[ndctl PATCH v3 4/4] Use page size as alignment value
The alignment sizes passed to ndctl in the tests are all hardcoded to 4k,
the default page size on x86. Change those to the default page size on that
architecture (sysconf/getconf). No functional changes otherwise.
Signed-off-by: Santosh Sivaraj
---
test/dpa-alloc.c| 15 ---
test/multi-dax.sh | 6 --
test/sector-mode.sh | 4 +++-
3 files changed, 15 insertions(+), 10 deletions(-)
diff --git a/test/dpa-alloc.c b/test/dpa-alloc.c
index 0b3bb7a..59185cf 100644
--- a/test/dpa-alloc.c
+++ b/test/dpa-alloc.c
@@ -38,12 +38,13 @@ static int do_test(struct ndctl_ctx *ctx, struct ndctl_test
*test)
struct ndctl_region *region, *blk_region = NULL;
struct ndctl_namespace *ndns;
struct ndctl_dimm *dimm;
- unsigned long size;
+ unsigned long size, page_size;
struct ndctl_bus *bus;
char uuid_str[40];
int round;
int rc;
+ page_size = sysconf(_SC_PAGESIZE);
/* disable nfit_test.1, not used in this test */
bus = ndctl_bus_get_by_provider(ctx, NFIT_PROVIDER1);
if (!bus)
@@ -124,11 +125,11 @@ static int do_test(struct ndctl_ctx *ctx, struct
ndctl_test *test)
return rc;
}
ndctl_namespace_disable_invalidate(ndns);
- rc = ndctl_namespace_set_size(ndns, SZ_4K);
+ rc = ndctl_namespace_set_size(ndns, page_size);
if (rc) {
- fprintf(stderr, "failed to init %s to size: %d\n",
+ fprintf(stderr, "failed to init %s to size: %lu\n",
ndctl_namespace_get_devname(ndns),
- SZ_4K);
+ page_size);
return rc;
}
namespaces[i].ndns = ndns;
@@ -150,7 +151,7 @@ static int do_test(struct ndctl_ctx *ctx, struct ndctl_test
*test)
ndns = namespaces[i % ARRAY_SIZE(namespaces)].ndns;
if (i % ARRAY_SIZE(namespaces) == 0)
round++;
- size = SZ_4K * round;
+ size = page_size * round;
rc = ndctl_namespace_set_size(ndns, size);
if (rc) {
fprintf(stderr, "%s: set_size: %lx failed: %d\n",
@@ -166,7 +167,7 @@ static int do_test(struct ndctl_ctx *ctx, struct ndctl_test
*test)
i--;
round++;
ndns = namespaces[i % ARRAY_SIZE(namespaces)].ndns;
- size = SZ_4K * round;
+ size = page_size * round;
rc = ndctl_namespace_set_size(ndns, size);
if (rc) {
fprintf(stderr, "%s failed to update while labels full\n",
@@ -175,7 +176,7 @@ static int do_test(struct ndctl_ctx *ctx, struct ndctl_test
*test)
}
round--;
- size = SZ_4K * round;
+ size = page_size * round;
rc = ndctl_namespace_set_size(ndns, size);
if (rc) {
fprintf(stderr, "%s failed to reduce size while labels full\n",
diff --git a/test/multi-dax.sh b/test/multi-dax.sh
index e932569..9451ed0 100755
--- a/test/multi-dax.sh
+++ b/test/multi-dax.sh
@@ -12,6 +12,8 @@ check_min_kver "4.13" || do_skip "may lack multi-dax support"
trap 'err $LINENO' ERR
+ALIGN_SIZE=`getconf PAGESIZE`
+
# setup (reset nfit_test dimms)
modprobe nfit_test
$NDCTL disable-region -b $NFIT_TEST_BUS0 all
@@ -22,9 +24,9 @@ rc=1
query=". | sort_by(.available_size) | reverse | .[0].dev"
region=$($NDCTL list -b $NFIT_TEST_BUS0 -t pmem -Ri | jq -r "$query")
-json=$($NDCTL create-namespace -b $NFIT_TEST_BUS0 -r $region -t pmem -m devdax
-a 4096 -s 16M)
+json=$($NDCTL create-namespace -b $NFIT_TEST_BUS0 -r $region -t pmem -m devdax
-a $ALIGN_SIZE -s 16M)
chardev1=$(echo $json | jq ". | select(.mode == \"devdax\") |
.daxregion.devices[0].chardev")
-json=$($NDCTL create-namespace -b $NFIT_TEST_BUS0 -r $region -t pmem -m devdax
-a 4096 -s 16M)
+json=$($NDCTL create-namespace -b $NFIT_TEST_BUS0 -r $region -t pmem -m devdax
-a $ALIGN_SIZE -s 16M)
chardev2=$(echo $json | jq ". | select(.mode == \"devdax\") |
.daxregion.devices[0].chardev")
_cleanup
diff --git a/test/sector-mode.sh b/test/sector-mode.sh
index dd7013e..d03c0ca 100755
--- a/test/sector-mode.sh
+++ b/test/sector-mode.sh
@@ -9,6 +9,8 @@ rc=77
set -e
trap 'err $LINENO' ERR
+ALIGN_SIZE=`getconf PAGESIZE`
+
# setup (reset nfit_test dimms)
modprobe nfit_test
$NDCTL disable-region -b $NFIT_TEST_BUS0 all
@@ -25,7 +27,7 @@ NAMESPACE=$($NDCTL list -b $NFIT_TEST_BUS1 -N | jq -r
"$query")
REGION=$($NDCTL list -R --namespace=$NAMESPACE | jq -r "(.[]) | .dev")
echo 0 > /sys/bus/nd/devices/$REGION/read_only
