mm: replace FAULT_FLAG_SIZE with parameter to huge_fault

Since the introduction of FAULT_FLAG_SIZE to the vm_fault flag, it has
been somewhat painful with getting the flags set and removed at the
correct locations.  More than one kernel oops was introduced due to
difficulties of getting the placement correctly.

Remove the flag values and introduce an input parameter to huge_fault
that indicates the size of the page entry.  This makes the code easier
to trace and should avoid the issues we see with the fault flags where
removal of the flag was necessary in the fallback paths.

Link: http://lkml.kernel.org/r/148615748258.43180.1690152053774975329.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Tested-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Matthew Wilcox <mawilcox@microsoft.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c
index b90bb301bda0b9461bfb560f45d8ee3744fdf4ad..b75c77254fdb56dee9e66da6a254688a5529f2d4 100644 (file)
--- a/drivers/dax/dax.c
+++ b/drivers/dax/dax.c
@@ -538,7 +538,8 @@ static int __dax_dev_pud_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
 }
 #endif /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
 
-static int dax_dev_fault(struct vm_fault *vmf)
+static int dax_dev_huge_fault(struct vm_fault *vmf,
+               enum page_entry_size pe_size)
 {
        int rc;
        struct file *filp = vmf->vma->vm_file;
@@ -550,14 +551,14 @@ static int dax_dev_fault(struct vm_fault *vmf)
                        vmf->vma->vm_start, vmf->vma->vm_end);
 
        rcu_read_lock();
-       switch (vmf->flags & FAULT_FLAG_SIZE_MASK) {
-       case FAULT_FLAG_SIZE_PTE:
+       switch (pe_size) {
+       case PE_SIZE_PTE:
                rc = __dax_dev_pte_fault(dax_dev, vmf);
                break;
-       case FAULT_FLAG_SIZE_PMD:
+       case PE_SIZE_PMD:
                rc = __dax_dev_pmd_fault(dax_dev, vmf);
                break;
-       case FAULT_FLAG_SIZE_PUD:
+       case PE_SIZE_PUD:
                rc = __dax_dev_pud_fault(dax_dev, vmf);
                break;
        default:
@@ -568,9 +569,14 @@ static int dax_dev_fault(struct vm_fault *vmf)
        return rc;
 }
 
+static int dax_dev_fault(struct vm_fault *vmf)
+{
+       return dax_dev_huge_fault(vmf, PE_SIZE_PTE);
+}
+
 static const struct vm_operations_struct dax_dev_vm_ops = {
        .fault = dax_dev_fault,
-       .huge_fault = dax_dev_fault,
+       .huge_fault = dax_dev_huge_fault,
 };
 
 static int dax_mmap(struct file *filp, struct vm_area_struct *vma)

diff --git a/fs/dax.c b/fs/dax.c
index c3c29fbf64be09dc60a4f517c97745068feb9ac5..5ae8b71ebadc91eaff464128422ce5571fb4e24e 100644 (file)
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1452,12 +1452,13 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf, struct iomap_ops *ops)
  * has done all the necessary locking for page fault to proceed
  * successfully.
  */
-int dax_iomap_fault(struct vm_fault *vmf, const struct iomap_ops *ops)
+int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
+                   const struct iomap_ops *ops)
 {
-       switch (vmf->flags & FAULT_FLAG_SIZE_MASK) {
-       case FAULT_FLAG_SIZE_PTE:
+       switch (pe_size) {
+       case PE_SIZE_PTE:
                return dax_iomap_pte_fault(vmf, ops);
-       case FAULT_FLAG_SIZE_PMD:
+       case PE_SIZE_PMD:
                return dax_iomap_pmd_fault(vmf, ops);
        default:
                return VM_FAULT_FALLBACK;

diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 68738832beda615dff8f926882d32692b5bc4a70..b21891a6bfca6611f9ad89a412594c2e92d695cc 100644 (file)
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -99,7 +99,7 @@ static int ext2_dax_fault(struct vm_fault *vmf)
        }
        down_read(&ei->dax_sem);
 
-       ret = dax_iomap_fault(vmf, &ext2_iomap_ops);
+       ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &ext2_iomap_ops);
 
        up_read(&ei->dax_sem);
        if (vmf->flags & FAULT_FLAG_WRITE)

diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 502d2d07d19116cbf5283d5b591187778c5f8707..8210c1f43556f4358e9b602a93d158e5c0780c44 100644 (file)
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -253,7 +253,8 @@ out:
 }
 
