- Linux-stable-mirror - lists.linaro.org

[failures] zboot-fix-stack-protector-in-compressed-boot-phase.patch removed from -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: zboot: fix stack protector in compressed boot phase has been removed from the -mm tree. Its filename was zboot-fix-stack-protector-in-compressed-boot-phase.patch This patch was dropped because it had testing failures ------------------------------------------------------ From: Huacai Chen <chenhc(a)lemote.com> Subject: zboot: fix stack protector in compressed boot phase Calling __stack_chk_guard_setup() in decompress_kernel() is too late, so stack checking always fails for decompress_kernel() itself. So remove __stack_chk_guard_setup() and initialize __stack_chk_guard before we call decompress_kernel(). Original code comes from ARM but also used for MIPS and SH, so fix them together. If without this fix, compressed booting of these archs will fail because stack checking is enabled by default (>=4.16). Link: http://lkml.kernel.org/r/1521186916-13745-1-git-send-email-chenhc@lemote.com Signed-off-by: Huacai Chen <chenhc(a)lemote.com> Cc: Ralf Baechle <ralf(a)linux-mips.org> Cc: James Hogan <james.hogan(a)mips.com> Cc: Russell King <linux(a)arm.linux.org.uk> Cc: Yoshinori Sato <ysato(a)users.sourceforge.jp> Cc: Rich Felker <dalias(a)libc.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- arch/arm/boot/compressed/head.S | 4 ++++ arch/arm/boot/compressed/misc.c | 7 ------- arch/mips/boot/compressed/decompress.c | 7 ------- arch/mips/boot/compressed/head.S | 4 ++++ arch/sh/boot/compressed/head_32.S | 8 ++++++++ arch/sh/boot/compressed/head_64.S | 4 ++++ arch/sh/boot/compressed/misc.c | 7 ------- 7 files changed, 20 insertions(+), 21 deletions(-) diff -puN arch/arm/boot/compressed/head.S~zboot-fix-stack-protector-in-compressed-boot-phase arch/arm/boot/compressed/head.S --- a/arch/arm/boot/compressed/head.S~zboot-fix-stack-protector-in-compressed-boot-phase +++ a/arch/arm/boot/compressed/head.S @@ -547,6 +547,10 @@ not_relocated: mov r0, #0 bic r4, r4, #1 blne cache_on + ldr r0, =__stack_chk_guard + ldr r1, =0x000a0dff + str r1, [r0] + /* * The C runtime environment should now be setup sufficiently. * Set up some pointers, and start decompressing. diff -puN arch/arm/boot/compressed/misc.c~zboot-fix-stack-protector-in-compressed-boot-phase arch/arm/boot/compressed/misc.c --- a/arch/arm/boot/compressed/misc.c~zboot-fix-stack-protector-in-compressed-boot-phase +++ a/arch/arm/boot/compressed/misc.c @@ -130,11 +130,6 @@ asmlinkage void __div0(void) unsigned long __stack_chk_guard; -void __stack_chk_guard_setup(void) -{ - __stack_chk_guard = 0x000a0dff; -} - void __stack_chk_fail(void) { error("stack-protector: Kernel stack is corrupted\n"); @@ -150,8 +145,6 @@ decompress_kernel(unsigned long output_s { int ret; - __stack_chk_guard_setup(); - output_data = (unsigned char *)output_start; free_mem_ptr = free_mem_ptr_p; free_mem_end_ptr = free_mem_ptr_end_p; diff -puN arch/mips/boot/compressed/decompress.c~zboot-fix-stack-protector-in-compressed-boot-phase arch/mips/boot/compressed/decompress.c --- a/arch/mips/boot/compressed/decompress.c~zboot-fix-stack-protector-in-compressed-boot-phase +++ a/arch/mips/boot/compressed/decompress.c @@ -78,11 +78,6 @@ void error(char *x) unsigned long __stack_chk_guard; -void __stack_chk_guard_setup(void) -{ - __stack_chk_guard = 0x000a0dff; -} - void __stack_chk_fail(void) { error("stack-protector: Kernel stack is corrupted\n"); @@ -92,8 +87,6 @@ void decompress_kernel(unsigned long boo { unsigned long zimage_start, zimage_size; - __stack_chk_guard_setup(); - zimage_start = (unsigned long)(&__image_begin); zimage_size = (unsigned long)(&__image_end) - (unsigned long)(&__image_begin); diff -puN arch/mips/boot/compressed/head.S~zboot-fix-stack-protector-in-compressed-boot-phase arch/mips/boot/compressed/head.S --- a/arch/mips/boot/compressed/head.S~zboot-fix-stack-protector-in-compressed-boot-phase +++ a/arch/mips/boot/compressed/head.S @@ -32,6 +32,10 @@ start: bne a2, a0, 1b addiu a0, a0, 4 + PTR_LA a0, __stack_chk_guard + PTR_LI a1, 0x000a0dff + sw a1, 0(a0) + PTR_LA a0, (.heap) /* heap address */ PTR_LA sp, (.stack + 8192) /* stack address */ diff -puN arch/sh/boot/compressed/head_32.S~zboot-fix-stack-protector-in-compressed-boot-phase arch/sh/boot/compressed/head_32.S --- a/arch/sh/boot/compressed/head_32.S~zboot-fix-stack-protector-in-compressed-boot-phase +++ a/arch/sh/boot/compressed/head_32.S @@ -76,6 +76,10 @@ l1: mov.l init_stack_addr, r0 mov.l @r0, r15 + mov.l __stack_chk_guard_addr, r0 + mov.l __stack_chk_guard_val, r1 + mov.l r1, @r0 + /* Decompress the kernel */ mov.l decompress_kernel_addr, r0 jsr @r0 @@ -97,6 +101,10 @@ kexec_magic: .long 0x400000F0 /* magic used by kexec to parse zImage format */ init_stack_addr: .long stack_start +__stack_chk_guard_val: + .long 0x000A0DFF +__stack_chk_guard_addr: + .long __stack_chk_guard decompress_kernel_addr: .long decompress_kernel kernel_start_addr: diff -puN arch/sh/boot/compressed/head_64.S~zboot-fix-stack-protector-in-compressed-boot-phase arch/sh/boot/compressed/head_64.S --- a/arch/sh/boot/compressed/head_64.S~zboot-fix-stack-protector-in-compressed-boot-phase +++ a/arch/sh/boot/compressed/head_64.S @@ -132,6 +132,10 @@ startup: addi r22, 4, r22 bne r22, r23, tr1 + movi datalabel __stack_chk_guard, r0 + movi 0x000a0dff, r1 + st.l r0, 0, r1 + /* * Decompress the kernel. */ diff -puN arch/sh/boot/compressed/misc.c~zboot-fix-stack-protector-in-compressed-boot-phase arch/sh/boot/compressed/misc.c --- a/arch/sh/boot/compressed/misc.c~zboot-fix-stack-protector-in-compressed-boot-phase +++ a/arch/sh/boot/compressed/misc.c @@ -106,11 +106,6 @@ static void error(char *x) unsigned long __stack_chk_guard; -void __stack_chk_guard_setup(void) -{ - __stack_chk_guard = 0x000a0dff; -} - void __stack_chk_fail(void) { error("stack-protector: Kernel stack is corrupted\n"); @@ -130,8 +125,6 @@ void decompress_kernel(void) { unsigned long output_addr; - __stack_chk_guard_setup(); - #ifdef CONFIG_SUPERH64 output_addr = (CONFIG_MEMORY_START + 0x2000); #else _ Patches currently in -mm which might be from chenhc(a)lemote.com are

