October 2024 - Linux-stable-mirror

[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

2 months, 1 week

2
2
0 0

[PATCH 5.10] perf/x86/intel: Fix PEBS-via-PT reload base value for Extended PEBS

by Murad Masimov

From: Like Xu <like.xu.linux(a)gmail.com> commit 4c58d922c0877e23cc7d3d7c6bff49b85faaca89 upstream. If we use the "PEBS-via-PT" feature on a platform that supports extended PBES, like this: perf record -c 10000 \ -e '{intel_pt/branch=0/,branch-instructions/aux-output/p}' uname we will encounter the following call trace: [ 250.906542] unchecked MSR access error: WRMSR to 0x14e1 (tried to write 0x0000000000000000) at rIP: 0xffffffff88073624 (native_write_msr+0x4/0x20) [ 250.920779] Call Trace: [ 250.923508] intel_pmu_pebs_enable+0x12c/0x190 [ 250.928359] intel_pmu_enable_event+0x346/0x390 [ 250.933300] x86_pmu_start+0x64/0x80 [ 250.937231] x86_pmu_enable+0x16a/0x2f0 [ 250.941434] perf_event_exec+0x144/0x4c0 [ 250.945731] begin_new_exec+0x650/0xbf0 [ 250.949933] load_elf_binary+0x13e/0x1700 [ 250.954321] ? lock_acquire+0xc2/0x390 [ 250.958430] ? bprm_execve+0x34f/0x8a0 [ 250.962544] ? lock_is_held_type+0xa7/0x120 [ 250.967118] ? find_held_lock+0x32/0x90 [ 250.971321] ? sched_clock_cpu+0xc/0xb0 [ 250.975527] bprm_execve+0x33d/0x8a0 [ 250.979452] do_execveat_common.isra.0+0x161/0x1d0 [ 250.984673] __x64_sys_execve+0x33/0x40 [ 250.988877] do_syscall_64+0x3d/0x80 [ 250.992806] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 250.998302] RIP: 0033:0x7fbc971d82fb [ 251.002235] Code: Unable to access opcode bytes at RIP 0x7fbc971d82d1. [ 251.009303] RSP: 002b:00007fffb8aed808 EFLAGS: 00000202 ORIG_RAX: 000000000000003b [ 251.017478] RAX: ffffffffffffffda RBX: 00007fffb8af2f00 RCX: 00007fbc971d82fb [ 251.025187] RDX: 00005574792aac50 RSI: 00007fffb8af2f00 RDI: 00007fffb8aed810 [ 251.032901] RBP: 00007fffb8aed970 R08: 0000000000000020 R09: 00007fbc9725c8b0 [ 251.040613] R10: 6d6c61632f6d6f63 R11: 0000000000000202 R12: 00005574792aac50 [ 251.048327] R13: 00007fffb8af35f0 R14: 00005574792aafdf R15: 00005574792aafe7 This is because the target reload msr address is calculated based on the wrong base msr and the target reload msr value is accessed from ds->pebs_event_reset[] with the wrong offset. According to Intel SDM Table 2-14, for extended PBES feature, the reload msr for MSR_IA32_FIXED_CTRx should be based on MSR_RELOAD_FIXED_CTRx. For fixed counters, let's fix it by overriding the reload msr address and its value, thus avoiding out-of-bounds access. Fixes: 42880f726c66("perf/x86/intel: Support PEBS output to PT") Signed-off-by: Like Xu <likexu(a)tencent.com> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Link: https://lkml.kernel.org/r/20210621034710.31107-1-likexu@tencent.com Signed-off-by: Murad Masimov <m.masimov(a)maxima.ru> --- arch/x86/events/intel/ds.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 48f30ffef1f4..182908aebed0 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1093,6 +1093,9 @@ static void intel_pmu_pebs_via_pt_enable(struct perf_event *event) struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; struct debug_store *ds = cpuc->ds; + u64 value = ds->pebs_event_reset[hwc->idx]; + u32 base = MSR_RELOAD_PMC0; + unsigned int idx = hwc->idx; if (!is_pebs_pt(event)) return; @@ -1102,7 +1105,12 @@ static void intel_pmu_pebs_via_pt_enable(struct perf_event *event) cpuc->pebs_enabled |= PEBS_OUTPUT_PT; - wrmsrl(MSR_RELOAD_PMC0 + hwc->idx, ds->pebs_event_reset[hwc->idx]); + if (hwc->idx >= INTEL_PMC_IDX_FIXED) { + base = MSR_RELOAD_FIXED_CTR0; + idx = hwc->idx - INTEL_PMC_IDX_FIXED; + value = ds->pebs_event_reset[MAX_PEBS_EVENTS + idx]; + } + wrmsrl(base + idx, value); } void intel_pmu_pebs_enable(struct perf_event *event) @@ -1110,6 +1118,7 @@ void intel_pmu_pebs_enable(struct perf_event *event) struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; struct debug_store *ds = cpuc->ds; + unsigned int idx = hwc->idx; hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT; @@ -1128,19 +1137,18 @@ void intel_pmu_pebs_enable(struct perf_event *event) } } + if (idx >= INTEL_PMC_IDX_FIXED) + idx = MAX_PEBS_EVENTS + (idx - INTEL_PMC_IDX_FIXED); + /* * Use auto-reload if possible to save a MSR write in the PMI. * This must be done in pmu::start(), because PERF_EVENT_IOC_PERIOD. */ if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { - unsigned int idx = hwc->idx; - - if (idx >= INTEL_PMC_IDX_FIXED) - idx = MAX_PEBS_EVENTS + (idx - INTEL_PMC_IDX_FIXED); ds->pebs_event_reset[idx] = (u64)(-hwc->sample_period) & x86_pmu.cntval_mask; } else { - ds->pebs_event_reset[hwc->idx] = 0; + ds->pebs_event_reset[idx] = 0; } intel_pmu_pebs_via_pt_enable(event); -- 2.39.2