$NDCTL create-namespace --no-autolabel -e $NAMESPACE -m sector -f -l 4K
-$NDCTL create-namespace --no-autolabel -e $NAMESPACE -m dax -f -a 4K
+$NDCTL create-namespace --no-autolabel -e $NAMESPACE -m dax -f -a $ALIGN_SIZE
$NDCTL create-namespace --no-autolabel -e $NAMESPACE
[ndctl PATCH v3 3/4] papr: Add support to parse save_fail flag for dimm
This will help in getting the dimm fail tests to run on papr family too. Also add nvdimm_test compatibility string for recognizing the test module. Signed-off-by: Santosh Sivaraj --- ndctl/lib/libndctl.c | 5 - 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/ndctl/lib/libndctl.c b/ndctl/lib/libndctl.c index 26b9317..dd1a5fc 100644 --- a/ndctl/lib/libndctl.c +++ b/ndctl/lib/libndctl.c @@ -805,6 +805,8 @@ static void parse_papr_flags(struct ndctl_dimm *dimm, char *flags) dimm->flags.f_restore = 1; else if (strcmp(start, "smart_notify") == 0) dimm->flags.f_smart = 1; + else if (strcmp(start, "save_fail") == 0) + dimm->flags.f_save = 1; start = end + 1; } if (end != start) @@ -1035,7 +1037,8 @@ NDCTL_EXPORT int ndctl_bus_is_papr_scm(struct ndctl_bus *bus) if (sysfs_read_attr(bus->ctx, bus->bus_buf, buf) < 0) return 0; - return (strcmp(buf, "ibm,pmemory") == 0); + return (strcmp(buf, "ibm,pmemory") == 0 || + strcmp(buf, "nvdimm_test") == 0); } /** -- 2.29.2 ___ Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org To unsubscribe send an email to linux-nvdimm-le...@lists.01.org
[ndctl PATCH v3 2/4] test: Don't skip tests if nfit modules are missing
For NFIT to be available ACPI is a must, so don't fail when nfit modules
are missing on a platform that doesn't support ACPI.
Signed-off-by: Santosh Sivaraj
---
test.h| 2 +-
test/ack-shutdown-count-set.c | 2 +-
test/blk_namespaces.c | 2 +-
test/core.c | 23 +--
test/dpa-alloc.c | 2 +-
test/dsm-fail.c | 2 +-
test/libndctl.c | 2 +-
test/multi-pmem.c | 2 +-
test/parent-uuid.c| 2 +-
test/pmem_namespaces.c| 2 +-
10 files changed, 30 insertions(+), 11 deletions(-)
diff --git a/test.h b/test.h
index cba8d41..7de13fe 100644
--- a/test.h
+++ b/test.h
@@ -20,7 +20,7 @@ void builtin_xaction_namespace_reset(void);
struct kmod_ctx;
struct kmod_module;
-int nfit_test_init(struct kmod_ctx **ctx, struct kmod_module **mod,
+int ndctl_test_init(struct kmod_ctx **ctx, struct kmod_module **mod,
struct ndctl_ctx *nd_ctx, int log_level,
struct ndctl_test *test);
diff --git a/test/ack-shutdown-count-set.c b/test/ack-shutdown-count-set.c
index fb1d82b..c561ff3 100644
--- a/test/ack-shutdown-count-set.c
+++ b/test/ack-shutdown-count-set.c
@@ -99,7 +99,7 @@ static int test_ack_shutdown_count_set(int loglevel, struct
ndctl_test *test,
int result = EXIT_FAILURE, err;
ndctl_set_log_priority(ctx, loglevel);
- err = nfit_test_init(_ctx, , NULL, loglevel, test);
+ err = ndctl_test_init(_ctx, , NULL, loglevel, test);
if (err < 0) {
result = 77;
ndctl_test_skip(test);
diff --git a/test/blk_namespaces.c b/test/blk_namespaces.c
index d7f00cb..f076e85 100644
--- a/test/blk_namespaces.c
+++ b/test/blk_namespaces.c
@@ -228,7 +228,7 @@ int test_blk_namespaces(int log_level, struct ndctl_test
*test,
if (!bus) {
fprintf(stderr, "ACPI.NFIT unavailable falling back to
nfit_test\n");
- rc = nfit_test_init(_ctx, , NULL, log_level, test);
+ rc = ndctl_test_init(_ctx, , NULL, log_level, test);
ndctl_invalidate(ctx);
bus = ndctl_bus_get_by_provider(ctx, "nfit_test.0");
if (rc < 0 || !bus) {
diff --git a/test/core.c b/test/core.c
index cc7d8d9..903034a 100644
--- a/test/core.c
+++ b/test/core.c
@@ -11,6 +11,7 @@
#include
#include
#include
+#include
#include
#define KVER_STRLEN 20
@@ -106,11 +107,11 @@ int ndctl_test_get_skipped(struct ndctl_test *test)
return test->skip;
}
-int nfit_test_init(struct kmod_ctx **ctx, struct kmod_module **mod,
+int ndctl_test_init(struct kmod_ctx **ctx, struct kmod_module **mod,
struct ndctl_ctx *nd_ctx, int log_level,
struct ndctl_test *test)
{
- int rc;
+ int rc, family = NVDIMM_FAMILY_INTEL;
unsigned int i;
const char *name;
struct ndctl_bus *bus;
@@ -127,6 +128,19 @@ int nfit_test_init(struct kmod_ctx **ctx, struct
kmod_module **mod,
