static int pmem_do_bvec(struct pmem_device *pmem, struct page *page,
unsigned int len, unsigned int off, int rw,
sector_t sector)
{
int rc = 0;
bool bad_pmem = false;
void *mem = kmap_atomic(page);
phys_addr_t pmem_off = sector * 512 + pmem->data_offset;
void __pmem *pmem_addr = pmem->virt_addr + pmem_off;
if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
bad_pmem = true;
if (rw == READ) {
if (unlikely(bad_pmem))
rc = -EIO;
else {
rc = memcpy_from_pmem(mem + off, pmem_addr, len);
flush_dcache_page(page);
}
} else {
/*
* Note that we write the data both before and after
* clearing poison. The write before clear poison
* handles situations where the latest written data is
* preserved and the clear poison operation simply marks
* the address range as valid without changing the data.
* In this case application software can assume that an
* interrupted write will either return the new good
* data or an error.
*
* However, if pmem_clear_poison() leaves the data in an
* indeterminate state we need to perform the write
* after clear poison.
*/
flush_dcache_page(page);
memcpy_to_pmem(pmem_addr, mem + off, len);
if (unlikely(bad_pmem)) {
pmem_clear_poison(pmem, pmem_off, len);
memcpy_to_pmem(pmem_addr, mem + off, len);
}
}
kunmap_atomic(mem);
return rc;
}
static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page,
unsigned int len, unsigned int off, unsigned int op,
sector_t sector)
{
blk_status_t rc = BLK_STS_OK;
bool bad_pmem = false;
phys_addr_t pmem_off = sector * 512 + pmem->data_offset;
void *pmem_addr = pmem->virt_addr + pmem_off;
if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
bad_pmem = true;
if (!op_is_write(op)) {
if (unlikely(bad_pmem))
rc = BLK_STS_IOERR;
else {
rc = read_pmem(page, off, pmem_addr, len);
flush_dcache_page(page);
}
} else {
/*
* Note that we write the data both before and after
* clearing poison. The write before clear poison
* handles situations where the latest written data is
* preserved and the clear poison operation simply marks
* the address range as valid without changing the data.
* In this case application software can assume that an
* interrupted write will either return the new good
* data or an error.
*
* However, if pmem_clear_poison() leaves the data in an
* indeterminate state we need to perform the write
* after clear poison.
*/
flush_dcache_page(page);
write_pmem(pmem_addr, page, off, len);
if (unlikely(bad_pmem)) {
rc = pmem_clear_poison(pmem, pmem_off, len);
write_pmem(pmem_addr, page, off, len);
}
}
return rc;
}
static int pmem_do_bvec(struct pmem_device *pmem, struct page *page,
unsigned int len, unsigned int off, int rw,
sector_t sector)
{
void *mem = kmap_atomic(page);
phys_addr_t pmem_off = sector * 512 + pmem->data_offset;
void __pmem *pmem_addr = pmem->virt_addr + pmem_off;
if (rw == READ) {
if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
return -EIO;
memcpy_from_pmem(mem + off, pmem_addr, len);
flush_dcache_page(page);
} else {
flush_dcache_page(page);
memcpy_to_pmem(pmem_addr, mem + off, len);
}
kunmap_atomic(mem);
return 0;
}
static int nsio_rw_bytes(struct nd_namespace_common *ndns,
resource_size_t offset, void *buf, size_t size, int rw)
{
struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
if (unlikely(offset + size > nsio->size)) {
dev_WARN_ONCE(&ndns->dev, 1, "request out of range\n");
return -EFAULT;
}
if (rw == READ) {
unsigned int sz_align = ALIGN(size + (offset & (512 - 1)), 512);
if (unlikely(is_bad_pmem(&nsio->bb, offset / 512, sz_align)))
return -EIO;
return memcpy_from_pmem(buf, nsio->addr + offset, size);
} else {
memcpy_to_pmem(nsio->addr + offset, buf, size);
nvdimm_flush(to_nd_region(ndns->dev.parent));
}
return 0;
}
long pmem_direct_access(struct block_device *bdev, sector_t sector,
void __pmem **kaddr, pfn_t *pfn, long size)
{
struct pmem_device *pmem = bdev->bd_queue->queuedata;
resource_size_t offset = sector * 512 + pmem->data_offset;
if (unlikely(is_bad_pmem(&pmem->bb, sector, size)))
return -EIO;
/*
* Limit dax to a single page at a time given vmalloc()-backed
* in the nfit_test case.
*/
if (get_nfit_res(pmem->phys_addr + offset)) {
struct page *page;
*kaddr = pmem->virt_addr + offset;
page = vmalloc_to_page(pmem->virt_addr + offset);
*pfn = page_to_pfn_t(page);
dev_dbg_ratelimited(disk_to_dev(bdev->bd_disk)->parent,
"%s: sector: %#llx pfn: %#lx\n", __func__,
(unsigned long long) sector, page_to_pfn(page));
return PAGE_SIZE;
}
*kaddr = pmem->virt_addr + offset;
*pfn = phys_to_pfn_t(pmem->phys_addr + offset, pmem->pfn_flags);
/*
* If badblocks are present, limit known good range to the
* requested range.
*/
if (unlikely(pmem->bb.count))
return size;
return pmem->size - pmem->pfn_pad - offset;
}