 #ifdef CONFIG_FS_DAX
-static int ext4_dax_fault(struct vm_fault *vmf)
+static int ext4_dax_huge_fault(struct vm_fault *vmf,
+               enum page_entry_size pe_size)
 {
        int result;
        struct inode *inode = file_inode(vmf->vma->vm_file);
@@ -265,7 +266,7 @@ static int ext4_dax_fault(struct vm_fault *vmf)
                file_update_time(vmf->vma->vm_file);
        }
        down_read(&EXT4_I(inode)->i_mmap_sem);
-       result = dax_iomap_fault(vmf, &ext4_iomap_ops);
+       result = dax_iomap_fault(vmf, pe_size, &ext4_iomap_ops);
        up_read(&EXT4_I(inode)->i_mmap_sem);
        if (write)
                sb_end_pagefault(sb);
@@ -273,6 +274,11 @@ static int ext4_dax_fault(struct vm_fault *vmf)
        return result;
 }
 
+static int ext4_dax_fault(struct vm_fault *vmf)
+{
+       return ext4_dax_huge_fault(vmf, PE_SIZE_PTE);
+}
+
 /*
  * Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_fault()
  * handler we check for races agaist truncate. Note that since we cycle through
@@ -305,7 +311,7 @@ static int ext4_dax_pfn_mkwrite(struct vm_fault *vmf)
 
 static const struct vm_operations_struct ext4_dax_vm_ops = {
        .fault          = ext4_dax_fault,
-       .huge_fault     = ext4_dax_fault,
+       .huge_fault     = ext4_dax_huge_fault,
        .page_mkwrite   = ext4_dax_fault,
        .pfn_mkwrite    = ext4_dax_pfn_mkwrite,
 };

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 990e0381937072b5bcf9fb515ce3ab99e4e64a95..a50eca676670f8e81331e9bec659e6bde45acf12 100644 (file)
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1391,7 +1391,7 @@ xfs_filemap_page_mkwrite(
        xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
        if (IS_DAX(inode)) {
-               ret = dax_iomap_fault(vmf, &xfs_iomap_ops);
+               ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &xfs_iomap_ops);
        } else {
                ret = iomap_page_mkwrite(vmf, &xfs_iomap_ops);
                ret = block_page_mkwrite_return(ret);
@@ -1418,7 +1418,7 @@ xfs_filemap_fault(
 
        xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
        if (IS_DAX(inode))
-               ret = dax_iomap_fault(vmf, &xfs_iomap_ops);
+               ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &xfs_iomap_ops);
        else
                ret = filemap_fault(vmf);
        xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
@@ -1435,7 +1435,8 @@ xfs_filemap_fault(
  */
 STATIC int
 xfs_filemap_huge_fault(
-       struct vm_fault         *vmf)
+       struct vm_fault         *vmf,
+       enum page_entry_size    pe_size)
 {
        struct inode            *inode = file_inode(vmf->vma->vm_file);
        struct xfs_inode        *ip = XFS_I(inode);
@@ -1452,7 +1453,7 @@ xfs_filemap_huge_fault(
        }
 
        xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-       ret = dax_iomap_fault(vmf, &xfs_iomap_ops);
+       ret = dax_iomap_fault(vmf, pe_size, &xfs_iomap_ops);
        xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
        if (vmf->flags & FAULT_FLAG_WRITE)

diff --git a/include/linux/dax.h b/include/linux/dax.h
index cf9af225962b1bb937ec963bf623a984ff7578aa..d8a3dc042e1cbb81f1c3a906ee6fc0d28fead8f8 100644 (file)
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -38,7 +38,8 @@ static inline void *dax_radix_locked_entry(sector_t sector, unsigned long flags)
 
 ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
                const struct iomap_ops *ops);
-int dax_iomap_fault(struct vm_fault *vmf, const struct iomap_ops *ops);
+int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
+                   const struct iomap_ops *ops);
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
 int dax_invalidate_mapping_entry(struct address_space *mapping, pgoff_t index);
 int dax_invalidate_mapping_entry_sync(struct address_space *mapping,

diff --git a/include/linux/mm.h b/include/linux/mm.h
index d8b75d7d6a9e41f0befe6152856580ad4605339a..c65aa43b5712a30a79261fbb1c9a884ff56d9aef 100644 (file)
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -285,11 +285,6 @@ extern pgprot_t protection_map[16];
 #define FAULT_FLAG_REMOTE      0x80    /* faulting for non current tsk/mm */
 #define FAULT_FLAG_INSTRUCTION  0x100  /* The fault was during an instruction fetch */
 
-#define FAULT_FLAG_SIZE_MASK   0x7000  /* Support up to 8-level page tables */
-#define FAULT_FLAG_SIZE_PTE    0x0000  /* First level (eg 4k) */
-#define FAULT_FLAG_SIZE_PMD    0x1000  /* Second level (eg 2MB) */
-#define FAULT_FLAG_SIZE_PUD    0x2000  /* Third level (eg 1GB) */
-
 #define FAULT_FLAG_TRACE \
        { FAULT_FLAG_WRITE,             "WRITE" }, \
        { FAULT_FLAG_MKWRITE,           "MKWRITE" }, \
@@ -349,6 +344,13 @@ struct vm_fault {
                                         */
 };
 
