summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2015-09-08 14:35:59 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2015-09-08 14:35:59 -0700
commit12f03ee606914317e7e6a0815e53a48205c31dae (patch)
treef8579bf77d29b3921e1877e0ae12ec65b5ebc738 /fs
parentd9241b22b58e012f26dd2244508d9f4837402af0 (diff)
parent004f1afbe199e6ab20805b95aefd83ccd24bc5c7 (diff)
Merge tag 'libnvdimm-for-4.3' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm
Pull libnvdimm updates from Dan Williams: "This update has successfully completed a 0day-kbuild run and has appeared in a linux-next release. The changes outside of the typical drivers/nvdimm/ and drivers/acpi/nfit.[ch] paths are related to the removal of IORESOURCE_CACHEABLE, the introduction of memremap(), and the introduction of ZONE_DEVICE + devm_memremap_pages(). Summary: - Introduce ZONE_DEVICE and devm_memremap_pages() as a generic mechanism for adding device-driver-discovered memory regions to the kernel's direct map. This facility is used by the pmem driver to enable pfn_to_page() operations on the page frames returned by DAX ('direct_access' in 'struct block_device_operations'). For now, the 'memmap' allocation for these "device" pages comes from "System RAM". Support for allocating the memmap from device memory will arrive in a later kernel. - Introduce memremap() to replace usages of ioremap_cache() and ioremap_wt(). memremap() drops the __iomem annotation for these mappings to memory that do not have i/o side effects. The replacement of ioremap_cache() with memremap() is limited to the pmem driver to ease merging the api change in v4.3. Completion of the conversion is targeted for v4.4. - Similar to the usage of memcpy_to_pmem() + wmb_pmem() in the pmem driver, update the VFS DAX implementation and PMEM api to provide persistence guarantees for kernel operations on a DAX mapping. - Convert the ACPI NFIT 'BLK' driver to map the block apertures as cacheable to improve performance. - Miscellaneous updates and fixes to libnvdimm including support for issuing "address range scrub" commands, clarifying the optimal 'sector size' of pmem devices, a clarification of the usage of the ACPI '_STA' (status) property for DIMM devices, and other minor fixes" * tag 'libnvdimm-for-4.3' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (34 commits) libnvdimm, pmem: direct map legacy pmem by default libnvdimm, pmem: 'struct page' for pmem libnvdimm, pfn: 'struct page' provider infrastructure x86, pmem: clarify that ARCH_HAS_PMEM_API implies PMEM mapped WB add devm_memremap_pages mm: ZONE_DEVICE for "device memory" mm: move __phys_to_pfn and __pfn_to_phys to asm/generic/memory_model.h dax: drop size parameter to ->direct_access() nd_blk: change aperture mapping from WC to WB nvdimm: change to use generic kvfree() pmem, dax: have direct_access use __pmem annotation dax: update I/O path to do proper PMEM flushing pmem: add copy_from_iter_pmem() and clear_pmem() pmem, x86: clean up conditional pmem includes pmem: remove layer when calling arch_has_wmb_pmem() pmem, x86: move x86 PMEM API to new pmem.h header libnvdimm, e820: make CONFIG_X86_PMEM_LEGACY a tristate option pmem: switch to devm_ allocations devres: add devm_memremap libnvdimm, btt: write and validate parent_uuid ...
Diffstat (limited to 'fs')
-rw-r--r--fs/block_dev.c4
-rw-r--r--fs/dax.c62
2 files changed, 40 insertions, 26 deletions
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 33b813e04f79..f77da0ec0e64 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -441,7 +441,7 @@ EXPORT_SYMBOL_GPL(bdev_write_page);
* accessible at this address.
*/
long bdev_direct_access(struct block_device *bdev, sector_t sector,
- void **addr, unsigned long *pfn, long size)
+ void __pmem **addr, unsigned long *pfn, long size)
{
long avail;
const struct block_device_operations *ops = bdev->bd_disk->fops;
@@ -462,7 +462,7 @@ long bdev_direct_access(struct block_device *bdev, sector_t sector,
sector += get_start_sect(bdev);
if (sector % (PAGE_SIZE / 512))
return -EINVAL;
- avail = ops->direct_access(bdev, sector, addr, pfn, size);
+ avail = ops->direct_access(bdev, sector, addr, pfn);
if (!avail)
return -ERANGE;
return min(avail, size);
diff --git a/fs/dax.c b/fs/dax.c
index a7f77e1fa18c..57bb70b4af70 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -23,6 +23,7 @@
#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>
@@ -34,7 +35,7 @@ int dax_clear_blocks(struct inode *inode, sector_t block, long size)
might_sleep();
do {
- void *addr;
+ void __pmem *addr;
unsigned long pfn;
long count;
@@ -46,10 +47,7 @@ int dax_clear_blocks(struct inode *inode, sector_t block, long size)
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;
@@ -59,26 +57,29 @@ int dax_clear_blocks(struct inode *inode, sector_t block, long size)
}
} 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)
@@ -106,14 +107,15 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
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;
@@ -145,19 +147,23 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
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_nocache(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);
@@ -168,6 +174,9 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
addr += len;
}
+ if (need_wmb)
+ wmb_pmem();
+
return (pos == start) ? retval : pos - start;
}
@@ -260,11 +269,13 @@ static int dax_load_hole(struct address_space *mapping, struct page *page,
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;
}
@@ -275,7 +286,7 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
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;
@@ -303,8 +314,10 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
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);
@@ -548,11 +561,12 @@ int dax_zero_page_range(struct inode *inode, loff_t from, unsigned length,
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;