2 months, 1 week

1
0
0 0

[PATCH v2] KVM: arm64: Get rid of userspace_irqchip_in_use

by Raghavendra Rao Ananta

Improper use of userspace_irqchip_in_use led to syzbot hitting the following WARN_ON() in kvm_timer_update_irq(): WARNING: CPU: 0 PID: 3281 at arch/arm64/kvm/arch_timer.c:459 kvm_timer_update_irq+0x21c/0x394 Call trace: kvm_timer_update_irq+0x21c/0x394 arch/arm64/kvm/arch_timer.c:459 kvm_timer_vcpu_reset+0x158/0x684 arch/arm64/kvm/arch_timer.c:968 kvm_reset_vcpu+0x3b4/0x560 arch/arm64/kvm/reset.c:264 kvm_vcpu_set_target arch/arm64/kvm/arm.c:1553 [inline] kvm_arch_vcpu_ioctl_vcpu_init arch/arm64/kvm/arm.c:1573 [inline] kvm_arch_vcpu_ioctl+0x112c/0x1b3c arch/arm64/kvm/arm.c:1695 kvm_vcpu_ioctl+0x4ec/0xf74 virt/kvm/kvm_main.c:4658 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:907 [inline] __se_sys_ioctl fs/ioctl.c:893 [inline] __arm64_sys_ioctl+0x108/0x184 fs/ioctl.c:893 __invoke_syscall arch/arm64/kernel/syscall.c:35 [inline] invoke_syscall+0x78/0x1b8 arch/arm64/kernel/syscall.c:49 el0_svc_common+0xe8/0x1b0 arch/arm64/kernel/syscall.c:132 do_el0_svc+0x40/0x50 arch/arm64/kernel/syscall.c:151 el0_svc+0x54/0x14c arch/arm64/kernel/entry-common.c:712 el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:730 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598 The following sequence led to the scenario: - Userspace creates a VM and a vCPU. - The vCPU is initialized with KVM_ARM_VCPU_PMU_V3 during KVM_ARM_VCPU_INIT. - Without any other setup, such as vGIC or vPMU, userspace issues KVM_RUN on the vCPU. Since the vPMU is requested, but not setup, kvm_arm_pmu_v3_enable() fails in kvm_arch_vcpu_run_pid_change(). As a result, KVM_RUN returns after enabling the timer, but before incrementing 'userspace_irqchip_in_use': kvm_arch_vcpu_run_pid_change() ret = kvm_arm_pmu_v3_enable() if (!vcpu->arch.pmu.created) return -EINVAL; if (ret) return ret; [...] if (!irqchip_in_kernel(kvm)) static_branch_inc(&userspace_irqchip_in_use); - Userspace ignores the error and issues KVM_ARM_VCPU_INIT again. Since the timer is already enabled, control moves through the following flow, ultimately hitting the WARN_ON(): kvm_timer_vcpu_reset() if (timer->enabled) kvm_timer_update_irq() if (!userspace_irqchip()) ret = kvm_vgic_inject_irq() ret = vgic_lazy_init() if (unlikely(!vgic_initialized(kvm))) if (kvm->arch.vgic.vgic_model != KVM_DEV_TYPE_ARM_VGIC_V2) return -EBUSY; WARN_ON(ret); Theoretically, since userspace_irqchip_in_use's functionality can be simply replaced by '!irqchip_in_kernel()', get rid of the static key to avoid the mismanagement, which also helps with the syzbot issue. Cc: <stable(a)vger.kernel.org> Reported-by: syzbot <syzkaller(a)googlegroups.com> Suggested-by: Marc Zyngier <maz(a)kernel.org> Signed-off-by: Raghavendra Rao Ananta <rananta(a)google.com> --- v2: - Picked the diff shared by Marc to get rid of 'userspace_irqchip_in_use' (thanks). - Adjusted the commit message accordingly. v1: https://lore.kernel.org/all/20241025221220.2985227-1-rananta@google.com/ arch/arm64/include/asm/kvm_host.h | 2 -- arch/arm64/kvm/arch_timer.c | 3 +-- arch/arm64/kvm/arm.c | 18 +++--------------- 3 files changed, 4 insertions(+), 19 deletions(-) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 329619c6fa961..9f96594a0e05d 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -73,8 +73,6 @@ enum kvm_mode kvm_get_mode(void); static inline enum kvm_mode kvm_get_mode(void) { return KVM_MODE_NONE; }; #endif -DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use); - extern unsigned int __ro_after_init kvm_sve_max_vl; extern unsigned int __ro_after_init kvm_host_sve_max_vl; int __init kvm_arm_init_sve(void); diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index 879982b1cc739..1215df5904185 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -206,8 +206,7 @@ void get_timer_map(struct kvm_vcpu *vcpu, struct timer_map *map) static inline bool userspace_irqchip(struct kvm *kvm) { - return static_branch_unlikely(&userspace_irqchip_in_use) && - unlikely(!irqchip_in_kernel(kvm)); + return unlikely(!irqchip_in_kernel(kvm)); } static void soft_timer_start(struct hrtimer *hrt, u64 ns) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index a0d01c46e4084..63f5c05e9dec6 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -69,7 +69,6 @@ DECLARE_KVM_NVHE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt); static bool vgic_present, kvm_arm_initialised; static DEFINE_PER_CPU(unsigned char, kvm_hyp_initialized); -DEFINE_STATIC_KEY_FALSE(userspace_irqchip_in_use); bool is_kvm_arm_initialised(void) { @@ -503,9 +502,6 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { - if (vcpu_has_run_once(vcpu) && unlikely(!irqchip_in_kernel(vcpu->kvm))) - static_branch_dec(&userspace_irqchip_in_use); - kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache); kvm_timer_vcpu_terminate(vcpu); kvm_pmu_vcpu_destroy(vcpu); @@ -848,14 +844,6 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) return ret; } - if (!irqchip_in_kernel(kvm)) { - /* - * Tell the rest of the code that there are userspace irqchip - * VMs in the wild. - */ - static_branch_inc(&userspace_irqchip_in_use); - } - /* * Initialize traps for protected VMs. * NOTE: Move to run in EL2 directly, rather than via a hypercall, once @@ -1072,7 +1060,7 @@ static bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu, int *ret) * state gets updated in kvm_timer_update_run and * kvm_pmu_update_run below). */ - if (static_branch_unlikely(&userspace_irqchip_in_use)) { + if (unlikely(!irqchip_in_kernel(vcpu->kvm))) { if (kvm_timer_should_notify_user(vcpu) || kvm_pmu_should_notify_user(vcpu)) { *ret = -EINTR; @@ -1194,7 +1182,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; isb(); /* Ensure work in x_flush_hwstate is committed */ kvm_pmu_sync_hwstate(vcpu); - if (static_branch_unlikely(&userspace_irqchip_in_use)) + if (unlikely(!irqchip_in_kernel(vcpu->kvm))) kvm_timer_sync_user(vcpu); kvm_vgic_sync_hwstate(vcpu); local_irq_enable(); @@ -1240,7 +1228,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) * we don't want vtimer interrupts to race with syncing the * timer virtual interrupt state. */ - if (static_branch_unlikely(&userspace_irqchip_in_use)) + if (unlikely(!irqchip_in_kernel(vcpu->kvm))) kvm_timer_sync_user(vcpu); kvm_arch_vcpu_ctxsync_fp(vcpu); base-commit: 9852d85ec9d492ebef56dc5f229416c925758edc -- 2.47.0.163.g1226f6d8fa-goog

