>From c9eb74ef2414b542b20f934060a4b9123ba83d0f Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 13 Apr 2022 12:31:01 -0400 Subject: [PATCH] mm: Check against orig_pte for finish_fault() when proper This patch allows do_fault() to trigger on !pte_none() cases too. This prepares for the pte markers to be handled by do_fault() just like none pte. To achieve this, instead of unconditionally check against pte_none() in finish_fault(), we may hit the case that the orig_pte was some pte marker so what we want to do is to replace the pte marker with some valid pte entry. Then if orig_pte was set we'd want to check the current *pte (under pgtable lock) against orig_pte rather than none pte. Right now there's no solid way to safely reference orig_pte because when pmd is not allocated handle_pte_fault() will not initialize orig_pte, so it's not safe to reference it. There's another solution proposed before this patch to do pte_clear() for vmf->orig_pte for pmd==NULL case, however it turns out it'll break arm32 because arm32 could have assumption that pte_t* pointer will always reside on a real ram32 pgtable, not any kernel stack variable. To solve this, we add a new flag FAULT_FLAG_ORIG_PTE_VALID, and it'll be set along with orig_pte when there is valid orig_pte, or it'll be cleared when orig_pte was not initialized. It'll be updated every time we call handle_pte_fault(), so e.g. if a page fault retry happened it'll be properly updated along with orig_pte. [1] https://lore.kernel.org/lkml/710c48c9-406d-e4c5-a394-10501b951316@samsung.com/ Signed-off-by: Peter Xu --- include/linux/mm_types.h | 3 +++ mm/memory.c | 13 ++++++++++++- 2 files changed, 15 insertions(+), 1 deletion(-) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 5c567eabfb16..717a47056330 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -817,6 +817,8 @@ typedef struct { * @FAULT_FLAG_UNSHARE: The fault is an unsharing request to unshare (and mark * exclusive) a possibly shared anonymous page that is * mapped R/O. + * @FAULT_FLAG_ORIG_PTE_VALID: whether the fault has vmf->orig_pte cached. + * We should only access orig_pte if this flag set. * * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify * whether we would allow page faults to retry by specifying these two @@ -853,6 +855,7 @@ enum fault_flag { FAULT_FLAG_INSTRUCTION = 1 << 8, FAULT_FLAG_INTERRUPTIBLE = 1 << 9, FAULT_FLAG_UNSHARE = 1 << 10, + FAULT_FLAG_ORIG_PTE_VALID = 1 << 11, }; #endif /* _LINUX_MM_TYPES_H */ diff --git a/mm/memory.c b/mm/memory.c index f89034a60e9a..8e7f39c651c3 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4301,6 +4301,15 @@ void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr) set_pte_at(vma->vm_mm, addr, vmf->pte, entry); } +static bool vmf_pte_changed(struct vm_fault *vmf) +{ + if (vmf->flags & FAULT_FLAG_ORIG_PTE_VALID) { + return !pte_same(*vmf->pte, vmf->orig_pte); + } + + return !pte_none(*vmf->pte); +} + /** * finish_fault - finish page fault once we have prepared the page to fault * @@ -4359,7 +4368,7 @@ vm_fault_t finish_fault(struct vm_fault *vmf) vmf->address, &vmf->ptl); ret = 0; /* Re-check under ptl */ - if (likely(pte_none(*vmf->pte))) + if (likely(!vmf_pte_changed(vmf))) do_set_pte(vmf, page, vmf->address); else ret = VM_FAULT_NOPAGE; @@ -4837,6 +4846,7 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) * concurrent faults and from rmap lookups. */ vmf->pte = NULL; + vmf->flags &= ~FAULT_FLAG_ORIG_PTE_VALID; } else { /* * If a huge pmd materialized under us just retry later. Use @@ -4860,6 +4870,7 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) */ vmf->pte = pte_offset_map(vmf->pmd, vmf->address); vmf->orig_pte = *vmf->pte; + vmf->flags |= FAULT_FLAG_ORIG_PTE_VALID; /* * some architectures can have larger ptes than wordsize, -- 2.32.0