"nd_e820",
"nd_pmem",
};
+ char *test_env;
+
+ /* Do we want to force test PAPR? */
+ test_env = getenv("NDCTL_TEST_FAMILY");
+ if (test_env && strcmp(test_env, "PAPR") == 0)
+ family = NVDIMM_FAMILY_PAPR;
+
+ /* ACPI is a must for nfit, so if ACPI is not available let's default to
+* PAPR */
+ if (access("/sys/bus/acpi", F_OK) == -1) {
+ if (errno == ENOENT)
+ family = NVDIMM_FAMILY_PAPR;
+ }
log_init(_ctx, "test/init", "NDCTL_TEST");
log_ctx.log_priority = log_level;
@@ -185,6 +199,11 @@ retry:
path = kmod_module_get_path(*mod);
if (!path) {
+ if (family == NVDIMM_FAMILY_PAPR &&
+ (strcmp(name, "nfit") == 0 ||
+strcmp(name, "nd_e820") == 0))
+ continue;
+
log_err(_ctx, "%s.ko: failed to get path\n", name);
break;
}
diff --git a/test/dpa-alloc.c b/test/dpa-alloc.c
index e922009..0b3bb7a 100644
--- a/test/dpa-alloc.c
+++ b/test/dpa-alloc.c
@@ -289,7 +289,7 @@ int test_dpa_alloc(int loglevel, struct ndctl_test *test,
struct ndctl_ctx *ctx)
return 77;
ndctl_set_log_priority(ctx, loglevel);
- err = nfit_test_init(_ctx, , NULL, loglevel, test);
+ err = ndctl_test_init(_ctx, , NULL, loglevel, test);
if (err < 0) {
ndctl_test_skip(test);
fprintf(stderr, "nfit_test unavailable skipping tests\n");
diff --git a/test/dsm-fail.c b/test/dsm-fail.c
index 9dfd8b0..0a6383d 100644
--- a/test/dsm-fail.c
+++ b/test/dsm-fail.c
@@ -346,7 +346,7 @@ int test_dsm_fail(int loglevel, struct ndctl_test *test,
struct ndctl_ctx *ctx)
int result = EXIT_FAILURE, err;
ndctl_set_log_priority(ctx, loglevel);
-
[ndctl PATCH v3 1/4] libndctl: test enablement for non-nfit devices
Unify adding dimms for papr and nfit families, this will help in adding
all attributes needed for the unit tests too. We don't fail adding a dimm
if some of the dimm attributes are missing, so this will work fine on PAPR
platforms where most dimm attributes are provided.
Signed-off-by: Santosh Sivaraj
---
ndctl/lib/libndctl.c | 103 ---
1 file changed, 38 insertions(+), 65 deletions(-)
v3:
* Drop patch which skips SMART tests, smart test enablement will be posted
soon.
v2:
* Patch 2: Fix a bug, I skip erroring out if PAPR family, but condition had
INTEL family instead. That change was there to test the same code on x86, but
accidently committed. Now have a environment variable to force test PAPR
family on x86.
* Patch 4: Remove stray code, artifact of refactoring in patch 1.
diff --git a/ndctl/lib/libndctl.c b/ndctl/lib/libndctl.c
index 36fb6fe..26b9317 100644
--- a/ndctl/lib/libndctl.c
+++ b/ndctl/lib/libndctl.c
@@ -1646,41 +1646,9 @@ static int ndctl_bind(struct ndctl_ctx *ctx, struct
kmod_module *module,
static int ndctl_unbind(struct ndctl_ctx *ctx, const char *devpath);
static struct kmod_module *to_module(struct ndctl_ctx *ctx, const char *alias);
-static int add_papr_dimm(struct ndctl_dimm *dimm, const char *dimm_base)
-{
- int rc = -ENODEV;
- char buf[SYSFS_ATTR_SIZE];
- struct ndctl_ctx *ctx = dimm->bus->ctx;
- char *path = calloc(1, strlen(dimm_base) + 100);
- const char * const devname = ndctl_dimm_get_devname(dimm);
-
- dbg(ctx, "%s: Probing of_pmem dimm at %s\n", devname, dimm_base);
-
- if (!path)
- return -ENOMEM;
-
- /* construct path to the papr compatible dimm flags file */
- sprintf(path, "%s/papr/flags", dimm_base);
-
- if (ndctl_bus_is_papr_scm(dimm->bus) &&
- sysfs_read_attr(ctx, path, buf) == 0) {
-
- dbg(ctx, "%s: Adding papr-scm dimm flags:\"%s\"\n", devname,
buf);
- dimm->cmd_family = NVDIMM_FAMILY_PAPR;
-
- /* Parse dimm flags */
- parse_papr_flags(dimm, buf);
-
- /* Allocate monitor mode fd */
- dimm->health_eventfd = open(path, O_RDONLY|O_CLOEXEC);
- rc = 0;
- }
-
- free(path);
- return rc;
-}
-
-static int add_nfit_dimm(struct ndctl_dimm *dimm, const char *dimm_base)
+static int populate_dimm_attributes(struct ndctl_dimm *dimm,
+ const char *dimm_base,
+ const char *bus_prefix)
{
int i, rc = -1;
char buf[SYSFS_ATTR_SIZE];
@@ -1694,7 +1662,7 @@ static int add_nfit_dimm(struct ndctl_dimm *dimm, const
char *dimm_base)
* 'unique_id' may not be available on older kernels, so don't
* fail if the read fails.
