lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20220420020435.90326-5-jane.chu@oracle.com>
Date:   Tue, 19 Apr 2022 20:04:32 -0600
From:   Jane Chu <jane.chu@...cle.com>
To:     dan.j.williams@...el.com, bp@...en8.de, hch@...radead.org,
        dave.hansen@...el.com, peterz@...radead.org, luto@...nel.org,
        david@...morbit.com, djwong@...nel.org,
        linux-fsdevel@...r.kernel.org, nvdimm@...ts.linux.dev,
        linux-kernel@...r.kernel.org, x86@...nel.org
Cc:     vishal.l.verma@...el.com, dave.jiang@...el.com, agk@...hat.com,
        snitzer@...hat.com, dm-devel@...hat.com, ira.weiny@...el.com,
        willy@...radead.org, vgoyal@...hat.com
Subject: [PATCH v8 4/7] dax: introduce DAX_RECOVERY_WRITE dax access mode

Up till now, dax_direct_access() is used implicitly for normal
access, but for the purpose of recovery write, dax range with
poison is requested.  To make the interface clear, introduce
	enum dax_access_mode {
		DAX_ACCESS,
		DAX_RECOVERY_WRITE,
	}
where DAX_ACCESS is used for normal dax access, and
DAX_RECOVERY_WRITE is used for dax recovery write.

Suggested-by: Dan Williams <dan.j.williams@...el.com>
Signed-off-by: Jane Chu <jane.chu@...cle.com>
---
 drivers/dax/super.c             |  5 ++--
 drivers/md/dm-linear.c          |  5 ++--
 drivers/md/dm-log-writes.c      |  5 ++--
 drivers/md/dm-stripe.c          |  5 ++--
 drivers/md/dm-target.c          |  4 ++-
 drivers/md/dm-writecache.c      |  7 +++---
 drivers/md/dm.c                 |  5 ++--
 drivers/nvdimm/pmem.c           | 44 +++++++++++++++++++++++++--------
 drivers/nvdimm/pmem.h           |  5 +++-
 drivers/s390/block/dcssblk.c    |  9 ++++---
 fs/dax.c                        |  9 ++++---
 fs/fuse/dax.c                   |  4 +--
 include/linux/dax.h             |  9 +++++--
 include/linux/device-mapper.h   |  4 ++-
 tools/testing/nvdimm/pmem-dax.c |  3 ++-
 15 files changed, 85 insertions(+), 38 deletions(-)

diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 0211e6f7b47a..5405eb553430 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -117,6 +117,7 @@ enum dax_device_flags {
  * @dax_dev: a dax_device instance representing the logical memory range
  * @pgoff: offset in pages from the start of the device to translate
  * @nr_pages: number of consecutive pages caller can handle relative to @pfn
+ * @mode: indicator on normal access or recovery write
  * @kaddr: output parameter that returns a virtual address mapping of pfn
  * @pfn: output parameter that returns an absolute pfn translation of @pgoff
  *
@@ -124,7 +125,7 @@ enum dax_device_flags {
  * pages accessible at the device relative @pgoff.
  */
 long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
-		void **kaddr, pfn_t *pfn)
+		enum dax_access_mode mode, void **kaddr, pfn_t *pfn)
 {
 	long avail;
 
@@ -138,7 +139,7 @@ long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
 		return -EINVAL;
 
 	avail = dax_dev->ops->direct_access(dax_dev, pgoff, nr_pages,
-			kaddr, pfn);
+			mode, kaddr, pfn);
 	if (!avail)
 		return -ERANGE;
 	return min(avail, nr_pages);
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 76b486e4d2be..13e263299c9c 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -172,11 +172,12 @@ static struct dax_device *linear_dax_pgoff(struct dm_target *ti, pgoff_t *pgoff)
 }
 
 static long linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn)
+		long nr_pages, enum dax_access_mode mode, void **kaddr,
+		pfn_t *pfn)
 {
 	struct dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff);
 
-	return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn);
+	return dax_direct_access(dax_dev, pgoff, nr_pages, mode, kaddr, pfn);
 }
 
 static int linear_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c
index c9d036d6bb2e..06bdbed65eb1 100644
--- a/drivers/md/dm-log-writes.c
+++ b/drivers/md/dm-log-writes.c
@@ -889,11 +889,12 @@ static struct dax_device *log_writes_dax_pgoff(struct dm_target *ti,
 }
 
 static long log_writes_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
-					 long nr_pages, void **kaddr, pfn_t *pfn)
+		long nr_pages, enum dax_access_mode mode, void **kaddr,
+		pfn_t *pfn)
 {
 	struct dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff);
 
