From d72520ad004a8ce18a6ba6cde317f0081b27365a Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Sat, 21 Mar 2020 18:22:17 -0700 Subject: page-flags: fix a crash at SetPageError(THP_SWAP) Commit bd4c82c22c36 ("mm, THP, swap: delay splitting THP after swapped out") supported writing THP to a swap device but forgot to upgrade an older commit df8c94d13c7e ("page-flags: define behavior of FS/IO-related flags on compound pages") which could trigger a crash during THP swapping out with DEBUG_VM_PGFLAGS=y, kernel BUG at include/linux/page-flags.h:317! page dumped because: VM_BUG_ON_PAGE(1 && PageCompound(page)) page:fffff3b2ec3a8000 refcount:512 mapcount:0 mapping:000000009eb0338c index:0x7f6e58200 head:fffff3b2ec3a8000 order:9 compound_mapcount:0 compound_pincount:0 anon flags: 0x45fffe0000d8454(uptodate|lru|workingset|owner_priv_1|writeback|head|reclaim|swapbacked) end_swap_bio_write() SetPageError(page) VM_BUG_ON_PAGE(1 && PageCompound(page)) bio_endio+0x297/0x560 dec_pending+0x218/0x430 [dm_mod] clone_endio+0xe4/0x2c0 [dm_mod] bio_endio+0x297/0x560 blk_update_request+0x201/0x920 scsi_end_request+0x6b/0x4b0 scsi_io_completion+0x509/0x7e0 scsi_finish_command+0x1ed/0x2a0 scsi_softirq_done+0x1c9/0x1d0 __blk_mqnterrupt+0xf/0x20 Fix by checking PF_NO_TAIL in those places instead. Fixes: bd4c82c22c36 ("mm, THP, swap: delay splitting THP after swapped out") Signed-off-by: Qian Cai Signed-off-by: Andrew Morton Reviewed-by: David Hildenbrand Acked-by: "Huang, Ying" Acked-by: Rafael Aquini Cc: Link: http://lkml.kernel.org/r/20200310235846.1319-1-cai@lca.pw Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 1bf83c8fcaa7..77de28bfefb0 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -311,7 +311,7 @@ static inline int TestClearPage##uname(struct page *page) { return 0; } __PAGEFLAG(Locked, locked, PF_NO_TAIL) PAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) __CLEARPAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) -PAGEFLAG(Error, error, PF_NO_COMPOUND) TESTCLEARFLAG(Error, error, PF_NO_COMPOUND) +PAGEFLAG(Error, error, PF_NO_TAIL) TESTCLEARFLAG(Error, error, PF_NO_TAIL) PAGEFLAG(Referenced, referenced, PF_HEAD) TESTCLEARFLAG(Referenced, referenced, PF_HEAD) __SETPAGEFLAG(Referenced, referenced, PF_HEAD) -- cgit v1.2.3-59-g8ed1b From 763802b53a427ed3cbd419dbba255c414fdd9e7c Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Sat, 21 Mar 2020 18:22:41 -0700 Subject: x86/mm: split vmalloc_sync_all() Commit 3f8fd02b1bf1 ("mm/vmalloc: Sync unmappings in __purge_vmap_area_lazy()") introduced a call to vmalloc_sync_all() in the vunmap() code-path. While this change was necessary to maintain correctness on x86-32-pae kernels, it also adds additional cycles for architectures that don't need it. Specifically on x86-64 with CONFIG_VMAP_STACK=y some people reported severe performance regressions in micro-benchmarks because it now also calls the x86-64 implementation of vmalloc_sync_all() on vunmap(). But the vmalloc_sync_all() implementation on x86-64 is only needed for newly created mappings. To avoid the unnecessary work on x86-64 and to gain the performance back, split up vmalloc_sync_all() into two functions: * vmalloc_sync_mappings(), and * vmalloc_sync_unmappings() Most call-sites to vmalloc_sync_all() only care about new mappings being synchronized. The only exception is the new call-site added in the above mentioned commit. Shile Zhang directed us to a report of an 80% regression in reaim throughput. Fixes: 3f8fd02b1bf1 ("mm/vmalloc: Sync unmappings in __purge_vmap_area_lazy()") Reported-by: kernel test robot Reported-by: Shile Zhang Signed-off-by: Joerg Roedel Signed-off-by: Andrew Morton Tested-by: Borislav Petkov Acked-by: Rafael J. Wysocki [GHES] Cc: Dave Hansen Cc: Andy Lutomirski Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Link: http://lkml.kernel.org/r/20191009124418.8286-1-joro@8bytes.org Link: https://lists.01.org/hyperkitty/list/lkp@lists.01.org/thread/4D3JPPHBNOSPFK2KEPC6KGKS6J25AIDB/ Link: http://lkml.kernel.org/r/20191113095530.228959-1-shile.zhang@linux.alibaba.com