7 years, 5 months

1
0
0 0

[merged] mm-vmscan-wake-up-flushers-for-legacy-cgroups-too.patch removed from -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: mm/vmscan: wake up flushers for legacy cgroups too has been removed from the -mm tree. Its filename was mm-vmscan-wake-up-flushers-for-legacy-cgroups-too.patch This patch was dropped because it was merged into mainline or a subsystem tree ------------------------------------------------------ From: Andrey Ryabinin <aryabinin(a)virtuozzo.com> Subject: mm/vmscan: wake up flushers for legacy cgroups too Commit 726d061fbd36 ("mm: vmscan: kick flushers when we encounter dirty pages on the LRU") added flusher invocation to shrink_inactive_list() when many dirty pages on the LRU are encountered. However, shrink_inactive_list() doesn't wake up flushers for legacy cgroup reclaim, so the next commit bbef938429f5 ("mm: vmscan: remove old flusher wakeup from direct reclaim path") removed the only source of flusher's wake up in legacy mem cgroup reclaim path. This leads to premature OOM if there is too many dirty pages in cgroup: # mkdir /sys/fs/cgroup/memory/test # echo $$ > /sys/fs/cgroup/memory/test/tasks # echo 50M > /sys/fs/cgroup/memory/test/memory.limit_in_bytes # dd if=/dev/zero of=tmp_file bs=1M count=100 Killed dd invoked oom-killer: gfp_mask=0x14000c0(GFP_KERNEL), nodemask=(null), order=0, oom_score_adj=0 Call Trace: dump_stack+0x46/0x65 dump_header+0x6b/0x2ac oom_kill_process+0x21c/0x4a0 out_of_memory+0x2a5/0x4b0 mem_cgroup_out_of_memory+0x3b/0x60 mem_cgroup_oom_synchronize+0x2ed/0x330 pagefault_out_of_memory+0x24/0x54 __do_page_fault+0x521/0x540 page_fault+0x45/0x50 Task in /test killed as a result of limit of /test memory: usage 51200kB, limit 51200kB, failcnt 73 memory+swap: usage 51200kB, limit 9007199254740988kB, failcnt 0 kmem: usage 296kB, limit 9007199254740988kB, failcnt 0 Memory cgroup stats for /test: cache:49632KB rss:1056KB rss_huge:0KB shmem:0KB mapped_file:0KB dirty:49500KB writeback:0KB swap:0KB inactive_anon:0KB active_anon:1168KB inactive_file:24760KB active_file:24960KB unevictable:0KB Memory cgroup out of memory: Kill process 3861 (bash) score 88 or sacrifice child Killed process 3876 (dd) total-vm:8484kB, anon-rss:1052kB, file-rss:1720kB, shmem-rss:0kB oom_reaper: reaped process 3876 (dd), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB Wake up flushers in legacy cgroup reclaim too. Link: http://lkml.kernel.org/r/20180315164553.17856-1-aryabinin@virtuozzo.com Fixes: bbef938429f5 ("mm: vmscan: remove old flusher wakeup from direct reclaim path") Signed-off-by: Andrey Ryabinin <aryabinin(a)virtuozzo.com> Tested-by: Shakeel Butt <shakeelb(a)google.com> Acked-by: Michal Hocko <mhocko(a)suse.cz> Cc: Mel Gorman <mgorman(a)techsingularity.net> Cc: Tejun Heo <tj(a)kernel.org> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/vmscan.c | 31 ++++++++++++++++--------------- 1 file changed, 16 insertions(+), 15 deletions(-) diff -puN mm/vmscan.c~mm-vmscan-wake-up-flushers-for-legacy-cgroups-too mm/vmscan.c --- a/mm/vmscan.c~mm-vmscan-wake-up-flushers-for-legacy-cgroups-too +++ a/mm/vmscan.c @@ -1780,6 +1780,20 @@ shrink_inactive_list(unsigned long nr_to set_bit(PGDAT_WRITEBACK, &pgdat->flags); /* + * If dirty pages are scanned that are not queued for IO, it + * implies that flushers are not doing their job. This can + * happen when memory pressure pushes dirty pages to the end of + * the LRU before the dirty limits are breached and the dirty + * data has expired. It can also happen when the proportion of + * dirty pages grows not through writes but through memory + * pressure reclaiming all the clean cache. And in some cases, + * the flushers simply cannot keep up with the allocation + * rate. Nudge the flusher threads in case they are asleep. + */ + if (stat.nr_unqueued_dirty == nr_taken) + wakeup_flusher_threads(WB_REASON_VMSCAN); + + /* * Legacy memcg will stall in page writeback so avoid forcibly * stalling here. */ @@ -1791,22 +1805,9 @@ shrink_inactive_list(unsigned long nr_to if (stat.nr_dirty && stat.nr_dirty == stat.nr_congested) set_bit(PGDAT_CONGESTED, &pgdat->flags); - /* - * If dirty pages are scanned that are not queued for IO, it - * implies that flushers are not doing their job. This can - * happen when memory pressure pushes dirty pages to the end of - * the LRU before the dirty limits are breached and the dirty - * data has expired. It can also happen when the proportion of - * dirty pages grows not through writes but through memory - * pressure reclaiming all the clean cache. And in some cases, - * the flushers simply cannot keep up with the allocation - * rate. Nudge the flusher threads in case they are asleep, but - * also allow kswapd to start writing pages during reclaim. - */ - if (stat.nr_unqueued_dirty == nr_taken) { - wakeup_flusher_threads(WB_REASON_VMSCAN); + /* Allow kswapd to start writing pages during reclaim. */ + if (stat.nr_unqueued_dirty == nr_taken) set_bit(PGDAT_DIRTY, &pgdat->flags); - } /* * If kswapd scans pages marked marked for immediate _ Patches currently in -mm which might be from aryabinin(a)virtuozzo.com are mm-vmscan-update-stale-comments.patch mm-vmscan-replace-mm_vmscan_lru_shrink_inactive-with-shrink_page_list-tracepoint.patch mm-vmscan-remove-redundant-current_may_throttle-check.patch mm-vmscan-dont-change-pgdat-state-on-base-of-a-single-lru-list-state.patch mm-vmscan-dont-mess-with-pgdat-flags-in-memcg-reclaim.patch mm-kasan-dont-vfree-nonexistent-vm_area.patch

