linux/drivers/nvdimm/pfn_devs.c

850 lines
22 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright(c) 2013-2016 Intel Corporation. All rights reserved.
*/
#include <linux/memremap.h>
#include <linux/blkdev.h>
#include <linux/device.h>
#include <linux/genhd.h>
#include <linux/sizes.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include "nd-core.h"
#include "pfn.h"
#include "nd.h"
static void nd_pfn_release(struct device *dev)
{
struct nd_region *nd_region = to_nd_region(dev->parent);
struct nd_pfn *nd_pfn = to_nd_pfn(dev);
dev_dbg(dev, "trace\n");
nd_detach_ndns(&nd_pfn->dev, &nd_pfn->ndns);
ida_simple_remove(&nd_region->pfn_ida, nd_pfn->id);
kfree(nd_pfn->uuid);
kfree(nd_pfn);
}
struct nd_pfn *to_nd_pfn(struct device *dev)
{
struct nd_pfn *nd_pfn = container_of(dev, struct nd_pfn, dev);
WARN_ON(!is_nd_pfn(dev));
return nd_pfn;
}
EXPORT_SYMBOL(to_nd_pfn);
static ssize_t mode_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
switch (nd_pfn->mode) {
case PFN_MODE_RAM:
return sprintf(buf, "ram\n");
case PFN_MODE_PMEM:
return sprintf(buf, "pmem\n");
default:
return sprintf(buf, "none\n");
}
}
static ssize_t mode_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
ssize_t rc = 0;
driver-core, libnvdimm: Let device subsystems add local lockdep coverage For good reason, the standard device_lock() is marked lockdep_set_novalidate_class() because there is simply no sane way to describe the myriad ways the device_lock() ordered with other locks. However, that leaves subsystems that know their own local device_lock() ordering rules to find lock ordering mistakes manually. Instead, introduce an optional / additional lockdep-enabled lock that a subsystem can acquire in all the same paths that the device_lock() is acquired. A conversion of the NFIT driver and NVDIMM subsystem to a lockdep-validate device_lock() scheme is included. The debug_nvdimm_lock() implementation implements the correct lock-class and stacking order for the libnvdimm device topology hierarchy. Yes, this is a hack, but hopefully it is a useful hack for other subsystems device_lock() debug sessions. Quoting Greg: "Yeah, it feels a bit hacky but it's really up to a subsystem to mess up using it as much as anything else, so user beware :) I don't object to it if it makes things easier for you to debug." Cc: Ingo Molnar <mingo@redhat.com> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Link: https://lore.kernel.org/r/156341210661.292348.7014034644265455704.stgit@dwillia2-desk3.amr.corp.intel.com
2019-07-18 09:08:26 +08:00
nd_device_lock(dev);
nvdimm_bus_lock(dev);
if (dev->driver)
rc = -EBUSY;
else {
size_t n = len - 1;
if (strncmp(buf, "pmem\n", n) == 0
|| strncmp(buf, "pmem", n) == 0) {
nd_pfn->mode = PFN_MODE_PMEM;
} else if (strncmp(buf, "ram\n", n) == 0
|| strncmp(buf, "ram", n) == 0)
nd_pfn->mode = PFN_MODE_RAM;
else if (strncmp(buf, "none\n", n) == 0
|| strncmp(buf, "none", n) == 0)
nd_pfn->mode = PFN_MODE_NONE;
else
rc = -EINVAL;
}
dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf,
buf[len - 1] == '\n' ? "" : "\n");
nvdimm_bus_unlock(dev);
driver-core, libnvdimm: Let device subsystems add local lockdep coverage For good reason, the standard device_lock() is marked lockdep_set_novalidate_class() because there is simply no sane way to describe the myriad ways the device_lock() ordered with other locks. However, that leaves subsystems that know their own local device_lock() ordering rules to find lock ordering mistakes manually. Instead, introduce an optional / additional lockdep-enabled lock that a subsystem can acquire in all the same paths that the device_lock() is acquired. A conversion of the NFIT driver and NVDIMM subsystem to a lockdep-validate device_lock() scheme is included. The debug_nvdimm_lock() implementation implements the