-	return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn);
+	return dax_direct_access(dax_dev, pgoff, nr_pages, mode, kaddr, pfn);
 }
 
 static int log_writes_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index c81d331d1afe..77d72900e997 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -315,11 +315,12 @@ static struct dax_device *stripe_dax_pgoff(struct dm_target *ti, pgoff_t *pgoff)
 }
 
 static long stripe_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn)
+		long nr_pages, enum dax_access_mode mode, void **kaddr,
+		pfn_t *pfn)
 {
 	struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff);
 
-	return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn);
+	return dax_direct_access(dax_dev, pgoff, nr_pages, mode, kaddr, pfn);
 }
 
 static int stripe_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c
index 64dd0b34fcf4..8cd5184e62f0 100644
--- a/drivers/md/dm-target.c
+++ b/drivers/md/dm-target.c
@@ -10,6 +10,7 @@
 #include <linux/init.h>
 #include <linux/kmod.h>
 #include <linux/bio.h>
+#include <linux/dax.h>
 
 #define DM_MSG_PREFIX "target"
 
@@ -142,7 +143,8 @@ static void io_err_release_clone_rq(struct request *clone,
 }
 
 static long io_err_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn)
+		long nr_pages, enum dax_access_mode mode, void **kaddr,
+		pfn_t *pfn)
 {
 	return -EIO;
 }
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index 5630b470ba42..d74c5a7a0ab4 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -286,7 +286,8 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 
 	id = dax_read_lock();
 
-	da = dax_direct_access(wc->ssd_dev->dax_dev, offset, p, &wc->memory_map, &pfn);
+	da = dax_direct_access(wc->ssd_dev->dax_dev, offset, p, DAX_ACCESS,
+			&wc->memory_map, &pfn);
 	if (da < 0) {
 		wc->memory_map = NULL;
 		r = da;
@@ -308,8 +309,8 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 		i = 0;
 		do {
 			long daa;
-			daa = dax_direct_access(wc->ssd_dev->dax_dev, offset + i, p - i,
-						NULL, &pfn);
+			daa = dax_direct_access(wc->ssd_dev->dax_dev, offset + i,
+					p - i, DAX_ACCESS, NULL, &pfn);
 			if (daa <= 0) {
 				r = daa ? daa : -EINVAL;
 				goto err3;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 3c5fad7c4ee6..8258676a352f 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1093,7 +1093,8 @@ static struct dm_target *dm_dax_get_live_target(struct mapped_device *md,
 }
 
 static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
-				 long nr_pages, void **kaddr, pfn_t *pfn)
+		long nr_pages, enum dax_access_mode mode, void **kaddr,
+		pfn_t *pfn)
 {
 	struct mapped_device *md = dax_get_private(dax_dev);
 	sector_t sector = pgoff * PAGE_SECTORS;
@@ -1111,7 +1112,7 @@ static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
 	if (len < 1)
 		goto out;
 	nr_pages = min(len, nr_pages);
-	ret = ti->type->direct_access(ti, pgoff, nr_pages, kaddr, pfn);
+	ret = ti->type->direct_access(ti, pgoff, nr_pages, mode, kaddr, pfn);
 
  out:
 	dm_put_live_table(md, srcu_idx);
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 4aa17132a557..c77b7cf19639 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -239,24 +239,47 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
 
 /* see "strong" declaration in tools/testing/nvdimm/pmem-dax.c */
 __weak long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn)
+		long nr_pages, enum dax_access_mode mode, void **kaddr,
+		pfn_t *pfn)
 {
 	resource_size_t offset = PFN_PHYS(pgoff) + pmem->data_offset;
-
-	if (unlikely(is_bad_pmem(&pmem->bb, PFN_PHYS(pgoff) / 512,
-					PFN_PHYS(nr_pages))))
-		return -EIO;
+	sector_t sector = PFN_PHYS(pgoff) >> SECTOR_SHIFT;
+	unsigned int num = PFN_PHYS(nr_pages) >> SECTOR_SHIFT;
+	struct badblocks *bb = &pmem->bb;
+	sector_t first_bad;
+	int num_bad;
 
 	if (kaddr)
 		*kaddr = pmem->virt_addr + offset;
 	if (pfn)
 		*pfn = phys_to_pfn_t(pmem->phys_addr + offset, pmem->pfn_flags);
 