7 years, 5 months

1
0
0 0

[merged] revert-mm-page_alloc-skip-over-regions-of-invalid-pfns-where-possible.patch removed from -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: Revert "mm: page_alloc: skip over regions of invalid pfns where possible" has been removed from the -mm tree. Its filename was revert-mm-page_alloc-skip-over-regions-of-invalid-pfns-where-possible.patch This patch was dropped because it was merged into mainline or a subsystem tree ------------------------------------------------------ From: Daniel Vacek <neelx(a)redhat.com> Subject: Revert "mm: page_alloc: skip over regions of invalid pfns where possible" This reverts b92df1de5d289c0b ("mm: page_alloc: skip over regions of invalid pfns where possible"). The commit is meant to be a boot init speed up skipping the loop in memmap_init_zone() for invalid pfns. But given some specific memory mapping on x86_64 (or more generally theoretically anywhere but on arm with CONFIG_HAVE_ARCH_PFN_VALID) the implementation also skips valid pfns which is plain wrong and causes 'kernel BUG at mm/page_alloc.c:1389!' crash> log | grep -e BUG -e RIP -e Call.Trace -e move_freepages_block -e rmqueue -e freelist -A1 kernel BUG at mm/page_alloc.c:1389! invalid opcode: 0000 [#1] SMP -- RIP: 0010:[<ffffffff8118833e>] [<ffffffff8118833e>] move_freepages+0x15e/0x160 RSP: 0018:ffff88054d727688 EFLAGS: 00010087 -- Call Trace: [<ffffffff811883b3>] move_freepages_block+0x73/0x80 [<ffffffff81189e63>] __rmqueue+0x263/0x460 [<ffffffff8118c781>] get_page_from_freelist+0x7e1/0x9e0 [<ffffffff8118caf6>] __alloc_pages_nodemask+0x176/0x420 -- RIP [<ffffffff8118833e>] move_freepages+0x15e/0x160 RSP <ffff88054d727688> crash> page_init_bug -v | grep RAM <struct resource 0xffff88067fffd2f8> 1000 - 9bfff System RAM (620.00 KiB) <struct resource 0xffff88067fffd3a0> 100000 - 430bffff System RAM ( 1.05 GiB = 1071.75 MiB = 1097472.00 KiB) <struct resource 0xffff88067fffd410> 4b0c8000 - 4bf9cfff System RAM ( 14.83 MiB = 15188.00 KiB) <struct resource 0xffff88067fffd480> 4bfac000 - 646b1fff System RAM (391.02 MiB = 400408.00 KiB) <struct resource 0xffff88067fffd560> 7b788000 - 7b7fffff System RAM (480.00 KiB) <struct resource 0xffff88067fffd640> 100000000 - 67fffffff System RAM ( 22.00 GiB) crash> page_init_bug | head -6 <struct resource 0xffff88067fffd560> 7b788000 - 7b7fffff System RAM (480.00 KiB) <struct page 0xffffea0001ede200> 1fffff00000000 0 <struct pglist_data 0xffff88047ffd9000> 1 <struct zone 0xffff88047ffd9800> DMA32 4096 1048575 <struct page 0xffffea0001ede200> 505736 505344 <struct page 0xffffea0001ed8000> 505855 <struct page 0xffffea0001edffc0> <struct page 0xffffea0001ed8000> 0 0 <struct pglist_data 0xffff88047ffd9000> 0 <struct zone 0xffff88047ffd9000> DMA 1 4095 <struct page 0xffffea0001edffc0> 1fffff00000400 0 <struct pglist_data 0xffff88047ffd9000> 1 <struct zone 0xffff88047ffd9800> DMA32 4096 1048575 BUG, zones differ! crash> kmem -p 77fff000 78000000 7b5ff000 7b600000 7b787000 7b788000 PAGE PHYSICAL MAPPING INDEX CNT FLAGS ffffea0001e00000 78000000 0 0 0 0 ffffea0001ed7fc0 7b5ff000 0 0 0 0 ffffea0001ed8000 7b600000 0 0 0 0 <<<< ffffea0001ede1c0 7b787000 0 0 0 0 ffffea0001ede200 7b788000 0 0 1 1fffff00000000 Link: http://lkml.kernel.org/r/20180316143855.29838-1-neelx@redhat.com Fixes: b92df1de5d28 ("mm: page_alloc: skip over regions of invalid pfns where possible") Signed-off-by: Daniel Vacek <neelx(a)redhat.com> Acked-by: Ard Biesheuvel <ard.biesheuvel(a)linaro.org> Acked-by: Michal Hocko <mhocko(a)suse.com> Reviewed-by: Andrew Morton <akpm(a)linux-foundation.org> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: Mel Gorman <mgorman(a)techsingularity.net> Cc: Pavel Tatashin <pasha.tatashin(a)oracle.com> Cc: Paul Burton <paul.burton(a)imgtec.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/memblock.h | 1 - mm/memblock.c | 28 ---------------------------- mm/page_alloc.c | 11 +---------- 3 files changed, 1 insertion(+), 39 deletions(-) diff -puN include/linux/memblock.h~revert-mm-page_alloc-skip-over-regions-of-invalid-pfns-where-possible include/linux/memblock.h --- a/include/linux/memblock.h~revert-mm-page_alloc-skip-over-regions-of-invalid-pfns-where-possible +++ a/include/linux/memblock.h @@ -187,7 +187,6 @@ int memblock_search_pfn_nid(unsigned lon unsigned long *end_pfn); void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, unsigned long *out_end_pfn, int *out_nid); -unsigned long memblock_next_valid_pfn(unsigned long pfn, unsigned long max_pfn); /** * for_each_mem_pfn_range - early memory pfn range iterator diff -puN mm/memblock.c~revert-mm-page_alloc-skip-over-regions-of-invalid-pfns-where-possible mm/memblock.c --- a/mm/memblock.c~revert-mm-page_alloc-skip-over-regions-of-invalid-pfns-where-possible +++ a/mm/memblock.c @@ -1101,34 +1101,6 @@ void __init_memblock __next_mem_pfn_rang *out_nid = r->nid; } -unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn, - unsigned long max_pfn) -{ - struct memblock_type *type = &memblock.memory; - unsigned int right = type->cnt; - unsigned int mid, left = 0; - phys_addr_t addr = PFN_PHYS(++pfn); - - do { - mid = (right + left) / 2; - - if (addr < type->regions[mid].base) - right = mid; - else if (addr >= (type->regions[mid].base + - type->regions[mid].size)) - left = mid + 1; - else { - /* addr is within the region, so pfn is valid */ - return pfn; - } - } while (left < right); - - if (right == type->cnt) - return -1UL; - else - return PHYS_PFN(type->regions[right].base); -} - /** * memblock_set_node - set node ID on memblock regions * @base: base of area to set node ID for diff -puN mm/page_alloc.c~revert-mm-page_alloc-skip-over-regions-of-invalid-pfns-where-possible mm/page_alloc.c --- a/mm/page_alloc.c~revert-mm-page_alloc-skip-over-regions-of-invalid-pfns-where-possible +++ a/mm/page_alloc.c @@ -5356,17 +5356,8 @@ void __meminit memmap_init_zone(unsigned if (context != MEMMAP_EARLY) goto not_early; - if (!early_pfn_valid(pfn)) { -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP - /* - * Skip to the pfn preceding the next valid one (or - * end_pfn), such that we hit a valid pfn (or end_pfn) - * on our next iteration of the loop. - */ - pfn = memblock_next_valid_pfn(pfn, end_pfn) - 1; -#endif + if (!early_pfn_valid(pfn)) continue; - } if (!early_pfn_in_nid(pfn, nid)) continue; if (!update_defer_init(pgdat, pfn, end_pfn, &nr_initialised)) _ Patches currently in -mm which might be from neelx(a)redhat.com are

