#include <linux/atomic.h>
#include <linux/blkdev.h>
#include <linux/buffer_head.h>
+#include <linux/dax.h>
#include <linux/fs.h>
#include <linux/genhd.h>
#include <linux/highmem.h>
#include <linux/memcontrol.h>
#include <linux/mm.h>
#include <linux/mutex.h>
+#include <linux/pmem.h>
#include <linux/sched.h>
#include <linux/uio.h>
#include <linux/vmstat.h>
+/*
+ * dax_clear_blocks() is called from within transaction context from XFS,
+ * and hence this means the stack from this point must follow GFP_NOFS
+ * semantics for all operations.
+ */
int dax_clear_blocks(struct inode *inode, sector_t block, long size)
{
struct block_device *bdev = inode->i_sb->s_bdev;
might_sleep();
do {
- void *addr;
+ void __pmem *addr;
unsigned long pfn;
long count;
unsigned pgsz = PAGE_SIZE - offset_in_page(addr);
if (pgsz > count)
pgsz = count;
- if (pgsz < PAGE_SIZE)
- memset(addr, 0, pgsz);
- else
- clear_page(addr);
+ clear_pmem(addr, pgsz);
addr += pgsz;
size -= pgsz;
count -= pgsz;
}
} while (size);
+ wmb_pmem();
return 0;
}
EXPORT_SYMBOL_GPL(dax_clear_blocks);
-static long dax_get_addr(struct buffer_head *bh, void **addr, unsigned blkbits)
+static long dax_get_addr(struct buffer_head *bh, void __pmem **addr,
+ unsigned blkbits)
{
unsigned long pfn;
sector_t sector = bh->b_blocknr << (blkbits - 9);
return bdev_direct_access(bh->b_bdev, sector, addr, &pfn, bh->b_size);
}
-static void dax_new_buf(void *addr, unsigned size, unsigned first, loff_t pos,
- loff_t end)
+/* the clear_pmem() calls are ordered by a wmb_pmem() in the caller */
+static void dax_new_buf(void __pmem *addr, unsigned size, unsigned first,
+ loff_t pos, loff_t end)
{
loff_t final = end - pos + first; /* The final byte of the buffer */
if (first > 0)
- memset(addr, 0, first);
+ clear_pmem(addr, first);
if (final < size)
- memset(addr + final, 0, size - final);
+ clear_pmem(addr + final, size - final);
}
static bool buffer_written(struct buffer_head *bh)
loff_t pos = start;
loff_t max = start;
loff_t bh_max = start;
- void *addr;
+ void __pmem *addr;
bool hole = false;
+ bool need_wmb = false;
if (iov_iter_rw(iter) != WRITE)
end = min(end, i_size_read(inode));
while (pos < end) {
- unsigned len;
+ size_t len;
if (pos == max) {
unsigned blkbits = inode->i_blkbits;
- sector_t block = pos >> blkbits;
+ long page = pos >> PAGE_SHIFT;
+ sector_t block = page << (PAGE_SHIFT - blkbits);
unsigned first = pos - (block << blkbits);
long size;
retval = dax_get_addr(bh, &addr, blkbits);
if (retval < 0)
break;
- if (buffer_unwritten(bh) || buffer_new(bh))
+ if (buffer_unwritten(bh) || buffer_new(bh)) {
dax_new_buf(addr, retval, first, pos,
end);
+ need_wmb = true;
+ }
addr += first;
size = retval - first;
}
max = min(pos + size, end);
}
- if (iov_iter_rw(iter) == WRITE)
- len = copy_from_iter(addr, max - pos, iter);
- else if (!hole)
- len = copy_to_iter(addr, max - pos, iter);
+ if (iov_iter_rw(iter) == WRITE) {
+ len = copy_from_iter_pmem(addr, max - pos, iter);
+ need_wmb = true;
+ } else if (!hole)
+ len = copy_to_iter((void __force *)addr, max - pos,
+ iter);
else
len = iov_iter_zero(max - pos, iter);
- if (!len)
+ if (!len) {
+ retval = -EFAULT;
break;
+ }
pos += len;
addr += len;
}
+ if (need_wmb)
+ wmb_pmem();
+
return (pos == start) ? retval : pos - start;
}
}
/* Protects against truncate */
- inode_dio_begin(inode);