+	if (bb->count &&
+		badblocks_check(bb, sector, num, &first_bad, &num_bad)) {
+		long actual_nr;
+
+		if (mode != DAX_RECOVERY_WRITE)
+			return -EIO;
+
+		/*
+		 * Set the recovery stride is set to kernel page size because
+		 * the underlying driver and firmware clear poison functions
+		 * don't appear to handle large chunk(such as 2MiB) reliably.
+		 */
+		actual_nr = PHYS_PFN(
+			PAGE_ALIGN((first_bad - sector) << SECTOR_SHIFT));
+		dev_dbg(pmem->bb.dev, "start sector(%llu), nr_pages(%ld), first_bad(%llu), actual_nr(%ld)\n",
+				sector, nr_pages, first_bad, actual_nr);
+		if (actual_nr)
+			return actual_nr;
+		return 1;
+	}
+
 	/*
-	 * If badblocks are present, limit known good range to the
-	 * requested range.
+	 * If badblocks are present but not in the range, limit known good range
+	 * to the requested range.
 	 */
-	if (unlikely(pmem->bb.count))
+	if (bb->count)
 		return nr_pages;
 	return PHYS_PFN(pmem->size - pmem->pfn_pad - offset);
 }
@@ -278,11 +301,12 @@ static int pmem_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
 }
 
 static long pmem_dax_direct_access(struct dax_device *dax_dev,
-		pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn)
+		pgoff_t pgoff, long nr_pages, enum dax_access_mode mode,
+		void **kaddr, pfn_t *pfn)
 {
 	struct pmem_device *pmem = dax_get_private(dax_dev);
 
-	return __pmem_direct_access(pmem, pgoff, nr_pages, kaddr, pfn);
+	return __pmem_direct_access(pmem, pgoff, nr_pages, mode, kaddr, pfn);
 }
 
 static const struct dax_operations pmem_dax_ops = {
diff --git a/drivers/nvdimm/pmem.h b/drivers/nvdimm/pmem.h
index 1f51a2361429..392b0b38acb9 100644
--- a/drivers/nvdimm/pmem.h
+++ b/drivers/nvdimm/pmem.h
@@ -8,6 +8,8 @@
 #include <linux/pfn_t.h>
 #include <linux/fs.h>
 
+enum dax_access_mode;
+
 /* this definition is in it's own header for tools/testing/nvdimm to consume */
 struct pmem_device {
 	/* One contiguous memory region per device */
@@ -28,7 +30,8 @@ struct pmem_device {
 };
 
 long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn);
+		long nr_pages, enum dax_access_mode mode, void **kaddr,
+		pfn_t *pfn);
 
 #ifdef CONFIG_MEMORY_FAILURE
 static inline bool test_and_clear_pmem_poison(struct page *page)
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index d614843caf6c..8d0d0eaa3059 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -32,7 +32,8 @@ static int dcssblk_open(struct block_device *bdev, fmode_t mode);
 static void dcssblk_release(struct gendisk *disk, fmode_t mode);
 static void dcssblk_submit_bio(struct bio *bio);
 static long dcssblk_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn);
+		long nr_pages, enum dax_access_mode mode, void **kaddr,
+		pfn_t *pfn);
 
 static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0";
 
@@ -50,7 +51,8 @@ static int dcssblk_dax_zero_page_range(struct dax_device *dax_dev,
 	long rc;
 	void *kaddr;
 
-	rc = dax_direct_access(dax_dev, pgoff, nr_pages, &kaddr, NULL);
+	rc = dax_direct_access(dax_dev, pgoff, nr_pages, DAX_ACCESS,
+			&kaddr, NULL);
 	if (rc < 0)
 		return rc;
 	memset(kaddr, 0, nr_pages << PAGE_SHIFT);
@@ -927,7 +929,8 @@ __dcssblk_direct_access(struct dcssblk_dev_info *dev_info, pgoff_t pgoff,
 
 static long
 dcssblk_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn)
+		long nr_pages, enum dax_access_mode mode, void **kaddr,
+		pfn_t *pfn)
 {
 	struct dcssblk_dev_info *dev_info = dax_get_private(dax_dev);
 
diff --git a/fs/dax.c b/fs/dax.c
index 67a08a32fccb..ef3103107104 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -721,7 +721,8 @@ static int copy_cow_page_dax(struct vm_fault *vmf, const struct iomap_iter *iter
 	int id;
 
 	id = dax_read_lock();
-	rc = dax_direct_access(iter->iomap.dax_dev, pgoff, 1, &kaddr, NULL);
+	rc = dax_direct_access(iter->iomap.dax_dev, pgoff, 1, DAX_ACCESS,
+				&kaddr, NULL);
 	if (rc < 0) {
 		dax_read_unlock(id);
 		return rc;
@@ -1013,7 +1014,7 @@ static int dax_iomap_pfn(const struct iomap *iomap, loff_t pos, size_t size,
 
 	id = dax_read_lock();
 	length = dax_direct_access(iomap->dax_dev, pgoff, PHYS_PFN(size),
-				   NULL, pfnp);
+				   DAX_ACCESS, NULL, pfnp);
 	if (length < 0) {
 		rc = length;
 		goto out;
@@ -1122,7 +1123,7 @@ static int dax_memzero(struct dax_device *dax_dev, pgoff_t pgoff,
 	void *kaddr;
 	long ret;
 