7 years, 5 months

1
0
0 0

[merged] mm-shmem-do-not-wait-for-lock_page-in-shmem_unused_huge_shrink.patch removed from -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: mm/shmem: do not wait for lock_page() in shmem_unused_huge_shrink() has been removed from the -mm tree. Its filename was mm-shmem-do-not-wait-for-lock_page-in-shmem_unused_huge_shrink.patch This patch was dropped because it was merged into mainline or a subsystem tree ------------------------------------------------------ From: "Kirill A. Shutemov" <kirill.shutemov(a)linux.intel.com> Subject: mm/shmem: do not wait for lock_page() in shmem_unused_huge_shrink() shmem_unused_huge_shrink() gets called from reclaim path. Waiting for page lock may lead to deadlock there. There was a bug report that may be attributed to this: http://lkml.kernel.org/r/alpine.LRH.2.11.1801242349220.30642@mail.ewheeler.… Replace lock_page() with trylock_page() and skip the page if we failed to lock it. We will get to the page on the next scan. We can test for the PageTransHuge() outside the page lock as we only need protection against splitting the page under us. Holding pin oni the page is enough for this. Link: http://lkml.kernel.org/r/20180316210830.43738-1-kirill.shutemov@linux.intel… Fixes: 779750d20b93 ("shmem: split huge pages beyond i_size under memory pressure") Signed-off-by: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com> Reported-by: Eric Wheeler <linux-mm(a)lists.ewheeler.net> Acked-by: Michal Hocko <mhocko(a)suse.com> Reviewed-by: Andrew Morton <akpm(a)linux-foundation.org> Cc: Tetsuo Handa <penguin-kernel(a)I-love.SAKURA.ne.jp> Cc: Hugh Dickins <hughd(a)google.com> Cc: <stable(a)vger.kernel.org> [4.8+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/shmem.c | 31 ++++++++++++++++++++----------- 1 file changed, 20 insertions(+), 11 deletions(-) diff -puN mm/shmem.c~mm-shmem-do-not-wait-for-lock_page-in-shmem_unused_huge_shrink mm/shmem.c --- a/mm/shmem.c~mm-shmem-do-not-wait-for-lock_page-in-shmem_unused_huge_shrink +++ a/mm/shmem.c @@ -493,36 +493,45 @@ next: info = list_entry(pos, struct shmem_inode_info, shrinklist); inode = &info->vfs_inode; - if (nr_to_split && split >= nr_to_split) { - iput(inode); - continue; - } + if (nr_to_split && split >= nr_to_split) + goto leave; - page = find_lock_page(inode->i_mapping, + page = find_get_page(inode->i_mapping, (inode->i_size & HPAGE_PMD_MASK) >> PAGE_SHIFT); if (!page) goto drop; + /* No huge page at the end of the file: nothing to split */ if (!PageTransHuge(page)) { - unlock_page(page); put_page(page); goto drop; } + /* + * Leave the inode on the list if we failed to lock + * the page at this time. + * + * Waiting for the lock may lead to deadlock in the + * reclaim path. + */ + if (!trylock_page(page)) { + put_page(page); + goto leave; + } + ret = split_huge_page(page); unlock_page(page); put_page(page); - if (ret) { - /* split failed: leave it on the list */ - iput(inode); - continue; - } + /* If split failed leave the inode on the list */ + if (ret) + goto leave; split++; drop: list_del_init(&info->shrinklist); removed++; +leave: iput(inode); } _ Patches currently in -mm which might be from kirill.shutemov(a)linux.intel.com are

7 years, 5 months

1
0
0 0

[merged] mm-thp-do-not-wait-for-lock_page-in-deferred_split_scan.patch removed from -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: mm/thp: do not wait for lock_page() in deferred_split_scan() has been removed from the -mm tree. Its filename was mm-thp-do-not-wait-for-lock_page-in-deferred_split_scan.patch This patch was dropped because it was merged into mainline or a subsystem tree ------------------------------------------------------ From: "Kirill A. Shutemov" <kirill.shutemov(a)linux.intel.com> Subject: mm/thp: do not wait for lock_page() in deferred_split_scan() deferred_split_scan() gets called from reclaim path. Waiting for page lock may lead to deadlock there. Replace lock_page() with trylock_page() and skip the page if we failed to lock it. We will get to the page on the next scan. Link: http://lkml.kernel.org/r/20180315150747.31945-1-kirill.shutemov@linux.intel… Fixes: 9a982250f773 ("thp: introduce deferred_split_huge_page()") Signed-off-by: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com> Acked-by: Michal Hocko <mhocko(a)suse.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/huge_memory.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff -puN mm/huge_memory.c~mm-thp-do-not-wait-for-lock_page-in-deferred_split_scan mm/huge_memory.c --- a/mm/huge_memory.c~mm-thp-do-not-wait-for-lock_page-in-deferred_split_scan +++ a/mm/huge_memory.c @@ -2783,11 +2783,13 @@ static unsigned long deferred_split_scan list_for_each_safe(pos, next, &list) { page = list_entry((void *)pos, struct page, mapping); - lock_page(page); + if (!trylock_page(page)) + goto next; /* split_huge_page() removes page from list on success */ if (!split_huge_page(page)) split++; unlock_page(page); +next: put_page(page); } _ Patches currently in -mm which might be from kirill.shutemov(a)linux.intel.com are

7 years, 5 months

1
0
0 0

[merged] mm-khugepaged-convert-vm_bug_on-to-collapse-fail.patch removed from -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: mm/khugepaged.c: convert VM_BUG_ON() to collapse fail has been removed from the -mm tree. Its filename was mm-khugepaged-convert-vm_bug_on-to-collapse-fail.patch This patch was dropped because it was merged into mainline or a subsystem tree ------------------------------------------------------ From: "Kirill A. Shutemov" <kirill.shutemov(a)linux.intel.com> Subject: mm/khugepaged.c: convert VM_BUG_ON() to collapse fail khugepaged is not yet able to convert PTE-mapped huge pages back to PMD mapped. We do not collapse such pages. See check khugepaged_scan_pmd(). But if between khugepaged_scan_pmd() and __collapse_huge_page_isolate() somebody managed to instantiate THP in the range and then split the PMD back to PTEs we would have a problem -- VM_BUG_ON_PAGE(PageCompound(page)) will get triggered. It's possible since we drop mmap_sem during collapse to re-take for write. Replace the VM_BUG_ON() with graceful collapse fail. Link: http://lkml.kernel.org/r/20180315152353.27989-1-kirill.shutemov@linux.intel… Fixes: b1caa957ae6d ("khugepaged: ignore pmd tables with THP mapped with ptes") Signed-off-by: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com> Cc: Laura Abbott <labbott(a)redhat.com> Cc: Jerome Marchand <jmarchan(a)redhat.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/khugepaged.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff -puN mm/khugepaged.c~mm-khugepaged-convert-vm_bug_on-to-collapse-fail mm/khugepaged.c --- a/mm/khugepaged.c~mm-khugepaged-convert-vm_bug_on-to-collapse-fail +++ a/mm/khugepaged.c @@ -530,7 +530,12 @@ static int __collapse_huge_page_isolate( goto out; } - VM_BUG_ON_PAGE(PageCompound(page), page); + /* TODO: teach khugepaged to collapse THP mapped with pte */ + if (PageCompound(page)) { + result = SCAN_PAGE_COMPOUND; + goto out; + } + VM_BUG_ON_PAGE(!PageAnon(page), page); /* _ Patches currently in -mm which might be from kirill.shutemov(a)linux.intel.com are