+ if (!(flags & DIO_SKIP_DIO_COUNT))
+ inode_dio_begin(inode);
retval = dax_io(inode, iter, pos, end, get_block, &bh);
if ((retval > 0) && end_io)
end_io(iocb, pos, retval, bh.b_private);
- inode_dio_end(inode);
+ if (!(flags & DIO_SKIP_DIO_COUNT))
+ inode_dio_end(inode);
out:
return retval;
}
static int copy_user_bh(struct page *to, struct buffer_head *bh,
unsigned blkbits, unsigned long vaddr)
{
- void *vfrom, *vto;
+ void __pmem *vfrom;
+ void *vto;
+
if (dax_get_addr(bh, &vfrom, blkbits) < 0)
return -EIO;
vto = kmap_atomic(to);
- copy_user_page(vto, vfrom, vaddr, to);
+ copy_user_page(vto, (void __force *)vfrom, vaddr, to);
kunmap_atomic(vto);
return 0;
}
struct address_space *mapping = inode->i_mapping;
sector_t sector = bh->b_blocknr << (inode->i_blkbits - 9);
unsigned long vaddr = (unsigned long)vmf->virtual_address;
- void *addr;
+ void __pmem *addr;
unsigned long pfn;
pgoff_t size;
int error;
goto out;
}
- if (buffer_unwritten(bh) || buffer_new(bh))
- clear_page(addr);
+ if (buffer_unwritten(bh) || buffer_new(bh)) {
+ clear_pmem(addr, PAGE_SIZE);
+ wmb_pmem();
+ }
error = vm_insert_mixed(vma, vaddr, pfn);
out:
i_mmap_unlock_read(mapping);
- if (bh->b_end_io)
- bh->b_end_io(bh, 1);
-
return error;
}
-static int do_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
- get_block_t get_block)
+/**
+ * __dax_fault - handle a page fault on a DAX file
+ * @vma: The virtual memory area where the fault occurred
+ * @vmf: The description of the fault
+ * @get_block: The filesystem method used to translate file offsets to blocks
+ * @complete_unwritten: The filesystem method used to convert unwritten blocks
+ * to written so the data written to them is exposed. This is required for
+ * required by write faults for filesystems that will return unwritten
+ * extent mappings from @get_block, but it is optional for reads as
+ * dax_insert_mapping() will always zero unwritten blocks. If the fs does
+ * not support unwritten extents, the it should pass NULL.
+ *
+ * When a page fault occurs, filesystems may call this helper in their
+ * fault handler for DAX files. __dax_fault() assumes the caller has done all
+ * the necessary locking for the page fault to proceed successfully.
+ */
+int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
+ get_block_t get_block, dax_iodone_t complete_unwritten)
{
struct file *file = vma->vm_file;
struct address_space *mapping = file->f_mapping;
page_cache_release(page);
}
+ /*
+ * If we successfully insert the new mapping over an unwritten extent,
+ * we need to ensure we convert the unwritten extent. If there is an
+ * error inserting the mapping, the filesystem needs to leave it as
+ * unwritten to prevent exposure of the stale underlying data to
+ * userspace, but we still need to call the completion function so
+ * the private resources on the mapping buffer can be released. We
+ * indicate what the callback should do via the uptodate variable, same
+ * as for normal BH based IO completions.
+ */
error = dax_insert_mapping(inode, &bh, vma, vmf);
+ if (buffer_unwritten(&bh)) {
+ if (complete_unwritten)
+ complete_unwritten(&bh, !error);
+ else
+ WARN_ON_ONCE(!(vmf->flags & FAULT_FLAG_WRITE));
+ }
out:
if (error == -ENOMEM)
}
goto out;
}
+EXPORT_SYMBOL(__dax_fault);
/**
* dax_fault - handle a page fault on a DAX file
* fault handler for DAX files.
