From 46cbda7b65998a5af4493f745d94417af697bd68 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Wed, 23 Nov 2022 07:45:10 +0100 Subject: [PATCH 18/29] mm: introduce arch_has_hw_nonleaf_pmd_young() When running as a Xen PV guests commit eed9a328aa1a ("mm: x86: add CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG") can cause a protection violation in pmdp_test_and_clear_young(): BUG: unable to handle page fault for address: ffff8880083374d0 #PF: supervisor write access in kernel mode #PF: error_code(0x0003) - permissions violation PGD 3026067 P4D 3026067 PUD 3027067 PMD 7fee5067 PTE 8010000008337065 Oops: 0003 [#1] PREEMPT SMP NOPTI CPU: 7 PID: 158 Comm: kswapd0 Not tainted 6.1.0-rc5-20221118-doflr+ #1 RIP: e030:pmdp_test_and_clear_young+0x25/0x40 This happens because the Xen hypervisor can't emulate direct writes to page table entries other than PTEs. This can easily be fixed by introducing arch_has_hw_nonleaf_pmd_young() similar to arch_has_hw_pte_young() and test that instead of CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG. Link: https://lkml.kernel.org/r/20221123064510.16225-1-jgross@suse.com Fixes: eed9a328aa1a ("mm: x86: add CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG") Signed-off-by: Juergen Gross Reported-by: Sander Eikelenboom Acked-by: Yu Zhao Tested-by: Sander Eikelenboom Acked-by: David Hildenbrand [core changes] Signed-off-by: Andrew Morton --- arch/x86/include/asm/pgtable.h | 8 ++++++++ include/linux/pgtable.h | 11 +++++++++++ mm/vmscan.c | 10 +++++----- 3 files changed, 24 insertions(+), 5 deletions(-) --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1405,6 +1405,14 @@ static inline bool arch_has_hw_pte_young return true; } +#ifdef CONFIG_XEN_PV +#define arch_has_hw_nonleaf_pmd_young arch_has_hw_nonleaf_pmd_young +static inline bool arch_has_hw_nonleaf_pmd_young(void) +{ + return !cpu_feature_enabled(X86_FEATURE_XENPV); +} +#endif + #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_H */ --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -266,6 +266,17 @@ static inline int pmdp_clear_flush_young #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif +#ifndef arch_has_hw_nonleaf_pmd_young +/* + * Return whether the accessed bit in non-leaf PMD entries is supported on the + * local CPU. + */ +static inline bool arch_has_hw_nonleaf_pmd_young(void) +{ + return IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG); +} +#endif + #ifndef arch_has_hw_pte_young /* * Return whether the accessed bit is supported on the local CPU. --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3727,7 +3727,7 @@ static void walk_pmd_range_locked(pud_t goto next; if (!pmd_trans_huge(pmd[i])) { - if (IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) && + if (arch_has_hw_nonleaf_pmd_young() && get_cap(LRU_GEN_NONLEAF_YOUNG)) pmdp_test_and_clear_young(vma, addr, pmd + i); goto next; @@ -3825,14 +3825,14 @@ restart: #endif walk->mm_stats[MM_NONLEAF_TOTAL]++; -#ifdef CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG - if (get_cap(LRU_GEN_NONLEAF_YOUNG)) { + if (arch_has_hw_nonleaf_pmd_young() && + get_cap(LRU_GEN_NONLEAF_YOUNG)) { if (!pmd_young(val)) continue; walk_pmd_range_locked(pud, addr, vma, args, bitmap, &pos); } -#endif + if (!walk->force_scan && !test_bloom_filter(walk->lruvec, walk->max_seq, pmd + i)) continue; @@ -5132,7 +5132,7 @@ static ssize_t show_enabled(struct kobje if (arch_has_hw_pte_young() && get_cap(LRU_GEN_MM_WALK)) caps |= BIT(LRU_GEN_MM_WALK); - if (IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) && get_cap(LRU_GEN_NONLEAF_YOUNG)) + if (arch_has_hw_nonleaf_pmd_young() && get_cap(LRU_GEN_NONLEAF_YOUNG)) caps |= BIT(LRU_GEN_NONLEAF_YOUNG); return snprintf(buf, PAGE_SIZE, "0x%04x\n", caps);