From patchwork series 502184

https://patchwork.ozlabs.org//project/linuxppc-dev/list/?series=502184

Author: Fox Snowpatch

arch/arm/mm/fault.c

@@ -349,6 +349,7 @@ 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;
@@ -378,6 +379,10 @@ 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:

arch/arm64/mm/fault.c

@@ -626,6 +626,7 @@ 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;
@@ -672,6 +673,10 @@ 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:

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:

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

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:

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);

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:

include/linux/mm_types.h

@@ -1625,10 +1625,11 @@ 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,
 };
 

include/linux/pagemap.h

@@ -1101,7 +1101,6 @@ static inline bool wake_page_match(struct wait_page_queue *wait_page,
 
 void __folio_lock(struct folio *folio);
 int __folio_lock_killable(struct folio *folio);
-vm_fault_t __folio_lock_or_retry(struct folio *folio, struct vm_fault *vmf);
 void unlock_page(struct page *page);
 void folio_unlock(struct folio *folio);
 
@@ -1198,22 +1197,6 @@ static inline int folio_lock_killable(struct folio *folio)
 	return 0;
 }
 
-/*
- * folio_lock_or_retry - Lock the folio, unless this would block and the
- * caller indicated that it can handle a retry.
- *
- * Return value and mmap_lock implications depend on flags; see
- * __folio_lock_or_retry().
- */
-static inline vm_fault_t folio_lock_or_retry(struct folio *folio,
-					     struct vm_fault *vmf)
-{
-	might_sleep();
-	if (!folio_trylock(folio))
-		return __folio_lock_or_retry(folio, vmf);
-	return 0;
-}
-
 /*
  * This is exported only for folio_wait_locked/folio_wait_writeback, etc.,
  * and should not be used directly.

mm/filemap.c

@@ -1739,51 +1739,6 @@ static int __folio_lock_async(struct folio *folio, struct wait_page_queue *wait)
 	return ret;
 }
 
-/*
- * Return values:
- * 0 - folio is locked.
- * non-zero - folio is not locked.
- *     mmap_lock or per-VMA lock has been released (mmap_read_unlock() or
- *     vma_end_read()), unless flags had both FAULT_FLAG_ALLOW_RETRY and
- *     FAULT_FLAG_RETRY_NOWAIT set, in which case the lock is still held.
- *
- * If neither ALLOW_RETRY nor KILLABLE are set, will always return 0
- * with the folio locked and the mmap_lock/per-VMA lock is left unperturbed.
- */
-vm_fault_t __folio_lock_or_retry(struct folio *folio, struct vm_fault *vmf)
-{
-	unsigned int flags = vmf->flags;
-
-	if (fault_flag_allow_retry_first(flags)) {
-		/*
-		 * CAUTION! In this case, mmap_lock/per-VMA lock is not
-		 * released even though returning VM_FAULT_RETRY.
-		 */
-		if (flags & FAULT_FLAG_RETRY_NOWAIT)
-			return VM_FAULT_RETRY;
-
-		release_fault_lock(vmf);
-		if (flags & FAULT_FLAG_KILLABLE)
-			folio_wait_locked_killable(folio);
-		else
-			folio_wait_locked(folio);
-		return VM_FAULT_RETRY;
-	}
-	if (flags & FAULT_FLAG_KILLABLE) {
-		bool ret;
-
-		ret = __folio_lock_killable(folio);
-		if (ret) {
-			release_fault_lock(vmf);
-			return VM_FAULT_RETRY;
-		}
-	} else {
-		__folio_lock(folio);
-	}
-
-	return 0;
-}
-
 /**
  * page_cache_next_miss() - Find the next gap in the page cache.
  * @mapping: Mapping.
@@ -3520,6 +3475,7 @@ 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))
@@ -3572,6 +3528,13 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
 		}
 	}
 
+	/*
+	 * If the folio is uptodate, we are likely only waiting for
+	 * another concurrent PTE mapping to complete, which should
+	 * be brief. No need to drop the lock and retry the fault.
+	 */
+	if (folio_test_uptodate(folio))
+		vmf->flags &= ~FAULT_FLAG_ALLOW_RETRY;
 	if (!lock_folio_maybe_drop_mmap(vmf, folio, &fpin))
 		goto out_retry;
 
@@ -3616,6 +3579,8 @@ 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)
@@ -3666,7 +3631,7 @@ 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);