, the private pages of a process should not be unmapped mapping. This incorrect behavior on a dynamic shared libraries which will cause related processes to happen core dump. A simple test for a DSO (Prerequisite is the DSO mapped in file THP): int main(int argc, char *argv[]) { int fd; fd = open(argv[1], O_WRONLY); if (fd < 0) { perror("open"); } close(fd); return 0; } The test only to open a target DSO, and do nothing. But this operation will lead one or more process to happen core dump. This patch mainly to fix this bug. Link: https://lkml.kernel.org/r/20211025092134.18562-3-rongwei.wang@linux.alibaba.com Fixes: eb6ecbed0aa2 ("mm, thp: relax the VM_DENYWRITE constraint on file-backed THPs") Signed-off-by: Rongwei Wang Tested-by: Xu Yu Cc: Matthew Wilcox (Oracle) Cc: Song Liu Cc: William Kucharski Cc: Hugh Dickins Cc: Yang Shi Cc: Mike Kravetz Cc: Collin Fijalkovich Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/open.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/fs/open.c b/fs/open.c index 9ec3cfca3b1a..e0df1536eb69 100644 --- a/fs/open.c +++ b/fs/open.c @@ -857,8 +857,17 @@ static int do_dentry_open(struct file *f, */ smp_mb(); if (filemap_nr_thps(inode->i_mapping)) { + struct address_space *mapping = inode->i_mapping; + filemap_invalidate_lock(inode->i_mapping); - truncate_pagecache(inode, 0); + /* + * unmap_mapping_range just need to be called once + * here, because the private pages is not need to be + * unmapped mapping (e.g. data segment of dynamic + * shared libraries here). + */ + unmap_mapping_range(mapping, 0, 0, 0); + truncate_inode_pages(mapping, 0); filemap_invalidate_unlock(inode->i_mapping); } } From fb25a77dde78dbcaa70c828ea8c2f7cf182510ae Mon Sep 17 00:00:00 2001 From: Lin Feng Date: Fri, 5 Nov 2021 13:43:47 -0700 Subject: [PATCH 079/166] mm/readahead.c: fix incorrect comments for get_init_ra_size In fact, formated values returned by get_init_ra_size are not that intuitive. This patch make the comments reflect its truth. Link: https://lkml.kernel.org/r/20211019104812.135602-1-linf@wangsu.com Signed-off-by: Lin Feng Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/readahead.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/readahead.c b/mm/readahead.c index 41b75d76d36e..88a84f254ed6 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -309,7 +309,7 @@ void force_page_cache_ra(struct readahead_control *ractl, * Set the initial window size, round to next power of 2 and square * for small size, x 4 for medium, and x 2 for large * for 128k (32 page) max ra - * 1-8 page = 32k initial, > 8 page = 128k initial + * 1-2 page = 16k, 3-4 page 32k, 5-8 page = 64k, > 8 page = 128k initial */ static unsigned long get_init_ra_size(unsigned long size, unsigned long max) { From 916caa127cb2239989b2ec45e4288db61de01ed9 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Fri, 5 Nov 2021 13:43:50 -0700 Subject: [PATCH 080/166] mm: nommu: kill arch_get_unmapped_area() When nommu, the arch_get_unmapped_area() will not be called, just kill it. Link: https://lkml.kernel.org/r/20210910061906.36299-1-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/nommu.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/mm/nommu.c b/mm/nommu.c index 02d2427b8f9e..8943dc0e2132 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1639,12 +1639,6 @@ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, } EXPORT_SYMBOL(remap_vmalloc_range); -unsigned long arch_get_unmapped_area(struct file *file, unsigned long addr, - unsigned long len, unsigned long pgoff, unsigned long flags) -{ - return -ENOMEM; -} - vm_fault_t filemap_fault(struct vm_fault *vmf) { BUG(); From e3820ab252dd9fef6af875553c49b8d02339421d Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Fri, 5 Nov 2021 13:43:53 -0700 Subject: [PATCH 081/166] selftest/vm: fix ksm selftest to run with different NUMA topologies Platforms can have non-contiguous NUMA nodes like below #numactl -H available: 2 nodes (0,8) ..... node distances: node 0 8 0: 10 40 8: 40 10 #numactl -H available: 1 nodes (1) .... node distances: node 1 1: 10 Hence update the test to not assume the presence of Node 0 and 1 and also use numa_num_configured_nodes() instead of numa_max_node for finding whether to skip the test. Link: https://lkml.kernel.org/r/20210914141414.350759-1-aneesh.kumar@linux.ibm.com Fixes: 82e717ad3501 ("selftests: vm: add KSM merging across nodes test") Signed-off-by: Aneesh Kumar K.V Reviewed-by: Pasha Tatashin Cc: Zhansaya Bagdauletkyzy Cc: Pavel Tatashin Cc: Tyler Hicks Cc: Hugh Dickins Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/testing/selftests/vm/ksm_tests.c | 29 +++++++++++++++++++++++--- 1 file changed, 26 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/vm/ksm_tests.c b/tools/testing/selftests/vm/ksm_tests.c index b61dcdb44c5b..0e142d25b031 100644 --- a/tools/testing/selftests/vm/ksm_tests.c +++ b/tools/testing/selftests/vm/ksm_tests.c @@ -354,12 +354,34 @@ err_out: return KSFT_FAIL; } +static int get_next_mem_node(int node) +{ + + long node_size; + int mem_node = 0; + int i, max_node = numa_max_node(); + + for (i = node + 1; i <= max_node + node; i++) { + mem_node = i % (max_node + 1); + node_size = numa_node_size(mem_node, NULL); + if (node_size > 0) + break; + } + return mem_node; +} + +static int get_first_mem_node(void) +{ + return get_next_mem_node(numa_max_node()); +} + static int check_ksm_numa_merge(int mapping, int prot, int timeout, bool merge_across_nodes, size_t page_size) { void *numa1_map_ptr, *numa2_map_ptr; struct timespec start_time; int page_count = 2; + int first_node; if (clock_gettime(CLOCK_MONOTONIC_RAW, &start_time)) { perror("clock_gettime"); @@ -370,7 +392,7 @@ static int check_ksm_numa_merge(int mapping, int prot, int timeout, bool merge_a perror("NUMA support not enabled"); return KSFT_SKIP; } - if (numa_max_node() < 1) { + if (numa_num_configured_nodes() <= 1) { printf("At least 2 NUMA nodes must be available\n"); return KSFT_SKIP; } @@ -378,8 +400,9 @@ static int check_ksm_numa_merge(int mapping, int prot, int timeout, bool merge_a return KSFT_FAIL; /* allocate 2 pages in 2 different NUMA nodes and fill them with the same data */ - numa1_map_ptr = numa_alloc_onnode(page_size, 0); - numa2_map_ptr = numa_alloc_onnode(page_size, 1); + first_node = get_first_mem_node(); + numa1_map_ptr = numa_alloc_onnode(page_size, first_node); + numa2_map_ptr = numa_alloc_onnode(page_size, get_next_mem_node(first_node)); if (!numa1_map_ptr || !numa2_map_ptr) { perror("numa_alloc_onnode"); return KSFT_FAIL; From 325254899684adf32b95ae59000dec4a6853e930 Mon Sep 17 00:00:00 2001 From: Pedro Demarchi Gomes Date: Fri, 5 Nov 2021 13:43:56 -0700 Subject: [PATCH 082/166] selftests: vm: add KSM huge pages merging time test Add test case of KSM merging time using mostly huge pages Link: https://lkml.kernel.org/r/20211013044045.360251-1-pedrodemargomes@gmail.com Signed-off-by: Pedro Demarchi Gomes Cc: Zhansaya Bagdauletkyzy Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/testing/selftests/vm/ksm_tests.c | 125 ++++++++++++++++++++++++- 1 file changed, 124 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/vm/ksm_tests.c b/tools/testing/selftests/vm/ksm_tests.c index 0e142d25b031..1436e1a9a3d3 100644 --- a/tools/testing/selftests/vm/ksm_tests.c +++ b/tools/testing/selftests/vm/ksm_tests.c @@ -5,6 +5,10 @@ #include #include #include +#include +#include +#include +#include #include "../kselftest.h" #include "../../../../include/vdso/time64.h" @@ -18,6 +22,15 @@ #define KSM_MERGE_ACROSS_NODES_DEFAULT true #define MB (1ul << 20) +#define PAGE_SHIFT 12 +#define HPAGE_SHIFT 21 + +#define PAGE_SIZE (1 << PAGE_SHIFT) +#define HPAGE_SIZE (1 << HPAGE_SHIFT) + +#define PAGEMAP_PRESENT(ent) (((ent) & (1ull << 63)) != 0) +#define PAGEMAP_PFN(ent) ((ent) & ((1ull << 55) - 1)) + struct ksm_sysfs { unsigned long max_page_sharing; unsigned long merge_across_nodes; @@ -34,6 +47,7 @@ enum ksm_test_name { CHECK_KSM_ZERO_PAGE_MERGE, CHECK_KSM_NUMA_MERGE, KSM_MERGE_TIME, + KSM_MERGE_TIME_HUGE_PAGES, KSM_COW_TIME }; @@ -99,6 +113,9 @@ static void print_help(void) " -U (page unmerging)\n" " -P evaluate merging time and speed.\n" " For this test, the size of duplicated memory area (in MiB)\n" + " must be provided using -s option\n" + " -H evaluate merging time and speed of area allocated mostly with huge pages\n" + " For this test, the size of duplicated memory area (in MiB)\n" " must be provided using -s option\n" " -C evaluate the time required to break COW of merged pages.\n\n"); @@ -439,6 +456,101 @@ err_out: return KSFT_FAIL; } +int64_t allocate_transhuge(void *ptr, int pagemap_fd) +{ + uint64_t ent[2]; + + /* drop pmd */ + if (mmap(ptr, HPAGE_SIZE, PROT_READ | PROT_WRITE, + MAP_FIXED | MAP_ANONYMOUS | + MAP_NORESERVE | MAP_PRIVATE, -1, 0) != ptr) + errx(2, "mmap transhuge"); + + if (madvise(ptr, HPAGE_SIZE, MADV_HUGEPAGE)) + err(2, "MADV_HUGEPAGE"); + + /* allocate transparent huge page */ + *(volatile void **)ptr = ptr; + + if (pread(pagemap_fd, ent, sizeof(ent), + (uintptr_t)ptr >> (PAGE_SHIFT - 3)) != sizeof(ent)) + err(2, "read pagemap"); + + if (PAGEMAP_PRESENT(ent[0]) && PAGEMAP_PRESENT(ent[1]) && + PAGEMAP_PFN(ent[0]) + 1 == PAGEMAP_PFN(ent[1]) && + !(PAGEMAP_PFN(ent[0]) & ((1 << (HPAGE_SHIFT - PAGE_SHIFT)) - 1))) + return PAGEMAP_PFN(ent[0]); + + return -1; +} + +static int ksm_merge_hugepages_time(int mapping, int prot, int timeout, size_t map_size) +{ + void *map_ptr, *map_ptr_orig; + struct timespec start_time, end_time; + unsigned long scan_time_ns; + int pagemap_fd, n_normal_pages, n_huge_pages; + + map_size *= MB; + size_t len = map_size; + + len -= len % HPAGE_SIZE; + map_ptr_orig = mmap(NULL, len + HPAGE_SIZE, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_NORESERVE | MAP_PRIVATE, -1, 0); + map_ptr = map_ptr_orig + HPAGE_SIZE - (uintptr_t)map_ptr_orig % HPAGE_SIZE; + + if (map_ptr_orig == MAP_FAILED) + err(2, "initial mmap"); + + if (madvise(map_ptr, len + HPAGE_SIZE, MADV_HUGEPAGE)) + err(2, "MADV_HUGEPAGE"); + + pagemap_fd = open("/proc/self/pagemap", O_RDONLY); + if (pagemap_fd < 0) + err(2, "open pagemap"); + + n_normal_pages = 0; + n_huge_pages = 0; + for (void *p = map_ptr; p < map_ptr + len; p += HPAGE_SIZE) { + if (allocate_transhuge(p, pagemap_fd) < 0) + n_normal_pages++; + else + n_huge_pages++; + } + printf("Number of normal pages: %d\n", n_normal_pages); + printf("Number of huge pages: %d\n", n_huge_pages); + + memset(map_ptr, '*', len); + + if (clock_gettime(CLOCK_MONOTONIC_RAW, &start_time)) { + perror("clock_gettime"); + goto err_out; + } + if (ksm_merge_pages(map_ptr, map_size, start_time, timeout)) + goto err_out; + if (clock_gettime(CLOCK_MONOTONIC_RAW, &end_time)) { + perror("clock_gettime"); + goto err_out; + } + + scan_time_ns = (end_time.tv_sec - start_time.tv_sec) * NSEC_PER_SEC + + (end_time.tv_nsec - start_time.tv_nsec); + + printf("Total size: %lu MiB\n", map_size / MB); + printf("Total time: %ld.%09ld s\n", scan_time_ns / NSEC_PER_SEC, + scan_time_ns % NSEC_PER_SEC); + printf("Average speed: %.3f MiB/s\n", (map_size / MB) / + ((double)scan_time_ns / NSEC_PER_SEC)); + + munmap(map_ptr_orig, len + HPAGE_SIZE); + return KSFT_PASS; + +err_out: + printf("Not OK\n"); + munmap(map_ptr_orig, len + HPAGE_SIZE); + return KSFT_FAIL; +} + static int ksm_merge_time(int mapping, int prot, int timeout, size_t map_size) { void *map_ptr; @@ -564,7 +676,7 @@ int main(int argc, char *argv[]) bool merge_across_nodes = KSM_MERGE_ACROSS_NODES_DEFAULT; long size_MB = 0; - while ((opt = getopt(argc, argv, "ha:p:l:z:m:s:MUZNPC")) != -1) { + while ((opt = getopt(argc, argv, "ha:p:l:z:m:s:MUZNPCH")) != -1) { switch (opt) { case 'a': prot = str_to_prot(optarg); @@ -618,6 +730,9 @@ int main(int argc, char *argv[]) case 'P': test_name = KSM_MERGE_TIME; break; + case 'H': + test_name = KSM_MERGE_TIME_HUGE_PAGES; + break; case 'C': test_name = KSM_COW_TIME; break; @@ -670,6 +785,14 @@ int main(int argc, char *argv[]) ret = ksm_merge_time(MAP_PRIVATE | MAP_ANONYMOUS, prot, ksm_scan_limit_sec, size_MB); break; + case KSM_MERGE_TIME_HUGE_PAGES: + if (size_MB == 0) { + printf("Option '-s' is required.\n"); + return KSFT_FAIL; + } + ret = ksm_merge_hugepages_time(MAP_PRIVATE | MAP_ANONYMOUS, prot, + ksm_scan_limit_sec, size_MB); + break; case KSM_COW_TIME: ret = ksm_cow_time(MAP_PRIVATE | MAP_ANONYMOUS, prot, ksm_scan_limit_sec, page_size); From af1c31acc85325aec2bcc5941fb7a02e19143503 Mon Sep 17 00:00:00 2001 From: Liu Shixin Date: Fri, 5 Nov 2021 13:43:59 -0700 Subject: [PATCH 083/166] mm/vmstat: annotate data race for zone->free_area[order].nr_free KCSAN reports a data-race on v5.10 which also exists on mainline: BUG: KCSAN: data-race in extfrag_for_order+0x33/0x2d0 race at unknown origin, with read to 0xffff9ee9bfffab48 of 8 bytes by task 34 on cpu 1: extfrag_for_order+0x33/0x2d0 kcompactd+0x5f0/0xce0 kthread+0x1f9/0x220 ret_from_fork+0x22/0x30 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 34 Comm: kcompactd0 Not tainted 5.10.0+ #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 Access to zone->free_area[order].nr_free in extfrag_for_order() and frag_show_print() is lockless. That's intentional and the stats are a rough estimate anyway. Annotate them with data_race(). [liushixin2@huawei.com: add comments] Link: https://lkml.kernel.org/r/20210918084655.2696522-1-liushixin2@huawei.com Link: https://lkml.kernel.org/r/20210908015606.3999871-1-liushixin2@huawei.com Signed-off-by: Liu Shixin Cc: "Paul E . McKenney" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmstat.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/mm/vmstat.c b/mm/vmstat.c index 0f4643e5324d..0fde7470368d 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1070,8 +1070,13 @@ static void fill_contig_page_info(struct zone *zone, for (order = 0; order < MAX_ORDER; order++) { unsigned long blocks; - /* Count number of free blocks */ - blocks = zone->free_area[order].nr_free; + /* + * Count number of free blocks. + * + * Access to nr_free is lockless as nr_free is used only for + * diagnostic purposes. Use data_race to avoid KCSAN warning. + */ + blocks = data_race(zone->free_area[order].nr_free); info->free_blocks_total += blocks; /* Count free base pages */ @@ -1446,7 +1451,11 @@ static void frag_show_print(struct seq_file *m, pg_data_t *pgdat, seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name); for (order = 0; order < MAX_ORDER; ++order) - seq_printf(m, "%6lu ", zone->free_area[order].nr_free); + /* + * Access to nr_free is lockless as nr_free is used only for + * printing purposes. Use data_race to avoid KCSAN warning. + */ + seq_printf(m, "%6lu ", data_race(zone->free_area[order].nr_free)); seq_putc(m, '\n'); } From a997058679fb2bc244270c02c864595fc41f51d3 Mon Sep 17 00:00:00 2001 From: Lin Feng Date: Fri, 5 Nov 2021 13:44:02 -0700 Subject: [PATCH 084/166] mm: vmstat.c: make extfrag_index show more pretty fragmentation_index may return -1000 and the corresponding formated value showed by seq_printf will take a negative signatrue, but other positive formated values don't take a positive signatrue, so the output becomes unaligned. before: Node 0, zone DMA -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 Node 0, zone DMA32 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 Node 0, zone Normal -1.000 -1.000 -1.000 -1.000 0.931 0.966 0.983 0.992 0.996 0.998 0.999 after this patch: Node 0, zone DMA -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 Node 0, zone DMA32 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 Node 0, zone Normal -1.000 -1.000 -1.000 -1.000 0.931 0.966 0.983 0.992 0.996 0.998 0.999 Link: https://lkml.kernel.org/r/20211019103241.134797-1-linf@wangsu.com Signed-off-by: Lin Feng Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmstat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/vmstat.c b/mm/vmstat.c index 0fde7470368d..d701c335628c 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -2191,7 +2191,7 @@ static void extfrag_show_print(struct seq_file *m, for (order = 0; order < MAX_ORDER; ++order) { fill_contig_page_info(zone, order, &info); index = __fragmentation_index(order, &info); - seq_printf(m, "%d.%03d ", index / 1000, index % 1000); + seq_printf(m, "%2d.%03d ", index / 1000, index % 1000); } seq_putc(m, '\n'); From 39b2e5cae43dd05462125ff9024a0e0cf431e958 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:05 -0700 Subject: [PATCH 085/166] selftests/vm: make MADV_POPULATE_(READ|WRITE) use in-tree headers The madv_populate selftest currently builds with a warning when the local installed headers (via the distribution) don't include MADV_POPULATE_READ and MADV_POPULATE_WRITE. The warning is correct, because the test cannot locate the necessary header. The reason is that the in-tree installed headers (usr/include) have a "linux" instead of a "sys" subdirectory. Including "linux/mman.h" instead of "sys/mman.h" doesn't work (e.g., mmap() and madvise() are not defined that way). The only thing that seems to work is including "linux/mman.h" in addition to "sys/mman.h". We can get rid of our availability check and simplify. Link: https://lkml.kernel.org/r/20211015165758.41374-1-david@redhat.com Signed-off-by: David Hildenbrand Reported-by: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/testing/selftests/vm/madv_populate.c | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) diff --git a/tools/testing/selftests/vm/madv_populate.c b/tools/testing/selftests/vm/madv_populate.c index b959e4ebdad4..3ee0e8275600 100644 --- a/tools/testing/selftests/vm/madv_populate.c +++ b/tools/testing/selftests/vm/madv_populate.c @@ -14,12 +14,11 @@ #include #include #include +#include #include #include "../kselftest.h" -#if defined(MADV_POPULATE_READ) && defined(MADV_POPULATE_WRITE) - /* * For now, we're using 2 MiB of private anonymous memory for all tests. */ @@ -328,15 +327,3 @@ int main(int argc, char **argv) err, ksft_test_num()); return ksft_exit_pass(); } - -#else /* defined(MADV_POPULATE_READ) && defined(MADV_POPULATE_WRITE) */ - -#warning "missing MADV_POPULATE_READ or MADV_POPULATE_WRITE definition" - -int main(int argc, char **argv) -{ - ksft_print_header(); - ksft_exit_skip("MADV_POPULATE_READ or MADV_POPULATE_WRITE not defined\n"); -} - -#endif /* defined(MADV_POPULATE_READ) && defined(MADV_POPULATE_WRITE) */ From ac62554ba7060c8824d7821c1342673f1e13c31d Mon Sep 17 00:00:00 2001 From: Tang Yizhou Date: Fri, 5 Nov 2021 13:44:08 -0700 Subject: [PATCH 086/166] mm/memory_hotplug: add static qualifier for online_policy_to_str() online_policy_to_str is only used in memory_hotplug.c and should be defined as static. Link: https://lkml.kernel.org/r/20210913024534.26161-1-tangyizhou@huawei.com Signed-off-by: Tang Yizhou Reviewed-by: Muchun Song Reviewed-by: David Hildenbrand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index feffaa9423fe..afaae370b8cd 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -57,7 +57,7 @@ enum { ONLINE_POLICY_AUTO_MOVABLE, }; -const char *online_policy_to_str[] = { +static const char * const online_policy_to_str[] = { [ONLINE_POLICY_CONTIG_ZONES] = "contig-zones", [ONLINE_POLICY_AUTO_MOVABLE] = "auto-movable", }; From d83fe3c99d270df6ae40ce21842af0448797f3e0 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:11 -0700 Subject: [PATCH 087/166] memory-hotplug.rst: fix two instances of "movablecore" that should be "movable_node" Patch series "memory-hotplug.rst: document the "auto-movable" online policy". Now that the memory-hotplug.rst overhaul is upstream, proper documentation for the "auto-movable" online policy, documenting all new toggles and options. Along, two fixes for the original overhaul. This patch (of 3): We really want to refer to the "movable_node" kernel command line parameter here. Link: https://lkml.kernel.org/r/20210930144117.23641-2-david@redhat.com Fixes: ac3332c44767 ("memory-hotplug.rst: complete admin-guide overhaul") Signed-off-by: David Hildenbrand Acked-by: Mike Rapoport Cc: Jonathan Corbet Cc: Michal Hocko Cc: Oscar Salvador Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/mm/memory-hotplug.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/admin-guide/mm/memory-hotplug.rst b/Documentation/admin-guide/mm/memory-hotplug.rst index 03dfbc925252..27d748cb6ee0 100644 --- a/Documentation/admin-guide/mm/memory-hotplug.rst +++ b/Documentation/admin-guide/mm/memory-hotplug.rst @@ -166,7 +166,7 @@ Or alternatively:: % echo 1 > /sys/devices/system/memory/memoryXXX/online The kernel will select the target zone automatically, usually defaulting to -``ZONE_NORMAL`` unless ``movablecore=1`` has been specified on the kernel +``ZONE_NORMAL`` unless ``movable_node`` has been specified on the kernel command line or if the memory block would intersect the ZONE_MOVABLE already. One can explicitly request to associate an offline memory block with @@ -393,7 +393,7 @@ command line parameters are relevant: ======================== ======================================================= ``memhp_default_state`` configure auto-onlining by essentially setting ``/sys/devices/system/memory/auto_online_blocks``. -``movablecore`` configure automatic zone selection of the kernel. When +``movable_node`` configure automatic zone selection in the kernel. When set, the kernel will default to ZONE_MOVABLE, unless other zones can be kept contiguous. ======================== ======================================================= From a8db400f997c6e9ff505fb965a91fdb8427d366f Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:14 -0700 Subject: [PATCH 088/166] memory-hotplug.rst: fix wrong /sys/module/memory_hotplug/parameters/ path We accidentially added a superfluous "s". Link: https://lkml.kernel.org/r/20210930144117.23641-3-david@redhat.com Fixes: ac3332c44767 ("memory-hotplug.rst: complete admin-guide overhaul") Signed-off-by: David Hildenbrand Acked-by: Mike Rapoport Cc: Jonathan Corbet Cc: Michal Hocko Cc: Oscar Salvador Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/mm/memory-hotplug.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/admin-guide/mm/memory-hotplug.rst b/Documentation/admin-guide/mm/memory-hotplug.rst index 27d748cb6ee0..ee00b70dedde 100644 --- a/Documentation/admin-guide/mm/memory-hotplug.rst +++ b/Documentation/admin-guide/mm/memory-hotplug.rst @@ -410,7 +410,7 @@ them with ``memory_hotplug.`` such as:: and they can be observed (and some even modified at runtime) via:: - /sys/modules/memory_hotplug/parameters/ + /sys/module/memory_hotplug/parameters/ The following module parameters are currently defined: From 9e122cc1bdc4e8c8e2a97060ab85f9ee657a01a4 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:17 -0700 Subject: [PATCH 089/166] memory-hotplug.rst: document the "auto-movable" online policy Commit e83a437faa62 ("mm/memory_hotplug: introduce "auto-movable" online policy") introduced a new memory online policy to automatically select a zone for memory blocks to be onlined. It added a way to set the active online policy and tunables for the auto-movable online policy. Follow-up commits tweaked the "auto-movable" policy to also consider memory device details when selecting zones for memory blocks to be onlined. Let's document the new toggles and how the two online policies we have work. [david@redhat.com: updates] Link: https://lkml.kernel.org/r/20211011082058.6076-4-david@redhat.com Link: https://lkml.kernel.org/r/20210930144117.23641-4-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Mike Rapoport Cc: Jonathan Corbet Cc: Michal Hocko Cc: Oscar Salvador Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- .../admin-guide/mm/memory-hotplug.rst | 139 +++++++++++++++--- 1 file changed, 120 insertions(+), 19 deletions(-) diff --git a/Documentation/admin-guide/mm/memory-hotplug.rst b/Documentation/admin-guide/mm/memory-hotplug.rst index ee00b70dedde..0f56ecd8ac05 100644 --- a/Documentation/admin-guide/mm/memory-hotplug.rst +++ b/Documentation/admin-guide/mm/memory-hotplug.rst @@ -165,9 +165,8 @@ Or alternatively:: % echo 1 > /sys/devices/system/memory/memoryXXX/online -The kernel will select the target zone automatically, usually defaulting to -``ZONE_NORMAL`` unless ``movable_node`` has been specified on the kernel -command line or if the memory block would intersect the ZONE_MOVABLE already. +The kernel will select the target zone automatically, depending on the +configured ``online_policy``. One can explicitly request to associate an offline memory block with ZONE_MOVABLE by:: @@ -198,6 +197,9 @@ Auto-onlining can be enabled by writing ``online``, ``online_kernel`` or % echo online > /sys/devices/system/memory/auto_online_blocks +Similarly to manual onlining, with ``online`` the kernel will select the +target zone automatically, depending on the configured ``online_policy``. + Modifying the auto-online behavior will only affect all subsequently added memory blocks only. @@ -393,11 +395,16 @@ command line parameters are relevant: ======================== ======================================================= ``memhp_default_state`` configure auto-onlining by essentially setting ``/sys/devices/system/memory/auto_online_blocks``. -``movable_node`` configure automatic zone selection in the kernel. When - set, the kernel will default to ZONE_MOVABLE, unless - other zones can be kept contiguous. +``movable_node`` configure automatic zone selection in the kernel when + using the ``contig-zones`` online policy. When + set, the kernel will default to ZONE_MOVABLE when + onlining a memory block, unless other zones can be kept + contiguous. ======================== ======================================================= +See Documentation/admin-guide/kernel-parameters.txt for a more generic +description of these command line parameters. + Module Parameters ------------------ @@ -414,20 +421,114 @@ and they can be observed (and some even modified at runtime) via:: The following module parameters are currently defined: -======================== ======================================================= -``memmap_on_memory`` read-write: Allocate memory for the memmap from the - added memory block itself. Even if enabled, actual - support depends on various other system properties and - should only be regarded as a hint whether the behavior - would be desired. +================================ =============================================== +``memmap_on_memory`` read-write: Allocate memory for the memmap from + the added memory block itself. Even if enabled, + actual support depends on various other system + properties and should only be regarded as a + hint whether the behavior would be desired. - While allocating the memmap from the memory block - itself makes memory hotplug less likely to fail and - keeps the memmap on the same NUMA node in any case, it - can fragment physical memory in a way that huge pages - in bigger granularity cannot be formed on hotplugged - memory. -======================== ======================================================= + While allocating the memmap from the memory + block itself makes memory hotplug less likely + to fail and keeps the memmap on the same NUMA + node in any case, it can fragment physical + memory in a way that huge pages in bigger + granularity cannot be formed on hotplugged + memory. +``online_policy`` read-write: Set the basic policy used for + automatic zone selection when onlining memory + blocks without specifying a target zone. + ``contig-zones`` has been the kernel default + before this parameter was added. After an + online policy was configured and memory was + online, the policy should not be changed + anymore. + + When set to ``contig-zones``, the kernel will + try keeping zones contiguous. If a memory block + intersects multiple zones or no zone, the + behavior depends on the ``movable_node`` kernel + command line parameter: default to ZONE_MOVABLE + if set, default to the applicable kernel zone + (usually ZONE_NORMAL) if not set. + + When set to ``auto-movable``, the kernel will + try onlining memory blocks to ZONE_MOVABLE if + possible according to the configuration and + memory device details. With this policy, one + can avoid zone imbalances when eventually + hotplugging a lot of memory later and still + wanting to be able to hotunplug as much as + possible reliably, very desirable in + virtualized environments. This policy ignores + the ``movable_node`` kernel command line + parameter and isn't really applicable in + environments that require it (e.g., bare metal + with hotunpluggable nodes) where hotplugged + memory might be exposed via the + firmware-provided memory map early during boot + to the system instead of getting detected, + added and onlined later during boot (such as + done by virtio-mem or by some hypervisors + implementing emulated DIMMs). As one example, a + hotplugged DIMM will be onlined either + completely to ZONE_MOVABLE or completely to + ZONE_NORMAL, not a mixture. + As another example, as many memory blocks + belonging to a virtio-mem device will be + onlined to ZONE_MOVABLE as possible, + special-casing units of memory blocks that can + only get hotunplugged together. *This policy + does not protect from setups that are + problematic with ZONE_MOVABLE and does not + change the zone of memory blocks dynamically + after they were onlined.* +``auto_movable_ratio`` read-write: Set the maximum MOVABLE:KERNEL + memory ratio in % for the ``auto-movable`` + online policy. Whether the ratio applies only + for the system across all NUMA nodes or also + per NUMA nodes depends on the + ``auto_movable_numa_aware`` configuration. + + All accounting is based on present memory pages + in the zones combined with accounting per + memory device. Memory dedicated to the CMA + allocator is accounted as MOVABLE, although + residing on one of the kernel zones. The + possible ratio depends on the actual workload. + The kernel default is "301" %, for example, + allowing for hotplugging 24 GiB to a 8 GiB VM + and automatically onlining all hotplugged + memory to ZONE_MOVABLE in many setups. The + additional 1% deals with some pages being not + present, for example, because of some firmware + allocations. + + Note that ZONE_NORMAL memory provided by one + memory device does not allow for more + ZONE_MOVABLE memory for a different memory + device. As one example, onlining memory of a + hotplugged DIMM to ZONE_NORMAL will not allow + for another hotplugged DIMM to get onlined to + ZONE_MOVABLE automatically. In contrast, memory + hotplugged by a virtio-mem device that got + onlined to ZONE_NORMAL will allow for more + ZONE_MOVABLE memory within *the same* + virtio-mem device. +``auto_movable_numa_aware`` read-write: Configure whether the + ``auto_movable_ratio`` in the ``auto-movable`` + online policy also applies per NUMA + node in addition to the whole system across all + NUMA nodes. The kernel default is "Y". + + Disabling NUMA awareness can be helpful when + dealing with NUMA nodes that should be + completely hotunpluggable, onlining the memory + completely to ZONE_MOVABLE automatically if + possible. + + Parameter availability depends on CONFIG_NUMA. +================================ =============================================== ZONE_MOVABLE ============ From 71b6f2dda824d044242145db8dc10c2037242899 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:20 -0700 Subject: [PATCH 090/166] mm/memory_hotplug: remove CONFIG_X86_64_ACPI_NUMA dependency from CONFIG_MEMORY_HOTPLUG Patch series "mm/memory_hotplug: Kconfig and 32 bit cleanups". Some cleanups around CONFIG_MEMORY_HOTPLUG, including removing 32 bit leftovers of memory hotplug support. This patch (of 6): SPARSEMEM is the only possible memory model for x86-64, FLATMEM is not possible: config ARCH_FLATMEM_ENABLE def_bool y depends on X86_32 && !NUMA And X86_64_ACPI_NUMA (obviously) only supports x86-64: config X86_64_ACPI_NUMA def_bool y depends on X86_64 && NUMA && ACPI && PCI Let's just remove the CONFIG_X86_64_ACPI_NUMA dependency, as it does no longer make sense. Link: https://lkml.kernel.org/r/20210929143600.49379-2-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: Jonathan Corbet Cc: Alex Shi Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Dave Hansen Cc: Andy Lutomirski Cc: Peter Zijlstra Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: "Michael S. Tsirkin" Cc: Jason Wang Cc: Shuah Khan Cc: Michal Hocko Cc: Mike Rapoport Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/Kconfig b/mm/Kconfig index 9f1e0098522c..b2bf73c90a38 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -123,7 +123,7 @@ config ARCH_ENABLE_MEMORY_HOTPLUG config MEMORY_HOTPLUG bool "Allow for memory hot-add" select MEMORY_ISOLATION - depends on SPARSEMEM || X86_64_ACPI_NUMA + depends on SPARSEMEM depends on ARCH_ENABLE_MEMORY_HOTPLUG depends on 64BIT || BROKEN select NUMA_KEEP_MEMINFO if NUMA From 50f9481ed9fb8a2d2a06a155634c7f9eeff9fa61 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:24 -0700 Subject: [PATCH 091/166] mm/memory_hotplug: remove CONFIG_MEMORY_HOTPLUG_SPARSE CONFIG_MEMORY_HOTPLUG depends on CONFIG_SPARSEMEM, so there is no need for CONFIG_MEMORY_HOTPLUG_SPARSE anymore; adjust all instances to use CONFIG_MEMORY_HOTPLUG and remove CONFIG_MEMORY_HOTPLUG_SPARSE. Link: https://lkml.kernel.org/r/20210929143600.49379-3-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Shuah Khan [kselftest] Acked-by: Greg Kroah-Hartman Acked-by: Oscar Salvador Cc: Alex Shi Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Dave Hansen Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jason Wang Cc: Jonathan Corbet Cc: Michael Ellerman Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Mike Rapoport Cc: Paul Mackerras Cc: Peter Zijlstra Cc: "Rafael J. Wysocki" Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/include/asm/machdep.h | 2 +- arch/powerpc/kernel/setup_64.c | 2 +- arch/powerpc/platforms/powernv/setup.c | 4 ++-- arch/powerpc/platforms/pseries/setup.c | 2 +- drivers/base/Makefile | 2 +- drivers/base/node.c | 9 ++++--- drivers/virtio/Kconfig | 2 +- include/linux/memory.h | 24 ++++++++----------- include/linux/node.h | 4 ++-- lib/Kconfig.debug | 2 +- mm/Kconfig | 4 ---- mm/memory_hotplug.c | 2 -- tools/testing/selftests/memory-hotplug/config | 1 - 13 files changed, 24 insertions(+), 36 deletions(-) diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 764f2732a821..d8a2ca007082 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -32,7 +32,7 @@ struct machdep_calls { void (*iommu_save)(void); void (*iommu_restore)(void); #endif -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifdef CONFIG_MEMORY_HOTPLUG unsigned long (*memory_block_size)(void); #endif #endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 1777e992b20b..6052f5d5ded3 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -912,7 +912,7 @@ void __init setup_per_cpu_areas(void) } #endif -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifdef CONFIG_MEMORY_HOTPLUG unsigned long memory_block_size_bytes(void) { if (ppc_md.memory_block_size) diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index a8db3f153063..ad56a54ac9c5 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -440,7 +440,7 @@ static void pnv_kexec_cpu_down(int crash_shutdown, int secondary) } #endif /* CONFIG_KEXEC_CORE */ -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifdef CONFIG_MEMORY_HOTPLUG static unsigned long pnv_memory_block_size(void) { /* @@ -553,7 +553,7 @@ define_machine(powernv) { #ifdef CONFIG_KEXEC_CORE .kexec_cpu_down = pnv_kexec_cpu_down, #endif -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifdef CONFIG_MEMORY_HOTPLUG .memory_block_size = pnv_memory_block_size, #endif }; diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index f79126f16258..d29f6f1f7f37 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -1089,7 +1089,7 @@ define_machine(pseries) { .machine_kexec = pSeries_machine_kexec, .kexec_cpu_down = pseries_kexec_cpu_down, #endif -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifdef CONFIG_MEMORY_HOTPLUG .memory_block_size = pseries_memory_block_size, #endif }; diff --git a/drivers/base/Makefile b/drivers/base/Makefile index ef8e44a7d288..02f7f1358e86 100644 --- a/drivers/base/Makefile +++ b/drivers/base/Makefile @@ -13,7 +13,7 @@ obj-y += power/ obj-$(CONFIG_ISA_BUS_API) += isa.o obj-y += firmware_loader/ obj-$(CONFIG_NUMA) += node.o -obj-$(CONFIG_MEMORY_HOTPLUG_SPARSE) += memory.o +obj-$(CONFIG_MEMORY_HOTPLUG) += memory.o ifeq ($(CONFIG_SYSFS),y) obj-$(CONFIG_MODULES) += module.o endif diff --git a/drivers/base/node.c b/drivers/base/node.c index c56d34f8158f..b5a4ba18f9f9 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -629,7 +629,7 @@ static void node_device_release(struct device *dev) { struct node *node = to_node(dev); -#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HUGETLBFS) +#if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_HUGETLBFS) /* * We schedule the work only when a memory section is * onlined/offlined on this node. When we come here, @@ -782,7 +782,7 @@ int unregister_cpu_under_node(unsigned int cpu, unsigned int nid) return 0; } -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifdef CONFIG_MEMORY_HOTPLUG static int __ref get_nid_for_pfn(unsigned long pfn) { #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT @@ -958,10 +958,9 @@ static int node_memory_callback(struct notifier_block *self, return NOTIFY_OK; } #endif /* CONFIG_HUGETLBFS */ -#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ +#endif /* CONFIG_MEMORY_HOTPLUG */ -#if !defined(CONFIG_MEMORY_HOTPLUG_SPARSE) || \ - !defined(CONFIG_HUGETLBFS) +#if !defined(CONFIG_MEMORY_HOTPLUG) || !defined(CONFIG_HUGETLBFS) static inline int node_memory_callback(struct notifier_block *self, unsigned long action, void *arg) { diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig index ce1b3f6ec325..3654def9915c 100644 --- a/drivers/virtio/Kconfig +++ b/drivers/virtio/Kconfig @@ -98,7 +98,7 @@ config VIRTIO_MEM default m depends on X86_64 depends on VIRTIO - depends on MEMORY_HOTPLUG_SPARSE + depends on MEMORY_HOTPLUG depends on MEMORY_HOTREMOVE depends on CONTIG_ALLOC help diff --git a/include/linux/memory.h b/include/linux/memory.h index 053a530c7bdd..0328ec039c38 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -110,7 +110,7 @@ struct mem_section; #define SLAB_CALLBACK_PRI 1 #define IPC_CALLBACK_PRI 10 -#ifndef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifndef CONFIG_MEMORY_HOTPLUG static inline void memory_dev_init(void) { return; @@ -126,7 +126,14 @@ static inline int memory_notify(unsigned long val, void *v) { return 0; } -#else +static inline int hotplug_memory_notifier(notifier_fn_t fn, int pri) +{ + return 0; +} +/* These aren't inline functions due to a GCC bug. */ +#define register_hotmemory_notifier(nb) ({ (void)(nb); 0; }) +#define unregister_hotmemory_notifier(nb) ({ (void)(nb); }) +#else /* CONFIG_MEMORY_HOTPLUG */ extern int register_memory_notifier(struct notifier_block *nb); extern void unregister_memory_notifier(struct notifier_block *nb); int create_memory_block_devices(unsigned long start, unsigned long size, @@ -148,9 +155,6 @@ struct memory_group *memory_group_find_by_id(int mgid); typedef int (*walk_memory_groups_func_t)(struct memory_group *, void *); int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func, struct memory_group *excluded, void *arg); -#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ - -#ifdef CONFIG_MEMORY_HOTPLUG #define hotplug_memory_notifier(fn, pri) ({ \ static __meminitdata struct notifier_block fn##_mem_nb =\ { .notifier_call = fn, .priority = pri };\ @@ -158,15 +162,7 @@ int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func, }) #define register_hotmemory_notifier(nb) register_memory_notifier(nb) #define unregister_hotmemory_notifier(nb) unregister_memory_notifier(nb) -#else -static inline int hotplug_memory_notifier(notifier_fn_t fn, int pri) -{ - return 0; -} -/* These aren't inline functions due to a GCC bug. */ -#define register_hotmemory_notifier(nb) ({ (void)(nb); 0; }) -#define unregister_hotmemory_notifier(nb) ({ (void)(nb); }) -#endif +#endif /* CONFIG_MEMORY_HOTPLUG */ /* * Kernel text modification mutex, used for code patching. Users of this lock diff --git a/include/linux/node.h b/include/linux/node.h index 8e5a29897936..bb21fd631b16 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -85,7 +85,7 @@ struct node { struct device dev; struct list_head access_list; -#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HUGETLBFS) +#if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_HUGETLBFS) struct work_struct node_work; #endif #ifdef CONFIG_HMEM_REPORTING @@ -98,7 +98,7 @@ struct memory_block; extern struct node *node_devices[]; typedef void (*node_registration_func_t)(struct node *); -#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA) +#if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_NUMA) void link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn, enum meminit_context context); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 2a9b6dcdac4f..669fee1d26b8 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -877,7 +877,7 @@ config DEBUG_MEMORY_INIT config MEMORY_NOTIFIER_ERROR_INJECT tristate "Memory hotplug notifier error injection module" - depends on MEMORY_HOTPLUG_SPARSE && NOTIFIER_ERROR_INJECTION + depends on MEMORY_HOTPLUG && NOTIFIER_ERROR_INJECTION help This option provides the ability to inject artificial errors to memory hotplug notifier chain callbacks. It is controlled through diff --git a/mm/Kconfig b/mm/Kconfig index b2bf73c90a38..0148a9c4fa2a 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -128,10 +128,6 @@ config MEMORY_HOTPLUG depends on 64BIT || BROKEN select NUMA_KEEP_MEMINFO if NUMA -config MEMORY_HOTPLUG_SPARSE - def_bool y - depends on SPARSEMEM && MEMORY_HOTPLUG - config MEMORY_HOTPLUG_DEFAULT_ONLINE bool "Online the newly added memory blocks by default" depends on MEMORY_HOTPLUG diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index afaae370b8cd..fc07ce7b5842 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -220,7 +220,6 @@ static void release_memory_resource(struct resource *res) kfree(res); } -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE static int check_pfn_span(unsigned long pfn, unsigned long nr_pages, const char *reason) { @@ -1163,7 +1162,6 @@ failed_addition: mem_hotplug_done(); return ret; } -#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ static void reset_node_present_pages(pg_data_t *pgdat) { diff --git a/tools/testing/selftests/memory-hotplug/config b/tools/testing/selftests/memory-hotplug/config index a7e8cd5bb265..1eef042a31e1 100644 --- a/tools/testing/selftests/memory-hotplug/config +++ b/tools/testing/selftests/memory-hotplug/config @@ -1,5 +1,4 @@ CONFIG_MEMORY_HOTPLUG=y -CONFIG_MEMORY_HOTPLUG_SPARSE=y CONFIG_NOTIFIER_ERROR_INJECTION=y CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m CONFIG_MEMORY_HOTREMOVE=y From 7ec58a2b941ed88986694d037e38012738323171 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:28 -0700 Subject: [PATCH 092/166] mm/memory_hotplug: restrict CONFIG_MEMORY_HOTPLUG to 64 bit 32 bit support is broken in various ways: for example, we can online memory that should actually go to ZONE_HIGHMEM to ZONE_MOVABLE or in some cases even to one of the other kernel zones. We marked it BROKEN in commit b59d02ed0869 ("mm/memory_hotplug: disable the functionality for 32b") almost one year ago. According to that commit it might be broken at least since 2017. Further, there is hardly a sane use case nowadays. Let's just depend completely on 64bit, dropping the "BROKEN" dependency to make clear that we are not going to support it again. Next, we'll remove some HIGHMEM leftovers from memory hotplug code to clean up. Link: https://lkml.kernel.org/r/20210929143600.49379-4-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: Alex Shi Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Dave Hansen Cc: Greg Kroah-Hartman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jason Wang Cc: Jonathan Corbet Cc: Michael Ellerman Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Mike Rapoport Cc: Paul Mackerras Cc: Peter Zijlstra Cc: "Rafael J. Wysocki" Cc: Shuah Khan Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/Kconfig b/mm/Kconfig index 0148a9c4fa2a..ae1f151c2924 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -125,7 +125,7 @@ config MEMORY_HOTPLUG select MEMORY_ISOLATION depends on SPARSEMEM depends on ARCH_ENABLE_MEMORY_HOTPLUG - depends on 64BIT || BROKEN + depends on 64BIT select NUMA_KEEP_MEMINFO if NUMA config MEMORY_HOTPLUG_DEFAULT_ONLINE From 6b740c6c3aa371cd70ac07f8d071f2a8af28c51c Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:31 -0700 Subject: [PATCH 093/166] mm/memory_hotplug: remove HIGHMEM leftovers We don't support CONFIG_MEMORY_HOTPLUG on 32 bit and consequently not HIGHMEM. Let's remove any leftover code -- including the unused "status_change_nid_high" field part of the memory notifier. Link: https://lkml.kernel.org/r/20210929143600.49379-5-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: Alex Shi Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Dave Hansen Cc: Greg Kroah-Hartman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jason Wang Cc: Jonathan Corbet Cc: Michael Ellerman Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Mike Rapoport Cc: Paul Mackerras Cc: Peter Zijlstra Cc: "Rafael J. Wysocki" Cc: Shuah Khan Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/core-api/memory-hotplug.rst | 3 -- .../zh_CN/core-api/memory-hotplug.rst | 4 --- include/linux/memory.h | 1 - mm/memory_hotplug.c | 36 ++----------------- 4 files changed, 2 insertions(+), 42 deletions(-) diff --git a/Documentation/core-api/memory-hotplug.rst b/Documentation/core-api/memory-hotplug.rst index de7467e48067..682259ee633a 100644 --- a/Documentation/core-api/memory-hotplug.rst +++ b/Documentation/core-api/memory-hotplug.rst @@ -57,7 +57,6 @@ The third argument (arg) passes a pointer of struct memory_notify:: unsigned long start_pfn; unsigned long nr_pages; int status_change_nid_normal; - int status_change_nid_high; int status_change_nid; } @@ -65,8 +64,6 @@ The third argument (arg) passes a pointer of struct memory_notify:: - nr_pages is # of pages of online/offline memory. - status_change_nid_normal is set node id when N_NORMAL_MEMORY of nodemask is (will be) set/clear, if this is -1, then nodemask status is not changed. -- status_change_nid_high is set node id when N_HIGH_MEMORY of nodemask - is (will be) set/clear, if this is -1, then nodemask status is not changed. - status_change_nid is set node id when N_MEMORY of nodemask is (will be) set/clear. It means a new(memoryless) node gets new memory by online and a node loses all memory. If this is -1, then nodemask status is not changed. diff --git a/Documentation/translations/zh_CN/core-api/memory-hotplug.rst b/Documentation/translations/zh_CN/core-api/memory-hotplug.rst index 161f4d2c18cc..9a204eb196f2 100644 --- a/Documentation/translations/zh_CN/core-api/memory-hotplug.rst +++ b/Documentation/translations/zh_CN/core-api/memory-hotplug.rst @@ -63,7 +63,6 @@ memory_notify结构体的指针:: unsigned long start_pfn; unsigned long nr_pages; int status_change_nid_normal; - int status_change_nid_high; int status_change_nid; } @@ -74,9 +73,6 @@ memory_notify结构体的指针:: - status_change_nid_normal是当nodemask的N_NORMAL_MEMORY被设置/清除时设置节 点id，如果是-1，则nodemask状态不改变。 -- status_change_nid_high是当nodemask的N_HIGH_MEMORY被设置/清除时设置的节点 - id，如果这个值为-1，那么nodemask状态不会改变。 - - status_change_nid是当nodemask的N_MEMORY被（将）设置/清除时设置的节点id。这 意味着一个新的（没上线的）节点通过联机获得新的内存，而一个节点失去了所有的内 存。如果这个值为-1，那么nodemask的状态就不会改变。 diff --git a/include/linux/memory.h b/include/linux/memory.h index 0328ec039c38..88eb587b5143 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -96,7 +96,6 @@ struct memory_notify { unsigned long start_pfn; unsigned long nr_pages; int status_change_nid_normal; - int status_change_nid_high; int status_change_nid; }; diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index fc07ce7b5842..0aa7ca3dfbc9 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -21,7 +21,6 @@ #include #include #include -#include #include #include #include @@ -585,10 +584,6 @@ void generic_online_page(struct page *page, unsigned int order) debug_pagealloc_map_pages(page, 1 << order); __free_pages_core(page, order); totalram_pages_add(1UL << order); -#ifdef CONFIG_HIGHMEM - if (PageHighMem(page)) - totalhigh_pages_add(1UL << order); -#endif } EXPORT_SYMBOL_GPL(generic_online_page); @@ -625,16 +620,11 @@ static void node_states_check_changes_online(unsigned long nr_pages, arg->status_change_nid = NUMA_NO_NODE; arg->status_change_nid_normal = NUMA_NO_NODE; - arg->status_change_nid_high = NUMA_NO_NODE; if (!node_state(nid, N_MEMORY)) arg->status_change_nid = nid; if (zone_idx(zone) <= ZONE_NORMAL && !node_state(nid, N_NORMAL_MEMORY)) arg->status_change_nid_normal = nid; -#ifdef CONFIG_HIGHMEM - if (zone_idx(zone) <= ZONE_HIGHMEM && !node_state(nid, N_HIGH_MEMORY)) - arg->status_change_nid_high = nid; -#endif } static void node_states_set_node(int node, struct memory_notify *arg) @@ -642,9 +632,6 @@ static void node_states_set_node(int node, struct memory_notify *arg) if (arg->status_change_nid_normal >= 0) node_set_state(node, N_NORMAL_MEMORY); - if (arg->status_change_nid_high >= 0) - node_set_state(node, N_HIGH_MEMORY); - if (arg->status_change_nid >= 0) node_set_state(node, N_MEMORY); } @@ -1801,7 +1788,6 @@ static void node_states_check_changes_offline(unsigned long nr_pages, arg->status_change_nid = NUMA_NO_NODE; arg->status_change_nid_normal = NUMA_NO_NODE; - arg->status_change_nid_high = NUMA_NO_NODE; /* * Check whether node_states[N_NORMAL_MEMORY] will be changed. @@ -1816,24 +1802,9 @@ static void node_states_check_changes_offline(unsigned long nr_pages, if (zone_idx(zone) <= ZONE_NORMAL && nr_pages >= present_pages) arg->status_change_nid_normal = zone_to_nid(zone); -#ifdef CONFIG_HIGHMEM /* - * node_states[N_HIGH_MEMORY] contains nodes which - * have normal memory or high memory. - * Here we add the present_pages belonging to ZONE_HIGHMEM. - * If the zone is within the range of [0..ZONE_HIGHMEM), and - * we determine that the zones in that range become empty, - * we need to clear the node for N_HIGH_MEMORY. - */ - present_pages += pgdat->node_zones[ZONE_HIGHMEM].present_pages; - if (zone_idx(zone) <= ZONE_HIGHMEM && nr_pages >= present_pages) - arg->status_change_nid_high = zone_to_nid(zone); -#endif - - /* - * We have accounted the pages from [0..ZONE_NORMAL), and - * in case of CONFIG_HIGHMEM the pages from ZONE_HIGHMEM - * as well. + * We have accounted the pages from [0..ZONE_NORMAL); ZONE_HIGHMEM + * does not apply as we don't support 32bit. * Here we count the possible pages from ZONE_MOVABLE. * If after having accounted all the pages, we see that the nr_pages * to be offlined is over or equal to the accounted pages, @@ -1851,9 +1822,6 @@ static void node_states_clear_node(int node, struct memory_notify *arg) if (arg->status_change_nid_normal >= 0) node_clear_state(node, N_NORMAL_MEMORY); - if (arg->status_change_nid_high >= 0) - node_clear_state(node, N_HIGH_MEMORY); - if (arg->status_change_nid >= 0) node_clear_state(node, N_MEMORY); } From 43e3aa2a3247c9ca348884866a9846d788ec5ed6 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:35 -0700 Subject: [PATCH 094/166] mm/memory_hotplug: remove stale function declarations These functions no longer exist. Link: https://lkml.kernel.org/r/20210929143600.49379-6-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: Alex Shi Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Dave Hansen Cc: Greg Kroah-Hartman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jason Wang Cc: Jonathan Corbet Cc: Michael Ellerman Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Mike Rapoport Cc: Paul Mackerras Cc: Peter Zijlstra Cc: "Rafael J. Wysocki" Cc: Shuah Khan Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 3 --- 1 file changed, 3 deletions(-) diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index e5a867c950b2..be48e003a518 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -98,9 +98,6 @@ static inline void zone_seqlock_init(struct zone *zone) { seqlock_init(&zone->span_seqlock); } -extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages); -extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages); -extern int add_one_highpage(struct page *page, int pfn, int bad_ppro); extern void adjust_present_page_count(struct page *page, struct memory_group *group, long nr_pages); From 5c11f00b09c10340fcc363b332f6622d22d895ef Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:39 -0700 Subject: [PATCH 095/166] x86: remove memory hotplug support on X86_32 CONFIG_MEMORY_HOTPLUG was marked BROKEN over one year and we just restricted it to 64 bit. Let's remove the unused x86 32bit implementation and simplify the Kconfig. Link: https://lkml.kernel.org/r/20210929143600.49379-7-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: Alex Shi Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Dave Hansen Cc: Greg Kroah-Hartman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jason Wang Cc: Jonathan Corbet Cc: Michael Ellerman Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Mike Rapoport Cc: Paul Mackerras Cc: Peter Zijlstra Cc: "Rafael J. Wysocki" Cc: Shuah Khan Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/Kconfig | 6 +++--- arch/x86/mm/init_32.c | 31 ------------------------------- 2 files changed, 3 insertions(+), 34 deletions(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index d9830e7e1060..b2fb68da6697 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -62,7 +62,7 @@ config X86 select ARCH_32BIT_OFF_T if X86_32 select ARCH_CLOCKSOURCE_INIT select ARCH_ENABLE_HUGEPAGE_MIGRATION if X86_64 && HUGETLB_PAGE && MIGRATION - select ARCH_ENABLE_MEMORY_HOTPLUG if X86_64 || (X86_32 && HIGHMEM) + select ARCH_ENABLE_MEMORY_HOTPLUG if X86_64 select ARCH_ENABLE_MEMORY_HOTREMOVE if MEMORY_HOTPLUG select ARCH_ENABLE_SPLIT_PMD_PTLOCK if (PGTABLE_LEVELS > 2) && (X86_64 || X86_PAE) select ARCH_ENABLE_THP_MIGRATION if X86_64 && TRANSPARENT_HUGEPAGE @@ -1614,7 +1614,7 @@ config ARCH_SELECT_MEMORY_MODEL config ARCH_MEMORY_PROBE bool "Enable sysfs memory/probe interface" - depends on X86_64 && MEMORY_HOTPLUG + depends on MEMORY_HOTPLUG help This option enables a sysfs memory/probe interface for testing. See Documentation/admin-guide/mm/memory-hotplug.rst for more information. @@ -2394,7 +2394,7 @@ endmenu config ARCH_HAS_ADD_PAGES def_bool y - depends on X86_64 && ARCH_ENABLE_MEMORY_HOTPLUG + depends on ARCH_ENABLE_MEMORY_HOTPLUG config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE def_bool y diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index bd90b8fe81e4..5cd7ea6d645c 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -779,37 +779,6 @@ void __init mem_init(void) test_wp_bit(); } -#ifdef CONFIG_MEMORY_HOTPLUG -int arch_add_memory(int nid, u64 start, u64 size, - struct mhp_params *params) -{ - unsigned long start_pfn = start >> PAGE_SHIFT; - unsigned long nr_pages = size >> PAGE_SHIFT; - int ret; - - /* - * The page tables were already mapped at boot so if the caller - * requests a different mapping type then we must change all the - * pages with __set_memory_prot(). - */ - if (params->pgprot.pgprot != PAGE_KERNEL.pgprot) { - ret = __set_memory_prot(start, nr_pages, params->pgprot); - if (ret) - return ret; - } - - return __add_pages(nid, start_pfn, nr_pages, params); -} - -void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap) -{ - unsigned long start_pfn = start >> PAGE_SHIFT; - unsigned long nr_pages = size >> PAGE_SHIFT; - - __remove_pages(start_pfn, nr_pages, altmap); -} -#endif - int kernel_set_to_readonly __read_mostly; static void mark_nxdata_nx(void) From 53d38316ab2017a7c0d733765b521700aa357ec9 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:42 -0700 Subject: [PATCH 096/166] mm/memory_hotplug: handle memblock_add_node() failures in add_memory_resource() Patch series "mm/memory_hotplug: full support for add_memory_driver_managed() with CONFIG_ARCH_KEEP_MEMBLOCK", v2. Architectures that require CONFIG_ARCH_KEEP_MEMBLOCK=y, such as arm64, don't cleanly support add_memory_driver_managed() yet. Most prominently, kexec_file can still end up placing kexec images on such driver-managed memory, resulting in undesired behavior, for example, having kexec images located on memory not part of the firmware-provided memory map. Teaching kexec to not place images on driver-managed memory is especially relevant for virtio-mem. Details can be found in commit 7b7b27214bba ("mm/memory_hotplug: introduce add_memory_driver_managed()"). Extend memblock with a new flag and set it from memory hotplug code when applicable. This is required to fully support virtio-mem on arm64, making also kexec_file behave like on x86-64. This patch (of 2): If memblock_add_node() fails, we're most probably running out of memory. While this is unlikely to happen, it can happen and having memory added without a memblock can be problematic for architectures that use memblock to detect valid memory. Let's fail in a nice way instead of silently ignoring the error. Link: https://lkml.kernel.org/r/20211004093605.5830-1-david@redhat.com Link: https://lkml.kernel.org/r/20211004093605.5830-2-david@redhat.com Signed-off-by: David Hildenbrand Cc: Mike Rapoport Cc: Michal Hocko Cc: Oscar Salvador Cc: Jianyong Wu Cc: "Aneesh Kumar K . V" Cc: Vineet Gupta Cc: Geert Uytterhoeven Cc: Huacai Chen Cc: Jiaxun Yang Cc: Thomas Bogendoerfer Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: Eric Biederman Cc: Arnd Bergmann Cc: Shahab Vahedi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 0aa7ca3dfbc9..9d254e88221e 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1369,8 +1369,11 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) mem_hotplug_begin(); - if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) - memblock_add_node(start, size, nid); + if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) { + ret = memblock_add_node(start, size, nid); + if (ret) + goto error_mem_hotplug_end; + } ret = __try_online_node(nid, false); if (ret < 0) @@ -1443,6 +1446,7 @@ error: rollback_node_hotadd(nid); if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) memblock_remove(start, size); +error_mem_hotplug_end: mem_hotplug_done(); return ret; } From e14b41556d9ec20af60a9f672ac6f64dd450763c Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:46 -0700 Subject: [PATCH 097/166] memblock: improve MEMBLOCK_HOTPLUG documentation The description of MEMBLOCK_HOTPLUG is currently short and consequently misleading: we're actually dealing with a memory region that might get hotunplugged later (i.e., the platform+firmware supports it), yet it is indicated in the firmware-provided memory map as system ram that will just get used by the system for any purpose when not taking special care. The firmware marked this memory region as a hot(un)plugged (e.g., hotplugged before reboot), implying that it might get hotunplugged again later. Whether we consider this information depends on the "movable_node" kernel commandline parameter: only with "movable_node" set, we'll try keeping this memory hotunpluggable, for example, by not serving early allocations from this memory region and by letting the buddy manage it using the ZONE_MOVABLE. Let's make this clearer by extending the documentation. Note: kexec *has to* indicate this memory to the second kernel. With "movable_node" set, we don't want to place kexec-images on this memory. Without "movable_node" set, we don't care and can place kexec-images on this memory. In both cases, after successful memory hotunplug, kexec has to be re-armed to update the memory map for the second kernel and to place the kexec-images somewhere else. Link: https://lkml.kernel.org/r/20211004093605.5830-3-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Mike Rapoport Cc: "Aneesh Kumar K . V" Cc: Arnd Bergmann Cc: Christian Borntraeger Cc: Eric Biederman Cc: Geert Uytterhoeven Cc: Heiko Carstens Cc: Huacai Chen Cc: Jianyong Wu Cc: Jiaxun Yang Cc: Michal Hocko Cc: Oscar Salvador Cc: Shahab Vahedi Cc: Thomas Bogendoerfer Cc: Vasily Gorbik Cc: Vineet Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 484650681bee..1d2b3e902a84 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -28,7 +28,11 @@ extern unsigned long long max_possible_pfn; /** * enum memblock_flags - definition of memory region attributes * @MEMBLOCK_NONE: no special request - * @MEMBLOCK_HOTPLUG: hotpluggable region + * @MEMBLOCK_HOTPLUG: memory region indicated in the firmware-provided memory + * map during early boot as hot(un)pluggable system RAM (e.g., memory range + * that might get hotunplugged later). With "movable_node" set on the kernel + * commandline, try keeping this memory region hotunpluggable. Does not apply + * to memblocks added ("hotplugged") after early boot. * @MEMBLOCK_MIRROR: mirrored region * @MEMBLOCK_NOMAP: don't add to kernel direct mapping and treat as * reserved in the memory map; refer to memblock_mark_nomap() description From 952eea9b01e4bbb7011329f1b7240844e61e5128 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:49 -0700 Subject: [PATCH 098/166] memblock: allow to specify flags with memblock_add_node() We want to specify flags when hotplugging memory. Let's prepare to pass flags to memblock_add_node() by adjusting all existing users. Note that when hotplugging memory the system is already up and running and we might have concurrent memblock users: for example, while we're hotplugging memory, kexec_file code might search for suitable memory regions to place kexec images. It's important to add the memory directly to memblock via a single call with the right flags, instead of adding the memory first and apply flags later: otherwise, concurrent memblock users might temporarily stumble over memblocks with wrong flags, which will be important in a follow-up patch that introduces a new flag to properly handle add_memory_driver_managed(). Link: https://lkml.kernel.org/r/20211004093605.5830-4-david@redhat.com Acked-by: Geert Uytterhoeven Acked-by: Heiko Carstens Signed-off-by: David Hildenbrand Acked-by: Shahab Vahedi [arch/arc] Reviewed-by: Mike Rapoport Cc: "Aneesh Kumar K . V" Cc: Arnd Bergmann Cc: Christian Borntraeger Cc: Eric Biederman Cc: Huacai Chen Cc: Jianyong Wu Cc: Jiaxun Yang Cc: Michal Hocko Cc: Oscar Salvador Cc: Thomas Bogendoerfer Cc: Vasily Gorbik Cc: Vineet Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arc/mm/init.c | 4 ++-- arch/ia64/mm/contig.c | 2 +- arch/ia64/mm/init.c | 2 +- arch/m68k/mm/mcfmmu.c | 3 ++- arch/m68k/mm/motorola.c | 6 ++++-- arch/mips/loongson64/init.c | 4 +++- arch/mips/sgi-ip27/ip27-memory.c | 3 ++- arch/s390/kernel/setup.c | 3 ++- include/linux/memblock.h | 3 ++- include/linux/mm.h | 2 +- mm/memblock.c | 9 +++++---- mm/memory_hotplug.c | 2 +- 12 files changed, 26 insertions(+), 17 deletions(-) diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index 59408f6a02d4..ce4e939a7f07 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -59,13 +59,13 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size) low_mem_sz = size; in_use = 1; - memblock_add_node(base, size, 0); + memblock_add_node(base, size, 0, MEMBLOCK_NONE); } else { #ifdef CONFIG_HIGHMEM high_mem_start = base; high_mem_sz = size; in_use = 1; - memblock_add_node(base, size, 1); + memblock_add_node(base, size, 1, MEMBLOCK_NONE); memblock_reserve(base, size); #endif } diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c index 42e025cfbd08..24901d809301 100644 --- a/arch/ia64/mm/contig.c +++ b/arch/ia64/mm/contig.c @@ -153,7 +153,7 @@ find_memory (void) efi_memmap_walk(find_max_min_low_pfn, NULL); max_pfn = max_low_pfn; - memblock_add_node(0, PFN_PHYS(max_low_pfn), 0); + memblock_add_node(0, PFN_PHYS(max_low_pfn), 0, MEMBLOCK_NONE); find_initrd(); diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 5c6da8d83c1a..5d165607bf35 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -378,7 +378,7 @@ int __init register_active_ranges(u64 start, u64 len, int nid) #endif if (start < end) - memblock_add_node(__pa(start), end - start, nid); + memblock_add_node(__pa(start), end - start, nid, MEMBLOCK_NONE); return 0; } diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c index eac9dde65193..6f1f25125294 100644 --- a/arch/m68k/mm/mcfmmu.c +++ b/arch/m68k/mm/mcfmmu.c @@ -174,7 +174,8 @@ void __init cf_bootmem_alloc(void) m68k_memory[0].addr = _rambase; m68k_memory[0].size = _ramend - _rambase; - memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0); + memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0, + MEMBLOCK_NONE); /* compute total pages in system */ num_pages = PFN_DOWN(_ramend - _rambase); diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c index 9f3f77785aa7..2b05bb2bac00 100644 --- a/arch/m68k/mm/motorola.c +++ b/arch/m68k/mm/motorola.c @@ -410,7 +410,8 @@ void __init paging_init(void) min_addr = m68k_memory[0].addr; max_addr = min_addr + m68k_memory[0].size; - memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0); + memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0, + MEMBLOCK_NONE); for (i = 1; i < m68k_num_memory;) { if (m68k_memory[i].addr < min_addr) { printk("Ignoring memory chunk at 0x%lx:0x%lx before the first chunk\n", @@ -421,7 +422,8 @@ void __init paging_init(void) (m68k_num_memory - i) * sizeof(struct m68k_mem_info)); continue; } - memblock_add_node(m68k_memory[i].addr, m68k_memory[i].size, i); + memblock_add_node(m68k_memory[i].addr, m68k_memory[i].size, i, + MEMBLOCK_NONE); addr = m68k_memory[i].addr + m68k_memory[i].size; if (addr > max_addr) max_addr = addr; diff --git a/arch/mips/loongson64/init.c b/arch/mips/loongson64/init.c index 76e0a9636a0e..4ac5ba80bbf6 100644 --- a/arch/mips/loongson64/init.c +++ b/arch/mips/loongson64/init.c @@ -77,7 +77,9 @@ void __init szmem(unsigned int node) (u32)node_id, mem_type, mem_start, mem_size); pr_info(" start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n", start_pfn, end_pfn, num_physpages); - memblock_add_node(PFN_PHYS(start_pfn), PFN_PHYS(node_psize), node); + memblock_add_node(PFN_PHYS(start_pfn), + PFN_PHYS(node_psize), node, + MEMBLOCK_NONE); break; case SYSTEM_RAM_RESERVED: pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx MB\n", diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c index 6173684b5aaa..adc2faeecf7c 100644 --- a/arch/mips/sgi-ip27/ip27-memory.c +++ b/arch/mips/sgi-ip27/ip27-memory.c @@ -341,7 +341,8 @@ static void __init szmem(void) continue; } memblock_add_node(PFN_PHYS(slot_getbasepfn(node, slot)), - PFN_PHYS(slot_psize), node); + PFN_PHYS(slot_psize), node, + MEMBLOCK_NONE); } } } diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 7fc836e9e194..8a378d426239 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -593,7 +593,8 @@ static void __init setup_resources(void) * part of the System RAM resource. */ if (crashk_res.end) { - memblock_add_node(crashk_res.start, resource_size(&crashk_res), 0); + memblock_add_node(crashk_res.start, resource_size(&crashk_res), + 0, MEMBLOCK_NONE); memblock_reserve(crashk_res.start, resource_size(&crashk_res)); insert_resource(&iomem_resource, &crashk_res); } diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 1d2b3e902a84..8b6560dc7a9e 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -104,7 +104,8 @@ static inline void memblock_discard(void) {} #endif void memblock_allow_resize(void); -int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid); +int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid, + enum memblock_flags flags); int memblock_add(phys_addr_t base, phys_addr_t size); int memblock_remove(phys_addr_t base, phys_addr_t size); int memblock_phys_free(phys_addr_t base, phys_addr_t size); diff --git a/include/linux/mm.h b/include/linux/mm.h index 7e37c726b9db..15058d9cec99 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2425,7 +2425,7 @@ static inline unsigned long get_num_physpages(void) * unsigned long max_zone_pfns[MAX_NR_ZONES] = {max_dma, max_normal_pfn, * max_highmem_pfn}; * for_each_valid_physical_page_range() - * memblock_add_node(base, size, nid) + * memblock_add_node(base, size, nid, MEMBLOCK_NONE) * free_area_init(max_zone_pfns); */ void free_area_init(unsigned long *max_zone_pfn); diff --git a/mm/memblock.c b/mm/memblock.c index fb0c7f48e627..1b0cd8a52a13 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -655,6 +655,7 @@ repeat: * @base: base address of the new region * @size: size of the new region * @nid: nid of the new region + * @flags: flags of the new region * * Add new memblock region [@base, @base + @size) to the "memory" * type. See memblock_add_range() description for mode details @@ -663,14 +664,14 @@ repeat: * 0 on success, -errno on failure. */ int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size, - int nid) + int nid, enum memblock_flags flags) { phys_addr_t end = base + size - 1; - memblock_dbg("%s: [%pa-%pa] nid=%d %pS\n", __func__, - &base, &end, nid, (void *)_RET_IP_); + memblock_dbg("%s: [%pa-%pa] nid=%d flags=%x %pS\n", __func__, + &base, &end, nid, flags, (void *)_RET_IP_); - return memblock_add_range(&memblock.memory, base, size, nid, 0); + return memblock_add_range(&memblock.memory, base, size, nid, flags); } /** diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 9d254e88221e..cedeaa4d6f0e 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1370,7 +1370,7 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) mem_hotplug_begin(); if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) { - ret = memblock_add_node(start, size, nid); + ret = memblock_add_node(start, size, nid, MEMBLOCK_NONE); if (ret) goto error_mem_hotplug_end; } From f7892d8e288d4b090176f26d9bf7943dbbb639a6 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:53 -0700 Subject: [PATCH 099/166] memblock: add MEMBLOCK_DRIVER_MANAGED to mimic IORESOURCE_SYSRAM_DRIVER_MANAGED Let's add a flag that corresponds to IORESOURCE_SYSRAM_DRIVER_MANAGED, indicating that we're dealing with a memory region that is never indicated in the firmware-provided memory map, but always detected and added by a driver. Similar to MEMBLOCK_HOTPLUG, most infrastructure has to treat such memory regions like ordinary MEMBLOCK_NONE memory regions -- for example, when selecting memory regions to add to the vmcore for dumping in the crashkernel via for_each_mem_range(). However, especially kexec_file is not supposed to select such memblocks via for_each_free_mem_range() / for_each_free_mem_range_reverse() to place kexec images, similar to how we handle IORESOURCE_SYSRAM_DRIVER_MANAGED without CONFIG_ARCH_KEEP_MEMBLOCK. We'll make sure that memory hotplug code sets the flag where applicable (IORESOURCE_SYSRAM_DRIVER_MANAGED) next. This prepares architectures that need CONFIG_ARCH_KEEP_MEMBLOCK, such as arm64, for virtio-mem support. Note that kexec *must not* indicate this memory to the second kernel and *must not* place kexec-images on this memory. Let's add a comment to kexec_walk_memblock(), documenting how we handle MEMBLOCK_DRIVER_MANAGED now just like using IORESOURCE_SYSRAM_DRIVER_MANAGED in locate_mem_hole_callback() for kexec_walk_resources(). Also note that MEMBLOCK_HOTPLUG cannot be reused due to different semantics: MEMBLOCK_HOTPLUG: memory is indicated as "System RAM" in the firmware-provided memory map and added to the system early during boot; kexec *has to* indicate this memory to the second kernel and can place kexec-images on this memory. After memory hotunplug, kexec has to be re-armed. We mostly ignore this flag when "movable_node" is not set on the kernel command line, because then we're told to not care about hotunpluggability of such memory regions. MEMBLOCK_DRIVER_MANAGED: memory is not indicated as "System RAM" in the firmware-provided memory map; this memory is always detected and added to the system by a driver; memory might not actually be physically hotunpluggable. kexec *must not* indicate this memory to the second kernel and *must not* place kexec-images on this memory. Link: https://lkml.kernel.org/r/20211004093605.5830-5-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Mike Rapoport Cc: "Aneesh Kumar K . V" Cc: Arnd Bergmann Cc: Christian Borntraeger Cc: Eric Biederman Cc: Geert Uytterhoeven Cc: Heiko Carstens Cc: Huacai Chen Cc: Jianyong Wu Cc: Jiaxun Yang Cc: Michal Hocko Cc: Oscar Salvador Cc: Shahab Vahedi Cc: Thomas Bogendoerfer Cc: Vasily Gorbik Cc: Vineet Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 16 ++++++++++++++-- kernel/kexec_file.c | 5 +++++ mm/memblock.c | 4 ++++ 3 files changed, 23 insertions(+), 2 deletions(-) diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 8b6560dc7a9e..7df557b16c1e 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -37,12 +37,17 @@ extern unsigned long long max_possible_pfn; * @MEMBLOCK_NOMAP: don't add to kernel direct mapping and treat as * reserved in the memory map; refer to memblock_mark_nomap() description * for further details + * @MEMBLOCK_DRIVER_MANAGED: memory region that is always detected and added + * via a driver, and never indicated in the firmware-provided memory map as + * system RAM. This corresponds to IORESOURCE_SYSRAM_DRIVER_MANAGED in the + * kernel resource tree. */ enum memblock_flags { MEMBLOCK_NONE = 0x0, /* No special request */ MEMBLOCK_HOTPLUG = 0x1, /* hotpluggable region */ MEMBLOCK_MIRROR = 0x2, /* mirrored region */ MEMBLOCK_NOMAP = 0x4, /* don't add to kernel direct mapping */ + MEMBLOCK_DRIVER_MANAGED = 0x8, /* always detected via a driver */ }; /** @@ -213,7 +218,8 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type, */ #define for_each_mem_range(i, p_start, p_end) \ __for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE, \ - MEMBLOCK_HOTPLUG, p_start, p_end, NULL) + MEMBLOCK_HOTPLUG | MEMBLOCK_DRIVER_MANAGED, \ + p_start, p_end, NULL) /** * for_each_mem_range_rev - reverse iterate through memblock areas from @@ -224,7 +230,8 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type, */ #define for_each_mem_range_rev(i, p_start, p_end) \ __for_each_mem_range_rev(i, &memblock.memory, NULL, NUMA_NO_NODE, \ - MEMBLOCK_HOTPLUG, p_start, p_end, NULL) + MEMBLOCK_HOTPLUG | MEMBLOCK_DRIVER_MANAGED,\ + p_start, p_end, NULL) /** * for_each_reserved_mem_range - iterate over all reserved memblock areas @@ -254,6 +261,11 @@ static inline bool memblock_is_nomap(struct memblock_region *m) return m->flags & MEMBLOCK_NOMAP; } +static inline bool memblock_is_driver_managed(struct memblock_region *m) +{ + return m->flags & MEMBLOCK_DRIVER_MANAGED; +} + int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn, unsigned long *end_pfn); void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 33400ff051a8..8347fc158d2b 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -556,6 +556,11 @@ static int kexec_walk_memblock(struct kexec_buf *kbuf, if (kbuf->image->type == KEXEC_TYPE_CRASH) return func(&crashk_res, kbuf); + /* + * Using MEMBLOCK_NONE will properly skip MEMBLOCK_DRIVER_MANAGED. See + * IORESOURCE_SYSRAM_DRIVER_MANAGED handling in + * locate_mem_hole_callback(). + */ if (kbuf->top_down) { for_each_free_mem_range_reverse(i, NUMA_NO_NODE, MEMBLOCK_NONE, &mstart, &mend, NULL) { diff --git a/mm/memblock.c b/mm/memblock.c index 1b0cd8a52a13..659bf0ffb086 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -982,6 +982,10 @@ static bool should_skip_region(struct memblock_type *type, if (!(flags & MEMBLOCK_NOMAP) && memblock_is_nomap(m)) return true; + /* skip driver-managed memory unless we were asked for it explicitly */ + if (!(flags & MEMBLOCK_DRIVER_MANAGED) && memblock_is_driver_managed(m)) + return true; + return false; } From 32befe9e27859b87e70e0aba9b60bfb8000d9a66 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:56 -0700 Subject: [PATCH 100/166] mm/memory_hotplug: indicate MEMBLOCK_DRIVER_MANAGED with IORESOURCE_SYSRAM_DRIVER_MANAGED Let's communicate driver-managed regions to memblock, to properly teach kexec_file with CONFIG_ARCH_KEEP_MEMBLOCK to not place images on these memory regions. Link: https://lkml.kernel.org/r/20211004093605.5830-6-david@redhat.com Signed-off-by: David Hildenbrand Cc: "Aneesh Kumar K . V" Cc: Arnd Bergmann Cc: Christian Borntraeger Cc: Eric Biederman Cc: Geert Uytterhoeven Cc: Heiko Carstens Cc: Huacai Chen Cc: Jianyong Wu Cc: Jiaxun Yang Cc: Michal Hocko Cc: Mike Rapoport Cc: Oscar Salvador Cc: Shahab Vahedi Cc: Thomas Bogendoerfer Cc: Vasily Gorbik Cc: Vineet Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index cedeaa4d6f0e..852041f6be41 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1342,6 +1342,7 @@ bool mhp_supports_memmap_on_memory(unsigned long size) int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) { struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) }; + enum memblock_flags memblock_flags = MEMBLOCK_NONE; struct vmem_altmap mhp_altmap = {}; struct memory_group *group = NULL; u64 start, size; @@ -1370,7 +1371,9 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) mem_hotplug_begin(); if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) { - ret = memblock_add_node(start, size, nid, MEMBLOCK_NONE); + if (res->flags & IORESOURCE_SYSRAM_DRIVER_MANAGED) + memblock_flags = MEMBLOCK_DRIVER_MANAGED; + ret = memblock_add_node(start, size, nid, memblock_flags); if (ret) goto error_mem_hotplug_end; } From 3d88705c10677d1fc3f14786361aee649839aa7e Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Fri, 5 Nov 2021 13:45:00 -0700 Subject: [PATCH 101/166] mm/rmap.c: avoid double faults migrating device private pages During migration special page table entries are installed for each page being migrated. These entries store the pfn and associated permissions of ptes mapping the page being migarted. Device-private pages use special swap pte entries to distinguish read-only vs. writeable pages which the migration code checks when creating migration entries. Normally this follows a fast path in migrate_vma_collect_pmd() which correctly copies the permissions of device-private pages over to migration entries when migrating pages back to the CPU. However the slow-path falls back to using try_to_migrate() which unconditionally creates read-only migration entries for device-private pages. This leads to unnecessary double faults on the CPU as the new pages are always mapped read-only even when they could be mapped writeable. Fix this by correctly copying device-private permissions in try_to_migrate_one(). Link: https://lkml.kernel.org/r/20211018045247.3128058-1-apopple@nvidia.com Signed-off-by: Alistair Popple Reported-by: Ralph Campbell Reviewed-by: John Hubbard Cc: Jerome Glisse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/rmap.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/mm/rmap.c b/mm/rmap.c index 6aebd1747251..d65a74e140f9 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1807,6 +1807,7 @@ static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma, update_hiwater_rss(mm); if (is_zone_device_page(page)) { + unsigned long pfn = page_to_pfn(page); swp_entry_t entry; pte_t swp_pte; @@ -1815,8 +1816,11 @@ static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma, * pte. do_swap_page() will wait until the migration * pte is removed and then restart fault handling. */ - entry = make_readable_migration_entry( - page_to_pfn(page)); + entry = pte_to_swp_entry(pteval); + if (is_writable_device_private_entry(entry)) + entry = make_writable_migration_entry(pfn); + else + entry = make_readable_migration_entry(pfn); swp_pte = swp_entry_to_pte(entry); /* From afe8605ca45424629fdddfd85984b442c763dc47 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Fri, 5 Nov 2021 13:45:03 -0700 Subject: [PATCH 102/166] mm/zsmalloc.c: close race window between zs_pool_dec_isolated() and zs_unregister_migration() There is one possible race window between zs_pool_dec_isolated() and zs_unregister_migration() because wait_for_isolated_drain() checks the isolated count without holding class->lock and there is no order inside zs_pool_dec_isolated(). Thus the below race window could be possible: zs_pool_dec_isolated zs_unregister_migration check pool->destroying != 0 pool->destroying = true; smp_mb(); wait_for_isolated_drain() wait for pool->isolated_pages == 0 atomic_long_dec(&pool->isolated_pages); atomic_long_read(&pool->isolated_pages) == 0 Since we observe the pool->destroying (false) before atomic_long_dec() for pool->isolated_pages, waking pool->migration_wait up is missed. Fix this by ensure checking pool->destroying happens after the atomic_long_dec(&pool->isolated_pages). Link: https://lkml.kernel.org/r/20210708115027.7557-1-linmiaohe@huawei.com Fixes: 701d678599d0 ("mm/zsmalloc.c: fix race condition in zs_destroy_pool") Signed-off-by: Miaohe Lin Cc: Minchan Kim Cc: Sergey Senozhatsky Cc: Henry Burns Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/zsmalloc.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 68e8831068f4..b897ce3b399a 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -1830,10 +1830,11 @@ static inline void zs_pool_dec_isolated(struct zs_pool *pool) VM_BUG_ON(atomic_long_read(&pool->isolated_pages) <= 0); atomic_long_dec(&pool->isolated_pages); /* - * There's no possibility of racing, since wait_for_isolated_drain() - * checks the isolated count under &class->lock after enqueuing - * on migration_wait. + * Checking pool->destroying must happen after atomic_long_dec() + * for pool->isolated_pages above. Paired with the smp_mb() in + * zs_unregister_migration(). */ + smp_mb__after_atomic(); if (atomic_long_read(&pool->isolated_pages) == 0 && pool->destroying) wake_up_all(&pool->migration_wait); } From d2c20e51e3966bc668ef1ef21fbe90704286c8d0 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Fri, 5 Nov 2021 13:45:06 -0700 Subject: [PATCH 103/166] mm/highmem: remove deprecated kmap_atomic kmap_atomic() is being deprecated in favor of kmap_local_page(). Replace the uses of kmap_atomic() within the highmem code. On profiling clear_huge_page() using ftrace an improvement of 62% was observed on the below setup. Setup:- Below data has been collected on Qualcomm's SM7250 SoC THP enabled (kernel v4.19.113) with only CPU-0(Cortex-A55) and CPU-7(Cortex-A76) switched on and set to max frequency, also DDR set to perf governor. FTRACE Data:- Base data:- Number of iterations: 48 Mean of allocation time: 349.5 us std deviation: 74.5 us v4 data:- Number of iterations: 48 Mean of allocation time: 131 us std deviation: 32.7 us The following simple userspace experiment to allocate 100MB(BUF_SZ) of pages and writing to it gave us a good insight, we observed an improvement of 42% in allocation and writing timings. ------------------------------------------------------------- Test code snippet ------------------------------------------------------------- clock_start(); buf = malloc(BUF_SZ); /* Allocate 100 MB of memory */ for(i=0; i < BUF_SZ_PAGES; i++) { *((int *)(buf + (i*PAGE_SIZE))) = 1; } clock_end(); ------------------------------------------------------------- Malloc test timings for 100MB anon allocation:- Base data:- Number of iterations: 100 Mean of allocation time: 31831 us std deviation: 4286 us v4 data:- Number of iterations: 100 Mean of allocation time: 18193 us std deviation: 4915 us [willy@infradead.org: fix zero_user_segments()] Link: https://lkml.kernel.org/r/YYVhHCJcm2DM2G9u@casper.infradead.org Link: https://lkml.kernel.org/r/20210204073255.20769-2-prathu.baronia@oneplus.com Signed-off-by: Ira Weiny Signed-off-by: Prathu Baronia Cc: Thomas Gleixner Cc: Matthew Wilcox Cc: Peter Zijlstra Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 28 ++++++++++++++-------------- mm/highmem.c | 6 +++--- 2 files changed, 17 insertions(+), 17 deletions(-) diff --git a/include/linux/highmem.h b/include/linux/highmem.h index b4c49f9cc379..31ebee36f26c 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -143,9 +143,9 @@ static inline void invalidate_kernel_vmap_range(void *vaddr, int size) #ifndef clear_user_highpage static inline void clear_user_highpage(struct page *page, unsigned long vaddr) { - void *addr = kmap_atomic(page); + void *addr = kmap_local_page(page); clear_user_page(addr, vaddr, page); - kunmap_atomic(addr); + kunmap_local(addr); } #endif @@ -177,9 +177,9 @@ alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma, static inline void clear_highpage(struct page *page) { - void *kaddr = kmap_atomic(page); + void *kaddr = kmap_local_page(page); clear_page(kaddr); - kunmap_atomic(kaddr); + kunmap_local(kaddr); } #ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGE @@ -202,7 +202,7 @@ static inline void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned start2, unsigned end2) { - void *kaddr = kmap_atomic(page); + void *kaddr = kmap_local_page(page); unsigned int i; BUG_ON(end1 > page_size(page) || end2 > page_size(page)); @@ -213,7 +213,7 @@ static inline void zero_user_segments(struct page *page, if (end2 > start2) memset(kaddr + start2, 0, end2 - start2); - kunmap_atomic(kaddr); + kunmap_local(kaddr); for (i = 0; i < compound_nr(page); i++) flush_dcache_page(page + i); } @@ -238,11 +238,11 @@ static inline void copy_user_highpage(struct page *to, struct page *from, { char *vfrom, *vto; - vfrom = kmap_atomic(from); - vto = kmap_atomic(to); + vfrom = kmap_local_page(from); + vto = kmap_local_page(to); copy_user_page(vto, vfrom, vaddr, to); - kunmap_atomic(vto); - kunmap_atomic(vfrom); + kunmap_local(vto); + kunmap_local(vfrom); } #endif @@ -253,11 +253,11 @@ static inline void copy_highpage(struct page *to, struct page *from) { char *vfrom, *vto; - vfrom = kmap_atomic(from); - vto = kmap_atomic(to); + vfrom = kmap_local_page(from); + vto = kmap_local_page(to); copy_page(vto, vfrom); - kunmap_atomic(vto); - kunmap_atomic(vfrom); + kunmap_local(vto); + kunmap_local(vfrom); } #endif diff --git a/mm/highmem.c b/mm/highmem.c index 4212ad0e4a19..eb3b8c288de4 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -383,7 +383,7 @@ void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned this_end = min_t(unsigned, end1, PAGE_SIZE); if (end1 > start1) { - kaddr = kmap_atomic(page + i); + kaddr = kmap_local_page(page + i); memset(kaddr + start1, 0, this_end - start1); } end1 -= this_end; @@ -398,7 +398,7 @@ void zero_user_segments(struct page *page, unsigned start1, unsigned end1, if (end2 > start2) { if (!kaddr) - kaddr = kmap_atomic(page + i); + kaddr = kmap_local_page(page + i); memset(kaddr + start2, 0, this_end - start2); } end2 -= this_end; @@ -406,7 +406,7 @@ void zero_user_segments(struct page *page, unsigned start1, unsigned end1, } if (kaddr) { - kunmap_atomic(kaddr); + kunmap_local(kaddr); flush_dcache_page(page + i); } From 4aabdc14c4d2a01c2968bdc8919f81d9f9b4f790 Mon Sep 17 00:00:00 2001 From: Jaewon Kim Date: Fri, 5 Nov 2021 13:45:09 -0700 Subject: [PATCH 104/166] zram_drv: allow reclaim on bio_alloc The read_from_bdev_async is not called on atomic context. So GFP_NOIO is available rather than GFP_ATOMIC. If there were reclaimable pages with GFP_NOIO, we can avoid allocation failure and page fault failure. Link: https://lkml.kernel.org/r/20210908005241.28062-1-jaewon31.kim@samsung.com Signed-off-by: Jaewon Kim Reported-by: Yong-Taek Lee Acked-by: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/block/zram/zram_drv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index fcaf2750f68f..081e77d595d7 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -587,7 +587,7 @@ static int read_from_bdev_async(struct zram *zram, struct bio_vec *bvec, { struct bio *bio; - bio = bio_alloc(GFP_ATOMIC, 1); + bio = bio_alloc(GFP_NOIO, 1); if (!bio) return -ENOMEM; From a88e03cf3d190cf46bc4063a9b7efe87590de5f4 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 5 Nov 2021 13:45:12 -0700 Subject: [PATCH 105/166] zram: off by one in read_block_state() snprintf() returns the number of bytes it would have printed if there were space. But it does not count the NUL terminator. So that means that if "count == copied" then this has already overflowed by one character. This bug likely isn't super harmful in real life. Link: https://lkml.kernel.org/r/20210916130404.GA25094@kili Fixes: c0265342bff4 ("zram: introduce zram memory tracking") Signed-off-by: Dan Carpenter Cc: Minchan Kim Cc: Sergey Senozhatsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/block/zram/zram_drv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 081e77d595d7..f61910c65f0f 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -910,7 +910,7 @@ static ssize_t read_block_state(struct file *file, char __user *buf, zram_test_flag(zram, index, ZRAM_HUGE) ? 