*/
int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
- get_block_t get_block)
+ get_block_t get_block, dax_iodone_t complete_unwritten)
{
int result;
struct super_block *sb = file_inode(vma->vm_file)->i_sb;
sb_start_pagefault(sb);
file_update_time(vma->vm_file);
}
- result = do_dax_fault(vma, vmf, get_block);
+ result = __dax_fault(vma, vmf, get_block, complete_unwritten);
if (vmf->flags & FAULT_FLAG_WRITE)
sb_end_pagefault(sb);
}
EXPORT_SYMBOL_GPL(dax_fault);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+/*
+ * The 'colour' (ie low bits) within a PMD of a page offset. This comes up
+ * more often than one might expect in the below function.
+ */
+#define PG_PMD_COLOUR ((PMD_SIZE >> PAGE_SHIFT) - 1)
+
+int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
+ pmd_t *pmd, unsigned int flags, get_block_t get_block,
+ dax_iodone_t complete_unwritten)
+{
+ struct file *file = vma->vm_file;
+ struct address_space *mapping = file->f_mapping;
+ struct inode *inode = mapping->host;
+ struct buffer_head bh;
+ unsigned blkbits = inode->i_blkbits;
+ unsigned long pmd_addr = address & PMD_MASK;
+ bool write = flags & FAULT_FLAG_WRITE;
+ long length;
+ void __pmem *kaddr;
+ pgoff_t size, pgoff;
+ sector_t block, sector;
+ unsigned long pfn;
+ int result = 0;
+
+ /* dax pmd mappings are broken wrt gup and fork */
+ if (!IS_ENABLED(CONFIG_FS_DAX_PMD))
+ return VM_FAULT_FALLBACK;
+
+ /* Fall back to PTEs if we're going to COW */
+ if (write && !(vma->vm_flags & VM_SHARED))
+ return VM_FAULT_FALLBACK;
+ /* If the PMD would extend outside the VMA */
+ if (pmd_addr < vma->vm_start)
+ return VM_FAULT_FALLBACK;
+ if ((pmd_addr + PMD_SIZE) > vma->vm_end)
+ return VM_FAULT_FALLBACK;
+
+ pgoff = linear_page_index(vma, pmd_addr);
+ size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ if (pgoff >= size)
+ return VM_FAULT_SIGBUS;
+ /* If the PMD would cover blocks out of the file */
+ if ((pgoff | PG_PMD_COLOUR) >= size)
+ return VM_FAULT_FALLBACK;
+
+ memset(&bh, 0, sizeof(bh));
+ block = (sector_t)pgoff << (PAGE_SHIFT - blkbits);
+
+ bh.b_size = PMD_SIZE;
+ length = get_block(inode, block, &bh, write);
+ if (length)
+ return VM_FAULT_SIGBUS;
+ i_mmap_lock_read(mapping);
+
+ /*
+ * If the filesystem isn't willing to tell us the length of a hole,
+ * just fall back to PTEs. Calling get_block 512 times in a loop
+ * would be silly.
+ */
+ if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE)
+ goto fallback;
+
+ /*
+ * If we allocated new storage, make sure no process has any
+ * zero pages covering this hole
+ */
+ if (buffer_new(&bh)) {
+ i_mmap_unlock_read(mapping);
+ unmap_mapping_range(mapping, pgoff << PAGE_SHIFT, PMD_SIZE, 0);
+ i_mmap_lock_read(mapping);
+ }
+
+ /*
+ * If a truncate happened while we were allocating blocks, we may
+ * leave blocks allocated to the file that are beyond EOF. We can't
+ * take i_mutex here, so just leave them hanging; they'll be freed
+ * when the file is deleted.