*/
- sprintf(path, "%s/nfit/id", dimm_base);
+ sprintf(path, "%s/%s/id", dimm_base, bus_prefix);
if (sysfs_read_attr(ctx, path, buf) == 0) {
unsigned int b[9];
@@ -1709,68 +1677,74 @@ static int add_nfit_dimm(struct ndctl_dimm *dimm, const
char *dimm_base)
}
}
- sprintf(path, "%s/nfit/handle", dimm_base);
+ sprintf(path, "%s/%s/handle", dimm_base, bus_prefix);
if (sysfs_read_attr(ctx, path, buf) < 0)
goto err_read;
dimm->handle = strtoul(buf, NULL, 0);
- sprintf(path, "%s/nfit/phys_id", dimm_base);
+ sprintf(path, "%s/%s/phys_id", dimm_base, bus_prefix);
if (sysfs_read_attr(ctx, path, buf) < 0)
goto err_read;
dimm->phys_id = strtoul(buf, NULL, 0);
- sprintf(path, "%s/nfit/serial", dimm_base);
+ sprintf(path, "%s/%s/serial", dimm_base, bus_prefix);
if (sysfs_read_attr(ctx, path, buf) == 0)
dimm->serial = strtoul(buf, NULL, 0);
- sprintf(path, "%s/nfit/vendor", dimm_base);
+ sprintf(path, "%s/%s/vendor", dimm_base, bus_prefix);
if (sysfs_read_attr(ctx, path, buf) == 0)
dimm->vendor_id = strtoul(buf, NULL, 0);
- sprintf(path, "%s/nfit/device", dimm_base);
+ sprintf(path, "%s/%s/device", dimm_base, bus_prefix);
if (sysfs_read_attr(ctx, path, buf) == 0)
dimm->device_id = strtoul(buf, NULL, 0);
- sprintf(path, "%s/nfit/rev_id", dimm_base);
+ sprintf(path, "%s/%s/rev_id", dimm_base, bus_prefix);
if (sysfs_read_attr(ctx, path, buf) == 0)
dimm->revision_id = strtoul(buf, NULL, 0);
- sprintf(path, "%s/nfit/dirty_shutdown", dimm_base);
+ sprintf(path, "%s/%s/dirty_shutdown", dimm_base, bus_prefix);
if (sysfs_read_attr(ctx, path, buf) == 0)
dimm->dirty_shutdown = strtoll(buf, NULL, 0);
- sprintf(path, "%s/nfit/subsystem_vendor", dimm_base);
+ sprintf(path, "%s/%s/subsystem_vendor", dimm_base, bus_prefix);
if (sysfs_read_attr(ctx, path, buf) == 0)
Re: [PATCH v2 00/10] fsdax,xfs: Add reflink support for fsdax
On Wed, Mar 10, 2021 at 6:27 AM Matthew Wilcox wrote: > > On Wed, Mar 10, 2021 at 08:21:59AM -0600, Goldwyn Rodrigues wrote: > > On 13:02 10/03, Matthew Wilcox wrote: > > > On Wed, Mar 10, 2021 at 07:30:41AM -0500, Neal Gompa wrote: > > > > Forgive my ignorance, but is there a reason why this isn't wired up to > > > > Btrfs at the same time? It seems weird to me that adding a feature > > > > > > btrfs doesn't support DAX. only ext2, ext4, XFS and FUSE have DAX > > > support. > > > > > > If you think about it, btrfs and DAX are diametrically opposite things. > > > DAX is about giving raw access to the hardware. btrfs is about offering > > > extra value (RAID, checksums, ...), none of which can be done if the > > > filesystem isn't in the read/write path. > > > > > > That's why there's no DAX support in btrfs. If you want DAX, you have > > > to give up all the features you like in btrfs. So you may as well use > > > a different filesystem. > > > > DAX on btrfs has been attempted[1]. Of course, we could not > > But why? A completeness fetish? I don't understand why you decided > to do this work. Isn't DAX useful for pagecache minimization on read even if it is awkward for a copy-on-write fs? Seems it would be a useful case to have COW'd VM images on BTRFS that don't need superfluous page cache allocations. ___ Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org To unsubscribe send an email to linux-nvdimm-le...@lists.01.org
Re: [PATCH v2] libnvdimm: Notify disk drivers to revalidate region read-only
On Tue, Mar 9, 2021 at 10:54 PM Christoph Hellwig wrote: > > Looks good to me: > > Reviewed-by: Christoph Hellwig > > Question on the pre-existing code: given that nvdimm_check_and_set_ro is > the only caller of set_disk_ro for nvdimm devices, we'll also get > the message when initially setting up any read-only disk. Is that > intentional? Yeah, that's intentional. There's no other notification that userspace would be looking for by default besides the kernel log, and the block device name is more meaningful than the region name, or the nvdimm device status for that matter. ___ Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org To unsubscribe send an email to linux-nvdimm-le...@lists.01.org
Re: [PATCH v2] include: Remove pagemap.h from blkdev.h
Nice cleanup, IMHO. Reviewed-by: William Kucharski > On Mar 9, 2021, at 12:57 PM, Matthew Wilcox (Oracle) > wrote: > > My UEK-derived config has 1030 files depending on pagemap.h before > this change. Afterwards, just 326 files need to be rebuilt when I > touch pagemap.h. I think blkdev.h is probably included too widely, > but untangling that dependency is harder and this solves my problem. > x86 allmodconfig builds, but there may be implicit include problems > on other architectures. > > Signed-off-by: Matthew Wilcox (Oracle) > --- > v2: Fix CONFIG_SWAP=n implicit use of pagemap.h by swap.h. Increases >the number of files from 240, but that's still a big win -- 68% >reduction instead of 77%. > > block/blk-settings.c | 1 + > drivers/block/brd.c | 1 + > drivers/block/loop.c | 1 + > drivers/md/bcache/super.c | 1 + > drivers/nvdimm/btt.c | 1 + > drivers/nvdimm/pmem.c | 1 + > drivers/scsi/scsicam.c| 1 + > include/linux/blkdev.h| 1 - > include/linux/swap.h | 1 + > 9 files changed, 8 insertions(+), 1 deletion(-) > > diff --git a/block/blk-settings.c b/block/blk-settings.c > index b4aa2f37fab6..976085a44fb8 100644 > --- a/block/blk-settings.c > +++ b/block/blk-settings.c > @@ -7,6 +7,7 @@ > #include > #include > #include > +#include > #include/* for max_pfn/max_low_pfn */ > #include > #include > diff --git a/drivers/block/brd.c b/drivers/block/brd.c > index 18bf99906662..2a5a1933826b 100644 > --- a/drivers/block/brd.c > +++ b/drivers/block/brd.c > @@ -18,6 +18,7 @@ > #include > #include > #include > +#include > #include > #include > #include > diff --git a/drivers/block/loop.c b/drivers/block/loop.c > index a370cde3ddd4..d58d68f3c7cd 100644 > --- a/drivers/block/loop.c > +++ b/drivers/block/loop.c > @@ -53,6 +53,7 @@ > #include > #include > #include > +#include > #include > #include > #include > diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c > index 71691f32959b..f154c89d1326 100644 > --- a/drivers/md/bcache/super.c > +++ b/drivers/md/bcache/super.c > @@ -16,6 +16,7 @@ > #include "features.h" > > #include > +#include > #include > #include > #include > diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c > index 41aa1f01fc07..18a267d5073f 100644 > --- a/drivers/nvdimm/btt.c > +++ b/drivers/nvdimm/btt.c > @@ -6,6 +6,7 @@ > #include > #include > #include > +#include > #include > #include > #include > diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c > index b8a85bfb2e95..16760b237229 100644 > --- a/drivers/nvdimm/pmem.c > +++ b/drivers/nvdimm/pmem.c > @@ -8,6 +8,7 @@ > */ > > #include > +#include > #include > #include > #include > diff --git a/drivers/scsi/scsicam.c b/drivers/scsi/scsicam.c > index f1553a453616..0ffdb8f2995f 100644 > --- a/drivers/scsi/scsicam.c > +++ b/drivers/scsi/scsicam.c > @@ -17,6 +17,7 @@ > #include > #include > #include > +#include > #include > #include > > diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h > index c032cfe133c7..1e2a95599390 100644 > --- a/include/linux/blkdev.h > +++ b/include/linux/blkdev.h > @@ -11,7 +11,6 @@ > #include > #include > #include > -#include > #include > #include > #include > diff --git a/include/linux/swap.h b/include/linux/swap.h > index 4cc6ec3bf0ab..ae194bb7ddb4 100644 > --- a/include/linux/swap.h > +++ b/include/linux/swap.h > @@ -10,6 +10,7 @@ > #include > #include > #include > +#include > #include > #include > #include > -- > 2.30.0 > > ___ Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org To unsubscribe send an email to linux-nvdimm-le...@lists.01.org
AW:AW:AW: INVOICE
___ Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org To unsubscribe send an email to linux-nvdimm-le...@lists.01.org
Re: [PATCH RFC 1/9] memremap: add ZONE_DEVICE support for compound pages
On 2/22/21 8:37 PM, Dan Williams wrote: > On Mon, Feb 22, 2021 at 3:24 AM Joao Martins > wrote: >> On 2/20/21 1:43 AM, Dan Williams wrote: >>> On Tue, Dec 8, 2020 at 9:59 PM John Hubbard wrote: On 12/8/20 9:28 AM, Joao Martins wrote: >> One thing to point out about altmap is that the degradation (in pinning and >> unpining) we observed with struct page's in device memory, is no longer >> observed >> once 1) we batch ref count updates as we move to compound pages 2) reusing >> tail pages seems to lead to these struct pages staying more likely in cache >> which perhaps contributes to dirtying a lot less cachelines. > > True, it makes it more palatable to survive 'struct page' in PMEM, I want to retract for now what I said above wrt to the no degradation with struct page in device comment. I was fooled by a bug on a patch later down this series. Particular because I accidentally cleared PGMAP_ALTMAP_VALID when unilaterally setting PGMAP_COMPOUND, which consequently lead to always allocating struct pages from memory. No wonder the numbers were just as fast. I am still confident that it's going to be faster and observe less degradation in pinning/init. Init for now is worst-case 2x faster. But to be *as fast* struct pages in memory might still be early to say. The broken masking of the PGMAP_ALTMAP_VALID bit did hide one flaw, where we don't support altmap for basepages on x86/mm and it apparently depends on architectures to implement it (and a couple other issues). The vmemmap allocation isn't the problem, so the previous comment in this thread that altmap doesn't change much in the vmemmap_populate_compound_pages() is still accurate. The problem though resides on the freeing of vmemmap pagetables with basepages *with altmap* (e.g. at dax-device teardown) which require arch support. Doing it properly would mean making the altmap reserve smaller (given fewer pages are allocated), and the ability for the altmap pfn allocator to track references per pfn. But I think it deserves its own separate patch series (probably almost just as big). Perhaps for this set I can stick without altmap as you suggested, and use hugepage vmemmap population (which wouldn't lead to device memory savings) instead of reusing base pages . I would still leave the compound page support logic as metadata representation for > 4K @align, as I think that's the right thing to do. And then a separate series onto improving altmap to leverage the metadata reduction support as done with non-device struct pages. Thoughts? Joao ___ Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org To unsubscribe send an email to linux-nvdimm-le...@lists.01.org
Re: [PATCH v2 00/10] fsdax,xfs: Add reflink support for fsdax
On 14:26 10/03, Matthew Wilcox wrote: > On Wed, Mar 10, 2021 at 08:21:59AM -0600, Goldwyn Rodrigues wrote: > > On 13:02 10/03, Matthew Wilcox wrote: > > > On Wed, Mar 10, 2021 at 07:30:41AM -0500, Neal Gompa wrote: > > > > Forgive my ignorance, but is there a reason why this isn't wired up to > > > > Btrfs at the same time? It seems weird to me that adding a feature > > > > > > btrfs doesn't support DAX. only ext2, ext4, XFS and FUSE have DAX > > > support. > > > > > > If you think about it, btrfs and DAX are diametrically opposite things. > > > DAX is about giving raw access to the hardware. btrfs is about offering > > > extra value (RAID, checksums, ...), none of which can be done if the > > > filesystem isn't in the read/write path. > > > > > > That's why there's no DAX support in btrfs. If you want DAX, you have > > > to give up all the features you like in btrfs. So you may as well use > > > a different filesystem. > > > > DAX on btrfs has been attempted[1]. Of course, we could not > > But why? A completeness fetish? I don't understand why you decided > to do this work. If only I had a penny every time I heard "why would you want to do that?" > > > have checksums or multi-device with it. However, got stuck on > > associating a shared extent on the same page mapping: basically the > > TODO above dax_associate_entry(). > > > > Shiyang has proposed a way to disassociate existing mapping, but I > > don't think that is the best solution. DAX for CoW will not work until > > we have a way of mapping a page to multiple inodes (page->mapping), > > which will convert a 1-N inode-page mapping to M-N inode-page mapping. > > If you're still thinking in terms of pages, you're doing DAX wrong. > DAX should work without a struct page. Not pages specifically, but mappings. fsdax needs the mappings during the page fault and it breaks in case both files fault on the same shared extent. For Reference: WARN_ON_ONCE(page->mapping && page->mapping != mapping) in dax_disassociate_entry(). -- Goldwyn ___ Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org To unsubscribe send an email to linux-nvdimm-le...@lists.01.org