'h' : '.', zram_test_flag(zram, index, ZRAM_IDLE) ? 'i' : '.'); - if (count < copied) { + if (count <= copied) { zram_slot_unlock(zram, index); break; } From 755804d16965888bb069a4cd39005b97ba9e11fd Mon Sep 17 00:00:00 2001 From: Brian Geffon Date: Fri, 5 Nov 2021 13:45:15 -0700 Subject: [PATCH 106/166] zram: introduce an aged idle interface This change introduces an aged idle interface to the existing idle sysfs file for zram. When CONFIG_ZRAM_MEMORY_TRACKING is enabled the idle file now also accepts an integer argument. This integer is the age (in seconds) of pages to mark as idle. The idle file still supports 'all' as it always has. This new approach allows for much more control over which pages get marked as idle. [bgeffon@google.com: use IS_ENABLED and cleanup comment] Link: https://lkml.kernel.org/r/20210924161128.1508015-1-bgeffon@google.com [bgeffon@google.com: Sergey's cleanup suggestions] Link: https://lkml.kernel.org/r/20210929143056.13067-1-bgeffon@google.com Link: https://lkml.kernel.org/r/20210923130115.1344361-1-bgeffon@google.com Signed-off-by: Brian Geffon Acked-by: Minchan Kim Reviewed-by: Sergey Senozhatsky Cc: Nitin Gupta Cc: Jonathan Corbet Cc: Suleiman Souhlal Cc: Jesse Barnes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/blockdev/zram.rst | 8 +++ drivers/block/zram/zram_drv.c | 62 +++++++++++++++------ 2 files changed, 54 insertions(+), 16 deletions(-) diff --git a/Documentation/admin-guide/blockdev/zram.rst b/Documentation/admin-guide/blockdev/zram.rst index 700329d25f57..3e11926a4df9 100644 --- a/Documentation/admin-guide/blockdev/zram.rst +++ b/Documentation/admin-guide/blockdev/zram.rst @@ -328,6 +328,14 @@ as idle:: From now on, any pages on zram are idle pages. The idle mark will be removed until someone requests access of the block. IOW, unless there is access request, those pages are still idle pages. +Additionally, when CONFIG_ZRAM_MEMORY_TRACKING is enabled pages can be +marked as idle based on how long (in seconds) it's been since they were +last accessed:: + + echo 86400 > /sys/block/zramX/idle + +In this example all pages which haven't been accessed in more than 86400 +seconds (one day) will be marked idle. Admin can request writeback of those idle pages at right timing via:: diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index f61910c65f0f..0a9309a2ef54 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -291,22 +291,16 @@ static ssize_t mem_used_max_store(struct device *dev, return len; } -static ssize_t idle_store(struct device *dev, - struct device_attribute *attr, const char *buf, size_t len) +/* + * Mark all pages which are older than or equal to cutoff as IDLE. + * Callers should hold the zram init lock in read mode + */ +static void mark_idle(struct zram *zram, ktime_t cutoff) { - struct zram *zram = dev_to_zram(dev); + int is_idle = 1; unsigned long nr_pages = zram->disksize >> PAGE_SHIFT; int index; - if (!sysfs_streq(buf, "all")) - return -EINVAL; - - down_read(&zram->init_lock); - if (!init_done(zram)) { - up_read(&zram->init_lock); - return -EINVAL; - } - for (index = 0; index < nr_pages; index++) { /* * Do not mark ZRAM_UNDER_WB slot as ZRAM_IDLE to close race. @@ -314,14 +308,50 @@ static ssize_t idle_store(struct device *dev, */ zram_slot_lock(zram, index); if (zram_allocated(zram, index) && - !zram_test_flag(zram, index, ZRAM_UNDER_WB)) - zram_set_flag(zram, index, ZRAM_IDLE); + !zram_test_flag(zram, index, ZRAM_UNDER_WB)) { +#ifdef CONFIG_ZRAM_MEMORY_TRACKING + is_idle = !cutoff || ktime_after(cutoff, zram->table[index].ac_time); +#endif + if (is_idle) + zram_set_flag(zram, index, ZRAM_IDLE); + } zram_slot_unlock(zram, index); } +} +static ssize_t idle_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) +{ + struct zram *zram = dev_to_zram(dev); + ktime_t cutoff_time = 0; + ssize_t rv = -EINVAL; + + if (!sysfs_streq(buf, "all")) { + /* + * If it did not parse as 'all' try to treat it as an integer when + * we have memory tracking enabled. + */ + u64 age_sec; + + if (IS_ENABLED(CONFIG_ZRAM_MEMORY_TRACKING) && !kstrtoull(buf, 0, &age_sec)) + cutoff_time = ktime_sub(ktime_get_boottime(), + ns_to_ktime(age_sec * NSEC_PER_SEC)); + else + goto out; + } + + down_read(&zram->init_lock); + if (!init_done(zram)) + goto out_unlock; + + /* A cutoff_time of 0 marks everything as idle, this is the "all" behavior */ + mark_idle(zram, cutoff_time); + rv = len; + +out_unlock: up_read(&zram->init_lock); - - return len; +out: + return rv; } #ifdef CONFIG_ZRAM_WRITEBACK From 53944f171a89dff4e2a3d76f42e6eedb551bb861 Mon Sep 17 00:00:00 2001 From: Stephen Kitt Date: Fri, 5 Nov 2021 13:45:18 -0700 Subject: [PATCH 107/166] mm: remove HARDENED_USERCOPY_FALLBACK This has served its purpose and is no longer used. All usercopy violations appear to have been handled by now, any remaining instances (or new bugs) will cause copies to be rejected. This isn't a direct revert of commit 2d891fbc3bb6 ("usercopy: Allow strict enforcement of whitelists"); since usercopy_fallback is effectively 0, the fallback handling is removed too. This also removes the usercopy_fallback module parameter on slab_common. Link: https://github.com/KSPP/linux/issues/153 Link: https://lkml.kernel.org/r/20210921061149.1091163-1-steve@sk2.org Signed-off-by: Stephen Kitt Suggested-by: Kees Cook Acked-by: Kees Cook Reviewed-by: Joel Stanley [defconfig change] Acked-by: David Rientjes Cc: Christoph Lameter Cc: Pekka Enberg Cc: Joonsoo Kim Cc: Vlastimil Babka Cc: James Morris Cc: "Serge E . Hallyn" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/configs/skiroot_defconfig | 1 - include/linux/slab.h | 2 -- mm/slab.c | 13 ------------- mm/slab_common.c | 8 -------- mm/slub.c | 14 -------------- security/Kconfig | 14 -------------- 6 files changed, 52 deletions(-) diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig index b806a5d3a695..c3ba614c973d 100644 --- a/arch/powerpc/configs/skiroot_defconfig +++ b/arch/powerpc/configs/skiroot_defconfig @@ -275,7 +275,6 @@ CONFIG_NLS_UTF8=y CONFIG_ENCRYPTED_KEYS=y CONFIG_SECURITY=y CONFIG_HARDENED_USERCOPY=y -# CONFIG_HARDENED_USERCOPY_FALLBACK is not set CONFIG_HARDENED_USERCOPY_PAGESPAN=y CONFIG_FORTIFY_SOURCE=y CONFIG_SECURITY_LOCKDOWN_LSM=y diff --git a/include/linux/slab.h b/include/linux/slab.h index 837cb16232ef..181045148b06 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -142,8 +142,6 @@ struct mem_cgroup; void __init kmem_cache_init(void); bool slab_is_available(void); -extern bool usercopy_fallback; - struct kmem_cache *kmem_cache_create(const char *name, unsigned int size, unsigned int align, slab_flags_t flags, void (*ctor)(void *)); diff --git a/mm/slab.c b/mm/slab.c index 64ec17a3bc2b..da132a9ae6f8 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -4204,19 +4204,6 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page, n <= cachep->useroffset - offset + cachep->usersize) return; - /* - * If the copy is still within the allocated object, produce - * a warning instead of rejecting the copy. This is intended - * to be a temporary method to find any missing usercopy - * whitelists. - */ - if (usercopy_fallback && - offset <= cachep->object_size && - n <= cachep->object_size - offset) { - usercopy_warn("SLAB object", cachep->name, to_user, offset, n); - return; - } - usercopy_abort("SLAB object", cachep->name, to_user, offset, n); } #endif /* CONFIG_HARDENED_USERCOPY */ diff --git a/mm/slab_common.c b/mm/slab_common.c index ec2bb0beed75..e5d080a93009 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -37,14 +37,6 @@ LIST_HEAD(slab_caches); DEFINE_MUTEX(slab_mutex); struct kmem_cache *kmem_cache; -#ifdef CONFIG_HARDENED_USERCOPY -bool usercopy_fallback __ro_after_init = - IS_ENABLED(CONFIG_HARDENED_USERCOPY_FALLBACK); -module_param(usercopy_fallback, bool, 0400); -MODULE_PARM_DESC(usercopy_fallback, - "WARN instead of reject usercopy whitelist violations"); -#endif - static LIST_HEAD(slab_caches_to_rcu_destroy); static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work); static DECLARE_WORK(slab_caches_to_rcu_destroy_work, diff --git a/mm/slub.c b/mm/slub.c index e9a51dcf8bf9..432145d7b4ec 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -4489,7 +4489,6 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page, { struct kmem_cache *s; unsigned int offset; - size_t object_size; bool is_kfence = is_kfence_address(ptr); ptr = kasan_reset_tag(ptr); @@ -4522,19 +4521,6 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page, n <= s->useroffset - offset + s->usersize) return; - /* - * If the copy is still within the allocated object, produce - * a warning instead of rejecting the copy. This is intended - * to be a temporary method to find any missing usercopy - * whitelists. - */ - object_size = slab_ksize(s); - if (usercopy_fallback && - offset <= object_size && n <= object_size - offset) { - usercopy_warn("SLUB object", s->name, to_user, offset, n); - return; - } - usercopy_abort("SLUB object", s->name, to_user, offset, n); } #endif /* CONFIG_HARDENED_USERCOPY */ diff --git a/security/Kconfig b/security/Kconfig index 0ced7fd33e4d..d9698900c9b7 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -163,20 +163,6 @@ config HARDENED_USERCOPY or are part of the kernel text. This kills entire classes of heap overflow exploits and similar kernel memory exposures. -config HARDENED_USERCOPY_FALLBACK - bool "Allow usercopy whitelist violations to fallback to object size" - depends on HARDENED_USERCOPY - default y - help - This is a temporary option that allows missing usercopy whitelists - to be discovered via a WARN() to the kernel log, instead of - rejecting the copy, falling back to non-whitelisted hardened - usercopy that checks the slab allocation size instead of the - whitelist size. This option will be removed once it seems like - all missing usercopy whitelists have been identified and fixed. - Booting with "slab_common.usercopy_fallback=Y/N" can change - this setting. - config HARDENED_USERCOPY_PAGESPAN bool "Refuse to copy allocations that span multiple pages" depends on HARDENED_USERCOPY From a1554c002699cbc9ced2e9f44f9c1357181bead3 Mon Sep 17 00:00:00 2001 From: Mianhan Liu Date: Fri, 5 Nov 2021 13:45:21 -0700 Subject: [PATCH 108/166] include/linux/mm.h: move nr_free_buffer_pages from swap.h to mm.h nr_free_buffer_pages could be exposed through mm.h instead of swap.h. The advantage of this change is that it can reduce the obsolete includes. For example, net/ipv4/tcp.c wouldn't need swap.h any more since it has already included mm.h. Similarly, after checking all the other files, it comes that tcp.c, udp.c meter.c ,... follow the same rule, so these files can have swap.h removed too. Moreover, after preprocessing all the files that use nr_free_buffer_pages, it turns out that those files have already included mm.h.Thus, we can move nr_free_buffer_pages from swap.h to mm.h safely. This change will not affect the compilation of other files. Link: https://lkml.kernel.org/r/20210912133640.1624-1-liumh1@shanghaitech.edu.cn Signed-off-by: Mianhan Liu Cc: Jakub Kicinski CC: Ulf Hansson Cc: "David S . Miller" Cc: Simon Horman Cc: Pravin B Shelar Cc: Vlad Yasevich Cc: Marcelo Ricardo Leitner Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/mmc/core/mmc_test.c | 1 - include/linux/mm.h | 2 ++ include/linux/swap.h | 1 - net/ipv4/tcp.c | 1 - net/ipv4/udp.c | 1 - net/netfilter/ipvs/ip_vs_ctl.c | 1 - net/openvswitch/meter.c | 1 - net/sctp/protocol.c | 1 - 8 files changed, 2 insertions(+), 7 deletions(-) diff --git a/drivers/mmc/core/mmc_test.c b/drivers/mmc/core/mmc_test.c index 63524551a13a..e6a2fd2c6d5c 100644 --- a/drivers/mmc/core/mmc_test.c +++ b/drivers/mmc/core/mmc_test.c @@ -10,7 +10,6 @@ #include #include -#include /* For nr_free_buffer_pages() */ #include #include diff --git a/include/linux/mm.h b/include/linux/mm.h index 15058d9cec99..b1720aa63727 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -875,6 +875,8 @@ void put_pages_list(struct list_head *pages); void split_page(struct page *page, unsigned int order); void copy_huge_page(struct page *dst, struct page *src); +unsigned long nr_free_buffer_pages(void); + /* * Compound pages have a destructor function. Provide a * prototype for that function and accessor functions. diff --git a/include/linux/swap.h b/include/linux/swap.h index ba52f3a3478e..53f759a59996 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -335,7 +335,6 @@ void workingset_update_node(struct xa_node *node); /* linux/mm/page_alloc.c */ extern unsigned long totalreserve_pages; -extern unsigned long nr_free_buffer_pages(void); /* Definition of global_zone_page_state not available yet */ #define nr_free_pages() global_zone_page_state(NR_FREE_PAGES) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f5c336f8b0c8..c5e07a2c6c52 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -260,7 +260,6 @@ #include #include #include -#include #include #include #include diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 2fffcf2b54f3..319dd7bbfe33 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -78,7 +78,6 @@ #include #include #include -#include #include #include #include diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 29ec3ef63edc..6ea4b882435e 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -24,7 +24,6 @@ #include #include #include -#include #include #include diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index 896b8f5bc885..04a060ac7fdf 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index ec0f52567c16..35928fefae33 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -33,7 +33,6 @@ #include #include #include -#include #include #include #include From f39f21b3ddc7fc0f87eb6dc75ddc81b5bbfb7672 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 5 Nov 2021 13:45:25 -0700 Subject: [PATCH 109/166] stacktrace: move filter_irq_stacks() to kernel/stacktrace.c filter_irq_stacks() has little to do with the stackdepot implementation, except that it is usually used by users (such as KASAN) of stackdepot to reduce the stack trace. However, filter_irq_stacks() itself is not useful without a stack trace as obtained by stack_trace_save() and friends. Therefore, move filter_irq_stacks() to kernel/stacktrace.c, so that new users of filter_irq_stacks() do not have to start depending on STACKDEPOT only for filter_irq_stacks(). Link: https://lkml.kernel.org/r/20210923104803.2620285-1-elver@google.com Signed-off-by: Marco Elver Acked-by: Dmitry Vyukov Cc: Alexander Potapenko Cc: Jann Horn Cc: Aleksandr Nogikh Cc: Taras Madan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/stackdepot.h | 2 -- include/linux/stacktrace.h | 1 + kernel/stacktrace.c | 30 ++++++++++++++++++++++++++++++ lib/stackdepot.c | 24 ------------------------ 4 files changed, 31 insertions(+), 26 deletions(-) diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index b2f7e7c6ba54..d29860966bc9 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -25,8 +25,6 @@ depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned int stack_depot_fetch(depot_stack_handle_t handle, unsigned long **entries); -unsigned int filter_irq_stacks(unsigned long *entries, unsigned int nr_entries); - #ifdef CONFIG_STACKDEPOT int stack_depot_init(void); #else diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h index 9edecb494e9e..bef158815e83 100644 --- a/include/linux/stacktrace.h +++ b/include/linux/stacktrace.h @@ -21,6 +21,7 @@ unsigned int stack_trace_save_tsk(struct task_struct *task, unsigned int stack_trace_save_regs(struct pt_regs *regs, unsigned long *store, unsigned int size, unsigned int skipnr); unsigned int stack_trace_save_user(unsigned long *store, unsigned int size); +unsigned int filter_irq_stacks(unsigned long *entries, unsigned int nr_entries); /* Internal interfaces. Do not use in generic code */ #ifdef CONFIG_ARCH_STACKWALK diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c index 9f8117c7cfdd..9c625257023d 100644 --- a/kernel/stacktrace.c +++ b/kernel/stacktrace.c @@ -13,6 +13,7 @@ #include #include #include +#include /** * stack_trace_print - Print the entries in the stack trace @@ -373,3 +374,32 @@ unsigned int stack_trace_save_user(unsigned long *store, unsigned int size) #endif /* CONFIG_USER_STACKTRACE_SUPPORT */ #endif /* !CONFIG_ARCH_STACKWALK */ + +static inline bool in_irqentry_text(unsigned long ptr) +{ + return (ptr >= (unsigned long)&__irqentry_text_start && + ptr < (unsigned long)&__irqentry_text_end) || + (ptr >= (unsigned long)&__softirqentry_text_start && + ptr < (unsigned long)&__softirqentry_text_end); +} + +/** + * filter_irq_stacks - Find first IRQ stack entry in trace + * @entries: Pointer to stack trace array + * @nr_entries: Number of entries in the storage array + * + * Return: Number of trace entries until IRQ stack starts. + */ +unsigned int filter_irq_stacks(unsigned long *entries, unsigned int nr_entries) +{ + unsigned int i; + + for (i = 0; i < nr_entries; i++) { + if (in_irqentry_text(entries[i])) { + /* Include the irqentry function into the stack. */ + return i + 1; + } + } + return nr_entries; +} +EXPORT_SYMBOL_GPL(filter_irq_stacks); diff --git a/lib/stackdepot.c b/lib/stackdepot.c index bda58597e375..09485dc5bd12 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -20,7 +20,6 @@ */ #include -#include #include #include #include @@ -371,26 +370,3 @@ depot_stack_handle_t stack_depot_save(unsigned long *entries, return __stack_depot_save(entries, nr_entries, alloc_flags, true); } EXPORT_SYMBOL_GPL(stack_depot_save); - -static inline int in_irqentry_text(unsigned long ptr) -{ - return (ptr >= (unsigned long)&__irqentry_text_start && - ptr < (unsigned long)&__irqentry_text_end) || - (ptr >= (unsigned long)&__softirqentry_text_start && - ptr < (unsigned long)&__softirqentry_text_end); -} - -unsigned int filter_irq_stacks(unsigned long *entries, - unsigned int nr_entries) -{ - unsigned int i; - - for (i = 0; i < nr_entries; i++) { - if (in_irqentry_text(entries[i])) { - /* Include the irqentry function into the stack. */ - return i + 1; - } - } - return nr_entries; -} -EXPORT_SYMBOL_GPL(filter_irq_stacks); From 9a19aeb5665068c3e2727230588684aae2cab7ef Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 5 Nov 2021 13:45:28 -0700 Subject: [PATCH 110/166] kfence: count unexpectedly skipped allocations Maintain a counter to count allocations that are skipped due to being incompatible (oversized, incompatible gfp flags) or no capacity. This is to compute the fraction of allocations that could not be serviced by KFENCE, which we expect to be rare. Link: https://lkml.kernel.org/r/20210923104803.2620285-2-elver@google.com Signed-off-by: Marco Elver Reviewed-by: Dmitry Vyukov Acked-by: Alexander Potapenko Cc: Aleksandr Nogikh Cc: Jann Horn Cc: Taras Madan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kfence/core.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 7a97db8bc8e7..249d75b7e5ee 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -112,6 +112,8 @@ enum kfence_counter_id { KFENCE_COUNTER_FREES, KFENCE_COUNTER_ZOMBIES, KFENCE_COUNTER_BUGS, + KFENCE_COUNTER_SKIP_INCOMPAT, + KFENCE_COUNTER_SKIP_CAPACITY, KFENCE_COUNTER_COUNT, }; static atomic_long_t counters[KFENCE_COUNTER_COUNT]; @@ -121,6 +123,8 @@ static const char *const counter_names[] = { [KFENCE_COUNTER_FREES] = "total frees", [KFENCE_COUNTER_ZOMBIES] = "zombie allocations", [KFENCE_COUNTER_BUGS] = "total bugs", + [KFENCE_COUNTER_SKIP_INCOMPAT] = "skipped allocations (incompatible)", + [KFENCE_COUNTER_SKIP_CAPACITY] = "skipped allocations (capacity)", }; static_assert(ARRAY_SIZE(counter_names) == KFENCE_COUNTER_COUNT); @@ -271,8 +275,10 @@ static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t g list_del_init(&meta->list); } raw_spin_unlock_irqrestore(&kfence_freelist_lock, flags); - if (!meta) + if (!meta) { + atomic_long_inc(&counters[KFENCE_COUNTER_SKIP_CAPACITY]); return NULL; + } if (unlikely(!raw_spin_trylock_irqsave(&meta->lock, flags))) { /* @@ -740,8 +746,10 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) * Perform size check before switching kfence_allocation_gate, so that * we don't disable KFENCE without making an allocation. */ - if (size > PAGE_SIZE) + if (size > PAGE_SIZE) { + atomic_long_inc(&counters[KFENCE_COUNTER_SKIP_INCOMPAT]); return NULL; + } /* * Skip allocations from non-default zones, including DMA. We cannot @@ -749,8 +757,10 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) * properties (e.g. reside in DMAable memory). */ if ((flags & GFP_ZONEMASK) || - (s->flags & (SLAB_CACHE_DMA | SLAB_CACHE_DMA32))) + (s->flags & (SLAB_CACHE_DMA | SLAB_CACHE_DMA32))) { + atomic_long_inc(&counters[KFENCE_COUNTER_SKIP_INCOMPAT]); return NULL; + } /* * allocation_gate only needs to become non-zero, so it doesn't make From a9ab52bbcb52df49ec4b30e6741e120588989455 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 5 Nov 2021 13:45:31 -0700 Subject: [PATCH 111/166] kfence: move saving stack trace of allocations into __kfence_alloc() Move the saving of the stack trace of allocations into __kfence_alloc(), so that the stack entries array can be used outside of kfence_guarded_alloc() and we avoid potentially unwinding the stack multiple times. Link: https://lkml.kernel.org/r/20210923104803.2620285-3-elver@google.com Signed-off-by: Marco Elver Reviewed-by: Dmitry Vyukov Acked-by: Alexander Potapenko Cc: Aleksandr Nogikh Cc: Jann Horn Cc: Taras Madan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kfence/core.c | 35 ++++++++++++++++++++++++----------- 1 file changed, 24 insertions(+), 11 deletions(-) diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 249d75b7e5ee..db01814f8ff0 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -187,19 +187,26 @@ static inline unsigned long metadata_to_pageaddr(const struct kfence_metadata *m * Update the object's metadata state, including updating the alloc/free stacks * depending on the state transition. */ -static noinline void metadata_update_state(struct kfence_metadata *meta, - enum kfence_object_state next) +static noinline void +metadata_update_state(struct kfence_metadata *meta, enum kfence_object_state next, + unsigned long *stack_entries, size_t num_stack_entries) { struct kfence_track *track = next == KFENCE_OBJECT_FREED ? &meta->free_track : &meta->alloc_track; lockdep_assert_held(&meta->lock); - /* - * Skip over 1 (this) functions; noinline ensures we do not accidentally - * skip over the caller by never inlining. - */ - track->num_stack_entries = stack_trace_save(track->stack_entries, KFENCE_STACK_DEPTH, 1); + if (stack_entries) { + memcpy(track->stack_entries, stack_entries, + num_stack_entries * sizeof(stack_entries[0])); + } else { + /* + * Skip over 1 (this) functions; noinline ensures we do not + * accidentally skip over the caller by never inlining. + */ + num_stack_entries = stack_trace_save(track->stack_entries, KFENCE_STACK_DEPTH, 1); + } + track->num_stack_entries = num_stack_entries; track->pid = task_pid_nr(current); track->cpu = raw_smp_processor_id(); track->ts_nsec = local_clock(); /* Same source as printk timestamps. */ @@ -261,7 +268,8 @@ static __always_inline void for_each_canary(const struct kfence_metadata *meta, } } -static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t gfp) +static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t gfp, + unsigned long *stack_entries, size_t num_stack_entries) { struct kfence_metadata *meta = NULL; unsigned long flags; @@ -320,7 +328,7 @@ static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t g addr = (void *)meta->addr; /* Update remaining metadata. */ - metadata_update_state(meta, KFENCE_OBJECT_ALLOCATED); + metadata_update_state(meta, KFENCE_OBJECT_ALLOCATED, stack_entries, num_stack_entries); /* Pairs with READ_ONCE() in kfence_shutdown_cache(). */ WRITE_ONCE(meta->cache, cache); meta->size = size; @@ -400,7 +408,7 @@ static void kfence_guarded_free(void *addr, struct kfence_metadata *meta, bool z memzero_explicit(addr, meta->size); /* Mark the object as freed. */ - metadata_update_state(meta, KFENCE_OBJECT_FREED); + metadata_update_state(meta, KFENCE_OBJECT_FREED, NULL, 0); raw_spin_unlock_irqrestore(&meta->lock, flags); @@ -742,6 +750,9 @@ void kfence_shutdown_cache(struct kmem_cache *s) void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) { + unsigned long stack_entries[KFENCE_STACK_DEPTH]; + size_t num_stack_entries; + /* * Perform size check before switching kfence_allocation_gate, so that * we don't disable KFENCE without making an allocation. @@ -786,7 +797,9 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) if (!READ_ONCE(kfence_enabled)) return NULL; - return kfence_guarded_alloc(s, size, flags); + num_stack_entries = stack_trace_save(stack_entries, KFENCE_STACK_DEPTH, 0); + + return kfence_guarded_alloc(s, size, flags, stack_entries, num_stack_entries); } size_t kfence_ksize(const void *addr) From 08f6b10630f284755087f58aa393402e15b92977 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 5 Nov 2021 13:45:34 -0700 Subject: [PATCH 112/166] kfence: limit currently covered allocations when pool nearly full One of KFENCE's main design principles is that with increasing uptime, allocation coverage increases sufficiently to detect previously undetected bugs. We have observed that frequent long-lived allocations of the same source (e.g. pagecache) tend to permanently fill up the KFENCE pool with increasing system uptime, thus breaking the above requirement. The workaround thus far had been increasing the sample interval and/or increasing the KFENCE pool size, but is no reliable solution. To ensure diverse coverage of allocations, limit currently covered allocations of the same source once pool utilization reaches 75% (configurable via `kfence.skip_covered_thresh`) or above. The effect is retaining reasonable allocation coverage when the pool is close to full. A side-effect is that this also limits frequent long-lived allocations of the same source filling up the pool permanently. Uniqueness of an allocation for coverage purposes is based on its (partial) allocation stack trace (the source). A Counting Bloom filter is used to check if an allocation is covered; if the allocation is currently covered, the allocation is skipped by KFENCE. Testing was done using: (a) a synthetic workload that performs frequent long-lived allocations (default config values; sample_interval=1; num_objects=63), and (b) normal desktop workloads on an otherwise idle machine where the problem was first reported after a few days of uptime (default config values). In both test cases the sampled allocation rate no longer drops to zero at any point. In the case of (b) we observe (after 2 days uptime) 15% unique allocations in the pool, 77% pool utilization, with 20% "skipped allocations (covered)". [elver@google.com: simplify and just use hash_32(), use more random stack_hash_seed] Link: https://lkml.kernel.org/r/YU3MRGaCaJiYht5g@elver.google.com [elver@google.com: fix 32 bit] Link: https://lkml.kernel.org/r/20210923104803.2620285-4-elver@google.com Signed-off-by: Marco Elver Reviewed-by: Dmitry Vyukov Acked-by: Alexander Potapenko Cc: Aleksandr Nogikh Cc: Jann Horn Cc: Taras Madan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kfence/core.c | 109 ++++++++++++++++++++++++++++++++++++++++++++- mm/kfence/kfence.h | 2 + 2 files changed, 109 insertions(+), 2 deletions(-) diff --git a/mm/kfence/core.c b/mm/kfence/core.c index db01814f8ff0..b61ef93d9f98 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -10,12 +10,15 @@ #include #include #include +#include #include +#include #include #include #include #include #include +#include #include #include #include @@ -82,6 +85,10 @@ static const struct kernel_param_ops sample_interval_param_ops = { }; module_param_cb(sample_interval, &sample_interval_param_ops, &kfence_sample_interval, 0600); +/* Pool usage% threshold when currently covered allocations are skipped. */ +static unsigned long kfence_skip_covered_thresh __read_mostly = 75; +module_param_named(skip_covered_thresh, kfence_skip_covered_thresh, ulong, 0644); + /* The pool of pages used for guard pages and objects. */ char *__kfence_pool __ro_after_init; EXPORT_SYMBOL(__kfence_pool); /* Export for test modules. */ @@ -105,6 +112,32 @@ DEFINE_STATIC_KEY_FALSE(kfence_allocation_key); /* Gates the allocation, ensuring only one succeeds in a given period. */ atomic_t kfence_allocation_gate = ATOMIC_INIT(1); +/* + * A Counting Bloom filter of allocation coverage: limits currently covered + * allocations of the same source filling up the pool. + * + * Assuming a range of 15%-85% unique allocations in the pool at any point in + * time, the below parameters provide a probablity of 0.02-0.33 for false + * positive hits respectively: + * + * P(alloc_traces) = (1 - e^(-HNUM * (alloc_traces / SIZE)) ^ HNUM + */ +#define ALLOC_COVERED_HNUM 2 +#define ALLOC_COVERED_ORDER (const_ilog2(CONFIG_KFENCE_NUM_OBJECTS) + 2) +#define ALLOC_COVERED_SIZE (1 << ALLOC_COVERED_ORDER) +#define ALLOC_COVERED_HNEXT(h) hash_32(h, ALLOC_COVERED_ORDER) +#define ALLOC_COVERED_MASK (ALLOC_COVERED_SIZE - 1) +static atomic_t alloc_covered[ALLOC_COVERED_SIZE]; + +/* Stack depth used to determine uniqueness of an allocation. */ +#define UNIQUE_ALLOC_STACK_DEPTH ((size_t)8) + +/* + * Randomness for stack hashes, making the same collisions across reboots and + * different machines less likely. + */ +static u32 stack_hash_seed __ro_after_init; + /* Statistics counters for debugfs. */ enum kfence_counter_id { KFENCE_COUNTER_ALLOCATED, @@ -114,6 +147,7 @@ enum kfence_counter_id { KFENCE_COUNTER_BUGS, KFENCE_COUNTER_SKIP_INCOMPAT, KFENCE_COUNTER_SKIP_CAPACITY, + KFENCE_COUNTER_SKIP_COVERED, KFENCE_COUNTER_COUNT, }; static atomic_long_t counters[KFENCE_COUNTER_COUNT]; @@ -125,11 +159,57 @@ static const char *const counter_names[] = { [KFENCE_COUNTER_BUGS] = "total bugs", [KFENCE_COUNTER_SKIP_INCOMPAT] = "skipped allocations (incompatible)", [KFENCE_COUNTER_SKIP_CAPACITY] = "skipped allocations (capacity)", + [KFENCE_COUNTER_SKIP_COVERED] = "skipped allocations (covered)", }; static_assert(ARRAY_SIZE(counter_names) == KFENCE_COUNTER_COUNT); /* === Internals ============================================================ */ +static inline bool should_skip_covered(void) +{ + unsigned long thresh = (CONFIG_KFENCE_NUM_OBJECTS * kfence_skip_covered_thresh) / 100; + + return atomic_long_read(&counters[KFENCE_COUNTER_ALLOCATED]) > thresh; +} + +static u32 get_alloc_stack_hash(unsigned long *stack_entries, size_t num_entries) +{ + num_entries = min(num_entries, UNIQUE_ALLOC_STACK_DEPTH); + num_entries = filter_irq_stacks(stack_entries, num_entries); + return jhash(stack_entries, num_entries * sizeof(stack_entries[0]), stack_hash_seed); +} + +/* + * Adds (or subtracts) count @val for allocation stack trace hash + * @alloc_stack_hash from Counting Bloom filter. + */ +static void alloc_covered_add(u32 alloc_stack_hash, int val) +{ + int i; + + for (i = 0; i < ALLOC_COVERED_HNUM; i++) { + atomic_add(val, &alloc_covered[alloc_stack_hash & ALLOC_COVERED_MASK]); + alloc_stack_hash = ALLOC_COVERED_HNEXT(alloc_stack_hash); + } +} + +/* + * Returns true if the allocation stack trace hash @alloc_stack_hash is + * currently contained (non-zero count) in Counting Bloom filter. + */ +static bool alloc_covered_contains(u32 alloc_stack_hash) +{ + int i; + + for (i = 0; i < ALLOC_COVERED_HNUM; i++) { + if (!atomic_read(&alloc_covered[alloc_stack_hash & ALLOC_COVERED_MASK])) + return false; + alloc_stack_hash = ALLOC_COVERED_HNEXT(alloc_stack_hash); + } + + return true; +} + static bool kfence_protect(unsigned long addr) { return !KFENCE_WARN_ON(!kfence_protect_page(ALIGN_DOWN(addr, PAGE_SIZE), true)); @@ -269,7 +349,8 @@ static __always_inline void for_each_canary(const struct kfence_metadata *meta, } static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t gfp, - unsigned long *stack_entries, size_t num_stack_entries) + unsigned long *stack_entries, size_t num_stack_entries, + u32 alloc_stack_hash) { struct kfence_metadata *meta = NULL; unsigned long flags; @@ -332,6 +413,8 @@ static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t g /* Pairs with READ_ONCE() in kfence_shutdown_cache(). */ WRITE_ONCE(meta->cache, cache); meta->size = size; + meta->alloc_stack_hash = alloc_stack_hash; + for_each_canary(meta, set_canary_byte); /* Set required struct page fields. */ @@ -344,6 +427,8 @@ static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t g raw_spin_unlock_irqrestore(&meta->lock, flags); + alloc_covered_add(alloc_stack_hash, 1); + /* Memory initialization. */ /* @@ -412,6 +497,8 @@ static void kfence_guarded_free(void *addr, struct kfence_metadata *meta, bool z raw_spin_unlock_irqrestore(&meta->lock, flags); + alloc_covered_add(meta->alloc_stack_hash, -1); + /* Protect to detect use-after-frees. */ kfence_protect((unsigned long)addr); @@ -677,6 +764,7 @@ void __init kfence_init(void) if (!kfence_sample_interval) return; + stack_hash_seed = (u32)random_get_entropy(); if (!kfence_init_pool()) { pr_err("%s failed\n", __func__); return; @@ -752,6 +840,7 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) { unsigned long stack_entries[KFENCE_STACK_DEPTH]; size_t num_stack_entries; + u32 alloc_stack_hash; /* * Perform size check before switching kfence_allocation_gate, so that @@ -799,7 +888,23 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) num_stack_entries = stack_trace_save(stack_entries, KFENCE_STACK_DEPTH, 0); - return kfence_guarded_alloc(s, size, flags, stack_entries, num_stack_entries); + /* + * Do expensive check for coverage of allocation in slow-path after + * allocation_gate has already become non-zero, even though it might + * mean not making any allocation within a given sample interval. + * + * This ensures reasonable allocation coverage when the pool is almost + * full, including avoiding long-lived allocations of the same source + * filling up the pool (e.g. pagecache allocations). + */ + alloc_stack_hash = get_alloc_stack_hash(stack_entries, num_stack_entries); + if (should_skip_covered() && alloc_covered_contains(alloc_stack_hash)) { + atomic_long_inc(&counters[KFENCE_COUNTER_SKIP_COVERED]); + return NULL; + } + + return kfence_guarded_alloc(s, size, flags, stack_entries, num_stack_entries, + alloc_stack_hash); } size_t kfence_ksize(const void *addr) diff --git a/mm/kfence/kfence.h b/mm/kfence/kfence.h index c1f23c61e5f9..2a2d5de9d379 100644 --- a/mm/kfence/kfence.h +++ b/mm/kfence/kfence.h @@ -87,6 +87,8 @@ struct kfence_metadata { /* Allocation and free stack information. */ struct kfence_track alloc_track; struct kfence_track free_track; + /* For updating alloc_covered on frees. */ + u32 alloc_stack_hash; }; extern struct kfence_metadata kfence_metadata[CONFIG_KFENCE_NUM_OBJECTS]; From 5cc906b4b4a510b274113ddb3f88d60644553f79 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 5 Nov 2021 13:45:37 -0700 Subject: [PATCH 113/166] kfence: add note to documentation about skipping covered allocations Add a note briefly mentioning the new policy about "skipping currently covered allocations if pool close to full." Since this has a notable impact on KFENCE's bug-detection ability on systems with large uptimes, it is worth pointing out the feature. Link: https://lkml.kernel.org/r/20210923104803.2620285-5-elver@google.com Signed-off-by: Marco Elver Reviewed-by: Dmitry Vyukov Acked-by: Alexander Potapenko Cc: Aleksandr Nogikh Cc: Jann Horn Cc: Taras Madan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/dev-tools/kfence.rst | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/Documentation/dev-tools/kfence.rst b/Documentation/dev-tools/kfence.rst index 0fbe3308bf37..d45f952986ae 100644 --- a/Documentation/dev-tools/kfence.rst +++ b/Documentation/dev-tools/kfence.rst @@ -269,6 +269,17 @@ tail of KFENCE's freelist, so that the least recently freed objects are reused first, and the chances of detecting use-after-frees of recently freed objects is increased. +If pool utilization reaches 75% (default) or above, to reduce the risk of the +pool eventually being fully occupied by allocated objects yet ensure diverse +coverage of allocations, KFENCE limits currently covered allocations of the +same source from further filling up the pool. The "source" of an allocation is +based on its partial allocation stack trace. A side-effect is that this also +limits frequent long-lived allocations (e.g. pagecache) of the same source +filling up the pool permanently, which is the most common risk for the pool +becoming full and the sampled allocation rate dropping to zero. The threshold +at which to start limiting currently covered allocations can be configured via +the boot parameter ``kfence.skip_covered_thresh`` (pool usage%). + Interface --------- From f51733e2fc4d8f01d813d71fb036d6854a53e7e3 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 5 Nov 2021 13:45:40 -0700 Subject: [PATCH 114/166] kfence: test: use kunit_skip() to skip tests Use the new kunit_skip() to skip tests if requirements were not met. It makes it easier to see in KUnit's summary if there were skipped tests. Link: https://lkml.kernel.org/r/20210922182541.1372400-1-elver@google.com Signed-off-by: Marco Elver Reviewed-by: David Gow Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Aleksandr Nogikh Cc: Taras Madan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kfence/kfence_test.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/mm/kfence/kfence_test.c b/mm/kfence/kfence_test.c index f1690cf54199..695030c1fff8 100644 --- a/mm/kfence/kfence_test.c +++ b/mm/kfence/kfence_test.c @@ -32,6 +32,11 @@ #define arch_kfence_test_address(addr) (addr) #endif +#define KFENCE_TEST_REQUIRES(test, cond) do { \ + if (!