From 09f08f63015b11f192df40546cf050f2d4565d25 Mon Sep 17 00:00:00 2001 From: Rafael Aquini Date: Fri, 27 Sep 2024 10:43:07 -0400 Subject: [PATCH] mm: drop per-VMA lock when returning VM_FAULT_RETRY or VM_FAULT_COMPLETED JIRA: https://issues.redhat.com/browse/RHEL-27743 Conflicts: * arch/riscv/mm/fault.c: hunk dropped (unsupported arch) This patch is a backport of the following upstream commit: commit 4089eef0e6ac1a179c58304c657b3df3bb6fe509 Author: Suren Baghdasaryan Date: Fri Jun 30 14:19:54 2023 -0700 mm: drop per-VMA lock when returning VM_FAULT_RETRY or VM_FAULT_COMPLETED handle_mm_fault returning VM_FAULT_RETRY or VM_FAULT_COMPLETED means mmap_lock has been released. However with per-VMA locks behavior is different and the caller should still release it. To make the rules consistent for the caller, drop the per-VMA lock when returning VM_FAULT_RETRY or VM_FAULT_COMPLETED. Currently the only path returning VM_FAULT_RETRY under per-VMA locks is do_swap_page and no path returns VM_FAULT_COMPLETED for now. [willy@infradead.org: fix riscv] Link: https://lkml.kernel.org/r/CAJuCfpE6GWEx1rPBmNpUfoD5o-gNFz9-UFywzCE2PbEGBiVz7g@mail.gmail.com Link: https://lkml.kernel.org/r/20230630211957.1341547-4-surenb@google.com Signed-off-by: Suren Baghdasaryan Acked-by: Peter Xu Tested-by: Conor Dooley Cc: Alistair Popple Cc: Al Viro Cc: Christian Brauner Cc: Christoph Hellwig Cc: David Hildenbrand Cc: David Howells Cc: Davidlohr Bueso Cc: Hillf Danton Cc: "Huang, Ying" Cc: Hugh Dickins Cc: Jan Kara Cc: Johannes Weiner Cc: Josef Bacik Cc: Laurent Dufour Cc: Liam R. Howlett Cc: Lorenzo Stoakes Cc: Matthew Wilcox Cc: Michal Hocko Cc: Michel Lespinasse Cc: Minchan Kim Cc: Pavel Tatashin Cc: Punit Agrawal Cc: Vlastimil Babka Cc: Yu Zhao Signed-off-by: Andrew Morton Signed-off-by: Rafael Aquini --- arch/arm64/mm/fault.c | 3 ++- arch/powerpc/mm/fault.c | 3 ++- arch/s390/mm/fault.c | 3 ++- arch/x86/mm/fault.c | 3 ++- mm/memory.c | 12 ++++++++++++ 5 files changed, 20 insertions(+), 4 deletions(-) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 9c985f5d8157..f30dbb6309fe 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -597,7 +597,8 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr, goto lock_mmap; } fault = handle_mm_fault(vma, addr, mm_flags | FAULT_FLAG_VMA_LOCK, regs); - vma_end_read(vma); + if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED))) + vma_end_read(vma); if (!(fault & VM_FAULT_RETRY)) { count_vm_vma_lock_event(VMA_LOCK_SUCCESS); diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index e17847e30be2..9a1ef8e1bfd1 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -490,7 +490,8 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, } fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs); - vma_end_read(vma); + if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED))) + vma_end_read(vma); if (!(fault & VM_FAULT_RETRY)) { count_vm_vma_lock_event(VMA_LOCK_SUCCESS); diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 148b3260a0a3..bce0200f5730 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -383,7 +383,8 @@ static void do_exception(struct pt_regs *regs, int access) goto lock_mmap; } fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs); - vma_end_read(vma); + if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED))) + vma_end_read(vma); if (!(fault & VM_FAULT_RETRY)) { count_vm_vma_lock_event(VMA_LOCK_SUCCESS); if (likely(!(fault & VM_FAULT_ERROR))) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 492a19130c1e..2ea520653467 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1359,7 +1359,8 @@ void do_user_addr_fault(struct pt_regs *regs, goto lock_mmap; } fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs); - vma_end_read(vma); + if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED))) + vma_end_read(vma); if (!(fault & VM_FAULT_RETRY)) { count_vm_vma_lock_event(VMA_LOCK_SUCCESS); diff --git a/mm/memory.c b/mm/memory.c index 8a896275fe81..41b90139a22a 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3733,6 +3733,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) if (vmf->flags & FAULT_FLAG_VMA_LOCK) { ret = VM_FAULT_RETRY; + vma_end_read(vma); goto out; } @@ -5211,6 +5212,17 @@ static vm_fault_t sanitize_fault_flags(struct vm_area_struct *vma, !is_cow_mapping(vma->vm_flags))) return VM_FAULT_SIGSEGV; } +#ifdef CONFIG_PER_VMA_LOCK + /* + * Per-VMA locks can't be used with FAULT_FLAG_RETRY_NOWAIT because of + * the assumption that lock is dropped on VM_FAULT_RETRY. + */ + if (WARN_ON_ONCE((*flags & + (FAULT_FLAG_VMA_LOCK | FAULT_FLAG_RETRY_NOWAIT)) == + (FAULT_FLAG_VMA_LOCK | FAULT_FLAG_RETRY_NOWAIT))) + return VM_FAULT_SIGSEGV; +#endif + return 0; }