[PATCH v2 1/5] mm/filemap: Retry fault by VMA lock if the lock was released for I/O

["Barry Song (Xiaomi)" <baohua@kernel.org>]

From: Oven Liyang <liyangouwen1@oppo.com>

If the current page fault is using the per-VMA lock, and we only released
the lock to wait for I/O completion (e.g., using folio_lock()), then when
the fault is retried after the I/O completes, it should still qualify for
the per-VMA-lock path.

Acked-by: Pedro Falcato <pfalcato@suse.de>
Tested-by: Wang Lian <wanglian@kylinos.cn>
Tested-by: Kunwu Chan <chentao@kylinos.cn>
Reviewed-by: Wang Lian <lianux.mm@gmail.com>
Reviewed-by: Kunwu Chan <kunwu.chan@gmail.com>
Signed-off-by: Oven Liyang <liyangouwen1@oppo.com>
Co-developed-by: Barry Song <baohua@kernel.org>
Signed-off-by: Barry Song <baohua@kernel.org>
---
 arch/arm/mm/fault.c       | 5 +++++
 arch/arm64/mm/fault.c     | 5 +++++
 arch/loongarch/mm/fault.c | 4 ++++
 arch/powerpc/mm/fault.c   | 5 ++++-
 arch/riscv/mm/fault.c     | 4 ++++
 arch/s390/mm/fault.c      | 4 ++++
 arch/x86/mm/fault.c       | 4 ++++
 include/linux/mm_types.h  | 9 +++++----
 mm/filemap.c              | 5 ++++-
 9 files changed, 39 insertions(+), 6 deletions(-)

diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index e62cc4be5adf..5971e02845f7 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -391,6 +391,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	if (!(flags & FAULT_FLAG_USER))
 		goto lock_mmap;
 
+retry_vma:
 	vma = lock_vma_under_rcu(mm, addr);
 	if (!vma)
 		goto lock_mmap;
@@ -420,6 +421,10 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 			goto no_context;
 		return 0;
 	}
+
+	/* If the first try is only about waiting for the I/O to complete */
+	if (fault & VM_FAULT_RETRY_VMA)
+		goto retry_vma;
 lock_mmap:
 
 retry:
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 739800835920..d0362a3e11b7 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -673,6 +673,7 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr,
 	if (!(mm_flags & FAULT_FLAG_USER))
 		goto lock_mmap;
 
+retry_vma:
 	vma = lock_vma_under_rcu(mm, addr);
 	if (!vma)
 		goto lock_mmap;
@@ -719,6 +720,10 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr,
 			goto no_context;
 		return 0;
 	}
+
+	/* If the first try is only about waiting for the I/O to complete */
+	if (fault & VM_FAULT_RETRY_VMA)
+		goto retry_vma;
 lock_mmap:
 
 retry:
diff --git a/arch/loongarch/mm/fault.c b/arch/loongarch/mm/fault.c
index 2c93d33356e5..738f495560c0 100644
--- a/arch/loongarch/mm/fault.c
+++ b/arch/loongarch/mm/fault.c
@@ -219,6 +219,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs,
 	if (!(flags & FAULT_FLAG_USER))
 		goto lock_mmap;
 
+retry_vma:
 	vma = lock_vma_under_rcu(mm, address);
 	if (!vma)
 		goto lock_mmap;
@@ -265,6 +266,9 @@ static void __kprobes __do_page_fault(struct pt_regs *regs,
 			no_context(regs, write, address);
 		return;
 	}
+	/* If the first try is only about waiting for the I/O to complete */
+	if (fault & VM_FAULT_RETRY_VMA)
+		goto retry_vma;
 lock_mmap:
 
 retry:
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 806c74e0d5ab..cb7ffc20c760 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -487,6 +487,7 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address,
 	if (!(flags & FAULT_FLAG_USER))
 		goto lock_mmap;
 
+retry_vma:
 	vma = lock_vma_under_rcu(mm, address);
 	if (!vma)
 		goto lock_mmap;
@@ -516,7 +517,9 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address,
 
 	if (fault_signal_pending(fault, regs))
 		return user_mode(regs) ? 0 : SIGBUS;
-
+	/* If the first try is only about waiting for the I/O to complete */
+	if (fault & VM_FAULT_RETRY_VMA)
+		goto retry_vma;
 lock_mmap:
 
 	/* When running in the kernel we expect faults to occur only to
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index 04ed6f8acae4..b94cf57c2b9a 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -347,6 +347,7 @@ void handle_page_fault(struct pt_regs *regs)
 	if (!(flags & FAULT_FLAG_USER))
 		goto lock_mmap;
 