New Invoice(s) for C386790910 are Available to be Viewed
Your new Invoice(s) are available to be viewed.The Attachments include the following Invoice(s): Invoice Number CHR Load Number 6207666375386790910 Thank you for your business, if there are any issues with your Invoice(s) please contact your Sales Rep *This email and any files transmitted with it are confidential and intended solely for the use of the individual or entity to whom they are addressed. If you are not the named addressee you should not disseminate, distribute or copy this e-mail. Please notify the sender immediately by e-mail if you have received this e-mail by mistake and delete this e-mail from your system. Please note that any views or opinions presented in this email are solely those of the author and do not necessarily represent those of the sender of the e-mail. The sender of the e-mail accepts no liability for any damage caused by any virus transmitted by this email. (IP)* ___ Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org To unsubscribe send an email to linux-nvdimm-le...@lists.01.org
Re: [PATCH v2] include: Remove pagemap.h from blkdev.h
Matthew, > My UEK-derived config has 1030 files depending on pagemap.h before > this change. Afterwards, just 326 files need to be rebuilt when I > touch pagemap.h. I think blkdev.h is probably included too widely, > but untangling that dependency is harder and this solves my problem. > x86 allmodconfig builds, but there may be implicit include problems on > other architectures. SCSI portion looks fine. Acked-by: Martin K. Petersen -- Martin K. Petersen Oracle Linux Engineering ___ Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org To unsubscribe send an email to linux-nvdimm-le...@lists.01.org
Re: [PATCH v2 00/10] fsdax,xfs: Add reflink support for fsdax
On Wed, Mar 10, 2021 at 08:21:59AM -0600, Goldwyn Rodrigues wrote: > On 13:02 10/03, Matthew Wilcox wrote: > > On Wed, Mar 10, 2021 at 07:30:41AM -0500, Neal Gompa wrote: > > > Forgive my ignorance, but is there a reason why this isn't wired up to > > > Btrfs at the same time? It seems weird to me that adding a feature > > > > btrfs doesn't support DAX. only ext2, ext4, XFS and FUSE have DAX support. > > > > If you think about it, btrfs and DAX are diametrically opposite things. > > DAX is about giving raw access to the hardware. btrfs is about offering > > extra value (RAID, checksums, ...), none of which can be done if the > > filesystem isn't in the read/write path. > > > > That's why there's no DAX support in btrfs. If you want DAX, you have > > to give up all the features you like in btrfs. So you may as well use > > a different filesystem. > > DAX on btrfs has been attempted[1]. Of course, we could not But why? A completeness fetish? I don't understand why you decided to do this work. > have checksums or multi-device with it. However, got stuck on > associating a shared extent on the same page mapping: basically the > TODO above dax_associate_entry(). > > Shiyang has proposed a way to disassociate existing mapping, but I > don't think that is the best solution. DAX for CoW will not work until > we have a way of mapping a page to multiple inodes (page->mapping), > which will convert a 1-N inode-page mapping to M-N inode-page mapping. If you're still thinking in terms of pages, you're doing DAX wrong. DAX should work without a struct page. ___ Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org To unsubscribe send an email to linux-nvdimm-le...@lists.01.org
Re: [PATCH v2 00/10] fsdax,xfs: Add reflink support for fsdax
On 13:02 10/03, Matthew Wilcox wrote: > On Wed, Mar 10, 2021 at 07:30:41AM -0500, Neal Gompa wrote: > > Forgive my ignorance, but is there a reason why this isn't wired up to > > Btrfs at the same time? It seems weird to me that adding a feature > > btrfs doesn't support DAX. only ext2, ext4, XFS and FUSE have DAX support. > > If you think about it, btrfs and DAX are diametrically opposite things. > DAX is about giving raw access to the hardware. btrfs is about offering > extra value (RAID, checksums, ...), none of which can be done if the > filesystem isn't in the read/write path. > > That's why there's no DAX support in btrfs. If you want DAX, you have > to give up all the features you like in btrfs. So you may as well use > a different filesystem. DAX on btrfs has been attempted[1]. Of course, we could not have checksums or multi-device with it. However, got stuck on associating a shared extent on the same page mapping: basically the TODO above dax_associate_entry(). Shiyang has proposed a way to disassociate existing mapping, but I don't think that is the best solution. DAX for CoW will not work until we have a way of mapping a page to multiple inodes (page->mapping), which will convert a 1-N inode-page mapping to M-N inode-page mapping. [1] https://lore.kernel.org/linux-btrfs/20190429172649.8288-1-rgold...@suse.de/ -- Goldwyn ___ Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org To unsubscribe send an email to linux-nvdimm-le...@lists.01.org
Re: [PATCH v2 00/10] fsdax,xfs: Add reflink support for fsdax
On Wed, Mar 10, 2021 at 08:36:06AM -0500, Neal Gompa wrote: > On Wed, Mar 10, 2021 at 8:02 AM Matthew Wilcox wrote: > > > > On Wed, Mar 10, 2021 at 07:30:41AM -0500, Neal Gompa wrote: > > > Forgive my ignorance, but is there a reason why this isn't wired up to > > > Btrfs at the same time? It seems weird to me that adding a feature > > > > btrfs doesn't support DAX. only ext2, ext4, XFS and FUSE have DAX support. > > > > If you think about it, btrfs and DAX are diametrically opposite things. > > DAX is about giving raw access to the hardware. btrfs is about offering > > extra value (RAID, checksums, ...), none of which can be done if the > > filesystem isn't in the read/write path. > > > > That's why there's no DAX support in btrfs. If you want DAX, you have > > to give up all the features you like in btrfs. So you may as well use > > a different filesystem. > > So does that mean that DAX is incompatible with those filesystems when > layered on DM (e.g. through LVM)? Yes. It might be possible to work through RAID-0 or read-only through RAID-1, but I'm not sure anybody's bothered to do that work. > Also, based on what you're saying, that means that DAX'd resources > would not be able to use reflinks on XFS, right? That'd put it in > similar territory as swap files on Btrfs, I would think. You can use DAX with reflinks because the CPU can do read-only mmaps. On a write fault, we break the reflink, copy the data and put in a writable PTE. ___ Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org To unsubscribe send an email to linux-nvdimm-le...@lists.01.org
Re: [PATCH v2 00/10] fsdax,xfs: Add reflink support for fsdax
On Wed, Mar 10, 2021 at 8:02 AM Matthew Wilcox wrote: > > On Wed, Mar 10, 2021 at 07:30:41AM -0500, Neal Gompa wrote: > > Forgive my ignorance, but is there a reason why this isn't wired up to > > Btrfs at the same time? It seems weird to me that adding a feature > > btrfs doesn't support DAX. only ext2, ext4, XFS and FUSE have DAX support. > > If you think about it, btrfs and DAX are diametrically opposite things. > DAX is about giving raw access to the hardware. btrfs is about offering > extra value (RAID, checksums, ...), none of which can be done if the > filesystem isn't in the read/write path. > > That's why there's no DAX support in btrfs. If you want DAX, you have > to give up all the features you like in btrfs. So you may as well use > a different filesystem. So does that mean that DAX is incompatible with those filesystems when layered on DM (e.g. through LVM)? Also, based on what you're saying, that means that DAX'd resources would not be able to use reflinks on XFS, right? That'd put it in similar territory as swap files on Btrfs, I would think. -- 真実はいつも一つ！/ Always, there's only one truth! ___ Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org To unsubscribe send an email to linux-nvdimm-le...@lists.01.org
Re: [PATCH v2 00/10] fsdax,xfs: Add reflink support for fsdax
On Wed, Mar 10, 2021 at 07:30:41AM -0500, Neal Gompa wrote: > Forgive my ignorance, but is there a reason why this isn't wired up to > Btrfs at the same time? It seems weird to me that adding a feature btrfs doesn't support DAX. only ext2, ext4, XFS and FUSE have DAX support. If you think about it, btrfs and DAX are diametrically opposite things. DAX is about giving raw access to the hardware. btrfs is about offering extra value (RAID, checksums, ...), none of which can be done if the filesystem isn't in the read/write path. That's why there's no DAX support in btrfs. If you want DAX, you have to give up all the features you like in btrfs. So you may as well use a different filesystem. ___ Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org To unsubscribe send an email to linux-nvdimm-le...@lists.01.org
Re: [PATCH v2 00/10] fsdax,xfs: Add reflink support for fsdax
On Thu, Feb 25, 2021 at 7:23 PM Shiyang Ruan wrote: > > This patchset is attempt to add CoW support for fsdax, and take XFS, > which has both reflink and fsdax feature, as an example. > > Changes from V1: > - Factor some helper functions to simplify dax fault code > - Introduce iomap_apply2() for dax_dedupe_file_range_compare() > - Fix mistakes and other problems > - Rebased on v5.11 > > One of the key mechanism need to be implemented in fsdax is CoW. Copy > the data from srcmap before we actually write data to the destance > iomap. And we just copy range in which data won't be changed. > > Another mechanism is range comparison. In page cache case, readpage() > is used to load data on disk to page cache in order to be able to > compare data. In fsdax case, readpage() does not work. So, we need > another compare data with direct access support. > > With the two mechanism implemented in fsdax, we are able to make reflink > and fsdax work together in XFS. > > > Some of the patches are picked up from Goldwyn's patchset. I made some > changes to adapt to this patchset. > > (Rebased on v5.11) Forgive my ignorance, but is there a reason why this isn't wired up to Btrfs at the same time? It seems weird to me that adding a feature like DAX to work with CoW filesystems is not being wired into *the* CoW filesystem in the Linux kernel that fully takes advantage of copy-on-write. I'm aware that XFS supports reflinks and does some datacow stuff, but I don't know if I would consider XFS integration sufficient for integrating this feature now, especially if it's possible that the design might not work with Btrfs (I hadn't seen any feedback from Btrfs developers, though given how much email there is here, it's entirely possible that I missed it). -- 真実はいつも一つ！/ Always, there's only one truth! ___ Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org To unsubscribe send an email to linux-nvdimm-le...@lists.01.org
Re: [PATCH] include: Remove pagemap.h from blkdev.h