(cond)) \ + kunit_skip((test), "Test requires: " #cond); \ +} while (0) + /* Report as observed from console. */ static struct { spinlock_t lock; @@ -555,8 +560,7 @@ static void test_init_on_free(struct kunit *test) }; int i; - if (!IS_ENABLED(CONFIG_INIT_ON_FREE_DEFAULT_ON)) - return; + KFENCE_TEST_REQUIRES(test, IS_ENABLED(CONFIG_INIT_ON_FREE_DEFAULT_ON)); /* Assume it hasn't been disabled on command line. */ setup_test_cache(test, size, 0, NULL); @@ -603,10 +607,8 @@ static void test_gfpzero(struct kunit *test) char *buf1, *buf2; int i; - if (CONFIG_KFENCE_SAMPLE_INTERVAL > 100) { - kunit_warn(test, "skipping ... would take too long\n"); - return; - } + /* Skip if we think it'd take too long. */ + KFENCE_TEST_REQUIRES(test, CONFIG_KFENCE_SAMPLE_INTERVAL <= 100); setup_test_cache(test, size, 0, NULL); buf1 = test_alloc(test, size, GFP_KERNEL, ALLOCATE_ANY); From 49332956227adb35ffa7e3282c13e787325ff301 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 5 Nov 2021 13:45:43 -0700 Subject: [PATCH 115/166] kfence: shorten critical sections of alloc/free Initializing memory and setting/checking the canary bytes is relatively expensive, and doing so in the meta->lock critical sections extends the duration with preemption and interrupts disabled unnecessarily. Any reads to meta->addr and meta->size in kfence_guarded_alloc() and kfence_guarded_free() don't require locking meta->lock as long as the object is removed from the freelist: only kfence_guarded_alloc() sets meta->addr and meta->size after removing it from the freelist, which requires a preceding kfence_guarded_free() returning it to the list or the initial state. Therefore move reads to meta->addr and meta->size, including expensive memory initialization using them, out of meta->lock critical sections. Link: https://lkml.kernel.org/r/20210930153706.2105471-1-elver@google.com Signed-off-by: Marco Elver Acked-by: Alexander Potapenko Cc: Dmitry Vyukov Cc: Jann Horn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kfence/core.c | 38 +++++++++++++++++++++----------------- 1 file changed, 21 insertions(+), 17 deletions(-) diff --git a/mm/kfence/core.c b/mm/kfence/core.c index b61ef93d9f98..802905b1c89b 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -309,12 +309,19 @@ static inline bool set_canary_byte(u8 *addr) /* Check canary byte at @addr. */ static inline bool check_canary_byte(u8 *addr) { + struct kfence_metadata *meta; + unsigned long flags; + if (likely(*addr == KFENCE_CANARY_PATTERN(addr))) return true; atomic_long_inc(&counters[KFENCE_COUNTER_BUGS]); - kfence_report_error((unsigned long)addr, false, NULL, addr_to_metadata((unsigned long)addr), - KFENCE_ERROR_CORRUPTION); + + meta = addr_to_metadata((unsigned long)addr); + raw_spin_lock_irqsave(&meta->lock, flags); + kfence_report_error((unsigned long)addr, false, NULL, meta, KFENCE_ERROR_CORRUPTION); + raw_spin_unlock_irqrestore(&meta->lock, flags); + return false; } @@ -324,8 +331,6 @@ static __always_inline void for_each_canary(const struct kfence_metadata *meta, const unsigned long pageaddr = ALIGN_DOWN(meta->addr, PAGE_SIZE); unsigned long addr; - lockdep_assert_held(&meta->lock); - /* * We'll iterate over each canary byte per-side until fn() returns * false. However, we'll still iterate over the canary bytes to the @@ -414,8 +419,9 @@ static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t g WRITE_ONCE(meta->cache, cache); meta->size = size; meta->alloc_stack_hash = alloc_stack_hash; + raw_spin_unlock_irqrestore(&meta->lock, flags); - for_each_canary(meta, set_canary_byte); + alloc_covered_add(alloc_stack_hash, 1); /* Set required struct page fields. */ page = virt_to_page(meta->addr); @@ -425,11 +431,8 @@ static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t g if (IS_ENABLED(CONFIG_SLAB)) page->s_mem = addr; - raw_spin_unlock_irqrestore(&meta->lock, flags); - - alloc_covered_add(alloc_stack_hash, 1); - /* Memory initialization. */ + for_each_canary(meta, set_canary_byte); /* * We check slab_want_init_on_alloc() ourselves, rather than letting @@ -454,6 +457,7 @@ static void kfence_guarded_free(void *addr, struct kfence_metadata *meta, bool z { struct kcsan_scoped_access assert_page_exclusive; unsigned long flags; + bool init; raw_spin_lock_irqsave(&meta->lock, flags); @@ -481,6 +485,13 @@ static void kfence_guarded_free(void *addr, struct kfence_metadata *meta, bool z meta->unprotected_page = 0; } + /* Mark the object as freed. */ + metadata_update_state(meta, KFENCE_OBJECT_FREED, NULL, 0); + init = slab_want_init_on_free(meta->cache); + raw_spin_unlock_irqrestore(&meta->lock, flags); + + alloc_covered_add(meta->alloc_stack_hash, -1); + /* Check canary bytes for memory corruption. */ for_each_canary(meta, check_canary_byte); @@ -489,16 +500,9 @@ static void kfence_guarded_free(void *addr, struct kfence_metadata *meta, bool z * data is still there, and after a use-after-free is detected, we * unprotect the page, so the data is still accessible. */ - if (!zombie && unlikely(slab_want_init_on_free(meta->cache))) + if (!zombie && unlikely(init)) memzero_explicit(addr, meta->size); - /* Mark the object as freed. */ - metadata_update_state(meta, KFENCE_OBJECT_FREED, NULL, 0); - - raw_spin_unlock_irqrestore(&meta->lock, flags); - - alloc_covered_add(meta->alloc_stack_hash, -1); - /* Protect to detect use-after-frees. */ kfence_protect((unsigned long)addr); From 07e8481d3c38f461d7b79c1d5c9afe013b162b0c Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 5 Nov 2021 13:45:46 -0700 Subject: [PATCH 116/166] kfence: always use static branches to guard kfence_alloc() Regardless of KFENCE mode (CONFIG_KFENCE_STATIC_KEYS: either using static keys to gate allocations, or using a simple dynamic branch), always use a static branch to avoid the dynamic branch in kfence_alloc() if KFENCE was disabled at boot. For CONFIG_KFENCE_STATIC_KEYS=n, this now avoids the dynamic branch if KFENCE was disabled at boot. To simplify, also unifies the location where kfence_allocation_gate is read-checked to just be inline in kfence_alloc(). Link: https://lkml.kernel.org/r/20211019102524.2807208-1-elver@google.com Signed-off-by: Marco Elver Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Jann Horn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kfence.h | 21 +++++++++++---------- mm/kfence/core.c | 16 +++++++--------- 2 files changed, 18 insertions(+), 19 deletions(-) diff --git a/include/linux/kfence.h b/include/linux/kfence.h index 3fe6dd8a18c1..4b5e3679a72c 100644 --- a/include/linux/kfence.h +++ b/include/linux/kfence.h @@ -14,6 +14,9 @@ #ifdef CONFIG_KFENCE +#include +#include + /* * We allocate an even number of pages, as it simplifies calculations to map * address to metadata indices; effectively, the very first page serves as an @@ -22,13 +25,8 @@ #define KFENCE_POOL_SIZE ((CONFIG_KFENCE_NUM_OBJECTS + 1) * 2 * PAGE_SIZE) extern char *__kfence_pool; -#ifdef CONFIG_KFENCE_STATIC_KEYS -#include DECLARE_STATIC_KEY_FALSE(kfence_allocation_key); -#else -#include extern atomic_t kfence_allocation_gate; -#endif /** * is_kfence_address() - check if an address belongs to KFENCE pool @@ -116,13 +114,16 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags); */ static __always_inline void *kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) { -#ifdef CONFIG_KFENCE_STATIC_KEYS - if (static_branch_unlikely(&kfence_allocation_key)) +#if defined(CONFIG_KFENCE_STATIC_KEYS) || CONFIG_KFENCE_SAMPLE_INTERVAL == 0 + if (!static_branch_unlikely(&kfence_allocation_key)) + return NULL; #else - if (unlikely(!atomic_read(&kfence_allocation_gate))) + if (!static_branch_likely(&kfence_allocation_key)) + return NULL; #endif - return __kfence_alloc(s, size, flags); - return NULL; + if (likely(atomic_read(&kfence_allocation_gate))) + return NULL; + return __kfence_alloc(s, size, flags); } /** diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 802905b1c89b..09945784df9e 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -104,10 +104,11 @@ struct kfence_metadata kfence_metadata[CONFIG_KFENCE_NUM_OBJECTS]; static struct list_head kfence_freelist = LIST_HEAD_INIT(kfence_freelist); static DEFINE_RAW_SPINLOCK(kfence_freelist_lock); /* Lock protecting freelist. */ -#ifdef CONFIG_KFENCE_STATIC_KEYS -/* The static key to set up a KFENCE allocation. */ +/* + * The static key to set up a KFENCE allocation; or if static keys are not used + * to gate allocations, to avoid a load and compare if KFENCE is disabled. + */ DEFINE_STATIC_KEY_FALSE(kfence_allocation_key); -#endif /* Gates the allocation, ensuring only one succeeds in a given period. */ atomic_t kfence_allocation_gate = ATOMIC_INIT(1); @@ -774,6 +775,8 @@ void __init kfence_init(void) return; } + if (!IS_ENABLED(CONFIG_KFENCE_STATIC_KEYS)) + static_branch_enable(&kfence_allocation_key); WRITE_ONCE(kfence_enabled, true); queue_delayed_work(system_unbound_wq, &kfence_timer, 0); pr_info("initialized - using %lu bytes for %d objects at 0x%p-0x%p\n", KFENCE_POOL_SIZE, @@ -866,12 +869,7 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) return NULL; } - /* - * allocation_gate only needs to become non-zero, so it doesn't make - * sense to continue writing to it and pay the associated contention - * cost, in case we have a large number of concurrent allocations. - */ - if (atomic_read(&kfence_allocation_gate) || atomic_inc_return(&kfence_allocation_gate) > 1) + if (atomic_inc_return(&kfence_allocation_gate) > 1) return NULL; #ifdef CONFIG_KFENCE_STATIC_KEYS /* From 4f612ed3f748962cbef1316ff3d323e2b9055b6e Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 5 Nov 2021 13:45:49 -0700 Subject: [PATCH 117/166] kfence: default to dynamic branch instead of static keys mode We have observed that on very large machines with newer CPUs, the static key/branch switching delay is on the order of milliseconds. This is due to the required broadcast IPIs, which simply does not scale well to hundreds of CPUs (cores). If done too frequently, this can adversely affect tail latencies of various workloads. One workaround is to increase the sample interval to several seconds, while decreasing sampled allocation coverage, but the problem still exists and could still increase tail latencies. As already noted in the Kconfig help text, there are trade-offs: at lower sample intervals the dynamic branch results in better performance; however, at very large sample intervals, the static keys mode can result in better performance -- careful benchmarking is recommended. Our initial benchmarking showed that with large enough sample intervals and workloads stressing the allocator, the static keys mode was slightly better. Evaluating and observing the possible system-wide side-effects of the static-key-switching induced broadcast IPIs, however, was a blind spot (in particular on large machines with 100s of cores). Therefore, a major downside of the static keys mode is, unfortunately, that it is hard to predict performance on new system architectures and topologies, but also making conclusions about performance of new workloads based on a limited set of benchmarks. Most distributions will simply select the defaults, while targeting a large variety of different workloads and system architectures. As such, the better default is CONFIG_KFENCE_STATIC_KEYS=n, and re-enabling it is only recommended after careful evaluation. For reference, on x86-64 the condition in kfence_alloc() generates exactly 2 instructions in the kmem_cache_alloc() fast-path: | ... | cmpl $0x0,0x1a8021c(%rip) # ffffffff82d560d0 | je ffffffff812d6003 | ... which, given kfence_allocation_gate is infrequently modified, should be well predicted by most CPUs. Link: https://lkml.kernel.org/r/20211019102524.2807208-2-elver@google.com Signed-off-by: Marco Elver Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Jann Horn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/dev-tools/kfence.rst | 12 ++++++++---- lib/Kconfig.kfence | 26 +++++++++++++++----------- 2 files changed, 23 insertions(+), 15 deletions(-) diff --git a/Documentation/dev-tools/kfence.rst b/Documentation/dev-tools/kfence.rst index d45f952986ae..ac6b89d1a8c3 100644 --- a/Documentation/dev-tools/kfence.rst +++ b/Documentation/dev-tools/kfence.rst @@ -231,10 +231,14 @@ Guarded allocations are set up based on the sample interval. After expiration of the sample interval, the next allocation through the main allocator (SLAB or SLUB) returns a guarded allocation from the KFENCE object pool (allocation sizes up to PAGE_SIZE are supported). At this point, the timer is reset, and -the next allocation is set up after the expiration of the interval. To "gate" a -KFENCE allocation through the main allocator's fast-path without overhead, -KFENCE relies on static branches via the static keys infrastructure. The static -branch is toggled to redirect the allocation to KFENCE. +the next allocation is set up after the expiration of the interval. + +When using ``CONFIG_KFENCE_STATIC_KEYS=y``, KFENCE allocations are "gated" +through the main allocator's fast-path by relying on static branches via the +static keys infrastructure. The static branch is toggled to redirect the +allocation to KFENCE. Depending on sample interval, target workloads, and +system architecture, this may perform better than the simple dynamic branch. +Careful benchmarking is recommended. KFENCE objects each reside on a dedicated page, at either the left or right page boundaries selected at random. The pages to the left and right of the diff --git a/lib/Kconfig.kfence b/lib/Kconfig.kfence index e641add33947..912f252a41fc 100644 --- a/lib/Kconfig.kfence +++ b/lib/Kconfig.kfence @@ -25,17 +25,6 @@ menuconfig KFENCE if KFENCE -config KFENCE_STATIC_KEYS - bool "Use static keys to set up allocations" - default y - depends on JUMP_LABEL # To ensure performance, require jump labels - help - Use static keys (static branches) to set up KFENCE allocations. Using - static keys is normally recommended, because it avoids a dynamic - branch in the allocator's fast path. However, with very low sample - intervals, or on systems that do not support jump labels, a dynamic - branch may still be an acceptable performance trade-off. - config KFENCE_SAMPLE_INTERVAL int "Default sample interval in milliseconds" default 100 @@ -56,6 +45,21 @@ config KFENCE_NUM_OBJECTS pages are required; with one containing the object and two adjacent ones used as guard pages. +config KFENCE_STATIC_KEYS + bool "Use static keys to set up allocations" if EXPERT + depends on JUMP_LABEL + help + Use static keys (static branches) to set up KFENCE allocations. This + option is only recommended when using very large sample intervals, or + performance has carefully been evaluated with this option. + + Using static keys comes with trade-offs that need to be carefully + evaluated given target workloads and system architectures. Notably, + enabling and disabling static keys invoke IPI broadcasts, the latency + and impact of which is much harder to predict than a dynamic branch. + + Say N if you are unsure. + config KFENCE_STRESS_TEST_FAULTS int "Stress testing of fault handling and error reporting" if EXPERT default 0 From f24b0626076783d56ef41c6459fedf70ab6dcbd0 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 5 Nov 2021 13:45:52 -0700 Subject: [PATCH 118/166] mm/damon: grammar s/works/work/ Correct a singular versus plural grammar mistake in the help text for the DAMON_VADDR config symbol. Link: https://lkml.kernel.org/r/20210914073451.3883834-1-geert@linux-m68k.org Fixes: 3f49584b262cf8f4 ("mm/damon: implement primitives for the virtual memory address spaces") Signed-off-by: Geert Uytterhoeven Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/damon/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig index 37024798a97c..ba8898c7eb8e 100644 --- a/mm/damon/Kconfig +++ b/mm/damon/Kconfig @@ -30,7 +30,7 @@ config DAMON_VADDR select PAGE_IDLE_FLAG help This builds the default data access monitoring primitives for DAMON - that works for virtual address spaces. + that work for virtual address spaces. config DAMON_VADDR_KUNIT_TEST bool "Test for DAMON primitives" if !KUNIT_ALL_TESTS From ad782c48df326eb13cf5dec7aab571b44be3e415 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:45:55 -0700 Subject: [PATCH 119/166] Documentation/vm: move user guides to admin-guide/mm/ Most memory management user guide documents are in 'admin-guide/mm/', but two of those are in 'vm/'. This moves the two docs into 'admin-guide/mm' for easier documents finding. Link: https://lkml.kernel.org/r/20210917123958.3819-2-sj@kernel.org Signed-off-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/mm/index.rst | 2 ++ .../{vm => admin-guide/mm}/swap_numa.rst | 0 .../{vm => admin-guide/mm}/zswap.rst | 0 Documentation/vm/index.rst | 26 ++++--------------- 4 files changed, 7 insertions(+), 21 deletions(-) rename Documentation/{vm => admin-guide/mm}/swap_numa.rst (100%) rename Documentation/{vm => admin-guide/mm}/zswap.rst (100%) diff --git a/Documentation/admin-guide/mm/index.rst b/Documentation/admin-guide/mm/index.rst index cbd19d5e625f..c21b5823f126 100644 --- a/Documentation/admin-guide/mm/index.rst +++ b/Documentation/admin-guide/mm/index.rst @@ -37,5 +37,7 @@ the Linux memory management. numaperf pagemap soft-dirty + swap_numa transhuge userfaultfd + zswap diff --git a/Documentation/vm/swap_numa.rst b/Documentation/admin-guide/mm/swap_numa.rst similarity index 100% rename from Documentation/vm/swap_numa.rst rename to Documentation/admin-guide/mm/swap_numa.rst diff --git a/Documentation/vm/zswap.rst b/Documentation/admin-guide/mm/zswap.rst similarity index 100% rename from Documentation/vm/zswap.rst rename to Documentation/admin-guide/mm/zswap.rst diff --git a/Documentation/vm/index.rst b/Documentation/vm/index.rst index b51f0d8992f8..6f5ffef4b716 100644 --- a/Documentation/vm/index.rst +++ b/Documentation/vm/index.rst @@ -3,27 +3,11 @@ Linux Memory Management Documentation ===================================== This is a collection of documents about the Linux memory management (mm) -subsystem. If you are looking for advice on simply allocating memory, -see the :ref:`memory_allocation`. - -User guides for MM features -=========================== - -The following documents provide guides for controlling and tuning -various features of the Linux memory management - -.. toctree:: - :maxdepth: 1 - - swap_numa - zswap - -Kernel developers MM documentation -================================== - -The below documents describe MM internals with different level of -details ranging from notes and mailing list responses to elaborate -descriptions of data structures and algorithms. +subsystem internals with different level of details ranging from notes and +mailing list responses for elaborating descriptions of data structures and +algorithms. If you are looking for advice on simply allocating memory, see the +:ref:`memory_allocation`. For controlling and tuning guides, see the +:doc:`admin guide <../admin-guide/mm/index>`. .. toctree:: :maxdepth: 1 From f9803a9918468d70d98d31c23cb7613d873e723f Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:45:58 -0700 Subject: [PATCH 120/166] MAINTAINERS: update SeongJae's email address This updates SeongJae's email address in MAINTAINERS file to his preferred one. Link: https://lkml.kernel.org/r/20210917123958.3819-3-sj@kernel.org Signed-off-by: SeongJae Park Cc: Jonathan Corbet Cc: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 3b79fd441dde..3cf33e113b9b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5161,7 +5161,7 @@ F: net/ax25/ax25_timer.c F: net/ax25/sysctl_net_ax25.c DATA ACCESS MONITOR -M: SeongJae Park +M: SeongJae Park L: linux-mm@kvack.org S: Maintained F: Documentation/admin-guide/mm/damon/ From 876d0aac2e3af10fbaf1c7a814840c71e470dc5c Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:01 -0700 Subject: [PATCH 121/166] docs/vm/damon: remove broken reference Building DAMON documents warns for a reference to nonexisting doc, as below: $ time make htmldocs [...] Documentation/vm/damon/index.rst:24: WARNING: toctree contains reference to nonexisting document 'vm/damon/plans' This fixes the warning by removing the wrong reference. Link: https://lkml.kernel.org/r/20210917123958.3819-4-sj@kernel.org Signed-off-by: SeongJae Park Cc: Jonathan Corbet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/vm/damon/index.rst | 1 - 1 file changed, 1 deletion(-) diff --git a/Documentation/vm/damon/index.rst b/Documentation/vm/damon/index.rst index a2858baf3bf1..48c0bbff98b2 100644 --- a/Documentation/vm/damon/index.rst +++ b/Documentation/vm/damon/index.rst @@ -27,4 +27,3 @@ workloads and systems. faq design api - plans From d2f272b35a84ace2ef04334a9822fd726a7f061b Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:04 -0700 Subject: [PATCH 122/166] include/linux/damon.h: fix kernel-doc comments for 'damon_callback' A few Kernel-doc comments in 'damon.h' are broken. This fixes them. Link: https://lkml.kernel.org/r/20210917123958.3819-5-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 | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/include/linux/damon.h b/include/linux/damon.h index d68b67b8d458..755d70804705 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -62,7 +62,7 @@ struct damon_target { struct damon_ctx; /** - * struct damon_primitive Monitoring primitives for given use cases. + * struct damon_primitive - Monitoring primitives for given use cases. * * @init: Initialize primitive-internal data structures. * @update: Update primitive-internal data structures. @@ -108,8 +108,8 @@ struct damon_primitive { void (*cleanup)(struct damon_ctx *context); }; -/* - * struct damon_callback Monitoring events notification callbacks. +/** + * struct damon_callback - Monitoring events notification callbacks. * * @before_start: Called before starting the monitoring. * @after_sampling: Called after each sampling. From 704571f997424ecd64b10b37ca6097e65690240a Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:06 -0700 Subject: [PATCH 123/166] mm/damon/core: print kdamond start log in debug mode only Logging of kdamond startup is using 'pr_info()' unnecessarily. This makes it to use 'pr_debug()' instead. Link: https://lkml.kernel.org/r/20210917123958.3819-6-sj@kernel.org Signed-off-by: SeongJae Park Cc: Jonathan Corbet Cc: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/damon/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/damon/core.c b/mm/damon/core.c index 30e9211f494a..874558a790a0 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -653,7 +653,7 @@ static int kdamond_fn(void *data) unsigned long sz_limit = 0; mutex_lock(&ctx->kdamond_lock); - pr_info("kdamond (%d) starts\n", ctx->kdamond->pid); + pr_debug("kdamond (%d) starts\n", ctx->kdamond->pid); mutex_unlock(&ctx->kdamond_lock); if (ctx->primitive.init) From 5f7fe2b9b827662cf349ab45406d6cbf0cc6251f Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Fri, 5 Nov 2021 13:46:09 -0700 Subject: [PATCH 124/166] mm/damon: remove unnecessary do_exit() from kdamond Just return from the kthread function. Link: https://lkml.kernel.org/r/20210927232421.17694-1-changbin.du@gmail.com Signed-off-by: Changbin Du Cc: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/damon/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/damon/core.c b/mm/damon/core.c index 874558a790a0..61a9e3b37bc9 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -714,7 +714,7 @@ static int kdamond_fn(void *data) nr_running_ctxs--; mutex_unlock(&damon_lock); - do_exit(0); + return 0; } #include "core-test.h" From 42e4cef5fe48333e0db6e98b019edf5f2c2f11fd Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Fri, 5 Nov 2021 13:46:12 -0700 Subject: [PATCH 125/166] mm/damon: needn't hold kdamond_lock to print pid of kdamond Just get the pid by 'current->pid'. Meanwhile, to be symmetrical make the 'starts' and 'finishes' logs both use debug level. Link: https://lkml.kernel.org/r/20210927232432.17750-1-changbin.du@gmail.com Signed-off-by: Changbin Du Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/damon/core.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/mm/damon/core.c b/mm/damon/core.c index 61a9e3b37bc9..8171e7dddc30 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -652,9 +652,7 @@ static int kdamond_fn(void *data) unsigned int max_nr_accesses = 0; unsigned long sz_limit = 0; - mutex_lock(&ctx->kdamond_lock); - pr_debug("kdamond (%d) starts\n", ctx->kdamond->pid); - mutex_unlock(&ctx->kdamond_lock); + pr_debug("kdamond (%d) starts\n", current->pid); if (ctx->primitive.init) ctx->primitive.init(ctx); @@ -705,7 +703,7 @@ static int kdamond_fn(void *data) if (ctx->primitive.cleanup) ctx->primitive.cleanup(ctx); - pr_debug("kdamond (%d) finishes\n", ctx->kdamond->pid); + pr_debug("kdamond (%d) finishes\n", current->pid); mutex_lock(&ctx->kdamond_lock); ctx->kdamond = NULL; mutex_unlock(&ctx->kdamond_lock); From 7ec1992b891e59dba0f04e0327980786e8f61b13 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 5 Nov 2021 13:46:15 -0700 Subject: [PATCH 126/166] mm/damon/core: nullify pointer ctx->kdamond with a NULL Currently a plain integer is being used to nullify the pointer ctx->kdamond. Use NULL instead. Cleans up sparse warning: mm/damon/core.c:317:40: warning: Using plain integer as NULL pointer Link: https://lkml.kernel.org/r/20210925215908.181226-1-colin.king@canonical.com Signed-off-by: Colin Ian King Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/damon/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/damon/core.c b/mm/damon/core.c index 8171e7dddc30..d993db50280c 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -314,7 +314,7 @@ static int __damon_start(struct damon_ctx *ctx) nr_running_ctxs); if (IS_ERR(ctx->kdamond)) { err = PTR_ERR(ctx->kdamond); - ctx->kdamond = 0; + ctx->kdamond = NULL; } } mutex_unlock(&ctx->kdamond_lock); From fda504fade7f124858d7022341dc46ff35b45274 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:18 -0700 Subject: [PATCH 127/166] mm/damon/core: account age of target regions Patch series "Implement Data Access Monitoring-based Memory Operation Schemes". Introduction ============ DAMON[1] can be used as a primitive for data access aware memory management optimizations. For that, users who want such optimizations should run DAMON, read the monitoring results, analyze it, plan a new memory management scheme, and apply the new scheme by themselves. Such efforts will be inevitable for some complicated optimizations. However, in many other cases, the users would simply want the system to apply a memory management action to a memory region of a specific size having a specific access frequency for a specific time. For example, "page out a memory region larger than 100 MiB keeping only rare accesses more than 2 minutes", or "Do not use THP for a memory region larger than 2 MiB rarely accessed for more than 1 seconds". To make the works easier and non-redundant, this patchset implements a new feature of DAMON, which is called Data Access Monitoring-based Operation Schemes (DAMOS). Using the feature, users can describe the normal schemes in a simple way and ask DAMON to execute those on its own. [1] https://damonitor.github.io Evaluations =========== DAMOS is accurate and useful for memory management optimizations. An experimental DAMON-based operation scheme for THP, 'ethp', removes 76.15% of THP memory overheads while preserving 51.25% of THP speedup. Another experimental DAMON-based 'proactive reclamation' implementation, 'prcl', reduces 93.38% of residential sets and 23.63% of system memory footprint while incurring only 1.22% runtime overhead in the best case (parsec3/freqmine). NOTE that the experimental THP optimization and proactive reclamation are not for production but only for proof of concepts. Please refer to the showcase web site's evaluation document[1] for detailed evaluation setup and results. [1] https://damonitor.github.io/doc/html/v34/vm/damon/eval.html Long-term Support Trees ----------------------- For people who want to test DAMON but using LTS kernels, there are another couple of trees based on two latest LTS kernels respectively and containing the 'damon/master' backports. - For v5.4.y: https://git.kernel.org/sj/h/damon/for-v5.4.y - For v5.10.y: https://git.kernel.org/sj/h/damon/for-v5.10.y Sequence Of Patches =================== The 1st patch accounts age of each region. The 2nd patch implements the core of the DAMON-based operation schemes feature. The 3rd patch makes the default monitoring primitives for virtual address spaces to support the schemes. From this point, the kernel space users can use DAMOS. The 4th patch exports the feature to the user space via the debugfs interface. The 5th patch implements schemes statistics feature for easier tuning of the schemes and runtime access pattern analysis, and the 6th patch adds selftests for these changes. Finally, the 7th patch documents this new feature. This patch (of 7): DAMON can be used for data access pattern aware memory management optimizations. For that, users should run DAMON, read the monitoring results, analyze it, plan a new memory management scheme, and apply the new scheme by themselves. It would not be too hard, but still require some level of effort. For complicated cases, this effort is inevitable. That said, in many cases, users would simply want to apply an actions to a memory region of a specific size having a specific access frequency for a specific time. For example, "page out a memory region larger than 100 MiB but having a low access frequency more than 10 minutes", or "Use THP for a memory region larger than 2 MiB having a high access frequency for more than 2 seconds". For such optimizations, users will need to first account the age of each region themselves. To reduce such efforts, this implements a simple age account of each region in DAMON. For each aggregation step, DAMON compares the access frequency with that from last aggregation and reset the age of the region if the change is significant. Else, the age is incremented. Also, in case of the merge of regions, the region size-weighted average of the ages is set as the age of merged new region. Link: https://lkml.kernel.org/r/20211001125604.29660-1-sj@kernel.org Link: https://lkml.kernel.org/r/20211001125604.29660-2-sj@kernel.org Signed-off-by: SeongJae Park Cc: Jonathan Cameron Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Jonathan Corbet Cc: David Hildenbrand Cc: David Woodhouse Cc: Marco Elver Cc: Leonard Foerster Cc: Greg Thelen Cc: Markus Boehme Cc: David Rienjes Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 10 ++++++++++ mm/damon/core.c | 13 +++++++++++++ 2 files changed, 23 insertions(+) diff --git a/include/linux/damon.h b/include/linux/damon.h index 755d70804705..3e8215debbd4 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -31,12 +31,22 @@ struct damon_addr_range { * @sampling_addr: Address of the sample for the next access check. * @nr_accesses: Access frequency of this region. * @list: List head for siblings. + * @age: Age of this region. + * + * @age is initially zero, increased for each aggregation interval, and reset + * to zero again if the access frequency is significantly changed. If two + * regions are merged into a new region, both @nr_accesses and @age of the new + * region are set as region size-weighted average of those of the two regions. */ struct damon_region { struct damon_addr_range ar; unsigned long sampling_addr; unsigned int nr_accesses; struct list_head list; + + unsigned int age; +/* private: Internal value for age calculation. */ + unsigned int last_nr_accesses; }; /** diff --git a/mm/damon/core.c b/mm/damon/core.c index d993db50280c..3efbe80779db 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -45,6 +45,9 @@ struct damon_region *damon_new_region(unsigned long start, unsigned long end) region->nr_accesses = 0; INIT_LIST_HEAD(®ion->list); + region->age = 0; + region->last_nr_accesses = 0; + return region; } @@ -444,6 +447,7 @@ static void kdamond_reset_aggregated(struct damon_ctx *c) damon_for_each_region(r, t) { trace_damon_aggregated(t, r, damon_nr_regions(t)); + r->last_nr_accesses = r->nr_accesses; r->nr_accesses = 0; } } @@ -461,6 +465,7 @@ static void damon_merge_two_regions(struct damon_target *t, l->nr_accesses = (l->nr_accesses * sz_l + r->nr_accesses * sz_r) / (sz_l + sz_r); + l->age = (l->age * sz_l + r->age * sz_r) / (sz_l + sz_r); l->ar.end = r->ar.end; damon_destroy_region(r, t); } @@ -480,6 +485,11 @@ static void damon_merge_regions_of(struct damon_target *t, unsigned int thres, struct damon_region *r, *prev = NULL, *next; damon_for_each_region_safe(r, next, t) { + if (diff_of(r->nr_accesses, r->last_nr_accesses) > thres) + r->age = 0; + else + r->age++; + if (prev && prev->ar.end == r->ar.start && diff_of(prev->nr_accesses, r->nr_accesses) <= thres && sz_damon_region(prev) + sz_damon_region(r) <= sz_limit) @@ -527,6 +537,9 @@ static void damon_split_region_at(struct damon_ctx *ctx, r->ar.end = new->ar.start; + new->age = r->age; + new->last_nr_accesses = r->last_nr_accesses; + damon_insert_region(new, r, damon_next_region(r), t); } From 1f366e421c8f69583ed37b56d86e3747331869c3 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:22 -0700 Subject: [PATCH 128/166] mm/damon/core: implement DAMON-based Operation Schemes (DAMOS) In many cases, users might use DAMON for simple data access aware memory management optimizations such as applying an operation scheme to a memory region of a specific size having a specific access frequency for a specific time. For example, "page out a memory region larger than 100 MiB but having a low access frequency more than 10 minutes", or "Use THP for a memory region larger than 2 MiB having a high access frequency for more than 2 seconds". Most simple form of the solution would be doing offline data access pattern profiling using DAMON and modifying the application source code or system configuration based on the profiling results. Or, developing a daemon constructed with two modules (one for access monitoring and the other for applying memory management actions via mlock(), madvise(), sysctl, etc) is imaginable. To avoid users spending their time for implementation of such simple data access monitoring-based operation schemes, this makes DAMON to handle such schemes directly. With this change, users can simply specify their desired schemes to DAMON. Then, DAMON will automatically apply the schemes to the user-specified target processes. Each of the schemes is composed with conditions for filtering of the target memory regions and desired memory management action for the target. Specifically, the format is:: The filtering conditions are size of memory region, number of accesses to the region monitored by DAMON, and the age of the region. The age of region is incremented periodically but reset when its addresses or access frequency has significantly changed or the action of a scheme was applied. For the action, current implementation supports a few of madvise()-like hints, ``WILLNEED``, ``COLD``, ``PAGEOUT``, ``HUGEPAGE``, and ``NOHUGEPAGE``. Because DAMON supports various address spaces and application of the actions to a monitoring target region is dependent to the type of the target address space, the application code should be implemented by each primitives and registered to the framework. Note that this only implements the framework part. Following commit will implement the action applications for virtual address spaces primitives. Link: https://lkml.kernel.org/r/20211001125604.29660-3-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rienjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 66 +++++++++++++++++++++++++ mm/damon/core.c | 109 ++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 175 insertions(+) diff --git a/include/linux/damon.h b/include/linux/damon.h index 3e8215debbd4..dbe18b0fb795 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -69,6 +69,48 @@ struct damon_target { struct list_head list; }; +/** + * enum damos_action - Represents an action of a Data Access Monitoring-based + * Operation Scheme. + * + * @DAMOS_WILLNEED: Call ``madvise()`` for the region with MADV_WILLNEED. + * @DAMOS_COLD: Call ``madvise()`` for the region with MADV_COLD. + * @DAMOS_PAGEOUT: Call ``madvise()`` for the region with MADV_PAGEOUT. + * @DAMOS_HUGEPAGE: Call ``madvise()`` for the region with MADV_HUGEPAGE. + * @DAMOS_NOHUGEPAGE: Call ``madvise()`` for the region with MADV_NOHUGEPAGE. + */ +enum damos_action { + DAMOS_WILLNEED, + DAMOS_COLD, + DAMOS_PAGEOUT, + DAMOS_HUGEPAGE, + DAMOS_NOHUGEPAGE, +}; + +/** + * struct damos - Represents a Data Access Monitoring-based Operation Scheme. + * @min_sz_region: Minimum size of target regions. + * @max_sz_region: Maximum size of target regions. + * @min_nr_accesses: Minimum ``->nr_accesses`` of target regions. + * @max_nr_accesses: Maximum ``->nr_accesses`` of target regions. + * @min_age_region: Minimum age of target regions. + * @max_age_region: Maximum age of target regions. + * @action: &damo_action to be applied to the target regions. + * @list: List head for siblings. + * + * Note that both the minimums and the maximums are inclusive. + */ +struct damos { + unsigned long min_sz_region; + unsigned long max_sz_region; + unsigned int min_nr_accesses; + unsigned int max_nr_accesses; + unsigned int min_age_region; + unsigned int max_age_region; + enum damos_action action; + struct list_head list; +}; + struct damon_ctx; /** @@ -79,6 +121,7 @@ struct damon_ctx; * @prepare_access_checks: Prepare next access check of target regions. * @check_accesses: Check the accesses to target regions. * @reset_aggregated: Reset aggregated accesses monitoring results. + * @apply_scheme: Apply a DAMON-based operation scheme. * @target_valid: Determine if the target is valid. * @cleanup: Clean up the context. * @@ -104,6 +147,9 @@ struct damon_ctx; * of its update. The value will be used for regions adjustment threshold. * @reset_aggregated should reset the access monitoring results that aggregated * by @check_accesses. + * @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. * @target_valid should check whether the target is still valid for the * monitoring. * @cleanup is called from @kdamond just before its termination. @@ -114,6 +160,8 @@ struct damon_primitive { void (*prepare_access_checks)(struct damon_ctx *context); unsigned int (*check_accesses)(struct damon_ctx *context); void (*reset_aggregated)(struct damon_ctx *context); + int (*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); }; @@ -192,6 +240,7 @@ struct damon_callback { * @min_nr_regions: The minimum number of adaptive monitoring regions. * @max_nr_regions: The maximum number of adaptive monitoring regions. * @adaptive_targets: Head of monitoring targets (&damon_target) list. + * @schemes: Head of schemes (&damos) list. */ struct damon_ctx { unsigned long sample_interval; @@ -213,6 +262,7 @@ struct damon_ctx { unsigned long min_nr_regions; unsigned long max_nr_regions; struct list_head adaptive_targets; + struct list_head schemes; }; #define damon_next_region(r) \ @@ -233,6 +283,12 @@ struct damon_ctx { #define damon_for_each_target_safe(t, next, ctx) \ list_for_each_entry_safe(t, next, &(ctx)->adaptive_targets, list) +#define damon_for_each_scheme(s, ctx) \ + list_for_each_entry(s, &(ctx)->schemes, list) + +#define damon_for_each_scheme_safe(s, next, ctx) \ + list_for_each_entry_safe(s, next, &(ctx)->schemes, list) + #ifdef CONFIG_DAMON struct damon_region *damon_new_region(unsigned long start, unsigned long end); @@ -242,6 +298,14 @@ inline void damon_insert_region(struct damon_region *r, void damon_add_region(struct damon_region *r, struct damon_target *t); void damon_destroy_region(struct damon_region *r, struct damon_target *t); +struct damos *damon_new_scheme( + unsigned long min_sz_region, unsigned long max_sz_region, + unsigned int min_nr_accesses, unsigned int max_nr_accesses, + unsigned int min_age_region, unsigned int max_age_region, + enum damos_action action); +void damon_add_scheme(struct damon_ctx *ctx, struct damos *s); +void damon_destroy_scheme(struct damos *s); + struct damon_target *damon_new_target(unsigned long id); void damon_add_target(struct damon_ctx *ctx, struct damon_target *t); void damon_free_target(struct damon_target *t); @@ -255,6 +319,8 @@ int damon_set_targets(struct damon_ctx *ctx, int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, unsigned long aggr_int, unsigned long primitive_upd_int, unsigned long min_nr_reg, unsigned long max_nr_reg); +int damon_set_schemes(struct damon_ctx *ctx, + struct damos **schemes, ssize_t nr_schemes); int damon_nr_running_ctxs(void); int damon_start(struct damon_ctx **ctxs, int nr_ctxs); diff --git a/mm/damon/core.c b/mm/damon/core.c index 3efbe80779db..0ed97b21cbb6 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -85,6 +85,50 @@ void damon_destroy_region(struct damon_region *r, struct damon_target *t) damon_free_region(r); } +struct damos *damon_new_scheme( + unsigned long min_sz_region, unsigned long max_sz_region, + unsigned int min_nr_accesses, unsigned int max_nr_accesses, + unsigned int min_age_region, unsigned int max_age_region, + enum damos_action action) +{ + struct damos *scheme; + + scheme = kmalloc(sizeof(*scheme), GFP_KERNEL); + if (!scheme) + return NULL; + scheme->min_sz_region = min_sz_region; + scheme->max_sz_region = max_sz_region; + scheme->min_nr_accesses = min_nr_accesses; + scheme->max_nr_accesses = max_nr_accesses; + scheme->min_age_region = min_age_region; + scheme->max_age_region = max_age_region; + scheme->action = action; + INIT_LIST_HEAD(&scheme->list); + + return scheme; +} + +void damon_add_scheme(struct damon_ctx *ctx, struct damos *s) +{ + list_add_tail(&s->list, &ctx->schemes); +} + +static void damon_del_scheme(struct damos *s) +{ + list_del(&s->list); +} + +static void damon_free_scheme(struct damos *s) +{ + kfree(s); +} + +void damon_destroy_scheme(struct damos *s) +{ + damon_del_scheme(s); + damon_free_scheme(s); +} + /* * Construct a damon_target struct * @@ -156,6 +200,7 @@ struct damon_ctx *damon_new_ctx(void) ctx->max_nr_regions = 1000; INIT_LIST_HEAD(&ctx->adaptive_targets); + INIT_LIST_HEAD(&ctx->schemes); return ctx; } @@ -175,7 +220,13 @@ static void damon_destroy_targets(struct damon_ctx *ctx) void damon_destroy_ctx(struct damon_ctx *ctx) { + struct damos *s, *next_s; + damon_destroy_targets(ctx); + + damon_for_each_scheme_safe(s, next_s, ctx) + damon_destroy_scheme(s); + kfree(ctx); } @@ -250,6 +301,30 @@ int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, return 0; } +/** + * damon_set_schemes() - Set data access monitoring based operation schemes. + * @ctx: monitoring context + * @schemes: array of the schemes + * @nr_schemes: number of entries in @schemes + * + * This function should not be called while the kdamond of the context is + * running. + * + * Return: 0 if success, or negative error code otherwise. + */ +int damon_set_schemes(struct damon_ctx *ctx, struct damos **schemes, + ssize_t nr_schemes) +{ + struct damos *s, *next; + ssize_t i; + + damon_for_each_scheme_safe(s, next, ctx) + damon_destroy_scheme(s); + for (i = 0; i < nr_schemes; i++) + damon_add_scheme(ctx, schemes[i]); + return 0; +} + /** * damon_nr_running_ctxs() - Return number of currently running contexts. */ @@ -453,6 +528,39 @@ static void kdamond_reset_aggregated(struct damon_ctx *c) } } +static void damon_do_apply_schemes(struct damon_ctx *c, + struct damon_target *t, + struct damon_region *r) +{ + struct damos *s; + unsigned long sz; + + damon_for_each_scheme(s, c) { + sz = r->ar.end - r->ar.start; + if (sz < s->min_sz_region || s->max_sz_region < sz) + continue; + if (r->nr_accesses < s->min_nr_accesses || + s->max_nr_accesses < r->nr_accesses) + continue; + if (r->age < s->min_age_region || s->max_age_region < r->age) + continue; + if (c->primitive.apply_scheme) + c->primitive.apply_scheme(c, t, r, s); + r->age = 0; + } +} + +static void kdamond_apply_schemes(struct damon_ctx *c) +{ + struct damon_target *t; + struct damon_region *r; + + damon_for_each_target(t, c) { + damon_for_each_region(r, t) + damon_do_apply_schemes(c, t, r); + } +} + #define sz_damon_region(r) (r->ar.end - r->ar.start) /* @@ -693,6 +801,7 @@ static int kdamond_fn(void *data) if (ctx->callback.after_aggregation && ctx->callback.after_aggregation(ctx)) set_kdamond_stop(ctx); + kdamond_apply_schemes(ctx); kdamond_reset_aggregated(ctx); kdamond_split_regions(ctx); if (ctx->primitive.reset_aggregated) From 6dea8add4d2875b80843e4a4c8acd334a4db8c8f Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:25 -0700 Subject: [PATCH 129/166] mm/damon/vaddr: support DAMON-based Operation Schemes This makes DAMON's default primitives for virtual address spaces to support DAMON-based Operation Schemes (DAMOS) by implementing actions application functions and registering it to the monitoring context. The implementation simply links 'madvise()' for related DAMOS actions. That is, 'madvise(MADV_WILLNEED)' is called for 'WILLNEED' DAMOS action and similar for other actions ('COLD', 'PAGEOUT', 'HUGEPAGE', 'NOHUGEPAGE'). So, the kernel space DAMON users can now use the DAMON-based optimizations with only small amount of code. Link: https://lkml.kernel.org/r/20211001125604.29660-4-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rienjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 2 ++ mm/damon/vaddr.c | 56 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 58 insertions(+) diff --git a/include/linux/damon.h b/include/linux/damon.h index dbe18b0fb795..be6b6e81e8ee 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -337,6 +337,8 @@ 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); void damon_va_set_primitives(struct damon_ctx *ctx); #endif /* CONFIG_DAMON_VADDR */ diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index 58c1fb2aafa9..3e1c74d36bab 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -7,6 +7,7 @@ #define pr_fmt(fmt) "damon-va: " fmt +#include #include #include #include @@ -658,6 +659,60 @@ bool damon_va_target_valid(void *target) return false; } +#ifndef CONFIG_ADVISE_SYSCALLS +static int damos_madvise(struct damon_target *target, struct damon_region *r, + int behavior) +{ + return -EINVAL; +} +#else +static int damos_madvise(struct damon_target *target, struct damon_region *r, + int behavior) +{ + struct mm_struct *mm; + int ret = -ENOMEM; + + mm = damon_get_mm(target); + if (!mm) + goto out; + + ret = do_madvise(mm, PAGE_ALIGN(r->ar.start), + PAGE_ALIGN(r->ar.end - r->ar.start), behavior); + mmput(mm); +out: + return ret; +} +#endif /* CONFIG_ADVISE_SYSCALLS */ + +int damon_va_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, + struct damon_region *r, struct damos *scheme) +{ + int madv_action; + + switch (scheme->action) { + case DAMOS_WILLNEED: + madv_action = MADV_WILLNEED; + break; + case DAMOS_COLD: + madv_action = MADV_COLD; + break; + case DAMOS_PAGEOUT: + madv_action = MADV_PAGEOUT; + break; + case DAMOS_HUGEPAGE: + madv_action = MADV_HUGEPAGE; + break; + case DAMOS_NOHUGEPAGE: + madv_action = MADV_NOHUGEPAGE; + break; + default: + pr_warn("Wrong action %d\n", scheme->action); + return -EINVAL; + } + + return damos_madvise(t, r, madv_action); +} + void damon_va_set_primitives(struct damon_ctx *ctx) { ctx->primitive.init = damon_va_init; @@ -667,6 +722,7 @@ void damon_va_set_primitives(struct damon_ctx *ctx) ctx->primitive.reset_aggregated = NULL; ctx->primitive.target_valid = damon_va_target_valid; ctx->primitive.cleanup = NULL; + ctx->primitive.apply_scheme = damon_va_apply_scheme; } #include "vaddr-test.h" From af122dd8f3c0099349bc98ff69f0d90efd8b149f Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:29 -0700 Subject: [PATCH 130/166] mm/damon/dbgfs: support DAMON-based Operation Schemes This makes 'damon-dbgfs' to support the data access monitoring oriented memory management schemes. Users can read and update the schemes using ``/damon/schemes`` file. The format is:: Link: https://lkml.kernel.org/r/20211001125604.29660-5-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rienjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/damon/dbgfs.c | 165 ++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 162 insertions(+), 3 deletions(-) diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index faee070977d8..78b7a04490c5 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -98,6 +98,159 @@ out: return ret; } +static ssize_t sprint_schemes(struct damon_ctx *c, char *buf, ssize_t len) +{ + struct damos *s; + int written = 0; + int rc; + + damon_for_each_scheme(s, c) { + rc = scnprintf(&buf[written], len - written, + "%lu %lu %u %u %u %u %d\n", + s->min_sz_region, s->max_sz_region, + s->min_nr_accesses, s->max_nr_accesses, + s->min_age_region, s->max_age_region, + s->action); + if (!rc) + return -ENOMEM; + + written += rc; + } + return written; +} + +static ssize_t dbgfs_schemes_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct damon_ctx *ctx = file->private_data; + char *kbuf; + ssize_t len; + + kbuf = kmalloc(count, GFP_KERNEL); + if (!kbuf) + return -ENOMEM; + + mutex_lock(&ctx->kdamond_lock); + len = sprint_schemes(ctx, kbuf, count); + mutex_unlock(&ctx->kdamond_lock); + if (len < 0) + goto out; + len = simple_read_from_buffer(buf, count, ppos, kbuf, len); + +out: + kfree(kbuf); + return len; +} + +static void free_schemes_arr(struct damos **schemes, ssize_t nr_schemes) +{ + ssize_t i; + + for (i = 0; i < nr_schemes; i++) + kfree(schemes[i]); + kfree(schemes); +} + +static bool damos_action_valid(int action) +{ + switch (action) { + case DAMOS_WILLNEED: + case DAMOS_COLD: + case DAMOS_PAGEOUT: + case DAMOS_HUGEPAGE: + case DAMOS_NOHUGEPAGE: + return true; + default: + return false; + } +} + +/* + * Converts a string into an array of struct damos pointers + * + * Returns an array of struct damos pointers that converted if the conversion + * success, or NULL otherwise. + */ +static struct damos **str_to_schemes(const char *str, ssize_t len, + ssize_t *nr_schemes) +{ + struct damos *scheme, **schemes; + const int max_nr_schemes = 256; + int pos = 0, parsed, ret; + unsigned long min_sz, max_sz; + unsigned int min_nr_a, max_nr_a, min_age, max_age; + unsigned int action; + + schemes = kmalloc_array(max_nr_schemes, sizeof(scheme), + GFP_KERNEL); + if (!schemes) + return NULL; + + *nr_schemes = 0; + while (pos < len && *nr_schemes < max_nr_schemes) { + ret = sscanf(&str[pos], "%lu %lu %u %u %u %u %u%n", + &min_sz, &max_sz, &min_nr_a, &max_nr_a, + &min_age, &max_age, &action, &parsed); + if (ret != 7) + break; + if (!damos_action_valid(action)) { + pr_err("wrong action %d\n", action); + goto fail; + } + + pos += parsed; + scheme = damon_new_scheme(min_sz, max_sz, min_nr_a, max_nr_a, + min_age, max_age, action); + if (!scheme) + goto fail; + + schemes[*nr_schemes] = scheme; + *nr_schemes += 1; + } + return schemes; +fail: + free_schemes_arr(schemes, *nr_schemes); + return NULL; +} + +static ssize_t dbgfs_schemes_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct damon_ctx *ctx = file->private_data; + char *kbuf; + struct damos **schemes; + ssize_t nr_schemes = 0, ret = count; + int err; + + kbuf = user_input_str(buf, count, ppos); + if (IS_ERR(kbuf)) + return PTR_ERR(kbuf); + + schemes = str_to_schemes(kbuf, ret, &nr_schemes); + if (!schemes) { + ret = -EINVAL; + goto out; + } + + mutex_lock(&ctx->kdamond_lock); + if (ctx->kdamond) { + ret = -EBUSY; + goto unlock_out; + } + + err = damon_set_schemes(ctx, schemes, nr_schemes); + if (err) + ret = err; + else + nr_schemes = 0; +unlock_out: + mutex_unlock(&ctx->kdamond_lock); + free_schemes_arr(schemes, nr_schemes); +out: + kfree(kbuf); + return ret; +} + static inline bool targetid_is_pid(const struct damon_ctx *ctx) { return ctx->primitive.target_valid == damon_va_target_valid; @@ -279,6 +432,12 @@ static const struct file_operations attrs_fops = { .write = dbgfs_attrs_write, }; +static const struct file_operations schemes_fops = { + .open = damon_dbgfs_open, + .read = dbgfs_schemes_read, + .write = dbgfs_schemes_write, +}; + static const struct file_operations target_ids_fops = { .open = damon_dbgfs_open, .read = dbgfs_target_ids_read, @@ -292,10 +451,10 @@ static const struct file_operations kdamond_pid_fops = { static void dbgfs_fill_ctx_dir(struct dentry *dir, struct damon_ctx *ctx) { - const char * const file_names[] = {"attrs", "target_ids", + const char * const file_names[] = {"attrs", "schemes", "target_ids", "kdamond_pid"}; - const struct file_operations *fops[] = {&attrs_fops, &target_ids_fops, - &kdamond_pid_fops}; + const struct file_operations *fops[] = {&attrs_fops, &schemes_fops, + &target_ids_fops, &kdamond_pid_fops}; int i; for (i = 0; i < ARRAY_SIZE(file_names); i++) From 2f0b548c9f03a78f4ce6ab48986e3108028936a6 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:32 -0700 Subject: [PATCH 131/166] mm/damon/schemes: implement statistics feature To tune the DAMON-based operation schemes, knowing how many and how large regions are affected by each of the schemes will be helful. Those stats could be used for not only the tuning, but also monitoring of the working set size and the number of regions, if the scheme does not change the program behavior too much. For the reason, this implements the statistics for the schemes. The total number and size of the regions that each scheme is applied are exported to users via '->stat_count' and '->stat_sz' of 'struct damos'. Admins can also check the number by reading 'schemes' debugfs file. The last two integers now represents the stats. To allow collecting the stats without changing the program behavior, this also adds new scheme action, 'DAMOS_STAT'. Note that 'DAMOS_STAT' is not only making no memory operation actions, but also does not reset the age of regions. Link: https://lkml.kernel.org/r/20211001125604.29660-6-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rienjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 10 +++++++++- mm/damon/core.c | 7 ++++++- mm/damon/dbgfs.c | 5 +++-- mm/damon/vaddr.c | 2 ++ 4 files changed, 20 insertions(+), 4 deletions(-) diff --git a/include/linux/damon.h b/include/linux/damon.h index be6b6e81e8ee..f301bb53381c 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -78,6 +78,7 @@ struct damon_target { * @DAMOS_PAGEOUT: Call ``madvise()`` for the region with MADV_PAGEOUT. * @DAMOS_HUGEPAGE: Call ``madvise()`` for the region with MADV_HUGEPAGE. * @DAMOS_NOHUGEPAGE: Call ``madvise()`` for the region with MADV_NOHUGEPAGE. + * @DAMOS_STAT: Do nothing but count the stat. */ enum damos_action { DAMOS_WILLNEED, @@ -85,6 +86,7 @@ enum damos_action { DAMOS_PAGEOUT, DAMOS_HUGEPAGE, DAMOS_NOHUGEPAGE, + DAMOS_STAT, /* Do nothing but only record the stat */ }; /** @@ -96,9 +98,13 @@ enum damos_action { * @min_age_region: Minimum age of target regions. * @max_age_region: Maximum age of target regions. * @action: &damo_action to be applied to the target regions. + * @stat_count: Total number of regions that this scheme is applied. + * @stat_sz: Total size of regions that this scheme is applied. * @list: List head for siblings. * - * Note that both the minimums and the maximums are inclusive. + * For each aggregation interval, DAMON applies @action to monitoring target + * regions fit in the condition and updates the statistics. Note that both + * the minimums and the maximums are inclusive. */ struct damos { unsigned long min_sz_region; @@ -108,6 +114,8 @@ struct damos { unsigned int min_age_region; unsigned int max_age_region; enum damos_action action; + unsigned long stat_count; + unsigned long stat_sz; struct list_head list; }; diff --git a/mm/damon/core.c b/mm/damon/core.c index 0ed97b21cbb6..2f6785737902 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -103,6 +103,8 @@ 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; INIT_LIST_HEAD(&scheme->list); return scheme; @@ -544,9 +546,12 @@ static void damon_do_apply_schemes(struct damon_ctx *c, continue; if (r->age < s->min_age_region || s->max_age_region < r->age) continue; + s->stat_count++; + s->stat_sz += sz; if (c->primitive.apply_scheme) c->primitive.apply_scheme(c, t, r, s); - r->age = 0; + if (s->action != DAMOS_STAT) + r->age = 0; } } diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index 78b7a04490c5..28d6abf27763 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -106,11 +106,11 @@ static ssize_t sprint_schemes(struct damon_ctx *c, char *buf, ssize_t len) damon_for_each_scheme(s, c) { rc = scnprintf(&buf[written], len - written, - "%lu %lu %u %u %u %u %d\n", + "%lu %lu %u %u %u %u %d %lu %lu\n", s->min_sz_region, s->max_sz_region, s->min_nr_accesses, s->max_nr_accesses, s->min_age_region, s->max_age_region, - s->action); + s->action, s->stat_count, s->stat_sz); if (!rc) return -ENOMEM; @@ -159,6 +159,7 @@ static bool damos_action_valid(int action) case DAMOS_PAGEOUT: case DAMOS_HUGEPAGE: case DAMOS_NOHUGEPAGE: + case DAMOS_STAT: return true; default: return false; diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index 3e1c74d36bab..953c145b4f08 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -705,6 +705,8 @@ int damon_va_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, case DAMOS_NOHUGEPAGE: madv_action = MADV_NOHUGEPAGE; break; + case DAMOS_STAT: + return 0; default: pr_warn("Wrong action %d\n", scheme->action); return -EINVAL; From 8d5d4c6359054f3e680e1a2caca50e9b6d688b7d Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:36 -0700 Subject: [PATCH 132/166] selftests/damon: add 'schemes' debugfs tests This adds simple selftets for 'schemes' debugfs file of DAMON. Link: https://lkml.kernel.org/r/20211001125604.29660-7-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rienjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/testing/selftests/damon/debugfs_attrs.sh | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/tools/testing/selftests/damon/debugfs_attrs.sh b/tools/testing/selftests/damon/debugfs_attrs.sh index bfabb19dc0d3..639cfb6a1f65 100644 --- a/tools/testing/selftests/damon/debugfs_attrs.sh +++ b/tools/testing/selftests/damon/debugfs_attrs.sh @@ -57,6 +57,19 @@ test_write_fail "$file" "1 2 3 5 4" "$orig_content" \ test_content "$file" "$orig_content" "1 2 3 4 5" "successfully written" echo "$orig_content" > "$file" +# Test schemes file +# ================= + +file="$DBGFS/schemes" +orig_content=$(cat "$file") + +test_write_succ "$file" "1 2 3 4 5 6 4" \ + "$orig_content" "valid input" +test_write_fail "$file" "1 2 +3 4 5 6 3" "$orig_content" "multi lines" +test_write_succ "$file" "" "$orig_content" "disabling" +echo "$orig_content" > "$file" + # Test target_ids file # ==================== From 68536f8e01e571f553f78fa058ba543de3834452 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:39 -0700 Subject: [PATCH 133/166] Docs/admin-guide/mm/damon: document DAMON-based Operation Schemes This adds the description of DAMON-based operation schemes in the DAMON documents. Link: https://lkml.kernel.org/r/20211001125604.29660-8-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rienjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/mm/damon/start.rst | 11 +++++ Documentation/admin-guide/mm/damon/usage.rst | 51 +++++++++++++++++++- 2 files changed, 60 insertions(+), 2 deletions(-) diff --git a/Documentation/admin-guide/mm/damon/start.rst b/Documentation/admin-guide/mm/damon/start.rst index d5eb89a8fc38..51503cf90ca2 100644 --- a/Documentation/admin-guide/mm/damon/start.rst +++ b/Documentation/admin-guide/mm/damon/start.rst @@ -108,6 +108,17 @@ the results as separate image files. :: You can view the visualizations of this example workload at [1]_. Visualizations of other realistic workloads are available at [2]_ [3]_ [4]_. + +Data Access Pattern Aware Memory Management +=========================================== + +Below three commands make every memory region of size >=4K that doesn't +accessed for >=60 seconds in your workload to be swapped out. :: + + $ echo "#min-size max-size min-acc max-acc min-age max-age action" > scheme + $ echo "4K max 0 0 60s max pageout" >> scheme + $ damo schemes -c my_thp_scheme + .. [1] https://damonitor.github.io/doc/html/v17/admin-guide/mm/damon/start.html#visualizing-recorded-patterns .. [2] https://damonitor.github.io/test/result/visual/latest/rec.heatmap.1.png.html .. [3] https://damonitor.github.io/test/result/visual/latest/rec.wss_sz.png.html diff --git a/Documentation/admin-guide/mm/damon/usage.rst b/Documentation/admin-guide/mm/damon/usage.rst index a72cda374aba..c0296c14babf 100644 --- a/Documentation/admin-guide/mm/damon/usage.rst +++ b/Documentation/admin-guide/mm/damon/usage.rst @@ -34,8 +34,8 @@ the reason, this document describes only the debugfs interface debugfs Interface ================= -DAMON exports three files, ``attrs``, ``target_ids``, and ``monitor_on`` under -its debugfs directory, ``/damon/``. +DAMON exports four files, ``attrs``, ``target_ids``, ``schemes`` and +``monitor_on`` under its debugfs directory, ``/damon/``. Attributes @@ -74,6 +74,53 @@ check it again:: Note that setting the target ids doesn't start the monitoring. +Schemes +------- + +For usual DAMON-based data access aware memory management optimizations, users +would simply want the system to apply a memory management action to a memory +region of a specific size having a specific access frequency for a specific +time. DAMON receives such formalized operation schemes from the user and +applies those to the target processes. It also counts the total number and +size of regions that each scheme is applied. This statistics can be used for +online analysis or tuning of the schemes. + +Users can get and set the schemes by reading from and writing to ``schemes`` +debugfs file. Reading the file also shows the statistics of each scheme. To +the file, each of the schemes should be represented in each line in below form: + + min-size max-size min-acc max-acc min-age max-age action + +Note that the ranges are closed interval. Bytes for the size of regions +(``min-size`` and ``max-size``), number of monitored accesses per aggregate +interval for access frequency (``min-acc`` and ``max-acc``), number of +aggregate intervals for the age of regions (``min-age`` and ``max-age``), and a +predefined integer for memory management actions should be used. The supported +numbers and their meanings are as below. + + - 0: Call ``madvise()`` for the region with ``MADV_WILLNEED`` + - 1: Call ``madvise()`` for the region with ``MADV_COLD`` + - 2: Call ``madvise()`` for the region with ``MADV_PAGEOUT`` + - 3: Call ``madvise()`` for the region with ``MADV_HUGEPAGE`` + - 4: Call ``madvise()`` for the region with ``MADV_NOHUGEPAGE`` + - 5: Do nothing but count the statistics + +You can disable schemes by simply writing an empty string to the file. For +example, below commands applies a scheme saying "If a memory region of size in +[4KiB, 8KiB] is showing accesses per aggregate interval in [0, 5] for aggregate +interval in [10, 20], page out the region", check the entered scheme again, and +finally remove the scheme. :: + + # cd /damon + # echo "4096 8192 0 5 10 20 2" > schemes + # cat schemes + 4096 8192 0 5 10 20 2 0 0 + # echo > schemes + +The last two integers in the 4th line of above example is the total number and +the total size of the regions that the scheme is applied. + + Turning On/Off -------------- From 90bebce9fcd6488ba6b010af3a16a0a0d7e44cb6 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:42 -0700 Subject: [PATCH 134/166] mm/damon/dbgfs: allow users to set initial monitoring target regions Patch series "DAMON: Support Physical Memory Address Space Monitoring:. DAMON currently supports only virtual address spaces monitoring. It can be easily extended for various use cases and address spaces by configuring its monitoring primitives layer to use appropriate primitives implementations, though. This patchset implements monitoring primitives for the physical address space monitoring using the structure. The first 3 patches allow the user space users manually set the monitoring regions. The 1st patch implements the feature in the 'damon-dbgfs'. Then, patches for adding a unit tests (the 2nd patch) and updating the documentation (the 3rd patch) follow. Following 4 patches implement the physical address space monitoring primitives. The 4th patch makes some primitive functions for the virtual address spaces primitives reusable. The 5th patch implements the physical address space monitoring primitives. The 6th patch links the primitives to the 'damon-dbgfs'. Finally, 7th patch documents this new features. This patch (of 7): Some 'damon-dbgfs' users would want to monitor only a part of the entire virtual memory address space. The program interface users in the kernel space could use '->before_start()' callback or set the regions inside the context struct as they want, but 'damon-dbgfs' users cannot. For that reason, this introduces a new debugfs file called 'init_region'. 'damon-dbgfs' users can specify which initial monitoring target address regions they want by writing special input to the file. The input should describe each region in each line in the below form: Note that the regions will be updated to cover entire memory mapped regions after a 'regions update interval' is passed. If you want the regions to not be updated after the initial setting, you could set the interval as a very long time, say, a few decades. Link: https://lkml.kernel.org/r/20211012205711.29216-1-sj@kernel.org Link: https://lkml.kernel.org/r/20211012205711.29216-2-sj@kernel.org Signed-off-by: SeongJae Park Cc: Jonathan Cameron Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Jonathan Corbet Cc: David Hildenbrand Cc: David Woodhouse Cc: Marco Elver Cc: Leonard Foerster Cc: Greg Thelen Cc: Markus Boehme Cc: David Rienjes Cc: Shakeel Butt Cc: Shuah Khan Cc: Brendan Higgins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/damon/dbgfs.c | 156 ++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 154 insertions(+), 2 deletions(-) diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index 28d6abf27763..1cce53cd241d 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -394,6 +394,152 @@ out: return ret; } +static ssize_t sprint_init_regions(struct damon_ctx *c, char *buf, ssize_t len) +{ + struct damon_target *t; + struct damon_region *r; + int written = 0; + int rc; + + damon_for_each_target(t, c) { + damon_for_each_region(r, t) { + rc = scnprintf(&buf[written], len - written, + "%lu %lu %lu\n", + t->id, r->ar.start, r->ar.end); + if (!rc) + return -ENOMEM; + written += rc; + } + } + return written; +} + +static ssize_t dbgfs_init_regions_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct damon_ctx *ctx = file->private_data; + char *kbuf; + ssize_t len; + + kbuf = kmalloc(count, GFP_KERNEL); + if (!kbuf) + return -ENOMEM; + + mutex_lock(&ctx->kdamond_lock); + if (ctx->kdamond) { + mutex_unlock(&ctx->kdamond_lock); + len = -EBUSY; + goto out; + } + + len = sprint_init_regions(ctx, kbuf, count); + mutex_unlock(&ctx->kdamond_lock); + if (len < 0) + goto out; + len = simple_read_from_buffer(buf, count, ppos, kbuf, len); + +out: + kfree(kbuf); + return len; +} + +static int add_init_region(struct damon_ctx *c, + unsigned long target_id, struct damon_addr_range *ar) +{ + struct damon_target *t; + struct damon_region *r, *prev; + unsigned long id; + int rc = -EINVAL; + + if (ar->start >= ar->end) + return -EINVAL; + + damon_for_each_target(t, c) { + id = t->id; + if (targetid_is_pid(c)) + id = (unsigned long)pid_vnr((struct pid *)id); + if (id == target_id) { + r = damon_new_region(ar->start, ar->end); + if (!r) + return -ENOMEM; + damon_add_region(r, t); + if (damon_nr_regions(t) > 1) { + prev = damon_prev_region(r); + if (prev->ar.end > r->ar.start) { + damon_destroy_region(r, t); + return -EINVAL; + } + } + rc = 0; + } + } + return rc; +} + +static int set_init_regions(struct damon_ctx *c, const char *str, ssize_t len) +{ + struct damon_target *t; + struct damon_region *r, *next; + int pos = 0, parsed, ret; + unsigned long target_id; + struct damon_addr_range ar; + int err; + + damon_for_each_target(t, c) { + damon_for_each_region_safe(r, next, t) + damon_destroy_region(r, t); + } + + while (pos < len) { + ret = sscanf(&str[pos], "%lu %lu %lu%n", + &target_id, &ar.start, &ar.end, &parsed); + if (ret != 3) + break; + err = add_init_region(c, target_id, &ar); + if (err) + goto fail; + pos += parsed; + } + + return 0; + +fail: + damon_for_each_target(t, c) { + damon_for_each_region_safe(r, next, t) + damon_destroy_region(r, t); + } + return err; +} + +static ssize_t dbgfs_init_regions_write(struct file *file, + const char __user *buf, size_t count, + loff_t *ppos) +{ + struct damon_ctx *ctx = file->private_data; + char *kbuf; + ssize_t ret = count; + int err; + + kbuf = user_input_str(buf, count, ppos); + if (IS_ERR(kbuf)) + return PTR_ERR(kbuf); + + mutex_lock(&ctx->kdamond_lock); + if (ctx->kdamond) { + ret = -EBUSY; + goto unlock_out; + } + + err = set_init_regions(ctx, kbuf, ret); + if (err) + ret = err; + +unlock_out: + mutex_unlock(&ctx->kdamond_lock); + kfree(kbuf); + return ret; +} + static ssize_t dbgfs_kdamond_pid_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { @@ -445,6 +591,12 @@ static const struct file_operations target_ids_fops = { .write = dbgfs_target_ids_write, }; +static const struct file_operations init_regions_fops = { + .open = damon_dbgfs_open, + .read = dbgfs_init_regions_read, + .write = dbgfs_init_regions_write, +}; + static const struct file_operations kdamond_pid_fops = { .open = damon_dbgfs_open, .read = dbgfs_kdamond_pid_read, @@ -453,9 +605,9 @@ static const struct file_operations kdamond_pid_fops = { static void dbgfs_fill_ctx_dir(struct dentry *dir, struct damon_ctx *ctx) { const char * const file_names[] = {"attrs", "schemes", "target_ids", - "kdamond_pid"}; + "init_regions", "kdamond_pid"}; const struct file_operations *fops[] = {&attrs_fops, &schemes_fops, - &target_ids_fops, &kdamond_pid_fops}; + &target_ids_fops, &init_regions_fops, &kdamond_pid_fops}; int i; for (i = 0; i < ARRAY_SIZE(file_names); i++) From 1c2e11bfa649cc07e6322b0e5ea3cdbada9c43c3 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:46 -0700 Subject: [PATCH 135/166] mm/damon/dbgfs-test: add a unit test case for 'init_regions' This adds another test case for the new feature, 'init_regions'. Link: https://lkml.kernel.org/r/20211012205711.29216-3-sj@kernel.org Signed-off-by: SeongJae Park Reviewed-by: Brendan Higgins Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rienjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/damon/dbgfs-test.h | 54 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) diff --git a/mm/damon/dbgfs-test.h b/mm/damon/dbgfs-test.h index 4eddcfa73996..104b22957616 100644 --- a/mm/damon/dbgfs-test.h +++ b/mm/damon/dbgfs-test.h @@ -109,9 +109,63 @@ static void damon_dbgfs_test_set_targets(struct kunit *test) dbgfs_destroy_ctx(ctx); } +static void damon_dbgfs_test_set_init_regions(struct kunit *test) +{ + struct damon_ctx *ctx = damon_new_ctx(); + unsigned long ids[] = {1, 2, 3}; + /* Each line represents one region in `` `` */ + char * const valid_inputs[] = {"2 10 20\n 2 20 30\n2 35 45", + "2 10 20\n", + "2 10 20\n1 39 59\n1 70 134\n 2 20 25\n", + ""}; + /* Reading the file again will show sorted, clean output */ + char * const valid_expects[] = {"2 10 20\n2 20 30\n2 35 45\n", + "2 10 20\n", + "1 39 59\n1 70 134\n2 10 20\n2 20 25\n", + ""}; + char * const invalid_inputs[] = {"4 10 20\n", /* target not exists */ + "2 10 20\n 2 14 26\n", /* regions overlap */ + "1 10 20\n2 30 40\n 1 5 8"}; /* not sorted by address */ + char *input, *expect; + int i, rc; + char buf[256]; + + damon_set_targets(ctx, ids, 3); + + /* Put valid inputs and check the results */ + for (i = 0; i < ARRAY_SIZE(valid_inputs); i++) { + input = valid_inputs[i]; + expect = valid_expects[i]; + + rc = set_init_regions(ctx, input, strnlen(input, 256)); + KUNIT_EXPECT_EQ(test, rc, 0); + + memset(buf, 0, 256); + sprint_init_regions(ctx, buf, 256); + + KUNIT_EXPECT_STREQ(test, (char *)buf, expect); + } + /* Put invlid inputs and check the return error code */ + for (i = 0; i < ARRAY_SIZE(invalid_inputs); i++) { + input = invalid_inputs[i]; + pr_info("input: %s\n", input); + rc = set_init_regions(ctx, input, strnlen(input, 256)); + KUNIT_EXPECT_EQ(test, rc, -EINVAL); + + memset(buf, 0, 256); + sprint_init_regions(ctx, buf, 256); + + KUNIT_EXPECT_STREQ(test, (char *)buf, ""); + } + + damon_set_targets(ctx, NULL, 0); + damon_destroy_ctx(ctx); +} + static struct kunit_case damon_test_cases[] = { KUNIT_CASE(damon_dbgfs_test_str_to_target_ids), KUNIT_CASE(damon_dbgfs_test_set_targets), + KUNIT_CASE(damon_dbgfs_test_set_init_regions), {}, }; From c2fe4987ed31c32591c9aea5a1e8e2540ce66e12 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:49 -0700 Subject: [PATCH 136/166] Docs/admin-guide/mm/damon: document 'init_regions' feature This adds description of the 'init_regions' feature in the DAMON usage document. Link: https://lkml.kernel.org/r/20211012205711.29216-4-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Brendan Higgins Cc: David Hildenbrand Cc: David Rienjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/mm/damon/usage.rst | 41 +++++++++++++++++++- 1 file changed, 39 insertions(+), 2 deletions(-) diff --git a/Documentation/admin-guide/mm/damon/usage.rst b/Documentation/admin-guide/mm/damon/usage.rst index c0296c14babf..f7d5cfbb50c2 100644 --- a/Documentation/admin-guide/mm/damon/usage.rst +++ b/Documentation/admin-guide/mm/damon/usage.rst @@ -34,8 +34,9 @@ the reason, this document describes only the debugfs interface debugfs Interface ================= -DAMON exports four files, ``attrs``, ``target_ids``, ``schemes`` and -``monitor_on`` under its debugfs directory, ``/damon/``. +DAMON exports five files, ``attrs``, ``target_ids``, ``init_regions``, +``schemes`` and ``monitor_on`` under its debugfs directory, +``/damon/``. Attributes @@ -74,6 +75,42 @@ check it again:: Note that setting the target ids doesn't start the monitoring. +Initial Monitoring Target Regions +--------------------------------- + +In case of the debugfs based monitoring, DAMON automatically sets and updates +the monitoring target regions so that entire memory mappings of target +processes can be covered. However, users can want to limit the monitoring +region to specific address ranges, such as the heap, the stack, or specific +file-mapped area. Or, some users can know the initial access pattern of their +workloads and therefore want to set optimal initial regions for the 'adaptive +regions adjustment'. + +In such cases, users can explicitly set the initial monitoring target regions +as they want, by writing proper values to the ``init_regions`` file. Each line +of the input should represent one region in below form.:: + + + +The ``target id`` should already in ``target_ids`` file, and the regions should +be passed in address order. For example, below commands will set a couple of +address ranges, ``1-100`` and ``100-200`` as the initial monitoring target +region of process 42, and another couple of address ranges, ``20-40`` and +``50-100`` as that of process 4242.:: + + # cd /damon + # echo "42 1 100 + 42 100 200 + 4242 20 40 + 4242 50 100" > init_regions + +Note that this sets the initial monitoring target regions only. In case of +virtual memory monitoring, DAMON will automatically updates the boundary of the +regions after one ``regions update interval``. Therefore, users should set the +``regions update interval`` large enough in this case, if they don't want the +update. + + Schemes ------- From 46c3a0accdc48c86928157fd073e66807f338485 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:53 -0700 Subject: [PATCH 137/166] mm/damon/vaddr: separate commonly usable functions This moves functions in the default virtual address spaces monitoring primitives that commonly usable from other address spaces like physical address space into a header file. Those will be reused by the physical address space monitoring primitives which will be implemented by the following commit. [sj@kernel.org: include 'highmem.h' to fix a build failure] Link: https://lkml.kernel.org/r/20211014110848.5204-1-sj@kernel.org Link: https://lkml.kernel.org/r/20211012205711.29216-5-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Brendan Higgins Cc: David Hildenbrand Cc: David Rienjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/damon/Makefile | 2 +- mm/damon/prmtv-common.c | 87 +++++++++++++++++++++++++++++++++++++++ mm/damon/prmtv-common.h | 17 ++++++++ mm/damon/vaddr.c | 90 ++--------------------------------------- 4 files changed, 109 insertions(+), 87 deletions(-) create mode 100644 mm/damon/prmtv-common.c create mode 100644 mm/damon/prmtv-common.h diff --git a/mm/damon/Makefile b/mm/damon/Makefile index fed4be3bace3..99b1bfe01ff5 100644 --- a/mm/damon/Makefile +++ b/mm/damon/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_DAMON) := core.o -obj-$(CONFIG_DAMON_VADDR) += vaddr.o +obj-$(CONFIG_DAMON_VADDR) += prmtv-common.o vaddr.o obj-$(CONFIG_DAMON_DBGFS) += dbgfs.o diff --git a/mm/damon/prmtv-common.c b/mm/damon/prmtv-common.c new file mode 100644 index 000000000000..7e62ee54fb54 --- /dev/null +++ b/mm/damon/prmtv-common.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Common Primitives for Data Access Monitoring + * + * Author: SeongJae Park + */ + +#include +#include +#include +#include + +#include "prmtv-common.h" + +/* + * Get an online page for a pfn if it's in the LRU list. Otherwise, returns + * NULL. + * + * The body of this function is stolen from the 'page_idle_get_page()'. We + * steal rather than reuse it because the code is quite simple. + */ +struct page *damon_get_page(unsigned long pfn) +{ + struct page *page = pfn_to_online_page(pfn); + + if (!page || !PageLRU(page) || !get_page_unless_zero(page)) + return NULL; + + if (unlikely(!PageLRU(page))) { + put_page(page); + page = NULL; + } + return page; +} + +void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr) +{ + bool referenced = false; + struct page *page = damon_get_page(pte_pfn(*pte)); + + if (!page) + return; + + if (pte_young(*pte)) { + referenced = true; + *pte = pte_mkold(*pte); + } + +#ifdef CONFIG_MMU_NOTIFIER + if (mmu_notifier_clear_young(mm, addr, addr + PAGE_SIZE)) + referenced = true; +#endif /* CONFIG_MMU_NOTIFIER */ + + if (referenced) + set_page_young(page); + + set_page_idle(page); + put_page(page); +} + +void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, unsigned long addr) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + bool referenced = false; + struct page *page = damon_get_page(pmd_pfn(*pmd)); + + if (!page) + return; + + if (pmd_young(*pmd)) { + referenced = true; + *pmd = pmd_mkold(*pmd); + } + +#ifdef CONFIG_MMU_NOTIFIER + if (mmu_notifier_clear_young(mm, addr, + addr + ((1UL) << HPAGE_PMD_SHIFT))) + referenced = true; +#endif /* CONFIG_MMU_NOTIFIER */ + + if (referenced) + set_page_young(page); + + set_page_idle(page); + put_page(page); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +} diff --git a/mm/damon/prmtv-common.h b/mm/damon/prmtv-common.h new file mode 100644 index 000000000000..7093d19e5d42 --- /dev/null +++ b/mm/damon/prmtv-common.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Common Primitives for Data Access Monitoring + * + * Author: SeongJae Park + */ + +#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); + +void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr); +void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, unsigned long addr); diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index 953c145b4f08..f0aef35602da 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -8,25 +8,19 @@ #define pr_fmt(fmt) "damon-va: " fmt #include -#include -#include -#include -#include #include +#include +#include #include #include -#include -#include -#include + +#include "prmtv-common.h" #ifdef CONFIG_DAMON_VADDR_KUNIT_TEST #undef DAMON_MIN_REGION #define DAMON_MIN_REGION 1 #endif -/* Get a random number in [l, r) */ -#define damon_rand(l, r) (l + prandom_u32_max(r - l)) - /* * 't->id' should be the pointer to the relevant 'struct pid' having reference * count. Caller must put the returned task, unless it is NULL. @@ -373,82 +367,6 @@ void damon_va_update(struct damon_ctx *ctx) } } -/* - * Get an online page for a pfn if it's in the LRU list. Otherwise, returns - * NULL. - * - * The body of this function is stolen from the 'page_idle_get_page()'. We - * steal rather than reuse it because the code is quite simple. - */ -static struct page *damon_get_page(unsigned long pfn) -{ - struct page *page = pfn_to_online_page(pfn); - - if (!page || !PageLRU(page) || !get_page_unless_zero(page)) - return NULL; - - if (unlikely(!PageLRU(page))) { - put_page(page); - page = NULL; - } - return page; -} - -static void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, - unsigned long addr) -{ - bool referenced = false; - struct page *page = damon_get_page(pte_pfn(*pte)); - - if (!page) - return; - - if (pte_young(*pte)) { - referenced = true; - *pte = pte_mkold(*pte); - } - -#ifdef CONFIG_MMU_NOTIFIER - if (mmu_notifier_clear_young(mm, addr, addr + PAGE_SIZE)) - referenced = true; -#endif /* CONFIG_MMU_NOTIFIER */ - - if (referenced) - set_page_young(page); - - set_page_idle(page); - put_page(page); -} - -static void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, - unsigned long addr) -{ -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - bool referenced = false; - struct page *page = damon_get_page(pmd_pfn(*pmd)); - - if (!page) - return; - - if (pmd_young(*pmd)) { - referenced = true; - *pmd = pmd_mkold(*pmd); - } - -#ifdef CONFIG_MMU_NOTIFIER - if (mmu_notifier_clear_young(mm, addr, - addr + ((1UL) << HPAGE_PMD_SHIFT))) - referenced = true; -#endif /* CONFIG_MMU_NOTIFIER */ - - if (referenced) - set_page_young(page); - - set_page_idle(page); - put_page(page); -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ -} - static int damon_mkold_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long next, struct mm_walk *walk) { From a28397beb55b68bd0f15c6778540e8ae1bc26d21 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:56 -0700 Subject: [PATCH 138/166] mm/damon: implement primitives for physical address space monitoring This implements the monitoring primitives for the physical memory address space. Internally, it uses the PTE Accessed bit, similar to that of the virtual address spaces monitoring primitives. It supports only user memory pages, as idle pages tracking does. If the monitoring target physical memory address range contains non-user memory pages, access check of the pages will do nothing but simply treat the pages as not accessed. Link: https://lkml.kernel.org/r/20211012205711.29216-6-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Brendan Higgins Cc: David Hildenbrand Cc: David Rienjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 10 ++ mm/damon/Kconfig | 8 ++ mm/damon/Makefile | 1 + mm/damon/paddr.c | 224 ++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 243 insertions(+) create mode 100644 mm/damon/paddr.c diff --git a/include/linux/damon.h b/include/linux/damon.h index f301bb53381c..715dadd21f7c 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -351,4 +351,14 @@ 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); +void damon_pa_set_primitives(struct damon_ctx *ctx); + +#endif /* CONFIG_DAMON_PADDR */ + #endif /* _DAMON_H */ diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig index ba8898c7eb8e..2a5923be631e 100644 --- a/mm/damon/Kconfig +++ b/mm/damon/Kconfig @@ -32,6 +32,14 @@ config DAMON_VADDR This builds the default data access monitoring primitives for DAMON that work for virtual address spaces. +config DAMON_PADDR + bool "Data access monitoring primitives for the physical address space" + depends on DAMON && MMU + select PAGE_IDLE_FLAG + help + This builds the default data access monitoring primitives for DAMON + that works for the physical address space. + config DAMON_VADDR_KUNIT_TEST bool "Test for DAMON primitives" if !KUNIT_ALL_TESTS depends on DAMON_VADDR && KUNIT=y diff --git a/mm/damon/Makefile b/mm/damon/Makefile index 99b1bfe01ff5..8d9b0df79702 100644 --- a/mm/damon/Makefile +++ b/mm/damon/Makefile @@ -2,4 +2,5 @@ obj-$(CONFIG_DAMON) := core.o obj-$(CONFIG_DAMON_VADDR) += prmtv-common.o vaddr.o +obj-$(CONFIG_DAMON_PADDR) += prmtv-common.o paddr.o obj-$(CONFIG_DAMON_DBGFS) += dbgfs.o diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c new file mode 100644 index 000000000000..d7a2ecd09ed0 --- /dev/null +++ b/mm/damon/paddr.c @@ -0,0 +1,224 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DAMON Primitives for The Physical Address Space + * + * Author: SeongJae Park + */ + +#define pr_fmt(fmt) "damon-pa: " fmt + +#include +#include +#include +#include + +#include "prmtv-common.h" + +static bool __damon_pa_mkold(struct page *page, struct vm_area_struct *vma, + unsigned long addr, void *arg) +{ + struct page_vma_mapped_walk pvmw = { + .page = page, + .vma = vma, + .address = addr, + }; + + while (page_vma_mapped_walk(&pvmw)) { + addr = pvmw.address; + if (pvmw.pte) + damon_ptep_mkold(pvmw.pte, vma->vm_mm, addr); + else + damon_pmdp_mkold(pvmw.pmd, vma->vm_mm, addr); + } + return true; +} + +static void damon_pa_mkold(unsigned long paddr) +{ + struct page *page = damon_get_page(PHYS_PFN(paddr)); + struct rmap_walk_control rwc = { + .rmap_one = __damon_pa_mkold, + .anon_lock = page_lock_anon_vma_read, + }; + bool need_lock; + + if (!page) + return; + + if (!page_mapped(page) || !page_rmapping(page)) { + set_page_idle(page); + goto out; + } + + need_lock = !PageAnon(page) || PageKsm(page); + if (need_lock && !trylock_page(page)) + goto out; + + rmap_walk(page, &rwc); + + if (need_lock) + unlock_page(page); + +out: + put_page(page); +} + +static void __damon_pa_prepare_access_check(struct damon_ctx *ctx, + struct damon_region *r) +{ + r->sampling_addr = damon_rand(r->ar.start, r->ar.end); + + damon_pa_mkold(r->sampling_addr); +} + +void damon_pa_prepare_access_checks(struct damon_ctx *ctx) +{ + struct damon_target *t; + struct damon_region *r; + + damon_for_each_target(t, ctx) { + damon_for_each_region(r, t) + __damon_pa_prepare_access_check(ctx, r); + } +} + +struct damon_pa_access_chk_result { + unsigned long page_sz; + bool accessed; +}; + +static bool __damon_pa_young(struct page *page, struct vm_area_struct *vma, + unsigned long addr, void *arg) +{ + struct damon_pa_access_chk_result *result = arg; + struct page_vma_mapped_walk pvmw = { + .page = page, + .vma = vma, + .address = addr, + }; + + result->accessed = false; + result->page_sz = PAGE_SIZE; + while (page_vma_mapped_walk(&pvmw)) { + addr = pvmw.address; + if (pvmw.pte) { + result->accessed = pte_young(*pvmw.pte) || + !page_is_idle(page) || + mmu_notifier_test_young(vma->vm_mm, addr); + } else { +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + result->accessed = pmd_young(*pvmw.pmd) || + !page_is_idle(page) || + mmu_notifier_test_young(vma->vm_mm, addr); + result->page_sz = ((1UL) << HPAGE_PMD_SHIFT); +#else + WARN_ON_ONCE(1); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + } + if (result->accessed) { + page_vma_mapped_walk_done(&pvmw); + break; + } + } + + /* If accessed, stop walking */ + return !result->accessed; +} + +static bool damon_pa_young(unsigned long paddr, unsigned long *page_sz) +{ + struct page *page = damon_get_page(PHYS_PFN(paddr)); + struct damon_pa_access_chk_result result = { + .page_sz = PAGE_SIZE, + .accessed = false, + }; + struct rmap_walk_control rwc = { + .arg = &result, + .rmap_one = __damon_pa_young, + .anon_lock = page_lock_anon_vma_read, + }; + bool need_lock; + + if (!page) + return false; + + if (!page_mapped(page) || !page_rmapping(page)) { + if (page_is_idle(page)) + result.accessed = false; + else + result.accessed = true; + put_page(page); + goto out; + } + + need_lock = !PageAnon(page) || PageKsm(page); + if (need_lock && !trylock_page(page)) { + put_page(page); + return NULL; + } + + rmap_walk(page, &rwc); + + if (need_lock) + unlock_page(page); + put_page(page); + +out: + *page_sz = result.page_sz; + return result.accessed; +} + +static void __damon_pa_check_access(struct damon_ctx *ctx, + struct damon_region *r) +{ + static unsigned long last_addr; + static unsigned long last_page_sz = PAGE_SIZE; + static bool last_accessed; + + /* If the region is in the last checked page, reuse the result */ + if (ALIGN_DOWN(last_addr, last_page_sz) == + ALIGN_DOWN(r->sampling_addr, last_page_sz)) { + if (last_accessed) + r->nr_accesses++; + return; + } + + last_accessed = damon_pa_young(r->sampling_addr, &last_page_sz); + if (last_accessed) + r->nr_accesses++; + + last_addr = r->sampling_addr; +} + +unsigned int damon_pa_check_accesses(struct damon_ctx *ctx) +{ + struct damon_target *t; + struct damon_region *r; + unsigned int max_nr_accesses = 0; + + damon_for_each_target(t, ctx) { + damon_for_each_region(r, t) { + __damon_pa_check_access(ctx, r); + max_nr_accesses = max(r->nr_accesses, max_nr_accesses); + } + } + + return max_nr_accesses; +} + +bool damon_pa_target_valid(void *t) +{ + return true; +} + +void damon_pa_set_primitives(struct damon_ctx *ctx) +{ + ctx->primitive.init = NULL; + ctx->primitive.update = NULL; + ctx->primitive.prepare_access_checks = damon_pa_prepare_access_checks; + ctx->primitive.check_accesses = damon_pa_check_accesses; + ctx->primitive.reset_aggregated = NULL; + ctx->primitive.target_valid = damon_pa_target_valid; + ctx->primitive.cleanup = NULL; + ctx->primitive.apply_scheme = NULL; +} From c026291ab88f02247999959d01182cb8eb6e6a5b Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:00 -0700 Subject: [PATCH 139/166] mm/damon/dbgfs: support physical memory monitoring This makes the 'damon-dbgfs' to support the physical memory monitoring, in addition to the virtual memory monitoring. Users can do the physical memory monitoring by writing a special keyword, 'paddr' to the 'target_ids' debugfs file. Then, DAMON will check the special keyword and configure the monitoring context to run with the primitives for the physical address space. Unlike the virtual memory monitoring, the monitoring target region will not be automatically set. Therefore, users should also set the monitoring target address region using the 'init_regions' debugfs file. Also, note that the physical memory monitoring will not automatically terminated. The user should explicitly turn off the monitoring by writing 'off' to the 'monitor_on' debugfs file. Link: https://lkml.kernel.org/r/20211012205711.29216-7-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Brendan Higgins Cc: David Hildenbrand Cc: David Rienjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/damon/Kconfig | 2 +- mm/damon/dbgfs.c | 21 ++++++++++++++++++--- 2 files changed, 19 insertions(+), 4 deletions(-) diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig index 2a5923be631e..ca33b289ebbe 100644 --- a/mm/damon/Kconfig +++ b/mm/damon/Kconfig @@ -54,7 +54,7 @@ config DAMON_VADDR_KUNIT_TEST config DAMON_DBGFS bool "DAMON debugfs interface" - depends on DAMON_VADDR && DEBUG_FS + depends on DAMON_VADDR && DAMON_PADDR && DEBUG_FS help This builds the debugfs interface for DAMON. The user space admins can use the interface for arbitrary data access monitoring. diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index 1cce53cd241d..38188347d8ab 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -339,6 +339,7 @@ static ssize_t dbgfs_target_ids_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct damon_ctx *ctx = file->private_data; + bool id_is_pid = true; char *kbuf, *nrs; unsigned long *targets; ssize_t nr_targets; @@ -351,6 +352,11 @@ static ssize_t dbgfs_target_ids_write(struct file *file, return PTR_ERR(kbuf); nrs = kbuf; + if (!strncmp(kbuf, "paddr\n", count)) { + id_is_pid = false; + /* target id is meaningless here, but we set it just for fun */ + scnprintf(kbuf, count, "42 "); + } targets = str_to_target_ids(nrs, ret, &nr_targets); if (!targets) { @@ -358,7 +364,7 @@ static ssize_t dbgfs_target_ids_write(struct file *file, goto out; } - if (targetid_is_pid(ctx)) { + if (id_is_pid) { for (i = 0; i < nr_targets; i++) { targets[i] = (unsigned long)find_get_pid( (int)targets[i]); @@ -372,15 +378,24 @@ static ssize_t dbgfs_target_ids_write(struct file *file, mutex_lock(&ctx->kdamond_lock); if (ctx->kdamond) { - if (targetid_is_pid(ctx)) + if (id_is_pid) dbgfs_put_pids(targets, nr_targets); ret = -EBUSY; goto unlock_out; } + /* remove targets with previously-set primitive */ + damon_set_targets(ctx, NULL, 0); + + /* Configure the context for the address space type */ + if (id_is_pid) + damon_va_set_primitives(ctx); + else + damon_pa_set_primitives(ctx); + err = damon_set_targets(ctx, targets, nr_targets); if (err) { - if (targetid_is_pid(ctx)) + if (id_is_pid) dbgfs_put_pids(targets, nr_targets); ret = err; } From c638072107f52ec35f292c97b6f3df9b9f2ed87d Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:03 -0700 Subject: [PATCH 140/166] Docs/DAMON: document physical memory monitoring support This updates the DAMON documents for the physical memory address space monitoring support. Link: https://lkml.kernel.org/r/20211012205711.29216-8-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Brendan Higgins Cc: David Hildenbrand Cc: David Rienjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/mm/damon/usage.rst | 25 +++++++++++++---- Documentation/vm/damon/design.rst | 29 ++++++++++++-------- Documentation/vm/damon/faq.rst | 5 ++-- 3 files changed, 40 insertions(+), 19 deletions(-) diff --git a/Documentation/admin-guide/mm/damon/usage.rst b/Documentation/admin-guide/mm/damon/usage.rst index f7d5cfbb50c2..ed96bbf0daff 100644 --- a/Documentation/admin-guide/mm/damon/usage.rst +++ b/Documentation/admin-guide/mm/damon/usage.rst @@ -10,15 +10,16 @@ DAMON provides below three interfaces for different users. This is for privileged people such as system administrators who want a just-working human-friendly interface. Using this, users can use the DAMON’s major features in a human-friendly way. It may not be highly tuned for - special cases, though. It supports only virtual address spaces monitoring. + special cases, though. It supports both virtual and physical address spaces + monitoring. - *debugfs interface.