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

+ selftests-memfd_secret-dont-build-memfd_secret-test-on-unsupported-arches.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: selftests: memfd_secret: don't build memfd_secret test on unsupported arches has been added to the -mm mm-hotfixes-unstable branch. Its filename is selftests-memfd_secret-dont-build-memfd_secret-test-on-unsupported-arches.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Muhammad Usama Anjum <usama.anjum(a)collabora.com> Subject: selftests: memfd_secret: don't build memfd_secret test on unsupported arches Date: Fri, 9 Aug 2024 12:56:42 +0500 [1] mentions that memfd_secret is only supported on arm64, riscv, x86 and x86_64 for now. It doesn't support other architectures. I found the build error on arm and decided to send the fix as it was creating noise on KernelCI. Hence I'm adding condition that memfd_secret should only be compiled on supported architectures. Also check in run_vmtests script if memfd_secret binary is present before executing it. Link: https://lore.kernel.org/all/20210518072034.31572-7-rppt@kernel.org/ [1] Link: https://lkml.kernel.org/r/20240809075642.403247-1-usama.anjum@collabora.com Fixes: 76fe17ef588a ("secretmem: test: add basic selftest for memfd_secret(2)") Signed-off-by: Muhammad Usama Anjum <usama.anjum(a)collabora.com> Cc: Albert Ou <aou(a)eecs.berkeley.edu> Cc: James Bottomley <James.Bottomley(a)HansenPartnership.com> Cc: Mike Rapoport (Microsoft) <rppt(a)kernel.org> Cc: Palmer Dabbelt <palmer(a)dabbelt.com> Cc: Paul Walmsley <paul.walmsley(a)sifive.com> Cc: Shuah Khan <shuah(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- tools/testing/selftests/mm/Makefile | 2 ++ tools/testing/selftests/mm/run_vmtests.sh | 3 +++ 2 files changed, 5 insertions(+) --- a/tools/testing/selftests/mm/Makefile~selftests-memfd_secret-dont-build-memfd_secret-test-on-unsupported-arches +++ a/tools/testing/selftests/mm/Makefile @@ -53,7 +53,9 @@ TEST_GEN_FILES += madv_populate TEST_GEN_FILES += map_fixed_noreplace TEST_GEN_FILES += map_hugetlb TEST_GEN_FILES += map_populate +ifneq (,$(filter $(ARCH),arm64 riscv riscv64 x86 x86_64)) TEST_GEN_FILES += memfd_secret +endif TEST_GEN_FILES += migration TEST_GEN_FILES += mkdirty TEST_GEN_FILES += mlock-random-test --- a/tools/testing/selftests/mm/run_vmtests.sh~selftests-memfd_secret-dont-build-memfd_secret-test-on-unsupported-arches +++ a/tools/testing/selftests/mm/run_vmtests.sh @@ -374,8 +374,11 @@ CATEGORY="hmm" run_test bash ./test_hmm. # MADV_POPULATE_READ and MADV_POPULATE_WRITE tests CATEGORY="madv_populate" run_test ./madv_populate +if [ -x ./memfd_secret ] +then (echo 0 | sudo tee /proc/sys/kernel/yama/ptrace_scope 2>&1) | tap_prefix CATEGORY="memfd_secret" run_test ./memfd_secret +fi # KSM KSM_MERGE_TIME_HUGE_PAGES test with size of 100 CATEGORY="ksm" run_test ./ksm_tests -H -s 100 _ Patches currently in -mm which might be from usama.anjum(a)collabora.com are selftests-mm-fix-build-errors-on-armhf.patch selftests-memfd_secret-dont-build-memfd_secret-test-on-unsupported-arches.patch

9 months

1
0
0 0

+ selftests-mm-fix-build-errors-on-armhf.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: selftests: mm: fix build errors on armhf has been added to the -mm mm-hotfixes-unstable branch. Its filename is selftests-mm-fix-build-errors-on-armhf.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Muhammad Usama Anjum <usama.anjum(a)collabora.com> Subject: selftests: mm: fix build errors on armhf Date: Fri, 9 Aug 2024 13:25:11 +0500 The __NR_mmap isn't found on armhf. The mmap() is commonly available system call and its wrapper is present on all architectures. So it should be used directly. It solves problem for armhf and doesn't create problem for other architectures. Remove sys_mmap() functions as they aren't doing anything else other than calling mmap(). There is no need to set errno = 0 manually as glibc always resets it. For reference errors are as following: CC seal_elf seal_elf.c: In function 'sys_mmap': seal_elf.c:39:33: error: '__NR_mmap' undeclared (first use in this function) 39 | sret = (void *) syscall(__NR_mmap, addr, len, prot, | ^~~~~~~~~ mseal_test.c: In function 'sys_mmap': mseal_test.c:90:33: error: '__NR_mmap' undeclared (first use in this function) 90 | sret = (void *) syscall(__NR_mmap, addr, len, prot, | ^~~~~~~~~ Link: https://lkml.kernel.org/r/20240809082511.497266-1-usama.anjum@collabora.com Fixes: 4926c7a52de7 ("selftest mm/mseal memory sealing") Signed-off-by: Muhammad Usama Anjum <usama.anjum(a)collabora.com> Cc: Jeff Xu <jeffxu(a)chromium.org> Cc: Kees Cook <kees(a)kernel.org> Cc: Liam R. Howlett <Liam.Howlett(a)oracle.com> Cc: Shuah Khan <shuah(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- tools/testing/selftests/mm/mseal_test.c | 37 +++++++--------------- tools/testing/selftests/mm/seal_elf.c | 13 ------- 2 files changed, 14 insertions(+), 36 deletions(-) --- a/tools/testing/selftests/mm/mseal_test.c~selftests-mm-fix-build-errors-on-armhf +++ a/tools/testing/selftests/mm/mseal_test.c @@ -81,17 +81,6 @@ static int sys_mprotect_pkey(void *ptr, return sret; } -static void *sys_mmap(void *addr, unsigned long len, unsigned long prot, - unsigned long flags, unsigned long fd, unsigned long offset) -{ - void *sret; - - errno = 0; - sret = (void *) syscall(__NR_mmap, addr, len, prot, - flags, fd, offset); - return sret; -} - static int sys_munmap(void *ptr, size_t size) { int sret; @@ -172,7 +161,7 @@ static void setup_single_address(int siz { void *ptr; - ptr = sys_mmap(NULL, size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + ptr = mmap(NULL, size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); *ptrOut = ptr; } @@ -181,7 +170,7 @@ static void setup_single_address_rw(int void *ptr; unsigned long mapflags = MAP_ANONYMOUS | MAP_PRIVATE; - ptr = sys_mmap(NULL, size, PROT_READ | PROT_WRITE, mapflags, -1, 0); + ptr = mmap(NULL, size, PROT_READ | PROT_WRITE, mapflags, -1, 0); *ptrOut = ptr; } @@ -205,7 +194,7 @@ bool seal_support(void) void *ptr; unsigned long page_size = getpagesize(); - ptr = sys_mmap(NULL, page_size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + ptr = mmap(NULL, page_size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); if (ptr == (void *) -1) return false; @@ -481,8 +470,8 @@ static void test_seal_zero_address(void) int prot; /* use mmap to change protection. */ - ptr = sys_mmap(0, size, PROT_NONE, - MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); + ptr = mmap(0, size, PROT_NONE, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); FAIL_TEST_IF_FALSE(ptr == 0); size = get_vma_size(ptr, &prot); @@ -1209,8 +1198,8 @@ static void test_seal_mmap_overwrite_pro } /* use mmap to change protection. */ - ret2 = sys_mmap(ptr, size, PROT_NONE, - MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); + ret2 = mmap(ptr, size, PROT_NONE, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); if (seal) { FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); FAIL_TEST_IF_FALSE(errno == EPERM); @@ -1240,8 +1229,8 @@ static void test_seal_mmap_expand(bool s } /* use mmap to expand. */ - ret2 = sys_mmap(ptr, size, PROT_READ, - MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); + ret2 = mmap(ptr, size, PROT_READ, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); if (seal) { FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); FAIL_TEST_IF_FALSE(errno == EPERM); @@ -1268,8 +1257,8 @@ static void test_seal_mmap_shrink(bool s } /* use mmap to shrink. */ - ret2 = sys_mmap(ptr, 8 * page_size, PROT_READ, - MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); + ret2 = mmap(ptr, 8 * page_size, PROT_READ, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); if (seal) { FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); FAIL_TEST_IF_FALSE(errno == EPERM); @@ -1650,7 +1639,7 @@ static void test_seal_discard_ro_anon_on ret = fallocate(fd, 0, 0, size); FAIL_TEST_IF_FALSE(!ret); - ptr = sys_mmap(NULL, size, PROT_READ, mapflags, fd, 0); + ptr = mmap(NULL, size, PROT_READ, mapflags, fd, 0); FAIL_TEST_IF_FALSE(ptr != MAP_FAILED); if (seal) { @@ -1680,7 +1669,7 @@ static void test_seal_discard_ro_anon_on int ret; unsigned long mapflags = MAP_ANONYMOUS | MAP_SHARED; - ptr = sys_mmap(NULL, size, PROT_READ, mapflags, -1, 0); + ptr = mmap(NULL, size, PROT_READ, mapflags, -1, 0); FAIL_TEST_IF_FALSE(ptr != (void *)-1); if (seal) { --- a/tools/testing/selftests/mm/seal_elf.c~selftests-mm-fix-build-errors-on-armhf +++ a/tools/testing/selftests/mm/seal_elf.c @@ -30,17 +30,6 @@ static int sys_mseal(void *start, size_t return sret; } -static void *sys_mmap(void *addr, unsigned long len, unsigned long prot, - unsigned long flags, unsigned long fd, unsigned long offset) -{ - void *sret; - - errno = 0; - sret = (void *) syscall(__NR_mmap, addr, len, prot, - flags, fd, offset); - return sret; -} - static inline int sys_mprotect(void *ptr, size_t size, unsigned long prot) { int sret; @@ -56,7 +45,7 @@ static bool seal_support(void) void *ptr; unsigned long page_size = getpagesize(); - ptr = sys_mmap(NULL, page_size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + ptr = mmap(NULL, page_size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); if (ptr == (void *) -1) return false; _ Patches currently in -mm which might be from usama.anjum(a)collabora.com are selftests-mm-fix-build-errors-on-armhf.patch

9 months

1
0
0 0

+ mm-fix-endless-reclaim-on-machines-with-unaccepted-memory.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: mm: fix endless reclaim on machines with unaccepted memory has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-fix-endless-reclaim-on-machines-with-unaccepted-memory.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: "Kirill A. Shutemov" <kirill.shutemov(a)linux.intel.com> Subject: mm: fix endless reclaim on machines with unaccepted memory Date: Fri, 9 Aug 2024 14:48:47 +0300 Unaccepted memory is considered unusable free memory, which is not counted as free on the zone watermark check. This causes get_page_from_freelist() to accept more memory to hit the high watermark, but it creates problems in the reclaim path. The reclaim path encounters a failed zone watermark check and attempts to reclaim memory. This is usually successful, but if there is little or no reclaimable memory, it can result in endless reclaim with little to no progress. This can occur early in the boot process, just after start of the init process when the only reclaimable memory is the page cache of the init executable and its libraries. Make unaccepted memory free from watermark check point of view. This way unaccepted memory will never be the trigger of memory reclaim. Accept more memory in the get_page_from_freelist() if needed. Link: https://lkml.kernel.org/r/20240809114854.3745464-2-kirill.shutemov@linux.in… Signed-off-by: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com> Reported-by: Jianxiong Gao <jxgao(a)google.com> Acked-by: David Hildenbrand <david(a)redhat.com> Fixes: dcdfdd40fa82 ("mm: Add support for unaccepted memory") Cc: Borislav Petkov <bp(a)alien8.de> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com> Cc: Matthew Wilcox <willy(a)infradead.org> Cc: Mel Gorman <mgorman(a)suse.de> Cc: Mike Rapoport (Microsoft) <rppt(a)kernel.org> Cc: Tom Lendacky <thomas.lendacky(a)amd.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: <stable(a)vger.kernel.org> [6.5+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/page_alloc.c | 42 ++++++++++++++++++++---------------------- 1 file changed, 20 insertions(+), 22 deletions(-) --- a/mm/page_alloc.c~mm-fix-endless-reclaim-on-machines-with-unaccepted-memory +++ a/mm/page_alloc.c @@ -287,7 +287,7 @@ EXPORT_SYMBOL(nr_online_nodes); static bool page_contains_unaccepted(struct page *page, unsigned int order); static void accept_page(struct page *page, unsigned int order); -static bool try_to_accept_memory(struct zone *zone, unsigned int order); +static bool cond_accept_memory(struct zone *zone, unsigned int order); static inline bool has_unaccepted_memory(void); static bool __free_unaccepted(struct page *page); @@ -3072,9 +3072,6 @@ static inline long __zone_watermark_unus if (!(alloc_flags & ALLOC_CMA)) unusable_free += zone_page_state(z, NR_FREE_CMA_PAGES); #endif -#ifdef CONFIG_UNACCEPTED_MEMORY - unusable_free += zone_page_state(z, NR_UNACCEPTED); -#endif return unusable_free; } @@ -3368,6 +3365,8 @@ retry: } } + cond_accept_memory(zone, order); + /* * Detect whether the number of free pages is below high * watermark. If so, we will decrease pcp->high and free @@ -3393,10 +3392,8 @@ check_alloc_wmark: gfp_mask)) { int ret; - if (has_unaccepted_memory()) { - if (try_to_accept_memory(zone, order)) - goto try_this_zone; - } + if (cond_accept_memory(zone, order)) + goto try_this_zone; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* @@ -3450,10 +3447,8 @@ try_this_zone: return page; } else { - if (has_unaccepted_memory()) { - if (try_to_accept_memory(zone, order)) - goto try_this_zone; - } + if (cond_accept_memory(zone, order)) + goto try_this_zone; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* Try again if zone has deferred pages */ @@ -6950,9 +6945,6 @@ static bool try_to_accept_memory_one(str struct page *page; bool last; - if (list_empty(&zone->unaccepted_pages)) - return false; - spin_lock_irqsave(&zone->lock, flags); page = list_first_entry_or_null(&zone->unaccepted_pages, struct page, lru); @@ -6978,23 +6970,29 @@ static bool try_to_accept_memory_one(str return true; } -static bool try_to_accept_memory(struct zone *zone, unsigned int order) +static bool cond_accept_memory(struct zone *zone, unsigned int order) { long to_accept; - int ret = false; + bool ret = false; + + if (!has_unaccepted_memory()) + return false; + + if (list_empty(&zone->unaccepted_pages)) + return false; /* How much to accept to get to high watermark? */ to_accept = high_wmark_pages(zone) - (zone_page_state(zone, NR_FREE_PAGES) - - __zone_watermark_unusable_free(zone, order, 0)); + __zone_watermark_unusable_free(zone, order, 0) - + zone_page_state(zone, NR_UNACCEPTED)); - /* Accept at least one page */ - do { + while (to_accept > 0) { if (!try_to_accept_memory_one(zone)) break; ret = true; to_accept -= MAX_ORDER_NR_PAGES; - } while (to_accept > 0); + } return ret; } @@ -7037,7 +7035,7 @@ static void accept_page(struct page *pag { } -static bool try_to_accept_memory(struct zone *zone, unsigned int order) +static bool cond_accept_memory(struct zone *zone, unsigned int order) { return false; } _ Patches currently in -mm which might be from kirill.shutemov(a)linux.intel.com are mm-fix-endless-reclaim-on-machines-with-unaccepted-memory.patch

9 months

1
0
0 0

+ mm-numa-no-task_numa_fault-call-if-pmd-is-changed.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: mm/numa: no task_numa_fault() call if PMD is changed has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-numa-no-task_numa_fault-call-if-pmd-is-changed.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Zi Yan <ziy(a)nvidia.com> Subject: mm/numa: no task_numa_fault() call if PMD is changed Date: Fri, 9 Aug 2024 10:59:05 -0400 When handling a numa page fault, task_numa_fault() should be called by a process that restores the page table of the faulted folio to avoid duplicated stats counting. Commit c5b5a3dd2c1f ("mm: thp: refactor NUMA fault handling") restructured do_huge_pmd_numa_page() and did not avoid task_numa_fault() call in the second page table check after a numa migration failure. Fix it by making all !pmd_same() return immediately. This issue can cause task_numa_fault() being called more than necessary and lead to unexpected numa balancing results (It is hard to tell whether the issue will cause positive or negative performance impact due to duplicated numa fault counting). Link: https://lkml.kernel.org/r/20240809145906.1513458-3-ziy@nvidia.com Fixes: c5b5a3dd2c1f ("mm: thp: refactor NUMA fault handling") Reported-by: "Huang, Ying" <ying.huang(a)intel.com> Closes: https://lore.kernel.org/linux-mm/87zfqfw0yw.fsf@yhuang6-desk2.ccr.corp.inte… Signed-off-by: Zi Yan <ziy(a)nvidia.com> Acked-by: David Hildenbrand <david(a)redhat.com> Cc: Baolin Wang <baolin.wang(a)linux.alibaba.com> Cc: "Huang, Ying" <ying.huang(a)intel.com> Cc: Kefeng Wang <wangkefeng.wang(a)huawei.com> Cc: Mel Gorman <mgorman(a)suse.de> Cc: Yang Shi <shy828301(a)gmail.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/huge_memory.c | 29 +++++++++++++---------------- 1 file changed, 13 insertions(+), 16 deletions(-) --- a/mm/huge_memory.c~mm-numa-no-task_numa_fault-call-if-pmd-is-changed +++ a/mm/huge_memory.c @@ -1685,7 +1685,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) { spin_unlock(vmf->ptl); - goto out; + return 0; } pmd = pmd_modify(oldpmd, vma->vm_page_prot); @@ -1728,22 +1728,16 @@ vm_fault_t do_huge_pmd_numa_page(struct if (!migrate_misplaced_folio(folio, vma, target_nid)) { flags |= TNF_MIGRATED; nid = target_nid; - } else { - flags |= TNF_MIGRATE_FAIL; - vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); - if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) { - spin_unlock(vmf->ptl); - goto out; - } - goto out_map; - } - -out: - if (nid != NUMA_NO_NODE) task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags); + return 0; + } - return 0; - + flags |= TNF_MIGRATE_FAIL; + vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); + if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) { + spin_unlock(vmf->ptl); + return 0; + } out_map: /* Restore the PMD */ pmd = pmd_modify(oldpmd, vma->vm_page_prot); @@ -1753,7 +1747,10 @@ out_map: set_pmd_at(vma->vm_mm, haddr, vmf->pmd, pmd); update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); spin_unlock(vmf->ptl); - goto out; + + if (nid != NUMA_NO_NODE) + task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags); + return 0; } /* _ Patches currently in -mm which might be from ziy(a)nvidia.com are mm-numa-no-task_numa_fault-call-if-pte-is-changed.patch mm-numa-no-task_numa_fault-call-if-pmd-is-changed.patch memory-tiering-read-last_cpupid-correctly-in-do_huge_pmd_numa_page.patch memory-tiering-introduce-folio_use_access_time-check.patch memory-tiering-count-pgpromote_success-when-mem-tiering-is-enabled.patch

9 months

1
0
0 0

+ mm-numa-no-task_numa_fault-call-if-pte-is-changed.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: mm/numa: no task_numa_fault() call if PTE is changed has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-numa-no-task_numa_fault-call-if-pte-is-changed.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Zi Yan <ziy(a)nvidia.com> Subject: mm/numa: no task_numa_fault() call if PTE is changed Date: Fri, 9 Aug 2024 10:59:04 -0400 When handling a numa page fault, task_numa_fault() should be called by a process that restores the page table of the faulted folio to avoid duplicated stats counting. Commit b99a342d4f11 ("NUMA balancing: reduce TLB flush via delaying mapping on hint page fault") restructured do_numa_page() and did not avoid task_numa_fault() call in the second page table check after a numa migration failure. Fix it by making all !pte_same() return immediately. This issue can cause task_numa_fault() being called more than necessary and lead to unexpected numa balancing results (It is hard to tell whether the issue will cause positive or negative performance impact due to duplicated numa fault counting). Link: https://lkml.kernel.org/r/20240809145906.1513458-2-ziy@nvidia.com Fixes: b99a342d4f11 ("NUMA balancing: reduce TLB flush via delaying mapping on hint page fault") Signed-off-by: Zi Yan <ziy(a)nvidia.com> Reported-by: "Huang, Ying" <ying.huang(a)intel.com> Closes: https://lore.kernel.org/linux-mm/87zfqfw0yw.fsf@yhuang6-desk2.ccr.corp.inte… Acked-by: David Hildenbrand <david(a)redhat.com> Cc: Baolin Wang <baolin.wang(a)linux.alibaba.com> Cc: Kefeng Wang <wangkefeng.wang(a)huawei.com> Cc: Mel Gorman <mgorman(a)suse.de> Cc: Yang Shi <shy828301(a)gmail.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/memory.c | 33 ++++++++++++++++----------------- 1 file changed, 16 insertions(+), 17 deletions(-) --- a/mm/memory.c~mm-numa-no-task_numa_fault-call-if-pte-is-changed +++ a/mm/memory.c @@ -5295,7 +5295,7 @@ static vm_fault_t do_numa_page(struct vm if (unlikely(!pte_same(old_pte, vmf->orig_pte))) { pte_unmap_unlock(vmf->pte, vmf->ptl); - goto out; + return 0; } pte = pte_modify(old_pte, vma->vm_page_prot); @@ -5358,23 +5358,19 @@ static vm_fault_t do_numa_page(struct vm if (!migrate_misplaced_folio(folio, vma, target_nid)) { nid = target_nid; flags |= TNF_MIGRATED; - } else { - flags |= TNF_MIGRATE_FAIL; - vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, - vmf->address, &vmf->ptl); - if (unlikely(!vmf->pte)) - goto out; - if (unlikely(!pte_same(ptep_get(vmf->pte), vmf->orig_pte))) { - pte_unmap_unlock(vmf->pte, vmf->ptl); - goto out; - } - goto out_map; + task_numa_fault(last_cpupid, nid, nr_pages, flags); + return 0; } -out: - if (nid != NUMA_NO_NODE) - task_numa_fault(last_cpupid, nid, nr_pages, flags); - return 0; + flags |= TNF_MIGRATE_FAIL; + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, + vmf->address, &vmf->ptl); + if (unlikely(!vmf->pte)) + return 0; + if (unlikely(!pte_same(ptep_get(vmf->pte), vmf->orig_pte))) { + pte_unmap_unlock(vmf->pte, vmf->ptl); + return 0; + } out_map: /* * Make it present again, depending on how arch implements @@ -5387,7 +5383,10 @@ out_map: numa_rebuild_single_mapping(vmf, vma, vmf->address, vmf->pte, writable); pte_unmap_unlock(vmf->pte, vmf->ptl); - goto out; + + if (nid != NUMA_NO_NODE) + task_numa_fault(last_cpupid, nid, nr_pages, flags); + return 0; } static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf) _ Patches currently in -mm which might be from ziy(a)nvidia.com are mm-numa-no-task_numa_fault-call-if-pte-is-changed.patch mm-numa-no-task_numa_fault-call-if-pmd-is-changed.patch memory-tiering-read-last_cpupid-correctly-in-do_huge_pmd_numa_page.patch memory-tiering-introduce-folio_use_access_time-check.patch memory-tiering-count-pgpromote_success-when-mem-tiering-is-enabled.patch

9 months

1
0
0 0

[PATCH v3] usb: dwc3: Runtime get and put usb power_supply handle

by Kyle Tso

It is possible that the usb power_supply is registered after the probe of dwc3. In this case, trying to get the usb power_supply during the probe will fail and there is no chance to try again. Also the usb power_supply might be unregistered at anytime so that the handle of it in dwc3 would become invalid. To fix this, get the handle right before calling to power_supply functions and put it afterward. dwc3_gadet_vbus_draw might be in interrupt context. Create a kthread worker beforehand and use it to process the "might-sleep" power_supply_put ASAP after the property set. Fixes: 6f0764b5adea ("usb: dwc3: add a power supply for current control") Cc: stable(a)vger.kernel.org Signed-off-by: Kyle Tso <kyletso(a)google.com> --- v2 -> v3: - Only move power_supply_put to a work. Still call _get_by_name and _set_property in dwc3_gadget_vbus_draw. - Create a kthread_worker to handle the work v1 -> v2: - move power_supply_put out of interrupt context drivers/usb/dwc3/core.c | 29 ++++++++++++---------------- drivers/usb/dwc3/core.h | 6 ++++-- drivers/usb/dwc3/gadget.c | 40 +++++++++++++++++++++++++++++++++++---- 3 files changed, 52 insertions(+), 23 deletions(-) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 734de2a8bd21..82c8376330d7 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1631,8 +1631,6 @@ static void dwc3_get_properties(struct dwc3 *dwc) u8 tx_thr_num_pkt_prd = 0; u8 tx_max_burst_prd = 0; u8 tx_fifo_resize_max_num; - const char *usb_psy_name; - int ret; /* default to highest possible threshold */ lpm_nyet_threshold = 0xf; @@ -1667,12 +1665,7 @@ static void dwc3_get_properties(struct dwc3 *dwc) dwc->sys_wakeup = device_may_wakeup(dwc->sysdev); - ret = device_property_read_string(dev, "usb-psy-name", &usb_psy_name); - if (ret >= 0) { - dwc->usb_psy = power_supply_get_by_name(usb_psy_name); - if (!dwc->usb_psy) - dev_err(dev, "couldn't get usb power supply\n"); - } + device_property_read_string(dev, "usb-psy-name", &dwc->usb_psy_name); dwc->has_lpm_erratum = device_property_read_bool(dev, "snps,has-lpm-erratum"); @@ -2132,19 +2125,24 @@ static int dwc3_probe(struct platform_device *pdev) dwc3_get_software_properties(dwc); + dwc->worker = kthread_create_worker(0, "dwc3-worker"); + if (IS_ERR(dwc->worker)) + return PTR_ERR(dwc->worker); + sched_set_fifo(dwc->worker->task); + dwc->reset = devm_reset_control_array_get_optional_shared(dev); if (IS_ERR(dwc->reset)) { ret = PTR_ERR(dwc->reset); - goto err_put_psy; + goto err_destroy_worker; } ret = dwc3_get_clocks(dwc); if (ret) - goto err_put_psy; + goto err_destroy_worker; ret = reset_control_deassert(dwc->reset); if (ret) - goto err_put_psy; + goto err_destroy_worker; ret = dwc3_clk_enable(dwc); if (ret) @@ -2245,9 +2243,8 @@ static int dwc3_probe(struct platform_device *pdev) dwc3_clk_disable(dwc); err_assert_reset: reset_control_assert(dwc->reset); -err_put_psy: - if (dwc->usb_psy) - power_supply_put(dwc->usb_psy); +err_destroy_worker: + kthread_destroy_worker(dwc->worker); return ret; } @@ -2258,6 +2255,7 @@ static void dwc3_remove(struct platform_device *pdev) pm_runtime_get_sync(&pdev->dev); + kthread_destroy_worker(dwc->worker); dwc3_core_exit_mode(dwc); dwc3_debugfs_exit(dwc); @@ -2276,9 +2274,6 @@ static void dwc3_remove(struct platform_device *pdev) pm_runtime_set_suspended(&pdev->dev); dwc3_free_event_buffers(dwc); - - if (dwc->usb_psy) - power_supply_put(dwc->usb_psy); } #ifdef CONFIG_PM diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index 1e561fd8b86e..3fc58204db6e 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -993,6 +993,7 @@ struct dwc3_scratchpad_array { /** * struct dwc3 - representation of our controller * @drd_work: workqueue used for role swapping + * @worker: dedicated kthread worker * @ep0_trb: trb which is used for the ctrl_req * @bounce: address of bounce buffer * @setup_buf: used while precessing STD USB requests @@ -1045,7 +1046,7 @@ struct dwc3_scratchpad_array { * @role_sw: usb_role_switch handle * @role_switch_default_mode: default operation mode of controller while * usb role is USB_ROLE_NONE. - * @usb_psy: pointer to power supply interface. + * @usb_psy_name: name of the usb power supply interface * @usb2_phy: pointer to USB2 PHY * @usb3_phy: pointer to USB3 PHY * @usb2_generic_phy: pointer to array of USB2 PHYs @@ -1163,6 +1164,7 @@ struct dwc3_scratchpad_array { */ struct dwc3 { struct work_struct drd_work; + struct kthread_worker *worker; struct dwc3_trb *ep0_trb; void *bounce; u8 *setup_buf; @@ -1223,7 +1225,7 @@ struct dwc3 { struct usb_role_switch *role_sw; enum usb_dr_mode role_switch_default_mode; - struct power_supply *usb_psy; + const char *usb_psy_name; u32 fladj; u32 ref_clk_per; diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 89fc690fdf34..1ff583281eff 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -30,6 +30,11 @@ #define DWC3_ALIGN_FRAME(d, n) (((d)->frame_number + ((d)->interval * (n))) \ & ~((d)->interval - 1)) +struct dwc3_psy_put { + struct kthread_work work; + struct power_supply *psy; +}; + /** * dwc3_gadget_set_test_mode - enables usb2 test modes * @dwc: pointer to our context structure @@ -3047,22 +3052,49 @@ static void dwc3_gadget_set_ssp_rate(struct usb_gadget *g, spin_unlock_irqrestore(&dwc->lock, flags); } +static void dwc3_gadget_psy_put(struct kthread_work *work) +{ + struct dwc3_psy_put *psy_put = container_of(work, struct dwc3_psy_put, work); + + power_supply_put(psy_put->psy); + kfree(psy_put); +} + static int dwc3_gadget_vbus_draw(struct usb_gadget *g, unsigned int mA) { - struct dwc3 *dwc = gadget_to_dwc(g); + struct dwc3 *dwc = gadget_to_dwc(g); + struct power_supply *usb_psy; union power_supply_propval val = {0}; + struct dwc3_psy_put *psy_put; int ret; if (dwc->usb2_phy) return usb_phy_set_power(dwc->usb2_phy, mA); - if (!dwc->usb_psy) + if (!dwc->usb_psy_name) return -EOPNOTSUPP; + usb_psy = power_supply_get_by_name(dwc->usb_psy_name); + if (!usb_psy) { + dev_err(dwc->dev, "couldn't get usb power supply\n"); + return -ENODEV; + } + val.intval = 1000 * mA; - ret = power_supply_set_property(dwc->usb_psy, POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT, &val); + ret = power_supply_set_property(usb_psy, POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT, &val); + if (ret < 0) { + dev_err(dwc->dev, "failed to set power supply property\n"); + return ret; + } - return ret; + psy_put = kzalloc(sizeof(*psy_put), GFP_ATOMIC); + if (!psy_put) + return -ENOMEM; + kthread_init_work(&psy_put->work, dwc3_gadget_psy_put); + psy_put->psy = usb_psy; + kthread_queue_work(dwc->worker, &psy_put->work); + + return 0; } /** -- 2.46.0.rc2.264.g509ed76dc8-goog

9 months

2
5
0 0

[to-be-updated] crash-fix-riscv64-crash-memory-reserve-dead-loop.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: crash: Fix riscv64 crash memory reserve dead loop has been removed from the -mm tree. Its filename was crash-fix-riscv64-crash-memory-reserve-dead-loop.patch This patch was dropped because an updated version will be issued ------------------------------------------------------ From: Jinjie Ruan <ruanjinjie(a)huawei.com> Subject: crash: Fix riscv64 crash memory reserve dead loop Date: Fri, 2 Aug 2024 17:01:05 +0800 On RISCV64 Qemu machine with 512MB memory, cmdline "crashkernel=500M,high" will cause system stall as below: Zone ranges: DMA32 [mem 0x0000000080000000-0x000000009fffffff] Normal empty Movable zone start for each node Early memory node ranges node 0: [mem 0x0000000080000000-0x000000008005ffff] node 0: [mem 0x0000000080060000-0x000000009fffffff] Initmem setup node 0 [mem 0x0000000080000000-0x000000009fffffff] (stall here) commit 5d99cadf1568 ("crash: fix x86_32 crash memory reserve dead loop bug") fix this on 32-bit architecture. However, the problem is not completely solved. If `CRASH_ADDR_LOW_MAX = CRASH_ADDR_HIGH_MAX` on 64-bit architecture, for example, when system memory is equal to CRASH_ADDR_LOW_MAX on RISCV64, the following infinite loop will also occur: -> reserve_crashkernel_generic() and high is true -> alloc at [CRASH_ADDR_LOW_MAX, CRASH_ADDR_HIGH_MAX] fail -> alloc at [0, CRASH_ADDR_LOW_MAX] fail and repeatedly (because CRASH_ADDR_LOW_MAX = CRASH_ADDR_HIGH_MAX). Before refactor in commit 9c08a2a139fe ("x86: kdump: use generic interface to simplify crashkernel reservation code"), x86 do not try to reserve crash memory at low if it fails to alloc above high 4G. However before refator in commit fdc268232dbba ("arm64: kdump: use generic interface to simplify crashkernel reservation"), arm64 try to reserve crash memory at low if it fails above high 4G. For 64-bit systems, this attempt is less beneficial than the opposite, remove it to fix this bug and align with native x86 implementation. After this patch, it print: cannot allocate crashkernel (size:0x1f400000) Link: https://lkml.kernel.org/r/20240802090105.3871929-1-ruanjinjie@huawei.com Fixes: 39365395046f ("riscv: kdump: use generic interface to simplify crashkernel reservation") Signed-off-by: Jinjie Ruan <ruanjinjie(a)huawei.com> Acked-by: Baoquan He <bhe(a)redhat.com> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Albert Ou <aou(a)eecs.berkeley.edu> Cc: Chen Jiahao <chenjiahao16(a)huawei.com> Cc: Dave Young <dyoung(a)redhat.com> Cc: Palmer Dabbelt <palmer(a)dabbelt.com> Cc: Paul Walmsley <paul.walmsley(a)sifive.com> Cc: Vivek Goyal <vgoyal(a)redhat.com> Cc: Alexandre Ghiti <alex(a)ghiti.fr> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- kernel/crash_reserve.c | 9 --------- 1 file changed, 9 deletions(-) --- a/kernel/crash_reserve.c~crash-fix-riscv64-crash-memory-reserve-dead-loop +++ a/kernel/crash_reserve.c @@ -416,15 +416,6 @@ retry: goto retry; } - /* - * For crashkernel=size[KMG],high, if the first attempt was - * for high memory, fall back to low memory. - */ - if (high && search_end == CRASH_ADDR_HIGH_MAX) { - search_end = CRASH_ADDR_LOW_MAX; - search_base = 0; - goto retry; - } pr_warn("cannot allocate crashkernel (size:0x%llx)\n", crash_size); return; _ Patches currently in -mm which might be from ruanjinjie(a)huawei.com are crash-fix-x86_32-crash-memory-reserve-dead-loop-bug.patch crash-fix-x86_32-crash-memory-reserve-dead-loop.patch arm-use-generic-interface-to-simplify-crashkernel-reservation.patch crash-fix-crash-memory-reserve-exceed-system-memory-bug.patch

9 months

1
0
0 0

[PATCH 22/24] drm/amd/display: Adjust cursor position

by Tom Chung

From: Rodrigo Siqueira <Rodrigo.Siqueira(a)amd.com> [why & how] When the commit 9d84c7ef8a87 ("drm/amd/display: Correct cursor position on horizontal mirror") was introduced, it used the wrong calculation for the position copy for X. This commit uses the correct calculation for that based on the original patch. Fixes: 9d84c7ef8a87 ("drm/amd/display: Correct cursor position on horizontal mirror") Cc: Mario Limonciello <mario.limonciello(a)amd.com> Cc: Alex Deucher <alexander.deucher(a)amd.com> Cc: stable(a)vger.kernel.org Acked-by: Wayne Lin <wayne.lin(a)amd.com> Signed-off-by: Rodrigo Siqueira <Rodrigo.Siqueira(a)amd.com> Signed-off-by: Tom Chung <chiahsuan.chung(a)amd.com> --- drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c index 802902f54d09..01dffed4d30b 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c @@ -3687,7 +3687,7 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) (int)hubp->curs_attr.width || pos_cpy.x <= (int)hubp->curs_attr.width + pipe_ctx->plane_state->src_rect.x) { - pos_cpy.x = 2 * viewport_width - temp_x; + pos_cpy.x = temp_x + viewport_width; } } } else { -- 2.34.1

9 months

3
2
0 0

[PATCH v3 2/3] mm/numa: no task_numa_fault() call if PMD is changed

by Zi Yan

When handling a numa page fault, task_numa_fault() should be called by a process that restores the page table of the faulted folio to avoid duplicated stats counting. Commit c5b5a3dd2c1f ("mm: thp: refactor NUMA fault handling") restructured do_huge_pmd_numa_page() and did not avoid task_numa_fault() call in the second page table check after a numa migration failure. Fix it by making all !pmd_same() return immediately. This issue can cause task_numa_fault() being called more than necessary and lead to unexpected numa balancing results (It is hard to tell whether the issue will cause positive or negative performance impact due to duplicated numa fault counting). Reported-by: "Huang, Ying" <ying.huang(a)intel.com> Closes: https://lore.kernel.org/linux-mm/87zfqfw0yw.fsf@yhuang6-desk2.ccr.corp.inte… Fixes: c5b5a3dd2c1f ("mm: thp: refactor NUMA fault handling") Cc: <stable(a)vger.kernel.org> Signed-off-by: Zi Yan <ziy(a)nvidia.com> --- mm/huge_memory.c | 29 +++++++++++++---------------- 1 file changed, 13 insertions(+), 16 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 0024266dea0a..666fa675e5b6 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1681,7 +1681,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) { spin_unlock(vmf->ptl); - goto out; + return 0; } pmd = pmd_modify(oldpmd, vma->vm_page_prot); @@ -1724,22 +1724,16 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) if (!migrate_misplaced_folio(folio, vma, target_nid)) { flags |= TNF_MIGRATED; nid = target_nid; - } else { - flags |= TNF_MIGRATE_FAIL; - vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); - if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) { - spin_unlock(vmf->ptl); - goto out; - } - goto out_map; - } - -out: - if (nid != NUMA_NO_NODE) task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags); + return 0; + } - return 0; - + flags |= TNF_MIGRATE_FAIL; + vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); + if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) { + spin_unlock(vmf->ptl); + return 0; + } out_map: /* Restore the PMD */ pmd = pmd_modify(oldpmd, vma->vm_page_prot); @@ -1749,7 +1743,10 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) set_pmd_at(vma->vm_mm, haddr, vmf->pmd, pmd); update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); spin_unlock(vmf->ptl); - goto out; + + if (nid != NUMA_NO_NODE) + task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags); + return 0; } /* -- 2.43.0

9 months

2
1
0 0

[PATCH v3 1/3] mm/numa: no task_numa_fault() call if PTE is changed

by Zi Yan

When handling a numa page fault, task_numa_fault() should be called by a process that restores the page table of the faulted folio to avoid duplicated stats counting. Commit b99a342d4f11 ("NUMA balancing: reduce TLB flush via delaying mapping on hint page fault") restructured do_numa_page() and did not avoid task_numa_fault() call in the second page table check after a numa migration failure. Fix it by making all !pte_same() return immediately. This issue can cause task_numa_fault() being called more than necessary and lead to unexpected numa balancing results (It is hard to tell whether the issue will cause positive or negative performance impact due to duplicated numa fault counting). Reported-by: "Huang, Ying" <ying.huang(a)intel.com> Closes: https://lore.kernel.org/linux-mm/87zfqfw0yw.fsf@yhuang6-desk2.ccr.corp.inte… Fixes: b99a342d4f11 ("NUMA balancing: reduce TLB flush via delaying mapping on hint page fault") Cc: <stable(a)vger.kernel.org> Signed-off-by: Zi Yan <ziy(a)nvidia.com> --- mm/memory.c | 33 ++++++++++++++++----------------- 1 file changed, 16 insertions(+), 17 deletions(-) diff --git a/mm/memory.c b/mm/memory.c index 67496dc5064f..bf791da57cab 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -5461,7 +5461,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) if (unlikely(!pte_same(old_pte, vmf->orig_pte))) { pte_unmap_unlock(vmf->pte, vmf->ptl); - goto out; + return 0; } pte = pte_modify(old_pte, vma->vm_page_prot); @@ -5523,23 +5523,19 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) if (!migrate_misplaced_folio(folio, vma, target_nid)) { nid = target_nid; flags |= TNF_MIGRATED; - } else { - flags |= TNF_MIGRATE_FAIL; - vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, - vmf->address, &vmf->ptl); - if (unlikely(!vmf->pte)) - goto out; - if (unlikely(!pte_same(ptep_get(vmf->pte), vmf->orig_pte))) { - pte_unmap_unlock(vmf->pte, vmf->ptl); - goto out; - } - goto out_map; + task_numa_fault(last_cpupid, nid, nr_pages, flags); + return 0; } -out: - if (nid != NUMA_NO_NODE) - task_numa_fault(last_cpupid, nid, nr_pages, flags); - return 0; + flags |= TNF_MIGRATE_FAIL; + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, + vmf->address, &vmf->ptl); + if (unlikely(!vmf->pte)) + return 0; + if (unlikely(!pte_same(ptep_get(vmf->pte), vmf->orig_pte))) { + pte_unmap_unlock(vmf->pte, vmf->ptl); + return 0; + } out_map: /* * Make it present again, depending on how arch implements @@ -5552,7 +5548,10 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) numa_rebuild_single_mapping(vmf, vma, vmf->address, vmf->pte, writable); pte_unmap_unlock(vmf->pte, vmf->ptl); - goto out; + + if (nid != NUMA_NO_NODE) + task_numa_fault(last_cpupid, nid, nr_pages, flags); + return 0; } static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf) -- 2.43.0

9 months

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror