From d659b715e94ac039803d7601505d3473393fc0be Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Mon, 15 Jul 2024 10:04:23 +1000 Subject: mm/huge_memory: avoid PMD-size page cache if needed xarray can't support arbitrary page cache size. the largest and supported page cache size is defined as MAX_PAGECACHE_ORDER by commit 099d90642a71 ("mm/filemap: make MAX_PAGECACHE_ORDER acceptable to xarray"). However, it's possible to have 512MB page cache in the huge memory's collapsing path on ARM64 system whose base page size is 64KB. 512MB page cache is breaking the limitation and a warning is raised when the xarray entry is split as shown in the following example. [root@dhcp-10-26-1-207 ~]# cat /proc/1/smaps | grep KernelPageSize KernelPageSize: 64 kB [root@dhcp-10-26-1-207 ~]# cat /tmp/test.c : int main(int argc, char **argv) { const char *filename = TEST_XFS_FILENAME; int fd = 0; void *buf = (void *)-1, *p; int pgsize = getpagesize(); int ret = 0; if (pgsize != 0x10000) { fprintf(stdout, "System with 64KB base page size is required!\n"); return -EPERM; } system("echo 0 > /sys/devices/virtual/bdi/253:0/read_ahead_kb"); system("echo 1 > /proc/sys/vm/drop_caches"); /* Open the xfs file */ fd = open(filename, O_RDONLY); assert(fd > 0); /* Create VMA */ buf = mmap(NULL, TEST_MEM_SIZE, PROT_READ, MAP_SHARED, fd, 0); assert(buf != (void *)-1); fprintf(stdout, "mapped buffer at 0x%p\n", buf); /* Populate VMA */ ret = madvise(buf, TEST_MEM_SIZE, MADV_NOHUGEPAGE); assert(ret == 0); ret = madvise(buf, TEST_MEM_SIZE, MADV_POPULATE_READ); assert(ret == 0); /* Collapse VMA */ ret = madvise(buf, TEST_MEM_SIZE, MADV_HUGEPAGE); assert(ret == 0); ret = madvise(buf, TEST_MEM_SIZE, MADV_COLLAPSE); if (ret) { fprintf(stdout, "Error %d to madvise(MADV_COLLAPSE)\n", errno); goto out; } /* Split xarray entry. Write permission is needed */ munmap(buf, TEST_MEM_SIZE); buf = (void *)-1; close(fd); fd = open(filename, O_RDWR); assert(fd > 0); fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, TEST_MEM_SIZE - pgsize, pgsize); out: if (buf != (void *)-1) munmap(buf, TEST_MEM_SIZE); if (fd > 0) close(fd); return ret; } [root@dhcp-10-26-1-207 ~]# gcc /tmp/test.c -o /tmp/test [root@dhcp-10-26-1-207 ~]# /tmp/test ------------[ cut here ]------------ WARNING: CPU: 25 PID: 7560 at lib/xarray.c:1025 xas_split_alloc+0xf8/0x128 Modules linked in: nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib \ nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct \ nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 \ ip_set rfkill nf_tables nfnetlink vfat fat virtio_balloon drm fuse \ xfs libcrc32c crct10dif_ce ghash_ce sha2_ce sha256_arm64 virtio_net \ sha1_ce net_failover virtio_blk virtio_console failover dimlib virtio_mmio CPU: 25 PID: 7560 Comm: test Kdump: loaded Not tainted 6.10.0-rc7-gavin+ #9 Hardware name: QEMU KVM Virtual Machine, BIOS edk2-20240524-1.el9 05/24/2024 pstate: 83400005 (Nzcv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--) pc : xas_split_alloc+0xf8/0x128 lr : split_huge_page_to_list_to_order+0x1c4/0x780 sp : ffff8000ac32f660 x29: ffff8000ac32f660 x28: ffff0000e0969eb0 x27: ffff8000ac32f6c0 x26: 0000000000000c40 x25: ffff0000e0969eb0 x24: 000000000000000d x23: ffff8000ac32f6c0 x22: ffffffdfc0700000 x21: 0000000000000000 x20: 0000000000000000 x19: ffffffdfc0700000 x18: 0000000000000000 x17: 0000000000000000 x16: ffffd5f3708ffc70 x15: 0000000000000000 x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000000 