7 years, 5 months

1
0
0 0

[merged] x86-mm-implement-free-pmd-pte-page-interfaces.patch removed from -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: x86/mm: implement free pmd/pte page interfaces has been removed from the -mm tree. Its filename was x86-mm-implement-free-pmd-pte-page-interfaces.patch This patch was dropped because it was merged into mainline or a subsystem tree ------------------------------------------------------ From: Toshi Kani <toshi.kani(a)hpe.com> Subject: x86/mm: implement free pmd/pte page interfaces Implement pud_free_pmd_page() and pmd_free_pte_page() on x86, which clear a given pud/pmd entry and free up lower level page table(s). Address range associated with the pud/pmd entry must have been purged by INVLPG. Link: http://lkml.kernel.org/r/20180314180155.19492-3-toshi.kani@hpe.com Fixes: e61ce6ade404e ("mm: change ioremap to set up huge I/O mappings") Signed-off-by: Toshi Kani <toshi.kani(a)hpe.com> Reported-by: Lei Li <lious.lilei(a)hisilicon.com> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: "H. Peter Anvin" <hpa(a)zytor.com> Cc: Borislav Petkov <bp(a)suse.de> Cc: Matthew Wilcox <willy(a)infradead.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- arch/x86/mm/pgtable.c | 28 ++++++++++++++++++++++++++-- 1 file changed, 26 insertions(+), 2 deletions(-) diff -puN arch/x86/mm/pgtable.c~x86-mm-implement-free-pmd-pte-page-interfaces arch/x86/mm/pgtable.c --- a/arch/x86/mm/pgtable.c~x86-mm-implement-free-pmd-pte-page-interfaces +++ a/arch/x86/mm/pgtable.c @@ -712,7 +712,22 @@ int pmd_clear_huge(pmd_t *pmd) */ int pud_free_pmd_page(pud_t *pud) { - return pud_none(*pud); + pmd_t *pmd; + int i; + + if (pud_none(*pud)) + return 1; + + pmd = (pmd_t *)pud_page_vaddr(*pud); + + for (i = 0; i < PTRS_PER_PMD; i++) + if (!pmd_free_pte_page(&pmd[i])) + return 0; + + pud_clear(pud); + free_page((unsigned long)pmd); + + return 1; } /** @@ -724,6 +739,15 @@ int pud_free_pmd_page(pud_t *pud) */ int pmd_free_pte_page(pmd_t *pmd) { - return pmd_none(*pmd); + pte_t *pte; + + if (pmd_none(*pmd)) + return 1; + + pte = (pte_t *)pmd_page_vaddr(*pmd); + pmd_clear(pmd); + free_page((unsigned long)pte); + + return 1; } #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ _ Patches currently in -mm which might be from toshi.kani(a)hpe.com are