* This is for privileged user space programmers who want more optimized use of DAMON. Using this, users can use DAMON’s major features by reading from and writing to special debugfs files. Therefore, you can write and use your personalized DAMON debugfs wrapper programs that reads/writes the debugfs files instead of you. The DAMON user space tool is also a reference - implementation of such programs. It supports only virtual address spaces - monitoring. + implementation of such programs. It supports both virtual and physical + address spaces monitoring. - *Kernel Space Programming Interface.* This is for kernel space programmers. Using this, users can utilize every feature of DAMON most flexibly and efficiently by writing kernel space @@ -72,20 +73,34 @@ check it again:: # cat target_ids 42 4242 +Users can also monitor the physical memory address space of the system by +writing a special keyword, "``paddr\n``" to the file. Because physical address +space monitoring doesn't support multiple targets, reading the file will show a +fake value, ``42``, as below:: + + # cd /damon + # echo paddr > target_ids + # cat target_ids + 42 + Note that setting the target ids doesn't start the monitoring. Initial Monitoring Target Regions --------------------------------- -In case of the debugfs based monitoring, DAMON automatically sets and updates -the monitoring target regions so that entire memory mappings of target +In case of the virtual address space monitoring, DAMON automatically sets and +updates the monitoring target regions so that entire memory mappings of target processes can be covered. However, users can want to limit the monitoring region to specific address ranges, such as the heap, the stack, or specific file-mapped area. Or, some users can know the initial access pattern of their workloads and therefore want to set optimal initial regions for the 'adaptive regions adjustment'. +In contrast, DAMON do not automatically sets and updates the monitoring target +regions in case of physical memory monitoring. Therefore, users should set the +monitoring target regions by themselves. + In such cases, users can explicitly set the initial monitoring target regions as they want, by writing proper values to the ``init_regions`` file. Each line of the input should represent one region in below form.:: diff --git a/Documentation/vm/damon/design.rst b/Documentation/vm/damon/design.rst index b05159c295f4..210f0f50efd8 100644 --- a/Documentation/vm/damon/design.rst +++ b/Documentation/vm/damon/design.rst @@ -35,13 +35,17 @@ two parts: 1. Identification of the monitoring target address range for the address space. 2. Access check of specific address range in the target space. -DAMON currently provides the implementation of the primitives for only the -virtual address spaces. Below two subsections describe how it works. +DAMON currently provides the implementations of the primitives for the physical +and virtual address spaces. Below two subsections describe how those work. VMA-based Target Address Range Construction ------------------------------------------- +This is only for the virtual address space primitives implementation. That for +the physical address space simply asks users to manually set the monitoring +target address ranges. + Only small parts in the super-huge virtual address space of the processes are mapped to the physical memory and accessed. Thus, tracking the unmapped address regions is just wasteful. However, because DAMON can deal with some @@ -71,15 +75,18 @@ to make a reasonable trade-off. Below shows this in detail:: PTE Accessed-bit Based Access Check ----------------------------------- -The implementation for the virtual address space uses PTE Accessed-bit for -basic access checks. It finds the relevant PTE Accessed bit from the address -by walking the page table for the target task of the address. In this way, the -implementation finds and clears the bit for next sampling target address and -checks whether the bit set again after one sampling period. This could disturb -other kernel subsystems using the Accessed bits, namely Idle page tracking and -the reclaim logic. To avoid such disturbances, DAMON makes it mutually -exclusive with Idle page tracking and uses ``PG_idle`` and ``PG_young`` page -flags to solve the conflict with the reclaim logic, as Idle page tracking does. +Both of the implementations for physical and virtual address spaces use PTE +Accessed-bit for basic access checks. Only one difference is the way of +finding the relevant PTE Accessed bit(s) from the address. While the +implementation for the virtual address walks the page table for the target task +of the address, the implementation for the physical address walks every page +table having a mapping to the address. In this way, the implementations find +and clear the bit(s) for next sampling target address and checks whether the +bit(s) set again after one sampling period. This could disturb other kernel +subsystems using the Accessed bits, namely Idle page tracking and the reclaim +logic. To avoid such disturbances, DAMON makes it mutually exclusive with Idle +page tracking and uses ``PG_idle`` and ``PG_young`` page flags to solve the +conflict with the reclaim logic, as Idle page tracking does. Address Space Independent Core Mechanisms diff --git a/Documentation/vm/damon/faq.rst b/Documentation/vm/damon/faq.rst index cb3d8b585a8b..11aea40eb328 100644 --- a/Documentation/vm/damon/faq.rst +++ b/Documentation/vm/damon/faq.rst @@ -36,10 +36,9 @@ constructions and actual access checks can be implemented and configured on the DAMON core by the users. In this way, DAMON users can monitor any address space with any access check technique. -Nonetheless, DAMON provides vma tracking and PTE Accessed bit check based +Nonetheless, DAMON provides vma/rmap tracking and PTE Accessed bit check based implementations of the address space dependent functions for the virtual memory -by default, for a reference and convenient use. In near future, we will -provide those for physical memory address space. +and the physical memory by default, for a reference and convenient use. Can I simply monitor page granularity? From 199b50f4c9485c46c2403d8b3e0eca90ec401ed6 Mon Sep 17 00:00:00 2001 From: Rikard Falkeborn Date: Fri, 5 Nov 2021 13:47:07 -0700 Subject: [PATCH 141/166] mm/damon/vaddr: constify static mm_walk_ops The only usage of these structs is to pass their addresses to walk_page_range(), which takes a pointer to const mm_walk_ops as argument. Make them const to allow the compiler to put them in read-only memory. Link: https://lkml.kernel.org/r/20211014075042.17174-2-rikard.falkeborn@gmail.com Signed-off-by: Rikard Falkeborn Reviewed-by: SeongJae Park Reviewed-by: Anshuman Khandual Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/damon/vaddr.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index f0aef35602da..758501b8d97d 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -394,7 +394,7 @@ out: return 0; } -static struct mm_walk_ops damon_mkold_ops = { +static const struct mm_walk_ops damon_mkold_ops = { .pmd_entry = damon_mkold_pmd_entry, }; @@ -490,7 +490,7 @@ out: return 0; } -static struct mm_walk_ops damon_young_ops = { +static const struct mm_walk_ops damon_young_ops = { .pmd_entry = damon_young_pmd_entry, }; From 9210622ab81f7e722da7563166d93b2a028a79d4 Mon Sep 17 00:00:00 2001 From: Rongwei Wang Date: Fri, 5 Nov 2021 13:47:09 -0700 Subject: [PATCH 142/166] mm/damon/dbgfs: remove unnecessary variables In some functions, it's unnecessary to declare 'err' and 'ret' variables at the same time. This patch mainly to simplify the issue of such declarations by reusing one variable. Link: https://lkml.kernel.org/r/20211014073014.35754-1-sj@kernel.org Signed-off-by: Rongwei Wang Signed-off-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/damon/dbgfs.c | 66 +++++++++++++++++++++++------------------------- 1 file changed, 31 insertions(+), 35 deletions(-) diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index 38188347d8ab..c90988a20fa4 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -69,8 +69,7 @@ static ssize_t dbgfs_attrs_write(struct file *file, struct damon_ctx *ctx = file->private_data; unsigned long s, a, r, minr, maxr; char *kbuf; - ssize_t ret = count; - int err; + ssize_t ret; kbuf = user_input_str(buf, count, ppos); if (IS_ERR(kbuf)) @@ -88,9 +87,9 @@ static ssize_t dbgfs_attrs_write(struct file *file, goto unlock_out; } - err = damon_set_attrs(ctx, s, a, r, minr, maxr); - if (err) - ret = err; + ret = damon_set_attrs(ctx, s, a, r, minr, maxr); + if (!ret) + ret = count; unlock_out: mutex_unlock(&ctx->kdamond_lock); out: @@ -220,14 +219,13 @@ static ssize_t dbgfs_schemes_write(struct file *file, const char __user *buf, struct damon_ctx *ctx = file->private_data; char *kbuf; struct damos **schemes; - ssize_t nr_schemes = 0, ret = count; - int err; + ssize_t nr_schemes = 0, ret; kbuf = user_input_str(buf, count, ppos); if (IS_ERR(kbuf)) return PTR_ERR(kbuf); - schemes = str_to_schemes(kbuf, ret, &nr_schemes); + schemes = str_to_schemes(kbuf, count, &nr_schemes); if (!schemes) { ret = -EINVAL; goto out; @@ -239,11 +237,12 @@ static ssize_t dbgfs_schemes_write(struct file *file, const char __user *buf, goto unlock_out; } - err = damon_set_schemes(ctx, schemes, nr_schemes); - if (err) - ret = err; - else + ret = damon_set_schemes(ctx, schemes, nr_schemes); + if (!ret) { + ret = count; nr_schemes = 0; + } + unlock_out: mutex_unlock(&ctx->kdamond_lock); free_schemes_arr(schemes, nr_schemes); @@ -343,9 +342,8 @@ static ssize_t dbgfs_target_ids_write(struct file *file, char *kbuf, *nrs; unsigned long *targets; ssize_t nr_targets; - ssize_t ret = count; + ssize_t ret; int i; - int err; kbuf = user_input_str(buf, count, ppos); if (IS_ERR(kbuf)) @@ -358,7 +356,7 @@ static ssize_t dbgfs_target_ids_write(struct file *file, scnprintf(kbuf, count, "42 "); } - targets = str_to_target_ids(nrs, ret, &nr_targets); + targets = str_to_target_ids(nrs, count, &nr_targets); if (!targets) { ret = -ENOMEM; goto out; @@ -393,11 +391,12 @@ static ssize_t dbgfs_target_ids_write(struct file *file, else damon_pa_set_primitives(ctx); - err = damon_set_targets(ctx, targets, nr_targets); - if (err) { + ret = damon_set_targets(ctx, targets, nr_targets); + if (ret) { if (id_is_pid) dbgfs_put_pids(targets, nr_targets); - ret = err; + } else { + ret = count; } unlock_out: @@ -715,8 +714,7 @@ static ssize_t dbgfs_mk_context_write(struct file *file, { char *kbuf; char *ctx_name; - ssize_t ret = count; - int err; + ssize_t ret; kbuf = user_input_str(buf, count, ppos); if (IS_ERR(kbuf)) @@ -734,9 +732,9 @@ static ssize_t dbgfs_mk_context_write(struct file *file, } mutex_lock(&damon_dbgfs_lock); - err = dbgfs_mk_context(ctx_name); - if (err) - ret = err; + ret = dbgfs_mk_context(ctx_name); + if (!ret) + ret = count; mutex_unlock(&damon_dbgfs_lock); out: @@ -805,8 +803,7 @@ static ssize_t dbgfs_rm_context_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { char *kbuf; - ssize_t ret = count; - int err; + ssize_t ret; char *ctx_name; kbuf = user_input_str(buf, count, ppos); @@ -825,9 +822,9 @@ static ssize_t dbgfs_rm_context_write(struct file *file, } mutex_lock(&damon_dbgfs_lock); - err = dbgfs_rm_context(ctx_name); - if (err) - ret = err; + ret = dbgfs_rm_context(ctx_name); + if (!ret) + ret = count; mutex_unlock(&damon_dbgfs_lock); out: @@ -851,9 +848,8 @@ static ssize_t dbgfs_monitor_on_read(struct file *file, static ssize_t dbgfs_monitor_on_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - ssize_t ret = count; + ssize_t ret; char *kbuf; - int err; kbuf = user_input_str(buf, count, ppos); if (IS_ERR(kbuf)) @@ -866,14 +862,14 @@ static ssize_t dbgfs_monitor_on_write(struct file *file, } if (!strncmp(kbuf, "on", count)) - err = damon_start(dbgfs_ctxs, dbgfs_nr_ctxs); + ret = damon_start(dbgfs_ctxs, dbgfs_nr_ctxs); else if (!strncmp(kbuf, "off", count)) - err = damon_stop(dbgfs_ctxs, dbgfs_nr_ctxs); + ret = damon_stop(dbgfs_ctxs, dbgfs_nr_ctxs); else - err = -EINVAL; + ret = -EINVAL; - if (err) - ret = err; + if (!ret) + ret = count; kfree(kbuf); return ret; } From 57223ac295845b1d72ec1bd02b5fab992b77a021 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:13 -0700 Subject: [PATCH 143/166] mm/damon/paddr: support the pageout scheme Introduction ============ This patchset 1) makes the engine for general data access pattern-oriented memory management (DAMOS) be more useful for production environments, and 2) implements a static kernel module for lightweight proactive reclamation using the engine. Proactive Reclamation --------------------- On general memory over-committed systems, proactively reclaiming cold pages helps saving memory and reducing latency spikes that incurred by the direct reclaim or the CPU consumption of kswapd, while incurring only minimal performance degradation[2]. A Free Pages Reporting[8] based memory over-commit virtualization system would be one more specific use case. In the system, the guest VMs reports their free memory to host, and the host reallocates the reported memory to other guests. As a result, the system's memory utilization can be maximized. However, the guests could be not so memory-frugal, because some kernel subsystems and user-space applications are designed to use as much memory as available. Then, guests would report only small amount of free memory to host, results in poor memory utilization. Running the proactive reclamation in such guests could help mitigating this problem. Google has also implemented this idea and using it in their data center. They further proposed upstreaming it in LSFMM'19, and "the general consensus was that, while this sort of proactive reclaim would be useful for a number of users, the cost of this particular solution was too high to consider merging it upstream"[3]. The cost mainly comes from the coldness tracking. Roughly speaking, the implementation periodically scans the 'Accessed' bit of each page. For the reason, the overhead linearly increases as the size of the memory and the scanning frequency grows. As a result, Google is known to dedicating one CPU for the work. That's a reasonable option to someone like Google, but it wouldn't be so to some others. DAMON and DAMOS: An engine for data access pattern-oriented memory management ----------------------------------------------------------------------------- DAMON[4] is a framework for general data access monitoring. Its adaptive monitoring overhead control feature minimizes its monitoring overhead. It also let the upper-bound of the overhead be configurable by clients, regardless of the size of the monitoring target memory. While monitoring 70 GiB memory of a production system every 5 milliseconds, it consumes less than 1% single CPU time. For this, it could sacrify some of the quality of the monitoring results. Nevertheless, the lower-bound of the quality is configurable, and it uses a best-effort algorithm for better quality. Our test results[5] show the quality is practical enough. From the production system monitoring, we were able to find a 4 KiB region in the 70 GiB memory that shows highest access frequency. We normally don't monitor the data access pattern just for fun but to improve something like memory management. Proactive reclamation is one such usage. For such general cases, DAMON provides a feature called DAMon-based Operation Schemes (DAMOS)[6]. It makes DAMON an engine for general data access pattern oriented memory management. Using this, clients can ask DAMON to find memory regions of specific data access pattern and apply some memory management action (e.g., page out, move to head of the LRU list, use huge page, ...). We call the request 'scheme'. Proactive Reclamation on top of DAMON/DAMOS ------------------------------------------- Therefore, by using DAMON for the cold pages detection, the proactive reclamation's monitoring overhead issue can be solved. Actually, we previously implemented a version of proactive reclamation using DAMOS and achieved noticeable improvements with our evaluation setup[5]. Nevertheless, it more for a proof-of-concept, rather than production uses. It supports only virtual address spaces of processes, and require additional tuning efforts for given workloads and the hardware. For the tuning, we introduced a simple auto-tuning user space tool[8]. Google is also known to using a ML-based similar approach for their fleets[2]. But, making it just works with intuitive knobs in the kernel would be helpful for general users. To this end, this patchset improves DAMOS to be ready for such production usages, and implements another version of the proactive reclamation, namely DAMON_RECLAIM, on top of it. DAMOS Improvements: Aggressiveness Control, Prioritization, and Watermarks -------------------------------------------------------------------------- First of all, the current version of DAMOS supports only virtual address spaces. This patchset makes it supports the physical address space for the page out action. Next major problem of the current version of DAMOS is the lack of the aggressiveness control, which can results in arbitrary overhead. For example, if huge memory regions having the data access pattern of interest are found, applying the requested action to all of the regions could incur significant overhead. It can be controlled by tuning the target data access pattern with manual or automated approaches[2,7]. But, some people would prefer the kernel to just work with only intuitive tuning or default values. For such cases, this patchset implements a safeguard, namely time/size quota. Using this, the clients can specify up to how much time can be used for applying the action, and/or up to how much memory regions the action can be applied within a user-specified time duration. A followup question is, to which memory regions should the action applied within the limits? We implement a simple regions prioritization mechanism for each action and make DAMOS to apply the action to high priority regions first. It also allows clients tune the prioritization mechanism to use different weights for size, access frequency, and age of memory regions. This means we could use not only LRU but also LFU or some fancy algorithms like CAR[9] with lightweight overhead. Though DAMON is lightweight, someone would want to remove even the cold pages monitoring overhead when it is unnecessary. Currently, it should manually turned on and off by clients, but some clients would simply want to turn it on and off based on some metrics like free memory ratio or memory fragmentation. For such cases, this patchset implements a watermarks-based automatic activation feature. It allows the clients configure the metric of their interest, and three watermarks of the metric. If the metric is higher than the high watermark or lower than the low watermark, the scheme is deactivated. If the metric is lower than the mid watermark but higher than the low watermark, the scheme is activated. DAMON-based Reclaim ------------------- Using the improved version of DAMOS, this patchset implements a static kernel module called 'damon_reclaim'. It finds memory regions that didn't accessed for specific time duration and page out. Consuming too much CPU for the paging out operations, or doing pageout too frequently can be critical for systems configuring their swap devices with software-defined in-memory block devices like zram/zswap or total number of writes limited devices like SSDs, respectively. To avoid the problems, the time/size quotas can be configured. Under the quotas, it pages out memory regions that didn't accessed longer first. Also, to remove the monitoring overhead under peaceful situation, and to fall back to the LRU-list based page granularity reclamation when it doesn't make progress, the three watermarks based activation mechanism is used, with the free memory ratio as the watermark metric. For convenient configurations, it provides several module parameters. Using these, sysadmins can enable/disable it, and tune its parameters including the coldness identification time threshold, the time/size quotas and the three watermarks. Evaluation ========== In short, DAMON_RECLAIM with 50ms/s time quota and regions prioritization on v5.15-rc5 Linux kernel with ZRAM swap device achieves 38.58% memory saving with only 1.94% runtime overhead. For this, DAMON_RECLAIM consumes only 4.97% of single CPU time. Setup ----- We evaluate DAMON_RECLAIM to show how each of the DAMOS improvements make effect. For this, we measure DAMON_RECLAIM's CPU consumption, entire system memory footprint, total number of major page faults, and runtime of 24 realistic workloads in PARSEC3 and SPLASH-2X benchmark suites on my QEMU/KVM based virtual machine. The virtual machine runs on an i3.metal AWS instance, has 130GiB memory, and runs a linux kernel built on latest -mm tree[1] plus this patchset. It also utilizes a 4 GiB ZRAM swap device. We repeats the measurement 5 times and use averages. [1] https://github.com/hnaz/linux-mm/tree/v5.15-rc5-mmots-2021-10-13-19-55 Detailed Results ---------------- The results are summarized in the below table. With coldness identification threshold of 5 seconds, DAMON_RECLAIM without the time quota-based speed limit achieves 47.21% memory saving, but incur 4.59% runtime slowdown to the workloads on average. For this, DAMON_RECLAIM consumes about 11.28% single CPU time. Applying time quotas of 200ms/s, 50ms/s, and 10ms/s without the regions prioritization reduces the slowdown to 4.89%, 2.65%, and 1.5%, respectively. Time quota of 200ms/s (20%) makes no real change compared to the quota unapplied version, because the quota unapplied version consumes only 11.28% CPU time. DAMON_RECLAIM's CPU utilization also similarly reduced: 11.24%, 5.51%, and 2.01% of single CPU time. That is, the overhead is proportional to the speed limit. Nevertheless, it also reduces the memory saving because it becomes less aggressive. In detail, the three variants show 48.76%, 37.83%, and 7.85% memory saving, respectively. Applying the regions prioritization (page out regions that not accessed longer first within the time quota) further reduces the performance degradation. Runtime slowdowns and total number of major page faults increase has been 4.89%/218,690% -> 4.39%/166,136% (200ms/s), 2.65%/111,886% -> 1.94%/59,053% (50ms/s), and 1.5%/34,973.40% -> 2.08%/8,781.75% (10ms/s). The runtime under 10ms/s time quota has increased with prioritization, but apparently that's under the margin of error. time quota prioritization memory_saving cpu_util slowdown pgmajfaults overhead N N 47.21% 11.28% 4.59% 194,802% 200ms/s N 48.76% 11.24% 4.89% 218,690% 50ms/s N 37.83% 5.51% 2.65% 111,886% 10ms/s N 7.85% 2.01% 1.5% 34,793.40% 200ms/s Y 50.08% 10.38% 4.39% 166,136% 50ms/s Y 38.58% 4.97% 1.94% 59,053% 10ms/s Y 3.63% 1.73% 2.08% 8,781.75% Baseline and Complete Git Trees =============================== The patches are based on the latest -mm tree (v5.15-rc5-mmots-2021-10-13-19-55). You can also clone the complete git tree from: $ git clone git://github.com/sjp38/linux -b damon_reclaim/patches/v1 The web is also available: https://git.kernel.org/pub/scm/linux/kernel/git/sj/linux.git/tag/?h=damon_reclaim/patches/v1 Sequence Of Patches =================== The first patch makes DAMOS support the physical address space for the page out action. Following five patches (patches 2-6) implement the time/size quotas. Next four patches (patches 7-10) implement the memory regions prioritization within the limit. Then, three following patches (patches 11-13) implement the watermarks-based schemes activation. Finally, the last two patches (patches 14-15) implement and document the DAMON-based reclamation using the advanced DAMOS. [1] https://www.kernel.org/doc/html/v5.15-rc1/vm/damon/index.html [2] https://research.google/pubs/pub48551/ [3] https://lwn.net/Articles/787611/ [4] https://damonitor.github.io [5] https://damonitor.github.io/doc/html/latest/vm/damon/eval.html [6] https://lore.kernel.org/linux-mm/20211001125604.29660-1-sj@kernel.org/ [7] https://github.com/awslabs/damoos [8] https://www.kernel.org/doc/html/latest/vm/free_page_reporting.html [9] https://www.usenix.org/conference/fast-04/car-clock-adaptive-replacement This patch (of 15): This makes the DAMON primitives for physical address space support the pageout action for DAMON-based Operation Schemes. With this commit, hence, users can easily implement system-level data access-aware reclamations using DAMOS. [sj@kernel.org: fix missing-prototype build warning] Link: https://lkml.kernel.org/r/20211025064220.13904-1-sj@kernel.org Link: https://lkml.kernel.org/r/20211019150731.16699-1-sj@kernel.org Link: https://lkml.kernel.org/r/20211019150731.16699-2-sj@kernel.org Signed-off-by: SeongJae Park Cc: Jonathan Cameron Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Jonathan Corbet Cc: David Hildenbrand Cc: David Woodhouse Cc: Marco Elver Cc: Leonard Foerster Cc: Greg Thelen Cc: Markus Boehme Cc: David Rientjes Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 2 ++ mm/damon/paddr.c | 37 ++++++++++++++++++++++++++++++++++++- 2 files changed, 38 insertions(+), 1 deletion(-) diff --git a/include/linux/damon.h b/include/linux/damon.h index 715dadd21f7c..9a327bc787b5 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -357,6 +357,8 @@ void damon_va_set_primitives(struct damon_ctx *ctx); 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); void damon_pa_set_primitives(struct damon_ctx *ctx); #endif /* CONFIG_DAMON_PADDR */ diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c index d7a2ecd09ed0..957ada55de77 100644 --- a/mm/damon/paddr.c +++ b/mm/damon/paddr.c @@ -11,7 +11,9 @@ #include #include #include +#include +#include "../internal.h" #include "prmtv-common.h" static bool __damon_pa_mkold(struct page *page, struct vm_area_struct *vma, @@ -211,6 +213,39 @@ bool damon_pa_target_valid(void *t) return true; } +int damon_pa_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, + struct damon_region *r, struct damos *scheme) +{ + unsigned long addr; + LIST_HEAD(page_list); + + if (scheme->action != DAMOS_PAGEOUT) + return -EINVAL; + + for (addr = r->ar.start; addr < r->ar.end; addr += PAGE_SIZE) { + struct page *page = damon_get_page(PHYS_PFN(addr)); + + if (!page) + continue; + + ClearPageReferenced(page); + test_and_clear_page_young(page); + if (isolate_lru_page(page)) { + put_page(page); + continue; + } + if (PageUnevictable(page)) { + putback_lru_page(page); + } else { + list_add(&page->lru, &page_list); + put_page(page); + } + } + reclaim_pages(&page_list); + cond_resched(); + return 0; +} + void damon_pa_set_primitives(struct damon_ctx *ctx) { ctx->primitive.init = NULL; @@ -220,5 +255,5 @@ void damon_pa_set_primitives(struct damon_ctx *ctx) ctx->primitive.reset_aggregated = NULL; ctx->primitive.target_valid = damon_pa_target_valid; ctx->primitive.cleanup = NULL; - ctx->primitive.apply_scheme = NULL; + ctx->primitive.apply_scheme = damon_pa_apply_scheme; } From 2b8a248d5873343aa16f6c5ede30517693995f13 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:16 -0700 Subject: [PATCH 144/166] mm/damon/schemes: implement size quota for schemes application speed control There could be arbitrarily large memory regions fulfilling the target data access pattern of a DAMON-based operation scheme. In the case, applying the action of the scheme could incur too high overhead. To provide an intuitive way for avoiding it, this implements a feature called size quota. If the quota is set, DAMON tries to apply the action only up to the given amount of memory regions within a given time window. Link: https://lkml.kernel.org/r/20211019150731.16699-3-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 36 +++++++++++++++++++++++--- mm/damon/core.c | 60 +++++++++++++++++++++++++++++++++++++------ mm/damon/dbgfs.c | 4 ++- 3 files changed, 87 insertions(+), 13 deletions(-) diff --git a/include/linux/damon.h b/include/linux/damon.h index 9a327bc787b5..3a1ce9d9921c 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -89,6 +89,26 @@ enum damos_action { DAMOS_STAT, /* Do nothing but only record the stat */ }; +/** + * struct damos_quota - Controls the aggressiveness of the given scheme. + * @sz: Maximum bytes of memory that the action can be applied. + * @reset_interval: Charge reset interval in milliseconds. + * + * To avoid consuming too much CPU time or IO resources for applying the + * &struct damos->action to large memory, DAMON allows users to set a size + * quota. The quota can be set by writing non-zero values to &sz. If the size + * quota is set, DAMON tries to apply the action only up to &sz bytes within + * &reset_interval. + */ +struct damos_quota { + unsigned long sz; + unsigned long reset_interval; + +/* private: For charging the quota */ + unsigned long charged_sz; + unsigned long charged_from; +}; + /** * struct damos - Represents a Data Access Monitoring-based Operation Scheme. * @min_sz_region: Minimum size of target regions. @@ -98,13 +118,20 @@ enum damos_action { * @min_age_region: Minimum age of target regions. * @max_age_region: Maximum age of target regions. * @action: &damo_action to be applied to the target regions. + * @quota: Control the aggressiveness 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. * @list: List head for siblings. * - * For each aggregation interval, DAMON applies @action to monitoring target - * regions fit in the condition and updates the statistics. Note that both - * the minimums and the maximums are inclusive. + * For each aggregation interval, DAMON finds regions which fit in the + * condition (&min_sz_region, &max_sz_region, &min_nr_accesses, + * &max_nr_accesses, &min_age_region, &max_age_region) and applies &action to + * those. To avoid consuming too much CPU time or IO resources for the + * &action, "a is used. + * + * After applying the &action to each region, &stat_count and &stat_sz is + * updated to reflect the number of regions and total size of regions that the + * &action is applied. */ struct damos { unsigned long min_sz_region; @@ -114,6 +141,7 @@ struct damos { unsigned int min_age_region; unsigned int max_age_region; enum damos_action action; + struct damos_quota quota; unsigned long stat_count; unsigned long stat_sz; struct list_head list; @@ -310,7 +338,7 @@ struct damos *damon_new_scheme( unsigned long min_sz_region, unsigned long max_sz_region, unsigned int min_nr_accesses, unsigned int max_nr_accesses, unsigned int min_age_region, unsigned int max_age_region, - enum damos_action action); + enum damos_action action, struct damos_quota *quota); void damon_add_scheme(struct damon_ctx *ctx, struct damos *s); void damon_destroy_scheme(struct damos *s); diff --git a/mm/damon/core.c b/mm/damon/core.c index 2f6785737902..cce14a0d5c72 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -89,7 +89,7 @@ struct damos *damon_new_scheme( unsigned long min_sz_region, unsigned long max_sz_region, unsigned int min_nr_accesses, unsigned int max_nr_accesses, unsigned int min_age_region, unsigned int max_age_region, - enum damos_action action) + enum damos_action action, struct damos_quota *quota) { struct damos *scheme; @@ -107,6 +107,11 @@ struct damos *damon_new_scheme( scheme->stat_sz = 0; INIT_LIST_HEAD(&scheme->list); + scheme->quota.sz = quota->sz; + scheme->quota.reset_interval = quota->reset_interval; + scheme->quota.charged_sz = 0; + scheme->quota.charged_from = 0; + return scheme; } @@ -530,15 +535,25 @@ static void kdamond_reset_aggregated(struct damon_ctx *c) } } +static void damon_split_region_at(struct damon_ctx *ctx, + struct damon_target *t, struct damon_region *r, + unsigned long sz_r); + static void damon_do_apply_schemes(struct damon_ctx *c, struct damon_target *t, struct damon_region *r) { struct damos *s; - unsigned long sz; damon_for_each_scheme(s, c) { - sz = r->ar.end - r->ar.start; + struct damos_quota *quota = &s->quota; + unsigned long sz = r->ar.end - r->ar.start; + + /* Check the quota */ + if (quota->sz && quota->charged_sz >= quota->sz) + continue; + + /* Check the target regions condition */ if (sz < s->min_sz_region || s->max_sz_region < sz) continue; if (r->nr_accesses < s->min_nr_accesses || @@ -546,22 +561,51 @@ static void damon_do_apply_schemes(struct damon_ctx *c, continue; if (r->age < s->min_age_region || s->max_age_region < r->age) continue; - s->stat_count++; - s->stat_sz += sz; - if (c->primitive.apply_scheme) + + /* Apply the scheme */ + if (c->primitive.apply_scheme) { + if (quota->sz && quota->charged_sz + sz > quota->sz) { + sz = ALIGN_DOWN(quota->sz - quota->charged_sz, + DAMON_MIN_REGION); + if (!sz) + goto update_stat; + damon_split_region_at(c, t, r, sz); + } c->primitive.apply_scheme(c, t, r, s); + quota->charged_sz += sz; + } if (s->action != DAMOS_STAT) r->age = 0; + +update_stat: + s->stat_count++; + s->stat_sz += sz; } } static void kdamond_apply_schemes(struct damon_ctx *c) { struct damon_target *t; - struct damon_region *r; + struct damon_region *r, *next_r; + struct damos *s; + + damon_for_each_scheme(s, c) { + struct damos_quota *quota = &s->quota; + + if (!quota->sz) + continue; + + /* New charge window starts */ + if (time_after_eq(jiffies, quota->charged_from + + msecs_to_jiffies( + quota->reset_interval))) { + quota->charged_from = jiffies; + quota->charged_sz = 0; + } + } damon_for_each_target(t, c) { - damon_for_each_region(r, t) + damon_for_each_region_safe(r, next_r, t) damon_do_apply_schemes(c, t, r); } } diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index c90988a20fa4..a04bd50cc4c4 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -188,6 +188,8 @@ static struct damos **str_to_schemes(const char *str, ssize_t len, *nr_schemes = 0; while (pos < len && *nr_schemes < max_nr_schemes) { + struct damos_quota quota = {}; + ret = sscanf(&str[pos], "%lu %lu %u %u %u %u %u%n", &min_sz, &max_sz, &min_nr_a, &max_nr_a, &min_age, &max_age, &action, &parsed); @@ -200,7 +202,7 @@ static struct damos **str_to_schemes(const char *str, ssize_t len, pos += parsed; scheme = damon_new_scheme(min_sz, max_sz, min_nr_a, max_nr_a, - min_age, max_age, action); + min_age, max_age, action, "a); if (!scheme) goto fail; From 50585192bc2ef9309d32dabdbb5e735679f4f128 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:20 -0700 Subject: [PATCH 145/166] mm/damon/schemes: skip already charged targets and regions If DAMOS has stopped applying action in the middle of a group of memory regions due to its size quota, it starts the work again from the beginning of the address space in the next charge window. If there is a huge memory region at the beginning of the address space and it fulfills the scheme's target data access pattern always, the action will applied to only the region. This mitigates the case by skipping memory regions that charged in current charge window at the beginning of next charge window. Link: https://lkml.kernel.org/r/20211019150731.16699-4-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 5 +++++ mm/damon/core.c | 37 +++++++++++++++++++++++++++++++++++++ 2 files changed, 42 insertions(+) diff --git a/include/linux/damon.h b/include/linux/damon.h index 3a1ce9d9921c..585d985768fd 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -107,6 +107,8 @@ struct damos_quota { /* private: For charging the quota */ unsigned long charged_sz; unsigned long charged_from; + struct damon_target *charge_target_from; + unsigned long charge_addr_from; }; /** @@ -307,6 +309,9 @@ struct damon_ctx { #define damon_prev_region(r) \ (container_of(r->list.prev, struct damon_region, list)) +#define damon_last_region(t) \ + (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 cce14a0d5c72..693b75bc3450 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -111,6 +111,8 @@ struct damos *damon_new_scheme( scheme->quota.reset_interval = quota->reset_interval; scheme->quota.charged_sz = 0; scheme->quota.charged_from = 0; + scheme->quota.charge_target_from = NULL; + scheme->quota.charge_addr_from = 0; return scheme; } @@ -553,6 +555,37 @@ static void damon_do_apply_schemes(struct damon_ctx *c, if (quota->sz && quota->charged_sz >= quota->sz) continue; + /* Skip previously charged regions */ + if (quota->charge_target_from) { + if (t != quota->charge_target_from) + continue; + if (r == damon_last_region(t)) { + quota->charge_target_from = NULL; + quota->charge_addr_from = 0; + continue; + } + if (quota->charge_addr_from && + r->ar.end <= quota->charge_addr_from) + continue; + + if (quota->charge_addr_from && r->ar.start < + quota->charge_addr_from) { + sz = ALIGN_DOWN(quota->charge_addr_from - + r->ar.start, DAMON_MIN_REGION); + if (!sz) { + if (r->ar.end - r->ar.start <= + DAMON_MIN_REGION) + continue; + sz = DAMON_MIN_REGION; + } + damon_split_region_at(c, t, r, sz); + r = damon_next_region(r); + sz = r->ar.end - r->ar.start; + } + quota->charge_target_from = NULL; + quota->charge_addr_from = 0; + } + /* Check the target regions condition */ if (sz < s->min_sz_region || s->max_sz_region < sz) continue; @@ -573,6 +606,10 @@ static void damon_do_apply_schemes(struct damon_ctx *c, } c->primitive.apply_scheme(c, t, r, s); quota->charged_sz += sz; + if (quota->sz && quota->charged_sz >= quota->sz) { + quota->charge_target_from = t; + quota->charge_addr_from = r->ar.end + 1; + } } if (s->action != DAMOS_STAT) r->age = 0; From 1cd2430300594a230dba9178ac9e286d868d9da2 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:23 -0700 Subject: [PATCH 146/166] mm/damon/schemes: implement time quota The size quota feature of DAMOS is useful for IO resource-critical systems, but not so intuitive for CPU time-critical systems. Systems using zram or zswap-like swap device would be examples. To provide another intuitive ways for such systems, this implements time-based quota for DAMON-based Operation Schemes. If the quota is set, DAMOS tries to use only up to the user-defined quota of CPU time within a given time window. Link: https://lkml.kernel.org/r/20211019150731.16699-5-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 25 +++++++++++++++++++----- mm/damon/core.c | 45 ++++++++++++++++++++++++++++++++++++++----- 2 files changed, 60 insertions(+), 10 deletions(-) diff --git a/include/linux/damon.h b/include/linux/damon.h index 585d985768fd..1e7671bf3d23 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -91,20 +91,35 @@ enum damos_action { /** * struct damos_quota - Controls the aggressiveness of the given scheme. + * @ms: Maximum milliseconds that the scheme can use. * @sz: Maximum bytes of memory that the action can be applied. * @reset_interval: Charge reset interval in milliseconds. * * To avoid consuming too much CPU time or IO resources for applying the - * &struct damos->action to large memory, DAMON allows users to set a size - * quota. The quota can be set by writing non-zero values to &sz. If the size - * quota is set, DAMON tries to apply the action only up to &sz bytes within - * &reset_interval. + * &struct damos->action to large memory, DAMON allows users to set time and/or + * size quotas. The quotas can be set by writing non-zero values to &ms and + * &sz, respectively. If the time quota is set, DAMON tries to use only up to + * &ms milliseconds within &reset_interval for applying the action. If the + * size quota is set, DAMON tries to apply the action only up to &sz bytes + * within &reset_interval. + * + * Internally, the time quota is transformed to a size quota using estimated + * throughput of the scheme's action. DAMON then compares it against &sz and + * uses smaller one as the effective quota. */ struct damos_quota { + unsigned long ms; unsigned long sz; unsigned long reset_interval; -/* private: For charging the quota */ +/* private: */ + /* For throughput estimation */ + unsigned long total_charged_sz; + unsigned long total_charged_ns; + + unsigned long esz; /* Effective size quota in bytes */ + + /* For charging the quota */ unsigned long charged_sz; unsigned long charged_from; struct damon_target *charge_target_from; diff --git a/mm/damon/core.c b/mm/damon/core.c index 693b75bc3450..d1da4bef96ed 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -107,8 +107,12 @@ struct damos *damon_new_scheme( scheme->stat_sz = 0; INIT_LIST_HEAD(&scheme->list); + scheme->quota.ms = quota->ms; scheme->quota.sz = quota->sz; scheme->quota.reset_interval = quota->reset_interval; + scheme->quota.total_charged_sz = 0; + scheme->quota.total_charged_ns = 0; + scheme->quota.esz = 0; scheme->quota.charged_sz = 0; scheme->quota.charged_from = 0; scheme->quota.charge_target_from = NULL; @@ -550,9 +554,10 @@ static void damon_do_apply_schemes(struct damon_ctx *c, damon_for_each_scheme(s, c) { struct damos_quota *quota = &s->quota; unsigned long sz = r->ar.end - r->ar.start; + struct timespec64 begin, end; /* Check the quota */ - if (quota->sz && quota->charged_sz >= quota->sz) + if (quota->esz && quota->charged_sz >= quota->esz) continue; /* Skip previously charged regions */ @@ -597,16 +602,21 @@ static void damon_do_apply_schemes(struct damon_ctx *c, /* Apply the scheme */ if (c->primitive.apply_scheme) { - if (quota->sz && quota->charged_sz + sz > quota->sz) { - sz = ALIGN_DOWN(quota->sz - quota->charged_sz, + if (quota->esz && + quota->charged_sz + sz > quota->esz) { + sz = ALIGN_DOWN(quota->esz - quota->charged_sz, DAMON_MIN_REGION); if (!sz) goto update_stat; damon_split_region_at(c, t, r, sz); } + ktime_get_coarse_ts64(&begin); 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); quota->charged_sz += sz; - if (quota->sz && quota->charged_sz >= quota->sz) { + if (quota->esz && quota->charged_sz >= quota->esz) { quota->charge_target_from = t; quota->charge_addr_from = r->ar.end + 1; } @@ -620,6 +630,29 @@ update_stat: } } +/* Shouldn't be called if quota->ms and quota->sz are zero */ +static void damos_set_effective_quota(struct damos_quota *quota) +{ + unsigned long throughput; + unsigned long esz; + + if (!quota->ms) { + quota->esz = quota->sz; + return; + } + + if (quota->total_charged_ns) + throughput = quota->total_charged_sz * 1000000 / + quota->total_charged_ns; + else + throughput = PAGE_SIZE * 1024; + esz = throughput * quota->ms; + + if (quota->sz && quota->sz < esz) + esz = quota->sz; + quota->esz = esz; +} + static void kdamond_apply_schemes(struct damon_ctx *c) { struct damon_target *t; @@ -629,15 +662,17 @@ static void kdamond_apply_schemes(struct damon_ctx *c) damon_for_each_scheme(s, c) { struct damos_quota *quota = &s->quota; - if (!quota->sz) + if (!quota->ms && !quota->sz) continue; /* New charge window starts */ if (time_after_eq(jiffies, quota->charged_from + msecs_to_jiffies( quota->reset_interval))) { + quota->total_charged_sz += quota->charged_sz; quota->charged_from = jiffies; quota->charged_sz = 0; + damos_set_effective_quota(quota); } } From d7d0ec85e983945079364db3c3d2d80cc795a48c Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:27 -0700 Subject: [PATCH 147/166] mm/damon/dbgfs: support quotas of schemes This makes the debugfs interface of DAMON support the scheme quotas by chaning the format of the input for the schemes file. Link: https://lkml.kernel.org/r/20211019150731.16699-6-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/damon/dbgfs.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index a04bd50cc4c4..097e6745ba75 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -105,11 +105,14 @@ static ssize_t sprint_schemes(struct damon_ctx *c, char *buf, ssize_t len) damon_for_each_scheme(s, c) { rc = scnprintf(&buf[written], len - written, - "%lu %lu %u %u %u %u %d %lu %lu\n", + "%lu %lu %u %u %u %u %d %lu %lu %lu %lu %lu\n", s->min_sz_region, s->max_sz_region, s->min_nr_accesses, s->max_nr_accesses, s->min_age_region, s->max_age_region, - s->action, s->stat_count, s->stat_sz); + s->action, + s->quota.ms, s->quota.sz, + s->quota.reset_interval, + s->stat_count, s->stat_sz); if (!rc) return -ENOMEM; @@ -190,10 +193,11 @@ static struct damos **str_to_schemes(const char *str, ssize_t len, while (pos < len && *nr_schemes < max_nr_schemes) { struct damos_quota quota = {}; - ret = sscanf(&str[pos], "%lu %lu %u %u %u %u %u%n", + ret = sscanf(&str[pos], "%lu %lu %u %u %u %u %u %lu %lu %lu%n", &min_sz, &max_sz, &min_nr_a, &max_nr_a, - &min_age, &max_age, &action, &parsed); - if (ret != 7) + &min_age, &max_age, &action, "a.ms, + "a.sz, "a.reset_interval, &parsed); + if (ret != 10) break; if (!damos_action_valid(action)) { pr_err("wrong action %d\n", action); From a2cb4dd0d40d3dcb7288a963d0f66271934417b6 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:30 -0700 Subject: [PATCH 148/166] mm/damon/selftests: support schemes quotas This updates DAMON selftests to support updated schemes debugfs file format for the quotas. Link: https://lkml.kernel.org/r/20211019150731.16699-7-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/testing/selftests/damon/debugfs_attrs.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/damon/debugfs_attrs.sh b/tools/testing/selftests/damon/debugfs_attrs.sh index 639cfb6a1f65..8e33a7b584e7 100644 --- a/tools/testing/selftests/damon/debugfs_attrs.sh +++ b/tools/testing/selftests/damon/debugfs_attrs.sh @@ -63,10 +63,10 @@ echo "$orig_content" > "$file" file="$DBGFS/schemes" orig_content=$(cat "$file") -test_write_succ "$file" "1 2 3 4 5 6 4" \ +test_write_succ "$file" "1 2 3 4 5 6 4 0 0 0" \ "$orig_content" "valid input" test_write_fail "$file" "1 2 -3 4 5 6 3" "$orig_content" "multi lines" +3 4 5 6 3 0 0 0" "$orig_content" "multi lines" test_write_succ "$file" "" "$orig_content" "disabling" echo "$orig_content" > "$file" From 38683e003153f7abfa612d7b7fe147efa4624af2 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:33 -0700 Subject: [PATCH 149/166] mm/damon/schemes: prioritize regions within the quotas This makes DAMON apply schemes to regions having higher priority first, if it cannot apply schemes to all regions due to the quotas. The prioritization function should be implemented in the monitoring primitives. Those would commonly calculate the priority of the region using attributes of regions, namely 'size', 'nr_accesses', and 'age'. For example, some primitive would calculate the priority of each region using a weighted sum of 'nr_accesses' and 'age' of the region. The optimal weights would depend on give environments, so this makes those customizable. Nevertheless, the score calculation functions are only encouraged to respect the weights, not mandated. Link: https://lkml.kernel.org/r/20211019150731.16699-8-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 26 ++++++++++++++++++ mm/damon/core.c | 62 ++++++++++++++++++++++++++++++++++++++----- 2 files changed, 81 insertions(+), 7 deletions(-) diff --git a/include/linux/damon.h b/include/linux/damon.h index 1e7671bf3d23..5d47ad9e3911 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -14,6 +14,8 @@ /* 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) /** * struct damon_addr_range - Represents an address region of [@start, @end). @@ -95,6 +97,10 @@ enum damos_action { * @sz: Maximum bytes of memory that the action can be applied. * @reset_interval: Charge reset interval in milliseconds. * + * @weight_sz: Weight of the region's size for prioritization. + * @weight_nr_accesses: Weight of the region's nr_accesses for prioritization. + * @weight_age: Weight of the region's age for prioritization. + * * To avoid consuming too much CPU time or IO resources for applying the * &struct damos->action to large memory, DAMON allows users to set time and/or * size quotas. The quotas can be set by writing non-zero values to &ms and @@ -106,12 +112,22 @@ enum damos_action { * Internally, the time quota is transformed to a size quota using estimated * throughput of the scheme's action. DAMON then compares it against &sz and * uses smaller one as the effective quota. + * + * For selecting regions within the quota, DAMON prioritizes current scheme's + * target memory regions using the &struct damon_primitive->get_scheme_score. + * You could customize the prioritization logic by setting &weight_sz, + * &weight_nr_accesses, and &weight_age, because monitoring primitives are + * encouraged to respect those. */ struct damos_quota { unsigned long ms; unsigned long sz; unsigned long reset_interval; + unsigned int weight_sz; + unsigned int weight_nr_accesses; + unsigned int weight_age; + /* private: */ /* For throughput estimation */ unsigned long total_charged_sz; @@ -124,6 +140,10 @@ struct damos_quota { unsigned long charged_from; struct damon_target *charge_target_from; unsigned long charge_addr_from; + + /* For prioritization */ + unsigned long histogram[DAMOS_MAX_SCORE + 1]; + unsigned int min_score; }; /** @@ -174,6 +194,7 @@ struct damon_ctx; * @prepare_access_checks: Prepare next access check of target regions. * @check_accesses: Check the accesses to target regions. * @reset_aggregated: Reset aggregated accesses monitoring results. + * @get_scheme_score: Get the score of a region for a scheme. * @apply_scheme: Apply a DAMON-based operation scheme. * @target_valid: Determine if the target is valid. * @cleanup: Clean up the context. @@ -200,6 +221,8 @@ struct damon_ctx; * of its update. The value will be used for regions adjustment threshold. * @reset_aggregated should reset the access monitoring results that aggregated * by @check_accesses. + * @get_scheme_score should return the priority score of a region for a scheme + * 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. @@ -213,6 +236,9 @@ struct damon_primitive { void (*prepare_access_checks)(struct damon_ctx *context); unsigned int (*check_accesses)(struct damon_ctx *context); void (*reset_aggregated)(struct damon_ctx *context); + 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); bool (*target_valid)(void *target); diff --git a/mm/damon/core.c b/mm/damon/core.c index d1da4bef96ed..fad25778e2ec 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -12,6 +12,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -110,6 +111,9 @@ struct damos *damon_new_scheme( scheme->quota.ms = quota->ms; scheme->quota.sz = quota->sz; scheme->quota.reset_interval = quota->reset_interval; + scheme->quota.weight_sz = quota->weight_sz; + scheme->quota.weight_nr_accesses = quota->weight_nr_accesses; + scheme->quota.weight_age = quota->weight_age; scheme->quota.total_charged_sz = 0; scheme->quota.total_charged_ns = 0; scheme->quota.esz = 0; @@ -545,6 +549,28 @@ static void damon_split_region_at(struct damon_ctx *ctx, struct damon_target *t, struct damon_region *r, unsigned long sz_r); +static bool __damos_valid_target(struct damon_region *r, struct damos *s) +{ + unsigned long sz; + + sz = r->ar.end - r->ar.start; + return s->min_sz_region <= sz && sz <= s->max_sz_region && + s->min_nr_accesses <= r->nr_accesses && + r->nr_accesses <= s->max_nr_accesses && + s->min_age_region <= r->age && r->age <= s->max_age_region; +} + +static bool damos_valid_target(struct damon_ctx *c, struct damon_target *t, + struct damon_region *r, struct damos *s) +{ + bool ret = __damos_valid_target(r, s); + + if (!ret || !s->quota.esz || !c->primitive.get_scheme_score) + return ret; + + return c->primitive.get_scheme_score(c, t, r, s) >= s->quota.min_score; +} + static void damon_do_apply_schemes(struct damon_ctx *c, struct damon_target *t, struct damon_region *r) @@ -591,13 +617,7 @@ static void damon_do_apply_schemes(struct damon_ctx *c, quota->charge_addr_from = 0; } - /* Check the target regions condition */ - if (sz < s->min_sz_region || s->max_sz_region < sz) - continue; - if (r->nr_accesses < s->min_nr_accesses || - s->max_nr_accesses < r->nr_accesses) - continue; - if (r->age < s->min_age_region || s->max_age_region < r->age) + if (!damos_valid_target(c, t, r, s)) continue; /* Apply the scheme */ @@ -661,6 +681,8 @@ static void kdamond_apply_schemes(struct damon_ctx *c) damon_for_each_scheme(s, c) { struct damos_quota *quota = &s->quota; + unsigned long cumulated_sz; + unsigned int score, max_score = 0; if (!quota->ms && !quota->sz) continue; @@ -674,6 +696,32 @@ static void kdamond_apply_schemes(struct damon_ctx *c) quota->charged_sz = 0; damos_set_effective_quota(quota); } + + if (!c->primitive.get_scheme_score) + continue; + + /* Fill up the score histogram */ + memset(quota->histogram, 0, sizeof(quota->histogram)); + damon_for_each_target(t, c) { + damon_for_each_region(r, t) { + if (!__damos_valid_target(r, s)) + continue; + score = c->primitive.get_scheme_score( + c, t, r, s); + quota->histogram[score] += + r->ar.end - r->ar.start; + if (score > max_score) + max_score = score; + } + } + + /* Set the min score limit */ + for (cumulated_sz = 0, score = max_score; ; score--) { + cumulated_sz += quota->histogram[score]; + if (cumulated_sz >= quota->esz || !score) + break; + } + quota->min_score = score; } damon_for_each_target(t, c) { From 198f0f4c58b9f481e4e51c8c70a6ab9852bbab7f Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:37 -0700 Subject: [PATCH 150/166] mm/damon/vaddr,paddr: support pageout prioritization This makes the default monitoring primitives for virtual address spaces and the physical address sapce to support memory regions prioritization for 'PAGEOUT' DAMOS action. It calculates hotness of each region as weighted sum of 'nr_accesses' and 'age' of the region and get the priority score as reverse of the hotness, so that cold regions can be paged out first. Link: https://lkml.kernel.org/r/20211019150731.16699-9-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 4 ++++ mm/damon/paddr.c | 14 +++++++++++++ mm/damon/prmtv-common.c | 46 +++++++++++++++++++++++++++++++++++++++++ mm/damon/prmtv-common.h | 3 +++ mm/damon/vaddr.c | 15 ++++++++++++++ 5 files changed, 82 insertions(+) diff --git a/include/linux/damon.h b/include/linux/damon.h index 5d47ad9e3911..1217566a0ebc 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -421,6 +421,8 @@ 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 */ @@ -433,6 +435,8 @@ 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 */ diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c index 957ada55de77..a496d6f203d6 100644 --- a/mm/damon/paddr.c +++ b/mm/damon/paddr.c @@ -246,6 +246,19 @@ 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) +{ + switch (scheme->action) { + case DAMOS_PAGEOUT: + return damon_pageout_score(context, r, scheme); + default: + break; + } + + return DAMOS_MAX_SCORE; +} + void damon_pa_set_primitives(struct damon_ctx *ctx) { ctx->primitive.init = NULL; @@ -256,4 +269,5 @@ void damon_pa_set_primitives(struct damon_ctx *ctx) ctx->primitive.target_valid = damon_pa_target_valid; ctx->primitive.cleanup = NULL; ctx->primitive.apply_scheme = damon_pa_apply_scheme; + ctx->primitive.get_scheme_score = damon_pa_scheme_score; } diff --git a/mm/damon/prmtv-common.c b/mm/damon/prmtv-common.c index 7e62ee54fb54..92a04f5831d6 100644 --- a/mm/damon/prmtv-common.c +++ b/mm/damon/prmtv-common.c @@ -85,3 +85,49 @@ void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, unsigned long addr) put_page(page); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ } + +#define DAMON_MAX_SUBSCORE (100) +#define DAMON_MAX_AGE_IN_LOG (32) + +int damon_pageout_score(struct damon_ctx *c, struct damon_region *r, + struct damos *s) +{ + unsigned int max_nr_accesses; + int freq_subscore; + unsigned int age_in_sec; + int age_in_log, age_subscore; + unsigned int freq_weight = s->quota.weight_nr_accesses; + unsigned int age_weight = s->quota.weight_age; + int hotness; + + max_nr_accesses = c->aggr_interval / c->sample_interval; + freq_subscore = r->nr_accesses * DAMON_MAX_SUBSCORE / max_nr_accesses; + + age_in_sec = (unsigned long)r->age * c->aggr_interval / 1000000; + for (age_in_log = 0; age_in_log < DAMON_MAX_AGE_IN_LOG && age_in_sec; + age_in_log++, age_in_sec >>= 1) + ; + + /* If frequency is 0, higher age means it's colder */ + if (freq_subscore == 0) + age_in_log *= -1; + + /* + * Now age_in_log is in [-DAMON_MAX_AGE_IN_LOG, DAMON_MAX_AGE_IN_LOG]. + * Scale it to be in [0, 100] and set it as age subscore. + */ + age_in_log += DAMON_MAX_AGE_IN_LOG; + age_subscore = age_in_log * DAMON_MAX_SUBSCORE / + DAMON_MAX_AGE_IN_LOG / 2; + + hotness = (freq_weight * freq_subscore + age_weight * age_subscore); + if (freq_weight + age_weight) + hotness /= freq_weight + age_weight; + /* + * Transform it to fit in [0, DAMOS_MAX_SCORE] + */ + hotness = hotness * DAMOS_MAX_SCORE / DAMON_MAX_SUBSCORE; + + /* Return coldness of the region */ + return DAMOS_MAX_SCORE - hotness; +} diff --git a/mm/damon/prmtv-common.h b/mm/damon/prmtv-common.h index 7093d19e5d42..61f27037603e 100644 --- a/mm/damon/prmtv-common.h +++ b/mm/damon/prmtv-common.h @@ -15,3 +15,6 @@ struct page *damon_get_page(unsigned long pfn); void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr); void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, unsigned long addr); + +int damon_pageout_score(struct damon_ctx *c, struct damon_region *r, + struct damos *s); diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index 758501b8d97d..675cd8c7df9b 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -633,6 +633,20 @@ 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) +{ + + switch (scheme->action) { + case DAMOS_PAGEOUT: + return damon_pageout_score(context, r, scheme); + default: + break; + } + + return DAMOS_MAX_SCORE; +} + void damon_va_set_primitives(struct damon_ctx *ctx) { ctx->primitive.init = damon_va_init; @@ -643,6 +657,7 @@ void damon_va_set_primitives(struct damon_ctx *ctx) ctx->primitive.target_valid = damon_va_target_valid; ctx->primitive.cleanup = NULL; ctx->primitive.apply_scheme = damon_va_apply_scheme; + ctx->primitive.get_scheme_score = damon_va_scheme_score; } #include "vaddr-test.h" From f4a68b4a04e6db9397f7776c51d0f9715bd1a60e Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:40 -0700 Subject: [PATCH 151/166] mm/damon/dbgfs: support prioritization weights This allows DAMON debugfs interface users set the prioritization weights by putting three more numbers to the 'schemes' file. Link: https://lkml.kernel.org/r/20211019150731.16699-10-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/damon/dbgfs.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index 097e6745ba75..20c4feb8b918 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -105,13 +105,16 @@ static ssize_t sprint_schemes(struct damon_ctx *c, char *buf, ssize_t len) damon_for_each_scheme(s, c) { rc = scnprintf(&buf[written], len - written, - "%lu %lu %u %u %u %u %d %lu %lu %lu %lu %lu\n", + "%lu %lu %u %u %u %u %d %lu %lu %lu %u %u %u %lu %lu\n", s->min_sz_region, s->max_sz_region, s->min_nr_accesses, s->max_nr_accesses, s->min_age_region, s->max_age_region, s->action, s->quota.ms, s->quota.sz, s->quota.reset_interval, + s->quota.weight_sz, + s->quota.weight_nr_accesses, + s->quota.weight_age, s->stat_count, s->stat_sz); if (!rc) return -ENOMEM; @@ -193,11 +196,14 @@ static struct damos **str_to_schemes(const char *str, ssize_t len, while (pos < len && *nr_schemes < max_nr_schemes) { struct damos_quota quota = {}; - ret = sscanf(&str[pos], "%lu %lu %u %u %u %u %u %lu %lu %lu%n", + ret = sscanf(&str[pos], + "%lu %lu %u %u %u %u %u %lu %lu %lu %u %u %u%n", &min_sz, &max_sz, &min_nr_a, &max_nr_a, &min_age, &max_age, &action, "a.ms, - "a.sz, "a.reset_interval, &parsed); - if (ret != 10) + "a.sz, "a.reset_interval, + "a.weight_sz, "a.weight_nr_accesses, + "a.weight_age, &parsed); + if (ret != 13) break; if (!damos_action_valid(action)) { pr_err("wrong action %d\n", action); From 5a0d6a08b81162fbe1e207f02571ace6d888f8b0 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:44 -0700 Subject: [PATCH 152/166] tools/selftests/damon: update for regions prioritization of schemes This updates the DAMON selftests for 'schemes' debugfs file, as the file format is updated. Link: https://lkml.kernel.org/r/20211019150731.16699-11-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/testing/selftests/damon/debugfs_attrs.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/damon/debugfs_attrs.sh b/tools/testing/selftests/damon/debugfs_attrs.sh index 8e33a7b584e7..466dbeb37e31 100644 --- a/tools/testing/selftests/damon/debugfs_attrs.sh +++ b/tools/testing/selftests/damon/debugfs_attrs.sh @@ -63,10 +63,10 @@ echo "$orig_content" > "$file" file="$DBGFS/schemes" orig_content=$(cat "$file") -test_write_succ "$file" "1 2 3 4 5 6 4 0 0 0" \ +test_write_succ "$file" "1 2 3 4 5 6 4 0 0 0 1 2 3" \ "$orig_content" "valid input" test_write_fail "$file" "1 2 -3 4 5 6 3 0 0 0" "$orig_content" "multi lines" +3 4 5 6 3 0 0 0 1 2 3" "$orig_content" "multi lines" test_write_succ "$file" "" "$orig_content" "disabling" echo "$orig_content" > "$file" From ee801b7dd7822a82fd7663048ad649545fac6df3 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:47 -0700 Subject: [PATCH 153/166] mm/damon/schemes: activate schemes based on a watermarks mechanism DAMON-based operation schemes need to be manually turned on and off. In some use cases, however, the condition for turning a scheme on and off would depend on the system's situation. For example, schemes for proactive pages reclamation would need to be turned on when some memory pressure is detected, and turned off when the system has enough free memory. For easier control of schemes activation based on the system situation, this introduces a watermarks-based mechanism. The client can describe the watermark metric (e.g., amount of free memory in the system), watermark check interval, and three watermarks, namely high, mid, and low. If the scheme is deactivated, it only gets the metric and compare that to the three watermarks for every check interval. If the metric is higher than the high watermark, the scheme is deactivated. If the metric is between the mid watermark and the low watermark, the scheme is activated. If the metric is lower than the low watermark, the scheme is deactivated again. This is to allow users fall back to traditional page-granularity mechanisms. Link: https://lkml.kernel.org/r/20211019150731.16699-12-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 52 ++++++++++++++++++++++- mm/damon/core.c | 97 ++++++++++++++++++++++++++++++++++++++++++- mm/damon/dbgfs.c | 5 ++- 3 files changed, 151 insertions(+), 3 deletions(-) diff --git a/include/linux/damon.h b/include/linux/damon.h index 1217566a0ebc..c93325efddd7 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -146,6 +146,45 @@ struct damos_quota { unsigned int min_score; }; +/** + * enum damos_wmark_metric - Represents the watermark metric. + * + * @DAMOS_WMARK_NONE: Ignore the watermarks of the given scheme. + * @DAMOS_WMARK_FREE_MEM_RATE: Free memory rate of the system in [0,1000]. + */ +enum damos_wmark_metric { + DAMOS_WMARK_NONE, + DAMOS_WMARK_FREE_MEM_RATE, +}; + +/** + * struct damos_watermarks - Controls when a given scheme should be activated. + * @metric: Metric for the watermarks. + * @interval: Watermarks check time interval in microseconds. + * @high: High watermark. + * @mid: Middle watermark. + * @low: Low watermark. + * + * If &metric is &DAMOS_WMARK_NONE, the scheme is always active. Being active + * means DAMON does monitoring and applying the action of the scheme to + * appropriate memory regions. Else, DAMON checks &metric of the system for at + * least every &interval microseconds and works as below. + * + * If &metric is higher than &high, the scheme is inactivated. If &metric is + * between &mid and &low, the scheme is activated. If &metric is lower than + * &low, the scheme is inactivated. + */ +struct damos_watermarks { + enum damos_wmark_metric metric; + unsigned long interval; + unsigned long high; + unsigned long mid; + unsigned long low; + +/* private: */ + bool activated; +}; + /** * struct damos - Represents a Data Access Monitoring-based Operation Scheme. * @min_sz_region: Minimum size of target regions. @@ -156,6 +195,7 @@ struct damos_quota { * @max_age_region: Maximum age of target regions. * @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. * @list: List head for siblings. @@ -166,6 +206,14 @@ struct damos_quota { * those. To avoid consuming too much CPU time or IO resources for the * &action, "a is used. * + * To do the work only when needed, schemes can be activated for specific + * system situations using &wmarks. If all schemes that registered to the + * monitoring context are inactive, DAMON stops monitoring either, and just + * repeatedly checks the watermarks. + * + * If all schemes that registered to a &struct damon_ctx are inactive, DAMON + * stops monitoring and just repeatedly checks the watermarks. + * * After applying the &action to each region, &stat_count and &stat_sz is * updated to reflect the number of regions and total size of regions that the * &action is applied. @@ -179,6 +227,7 @@ struct damos { unsigned int max_age_region; enum damos_action action; struct damos_quota quota; + struct damos_watermarks wmarks; unsigned long stat_count; unsigned long stat_sz; struct list_head list; @@ -384,7 +433,8 @@ struct damos *damon_new_scheme( unsigned long min_sz_region, unsigned long max_sz_region, unsigned int min_nr_accesses, unsigned int max_nr_accesses, unsigned int min_age_region, unsigned int max_age_region, - enum damos_action action, struct damos_quota *quota); + enum damos_action action, struct damos_quota *quota, + struct damos_watermarks *wmarks); void damon_add_scheme(struct damon_ctx *ctx, struct damos *s); void damon_destroy_scheme(struct damos *s); diff --git a/mm/damon/core.c b/mm/damon/core.c index fad25778e2ec..6993c60ae31c 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -90,7 +91,8 @@ struct damos *damon_new_scheme( unsigned long min_sz_region, unsigned long max_sz_region, unsigned int min_nr_accesses, unsigned int max_nr_accesses, unsigned int min_age_region, unsigned int max_age_region, - enum damos_action action, struct damos_quota *quota) + enum damos_action action, struct damos_quota *quota, + struct damos_watermarks *wmarks) { struct damos *scheme; @@ -122,6 +124,13 @@ struct damos *damon_new_scheme( scheme->quota.charge_target_from = NULL; scheme->quota.charge_addr_from = 0; + scheme->wmarks.metric = wmarks->metric; + scheme->wmarks.interval = wmarks->interval; + scheme->wmarks.high = wmarks->high; + scheme->wmarks.mid = wmarks->mid; + scheme->wmarks.low = wmarks->low; + scheme->wmarks.activated = true; + return scheme; } @@ -582,6 +591,9 @@ static void damon_do_apply_schemes(struct damon_ctx *c, unsigned long sz = r->ar.end - r->ar.start; struct timespec64 begin, end; + if (!s->wmarks.activated) + continue; + /* Check the quota */ if (quota->esz && quota->charged_sz >= quota->esz) continue; @@ -684,6 +696,9 @@ static void kdamond_apply_schemes(struct damon_ctx *c) unsigned long cumulated_sz; unsigned int score, max_score = 0; + if (!s->wmarks.activated) + continue; + if (!quota->ms && !quota->sz) continue; @@ -924,6 +939,83 @@ static bool kdamond_need_stop(struct damon_ctx *ctx) return true; } +static unsigned long damos_wmark_metric_value(enum damos_wmark_metric metric) +{ + struct sysinfo i; + + switch (metric) { + case DAMOS_WMARK_FREE_MEM_RATE: + si_meminfo(&i); + return i.freeram * 1000 / i.totalram; + default: + break; + } + return -EINVAL; +} + +/* + * Returns zero if the scheme is active. Else, returns time to wait for next + * watermark check in micro-seconds. + */ +static unsigned long damos_wmark_wait_us(struct damos *scheme) +{ + unsigned long metric; + + if (scheme->wmarks.metric == DAMOS_WMARK_NONE) + return 0; + + metric = damos_wmark_metric_value(scheme->wmarks.metric); + /* higher than high watermark or lower than low watermark */ + if (metric > scheme->wmarks.high || scheme->wmarks.low > metric) { + if (scheme->wmarks.activated) + pr_debug("inactivate a scheme (%d) for %s wmark\n", + scheme->action, + metric > scheme->wmarks.high ? + "high" : "low"); + scheme->wmarks.activated = false; + return scheme->wmarks.interval; + } + + /* inactive and higher than middle watermark */ + if ((scheme->wmarks.high >= metric && metric >= scheme->wmarks.mid) && + !scheme->wmarks.activated) + return scheme->wmarks.interval; + + if (!scheme->wmarks.activated) + pr_debug("activate a scheme (%d)\n", scheme->action); + scheme->wmarks.activated = true; + return 0; +} + +static void kdamond_usleep(unsigned long usecs) +{ + if (usecs > 100 * 1000) + schedule_timeout_interruptible(usecs_to_jiffies(usecs)); + else + usleep_range(usecs, usecs + 1); +} + +/* Returns negative error code if it's not activated but should return */ +static int kdamond_wait_activation(struct damon_ctx *ctx) +{ + struct damos *s; + unsigned long wait_time; + unsigned long min_wait_time = 0; + + while (!kdamond_need_stop(ctx)) { + damon_for_each_scheme(s, ctx) { + wait_time = damos_wmark_wait_us(s); + if (!min_wait_time || wait_time < min_wait_time) + min_wait_time = wait_time; + } + if (!min_wait_time) + return 0; + + kdamond_usleep(min_wait_time); + } + return -EBUSY; +} + static void set_kdamond_stop(struct damon_ctx *ctx) { mutex_lock(&ctx->kdamond_lock); @@ -952,6 +1044,9 @@ static int kdamond_fn(void *data) sz_limit = damon_region_sz_limit(ctx); while (!kdamond_need_stop(ctx)) { + if (kdamond_wait_activation(ctx)) + continue; + if (ctx->primitive.prepare_access_checks) ctx->primitive.prepare_access_checks(ctx); if (ctx->callback.after_sampling && diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index 20c4feb8b918..9f13060d1058 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -195,6 +195,9 @@ static struct damos **str_to_schemes(const char *str, ssize_t len, *nr_schemes = 0; while (pos < len && *nr_schemes < max_nr_schemes) { struct damos_quota quota = {}; + struct damos_watermarks wmarks = { + .metric = DAMOS_WMARK_NONE, + }; ret = sscanf(&str[pos], "%lu %lu %u %u %u %u %u %lu %lu %lu %u %u %u%n", @@ -212,7 +215,7 @@ static struct damos **str_to_schemes(const char *str, ssize_t len, pos += parsed; scheme = damon_new_scheme(min_sz, max_sz, min_nr_a, max_nr_a, - min_age, max_age, action, "a); + min_age, max_age, action, "a, &wmarks); if (!scheme) goto fail; From ae666a6dddfd119da55cc1bad54f7cbd8b2ef54c Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:50 -0700 Subject: [PATCH 154/166] mm/damon/dbgfs: support watermarks This updates DAMON debugfs interface to support the watermarks based schemes activation. For this, now 'schemes' file receives five more values. Link: https://lkml.kernel.org/r/20211019150731.16699-13-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/damon/dbgfs.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index 9f13060d1058..6828e463348b 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -105,7 +105,7 @@ static ssize_t sprint_schemes(struct damon_ctx *c, char *buf, ssize_t len) damon_for_each_scheme(s, c) { rc = scnprintf(&buf[written], len - written, - "%lu %lu %u %u %u %u %d %lu %lu %lu %u %u %u %lu %lu\n", + "%lu %lu %u %u %u %u %d %lu %lu %lu %u %u %u %d %lu %lu %lu %lu %lu %lu\n", s->min_sz_region, s->max_sz_region, s->min_nr_accesses, s->max_nr_accesses, s->min_age_region, s->max_age_region, @@ -115,6 +115,8 @@ static ssize_t sprint_schemes(struct damon_ctx *c, char *buf, ssize_t len) s->quota.weight_sz, s->quota.weight_nr_accesses, 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); if (!rc) return -ENOMEM; @@ -195,18 +197,18 @@ static struct damos **str_to_schemes(const char *str, ssize_t len, *nr_schemes = 0; while (pos < len && *nr_schemes < max_nr_schemes) { struct damos_quota quota = {}; - struct damos_watermarks wmarks = { - .metric = DAMOS_WMARK_NONE, - }; + struct damos_watermarks wmarks; ret = sscanf(&str[pos], - "%lu %lu %u %u %u %u %u %lu %lu %lu %u %u %u%n", + "%lu %lu %u %u %u %u %u %lu %lu %lu %u %u %u %u %lu %lu %lu %lu%n", &min_sz, &max_sz, &min_nr_a, &max_nr_a, &min_age, &max_age, &action, "a.ms, "a.sz, "a.reset_interval, "a.weight_sz, "a.weight_nr_accesses, - "a.weight_age, &parsed); - if (ret != 13) + "a.weight_age, &wmarks.metric, + &wmarks.interval, &wmarks.high, &wmarks.mid, + &wmarks.low, &parsed); + if (ret != 18) break; if (!damos_action_valid(action)) { pr_err("wrong action %d\n", action); From 1dc90ccd15c55cc3edec508466db9248a841acad Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:54 -0700 Subject: [PATCH 155/166] selftests/damon: support watermarks This updates DAMON selftests for 'schemes' debugfs file to reflect the changes in the format. Link: https://lkml.kernel.org/r/20211019150731.16699-14-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/testing/selftests/damon/debugfs_attrs.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/damon/debugfs_attrs.sh b/tools/testing/selftests/damon/debugfs_attrs.sh index 466dbeb37e31..196b6640bf37 100644 --- a/tools/testing/selftests/damon/debugfs_attrs.sh +++ b/tools/testing/selftests/damon/debugfs_attrs.sh @@ -63,10 +63,10 @@ echo "$orig_content" > "$file" file="$DBGFS/schemes" orig_content=$(cat "$file") -test_write_succ "$file" "1 2 3 4 5 6 4 0 0 0 1 2 3" \ +test_write_succ "$file" "1 2 3 4 5 6 4 0 0 0 1 2 3 1 100 3 2 1" \ "$orig_content" "valid input" test_write_fail "$file" "1 2 -3 4 5 6 3 0 0 0 1 2 3" "$orig_content" "multi lines" +3 4 5 6 3 0 0 0 1 2 3 1 100 3 2 1" "$orig_content" "multi lines" test_write_succ "$file" "" "$orig_content" "disabling" echo "$orig_content" > "$file" From 43b0536cb4710e7bb591edfda7e68a1c327a3409 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:57 -0700 Subject: [PATCH 156/166] mm/damon: introduce DAMON-based Reclamation (DAMON_RECLAIM) This implements a new kernel subsystem that finds cold memory regions using DAMON and reclaims those immediately. It is intended to be used as proactive lightweigh reclamation logic for light memory pressure. For heavy memory pressure, it could be inactivated and fall back to the traditional page-scanning based reclamation. It's implemented on top of DAMON framework to use the DAMON-based Operation Schemes (DAMOS) feature. It utilizes all the DAMOS features including speed limit, prioritization, and watermarks. It could be enabled and tuned in boot time via the kernel boot parameter, and in run time via its module parameters ('/sys/module/damon_reclaim/parameters/') interface. [yangyingliang@huawei.com: fix error return code in damon_reclaim_turn()] Link: https://lkml.kernel.org/r/20211025124500.2758060-1-yangyingliang@huawei.com Link: https://lkml.kernel.org/r/20211019150731.16699-15-sj@kernel.org Signed-off-by: SeongJae Park Signed-off-by: Yang Yingliang Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/damon/Kconfig | 12 ++ mm/damon/Makefile | 1 + mm/damon/reclaim.c | 356 +++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 369 insertions(+) create mode 100644 mm/damon/reclaim.c diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig index ca33b289ebbe..5bcf05851ad0 100644 --- a/mm/damon/Kconfig +++ b/mm/damon/Kconfig @@ -73,4 +73,16 @@ config DAMON_DBGFS_KUNIT_TEST If unsure, say N. +config DAMON_RECLAIM + bool "Build DAMON-based reclaim (DAMON_RECLAIM)" + depends on DAMON_PADDR + help + This builds the DAMON-based reclamation subsystem. It finds pages + that not accessed for a long time (cold) using DAMON and reclaim + those. + + This is suggested to be used as a proactive and lightweight + reclamation under light memory pressure, while the traditional page + scanning-based reclamation is used for heavy pressure. + endmenu diff --git a/mm/damon/Makefile b/mm/damon/Makefile index 8d9b0df79702..f7d5ac377a2b 100644 --- a/mm/damon/Makefile +++ b/mm/damon/Makefile @@ -4,3 +4,4 @@ obj-$(CONFIG_DAMON) := core.o obj-$(CONFIG_DAMON_VADDR) += prmtv-common.o vaddr.o obj-$(CONFIG_DAMON_PADDR) += prmtv-common.o paddr.o obj-$(CONFIG_DAMON_DBGFS) += dbgfs.o +obj-$(CONFIG_DAMON_RECLAIM) += reclaim.o diff --git a/mm/damon/reclaim.c b/mm/damon/reclaim.c new file mode 100644 index 000000000000..dc1485044eaf --- /dev/null +++ b/mm/damon/reclaim.c @@ -0,0 +1,356 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DAMON-based page reclamation + * + * Author: SeongJae Park + */ + +#define pr_fmt(fmt) "damon-reclaim: " fmt + +#include +#include +#include +#include +#include + +#ifdef MODULE_PARAM_PREFIX +#undef MODULE_PARAM_PREFIX +#endif +#define MODULE_PARAM_PREFIX "damon_reclaim." + +/* + * Enable or disable DAMON_RECLAIM. + * + * You can enable DAMON_RCLAIM by setting the value of this parameter as ``Y``. + * Setting it as ``N`` disables DAMON_RECLAIM. Note that DAMON_RECLAIM could + * do no real monitoring and reclamation due to the watermarks-based activation + * condition. Refer to below descriptions for the watermarks parameter for + * this. + */ +static bool enabled __read_mostly; +module_param(enabled, bool, 0600); + +/* + * Time threshold for cold memory regions identification in microseconds. + * + * If a memory region is not accessed for this or longer time, DAMON_RECLAIM + * identifies the region as cold, and reclaims. 120 seconds by default. + */ +static unsigned long min_age __read_mostly = 120000000; +module_param(min_age, ulong, 0600); + +/* + * Limit of time for trying the reclamation in milliseconds. + * + * DAMON_RECLAIM tries to use only up to this time within a time window + * (quota_reset_interval_ms) for trying reclamation of cold pages. This can be + * used for limiting CPU consumption of DAMON_RECLAIM. If the value is zero, + * the limit is disabled. + * + * 10 ms by default. + */ +static unsigned long quota_ms __read_mostly = 10; +module_param(quota_ms, ulong, 0600); + +/* + * Limit of size of memory for the reclamation in bytes. + * + * DAMON_RECLAIM charges amount of memory which it tried to reclaim within a + * time window (quota_reset_interval_ms) and makes no more than this limit is + * tried. This can be used for limiting consumption of CPU and IO. If this + * value is zero, the limit is disabled. + * + * 128 MiB by default. + */ +static unsigned long quota_sz __read_mostly = 128 * 1024 * 1024; +module_param(quota_sz, ulong, 0600); + +/* + * The time/size quota charge reset interval in milliseconds. + * + * The charge reset interval for the quota of time (quota_ms) and size + * (quota_sz). That is, DAMON_RECLAIM does not try reclamation for more than + * quota_ms milliseconds or quota_sz bytes within quota_reset_interval_ms + * milliseconds. + * + * 1 second by default. + */ +static unsigned long quota_reset_interval_ms __read_mostly = 1000; +module_param(quota_reset_interval_ms, ulong, 0600); + +/* + * The watermarks check time interval in microseconds. + * + * Minimal time to wait before checking the watermarks, when DAMON_RECLAIM is + * enabled but inactive due to its watermarks rule. 5 seconds by default. + */ +static unsigned long wmarks_interval __read_mostly = 5000000; +module_param(wmarks_interval, ulong, 0600); + +/* + * Free memory rate (per thousand) for the high watermark. + * + * If free memory of the system in bytes per thousand bytes is higher than + * this, DAMON_RECLAIM becomes inactive, so it does nothing but periodically + * checks the watermarks. 500 (50%) by default. + */ +static unsigned long wmarks_high __read_mostly = 500; +module_param(wmarks_high, ulong, 0600); + +/* + * Free memory rate (per thousand) for the middle watermark. + * + * If free memory of the system in bytes per thousand bytes is between this and + * the low watermark, DAMON_RECLAIM becomes active, so starts the monitoring + * and the reclaiming. 400 (40%) by default. + */ +static unsigned long wmarks_mid __read_mostly = 400; +module_param(wmarks_mid, ulong, 0600); + +/* + * Free memory rate (per thousand) for the low watermark. + * + * If free memory of the system in bytes per thousand bytes is lower than this, + * DAMON_RECLAIM becomes inactive, so it does nothing but periodically checks + * the watermarks. In the case, the system falls back to the LRU-based page + * granularity reclamation logic. 200 (20%) by default. + */ +static unsigned long wmarks_low __read_mostly = 200; +module_param(wmarks_low, ulong, 0600); + +/* + * Sampling interval for the monitoring in microseconds. + * + * The sampling interval of DAMON for the cold memory monitoring. Please refer + * to the DAMON documentation for more detail. 5 ms by default. + */ +static unsigned long sample_interval __read_mostly = 5000; +module_param(sample_interval, ulong, 0600); + +/* + * Aggregation interval for the monitoring in microseconds. + * + * The aggregation interval of DAMON for the cold memory monitoring. Please + * refer to the DAMON documentation for more detail. 100 ms by default. + */ +static unsigned long aggr_interval __read_mostly = 100000; +module_param(aggr_interval, ulong, 0600); + +/* + * Minimum number of monitoring regions. + * + * The minimal number of monitoring regions of DAMON for the cold memory + * monitoring. This can be used to set lower-bound of the monitoring quality. + * But, setting this too high could result in increased monitoring overhead. + * Please refer to the DAMON documentation for more detail. 10 by default. + */ +static unsigned long min_nr_regions __read_mostly = 10; +module_param(min_nr_regions, ulong, 0600); + +/* + * Maximum number of monitoring regions. + * + * The maximum number of monitoring regions of DAMON for the cold memory + * monitoring. This can be used to set upper-bound of the monitoring overhead. + * However, setting this too low could result in bad monitoring quality. + * Please refer to the DAMON documentation for more detail. 1000 by default. + */ +static unsigned long max_nr_regions __read_mostly = 1000; +module_param(max_nr_regions, ulong, 0600); + +/* + * Start of the target memory region in physical address. + * + * The start physical address of memory region that DAMON_RECLAIM will do work + * against. By default, biggest System RAM is used as the region. + */ +static unsigned long monitor_region_start __read_mostly; +module_param(monitor_region_start, ulong, 0600); + +/* + * End of the target memory region in physical address. + * + * The end physical address of memory region that DAMON_RECLAIM will do work + * against. By default, biggest System RAM is used as the region. + */ +static unsigned long monitor_region_end __read_mostly; +module_param(monitor_region_end, ulong, 0600); + +/* + * PID of the DAMON thread + * + * If DAMON_RECLAIM is enabled, this becomes the PID of the worker thread. + * Else, -1. + */ +static int kdamond_pid __read_mostly = -1; +module_param(kdamond_pid, int, 0400); + +static struct damon_ctx *ctx; +static struct damon_target *target; + +struct damon_reclaim_ram_walk_arg { + unsigned long start; + unsigned long end; +}; + +static int walk_system_ram(struct resource *res, void *arg) +{ + struct damon_reclaim_ram_walk_arg *a = arg; + + if (a->end - a->start < res->end - res->start) { + a->start = res->start; + a->end = res->end; + } + return 0; +} + +/* + * Find biggest 'System RAM' resource and store its start and end address in + * @start and @end, respectively. If no System RAM is found, returns false. + */ +static bool get_monitoring_region(unsigned long *start, unsigned long *end) +{ + struct damon_reclaim_ram_walk_arg arg = {}; + + walk_system_ram_res(0, ULONG_MAX, &arg, walk_system_ram); + if (arg.end <= arg.start) + return false; + + *start = arg.start; + *end = arg.end; + return true; +} + +static struct damos *damon_reclaim_new_scheme(void) +{ + struct damos_watermarks wmarks = { + .metric = DAMOS_WMARK_FREE_MEM_RATE, + .interval = wmarks_interval, + .high = wmarks_high, + .mid = wmarks_mid, + .low = wmarks_low, + }; + struct damos_quota quota = { + /* + * Do not try reclamation for more than quota_ms milliseconds + * or quota_sz bytes within quota_reset_interval_ms. + */ + .ms = quota_ms, + .sz = quota_sz, + .reset_interval = quota_reset_interval_ms, + /* Within the quota, page out older regions first. */ + .weight_sz = 0, + .weight_nr_accesses = 0, + .weight_age = 1 + }; + struct damos *scheme = damon_new_scheme( + /* Find regions having PAGE_SIZE or larger size */ + PAGE_SIZE, ULONG_MAX, + /* and not accessed at all */ + 0, 0, + /* for min_age or more micro-seconds, and */ + min_age / aggr_interval, UINT_MAX, + /* page out those, as soon as found */ + DAMOS_PAGEOUT, + /* under the quota. */ + "a, + /* (De)activate this according to the watermarks. */ + &wmarks); + + return scheme; +} + +static int damon_reclaim_turn(bool on) +{ + struct damon_region *region; + struct damos *scheme; + int err; + + if (!on) { + err = damon_stop(&ctx, 1); + if (!err) + kdamond_pid = -1; + return err; + } + + err = damon_set_attrs(ctx, sample_interval, aggr_interval, 0, + min_nr_regions, max_nr_regions); + if (err) + return err; + + if (monitor_region_start > monitor_region_end) + return -EINVAL; + if (!monitor_region_start && !monitor_region_end && + !get_monitoring_region(&monitor_region_start, + &monitor_region_end)) + return -EINVAL; + /* DAMON will free this on its own when finish monitoring */ + region = damon_new_region(monitor_region_start, monitor_region_end); + if (!region) + return -ENOMEM; + damon_add_region(region, target); + + /* Will be freed by 'damon_set_schemes()' below */ + scheme = damon_reclaim_new_scheme(); + if (!scheme) { + err = -ENOMEM; + goto free_region_out; + } + err = damon_set_schemes(ctx, &scheme, 1); + if (err) + goto free_scheme_out; + + err = damon_start(&ctx, 1); + if (!err) { + kdamond_pid = ctx->kdamond->pid; + return 0; + } + +free_scheme_out: + damon_destroy_scheme(scheme); +free_region_out: + damon_destroy_region(region, target); + return err; +} + +#define ENABLE_CHECK_INTERVAL_MS 1000 +static struct delayed_work damon_reclaim_timer; +static void damon_reclaim_timer_fn(struct work_struct *work) +{ + static bool last_enabled; + bool now_enabled; + + now_enabled = enabled; + if (last_enabled != now_enabled) { + if (!damon_reclaim_turn(now_enabled)) + last_enabled = now_enabled; + else + enabled = last_enabled; + } + + schedule_delayed_work(&damon_reclaim_timer, + msecs_to_jiffies(ENABLE_CHECK_INTERVAL_MS)); +} +static DECLARE_DELAYED_WORK(damon_reclaim_timer, damon_reclaim_timer_fn); + +static int __init damon_reclaim_init(void) +{ + ctx = damon_new_ctx(); + if (!ctx) + return -ENOMEM; + + damon_pa_set_primitives(ctx); + + /* 4242 means nothing but fun */ + target = damon_new_target(4242); + if (!target) { + damon_destroy_ctx(ctx); + return -ENOMEM; + } + damon_add_target(ctx, target); + + schedule_delayed_work(&damon_reclaim_timer, 0); + return 0; +} + +module_init(damon_reclaim_init); From bec976b691437d056a92964cb7af07ee1a54221a Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:48:01 -0700 Subject: [PATCH 157/166] Documentation/admin-guide/mm/damon: add a document for DAMON_RECLAIM This adds an admin-guide document for DAMON-based Reclamation. Link: https://lkml.kernel.org/r/20211019150731.16699-16-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/mm/damon/index.rst | 1 + .../admin-guide/mm/damon/reclaim.rst | 235 ++++++++++++++++++ 2 files changed, 236 insertions(+) create mode 100644 Documentation/admin-guide/mm/damon/reclaim.rst diff --git a/Documentation/admin-guide/mm/damon/index.rst b/Documentation/admin-guide/mm/damon/index.rst index 8c5dde3a5754..61aff88347f3 100644 --- a/Documentation/admin-guide/mm/damon/index.rst +++ b/Documentation/admin-guide/mm/damon/index.rst @@ -13,3 +13,4 @@ optimize those. start usage + reclaim diff --git a/Documentation/admin-guide/mm/damon/reclaim.rst b/Documentation/admin-guide/mm/damon/reclaim.rst new file mode 100644 index 000000000000..fb9def3a7355 --- /dev/null +++ b/Documentation/admin-guide/mm/damon/reclaim.rst @@ -0,0 +1,235 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======================= +DAMON-based Reclamation +======================= + +DAMON-based Reclamation (DAMON_RECLAIM) is a static kernel module that aimed to +be used for proactive and lightweight reclamation under light memory pressure. +It doesn't aim to replace the LRU-list based page_granularity reclamation, but +to be selectively used for different level of memory pressure and requirements. + +Where Proactive Reclamation is Required? +======================================== + +On general memory over-committed systems, proactively reclaiming cold pages +helps saving memory and reducing latency spikes that incurred by the direct +reclaim of the process or CPU consumption of kswapd, while incurring only +minimal performance degradation [1]_ [2]_ . + +Free Pages Reporting [3]_ based memory over-commit virtualization systems are +good example of the cases. In such systems, the guest VMs reports their free +memory to host, and the host reallocates the reported memory to other guests. +As a result, the memory of the systems are fully utilized. However, the +guests could be not so memory-frugal, mainly because some kernel subsystems and +user-space applications are designed to use as much memory as available. Then, +guests could report only small amount of memory as free to host, results in +memory utilization drop of the systems. Running the proactive reclamation in +guests could mitigate this problem. + +How It Works? +============= + +DAMON_RECLAIM finds memory regions that didn't accessed for specific time +duration and page out. To avoid it consuming too much CPU for the paging out +operation, a speed limit can be configured. Under the speed limit, it pages +out memory regions that didn't accessed longer time first. System +administrators can also configure under what situation this scheme should +automatically activated and deactivated with three memory pressure watermarks. + +Interface: Module Parameters +============================ + +To use this feature, you should first ensure your system is running on a kernel +that is built with ``CONFIG_DAMON_RECLAIM=y``. + +To let sysadmins enable or disable it and tune for the given system, +DAMON_RECLAIM utilizes module parameters. That is, you can put +``damon_reclaim.=`` on the kernel boot command line or write +proper values to ``/sys/modules/damon_reclaim/parameters/`` files. + +Note that the parameter values except ``enabled`` are applied only when +DAMON_RECLAIM starts. Therefore, if you want to apply new parameter values in +runtime and DAMON_RECLAIM is already enabled, you should disable and re-enable +it via ``enabled`` parameter file. Writing of the new values to proper +parameter values should be done before the re-enablement. + +Below are the description of each parameter. + +enabled +------- + +Enable or disable DAMON_RECLAIM. + +You can enable DAMON_RCLAIM by setting the value of this parameter as ``Y``. +Setting it as ``N`` disables DAMON_RECLAIM. Note that DAMON_RECLAIM could do +no real monitoring and reclamation due to the watermarks-based activation +condition. Refer to below descriptions for the watermarks parameter for this. + +min_age +------- + +Time threshold for cold memory regions identification in microseconds. + +If a memory region is not accessed for this or longer time, DAMON_RECLAIM +identifies the region as cold, and reclaims it. + +120 seconds by default. + +quota_ms +-------- + +Limit of time for the reclamation in milliseconds. + +DAMON_RECLAIM tries to use only up to this time within a time window +(quota_reset_interval_ms) for trying reclamation of cold pages. This can be +used for limiting CPU consumption of DAMON_RECLAIM. If the value is zero, the +limit is disabled. + +10 ms by default. + +quota_sz +-------- + +Limit of size of memory for the reclamation in bytes. + +DAMON_RECLAIM charges amount of memory which it tried to reclaim within a time +window (quota_reset_interval_ms) and makes no more than this limit is tried. +This can be used for limiting consumption of CPU and IO. If this value is +zero, the limit is disabled. + +128 MiB by default. + +quota_reset_interval_ms +----------------------- + +The time/size quota charge reset interval in milliseconds. + +The charget reset interval for the quota of time (quota_ms) and size +(quota_sz). That is, DAMON_RECLAIM does not try reclamation for more than +quota_ms milliseconds or quota_sz bytes within quota_reset_interval_ms +milliseconds. + +1 second by default. + +wmarks_interval +--------------- + +Minimal time to wait before checking the watermarks, when DAMON_RECLAIM is +enabled but inactive due to its watermarks rule. + +wmarks_high +----------- + +Free memory rate (per thousand) for the high watermark. + +If free memory of the system in bytes per thousand bytes is higher than this, +DAMON_RECLAIM becomes inactive, so it does nothing but only periodically checks +the watermarks. + +wmarks_mid +---------- + +Free memory rate (per thousand) for the middle watermark. + +If free memory of the system in bytes per thousand bytes is between this and +the low watermark, DAMON_RECLAIM becomes active, so starts the monitoring and +the reclaiming. + +wmarks_low +---------- + +Free memory rate (per thousand) for the low watermark. + +If free memory of the system in bytes per thousand bytes is lower than this, +DAMON_RECLAIM becomes inactive, so it does nothing but periodically checks the +watermarks. In the case, the system falls back to the LRU-list based page +granularity reclamation logic. + +sample_interval +--------------- + +Sampling interval for the monitoring in microseconds. + +The sampling interval of DAMON for the cold memory monitoring. Please refer to +the DAMON documentation (:doc:`usage`) for more detail. + +aggr_interval +------------- + +Aggregation interval for the monitoring in microseconds. + +The aggregation interval of DAMON for the cold memory monitoring. Please +refer to the DAMON documentation (:doc:`usage`) for more detail. + +min_nr_regions +-------------- + +Minimum number of monitoring regions. + +The minimal number of monitoring regions of DAMON for the cold memory +monitoring. This can be used to set lower-bound of the monitoring quality. +But, setting this too high could result in increased monitoring overhead. +Please refer to the DAMON documentation (:doc:`usage`) for more detail. + +max_nr_regions +-------------- + +Maximum number of monitoring regions. + +The maximum number of monitoring regions of DAMON for the cold memory +monitoring. This can be used to set upper-bound of the monitoring overhead. +However, setting this too low could result in bad monitoring quality. Please +refer to the DAMON documentation (:doc:`usage`) for more detail. + +monitor_region_start +-------------------- + +Start of target memory region in physical address. + +The start physical address of memory region that DAMON_RECLAIM will do work +against. That is, DAMON_RECLAIM will find cold memory regions in this region +and reclaims. By default, biggest System RAM is used as the region. + +monitor_region_end +------------------ + +End of target memory region in physical address. + +The end physical address of memory region that DAMON_RECLAIM will do work +against. That is, DAMON_RECLAIM will find cold memory regions in this region +and reclaims. By default, biggest System RAM is used as the region. + +kdamond_pid +----------- + +PID of the DAMON thread. + +If DAMON_RECLAIM is enabled, this becomes the PID of the worker thread. Else, +-1. + +Example +======= + +Below runtime example commands make DAMON_RECLAIM to find memory regions that +not accessed for 30 seconds or more and pages out. The reclamation is limited +to be done only up to 1 GiB per second to avoid DAMON_RECLAIM consuming too +much CPU time for the paging out operation. It also asks DAMON_RECLAIM to do +nothing if the system's free memory rate is more than 50%, but start the real +works if it becomes lower than 40%. If DAMON_RECLAIM doesn't make progress and +therefore the free memory rate becomes lower than 20%, it asks DAMON_RECLAIM to +do nothing again, so that we can fall back to the LRU-list based page +granularity reclamation. :: + + # cd /sys/modules/damon_reclaim/parameters + # echo 30000000 > min_age + # echo $((1 * 1024 * 1024 * 1024)) > quota_sz + # echo 1000 > quota_reset_interval_ms + # echo 500 > wmarks_high + # echo 400 > wmarks_mid + # echo 200 > wmarks_low + # echo Y > enabled + +.. [1] https://research.google/pubs/pub48551/ +.. [2] https://lwn.net/Articles/787611/ +.. [3] https://www.kernel.org/doc/html/latest/vm/free_page_reporting.html From a460a36034bad4403c2c62e04a521bc6987ae5db Mon Sep 17 00:00:00 2001 From: Xin Hao Date: Fri, 5 Nov 2021 13:48:04 -0700 Subject: [PATCH 158/166] mm/damon: remove unnecessary variable initialization Patch series "mm/damon: Fix some small bugs", v4. This patch (of 2): In 'damon_va_apply_three_regions' there is no need to set variable 'i' to zero. Link: https://lkml.kernel.org/r/b7df8d3dad0943a37e01f60c441b1968b2b20354.1634720326.git.xhao@linux.alibaba.com Link: https://lkml.kernel.org/r/cover.1634720326.git.xhao@linux.alibaba.com Signed-off-by: Xin Hao Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/damon/vaddr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index 675cd8c7df9b..35fe49080ee9 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -306,7 +306,7 @@ static void damon_va_apply_three_regions(struct damon_target *t, struct damon_addr_range bregions[3]) { struct damon_region *r, *next; - unsigned int i = 0; + unsigned int i; /* Remove regions which are not in the three big regions now */ damon_for_each_region_safe(r, next, t) { From b5ca3e83ddb05342b1b30700b999cb9b107511f6 Mon Sep 17 00:00:00 2001 From: Xin Hao Date: Fri, 5 Nov 2021 13:48:07 -0700 Subject: [PATCH 159/166] mm/damon/dbgfs: add adaptive_targets list check before enable monitor_on When the ctx->adaptive_targets list is empty, I did some test on monitor_on interface like this. # cat /sys/kernel/debug/damon/target_ids # # echo on > /sys/kernel/debug/damon/monitor_on # damon: kdamond (5390) starts Though the ctx->adaptive_targets list is empty, but the kthread_run still be called, and the kdamond.x thread still be created, this is meaningless. So there adds a judgment in 'dbgfs_monitor_on_write', if the ctx->adaptive_targets list is empty, return -EINVAL. Link: https://lkml.kernel.org/r/0a60a6e8ec9d71989e0848a4dc3311996ca3b5d4.1634720326.git.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 | 1 + mm/damon/core.c | 5 +++++ mm/damon/dbgfs.c | 15 ++++++++++++--- 3 files changed, 18 insertions(+), 3 deletions(-) diff --git a/include/linux/damon.h b/include/linux/damon.h index c93325efddd7..fa7f32614b65 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -440,6 +440,7 @@ void damon_destroy_scheme(struct damos *s); struct damon_target *damon_new_target(unsigned long id); void damon_add_target(struct damon_ctx *ctx, struct damon_target *t); +bool damon_targets_empty(struct damon_ctx *ctx); void damon_free_target(struct damon_target *t); void damon_destroy_target(struct damon_target *t); unsigned int damon_nr_regions(struct damon_target *t); diff --git a/mm/damon/core.c b/mm/damon/core.c index 6993c60ae31c..46a6afea3030 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -180,6 +180,11 @@ void damon_add_target(struct damon_ctx *ctx, struct damon_target *t) list_add_tail(&t->list, &ctx->adaptive_targets); } +bool damon_targets_empty(struct damon_ctx *ctx) +{ + return list_empty(&ctx->adaptive_targets); +} + static void damon_del_target(struct damon_target *t) { list_del(&t->list); diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index 6828e463348b..befb27a29aab 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -878,12 +878,21 @@ static ssize_t dbgfs_monitor_on_write(struct file *file, return -EINVAL; } - if (!strncmp(kbuf, "on", count)) + if (!strncmp(kbuf, "on", count)) { + int i; + + for (i = 0; i < dbgfs_nr_ctxs; i++) { + if (damon_targets_empty(dbgfs_ctxs[i])) { + kfree(kbuf); + return -EINVAL; + } + } ret = damon_start(dbgfs_ctxs, dbgfs_nr_ctxs); - else if (!strncmp(kbuf, "off", count)) + } else if (!strncmp(kbuf, "off", count)) { ret = damon_stop(dbgfs_ctxs, dbgfs_nr_ctxs); - else + } else { ret = -EINVAL; + } if (!ret) ret = count; From 82e3fff55d0010310d3ee9005fec366c9cb3836a Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:48:10 -0700 Subject: [PATCH 160/166] Docs/admin-guide/mm/damon/start: fix wrong example commands Patch series "Fix trivial nits in Documentation/admin-guide/mm". This patchset fixes trivial nits in admin guide documents for DAMON and pagemap. This patch (of 4): Some of the example commands in DAMON getting started guide are outdated, missing sudo, or just wrong. This fixes those. Link: https://lkml.kernel.org/r/20211022090311.3856-2-sj@kernel.org Signed-off-by: SeongJae Park Cc: Jonathan Corbet Cc: Peter Xu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/mm/damon/start.rst | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/Documentation/admin-guide/mm/damon/start.rst b/Documentation/admin-guide/mm/damon/start.rst index 51503cf90ca2..3ad8bbed9b18 100644 --- a/Documentation/admin-guide/mm/damon/start.rst +++ b/Documentation/admin-guide/mm/damon/start.rst @@ -19,7 +19,7 @@ your workload. :: # mount -t debugfs none /sys/kernel/debug/ # git clone https://github.com/awslabs/damo # ./damo/damo record $(pidof ) - # ./damo/damo report heat --plot_ascii + # ./damo/damo report heats --heatmap stdout The final command draws the access heatmap of ````. The heatmap shows which memory region (x-axis) is accessed when (y-axis) and how frequently @@ -94,9 +94,9 @@ Visualizing Recorded Patterns The following three commands visualize the recorded access patterns and save the results as separate image files. :: - $ damo report heats --heatmap access_pattern_heatmap.png - $ damo report wss --range 0 101 1 --plot wss_dist.png - $ damo report wss --range 0 101 1 --sortby time --plot wss_chron_change.png + $ sudo damo report heats --heatmap access_pattern_heatmap.png + $ sudo damo report wss --range 0 101 1 --plot wss_dist.png + $ sudo damo report wss --range 0 101 1 --sortby time --plot wss_chron_change.png - ``access_pattern_heatmap.png`` will visualize the data access pattern in a heatmap, showing which memory region (y-axis) got accessed when (x-axis) @@ -115,9 +115,9 @@ Data Access Pattern Aware Memory Management Below three commands make every memory region of size >=4K that doesn't accessed for >=60 seconds in your workload to be swapped out. :: - $ echo "#min-size max-size min-acc max-acc min-age max-age action" > scheme - $ echo "4K max 0 0 60s max pageout" >> scheme - $ damo schemes -c my_thp_scheme + $ echo "#min-size max-size min-acc max-acc min-age max-age action" > test_scheme + $ echo "4K max 0 0 60s max pageout" >> test_scheme + $ damo schemes -c test_scheme .. [1] https://damonitor.github.io/doc/html/v17/admin-guide/mm/damon/start.html#visualizing-recorded-patterns .. [2] https://damonitor.github.io/test/result/visual/latest/rec.heatmap.1.png.html From 49ce7dee10891c709da769a731a45b42cf7c54f6 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:48:13 -0700 Subject: [PATCH 161/166] Docs/admin-guide/mm/damon/start: fix a wrong link The 'Getting Started' of DAMON is providing a link to DAMON's user interface document while saying about its user space tool's detailed usages. This fixes the link. Link: https://lkml.kernel.org/r/20211022090311.3856-3-sj@kernel.org Signed-off-by: SeongJae Park Cc: Jonathan Corbet Cc: Peter Xu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/mm/damon/start.rst | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/Documentation/admin-guide/mm/damon/start.rst b/Documentation/admin-guide/mm/damon/start.rst index 3ad8bbed9b18..5f3b22cafc76 100644 --- a/Documentation/admin-guide/mm/damon/start.rst +++ b/Documentation/admin-guide/mm/damon/start.rst @@ -6,7 +6,9 @@ Getting Started This document briefly describes how you can use DAMON by demonstrating its default user space tool. Please note that this document describes only a part -of its features for brevity. Please refer to :doc:`usage` for more details. +of its features for brevity. Please refer to the usage `doc +`_ of the tool for more +details. TL; DR From b1eee3c5486003b247127538210f15fd6ebb5ee5 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:48:16 -0700 Subject: [PATCH 162/166] Docs/admin-guide/mm/damon/start: simplify the content Information in 'TL; DR' section of 'Getting Started' is duplicated in other parts of the doc. It is also asking readers to visit the access pattern visualizations gallery web site to show the results of example visualization commands, while the users of the commands can use terminal output. To make the doc simple, this removes the duplicated 'TL; DR' section and replaces the visualization example commands with versions using terminal outputs. Link: https://lkml.kernel.org/r/20211022090311.3856-4-sj@kernel.org Signed-off-by: SeongJae Park Cc: Jonathan Corbet Cc: Peter Xu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/mm/damon/start.rst | 107 ++++++++++--------- 1 file changed, 57 insertions(+), 50 deletions(-) diff --git a/Documentation/admin-guide/mm/damon/start.rst b/Documentation/admin-guide/mm/damon/start.rst index 5f3b22cafc76..4d5ca2c46288 100644 --- a/Documentation/admin-guide/mm/damon/start.rst +++ b/Documentation/admin-guide/mm/damon/start.rst @@ -11,38 +11,6 @@ of its features for brevity. Please refer to the usage `doc details. -TL; DR -====== - -Follow the commands below to monitor and visualize the memory access pattern of -your workload. :: - - # # build the kernel with CONFIG_DAMON_*=y, install it, and reboot - # mount -t debugfs none /sys/kernel/debug/ - # git clone https://github.com/awslabs/damo - # ./damo/damo record $(pidof ) - # ./damo/damo report heats --heatmap stdout - -The final command draws the access heatmap of ````. The heatmap -shows which memory region (x-axis) is accessed when (y-axis) and how frequently -(number; the higher the more accesses have been observed). :: - - 111111111111111111111111111111111111111111111111111111110000 - 111121111111111111111111111111211111111111111111111111110000 - 000000000000000000000000000000000000000000000000001555552000 - 000000000000000000000000000000000000000000000222223555552000 - 000000000000000000000000000000000000000011111677775000000000 - 000000000000000000000000000000000000000488888000000000000000 - 000000000000000000000000000000000177888400000000000000000000 - 000000000000000000000000000046666522222100000000000000000000 - 000000000000000000000014444344444300000000000000000000000000 - 000000000000000002222245555510000000000000000000000000000000 - # access_frequency: 0 1 2 3 4 5 6 7 8 9 - # x-axis: space (140286319947776-140286426374096: 101.496 MiB) - # y-axis: time (605442256436361-605479951866441: 37.695430s) - # resolution: 60x10 (1.692 MiB and 3.770s for each character) - - Prerequisites ============= @@ -93,22 +61,66 @@ pattern in the ``damon.data`` file. Visualizing Recorded Patterns ============================= -The following three commands visualize the recorded access patterns and save -the results as separate image files. :: +You can visualize the pattern in a heatmap, showing which memory region +(x-axis) got accessed when (y-axis) and how frequently (number).:: - $ sudo damo report heats --heatmap access_pattern_heatmap.png - $ sudo damo report wss --range 0 101 1 --plot wss_dist.png - $ sudo damo report wss --range 0 101 1 --sortby time --plot wss_chron_change.png + $ sudo damo report heats --heatmap stdout + 22222222222222222222222222222222222222211111111111111111111111111111111111111100 + 44444444444444444444444444444444444444434444444444444444444444444444444444443200 + 44444444444444444444444444444444444444433444444444444444444444444444444444444200 + 33333333333333333333333333333333333333344555555555555555555555555555555555555200 + 33333333333333333333333333333333333344444444444444444444444444444444444444444200 + 22222222222222222222222222222222222223355555555555555555555555555555555555555200 + 00000000000000000000000000000000000000288888888888888888888888888888888888888400 + 00000000000000000000000000000000000000288888888888888888888888888888888888888400 + 33333333333333333333333333333333333333355555555555555555555555555555555555555200 + 88888888888888888888888888888888888888600000000000000000000000000000000000000000 + 88888888888888888888888888888888888888600000000000000000000000000000000000000000 + 33333333333333333333333333333333333333444444444444444444444444444444444444443200 + 00000000000000000000000000000000000000288888888888888888888888888888888888888400 + [...] + # access_frequency: 0 1 2 3 4 5 6 7 8 9 + # x-axis: space (139728247021568-139728453431248: 196.848 MiB) + # y-axis: time (15256597248362-15326899978162: 1 m 10.303 s) + # resolution: 80x40 (2.461 MiB and 1.758 s for each character) -- ``access_pattern_heatmap.png`` will visualize the data access pattern in a - heatmap, showing which memory region (y-axis) got accessed when (x-axis) - and how frequently (color). -- ``wss_dist.png`` will show the distribution of the working set size. -- ``wss_chron_change.png`` will show how the working set size has - chronologically changed. +You can also visualize the distribution of the working set size, sorted by the +size.:: -You can view the visualizations of this example workload at [1]_. -Visualizations of other realistic workloads are available at [2]_ [3]_ [4]_. + $ sudo damo report wss --range 0 101 10 + # + # target_id 18446632103789443072 + # avr: 107.708 MiB + 0 0 B | | + 10 95.328 MiB |**************************** | + 20 95.332 MiB |**************************** | + 30 95.340 MiB |**************************** | + 40 95.387 MiB |**************************** | + 50 95.387 MiB |**************************** | + 60 95.398 MiB |**************************** | + 70 95.398 MiB |**************************** | + 80 95.504 MiB |**************************** | + 90 190.703 MiB |********************************************************* | + 100 196.875 MiB |***********************************************************| + +Using ``--sortby`` option with the above command, you can show how the working +set size has chronologically changed.:: + + $ sudo damo report wss --range 0 101 10 --sortby time + # + # target_id 18446632103789443072 + # avr: 107.708 MiB + 0 3.051 MiB | | + 10 190.703 MiB |***********************************************************| + 20 95.336 MiB |***************************** | + 30 95.328 MiB |***************************** | + 40 95.387 MiB |***************************** | + 50 95.332 MiB |***************************** | + 60 95.320 MiB |***************************** | + 70 95.398 MiB |***************************** | + 80 95.398 MiB |***************************** | + 90 95.340 MiB |***************************** | + 100 95.398 MiB |***************************** | Data Access Pattern Aware Memory Management @@ -120,8 +132,3 @@ accessed for >=60 seconds in your workload to be swapped out. :: $ echo "#min-size max-size min-acc max-acc min-age max-age action" > test_scheme $ echo "4K max 0 0 60s max pageout" >> test_scheme $ damo schemes -c test_scheme - -.. [1] https://damonitor.github.io/doc/html/v17/admin-guide/mm/damon/start.html#visualizing-recorded-patterns -.. [2] https://damonitor.github.io/test/result/visual/latest/rec.heatmap.1.png.html -.. [3] https://damonitor.github.io/test/result/visual/latest/rec.wss_sz.png.html -.. [4] https://damonitor.github.io/test/result/visual/latest/rec.wss_time.png.html From 0d16cfd46b48689de6a5ca594bc1a68105f6658b Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:48:19 -0700 Subject: [PATCH 163/166] Docs/admin-guide/mm/pagemap: wordsmith page flags descriptions Some descriptions of page flags in 'pagemap.rst' are written in assumption of none-rst, which respects every new line, as below: 7 - SLAB page is managed by the SLAB/SLOB/SLUB/SLQB kernel memory allocator When compound page is used, SLUB/SLQB will only set this flag on the head Because rst ignores the new line between the first sentence and second sentence, resulting html looks a little bit weird, as below. 7 - SLAB page is managed by the SLAB/SLOB/SLUB/SLQB kernel memory allocator When ^ compound page is used, SLUB/SLQB will only set this flag on the head page; SLOB will not flag it at all. This change makes it more natural and consistent with other parts in the rendered version. Link: https://lkml.kernel.org/r/20211022090311.3856-5-sj@kernel.org Signed-off-by: SeongJae Park Cc: Jonathan Corbet Cc: Peter Xu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/mm/pagemap.rst | 53 ++++++++++++------------ 1 file changed, 27 insertions(+), 26 deletions(-) diff --git a/Documentation/admin-guide/mm/pagemap.rst b/Documentation/admin-guide/mm/pagemap.rst index 4581527c07ae..bfc28704856c 100644 --- a/Documentation/admin-guide/mm/pagemap.rst +++ b/Documentation/admin-guide/mm/pagemap.rst @@ -90,13 +90,14 @@ Short descriptions to the page flags ==================================== 0 - LOCKED - page is being locked for exclusive access, e.g. by undergoing read/write IO + The page is being locked for exclusive access, e.g. by undergoing read/write + IO. 7 - SLAB - page is managed by the SLAB/SLOB/SLUB/SLQB kernel memory allocator + The page is managed by the SLAB/SLOB/SLUB/SLQB kernel memory allocator. When compound page is used, SLUB/SLQB will only set this flag on the head page; SLOB will not flag it at all. 10 - BUDDY - a free memory block managed by the buddy system allocator + A free memory block managed by the buddy system allocator. The buddy system organizes free memory in blocks of various orders. An order N block has 2^N physically contiguous pages, with the BUDDY flag set for and _only_ for the first page. @@ -112,65 +113,65 @@ Short descriptions to the page flags 16 - COMPOUND_TAIL A compound page tail (see description above). 17 - HUGE - this is an integral part of a HugeTLB page + This is an integral part of a HugeTLB page. 19 - HWPOISON - hardware detected memory corruption on this page: don't touch the data! + Hardware detected memory corruption on this page: don't touch the data! 20 - NOPAGE - no page frame exists at the requested address + No page frame exists at the requested address. 21 - KSM - identical memory pages dynamically shared between one or more processes + Identical memory pages dynamically shared between one or more processes. 22 - THP - contiguous pages which construct transparent hugepages + Contiguous pages which construct transparent hugepages. 23 - OFFLINE - page is logically offline + The page is logically offline. 24 - ZERO_PAGE - zero page for pfn_zero or huge_zero page + Zero page for pfn_zero or huge_zero page. 25 - IDLE - page has not been accessed since it was marked idle (see + The page has not been accessed since it was marked idle (see :ref:`Documentation/admin-guide/mm/idle_page_tracking.rst `). Note that this flag may be stale in case the page was accessed via a PTE. To make sure the flag is up-to-date one has to read ``/sys/kernel/mm/page_idle/bitmap`` first. 26 - PGTABLE - page is in use as a page table + The page is in use as a page table. IO related page flags --------------------- 1 - ERROR - IO error occurred + IO error occurred. 3 - UPTODATE - page has up-to-date data + The page has up-to-date data. ie. for file backed page: (in-memory data revision >= on-disk one) 4 - DIRTY - page has been written to, hence contains new data + The page has been written to, hence contains new data. i.e. for file backed page: (in-memory data revision > on-disk one) 8 - WRITEBACK - page is being synced to disk + The page is being synced to disk. LRU related page flags ---------------------- 5 - LRU - page is in one of the LRU lists + The page is in one of the LRU lists. 6 - ACTIVE - page is in the active LRU list + The page is in the active LRU list. 18 - UNEVICTABLE - page is in the unevictable (non-)LRU list It is somehow pinned and + The page is in the unevictable (non-)LRU list It is somehow pinned and not a candidate for LRU page reclaims, e.g. ramfs pages, - shmctl(SHM_LOCK) and mlock() memory segments + shmctl(SHM_LOCK) and mlock() memory segments. 2 - REFERENCED - page has been referenced since last LRU list enqueue/requeue + The page has been referenced since last LRU list enqueue/requeue. 9 - RECLAIM - page will be reclaimed soon after its pageout IO completed + The page will be reclaimed soon after its pageout IO completed. 11 - MMAP - a memory mapped page + A memory mapped page. 12 - ANON - a memory mapped page that is not part of a file + A memory mapped page that is not part of a file. 13 - SWAPCACHE - page is mapped to swap space, i.e. has an associated swap entry + The page is mapped to swap space, i.e. has an associated swap entry. 14 - SWAPBACKED - page is backed by swap/RAM + The page is backed by swap/RAM. The page-types tool in the tools/vm directory can be used to query the above flags. From 0f91d13366a402420bf98eaaf393db03946c13e0 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Fri, 5 Nov 2021 13:48:22 -0700 Subject: [PATCH 164/166] mm/damon: simplify stop mechanism A kernel thread can exit gracefully with kthread_stop(). So we don't need a new flag 'kdamond_stop'. And to make sure the task struct is not freed when accessing it, get reference to it before termination. Link: https://lkml.kernel.org/r/20211027130517.4404-1-changbin.du@gmail.com Signed-off-by: Changbin Du Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 1 - mm/damon/core.c | 51 +++++++++++++------------------------------ 2 files changed, 15 insertions(+), 37 deletions(-) diff --git a/include/linux/damon.h b/include/linux/damon.h index fa7f32614b65..321de9d72360 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -381,7 +381,6 @@ struct damon_ctx { /* public: */ struct task_struct *kdamond; - bool kdamond_stop; struct mutex kdamond_lock; struct damon_primitive primitive; diff --git a/mm/damon/core.c b/mm/damon/core.c index 46a6afea3030..f37c17b53814 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -390,17 +390,6 @@ static unsigned long damon_region_sz_limit(struct damon_ctx *ctx) return sz; } -static bool damon_kdamond_running(struct damon_ctx *ctx) -{ - bool running; - - mutex_lock(&ctx->kdamond_lock); - running = ctx->kdamond != NULL; - mutex_unlock(&ctx->kdamond_lock); - - return running; -} - static int kdamond_fn(void *data); /* @@ -418,7 +407,6 @@ static int __damon_start(struct damon_ctx *ctx) mutex_lock(&ctx->kdamond_lock); if (!ctx->kdamond) { err = 0; - ctx->kdamond_stop = false; ctx->kdamond = kthread_run(kdamond_fn, ctx, "kdamond.%d", nr_running_ctxs); if (IS_ERR(ctx->kdamond)) { @@ -474,13 +462,15 @@ int damon_start(struct damon_ctx **ctxs, int nr_ctxs) */ static int __damon_stop(struct damon_ctx *ctx) { + struct task_struct *tsk; + mutex_lock(&ctx->kdamond_lock); - if (ctx->kdamond) { - ctx->kdamond_stop = true; + tsk = ctx->kdamond; + if (tsk) { + get_task_struct(tsk); mutex_unlock(&ctx->kdamond_lock); - while (damon_kdamond_running(ctx)) - usleep_range(ctx->sample_interval, - ctx->sample_interval * 2); + kthread_stop(tsk); + put_task_struct(tsk); return 0; } mutex_unlock(&ctx->kdamond_lock); @@ -925,12 +915,8 @@ static bool kdamond_need_update_primitive(struct damon_ctx *ctx) static bool kdamond_need_stop(struct damon_ctx *ctx) { struct damon_target *t; - bool stop; - mutex_lock(&ctx->kdamond_lock); - stop = ctx->kdamond_stop; - mutex_unlock(&ctx->kdamond_lock); - if (stop) + if (kthread_should_stop()) return true; if (!ctx->primitive.target_valid) @@ -1021,13 +1007,6 @@ static int kdamond_wait_activation(struct damon_ctx *ctx) return -EBUSY; } -static void set_kdamond_stop(struct damon_ctx *ctx) -{ - mutex_lock(&ctx->kdamond_lock); - ctx->kdamond_stop = true; - mutex_unlock(&ctx->kdamond_lock); -} - /* * The monitoring daemon that runs as a kernel thread */ @@ -1038,17 +1017,18 @@ static int kdamond_fn(void *data) struct damon_region *r, *next; unsigned int max_nr_accesses = 0; unsigned long sz_limit = 0; + bool done = false; pr_debug("kdamond (%d) starts\n", current->pid); if (ctx->primitive.init) ctx->primitive.init(ctx); if (ctx->callback.before_start && ctx->callback.before_start(ctx)) - set_kdamond_stop(ctx); + done = true; sz_limit = damon_region_sz_limit(ctx); - while (!kdamond_need_stop(ctx)) { + while (!kdamond_need_stop(ctx) && !done) { if (kdamond_wait_activation(ctx)) continue; @@ -1056,7 +1036,7 @@ static int kdamond_fn(void *data) ctx->primitive.prepare_access_checks(ctx); if (ctx->callback.after_sampling && ctx->callback.after_sampling(ctx)) - set_kdamond_stop(ctx); + done = true; usleep_range(ctx->sample_interval, ctx->sample_interval + 1); @@ -1069,7 +1049,7 @@ static int kdamond_fn(void *data) sz_limit); if (ctx->callback.after_aggregation && ctx->callback.after_aggregation(ctx)) - set_kdamond_stop(ctx); + done = true; kdamond_apply_schemes(ctx); kdamond_reset_aggregated(ctx); kdamond_split_regions(ctx); @@ -1088,9 +1068,8 @@ static int kdamond_fn(void *data) damon_destroy_region(r, t); } - if (ctx->callback.before_terminate && - ctx->callback.before_terminate(ctx)) - set_kdamond_stop(ctx); + if (ctx->callback.before_terminate) + ctx->callback.before_terminate(ctx); if (ctx->primitive.cleanup) ctx->primitive.cleanup(ctx); From 0107865541961ee128149c9873996d32143a74d0 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 5 Nov 2021 13:48:24 -0700 Subject: [PATCH 165/166] mm/damon: fix a few spelling mistakes in comments and a pr_debug message There are a few spelling mistakes in the code. Fix these. Link: https://lkml.kernel.org/r/20211028184157.614544-1-colin.i.king@gmail.com Signed-off-by: Colin Ian King Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/damon/core.c | 2 +- mm/damon/dbgfs-test.h | 2 +- mm/damon/vaddr-test.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/mm/damon/core.c b/mm/damon/core.c index f37c17b53814..c381b3c525d0 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -959,7 +959,7 @@ static unsigned long damos_wmark_wait_us(struct damos *scheme) /* higher than high watermark or lower than low watermark */ if (metric > scheme->wmarks.high || scheme->wmarks.low > metric) { if (scheme->wmarks.activated) - pr_debug("inactivate a scheme (%d) for %s wmark\n", + pr_debug("deactivate a scheme (%d) for %s wmark\n", scheme->action, metric > scheme->wmarks.high ? "high" : "low"); diff --git a/mm/damon/dbgfs-test.h b/mm/damon/dbgfs-test.h index 104b22957616..86b9f9528231 100644 --- a/mm/damon/dbgfs-test.h +++ b/mm/damon/dbgfs-test.h @@ -145,7 +145,7 @@ static void damon_dbgfs_test_set_init_regions(struct kunit *test) KUNIT_EXPECT_STREQ(test, (char *)buf, expect); } - /* Put invlid inputs and check the return error code */ + /* Put invalid inputs and check the return error code */ for (i = 0; i < ARRAY_SIZE(invalid_inputs); i++) { input = invalid_inputs[i]; pr_info("input: %s\n", input); diff --git a/mm/damon/vaddr-test.h b/mm/damon/vaddr-test.h index 1f5c13257dba..ecfd0b2ed222 100644 --- a/mm/damon/vaddr-test.h +++ b/mm/damon/vaddr-test.h @@ -233,7 +233,7 @@ static void damon_test_apply_three_regions3(struct kunit *test) * and 70-100) has totally freed and mapped to different area (30-32 and * 65-68). The target regions which were in the old second and third big * regions should now be removed and new target regions covering the new second - * and third big regions should be crated. + * and third big regions should be created. */ static void damon_test_apply_three_regions4(struct kunit *test) { From 658f9ae761b5965893727dd4edcdad56e5a439bb Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Fri, 5 Nov 2021 13:48:27 -0700 Subject: [PATCH 166/166] mm/damon: remove return value from before_terminate callback Since the return value of 'before_terminate' callback is never used, we make it have no return value. Link: https://lkml.kernel.org/r/20211029005023.8895-1-changbin.du@gmail.com Signed-off-by: Changbin Du Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 2 +- mm/damon/dbgfs.c | 5 ++--- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/include/linux/damon.h b/include/linux/damon.h index 321de9d72360..b4d4be3cc987 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -322,7 +322,7 @@ struct damon_callback { int (*before_start)(struct damon_ctx *context); int (*after_sampling)(struct damon_ctx *context); int (*after_aggregation)(struct damon_ctx *context); - int (*before_terminate)(struct damon_ctx *context); + void (*before_terminate)(struct damon_ctx *context); }; /** diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index befb27a29aab..eccc14b34901 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -645,18 +645,17 @@ static void dbgfs_fill_ctx_dir(struct dentry *dir, struct damon_ctx *ctx) debugfs_create_file(file_names[i], 0600, dir, ctx, fops[i]); } -static int dbgfs_before_terminate(struct damon_ctx *ctx) +static void dbgfs_before_terminate(struct damon_ctx *ctx) { struct damon_target *t, *next; if (!targetid_is_pid(ctx)) - return 0; + return; damon_for_each_target_safe(t, next, ctx) { put_pid((struct pid *)t->id); damon_destroy_target(t); } - return 0; } static struct damon_ctx *dbgfs_new_ctx(void)