On Tue, Mar 9, 2021 at 7:15 PM Matthew Wilcox (Oracle) wrote: > > My UEK-derived config has 1030 files depending on pagemap.h before > this change. Afterwards, just 240 files need to be rebuilt when I > touch pagemap.h. I think blkdev.h is probably included too widely, > but untangling that dependency is harder and this solves my problem. > x86 allmodconfig builds, but there may be implicit include problems > on other architectures. > > Signed-off-by: Matthew Wilcox (Oracle) Good catch! With the build regression fixed (I suppose you now need to include pagemap.h in swap.h): Acked-by: Arnd Bergmann ___ Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org To unsubscribe send an email to linux-nvdimm-le...@lists.01.org
Re: [PATCH v2] include: Remove pagemap.h from blkdev.h
On 3/10/21 3:57 AM, Matthew Wilcox (Oracle) wrote: > My UEK-derived config has 1030 files depending on pagemap.h before > this change. Afterwards, just 326 files need to be rebuilt when I > touch pagemap.h. I think blkdev.h is probably included too widely, > but untangling that dependency is harder and this solves my problem. > x86 allmodconfig builds, but there may be implicit include problems > on other architectures. > > Signed-off-by: Matthew Wilcox (Oracle) > --- > v2: Fix CONFIG_SWAP=n implicit use of pagemap.h by swap.h. Increases > the number of files from 240, but that's still a big win -- 68% > reduction instead of 77%. > > block/blk-settings.c | 1 + > drivers/block/brd.c | 1 + > drivers/block/loop.c | 1 + > drivers/md/bcache/super.c | 1 + > drivers/nvdimm/btt.c | 1 + > drivers/nvdimm/pmem.c | 1 + > drivers/scsi/scsicam.c| 1 + > include/linux/blkdev.h| 1 - > include/linux/swap.h | 1 + > 9 files changed, 8 insertions(+), 1 deletion(-) > [snipped] > diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c > index 71691f32959b..f154c89d1326 100644 > --- a/drivers/md/bcache/super.c > +++ b/drivers/md/bcache/super.c > @@ -16,6 +16,7 @@ > #include "features.h" > > #include > +#include > #include > #include > #include [snipped] For bcache part, Acked-by: Coly Li Thanks. Coly Li ___ Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org To unsubscribe send an email to linux-nvdimm-le...@lists.01.org
Re: [PATCH v2] libnvdimm: Notify disk drivers to revalidate region read-only
On Tue, 2021-03-09 at 17:43 -0800, Dan Williams wrote:
> Previous kernels allowed the BLKROSET to override the disk's read-only
> status. With that situation fixed the pmem driver needs to rely on
> notification events to reevaluate the disk read-only status after the
> host region has been marked read-write.
>
> Recall that when libnvdimm determines that the persistent memory has
> lost persistence (for example lack of energy to flush from DRAM to FLASH
> on an NVDIMM-N device) it marks the region read-only, but that state can
> be overridden by the user via:
>
> echo 0 > /sys/bus/nd/devices/regionX/read_only
>
> ...to date there is no notification that the region has restored
> persistence, so the user override is the only recovery.
>
> Fixes: 52f019d43c22 ("block: add a hard-readonly flag to struct gendisk")
> Cc: Christoph Hellwig
> Cc: Ming Lei
> Cc: Martin K. Petersen
> Cc: Hannes Reinecke
> Cc: Jens Axboe
> Reported-by: kernel test robot
> Reported-by: Vishal Verma
> Signed-off-by: Dan Williams
> ---
> Changes since v1 [1]:
> - Move from the sinking ship of revalidate_disk() to the local hotness
> of nd_pmem_notify() (hch).
>
> [1]:
> http://lore.kernel.org/r/161527286194.446794.5215036039655765042.st...@dwillia2-desk3.amr.corp.intel.com
>
> drivers/nvdimm/bus.c | 14 ++
> drivers/nvdimm/pmem.c| 37 +
> drivers/nvdimm/region_devs.c |7 +++
> include/linux/nd.h |1 +
> 4 files changed, 47 insertions(+), 12 deletions(-)
With the update to the unit test applied, and this, everything passes
for me. You can add:
Tested-by: Vishal Verma
___
Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org
To unsubscribe send an email to linux-nvdimm-le...@lists.01.org
Re: [ndctl PATCH 1/2] configure: add checking jq command
On Tue, 2021-03-02 at 02:25 +0900, QI Fuli wrote: > Add checking jq command since it is needed to validate tests > > Cc: Santosh Sivaraj > Signed-off-by: QI Fuli > Link: https://github.com/pmem/ndctl/issues/141 > --- > configure.ac | 6 ++ > 1 file changed, 6 insertions(+) Hm, I think I prefer how you did it in v1. i.e. no configure.ac check. In my view, configure.ac tests are for the core things needed to /run/ ndctl on a system. Development unit tests can just continue to use check_prereq as you did. So I'll pick up v1 of this for now - if you want me to do something else please let me know! > > diff --git a/configure.ac b/configure.ac > index 5ec8d2f..839836b 100644 > --- a/configure.ac > +++ b/configure.ac > @@ -65,6 +65,12 @@ fi > AC_SUBST([XMLTO]) > fi > > +AC_CHECK_PROG(JQ, [jq], [$(which jq)], [missing]) > +if test "x$JQ" = xmissing; then > + AC_MSG_ERROR([jq command needed to validate tests]) > +fi > +AC_SUBST([JQ]) > + > AC_C_TYPEOF > AC_DEFINE([HAVE_STATEMENT_EXPR], 1, [Define to 1 if you have statement > expressions.]) > > -- > 2.29.2 > ___ > Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org > To unsubscribe send an email to linux-nvdimm-le...@lists.01.org ___ Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org To unsubscribe send an email to linux-nvdimm-le...@lists.01.org
Re: [PATCH v2] include: Remove pagemap.h from blkdev.h
On Tue, Mar 09, 2021 at 07:57:47PM +, Matthew Wilcox (Oracle) wrote: > My UEK-derived config has 1030 files depending on pagemap.h before > this change. Afterwards, just 326 files need to be rebuilt when I > touch pagemap.h. I think blkdev.h is probably included too widely, > but untangling that dependency is harder and this solves my problem. > x86 allmodconfig builds, but there may be implicit include problems > on other architectures. > > Signed-off-by: Matthew Wilcox (Oracle) > --- > v2: Fix CONFIG_SWAP=n implicit use of pagemap.h by swap.h. Increases > the number of files from 240, but that's still a big win -- 68% > reduction instead of 77%. Looks good. I suspect blkdev.h also has penty of other includes that aren't needed either.. Reviewed-by: Christoph Hellwig ___ Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org To unsubscribe send an email to linux-nvdimm-le...@lists.01.org