7 years, 5 months

1
0
0 0

[merged] mm-vmalloc-add-interfaces-to-free-unmapped-page-table.patch removed from -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: mm/vmalloc: add interfaces to free unmapped page table has been removed from the -mm tree. Its filename was mm-vmalloc-add-interfaces-to-free-unmapped-page-table.patch This patch was dropped because it was merged into mainline or a subsystem tree ------------------------------------------------------ From: Toshi Kani <toshi.kani(a)hpe.com> Subject: mm/vmalloc: add interfaces to free unmapped page table On architectures with CONFIG_HAVE_ARCH_HUGE_VMAP set, ioremap() may create pud/pmd mappings. Kernel panic was observed on arm64 systems with Cortex-A75 in the following steps as described by Hanjun Guo. 1. ioremap a 4K size, valid page table will build, 2. iounmap it, pte0 will set to 0; 3. ioremap the same address with 2M size, pgd/pmd is unchanged, then set the a new value for pmd; 4. pte0 is leaked; 5. CPU may meet exception because the old pmd is still in TLB, which will lead to kernel panic. This panic is not reproducible on x86. INVLPG, called from iounmap, purges all levels of entries associated with purged address on x86. x86 still has memory leak. The patch changes the ioremap path to free unmapped page table(s) since doing so in the unmap path has the following issues: - The iounmap() path is shared with vunmap(). Since vmap() only supports pte mappings, making vunmap() to free a pte page is an overhead for regular vmap users as they do not need a pte page freed up. - Checking if all entries in a pte page are cleared in the unmap path is racy, and serializing this check is expensive. - The unmap path calls free_vmap_area_noflush() to do lazy TLB purges. Clearing a pud/pmd entry before the lazy TLB purges needs extra TLB purge. Add two interfaces, pud_free_pmd_page() and pmd_free_pte_page(), which clear a given pud/pmd entry and free up a page for the lower level entries. This patch implements their stub functions on x86 and arm64, which work as workaround. [akpm(a)linux-foundation.org: fix typo in pmd_free_pte_page() stub] Link: http://lkml.kernel.org/r/20180314180155.19492-2-toshi.kani@hpe.com Fixes: e61ce6ade404e ("mm: change ioremap to set up huge I/O mappings") Reported-by: Lei Li <lious.lilei(a)hisilicon.com> Signed-off-by: Toshi Kani <toshi.kani(a)hpe.com> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Wang Xuefeng <wxf.wang(a)hisilicon.com> Cc: Will Deacon <will.deacon(a)arm.com> Cc: Hanjun Guo <guohanjun(a)huawei.com> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: "H. Peter Anvin" <hpa(a)zytor.com> Cc: Borislav Petkov <bp(a)suse.de> Cc: Matthew Wilcox <willy(a)infradead.org> Cc: Chintan Pandya <cpandya(a)codeaurora.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- arch/arm64/mm/mmu.c | 10 ++++++++++ arch/x86/mm/pgtable.c | 24 ++++++++++++++++++++++++ include/asm-generic/pgtable.h | 10 ++++++++++ lib/ioremap.c | 6 ++++-- 4 files changed, 48 insertions(+), 2 deletions(-) diff -puN arch/arm64/mm/mmu.c~mm-vmalloc-add-interfaces-to-free-unmapped-page-table arch/arm64/mm/mmu.c --- a/arch/arm64/mm/mmu.c~mm-vmalloc-add-interfaces-to-free-unmapped-page-table +++ a/arch/arm64/mm/mmu.c @@ -972,3 +972,13 @@ int pmd_clear_huge(pmd_t *pmdp) pmd_clear(pmdp); return 1; } + +int pud_free_pmd_page(pud_t *pud) +{ + return pud_none(*pud); +} + +int pmd_free_pte_page(pmd_t *pmd) +{ + return pmd_none(*pmd); +} diff -puN arch/x86/mm/pgtable.c~mm-vmalloc-add-interfaces-to-free-unmapped-page-table arch/x86/mm/pgtable.c --- a/arch/x86/mm/pgtable.c~mm-vmalloc-add-interfaces-to-free-unmapped-page-table +++ a/arch/x86/mm/pgtable.c @@ -702,4 +702,28 @@ int pmd_clear_huge(pmd_t *pmd) return 0; } + +/** + * pud_free_pmd_page - Clear pud entry and free pmd page. + * @pud: Pointer to a PUD. + * + * Context: The pud range has been unmaped and TLB purged. + * Return: 1 if clearing the entry succeeded. 0 otherwise. + */ +int pud_free_pmd_page(pud_t *pud) +{ + return pud_none(*pud); +} + +/** + * pmd_free_pte_page - Clear pmd entry and free pte page. + * @pmd: Pointer to a PMD. + * + * Context: The pmd range has been unmaped and TLB purged. + * Return: 1 if clearing the entry succeeded. 0 otherwise. + */ +int pmd_free_pte_page(pmd_t *pmd) +{ + return pmd_none(*pmd); +} #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ diff -puN include/asm-generic/pgtable.h~mm-vmalloc-add-interfaces-to-free-unmapped-page-table include/asm-generic/pgtable.h --- a/include/asm-generic/pgtable.h~mm-vmalloc-add-interfaces-to-free-unmapped-page-table +++ a/include/asm-generic/pgtable.h @@ -983,6 +983,8 @@ int pud_set_huge(pud_t *pud, phys_addr_t int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot); int pud_clear_huge(pud_t *pud); int pmd_clear_huge(pmd_t *pmd); +int pud_free_pmd_page(pud_t *pud); +int pmd_free_pte_page(pmd_t *pmd); #else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */ static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) { @@ -1008,6 +1010,14 @@ static inline int pmd_clear_huge(pmd_t * { return 0; } +static inline int pud_free_pmd_page(pud_t *pud) +{ + return 0; +} +static inline int pmd_free_pte_page(pmd_t *pmd) +{ + return 0; +} #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ #ifndef __HAVE_ARCH_FLUSH_PMD_TLB_RANGE diff -puN lib/ioremap.c~mm-vmalloc-add-interfaces-to-free-unmapped-page-table lib/ioremap.c --- a/lib/ioremap.c~mm-vmalloc-add-interfaces-to-free-unmapped-page-table +++ a/lib/ioremap.c @@ -91,7 +91,8 @@ static inline int ioremap_pmd_range(pud_ if (ioremap_pmd_enabled() && ((next - addr) == PMD_SIZE) && - IS_ALIGNED(phys_addr + addr, PMD_SIZE)) { + IS_ALIGNED(phys_addr + addr, PMD_SIZE) && + pmd_free_pte_page(pmd)) { if (pmd_set_huge(pmd, phys_addr + addr, prot)) continue; } @@ -117,7 +118,8 @@ static inline int ioremap_pud_range(p4d_ if (ioremap_pud_enabled() && ((next - addr) == PUD_SIZE) && - IS_ALIGNED(phys_addr + addr, PUD_SIZE)) { + IS_ALIGNED(phys_addr + addr, PUD_SIZE) && + pud_free_pmd_page(pud)) { if (pud_set_huge(pud, phys_addr + addr, prot)) continue; } _ Patches currently in -mm which might be from toshi.kani(a)hpe.com are

7 years, 5 months

1
0
0 0

[merged] h8300-remove-extranous-__big_endian-definition.patch removed from -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: h8300: remove extraneous __BIG_ENDIAN definition has been removed from the -mm tree. Its filename was h8300-remove-extranous-__big_endian-definition.patch This patch was dropped because it was merged into mainline or a subsystem tree ------------------------------------------------------ From: Arnd Bergmann <arnd(a)arndb.de> Subject: h8300: remove extraneous __BIG_ENDIAN definition A bugfix I did earlier caused a build regression on h8300, which defines the __BIG_ENDIAN macro in a slightly different way than the generic code: arch/h8300/include/asm/byteorder.h:5:0: warning: "__BIG_ENDIAN" redefined We don't need to define it here, as the same macro is already provided by the linux/byteorder/big_endian.h, and that version does not conflict. While this is a v4.16 regression, my earlier patch also got backported to the 4.14 and 4.15 stable kernels, so we need the fixup there as well. Link: http://lkml.kernel.org/r/20180313120752.2645129-1-arnd@arndb.de Fixes: 101110f6271c ("Kbuild: always define endianess in kconfig.h") Signed-off-by: Arnd Bergmann <arnd(a)arndb.de> Cc: Yoshinori Sato <ysato(a)users.sourceforge.jp> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- arch/h8300/include/asm/byteorder.h | 1 - 1 file changed, 1 deletion(-) diff -puN arch/h8300/include/asm/byteorder.h~h8300-remove-extranous-__big_endian-definition arch/h8300/include/asm/byteorder.h --- a/arch/h8300/include/asm/byteorder.h~h8300-remove-extranous-__big_endian-definition +++ a/arch/h8300/include/asm/byteorder.h @@ -2,7 +2,6 @@ #ifndef __H8300_BYTEORDER_H__ #define __H8300_BYTEORDER_H__ -#define __BIG_ENDIAN __ORDER_BIG_ENDIAN__ #include <linux/byteorder/big_endian.h> #endif _ Patches currently in -mm which might be from arnd(a)arndb.de are