2 months, 1 week

3
8
0 0

[PATCH 2/2] mm/damon/core: handle zero schemes apply interval

by SeongJae Park

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. Fixes: 42f994b71404 ("mm/damon/core: implement scheme-specific apply interval") Cc: <stable(a)vger.kernel.org> # 6.7.x Signed-off-by: SeongJae Park <sj(a)kernel.org> --- mm/damon/core.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/mm/damon/core.c b/mm/damon/core.c index 931526fb2d2e..511c3f61ab44 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -1412,7 +1412,7 @@ static void damon_do_apply_schemes(struct damon_ctx *c, 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) @@ -1636,7 +1636,7 @@ static void kdamond_apply_schemes(struct damon_ctx *c) 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) @@ -1656,9 +1656,9 @@ static void kdamond_apply_schemes(struct damon_ctx *c) } 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; } -- 2.39.5

2 months, 1 week

1
0
0 0

[PATCH 1/2] mm/damon/core: handle zero {aggregation,ops_update} intervals

by SeongJae Park

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. Fixes: 4472edf63d66 ("mm/damon/core: use number of passed access sampling as a timer") Cc: <stable(a)vger.kernel.org> # 6.7.x Signed-off-by: SeongJae Park <sj(a)kernel.org> --- mm/damon/core.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/mm/damon/core.c b/mm/damon/core.c index 27745dcf855f..931526fb2d2e 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -2014,7 +2014,7 @@ 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); @@ -2032,7 +2032,7 @@ 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; @@ -2042,7 +2042,7 @@ 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; -- 2.39.5

2 months, 1 week

1
0
0 0

[PATCH 2/3] gpiolib: fix debugfs dangling chip separator

by Johan Hovold

Add the missing newline after entries for recently removed gpio chips so that the chip sections are separated by a newline as intended. Fixes: e348544f7994 ("gpio: protect the list of GPIO devices with SRCU") Cc: stable(a)vger.kernel.org # 6.9 Cc: Bartosz Golaszewski <bartosz.golaszewski(a)linaro.org> Signed-off-by: Johan Hovold <johan+linaro(a)kernel.org> --- drivers/gpio/gpiolib.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index e27488a90bc9..2b02655abb56 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -4971,7 +4971,7 @@ static int gpiolib_seq_show(struct seq_file *s, void *v) gc = srcu_dereference(gdev->chip, &gdev->srcu); if (!gc) { - seq_printf(s, "%s%s: (dangling chip)", + seq_printf(s, "%s%s: (dangling chip)\n", priv->newline ? "\n" : "", dev_name(&gdev->dev)); return 0; -- 2.45.2

2 months, 1 week

3
3
0 0

[PATCH] net: ethernet: broadcom: Fix uninitialized lockal variable

by George Rurikov

I can't find any reason why it won't happen. In SERDES_TG3_SGMII_MODE, when current_link_up == true and current_duplex == DUPLEX_FULL, program execution will be transferred using the goto fiber_setup_done, where the uninitialized remote_adv variable is passed as the second parameter to the tg3_setup_flow_control function. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 85730a631f0c ("tg3: Add SGMII phy support for 5719/5718 serdes") Cc: stable(a)vger.kernel.org Signed-off-by: George Rurikov <grurikov(a)gmail.com> --- drivers/net/ethernet/broadcom/tg3.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 378815917741..b1c60851c841 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -5802,7 +5802,8 @@ static int tg3_setup_fiber_mii_phy(struct tg3 *tp, bool force_reset) u32 current_speed = SPEED_UNKNOWN; u8 current_duplex = DUPLEX_UNKNOWN; bool current_link_up = false; - u32 local_adv, remote_adv, sgsr; + u32 local_adv, sgsr; + u32 remote_adv = 0; if ((tg3_asic_rev(tp) == ASIC_REV_5719 || tg3_asic_rev(tp) == ASIC_REV_5720) && -- 2.34.1

2 months, 1 week

2
1
0 0

[PATCH] ucounts: fix counter leak in inc_rlimit_get_ucounts()

by Andrei Vagin

The inc_rlimit_get_ucounts() increments the specified rlimit counter and then checks its limit. If the value exceeds the limit, the function returns an error without decrementing the counter. Fixes: 15bc01effefe ("ucounts: Fix signal ucount refcounting") Tested-by: Roman Gushchin <roman.gushchin(a)linux.dev> Co-debugged-by: Roman Gushchin <roman.gushchin(a)linux.dev> Cc: Kees Cook <kees(a)kernel.org> Cc: Andrei Vagin <avagin(a)google.com> Cc: "Eric W. Biederman" <ebiederm(a)xmission.com> Cc: Alexey Gladkov <legion(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrei Vagin <avagin(a)google.com> --- kernel/ucount.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/kernel/ucount.c b/kernel/ucount.c index 8c07714ff27d..16c0ea1cb432 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -328,13 +328,12 @@ long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type) if (new != 1) continue; if (!get_ucounts(iter)) - goto dec_unwind; + goto unwind; } return ret; -dec_unwind: +unwind: dec = atomic_long_sub_return(1, &iter->rlimit[type]); WARN_ON_ONCE(dec < 0); -unwind: do_dec_rlimit_put_ucounts(ucounts, iter, type); return 0; } -- 2.47.0.163.g1226f6d8fa-goog

2 months, 1 week

3
4
0 0

[PATCH v2] serial: 8250: omap: Move pm_runtime_get_sync

by Judith Mendez

From: Bin Liu <b-liu(a)ti.com> Currently in omap_8250_shutdown, the dma->rx_running flag is set to zero in omap_8250_rx_dma_flush. Next pm_runtime_get_sync is called, which is a runtime resume call stack which can re-set the flag. When the call omap_8250_shutdown returns, the flag is expected to be UN-SET, but this is not the case. This is causing issues the next time UART is re-opened and omap_8250_rx_dma is called. Fix by moving pm_runtime_get_sync before the omap_8250_rx_dma_flush. cc: stable(a)vger.kernel.org Fixes: 0e31c8d173ab ("tty: serial: 8250_omap: add custom DMA-RX callback") Signed-off-by: Bin Liu <b-liu(a)ti.com> [Judith: Add commit message] Signed-off-by: Judith Mendez <jm(a)ti.com> Reviewed-by: Kevin Hilman <khilman(a)baylibre.com> Tested-by: Kevin Hilman <khilman(a)baylibre.com> --- Issue seen on am335x devices so far [0]. The patch has been tested with sanity boot test on am335x EVM, am335x-boneblack and am57xx-beagle-x15. Changes since v1 RESEND: - Fix email header and commit description length - Add fixes tag, add link [0], cc stable, add kevin's reviewed-by/tested-by's - Separate patch from patch series [1] [0] https://e2e.ti.com/support/processors-group/processors/f/processors-forum/1… Link to v1 RESEND: [1] https://lore.kernel.org/linux-omap/20241011173356.870883-1-jm@ti.com/ --- drivers/tty/serial/8250/8250_omap.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c index 88b58f44e4e97..0dd68bdbfbcf7 100644 --- a/drivers/tty/serial/8250/8250_omap.c +++ b/drivers/tty/serial/8250/8250_omap.c @@ -776,12 +776,12 @@ static void omap_8250_shutdown(struct uart_port *port) struct uart_8250_port *up = up_to_u8250p(port); struct omap8250_priv *priv = port->private_data; + pm_runtime_get_sync(port->dev); + flush_work(&priv->qos_work); if (up->dma) omap_8250_rx_dma_flush(up); - pm_runtime_get_sync(port->dev); - serial_out(up, UART_OMAP_WER, 0); if (priv->habit & UART_HAS_EFR2) serial_out(up, UART_OMAP_EFR2, 0x0); -- 2.47.0

2 months, 1 week

1
0
0 0

[PATCH 0/2] leds: max5970: fix unreleased fwnode_handle in probe function

by Javier Carrasco

This series fixes the wrong management of the 'led_node' fwnode_handle, which is not released after it is no longer required. This affects both the normal path of execution and the existing error paths (currently two) in max5970_led_probe(). First, the missing callst to fwnode_handle_put() in the different code paths are added, to make the patch available for stable kernels. Then, the code gets updated to a more robust approach by means of the __free() macro to automatically release the node when it goes out of scope, removing the need for explicit calls to fwnode_handle_put(). Signed-off-by: Javier Carrasco <javier.carrasco.cruz(a)gmail.com> --- Javier Carrasco (2): leds: max5970: fix unreleased fwnode_handle in probe function leds: max5970: use cleanup facility for fwnode_handle led_node drivers/leds/leds-max5970.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) --- base-commit: f2493655d2d3d5c6958ed996b043c821c23ae8d3 change-id: 20241019-max5970-of_node_put-939b004f57d2 Best regards, -- Javier Carrasco <javier.carrasco.cruz(a)gmail.com>

2 months, 1 week

2
3
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror October 2024