-	ret = dax_direct_access(dax_dev, pgoff, 1, &kaddr, NULL);
+	ret = dax_direct_access(dax_dev, pgoff, 1, DAX_ACCESS, &kaddr, NULL);
 	if (ret > 0) {
 		memset(kaddr + offset, 0, size);
 		dax_flush(dax_dev, kaddr + offset, size);
@@ -1247,7 +1248,7 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
 		}
 
 		map_len = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size),
-				&kaddr, NULL);
+				DAX_ACCESS, &kaddr, NULL);
 		if (map_len < 0) {
 			ret = map_len;
 			break;
diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c
index d7d3a7f06862..10eb50cbf398 100644
--- a/fs/fuse/dax.c
+++ b/fs/fuse/dax.c
@@ -1241,8 +1241,8 @@ static int fuse_dax_mem_range_init(struct fuse_conn_dax *fcd)
 	INIT_DELAYED_WORK(&fcd->free_work, fuse_dax_free_mem_worker);
 
 	id = dax_read_lock();
-	nr_pages = dax_direct_access(fcd->dev, 0, PHYS_PFN(dax_size), NULL,
-				     NULL);
+	nr_pages = dax_direct_access(fcd->dev, 0, PHYS_PFN(dax_size),
+			DAX_ACCESS, NULL, NULL);
 	dax_read_unlock(id);
 	if (nr_pages < 0) {
 		pr_debug("dax_direct_access() returned %ld\n", nr_pages);
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 9fc5f99a0ae2..3f1339bce3c0 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -14,6 +14,11 @@ struct iomap_ops;
 struct iomap_iter;
 struct iomap;
 
+enum dax_access_mode {
+	DAX_ACCESS,
+	DAX_RECOVERY_WRITE,
+};
+
 struct dax_operations {
 	/*
 	 * direct_access: translate a device-relative
@@ -21,7 +26,7 @@ struct dax_operations {
 	 * number of pages available for DAX at that pfn.
 	 */
 	long (*direct_access)(struct dax_device *, pgoff_t, long,
-			void **, pfn_t *);
+			enum dax_access_mode, void **, pfn_t *);
 	/*
 	 * Validate whether this device is usable as an fsdax backing
 	 * device.
@@ -178,7 +183,7 @@ static inline void dax_read_unlock(int id)
 bool dax_alive(struct dax_device *dax_dev);
 void *dax_get_private(struct dax_device *dax_dev);
 long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
-		void **kaddr, pfn_t *pfn);
+		enum dax_access_mode mode, void **kaddr, pfn_t *pfn);
 size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 		size_t bytes, struct iov_iter *i);
 size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index c2a3758c4aaa..acdedda0d12b 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -20,6 +20,7 @@ struct dm_table;
 struct dm_report_zones_args;
 struct mapped_device;
 struct bio_vec;
+enum dax_access_mode;
 
 /*
  * Type of table, mapped_device's mempool and request_queue
@@ -146,7 +147,8 @@ typedef int (*dm_busy_fn) (struct dm_target *ti);
  * >= 0 : the number of bytes accessible at the address
  */
 typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn);
+		long nr_pages, enum dax_access_mode node, void **kaddr,
+		pfn_t *pfn);
 typedef int (*dm_dax_zero_page_range_fn)(struct dm_target *ti, pgoff_t pgoff,
 		size_t nr_pages);
 
diff --git a/tools/testing/nvdimm/pmem-dax.c b/tools/testing/nvdimm/pmem-dax.c
index af19c85558e7..dcc328eba811 100644
--- a/tools/testing/nvdimm/pmem-dax.c
+++ b/tools/testing/nvdimm/pmem-dax.c
@@ -8,7 +8,8 @@
 #include <nd.h>
 
 long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn)
+		long nr_pages, enum dax_access_mode mode, void **kaddr,
+		pfn_t *pfn)
 {
 	resource_size_t offset = PFN_PHYS(pgoff) + pmem->data_offset;
 
-- 
2.18.4

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