7 years, 5 months

1
0
0 0

[merged] hugetlbfs-check-for-pgoff-value-overflow.patch removed from -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: hugetlbfs: check for pgoff value overflow has been removed from the -mm tree. Its filename was hugetlbfs-check-for-pgoff-value-overflow.patch This patch was dropped because it was merged into mainline or a subsystem tree ------------------------------------------------------ From: Mike Kravetz <mike.kravetz(a)oracle.com> Subject: hugetlbfs: check for pgoff value overflow A vma with vm_pgoff large enough to overflow a loff_t type when converted to a byte offset can be passed via the remap_file_pages system call. The hugetlbfs mmap routine uses the byte offset to calculate reservations and file size. A sequence such as: mmap(0x20a00000, 0x600000, 0, 0x66033, -1, 0); remap_file_pages(0x20a00000, 0x600000, 0, 0x20000000000000, 0); will result in the following when task exits/file closed, kernel BUG at mm/hugetlb.c:749! Call Trace: hugetlbfs_evict_inode+0x2f/0x40 evict+0xcb/0x190 __dentry_kill+0xcb/0x150 __fput+0x164/0x1e0 task_work_run+0x84/0xa0 exit_to_usermode_loop+0x7d/0x80 do_syscall_64+0x18b/0x190 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 The overflowed pgoff value causes hugetlbfs to try to set up a mapping with a negative range (end < start) that leaves invalid state which causes the BUG. The previous overflow fix to this code was incomplete and did not take the remap_file_pages system call into account. [mike.kravetz(a)oracle.com: v3] Link: http://lkml.kernel.org/r/20180309002726.7248-1-mike.kravetz@oracle.com [akpm(a)linux-foundation.org: include mmdebug.h] [akpm(a)linux-foundation.org: fix -ve left shift count on sh] Link: http://lkml.kernel.org/r/20180308210502.15952-1-mike.kravetz@oracle.com Fixes: 045c7a3f53d9 ("hugetlbfs: fix offset overflow in hugetlbfs mmap") Signed-off-by: Mike Kravetz <mike.kravetz(a)oracle.com> Reported-by: Nic Losby <blurbdust(a)gmail.com> Acked-by: Michal Hocko <mhocko(a)suse.com> Cc: "Kirill A . Shutemov" <kirill.shutemov(a)linux.intel.com> Cc: Yisheng Xie <xieyisheng1(a)huawei.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- fs/hugetlbfs/inode.c | 17 ++++++++++++++--- mm/hugetlb.c | 7 +++++++ 2 files changed, 21 insertions(+), 3 deletions(-) diff -puN fs/hugetlbfs/inode.c~hugetlbfs-check-for-pgoff-value-overflow fs/hugetlbfs/inode.c --- a/fs/hugetlbfs/inode.c~hugetlbfs-check-for-pgoff-value-overflow +++ a/fs/hugetlbfs/inode.c @@ -108,6 +108,16 @@ static void huge_pagevec_release(struct pagevec_reinit(pvec); } +/* + * Mask used when checking the page offset value passed in via system + * calls. This value will be converted to a loff_t which is signed. + * Therefore, we want to check the upper PAGE_SHIFT + 1 bits of the + * value. The extra bit (- 1 in the shift value) is to take the sign + * bit into account. + */ +#define PGOFF_LOFFT_MAX \ + (((1UL << (PAGE_SHIFT + 1)) - 1) << (BITS_PER_LONG - (PAGE_SHIFT + 1))) + static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *inode = file_inode(file); @@ -127,12 +137,13 @@ static int hugetlbfs_file_mmap(struct fi vma->vm_ops = &hugetlb_vm_ops; /* - * Offset passed to mmap (before page shift) could have been - * negative when represented as a (l)off_t. + * page based offset in vm_pgoff could be sufficiently large to + * overflow a (l)off_t when converted to byte offset. */ - if (((loff_t)vma->vm_pgoff << PAGE_SHIFT) < 0) + if (vma->vm_pgoff & PGOFF_LOFFT_MAX) return -EINVAL; + /* must be huge page aligned */ if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT)) return -EINVAL; diff -puN mm/hugetlb.c~hugetlbfs-check-for-pgoff-value-overflow mm/hugetlb.c --- a/mm/hugetlb.c~hugetlbfs-check-for-pgoff-value-overflow +++ a/mm/hugetlb.c @@ -18,6 +18,7 @@ #include <linux/bootmem.h> #include <linux/sysfs.h> #include <linux/slab.h> +#include <linux/mmdebug.h> #include <linux/sched/signal.h> #include <linux/rmap.h> #include <linux/string_helpers.h> @@ -4374,6 +4375,12 @@ int hugetlb_reserve_pages(struct inode * struct resv_map *resv_map; long gbl_reserve; + /* This should never happen */ + if (from > to) { + VM_WARN(1, "%s called with a negative range\n", __func__); + return -EINVAL; + } + /* * Only apply hugepage reservation if asked. At fault time, an * attempt will be made for VM_NORESERVE to allocate a page _ Patches currently in -mm which might be from mike.kravetz(a)oracle.com are shm-add-split-function-to-shm_vm_ops.patch mm-hugetlbfs-move-hugetlbfs_i-outside-ifdef-config_hugetlbfs.patch mm-memfd-split-out-memfd-for-use-by-multiple-filesystems.patch mm-memfd-remove-memfd-code-from-shmem-files-and-use-new-memfd-files.patch mm-make-start_isolate_page_range-fail-if-already-isolated.patch

7 years, 5 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror