Linux-stable-mirror November 2024

linux-stable-mirror@lists.linaro.org

9 participants
16 discussions

+ mm-multi-gen-lru-use-pteppmdp_clear_young_notify.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: mm: multi-gen LRU: use {ptep,pmdp}_clear_young_notify() has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-multi-gen-lru-use-pteppmdp_clear_young_notify.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: Yu Zhao <yuzhao(a)google.com> Subject: mm: multi-gen LRU: use {ptep,pmdp}_clear_young_notify() Date: Sat, 19 Oct 2024 01:29:39 +0000 When the MM_WALK capability is enabled, memory that is mostly accessed by a VM appears younger than it really is, therefore this memory will be less likely to be evicted. Therefore, the presence of a running VM can significantly increase swap-outs for non-VM memory, regressing the performance for the rest of the system. Fix this regression by always calling {ptep,pmdp}_clear_young_notify() whenever we clear the young bits on PMDs/PTEs. Link: https://lkml.kernel.org/r/20241019012940.3656292-3-jthoughton@google.com Fixes: bd74fdaea146 ("mm: multi-gen LRU: support page table walks") Signed-off-by: Yu Zhao <yuzhao(a)google.com> Signed-off-by: James Houghton <jthoughton(a)google.com> Reported-by: David Stevens <stevensd(a)google.com> Cc: Axel Rasmussen <axelrasmussen(a)google.com> Cc: David Matlack <dmatlack(a)google.com> Cc: David Rientjes <rientjes(a)google.com> Cc: Oliver Upton <oliver.upton(a)linux.dev> Cc: Paolo Bonzini <pbonzini(a)redhat.com> Cc: Sean Christopherson <seanjc(a)google.com> Cc: Wei Xu <weixugc(a)google.com> Cc: <stable(a)vger.kernel.org> Cc: kernel test robot <lkp(a)intel.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/mmzone.h | 5 +- mm/rmap.c | 9 +-- mm/vmscan.c | 91 +++++++++++++++++++++------------------ 3 files changed, 55 insertions(+), 50 deletions(-) --- a/include/linux/mmzone.h~mm-multi-gen-lru-use-pteppmdp_clear_young_notify +++ a/include/linux/mmzone.h @@ -555,7 +555,7 @@ struct lru_gen_memcg { void lru_gen_init_pgdat(struct pglist_data *pgdat); void lru_gen_init_lruvec(struct lruvec *lruvec); -void lru_gen_look_around(struct page_vma_mapped_walk *pvmw); +bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw); void lru_gen_init_memcg(struct mem_cgroup *memcg); void lru_gen_exit_memcg(struct mem_cgroup *memcg); @@ -574,8 +574,9 @@ static inline void lru_gen_init_lruvec(s { } -static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) +static inline bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw) { + return false; } static inline void lru_gen_init_memcg(struct mem_cgroup *memcg) --- a/mm/rmap.c~mm-multi-gen-lru-use-pteppmdp_clear_young_notify +++ a/mm/rmap.c @@ -885,13 +885,10 @@ static bool folio_referenced_one(struct return false; } - if (pvmw.pte) { - if (lru_gen_enabled() && - pte_young(ptep_get(pvmw.pte))) { - lru_gen_look_around(&pvmw); + if (lru_gen_enabled() && pvmw.pte) { + if (lru_gen_look_around(&pvmw)) referenced++; - } - + } else if (pvmw.pte) { if (ptep_clear_flush_young_notify(vma, address, pvmw.pte)) referenced++; --- a/mm/vmscan.c~mm-multi-gen-lru-use-pteppmdp_clear_young_notify +++ a/mm/vmscan.c @@ -56,6 +56,7 @@ #include <linux/khugepaged.h> #include <linux/rculist_nulls.h> #include <linux/random.h> +#include <linux/mmu_notifier.h> #include <asm/tlbflush.h> #include <asm/div64.h> @@ -3294,7 +3295,8 @@ static bool get_next_vma(unsigned long m return false; } -static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned long addr) +static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned long addr, + struct pglist_data *pgdat) { unsigned long pfn = pte_pfn(pte); @@ -3306,13 +3308,20 @@ static unsigned long get_pte_pfn(pte_t p if (WARN_ON_ONCE(pte_devmap(pte) || pte_special(pte))) return -1; + if (!pte_young(pte) && !mm_has_notifiers(vma->vm_mm)) + return -1; + if (WARN_ON_ONCE(!pfn_valid(pfn))) return -1; + if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) + return -1; + return pfn; } -static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned long addr) +static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned long addr, + struct pglist_data *pgdat) { unsigned long pfn = pmd_pfn(pmd); @@ -3324,9 +3333,15 @@ static unsigned long get_pmd_pfn(pmd_t p if (WARN_ON_ONCE(pmd_devmap(pmd))) return -1; + if (!pmd_young(pmd) && !mm_has_notifiers(vma->vm_mm)) + return -1; + if (WARN_ON_ONCE(!pfn_valid(pfn))) return -1; + if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) + return -1; + return pfn; } @@ -3335,10 +3350,6 @@ static struct folio *get_pfn_folio(unsig { struct folio *folio; - /* try to avoid unnecessary memory loads */ - if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) - return NULL; - folio = pfn_folio(pfn); if (folio_nid(folio) != pgdat->node_id) return NULL; @@ -3394,20 +3405,16 @@ restart: total++; walk->mm_stats[MM_LEAF_TOTAL]++; - pfn = get_pte_pfn(ptent, args->vma, addr); + pfn = get_pte_pfn(ptent, args->vma, addr, pgdat); if (pfn == -1) continue; - if (!pte_young(ptent)) { - continue; - } - folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap); if (!folio) continue; - if (!ptep_test_and_clear_young(args->vma, addr, pte + i)) - VM_WARN_ON_ONCE(true); + if (!ptep_clear_young_notify(args->vma, addr, pte + i)) + continue; young++; walk->mm_stats[MM_LEAF_YOUNG]++; @@ -3473,21 +3480,22 @@ static void walk_pmd_range_locked(pud_t /* don't round down the first address */ addr = i ? (*first & PMD_MASK) + i * PMD_SIZE : *first; - pfn = get_pmd_pfn(pmd[i], vma, addr); - if (pfn == -1) - goto next; - - if (!pmd_trans_huge(pmd[i])) { - if (!walk->force_scan && should_clear_pmd_young()) + if (pmd_present(pmd[i]) && !pmd_trans_huge(pmd[i])) { + if (!walk->force_scan && should_clear_pmd_young() && + !mm_has_notifiers(args->mm)) pmdp_test_and_clear_young(vma, addr, pmd + i); goto next; } + pfn = get_pmd_pfn(pmd[i], vma, addr, pgdat); + if (pfn == -1) + goto next; + folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap); if (!folio) goto next; - if (!pmdp_test_and_clear_young(vma, addr, pmd + i)) + if (!pmdp_clear_young_notify(vma, addr, pmd + i)) goto next; walk->mm_stats[MM_LEAF_YOUNG]++; @@ -3545,24 +3553,18 @@ restart: } if (pmd_trans_huge(val)) { - unsigned long pfn = pmd_pfn(val); struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); + unsigned long pfn = get_pmd_pfn(val, vma, addr, pgdat); walk->mm_stats[MM_LEAF_TOTAL]++; - if (!pmd_young(val)) { - continue; - } - - /* try to avoid unnecessary memory loads */ - if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) - continue; - - walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first); + if (pfn != -1) + walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first); continue; } - if (!walk->force_scan && should_clear_pmd_young()) { + if (!walk->force_scan && should_clear_pmd_young() && + !mm_has_notifiers(args->mm)) { if (!pmd_young(val)) continue; @@ -4036,13 +4038,13 @@ static void lru_gen_age_node(struct pgli * the PTE table to the Bloom filter. This forms a feedback loop between the * eviction and the aging. */ -void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) +bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw) { int i; unsigned long start; unsigned long end; struct lru_gen_mm_walk *walk; - int young = 0; + int young = 1; pte_t *pte = pvmw->pte; unsigned long addr = pvmw->address; struct vm_area_struct *vma = pvmw->vma; @@ -4058,12 +4060,15 @@ void lru_gen_look_around(struct page_vma lockdep_assert_held(pvmw->ptl); VM_WARN_ON_ONCE_FOLIO(folio_test_lru(folio), folio); + if (!ptep_clear_young_notify(vma, addr, pte)) + return false; + if (spin_is_contended(pvmw->ptl)) - return; + return true; /* exclude special VMAs containing anon pages from COW */ if (vma->vm_flags & VM_SPECIAL) - return; + return true; /* avoid taking the LRU lock under the PTL when possible */ walk = current->reclaim_state ? current->reclaim_state->mm_walk : NULL; @@ -4071,6 +4076,9 @@ void lru_gen_look_around(struct page_vma start = max(addr & PMD_MASK, vma->vm_start); end = min(addr | ~PMD_MASK, vma->vm_end - 1) + 1; + if (end - start == PAGE_SIZE) + return true; + if (end - start > MIN_LRU_BATCH * PAGE_SIZE) { if (addr - start < MIN_LRU_BATCH * PAGE_SIZE / 2) end = start + MIN_LRU_BATCH * PAGE_SIZE; @@ -4084,7 +4092,7 @@ void lru_gen_look_around(struct page_vma /* folio_update_gen() requires stable folio_memcg() */ if (!mem_cgroup_trylock_pages(memcg)) - return; + return true; arch_enter_lazy_mmu_mode(); @@ -4094,19 +4102,16 @@ void lru_gen_look_around(struct page_vma unsigned long pfn; pte_t ptent = ptep_get(pte + i); - pfn = get_pte_pfn(ptent, vma, addr); + pfn = get_pte_pfn(ptent, vma, addr, pgdat); if (pfn == -1) continue; - if (!pte_young(ptent)) - continue; - folio = get_pfn_folio(pfn, memcg, pgdat, can_swap); if (!folio) continue; - if (!ptep_test_and_clear_young(vma, addr, pte + i)) - VM_WARN_ON_ONCE(true); + if (!ptep_clear_young_notify(vma, addr, pte + i)) + continue; young++; @@ -4136,6 +4141,8 @@ void lru_gen_look_around(struct page_vma /* feedback from rmap walkers to page table walkers */ if (mm_state && suitable_to_scan(i, young)) update_bloom_filter(mm_state, max_seq, pvmw->pmd); + + return true; } /****************************************************************************** _ Patches currently in -mm which might be from yuzhao(a)google.com are mm-multi-gen-lru-remove-mm_leaf_old-and-mm_nonleaf_total-stats.patch mm-multi-gen-lru-use-pteppmdp_clear_young_notify.patch mm-page_alloc-keep-track-of-free-highatomic.patch

3 hours, 18 minutes

+ mm-multi-gen-lru-remove-mm_leaf_old-and-mm_nonleaf_total-stats.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: mm: multi-gen LRU: remove MM_LEAF_OLD and MM_NONLEAF_TOTAL stats has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-multi-gen-lru-remove-mm_leaf_old-and-mm_nonleaf_total-stats.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: Yu Zhao <yuzhao(a)google.com> Subject: mm: multi-gen LRU: remove MM_LEAF_OLD and MM_NONLEAF_TOTAL stats Date: Sat, 19 Oct 2024 01:29:38 +0000 Patch series "mm: multi-gen LRU: Have secondary MMUs participate in MM_WALK". Today, the MM_WALK capability causes MGLRU to clear the young bit from PMDs and PTEs during the page table walk before eviction, but MGLRU does not call the clear_young() MMU notifier in this case. By not calling this notifier, the MM walk takes less time/CPU, but it causes pages that are accessed mostly through KVM / secondary MMUs to appear younger than they should be. We do call the clear_young() notifier today, but only when attempting to evict the page, so we end up clearing young/accessed information less frequently for secondary MMUs than for mm PTEs, and therefore they appear younger and are less likely to be evicted. Therefore, memory that is *not* being accessed mostly by KVM will be evicted *more* frequently, worsening performance. ChromeOS observed a tab-open latency regression when enabling MGLRU with a setup that involved running a VM: Tab-open latency histogram (ms) Version p50 mean p95 p99 max base 1315 1198 2347 3454 10319 mglru 2559 1311 7399 12060 43758 fix 1119 926 2470 4211 6947 This series replaces the final non-selftest patchs from this series[1], which introduced a similar change (and a new MMU notifier) with KVM optimizations. I'll send a separate series (to Sean and Paolo) for the KVM optimizations. This series also makes proactive reclaim with MGLRU possible for KVM memory. I have verified that this functions correctly with the selftest from [1], but given that that test is a KVM selftest, I'll send it with the rest of the KVM optimizations later. Andrew, let me know if you'd like to take the test now anyway. [1]: https://lore.kernel.org/linux-mm/20240926013506.860253-18-jthoughton@google… This patch (of 2): The removed stats, MM_LEAF_OLD and MM_NONLEAF_TOTAL, are not very helpful and become more complicated to properly compute when adding test/clear_young() notifiers in MGLRU's mm walk. Link: https://lkml.kernel.org/r/20241019012940.3656292-1-jthoughton@google.com Link: https://lkml.kernel.org/r/20241019012940.3656292-2-jthoughton@google.com Fixes: bd74fdaea146 ("mm: multi-gen LRU: support page table walks") Signed-off-by: Yu Zhao <yuzhao(a)google.com> Signed-off-by: James Houghton <jthoughton(a)google.com> Cc: Axel Rasmussen <axelrasmussen(a)google.com> Cc: David Matlack <dmatlack(a)google.com> Cc: David Rientjes <rientjes(a)google.com> Cc: David Stevens <stevensd(a)google.com> Cc: Oliver Upton <oliver.upton(a)linux.dev> Cc: Paolo Bonzini <pbonzini(a)redhat.com> Cc: Sean Christopherson <seanjc(a)google.com> Cc: Wei Xu <weixugc(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/mmzone.h | 2 -- mm/vmscan.c | 14 +++++--------- 2 files changed, 5 insertions(+), 11 deletions(-) --- a/include/linux/mmzone.h~mm-multi-gen-lru-remove-mm_leaf_old-and-mm_nonleaf_total-stats +++ a/include/linux/mmzone.h @@ -458,9 +458,7 @@ struct lru_gen_folio { enum { MM_LEAF_TOTAL, /* total leaf entries */ - MM_LEAF_OLD, /* old leaf entries */ MM_LEAF_YOUNG, /* young leaf entries */ - MM_NONLEAF_TOTAL, /* total non-leaf entries */ MM_NONLEAF_FOUND, /* non-leaf entries found in Bloom filters */ MM_NONLEAF_ADDED, /* non-leaf entries added to Bloom filters */ NR_MM_STATS --- a/mm/vmscan.c~mm-multi-gen-lru-remove-mm_leaf_old-and-mm_nonleaf_total-stats +++ a/mm/vmscan.c @@ -3399,7 +3399,6 @@ restart: continue; if (!pte_young(ptent)) { - walk->mm_stats[MM_LEAF_OLD]++; continue; } @@ -3552,7 +3551,6 @@ restart: walk->mm_stats[MM_LEAF_TOTAL]++; if (!pmd_young(val)) { - walk->mm_stats[MM_LEAF_OLD]++; continue; } @@ -3564,8 +3562,6 @@ restart: continue; } - walk->mm_stats[MM_NONLEAF_TOTAL]++; - if (!walk->force_scan && should_clear_pmd_young()) { if (!pmd_young(val)) continue; @@ -5254,11 +5250,11 @@ static void lru_gen_seq_show_full(struct for (tier = 0; tier < MAX_NR_TIERS; tier++) { seq_printf(m, " %10d", tier); for (type = 0; type < ANON_AND_FILE; type++) { - const char *s = " "; + const char *s = "xxx"; unsigned long n[3] = {}; if (seq == max_seq) { - s = "RT "; + s = "RTx"; n[0] = READ_ONCE(lrugen->avg_refaulted[type][tier]); n[1] = READ_ONCE(lrugen->avg_total[type][tier]); } else if (seq == min_seq[type] || NR_HIST_GENS > 1) { @@ -5280,14 +5276,14 @@ static void lru_gen_seq_show_full(struct seq_puts(m, " "); for (i = 0; i < NR_MM_STATS; i++) { - const char *s = " "; + const char *s = "xxxx"; unsigned long n = 0; if (seq == max_seq && NR_HIST_GENS == 1) { - s = "LOYNFA"; + s = "TYFA"; n = READ_ONCE(mm_state->stats[hist][i]); } else if (seq != max_seq && NR_HIST_GENS > 1) { - s = "loynfa"; + s = "tyfa"; n = READ_ONCE(mm_state->stats[hist][i]); } _ Patches currently in -mm which might be from yuzhao(a)google.com are mm-multi-gen-lru-remove-mm_leaf_old-and-mm_nonleaf_total-stats.patch mm-multi-gen-lru-use-pteppmdp_clear_young_notify.patch mm-page_alloc-keep-track-of-free-highatomic.patch

3 hours, 18 minutes

[merged mm-hotfixes-stable] mm-multi-gen-lru-use-pteppmdp_clear_young_notify.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm: multi-gen LRU: use {ptep,pmdp}_clear_young_notify() has been removed from the -mm tree. Its filename was mm-multi-gen-lru-use-pteppmdp_clear_young_notify.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Yu Zhao <yuzhao(a)google.com> Subject: mm: multi-gen LRU: use {ptep,pmdp}_clear_young_notify() Date: Sat, 19 Oct 2024 01:29:39 +0000 When the MM_WALK capability is enabled, memory that is mostly accessed by a VM appears younger than it really is, therefore this memory will be less likely to be evicted. Therefore, the presence of a running VM can significantly increase swap-outs for non-VM memory, regressing the performance for the rest of the system. Fix this regression by always calling {ptep,pmdp}_clear_young_notify() whenever we clear the young bits on PMDs/PTEs. Link: https://lkml.kernel.org/r/20241019012940.3656292-3-jthoughton@google.com Fixes: bd74fdaea146 ("mm: multi-gen LRU: support page table walks") Signed-off-by: Yu Zhao <yuzhao(a)google.com> Signed-off-by: James Houghton <jthoughton(a)google.com> Reported-by: David Stevens <stevensd(a)google.com> Cc: Axel Rasmussen <axelrasmussen(a)google.com> Cc: David Matlack <dmatlack(a)google.com> Cc: David Rientjes <rientjes(a)google.com> Cc: Oliver Upton <oliver.upton(a)linux.dev> Cc: Paolo Bonzini <pbonzini(a)redhat.com> Cc: Sean Christopherson <seanjc(a)google.com> Cc: Wei Xu <weixugc(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/mmzone.h | 5 +- mm/rmap.c | 9 +-- mm/vmscan.c | 91 +++++++++++++++++++++------------------ 3 files changed, 55 insertions(+), 50 deletions(-) --- a/include/linux/mmzone.h~mm-multi-gen-lru-use-pteppmdp_clear_young_notify +++ a/include/linux/mmzone.h @@ -555,7 +555,7 @@ struct lru_gen_memcg { void lru_gen_init_pgdat(struct pglist_data *pgdat); void lru_gen_init_lruvec(struct lruvec *lruvec); -void lru_gen_look_around(struct page_vma_mapped_walk *pvmw); +bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw); void lru_gen_init_memcg(struct mem_cgroup *memcg); void lru_gen_exit_memcg(struct mem_cgroup *memcg); @@ -574,8 +574,9 @@ static inline void lru_gen_init_lruvec(s { } -static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) +static inline bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw) { + return false; } static inline void lru_gen_init_memcg(struct mem_cgroup *memcg) --- a/mm/rmap.c~mm-multi-gen-lru-use-pteppmdp_clear_young_notify +++ a/mm/rmap.c @@ -885,13 +885,10 @@ static bool folio_referenced_one(struct return false; } - if (pvmw.pte) { - if (lru_gen_enabled() && - pte_young(ptep_get(pvmw.pte))) { - lru_gen_look_around(&pvmw); + if (lru_gen_enabled() && pvmw.pte) { + if (lru_gen_look_around(&pvmw)) referenced++; - } - + } else if (pvmw.pte) { if (ptep_clear_flush_young_notify(vma, address, pvmw.pte)) referenced++; --- a/mm/vmscan.c~mm-multi-gen-lru-use-pteppmdp_clear_young_notify +++ a/mm/vmscan.c @@ -56,6 +56,7 @@ #include <linux/khugepaged.h> #include <linux/rculist_nulls.h> #include <linux/random.h> +#include <linux/mmu_notifier.h> #include <asm/tlbflush.h> #include <asm/div64.h> @@ -3294,7 +3295,8 @@ static bool get_next_vma(unsigned long m return false; } -static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned long addr) +static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned long addr, + struct pglist_data *pgdat) { unsigned long pfn = pte_pfn(pte); @@ -3306,13 +3308,20 @@ static unsigned long get_pte_pfn(pte_t p if (WARN_ON_ONCE(pte_devmap(pte) || pte_special(pte))) return -1; + if (!pte_young(pte) && !mm_has_notifiers(vma->vm_mm)) + return -1; + if (WARN_ON_ONCE(!pfn_valid(pfn))) return -1; + if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) + return -1; + return pfn; } -static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned long addr) +static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned long addr, + struct pglist_data *pgdat) { unsigned long pfn = pmd_pfn(pmd); @@ -3324,9 +3333,15 @@ static unsigned long get_pmd_pfn(pmd_t p if (WARN_ON_ONCE(pmd_devmap(pmd))) return -1; + if (!pmd_young(pmd) && !mm_has_notifiers(vma->vm_mm)) + return -1; + if (WARN_ON_ONCE(!pfn_valid(pfn))) return -1; + if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) + return -1; + return pfn; } @@ -3335,10 +3350,6 @@ static struct folio *get_pfn_folio(unsig { struct folio *folio; - /* try to avoid unnecessary memory loads */ - if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) - return NULL; - folio = pfn_folio(pfn); if (folio_nid(folio) != pgdat->node_id) return NULL; @@ -3394,20 +3405,16 @@ restart: total++; walk->mm_stats[MM_LEAF_TOTAL]++; - pfn = get_pte_pfn(ptent, args->vma, addr); + pfn = get_pte_pfn(ptent, args->vma, addr, pgdat); if (pfn == -1) continue; - if (!pte_young(ptent)) { - continue; - } - folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap); if (!folio) continue; - if (!ptep_test_and_clear_young(args->vma, addr, pte + i)) - VM_WARN_ON_ONCE(true); + if (!ptep_clear_young_notify(args->vma, addr, pte + i)) + continue; young++; walk->mm_stats[MM_LEAF_YOUNG]++; @@ -3473,21 +3480,22 @@ static void walk_pmd_range_locked(pud_t /* don't round down the first address */ addr = i ? (*first & PMD_MASK) + i * PMD_SIZE : *first; - pfn = get_pmd_pfn(pmd[i], vma, addr); - if (pfn == -1) - goto next; - - if (!pmd_trans_huge(pmd[i])) { - if (!walk->force_scan && should_clear_pmd_young()) + if (pmd_present(pmd[i]) && !pmd_trans_huge(pmd[i])) { + if (!walk->force_scan && should_clear_pmd_young() && + !mm_has_notifiers(args->mm)) pmdp_test_and_clear_young(vma, addr, pmd + i); goto next; } + pfn = get_pmd_pfn(pmd[i], vma, addr, pgdat); + if (pfn == -1) + goto next; + folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap); if (!folio) goto next; - if (!pmdp_test_and_clear_young(vma, addr, pmd + i)) + if (!pmdp_clear_young_notify(vma, addr, pmd + i)) goto next; walk->mm_stats[MM_LEAF_YOUNG]++; @@ -3545,24 +3553,18 @@ restart: } if (pmd_trans_huge(val)) { - unsigned long pfn = pmd_pfn(val); struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); + unsigned long pfn = get_pmd_pfn(val, vma, addr, pgdat); walk->mm_stats[MM_LEAF_TOTAL]++; - if (!pmd_young(val)) { - continue; - } - - /* try to avoid unnecessary memory loads */ - if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) - continue; - - walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first); + if (pfn != -1) + walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first); continue; } - if (!walk->force_scan && should_clear_pmd_young()) { + if (!walk->force_scan && should_clear_pmd_young() && + !mm_has_notifiers(args->mm)) { if (!pmd_young(val)) continue; @@ -4036,13 +4038,13 @@ static void lru_gen_age_node(struct pgli * the PTE table to the Bloom filter. This forms a feedback loop between the * eviction and the aging. */ -void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) +bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw) { int i; unsigned long start; unsigned long end; struct lru_gen_mm_walk *walk; - int young = 0; + int young = 1; pte_t *pte = pvmw->pte; unsigned long addr = pvmw->address; struct vm_area_struct *vma = pvmw->vma; @@ -4058,12 +4060,15 @@ void lru_gen_look_around(struct page_vma lockdep_assert_held(pvmw->ptl); VM_WARN_ON_ONCE_FOLIO(folio_test_lru(folio), folio); + if (!ptep_clear_young_notify(vma, addr, pte)) + return false; + if (spin_is_contended(pvmw->ptl)) - return; + return true; /* exclude special VMAs containing anon pages from COW */ if (vma->vm_flags & VM_SPECIAL) - return; + return true; /* avoid taking the LRU lock under the PTL when possible */ walk = current->reclaim_state ? current->reclaim_state->mm_walk : NULL; @@ -4071,6 +4076,9 @@ void lru_gen_look_around(struct page_vma start = max(addr & PMD_MASK, vma->vm_start); end = min(addr | ~PMD_MASK, vma->vm_end - 1) + 1; + if (end - start == PAGE_SIZE) + return true; + if (end - start > MIN_LRU_BATCH * PAGE_SIZE) { if (addr - start < MIN_LRU_BATCH * PAGE_SIZE / 2) end = start + MIN_LRU_BATCH * PAGE_SIZE; @@ -4084,7 +4092,7 @@ void lru_gen_look_around(struct page_vma /* folio_update_gen() requires stable folio_memcg() */ if (!mem_cgroup_trylock_pages(memcg)) - return; + return true; arch_enter_lazy_mmu_mode(); @@ -4094,19 +4102,16 @@ void lru_gen_look_around(struct page_vma unsigned long pfn; pte_t ptent = ptep_get(pte + i); - pfn = get_pte_pfn(ptent, vma, addr); + pfn = get_pte_pfn(ptent, vma, addr, pgdat); if (pfn == -1) continue; - if (!pte_young(ptent)) - continue; - folio = get_pfn_folio(pfn, memcg, pgdat, can_swap); if (!folio) continue; - if (!ptep_test_and_clear_young(vma, addr, pte + i)) - VM_WARN_ON_ONCE(true); + if (!ptep_clear_young_notify(vma, addr, pte + i)) + continue; young++; @@ -4136,6 +4141,8 @@ void lru_gen_look_around(struct page_vma /* feedback from rmap walkers to page table walkers */ if (mm_state && suitable_to_scan(i, young)) update_bloom_filter(mm_state, max_seq, pvmw->pmd); + + return true; } /****************************************************************************** _ Patches currently in -mm which might be from yuzhao(a)google.com are mm-page_alloc-keep-track-of-free-highatomic.patch

3 hours, 18 minutes

[PATCH RESEND] thermal/drivers/qcom/lmh: remove false lockdep backtrace

by Dmitry Baryshkov

Annotate LMH IRQs with lockdep classes so that the lockdep doesn't report possible recursive locking issue between LMH and GIC interrupts. For the reference: CPU0 ---- lock(&irq_desc_lock_class); lock(&irq_desc_lock_class); *** DEADLOCK *** Call trace: dump_backtrace+0x98/0xf0 show_stack+0x18/0x24 dump_stack_lvl+0x90/0xd0 dump_stack+0x18/0x24 print_deadlock_bug+0x258/0x348 __lock_acquire+0x1078/0x1f44 lock_acquire+0x1fc/0x32c _raw_spin_lock_irqsave+0x60/0x88 __irq_get_desc_lock+0x58/0x98 enable_irq+0x38/0xa0 lmh_enable_interrupt+0x2c/0x38 irq_enable+0x40/0x8c __irq_startup+0x78/0xa4 irq_startup+0x78/0x168 __enable_irq+0x70/0x7c enable_irq+0x4c/0xa0 qcom_cpufreq_ready+0x20/0x2c cpufreq_online+0x2a8/0x988 cpufreq_add_dev+0x80/0x98 subsys_interface_register+0x104/0x134 cpufreq_register_driver+0x150/0x234 qcom_cpufreq_hw_driver_probe+0x2a8/0x388 platform_probe+0x68/0xc0 really_probe+0xbc/0x298 __driver_probe_device+0x78/0x12c driver_probe_device+0x3c/0x160 __device_attach_driver+0xb8/0x138 bus_for_each_drv+0x84/0xe0 __device_attach+0x9c/0x188 device_initial_probe+0x14/0x20 bus_probe_device+0xac/0xb0 deferred_probe_work_func+0x8c/0xc8 process_one_work+0x20c/0x62c worker_thread+0x1bc/0x36c kthread+0x120/0x124 ret_from_fork+0x10/0x20 Fixes: 53bca371cdf7 ("thermal/drivers/qcom: Add support for LMh driver") Cc: stable(a)vger.kernel.org Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov(a)linaro.org> --- drivers/thermal/qcom/lmh.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/thermal/qcom/lmh.c b/drivers/thermal/qcom/lmh.c index 5225b3621a56c4a11f0ae56af1060d6d1460ef02..d2d49264cf83a4c4646202044700a7a8bf3c0b95 100644 --- a/drivers/thermal/qcom/lmh.c +++ b/drivers/thermal/qcom/lmh.c @@ -73,7 +73,14 @@ static struct irq_chip lmh_irq_chip = { static int lmh_irq_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw) { struct lmh_hw_data *lmh_data = d->host_data; + static struct lock_class_key lmh_lock_key; + static struct lock_class_key lmh_request_key; + /* + * This lock class tells lockdep that GPIO irqs are in a different + * category than their parents, so it won't report false recursion. + */ + irq_set_lockdep_class(irq, &lmh_lock_key, &lmh_request_key); irq_set_chip_and_handler(irq, &lmh_irq_chip, handle_simple_irq); irq_set_chip_data(irq, lmh_data); --- base-commit: 797012914d2d031430268fe512af0ccd7d8e46ef change-id: 20240721-lmh-lockdep-88de09e77089 Best regards, -- Dmitry Baryshkov <dmitry.baryshkov(a)linaro.org>

3 hours, 22 minutes

+ mm-damon-core-handle-zero-schemes-apply-interval.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: mm/damon/core: handle zero schemes apply interval has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-damon-core-handle-zero-schemes-apply-interval.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: SeongJae Park <sj(a)kernel.org> Subject: mm/damon/core: handle zero schemes apply interval Date: Thu, 31 Oct 2024 11:37:57 -0700 DAMON's logics to determine if this is the time to apply damos schemes assumes next_apply_sis is always set larger than current passed_sample_intervals. And therefore assume continuously incrementing passed_sample_intervals will make it reaches to the next_apply_sis in future. The logic hence does apply the scheme and update next_apply_sis only if passed_sample_intervals is same to next_apply_sis. If Schemes apply interval is set as zero, however, next_apply_sis is set same to current passed_sample_intervals, respectively. And passed_sample_intervals is incremented before doing the next_apply_sis check. Hence, next_apply_sis becomes larger than next_apply_sis, and the logic says it is not the time to apply schemes and update next_apply_sis. In other words, DAMON stops applying schemes until passed_sample_intervals overflows. Based on the documents and the common sense, a reasonable behavior for such inputs would be applying the schemes for every sampling interval. Handle the case by removing the assumption. Link: https://lkml.kernel.org/r/20241031183757.49610-3-sj@kernel.org Fixes: 42f994b71404 ("mm/damon/core: implement scheme-specific apply interval") Signed-off-by: SeongJae Park <sj(a)kernel.org> Cc: <stable(a)vger.kernel.org> [6.7.x] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/damon/core.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) --- a/mm/damon/core.c~mm-damon-core-handle-zero-schemes-apply-interval +++ a/mm/damon/core.c @@ -1412,7 +1412,7 @@ static void damon_do_apply_schemes(struc damon_for_each_scheme(s, c) { struct damos_quota *quota = &s->quota; - if (c->passed_sample_intervals != s->next_apply_sis) + if (c->passed_sample_intervals < s->next_apply_sis) continue; if (!s->wmarks.activated) @@ -1622,7 +1622,7 @@ static void kdamond_apply_schemes(struct bool has_schemes_to_apply = false; damon_for_each_scheme(s, c) { - if (c->passed_sample_intervals != s->next_apply_sis) + if (c->passed_sample_intervals < s->next_apply_sis) continue; if (!s->wmarks.activated) @@ -1642,9 +1642,9 @@ static void kdamond_apply_schemes(struct } damon_for_each_scheme(s, c) { - if (c->passed_sample_intervals != s->next_apply_sis) + if (c->passed_sample_intervals < s->next_apply_sis) continue; - s->next_apply_sis += + s->next_apply_sis = c->passed_sample_intervals + (s->apply_interval_us ? s->apply_interval_us : c->attrs.aggr_interval) / sample_interval; } _ Patches currently in -mm which might be from sj(a)kernel.org are mm-damon-core-handle-zero-aggregationops_update-intervals.patch mm-damon-core-handle-zero-schemes-apply-interval.patch selftests-damon-huge_count_read_write-remove-unnecessary-debugging-message.patch selftests-damon-_debugfs_common-hide-expected-error-message-from-test_write_result.patch selftests-damon-debugfs_duplicate_context_creation-hide-errors-from-expected-file-write-failures.patch mm-damon-kconfig-update-dbgfs_kunit-prompt-copy-for-sysfs_kunit.patch mm-damon-tests-dbgfs-kunit-fix-the-header-double-inclusion-guarding-ifdef-comment.patch

4 hours, 2 minutes

+ mm-damon-core-handle-zero-aggregationops_update-intervals.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: mm/damon/core: handle zero {aggregation,ops_update} intervals has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-damon-core-handle-zero-aggregationops_update-intervals.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: SeongJae Park <sj(a)kernel.org> Subject: mm/damon/core: handle zero {aggregation,ops_update} intervals Date: Thu, 31 Oct 2024 11:37:56 -0700 Patch series "mm/damon/core: fix handling of zero non-sampling intervals". DAMON's internal intervals accounting logic is not correctly handling non-sampling intervals of zero values for a wrong assumption. This could cause unexpected monitoring behavior, and even result in infinite hang of DAMON sysfs interface user threads in case of zero aggregation interval. Fix those by updating the intervals accounting logic. For details of the root case and solutions, please refer to commit messages of fixes. This patch (of 2): DAMON's logics to determine if this is the time to do aggregation and ops update assumes next_{aggregation,ops_update}_sis are always set larger than current passed_sample_intervals. And therefore it further assumes continuously incrementing passed_sample_intervals every sampling interval will make it reaches to the next_{aggregation,ops_update}_sis in future. The logic therefore make the action and update next_{aggregation,ops_updaste}_sis only if passed_sample_intervals is same to the counts, respectively. If Aggregation interval or Ops update interval are zero, however, next_aggregation_sis or next_ops_update_sis are set same to current passed_sample_intervals, respectively. And passed_sample_intervals is incremented before doing the next_{aggregation,ops_update}_sis check. Hence, passed_sample_intervals becomes larger than next_{aggregation,ops_update}_sis, and the logic says it is not the time to do the action and update next_{aggregation,ops_update}_sis forever, until an overflow happens. In other words, DAMON stops doing aggregations or ops updates effectively forever, and users cannot get monitoring results. Based on the documents and the common sense, a reasonable behavior for such inputs is doing an aggregation and an ops update for every sampling interval. Handle the case by removing the assumption. Note that this could incur particular real issue for DAMON sysfs interface users, in case of zero Aggregation interval. When user starts DAMON with zero Aggregation interval and asks online DAMON parameter tuning via DAMON sysfs interface, the request is handled by the aggregation callback. Until the callback finishes the work, the user who requested the online tuning just waits. Hence, the user will be stuck until the passed_sample_intervals overflows. Link: https://lkml.kernel.org/r/20241031183757.49610-1-sj@kernel.org Link: https://lkml.kernel.org/r/20241031183757.49610-2-sj@kernel.org Fixes: 4472edf63d66 ("mm/damon/core: use number of passed access sampling as a timer") Signed-off-by: SeongJae Park <sj(a)kernel.org> Cc: <stable(a)vger.kernel.org> [6.7.x] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/damon/core.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) --- a/mm/damon/core.c~mm-damon-core-handle-zero-aggregationops_update-intervals +++ a/mm/damon/core.c @@ -2000,7 +2000,7 @@ static int kdamond_fn(void *data) if (ctx->ops.check_accesses) max_nr_accesses = ctx->ops.check_accesses(ctx); - if (ctx->passed_sample_intervals == next_aggregation_sis) { + if (ctx->passed_sample_intervals >= next_aggregation_sis) { kdamond_merge_regions(ctx, max_nr_accesses / 10, sz_limit); @@ -2018,7 +2018,7 @@ static int kdamond_fn(void *data) sample_interval = ctx->attrs.sample_interval ? ctx->attrs.sample_interval : 1; - if (ctx->passed_sample_intervals == next_aggregation_sis) { + if (ctx->passed_sample_intervals >= next_aggregation_sis) { ctx->next_aggregation_sis = next_aggregation_sis + ctx->attrs.aggr_interval / sample_interval; @@ -2028,7 +2028,7 @@ static int kdamond_fn(void *data) ctx->ops.reset_aggregated(ctx); } - if (ctx->passed_sample_intervals == next_ops_update_sis) { + if (ctx->passed_sample_intervals >= next_ops_update_sis) { ctx->next_ops_update_sis = next_ops_update_sis + ctx->attrs.ops_update_interval / sample_interval; _ Patches currently in -mm which might be from sj(a)kernel.org are mm-damon-core-handle-zero-aggregationops_update-intervals.patch mm-damon-core-handle-zero-schemes-apply-interval.patch selftests-damon-huge_count_read_write-remove-unnecessary-debugging-message.patch selftests-damon-_debugfs_common-hide-expected-error-message-from-test_write_result.patch selftests-damon-debugfs_duplicate_context_creation-hide-errors-from-expected-file-write-failures.patch mm-damon-kconfig-update-dbgfs_kunit-prompt-copy-for-sysfs_kunit.patch mm-damon-tests-dbgfs-kunit-fix-the-header-double-inclusion-guarding-ifdef-comment.patch

4 hours, 2 minutes

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror November 2024