From dc2da7b45ffe954a0090f5d0310ed7b0b37d2bd2 Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Tue, 29 Dec 2020 15:14:37 -0800 Subject: mm: memmap defer init doesn't work as expected VMware observed a performance regression during memmap init on their platform, and bisected to commit 73a6e474cb376 ("mm: memmap_init: iterate over memblock regions rather that check each PFN") causing it. Before the commit: [0.033176] Normal zone: 1445888 pages used for memmap [0.033176] Normal zone: 89391104 pages, LIFO batch:63 [0.035851] ACPI: PM-Timer IO Port: 0x448 With commit [0.026874] Normal zone: 1445888 pages used for memmap [0.026875] Normal zone: 89391104 pages, LIFO batch:63 [2.028450] ACPI: PM-Timer IO Port: 0x448 The root cause is the current memmap defer init doesn't work as expected. Before, memmap_init_zone() was used to do memmap init of one whole zone, to initialize all low zones of one numa node, but defer memmap init of the last zone in that numa node. However, since commit 73a6e474cb376, function memmap_init() is adapted to iterater over memblock regions inside one zone, then call memmap_init_zone() to do memmap init for each region. E.g, on VMware's system, the memory layout is as below, there are two memory regions in node 2. The current code will mistakenly initialize the whole 1st region [mem 0xab00000000-0xfcffffffff], then do memmap defer to iniatialize only one memmory section on the 2nd region [mem 0x10000000000-0x1033fffffff]. In fact, we only expect to see that there's only one memory section's memmap initialized. That's why more time is costed at the time. [ 0.008842] ACPI: SRAT: Node 0 PXM 0 [mem 0x00000000-0x0009ffff] [ 0.008842] ACPI: SRAT: Node 0 PXM 0 [mem 0x00100000-0xbfffffff] [ 0.008843] ACPI: SRAT: Node 0 PXM 0 [mem 0x100000000-0x55ffffffff] [ 0.008844] ACPI: SRAT: Node 1 PXM 1 [mem 0x5600000000-0xaaffffffff] [ 0.008844] ACPI: SRAT: Node 2 PXM 2 [mem 0xab00000000-0xfcffffffff] [ 0.008845] ACPI: SRAT: Node 2 PXM 2 [mem 0x10000000000-0x1033fffffff] Now, let's add a parameter 'zone_end_pfn' to memmap_init_zone() to pass down the real zone end pfn so that defer_init() can use it to judge whether defer need be taken in zone wide. Link: https://lkml.kernel.org/r/20201223080811.16211-1-bhe@redhat.com Link: https://lkml.kernel.org/r/20201223080811.16211-2-bhe@redhat.com Fixes: commit 73a6e474cb376 ("mm: memmap_init: iterate over memblock regions rather that check each PFN") Signed-off-by: Baoquan He Reported-by: Rahul Gopakumar Reviewed-by: Mike Rapoport Cc: David Hildenbrand Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7a2c89b21115..bdbec4c98173 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -423,6 +423,8 @@ defer_init(int nid, unsigned long pfn, unsigned long end_pfn) if (end_pfn < pgdat_end_pfn(NODE_DATA(nid))) return false; + if (NODE_DATA(nid)->first_deferred_pfn != ULONG_MAX) + return true; /* * We start only with one section of pages, more pages are added as * needed until the rest of deferred pages are initialized. @@ -6116,7 +6118,7 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn) * zone stats (e.g., nr_isolate_pageblock) are touched. */ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, - unsigned long start_pfn, + unsigned long start_pfn, unsigned long zone_end_pfn, enum meminit_context context, struct vmem_altmap *altmap, int migratetype) { @@ -6152,7 +6154,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, if (context == MEMINIT_EARLY) { if (overlap_memmap_init(zone, &pfn)) continue; - if (defer_init(nid, pfn, end_pfn)) + if (defer_init(nid, pfn, zone_end_pfn)) break; } @@ -6266,7 +6268,7 @@ void __meminit __weak memmap_init(unsigned long size, int nid, if (end_pfn > start_pfn) { size = end_pfn - start_pfn; - memmap_init_zone(size, nid, zone, start_pfn, + memmap_init_zone(size, nid, zone, start_pfn, range_end_pfn, MEMINIT_EARLY, NULL, MIGRATE_MOVABLE); } } -- cgit v1.2.3 From ce8f86ee94fabcc98537ddccd7e82cfd360a4dc5 Mon Sep 17 00:00:00 2001 From: Hailong liu Date: Tue, 12 Jan 2021 15:49:08 -0800 Subject: mm/page_alloc: add a missing mm_page_alloc_zone_locked() tracepoint The trace point *trace_mm_page_alloc_zone_locked()* in __rmqueue() does not currently cover all branches. Add the missing tracepoint and check the page before do that. [akpm@linux-foundation.org: use IS_ENABLED() to suppress warning] Link: https://lkml.kernel.org/r/20201228132901.41523-1-carver4lio@163.com Signed-off-by: Hailong liu Reviewed-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 31 ++++++++++++++++--------------- 1 file changed, 16 insertions(+), 15 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index bdbec4c98173..027f6481ba59 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2862,20 +2862,20 @@ __rmqueue(struct zone *zone, unsigned int order, int migratetype, { struct page *page; -#ifdef CONFIG_CMA - /* - * Balance movable allocations between regular and CMA areas by - * allocating from CMA when over half of the zone's free memory - * is in the CMA area. - */ - if (alloc_flags & ALLOC_CMA && - zone_page_state(zone, NR_FREE_CMA_PAGES) > - zone_page_state(zone, NR_FREE_PAGES) / 2) { - page = __rmqueue_cma_fallback(zone, order); - if (page) - return page; + if (IS_ENABLED(CONFIG_CMA)) { + /* + * Balance movable allocations between regular and CMA areas by + * allocating from CMA when over half of the zone's free memory + * is in the CMA area. + */ + if (alloc_flags & ALLOC_CMA && + zone_page_state(zone, NR_FREE_CMA_PAGES) > + zone_page_state(zone, NR_FREE_PAGES) / 2) { + page = __rmqueue_cma_fallback(zone, order); + if (page) + goto out; + } } -#endif retry: page = __rmqueue_smallest(zone, order, migratetype); if (unlikely(!page)) { @@ -2886,8 +2886,9 @@ retry: alloc_flags)) goto retry; } - - trace_mm_page_alloc_zone_locked(page, order, migratetype); +out: + if (page) + trace_mm_page_alloc_zone_locked(page, order, migratetype); return page; } -- cgit v1.2.3 From d3921cb8be29ce5668c64e23ffdaeec5f8c69399 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Sat, 23 Jan 2021 21:01:02 -0800 Subject: mm: fix initialization of struct page for holes in memory layout There could be struct pages that are not backed by actual physical memory. This can happen when the actual memory bank is not a multiple of SECTION_SIZE or when an architecture does not register memory holes reserved by the firmware as memblock.memory. Such pages are currently initialized using init_unavailable_mem() function that iterates through PFNs in holes in memblock.memory and if there is a struct page corresponding to a PFN, the fields if this page are set to default values and the page is marked as Reserved. init_unavailable_mem() does not take into account zone and node the page belongs to and sets both zone and node links in struct page to zero. On a system that has firmware reserved holes in a zone above ZONE_DMA, for instance in a configuration below: # grep -A1 E820 /proc/iomem 7a17b000-7a216fff : Unknown E820 type 7a217000-7bffffff : System RAM unset zone link in struct page will trigger VM_BUG_ON_PAGE(!zone_spans_pfn(page_zone(page), pfn), page); because there are pages in both ZONE_DMA32 and ZONE_DMA (unset zone link in struct page) in the same pageblock. Update init_unavailable_mem() to use zone constraints defined by an architecture to properly setup the zone link and use node ID of the adjacent range in memblock.memory to set the node link. Link: https://lkml.kernel.org/r/20210111194017.22696-3-rppt@kernel.org Fixes: 73a6e474cb37 ("mm: memmap_init: iterate over memblock regions rather that check each PFN") Signed-off-by: Mike Rapoport Reported-by: Andrea Arcangeli Cc: Andrea Arcangeli Cc: Baoquan He Cc: Borislav Petkov Cc: David Hildenbrand Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Mel Gorman Cc: Michal Hocko Cc: Qian Cai Cc: Thomas Gleixner Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 84 ++++++++++++++++++++++++++++++++++----------------------- 1 file changed, 50 insertions(+), 34 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 027f6481ba59..85ecaa6d0d06 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -7078,23 +7078,26 @@ void __init free_area_init_memoryless_node(int nid) * Initialize all valid struct pages in the range [spfn, epfn) and mark them * PageReserved(). Return the number of struct pages that were initialized. */ -static u64 __init init_unavailable_range(unsigned long spfn, unsigned long epfn) +static u64 __init init_unavailable_range(unsigned long spfn, unsigned long epfn, + int zone, int nid) { - unsigned long pfn; + unsigned long pfn, zone_spfn, zone_epfn; u64 pgcnt = 0; + zone_spfn = arch_zone_lowest_possible_pfn[zone]; + zone_epfn = arch_zone_highest_possible_pfn[zone]; + + spfn = clamp(spfn, zone_spfn, zone_epfn); + epfn = clamp(epfn, zone_spfn, zone_epfn); + for (pfn = spfn; pfn < epfn; pfn++) { if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) { pfn = ALIGN_DOWN(pfn, pageblock_nr_pages) + pageblock_nr_pages - 1; continue; } - /* - * Use a fake node/zone (0) for now. Some of these pages - * (in memblock.reserved but not in memblock.memory) will - * get re-initialized via reserve_bootmem_region() later. - */ - __init_single_page(pfn_to_page(pfn), pfn, 0, 0); + + __init_single_page(pfn_to_page(pfn), pfn, zone, nid); __SetPageReserved(pfn_to_page(pfn)); pgcnt++; } @@ -7103,51 +7106,64 @@ static u64 __init init_unavailable_range(unsigned long spfn, unsigned long epfn) } /* - * Only struct pages that are backed by physical memory are zeroed and - * initialized by going through __init_single_page(). But, there are some - * struct pages which are reserved in memblock allocator and their fields - * may be accessed (for example page_to_pfn() on some configuration accesses - * flags). We must explicitly initialize those struct pages. + * Only struct pages that correspond to ranges defined by memblock.memory + * are zeroed and initialized by going through __init_single_page() during + * memmap_init(). + * + * But, there could be struct pages that correspond to holes in + * memblock.memory. This can happen because of the following reasons: + * - phyiscal memory bank size is not necessarily the exact multiple of the + * arbitrary section size + * - early reserved memory may not be listed in memblock.memory + * - memory layouts defined with memmap= kernel parameter may not align + * nicely with memmap sections * - * This function also addresses a similar issue where struct pages are left - * uninitialized because the physical address range is not covered by - * memblock.memory or memblock.reserved. That could happen when memblock - * layout is manually configured via memmap=, or when the highest physical - * address (max_pfn) does not end on a section boundary. + * Explicitly initialize those struct pages so that: + * - PG_Reserved is set + * - zone link is set accorging to the architecture constrains + * - node is set to node id of the next populated region except for the + * trailing hole where last node id is used */ -static void __init init_unavailable_mem(void) +static void __init init_zone_unavailable_mem(int zone) { - phys_addr_t start, end; - u64 i, pgcnt; - phys_addr_t next = 0; + unsigned long start, end; + int i, nid; + u64 pgcnt; + unsigned long next = 0; /* - * Loop through unavailable ranges not covered by memblock.memory. + * Loop through holes in memblock.memory and initialize struct + * pages corresponding to these holes */ pgcnt = 0; - for_each_mem_range(i, &start, &end) { + for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, &nid) { if (next < start) - pgcnt += init_unavailable_range(PFN_DOWN(next), - PFN_UP(start)); + pgcnt += init_unavailable_range(next, start, zone, nid); next = end; } /* - * Early sections always have a fully populated memmap for the whole - * section - see pfn_valid(). If the last section has holes at the - * end and that section is marked "online", the memmap will be - * considered initialized. Make sure that memmap has a well defined - * state. + * Last section may surpass the actual end of memory (e.g. we can + * have 1Gb section and 512Mb of RAM pouplated). + * Make sure that memmap has a well defined state in this case. */ - pgcnt += init_unavailable_range(PFN_DOWN(next), - round_up(max_pfn, PAGES_PER_SECTION)); + end = round_up(max_pfn, PAGES_PER_SECTION); + pgcnt += init_unavailable_range(next, end, zone, nid); /* * Struct pages that do not have backing memory. This could be because * firmware is using some of this memory, or for some other reasons. */ if (pgcnt) - pr_info("Zeroed struct page in unavailable ranges: %lld pages", pgcnt); + pr_info("Zone %s: zeroed struct page in unavailable ranges: %lld pages", zone_names[zone], pgcnt); +} + +static void __init init_unavailable_mem(void) +{ + int zone; + + for (zone = 0; zone < ZONE_MOVABLE; zone++) + init_zone_unavailable_mem(zone); } #else static inline void __init init_unavailable_mem(void) -- cgit v1.2.3 From acb35b177c71d3d39b9a3b9ea213d926235066e3 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Sat, 23 Jan 2021 21:01:43 -0800 Subject: kasan, mm: fix resetting page_alloc tags for HW_TAGS A previous commit added resetting KASAN page tags to kernel_init_free_pages() to avoid false-positives due to accesses to metadata with the hardware tag-based mode. That commit did reset page tags before the metadata access, but didn't restore them after. As the result, KASAN fails to detect bad accesses to page_alloc allocations on some configurations. Fix this by recovering the tag after the metadata access. Link: https://lkml.kernel.org/r/02b5bcd692e912c27d484030f666b350ad7e4ae4.1611074450.git.andreyknvl@google.com Fixes: aa1ef4d7b3f6 ("kasan, mm: reset tags when accessing metadata") Signed-off-by: Andrey Konovalov Cc: Dmitry Vyukov Cc: Alexander Potapenko Cc: Marco Elver Cc: Catalin Marinas Cc: Will Deacon Cc: Vincenzo Frascino Cc: Andrey Ryabinin Cc: Peter Collingbourne Cc: Evgenii Stepanov Cc: Branislav Rankov Cc: Kevin Brodsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 85ecaa6d0d06..783913e41f65 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1207,8 +1207,10 @@ static void kernel_init_free_pages(struct page *page, int numpages) /* s390's use of memset() could override KASAN redzones. */ kasan_disable_current(); for (i = 0; i < numpages; i++) { + u8 tag = page_kasan_tag(page + i); page_kasan_tag_reset(page + i); clear_highpage(page + i); + page_kasan_tag_set(page + i, tag); } kasan_enable_current(); } -- cgit v1.2.3