+ */
+ size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ if (pgoff >= size) {
+ result = VM_FAULT_SIGBUS;
+ goto out;
+ }
+ if ((pgoff | PG_PMD_COLOUR) >= size)
+ goto fallback;
+
+ if (!write && !buffer_mapped(&bh) && buffer_uptodate(&bh)) {
+ spinlock_t *ptl;
+ pmd_t entry;
+ struct page *zero_page = get_huge_zero_page();
+
+ if (unlikely(!zero_page))
+ goto fallback;
+
+ ptl = pmd_lock(vma->vm_mm, pmd);
+ if (!pmd_none(*pmd)) {
+ spin_unlock(ptl);
+ goto fallback;
+ }
+
+ entry = mk_pmd(zero_page, vma->vm_page_prot);
+ entry = pmd_mkhuge(entry);
+ set_pmd_at(vma->vm_mm, pmd_addr, pmd, entry);
+ result = VM_FAULT_NOPAGE;
+ spin_unlock(ptl);
+ } else {
+ sector = bh.b_blocknr << (blkbits - 9);
+ length = bdev_direct_access(bh.b_bdev, sector, &kaddr, &pfn,
+ bh.b_size);
+ if (length < 0) {
+ result = VM_FAULT_SIGBUS;
+ goto out;
+ }
+ if ((length < PMD_SIZE) || (pfn & PG_PMD_COLOUR))
+ goto fallback;
+
+ /*
+ * TODO: teach vmf_insert_pfn_pmd() to support
+ * 'pte_special' for pmds
+ */
+ if (pfn_valid(pfn))
+ goto fallback;
+
+ if (buffer_unwritten(&bh) || buffer_new(&bh)) {
+ int i;
+ for (i = 0; i < PTRS_PER_PMD; i++)
+ clear_pmem(kaddr + i * PAGE_SIZE, PAGE_SIZE);
+ wmb_pmem();
+ count_vm_event(PGMAJFAULT);
+ mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
+ result |= VM_FAULT_MAJOR;
+ }
+
+ result |= vmf_insert_pfn_pmd(vma, address, pmd, pfn, write);
+ }
+
+ out:
+ i_mmap_unlock_read(mapping);
+
+ if (buffer_unwritten(&bh))
+ complete_unwritten(&bh, !(result & VM_FAULT_ERROR));
+
+ return result;
+
+ fallback:
+ count_vm_event(THP_FAULT_FALLBACK);
+ result = VM_FAULT_FALLBACK;
+ goto out;
+}
+EXPORT_SYMBOL_GPL(__dax_pmd_fault);
+
+/**
+ * dax_pmd_fault - handle a PMD fault on a DAX file
+ * @vma: The virtual memory area where the fault occurred
+ * @vmf: The description of the fault
+ * @get_block: The filesystem method used to translate file offsets to blocks
+ *
+ * When a page fault occurs, filesystems may call this helper in their
+ * pmd_fault handler for DAX files.
+ */
+int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
+ pmd_t *pmd, unsigned int flags, get_block_t get_block,
+ dax_iodone_t complete_unwritten)
+{
+ int result;
+ struct super_block *sb = file_inode(vma->vm_file)->i_sb;
+
+ if (flags & FAULT_FLAG_WRITE) {
+ sb_start_pagefault(sb);
+ file_update_time(vma->vm_file);
+ }
+ result = __dax_pmd_fault(vma, address, pmd, flags, get_block,
+ complete_unwritten);
+ if (flags & FAULT_FLAG_WRITE)
+ sb_end_pagefault(sb);
+
+ return result;
+}
+EXPORT_SYMBOL_GPL(dax_pmd_fault);
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
/**
* dax_pfn_mkwrite - handle first write to DAX page
* @vma: The virtual memory area where the fault occurred
if (err < 0)
return err;
if (buffer_written(&bh)) {
- void *addr;
+ void __pmem *addr;
err = dax_get_addr(&bh, &addr, inode->i_blkbits);
if (err < 0)
return err;
- memset(addr + offset, 0, length);
+ clear_pmem(addr + offset, length);
+ wmb_pmem();
}
return 0;
Code Review / kvmfornfv.git / blobdiff