x11: ffffffffffffffc0 x10: 0000000000000040 x9 : ffffd5f3708e692c x8 : 0000000000000003 x7 : 0000000000000000 x6 : ffff0000e0969eb8 x5 : ffffd5f37289e378 x4 : 0000000000000000 x3 : 0000000000000c40 x2 : 000000000000000d x1 : 000000000000000c x0 : 0000000000000000 Call trace: xas_split_alloc+0xf8/0x128 split_huge_page_to_list_to_order+0x1c4/0x780 truncate_inode_partial_folio+0xdc/0x160 truncate_inode_pages_range+0x1b4/0x4a8 truncate_pagecache_range+0x84/0xa0 xfs_flush_unmap_range+0x70/0x90 [xfs] xfs_file_fallocate+0xfc/0x4d8 [xfs] vfs_fallocate+0x124/0x2f0 ksys_fallocate+0x4c/0xa0 __arm64_sys_fallocate+0x24/0x38 invoke_syscall.constprop.0+0x7c/0xd8 do_el0_svc+0xb4/0xd0 el0_svc+0x44/0x1d8 el0t_64_sync_handler+0x134/0x150 el0t_64_sync+0x17c/0x180 Fix it by correcting the supported page cache orders, different sets for DAX and other files. With it corrected, 512MB page cache becomes disallowed on all non-DAX files on ARM64 system where the base page size is 64KB. After this patch is applied, the test program fails with error -EINVAL returned from __thp_vma_allowable_orders() and the madvise() system call to collapse the page caches. Link: https://lkml.kernel.org/r/20240715000423.316491-1-gshan@redhat.com Fixes: 6b24ca4a1a8d ("mm: Use multi-index entries in the page cache") Signed-off-by: Gavin Shan Acked-by: David Hildenbrand Reviewed-by: Ryan Roberts Acked-by: Zi Yan Cc: Baolin Wang Cc: Barry Song Cc: Don Dutile Cc: Matthew Wilcox (Oracle) Cc: Peter Xu Cc: Ryan Roberts Cc: William Kucharski Cc: [5.17+] Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index cff002be83eb..e25d9ebfdf89 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -74,14 +74,20 @@ extern struct kobj_attribute thpsize_shmem_enabled_attr; #define THP_ORDERS_ALL_ANON ((BIT(PMD_ORDER + 1) - 1) & ~(BIT(0) | BIT(1))) /* - * Mask of all large folio orders supported for file THP. + * Mask of all large folio orders supported for file THP. Folios in a DAX + * file is never split and the MAX_PAGECACHE_ORDER limit does not apply to + * it. */ -#define THP_ORDERS_ALL_FILE (BIT(PMD_ORDER) | BIT(PUD_ORDER)) +#define THP_ORDERS_ALL_FILE_DAX \ + (BIT(PMD_ORDER) | BIT(PUD_ORDER)) +#define THP_ORDERS_ALL_FILE_DEFAULT \ + ((BIT(MAX_PAGECACHE_ORDER + 1) - 1) & ~BIT(0)) /* * Mask of all large folio orders supported for THP. */ -#define THP_ORDERS_ALL (THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE) +#define THP_ORDERS_ALL \ + (THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE_DAX | THP_ORDERS_ALL_FILE_DEFAULT) #define TVA_SMAPS (1 << 0) /* Will be used for procfs */ #define TVA_IN_PF (1 << 1) /* Page fault handler */ -- cgit v1.2.3-70-g09d2 From b3bebe44306e23827397d0d774d206e3fa374041 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Wed, 17 Jul 2024 14:28:44 -0700 Subject: alloc_tag: outline and export free_reserved_page() Outline and export free_reserved_page() because modules use it and it in turn uses page_ext_{get|put} which should not be exported. The same result could be obtained by outlining {get|put}_page_tag_ref() but that would have higher performance impact as these functions are used in more performance critical paths. Link: https://lkml.kernel.org/r/20240717212844.2749975-1-surenb@google.com Fixes: dcfe378c81f7 ("lib: introduce support for page allocation tagging") Signed-off-by: Suren Baghdasaryan Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202407080044.DWMC9N9I-lkp@intel.com/ Suggested-by: Christoph