+retry_vma:
 	vma = lock_vma_under_rcu(mm, addr);
 	if (!vma)
 		goto lock_mmap;
@@ -376,6 +377,9 @@ void handle_page_fault(struct pt_regs *regs)
 			no_context(regs, addr);
 		return;
 	}
+	/* If the first try is only about waiting for the I/O to complete */
+	if (fault & VM_FAULT_RETRY_VMA)
+		goto retry_vma;
 lock_mmap:
 
 retry:
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 191cc53caead..e0576e629f65 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -294,6 +294,7 @@ static void do_exception(struct pt_regs *regs, int access)
 		flags |= FAULT_FLAG_WRITE;
 	if (!(flags & FAULT_FLAG_USER))
 		goto lock_mmap;
+retry_vma:
 	vma = lock_vma_under_rcu(mm, address);
 	if (!vma)
 		goto lock_mmap;
@@ -318,6 +319,9 @@ static void do_exception(struct pt_regs *regs, int access)
 			handle_fault_error_nolock(regs, 0);
 		return;
 	}
+	/* If the first try is only about waiting for the I/O to complete */
+	if (fault & VM_FAULT_RETRY_VMA)
+		goto retry_vma;
 lock_mmap:
 retry:
 	vma = lock_mm_and_find_vma(mm, address, regs);
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index f0e77e084482..0589fc693eea 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1322,6 +1322,7 @@ void do_user_addr_fault(struct pt_regs *regs,
 	if (!(flags & FAULT_FLAG_USER))
 		goto lock_mmap;
 
+retry_vma:
 	vma = lock_vma_under_rcu(mm, address);
 	if (!vma)
 		goto lock_mmap;
@@ -1351,6 +1352,9 @@ void do_user_addr_fault(struct pt_regs *regs,
 						 ARCH_DEFAULT_PKEY);
 		return;
 	}
+	/* If the first try is only about waiting for the I/O to complete */
+	if (fault & VM_FAULT_RETRY_VMA)
+		goto retry_vma;
 lock_mmap:
 
 retry:
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index a308e2c23b82..5907200ea587 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -1678,10 +1678,11 @@ enum vm_fault_reason {
 	VM_FAULT_NOPAGE         = (__force vm_fault_t)0x000100,
 	VM_FAULT_LOCKED         = (__force vm_fault_t)0x000200,
 	VM_FAULT_RETRY          = (__force vm_fault_t)0x000400,
-	VM_FAULT_FALLBACK       = (__force vm_fault_t)0x000800,
-	VM_FAULT_DONE_COW       = (__force vm_fault_t)0x001000,
-	VM_FAULT_NEEDDSYNC      = (__force vm_fault_t)0x002000,
-	VM_FAULT_COMPLETED      = (__force vm_fault_t)0x004000,
+	VM_FAULT_RETRY_VMA      = (__force vm_fault_t)0x000800,
+	VM_FAULT_FALLBACK       = (__force vm_fault_t)0x001000,
+	VM_FAULT_DONE_COW       = (__force vm_fault_t)0x002000,
+	VM_FAULT_NEEDDSYNC      = (__force vm_fault_t)0x004000,
+	VM_FAULT_COMPLETED      = (__force vm_fault_t)0x008000,
 	VM_FAULT_HINDEX_MASK    = (__force vm_fault_t)0x0f0000,
 };
 
diff --git a/mm/filemap.c b/mm/filemap.c
index ab34cab2416a..a045b771e8de 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3525,6 +3525,7 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
 	struct folio *folio;
 	vm_fault_t ret = 0;
 	bool mapping_locked = false;
+	bool retry_by_vma_lock = false;
 
 	max_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
 	if (unlikely(index >= max_idx))
@@ -3621,6 +3622,8 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
 	 */
 	if (fpin) {
 		folio_unlock(folio);
+		if (vmf->flags & FAULT_FLAG_VMA_LOCK)
+			retry_by_vma_lock = true;
 		goto out_retry;
 	}
 	if (mapping_locked)
@@ -3671,7 +3674,7 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
 		filemap_invalidate_unlock_shared(mapping);
 	if (fpin)
 		fput(fpin);
-	return ret | VM_FAULT_RETRY;
+	return ret | VM_FAULT_RETRY | (retry_by_vma_lock ? VM_FAULT_RETRY_VMA : 0);
 }
 EXPORT_SYMBOL(filemap_fault);
 
-- 
2.39.3 (Apple Git-146)