+/* page entry size for vm->huge_fault() */
+enum page_entry_size {
+       PE_SIZE_PTE = 0,
+       PE_SIZE_PMD,
+       PE_SIZE_PUD,
+};
+
 /*
  * These are the virtual MM functions - opening of an area, closing and
  * unmapping it (needed to keep files on disk up-to-date etc), pointer
@@ -359,7 +361,7 @@ struct vm_operations_struct {
        void (*close)(struct vm_area_struct * area);
        int (*mremap)(struct vm_area_struct * area);
        int (*fault)(struct vm_fault *vmf);
-       int (*huge_fault)(struct vm_fault *vmf);
+       int (*huge_fault)(struct vm_fault *vmf, enum page_entry_size pe_size);
        void (*map_pages)(struct vm_fault *vmf,
                        pgoff_t start_pgoff, pgoff_t end_pgoff);
 

diff --git a/mm/memory.c b/mm/memory.c
index 41e2a2d4b2a6cf24a275bb08b09c2532edf76205..6040b74d02a2bbce55f22e05b1bd723e5c31bb4b 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3489,7 +3489,7 @@ static int create_huge_pmd(struct vm_fault *vmf)
        if (vma_is_anonymous(vmf->vma))
                return do_huge_pmd_anonymous_page(vmf);
        if (vmf->vma->vm_ops->huge_fault)
-               return vmf->vma->vm_ops->huge_fault(vmf);
+               return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD);
        return VM_FAULT_FALLBACK;
 }
 
@@ -3498,7 +3498,7 @@ static int wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd)
        if (vma_is_anonymous(vmf->vma))
                return do_huge_pmd_wp_page(vmf, orig_pmd);
        if (vmf->vma->vm_ops->huge_fault)
-               return vmf->vma->vm_ops->huge_fault(vmf);
+               return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD);
 
        /* COW handled on pte level: split pmd */
        VM_BUG_ON_VMA(vmf->vma->vm_flags & VM_SHARED, vmf->vma);
@@ -3519,7 +3519,7 @@ static int create_huge_pud(struct vm_fault *vmf)
        if (vma_is_anonymous(vmf->vma))
                return VM_FAULT_FALLBACK;
        if (vmf->vma->vm_ops->huge_fault)
-               return vmf->vma->vm_ops->huge_fault(vmf);
+               return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD);
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
        return VM_FAULT_FALLBACK;
 }
@@ -3531,7 +3531,7 @@ static int wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud)
        if (vma_is_anonymous(vmf->vma))
                return VM_FAULT_FALLBACK;
        if (vmf->vma->vm_ops->huge_fault)
-               return vmf->vma->vm_ops->huge_fault(vmf);
+               return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD);
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
        return VM_FAULT_FALLBACK;
 }
@@ -3659,7 +3659,6 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
        if (!vmf.pud)
                return VM_FAULT_OOM;
        if (pud_none(*vmf.pud) && transparent_hugepage_enabled(vma)) {
-               vmf.flags |= FAULT_FLAG_SIZE_PUD;
                ret = create_huge_pud(&vmf);
                if (!(ret & VM_FAULT_FALLBACK))
                        return ret;
@@ -3670,8 +3669,6 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
                if (pud_trans_huge(orig_pud) || pud_devmap(orig_pud)) {
                        unsigned int dirty = flags & FAULT_FLAG_WRITE;
 
-                       vmf.flags |= FAULT_FLAG_SIZE_PUD;
-
                        /* NUMA case for anonymous PUDs would go here */
 
                        if (dirty && !pud_write(orig_pud)) {
@@ -3689,18 +3686,14 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
        if (!vmf.pmd)
                return VM_FAULT_OOM;
        if (pmd_none(*vmf.pmd) && transparent_hugepage_enabled(vma)) {
-               vmf.flags |= FAULT_FLAG_SIZE_PMD;
                ret = create_huge_pmd(&vmf);
                if (!(ret & VM_FAULT_FALLBACK))
                        return ret;
-               /* fall through path, remove PMD flag */
-               vmf.flags &= ~FAULT_FLAG_SIZE_PMD;
        } else {
                pmd_t orig_pmd = *vmf.pmd;
 
                barrier();
                if (pmd_trans_huge(orig_pmd) || pmd_devmap(orig_pmd)) {
-                       vmf.flags |= FAULT_FLAG_SIZE_PMD;
                        if (pmd_protnone(orig_pmd) && vma_is_accessible(vma))
                                return do_huge_pmd_numa_page(&vmf, orig_pmd);
 
@@ -3709,8 +3702,6 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
                                ret = wp_huge_pmd(&vmf, orig_pmd);
                                if (!(ret & VM_FAULT_FALLBACK))
                                        return ret;
-                               /* fall through path, remove PUD flag */
-                               vmf.flags &= ~FAULT_FLAG_SIZE_PUD;
                        } else {
                                huge_pmd_set_accessed(&vmf, orig_pmd);
                                return 0;