Hellwig Suggested-by: Vlastimil Babka Acked-by: Vlastimil Babka Cc: Kees Cook Cc: Kent Overstreet Cc: Pasha Tatashin Cc: Sourav Panda Cc: [6.10] Signed-off-by: Andrew Morton --- include/linux/mm.h | 16 +--------------- mm/page_alloc.c | 17 +++++++++++++++++ 2 files changed, 18 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 4563b560ced7..c4b238a20b76 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3137,21 +3137,7 @@ extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end, int nid); /* Free the reserved page into the buddy system, so it gets managed. */ -static inline void free_reserved_page(struct page *page) -{ - if (mem_alloc_profiling_enabled()) { - union codetag_ref *ref = get_page_tag_ref(page); - - if (ref) { - set_codetag_empty(ref); - put_page_tag_ref(ref); - } - } - ClearPageReserved(page); - init_page_count(page); - __free_page(page); - adjust_managed_page_count(page, 1); -} +void free_reserved_page(struct page *page); #define free_highmem_page(page) free_reserved_page(page) static inline void mark_page_reserved(struct page *page) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8337926b89d4..7ac8d61148fe 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5815,6 +5815,23 @@ unsigned long free_reserved_area(void *start, void *end, int poison, const char return pages; } +void free_reserved_page(struct page *page) +{ + if (mem_alloc_profiling_enabled()) { + union codetag_ref *ref = get_page_tag_ref(page); + + if (ref) { + set_codetag_empty(ref); + put_page_tag_ref(ref); + } + } + ClearPageReserved(page); + init_page_count(page); + __free_page(page); + adjust_managed_page_count(page, 1); +} +EXPORT_SYMBOL(free_reserved_page); + static int page_alloc_cpu_dead(unsigned int cpu) { struct zone *zone; -- cgit v1.2.3-70-g09d2 From f59adcf5933271ab7247c4c8938c67be8905b725 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 23 Jul 2024 17:12:44 +0000 Subject: mm: memcg: add cacheline padding after lruvec in mem_cgroup_per_node Oliver Sand reported a performance regression caused by commit 98c9daf5ae6b ("mm: memcg: guard memcg1-specific members of struct mem_cgroup_per_node"), which puts some fields of the mem_cgroup_per_node structure under the CONFIG_MEMCG_V1 config option. Apparently it causes a false cache sharing between lruvec and lru_zone_size members of the structure. Fix it by adding an explicit padding after the lruvec member. Even though the padding is not required with CONFIG_MEMCG_V1 set, it seems like the introduced memory overhead is not significant enough to warrant another divergence in the mem_cgroup_per_node layout, so the padding is added unconditionally. Link: https://lkml.kernel.org/r/20240723171244.747521-1-roman.gushchin@linux.dev Fixes: 98c9daf5ae6b ("mm: memcg: guard memcg1-specific members of struct mem_cgroup_per_node") Signed-off-by: Roman Gushchin Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-lkp/202407121335.31a10cb6-oliver.sang@intel.com Tested-by: Oliver Sang Acked-by: Shakeel Butt Cc: Johannes Weiner Cc: Michal Hocko Cc: Muchun Song Cc: Roman Gushchin Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 7e2eb091049a..0e5bf25d324f 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -109,6 +109,7 @@ struct mem_cgroup_per_node { /* Fields which get updated often at the end. */ struct lruvec lruvec; + CACHELINE_PADDING(_pad2_); unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS]; struct mem_cgroup_reclaim_iter iter; }; -- cgit v1.2.3-70-g09d2