Signed-off-by: Linus Torvalds --- arch/x86/mm/fault.c | 26 ++++++++++++++++++++++++-- drivers/acpi/apei/ghes.c | 2 +- include/linux/vmalloc.h | 5 +++-- kernel/notifier.c | 2 +- mm/nommu.c | 10 +++++++--- mm/vmalloc.c | 11 +++++++---- 6 files changed, 43 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index fa4ea09593ab..629fdf13f846 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -190,7 +190,7 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address) return pmd_k; } -void vmalloc_sync_all(void) +static void vmalloc_sync(void) { unsigned long address; @@ -217,6 +217,16 @@ void vmalloc_sync_all(void) } } +void vmalloc_sync_mappings(void) +{ + vmalloc_sync(); +} + +void vmalloc_sync_unmappings(void) +{ + vmalloc_sync(); +} + /* * 32-bit: * @@ -319,11 +329,23 @@ out: #else /* CONFIG_X86_64: */ -void vmalloc_sync_all(void) +void vmalloc_sync_mappings(void) { + /* + * 64-bit mappings might allocate new p4d/pud pages + * that need to be propagated to all tasks' PGDs. + */ sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END); } +void vmalloc_sync_unmappings(void) +{ + /* + * Unmappings never allocate or free p4d/pud pages. + * No work is required here. + */ +} + /* * 64-bit: * diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 103acbbfcf9a..24c9642e8fc7 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -171,7 +171,7 @@ int ghes_estatus_pool_init(int num_ghes) * New allocation must be visible in all pgd before it can be found by * an NMI allocating from the pool. */ - vmalloc_sync_all(); + vmalloc_sync_mappings(); rc = gen_pool_add(ghes_estatus_pool, addr, PAGE_ALIGN(len), -1); if (rc) diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index ec3813236699..0507a162ccd0 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -141,8 +141,9 @@ extern int remap_vmalloc_range_partial(struct vm_area_struct *vma, extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, unsigned long pgoff); -void vmalloc_sync_all(void); - +void vmalloc_sync_mappings(void); +void vmalloc_sync_unmappings(void); + /* * Lowlevel-APIs (not for driver use!) */ diff --git a/kernel/notifier.c b/kernel/notifier.c index 63d7501ac638..5989bbb93039 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -519,7 +519,7 @@ NOKPROBE_SYMBOL(notify_die); int register_die_notifier(struct notifier_block *nb) { - vmalloc_sync_all(); + vmalloc_sync_mappings(); return atomic_notifier_chain_register(&die_chain, nb); } EXPORT_SYMBOL_GPL(register_die_notifier); diff --git a/mm/nommu.c b/mm/nommu.c index bd2b4e5ef144..318df4e236c9 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -370,10 +370,14 @@ void vm_unmap_aliases(void) EXPORT_SYMBOL_GPL(vm_unmap_aliases); /* - * Implement a stub for vmalloc_sync_all() if the architecture chose not to - * have one. + * Implement a stub for vmalloc_sync_[un]mapping() if the architecture + * chose not to have one. */ -void __weak vmalloc_sync_all(void) +void __weak vmalloc_sync_mappings(void) +{ +} + +void __weak vmalloc_sync_unmappings(void) { } diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 1f46c3b86f9f..6b8eeb0ecee5 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1295,7 +1295,7 @@ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end) * First make sure the mappings are removed from all page-tables * before they are freed. */ - vmalloc_sync_all(); + vmalloc_sync_unmappings(); /* * TODO: to calculate a flush range without looping. @@ -3128,16 +3128,19 @@ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, EXPORT_SYMBOL(remap_vmalloc_range); /* - * Implement a stub for vmalloc_sync_all() if the architecture chose not to - * have one. + * Implement stubs for vmalloc_sync_[un]mappings () if the architecture chose + * not to have one. * * The purpose of this function is to make sure the vmalloc area * mappings are identical in all page-tables in the system. */ -void __weak vmalloc_sync_all(void) +void __weak vmalloc_sync_mappings(void) { } +void __weak vmalloc_sync_unmappings(void) +{ +} static int f(pte_t *pte, unsigned long addr, void *data) { -- cgit v1.2.3-59-g8ed1b