correct lock-class and stacking order for the libnvdimm device topology hierarchy. Yes, this is a hack, but hopefully it is a useful hack for other subsystems device_lock() debug sessions. Quoting Greg: "Yeah, it feels a bit hacky but it's really up to a subsystem to mess up using it as much as anything else, so user beware :) I don't object to it if it makes things easier for you to debug." Cc: Ingo Molnar <mingo@redhat.com> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Link: https://lore.kernel.org/r/156341210661.292348.7014034644265455704.stgit@dwillia2-desk3.amr.corp.intel.com
2019-07-18 09:08:26 +08:00
nd_device_unlock(dev);
return rc ? rc : len;
}
static DEVICE_ATTR_RW(mode);
static ssize_t align_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
return sprintf(buf, "%ld\n", nd_pfn->align);
}
libnvdimm/dax: Pick the right alignment default when creating dax devices Allow arch to provide the supported alignments and use hugepage alignment only if we support hugepage. Right now we depend on compile time configs whereas this patch switch this to runtime discovery. Architectures like ppc64 can have THP enabled in code, but then can have hugepage size disabled by the hypervisor. This allows us to create dax devices with PAGE_SIZE alignment in this case. Existing dax namespace with alignment larger than PAGE_SIZE will fail to initialize in this specific case. We still allow fsdax namespace initialization. With respect to identifying whether to enable hugepage fault for a dax device, if THP is enabled during compile, we default to taking hugepage fault and in dax fault handler if we find the fault size > alignment we retry with PAGE_SIZE fault size. This also addresses the below failure scenario on ppc64 ndctl create-namespace --mode=devdax | grep align "align":16777216, "align":16777216 cat /sys/devices/ndbus0/region0/dax0.0/supported_alignments 65536 16777216 daxio.static-debug -z -o /dev/dax0.0 Bus error (core dumped) $ dmesg | tail lpar: Failed hash pte insert with error -4 hash-mmu: mm: Hashing failure ! EA=0x7fff17000000 access=0x8000000000000006 current=daxio hash-mmu: trap=0x300 vsid=0x22cb7a3 ssize=1 base psize=2 psize 10 pte=0xc000000501002b86 daxio[3860]: bus error (7) at 7fff17000000 nip 7fff973c007c lr 7fff973bff34 code 2 in libpmem.so.1.0.0[7fff973b0000+20000] daxio[3860]: code: 792945e4 7d494b78 e95f0098 7d494b78 f93f00a0 4800012c e93f0088 f93f0120 daxio[3860]: code: e93f00a0 f93f0128 e93f0120 e95f0128 <f9490000> e93f0088 39290008 f93f0110 The failure was due to guest kernel using wrong page size. The namespaces created with 16M alignment will appear as below on a config with 16M page size disabled. $ ndctl list -Ni [ { "dev":"namespace0.1", "mode":"fsdax", "map":"dev", "size":5351931904, "uuid":"fc6e9667-461a-4718-82b4-69b24570bddb", "align":16777216, "blockdev":"pmem0.1", "supported_alignments":[ 65536 ] }, { "dev":"namespace0.0", "mode":"fsdax", <==== devdax 16M alignment marked disabled. "map":"mem", "size":5368709120, "uuid":"a4bdf81a-f2ee-4bc6-91db-7b87eddd0484", "state":"disabled" } ] Cc: linux-mm@kvack.org Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Link: https://lore.kernel.org/r/20190905154603.10349-8-aneesh.kumar@linux.ibm.com Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2019-09-05 23:46:03 +08:00
static unsigned long *nd_pfn_supported_alignments(unsigned long *alignments)
{
libnvdimm/dax: Pick the right alignment default when creating dax devices Allow arch to provide the supported alignments and use hugepage alignment only if we support hugepage. Right now we depend on compile time configs whereas this patch switch this to runtime discovery. Architectures like ppc64 can have THP enabled in code, but then can have hugepage size disabled by the hypervisor. This allows us to create dax devices with PAGE_SIZE alignment in this case. Existing dax namespace with alignment larger than PAGE_SIZE will fail to initialize in this specific case. We still allow fsdax namespace initialization. With respect to identifying whether to enable hugepage fault for a dax device, if THP is enabled during compile, we default to taking hugepage fault and in dax fault handler if we find the fault size > alignment we retry with PAGE_SIZE fault size. This also addresses the below failure scenario on ppc64 ndctl create-namespace --mode=devdax | grep align "align":16777216, "align":16777216 cat /sys/devices/ndbus0/region0/dax0.0/supported_alignments 65536 16777216 daxio.static-debug -z -o /dev/dax0.0 Bus error (core dumped) $ dmesg | tail lpar: Failed hash pte insert with error -4 hash-mmu: mm: Hashing failure ! EA=0x7fff17000000 access=0x8000000000000006 current=daxio hash-mmu: trap=0x300 vsid=0x22cb7a3 ssize=1 base psize=2 psize 10 pte=0xc000000501002b86 daxio[3860]: bus error (7) at 7fff17000000 nip 7fff973c007c lr 7fff973bff34 code 2 in libpmem.so.1.0.0[7fff973b0000+20000] daxio[3860]: code: 792945e4 7d494b78 e95f0098 7d494b78 f93f00a0 4800012c e93f0088 f93f0120 daxio[3860]: code: e93f00a0 f93f0128 e93f0120 e95f0128 <f9490000> e93f0088 39290008 f93f0110 The failure was due to guest kernel using wrong page size. The namespaces created with 16M alignment will appear as below on a config with 16M page size disabled. $ ndctl list -Ni [ { "dev":"namespace0.1", "mode":"fsdax", "map":"dev", "size":5351931904, "uuid":"fc6e9667-461a-4718-82b4-69b24570bddb", "align":16777216, "blockdev":"pmem0.1", "supported_alignments":[ 65536 ] }, { "dev":"namespace0.0", "mode":"fsdax", <==== devdax 16M alignment marked disabled. "map":"mem", "size":5368709120, "uuid":"a4bdf81a-f2ee-4bc6-91db-7b87eddd0484", "state":"disabled" } ] Cc: linux-mm@kvack.org Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Link: https://lore.kernel.org/r/20190905154603.10349-8-aneesh.kumar@linux.ibm.com Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2019-09-05 23:46:03 +08:00
alignments[0] = PAGE_SIZE;
if (has_transparent_hugepage()) {
alignments[1] = HPAGE_PMD_SIZE;
if (IS_ENABLED(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD))
alignments[2] = HPAGE_PUD_SIZE;
}
return alignments;
}
/*
* Use pmd mapping if supported as default alignment
*/
static unsigned long nd_pfn_default_alignment(void)
{
libnvdimm/dax: Pick the right alignment default when creating dax devices Allow arch to provide the supported alignments and use hugepage alignment only if we support hugepage. Right now we depend on compile time configs whereas this patch switch this to runtime discovery. Architectures like ppc64 can have THP enabled in code, but then can have hugepage size disabled by the hypervisor. This allows us to create dax devices with PAGE_SIZE alignment in this case. Existing dax namespace with alignment larger than PAGE_SIZE will fail to initialize in this specific case. We still allow fsdax namespace initialization. With respect to identifying whether to enable hugepage fault for a dax device, if THP is enabled during compile, we default to taking hugepage fault and in dax fault handler if we find the fault size > alignment we retry with PAGE_SIZE fault size. This also addresses the below failure scenario on ppc64 ndctl create-namespace --mode=devdax | grep align "align":16777216, "align":16777216 cat /sys/devices/ndbus0/region0/dax0.0/supported_alignments 65536 16777216 daxio.static-debug -z -o /dev/dax0.0 Bus error (core dumped) $ dmesg | tail lpar: Failed hash pte insert with error -4 hash-mmu: mm: Hashing failure ! EA=0x7fff17000000 access=0x8000000000000006 current=daxio hash-mmu: trap=0x300 vsid=0x22cb7a3 ssize=1 base psize=2 psize 10 pte=0xc000000501002b86 daxio[3860]: bus error (7) at 7fff17000000 nip 7fff973c007c lr 7fff973bff34 code 2 in libpmem.so.1.0.0[7fff973b0000+20000] daxio[3860]: code: 792945e4 7d494b78 e95f0098 7d494b78 f93f00a0 4800012c e93f0088 f93f0120 daxio[3860]: code: e93f00a0 f93f0128 e93f0120 e95f0128 <f9490000> e93f0088 39290008 f93f0110 The failure was due to guest kernel using wrong page size. The namespaces created with 16M alignment will appear as below on a config with 16M page size disabled. $ ndctl list -Ni [ { "dev":"namespace0.1", "mode":"fsdax", "map":"dev", "size":5351931904, "uuid":"fc6e9667-461a-4718-82b4-69b24570bddb", "align":16777216, "blockdev":"pmem0.1", "supported_alignments":[ 65536 ] }, { "dev":"namespace0.0", "mode":"fsdax", <==== devdax 16M alignment marked disabled. "map":"mem", "size":5368709120, "uuid":"a4bdf81a-f2ee-4bc6-91db-7b87eddd0484", "state":"disabled" } ] Cc: linux-mm@kvack.org Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Link: https://lore.kernel.org/r/20190905154603.10349-8-aneesh.kumar@linux.ibm.com Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2019-09-05 23:46:03 +08:00
if (has_transparent_hugepage())
return HPAGE_PMD_SIZE;
return PAGE_SIZE;
}
static ssize_t align_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
libnvdimm/dax: Pick the right alignment default when creating dax devices Allow arch to provide the supported alignments and use hugepage alignment only if we support hugepage. Right now we depend on compile time configs whereas this patch switch this to runtime discovery. Architectures like ppc64 can have THP enabled in code, but then can have hugepage size disabled by the hypervisor. This allows us to create dax devices with PAGE_SIZE alignment in this case. Existing dax namespace with alignment larger than PAGE_SIZE will fail to initialize in this specific case. We still allow fsdax namespace initialization. With respect to identifying whether to enable hugepage fault for a dax device, if THP is enabled during compile, we default to taking hugepage fault and in dax fault handler if we find the fault size > alignment we retry with PAGE_SIZE fault size. This also addresses the below failure scenario on ppc64 ndctl create-namespace --mode=devdax | grep align "align":16777216, "align":16777216 cat /sys/devices/ndbus0/region0/dax0.0/supported_alignments 65536 16777216 daxio.static-debug -z -o /dev/dax0.0 Bus error (core dumped) $ dmesg | tail lpar: Failed hash pte insert with error -4 hash-mmu: mm: Hashing failure ! EA=0x7fff17000000 access=0x8000000000000006 current=daxio hash-mmu: trap=0x300 vsid=0x22cb7a3 ssize=1 base psize=2 psize 10 pte=0xc000000501002b86 daxio[3860]: bus error (7) at 7fff17000000 nip 7fff973c007c lr 7fff973bff34 code 2 in libpmem.so.1.0.0[7fff973b0000+20000] daxio[3860]: code: 792945e4 7d494b78 e95f0098 7d494b78 f93f00a0 4800012c e93f0088 f93f0120 daxio[3860]: code: e93f00a0 f93f0128 e93f0120 e95f0128 <f9490000> e93f0088 39290008 f93f0110 The failure was due to guest kernel using wrong page size. The namespaces created with 16M alignment will appear as below on a config with 16M page size disabled. $ ndctl list -Ni [ { "dev":"namespace0.1", "mode":"fsdax", "map":"dev", "size":5351931904, "uuid":"fc6e9667-461a-4718-82b4-69b24570bddb", "align":16777216, "blockdev":"pmem0.1", "supported_alignments":[ 65536 ] }, { "dev":"namespace0.0", "mode":"fsdax", <==== devdax 16M alignment marked disabled. "map":"mem", "size":5368709120, "uuid":"a4bdf81a-f2ee-4bc6-91db-7b87eddd0484", "state":"disabled" } ] Cc: linux-mm@kvack.org Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Link: https://lore.kernel.org/r/20190905154603.10349-8-aneesh.kumar@linux.ibm.com Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2019-09-05 23:46:03 +08:00
unsigned long aligns[MAX_NVDIMM_ALIGN] = { [0] = 0, };
ssize_t rc;
driver-core, libnvdimm: Let device subsystems add local lockdep coverage For good reason, the standard device_lock() is marked lockdep_set_novalidate_class() because there is simply no sane way to describe the myriad ways the device_lock() ordered with other locks. However, that leaves subsystems that know their own local device_lock() ordering rules to find lock ordering mistakes manually. Instead, introduce an optional / additional lockdep-enabled lock that a subsystem can acquire in all the same paths that the device_lock() is acquired. A conversion of the NFIT driver and NVDIMM subsystem to a lockdep-validate device_lock() scheme is included. The debug_nvdimm_lock() implementation implements the correct lock-class and stacking order for the libnvdimm device topology hierarchy. Yes, this is a hack, but hopefully it is a useful hack for other subsystems device_lock() debug sessions. Quoting Greg: "Yeah, it feels a bit hacky but it's really up to a subsystem to mess up using it as much as anything else, so user beware :) I don't object to it if it makes things easier for you to debug." Cc: Ingo Molnar <mingo@redhat.com> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Link: https://lore.kernel.org/r/156341210661.292348.7014034644265455704.stgit@dwillia2-desk3.amr.corp.intel.com
2019-07-18 09:08:26 +08:00
nd_device_lock(dev);
nvdimm_bus_lock(dev);
rc = nd_size_select_store(dev, buf, &nd_pfn->align,
libnvdimm/dax: Pick the right alignment default when creating dax devices Allow arch to provide the supported alignments and use hugepage alignment only if we support hugepage. Right now we depend on compile time configs whereas this patch switch this to runtime discovery. Architectures like ppc64 can have THP enabled in code, but then can have hugepage size disabled by the hypervisor. This allows us to create dax devices with PAGE_SIZE alignment in this case. Existing dax namespace with alignment larger than PAGE_SIZE will fail to initialize in this specific case. We still allow fsdax namespace initialization. With respect to identifying whether to enable hugepage fault for a dax device, if THP is enabled during compile, we default to taking hugepage fault and in dax fault handler if we find the fault size > alignment we retry with PAGE_SIZE fault size. This also addresses the below failure scenario on ppc64 ndctl create-namespace --mode=devdax | grep align "align":16777216, "align":16777216 cat /sys/devices/ndbus0/region0/dax0.0/supported_alignments 65536 16777216 daxio.static-debug -z -o /dev/dax0.0 Bus error (core dumped) $ dmesg | tail lpar: Failed hash pte insert with error -4 hash-mmu: mm: Hashing failure ! EA=0x7fff17000000 access=0x8000000000000006 current=daxio hash-mmu: trap=0x300 vsid=0x22cb7a3 ssize=1 base psize=2 psize 10 pte=0xc000000501002b86 daxio[3860]: bus error (7) at 7fff17000000 nip 7fff973c007c lr 7fff973bff34 code 2 in libpmem.so.1.0.0[7fff973b0000+20000] daxio[3860]: code: 792945e4 7d494b78 e95f0098 7d494b78 f93f00a0 4800012c e93f0088 f93f0120 daxio[3860]: code: e93f00a0 f93f0128 e93f0120 e95f0128 <f9490000> e93f0088 39290008 f93f0110 The failure was due to guest kernel using wrong page size. The namespaces created with 16M alignment will appear as below on a config with 16M page size disabled. $ ndctl list -Ni [ { "dev":"namespace0.1", "mode":"fsdax", "map":"dev", "size":5351931904, "uuid":"fc6e9667-461a-4718-82b4-69b24570bddb", "align":16777216, "blockdev":"pmem0.1", "supported_alignments":[ 65536 ] }, { "dev":"namespace0.0", "mode":"fsdax", <==== devdax 16M alignment marked disabled. "map":"mem", "size":5368709120, "uuid":"a4bdf81a-f2ee-4bc6-91db-7b87eddd0484", "state":"disabled" } ] Cc: linux-mm@kvack.org Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Link: https://lore.kernel.org/r/20190905154603.10349-8-aneesh.kumar@linux.ibm.com Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2019-09-05 23:46:03 +08:00
nd_pfn_supported_alignments(aligns));
dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf,
buf[len - 1] == '\n' ? "" : "\n");
nvdimm_bus_unlock(dev);
driver-core, libnvdimm: Let device subsystems add local lockdep coverage For good reason, the standard device_lock() is marked lockdep_set_novalidate_class() because there is simply no sane way to describe the myriad ways the device_lock() ordered with other locks. However, that leaves subsystems that know their own local device_lock() ordering rules to find lock ordering mistakes manually. Instead, introduce an optional / additional lockdep-enabled lock that a subsystem can acquire in all the same paths that the device_lock() is acquired. A conversion of the NFIT driver and NVDIMM subsystem to a lockdep-validate device_lock() scheme is included. The debug_nvdimm_lock() implementation implements the correct lock-class and stacking order for the libnvdimm device topology hierarchy. Yes, this is a hack, but hopefully it is a useful hack for other subsystems device_lock() debug sessions. Quoting Greg: "Yeah, it feels a bit hacky but it's really up to a subsystem to mess up using it as much as anything else, so user beware :) I don't object to it if it makes things easier for you to debug." Cc: Ingo Molnar <mingo@redhat.com> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Link: https://lore.kernel.org/r/156341210661.292348.7014034644265455704.stgit@dwillia2-desk3.amr.corp.intel.com
2019-07-18 09:08:26 +08:00
nd_device_unlock(dev);
return rc ? rc : len;
}
static DEVICE_ATTR_RW(align);
static ssize_t uuid_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
if (nd_pfn->uuid)
return sprintf(buf, "%pUb\n", nd_pfn->uuid);
return sprintf(buf, "\n");
}
static ssize_t uuid_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
ssize_t rc;
driver-core, libnvdimm: Let device subsystems add local lockdep coverage For good reason, the standard device_lock() is marked lockdep_set_novalidate_class() because there is simply no sane way to describe the myriad ways the device_lock() ordered with other locks. However, that leaves subsystems that know their own local device_lock() ordering rules to find lock ordering mistakes manually. Instead, introduce an optional / additional lockdep-enabled lock that a subsystem can acquire in all the same paths that the device_lock() is acquired. A conversion of the NFIT driver and NVDIMM subsystem to a lockdep-validate device_lock() scheme is included. The debug_nvdimm_lock() implementation implements the correct lock-class and stacking order for the libnvdimm device topology hierarchy. Yes, this is a hack, but hopefully it is a useful hack for other subsystems device_lock() debug sessions. Quoting Greg: "Yeah, it feels a bit hacky but it's really up to a subsystem to mess up using it as much as anything else, so user beware :) I don't object to it if it makes things easier for you to debug." Cc: Ingo Molnar <mingo@redhat.com> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Link: https://lore.kernel.org/r/156341210661.292348.7014034644265455704.stgit@dwillia2-desk3.amr.corp.intel.com
2019-07-18 09:08:26 +08:00
nd_device_lock(dev);
rc = nd_uuid_store(dev, &nd_pfn->uuid, buf, len);
dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf,
buf[len - 1] == '\n' ? "" : "\n");
driver-core, libnvdimm: Let device subsystems add local lockdep coverage For good reason, the standard device_lock() is marked lockdep_set_novalidate_class() because there is simply no sane way to describe the myriad ways the device_lock() ordered with other locks. However, that leaves subsystems that know their own local device_lock() ordering rules to find lock ordering mistakes manually. Instead, introduce an optional / additional lockdep-enabled lock that a subsystem can acquire in all the same paths that the device_lock() is acquired. A conversion of the NFIT driver and NVDIMM subsystem to a lockdep-validate device_lock() scheme is included. The debug_nvdimm_lock() implementation implements the correct lock-class and stacking order for the libnvdimm device topology hierarchy. Yes, this is a hack, but hopefully it is a useful hack for other subsystems device_lock() debug sessions. Quoting Greg: "Yeah, it feels a bit hacky but it's really up to a subsystem to mess up using it as much as anything else, so user beware :) I don't object to it if it makes things easier for you to debug." Cc: Ingo Molnar <mingo@redhat.com> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Link: https://lore.kernel.org/r/156341210661.292348.7014034644265455704.stgit@dwillia2-desk3.amr.corp.intel.com
2019-07-18 09:08:26 +08:00
nd_device_unlock(dev);
return rc ? rc : len;
}
static DEVICE_ATTR_RW(uuid);
static ssize_t namespace_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
ssize_t rc;
nvdimm_bus_lock(dev);
rc = sprintf(buf, "%s\n", nd_pfn->ndns
? dev_name(&nd_pfn->ndns->dev) : "");
nvdimm_bus_unlock(dev);
return rc;
}
static ssize_t namespace_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
ssize_t rc;
driver-core, libnvdimm: Let device subsystems add local lockdep coverage For good reason, the standard device_lock() is marked lockdep_set_novalidate_class() because there is simply no sane way to describe the myriad ways the device_lock() ordered with other locks. However, that leaves subsystems that know their own local device_lock() ordering rules to find lock ordering mistakes manually. Instead, introduce an optional / additional lockdep-enabled lock that a subsystem can acquire in all the same paths that the device_lock() is acquired. A conversion of the NFIT driver and NVDIMM subsystem to a lockdep-validate device_lock() scheme is included. The debug_nvdimm_lock() implementation implements the correct lock-class and stacking order for the libnvdimm device topology hierarchy. Yes, this is a hack, but hopefully it is a useful hack for other subsystems device_lock() debug sessions. Quoting Greg: "Yeah, it feels a bit hacky but it's really up to a subsystem to mess up using it as much as anything else, so user beware :) I don't object to it if it makes things easier for you to debug." Cc: Ingo Molnar <mingo@redhat.com> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Link: https://lore.kernel.org/r/156341210661.292348.7014034644265455704.stgit@dwillia2-desk3.amr.corp.intel.com
2019-07-18 09:08:26 +08:00
nd_device_lock(dev);
nvdimm_bus_lock(dev);
rc = nd_namespace_store(dev, &nd_pfn->ndns, buf, len);
dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf,
buf[len - 1] == '\n' ? "" : "\n");
nvdimm_bus_unlock(dev);
driver-core, libnvdimm: Let device subsystems add local lockdep coverage For good reason, the standard device_lock() is marked lockdep_set_novalidate_class() because there is simply no sane way to describe the myriad ways the device_lock() ordered with other locks. However, that leaves subsystems that know their own local device_lock() ordering rules to find lock ordering mistakes manually. Instead, introduce an optional / additional lockdep-enabled lock that a subsystem can acquire in all the same paths that the device_lock() is acquired. A conversion of the NFIT driver and NVDIMM subsystem to a lockdep-validate device_lock() scheme is included. The debug_nvdimm_lock() implementation implements the correct lock-class and stacking order for the libnvdimm device topology hierarchy. Yes, this is a hack, but hopefully it is a useful hack for other subsystems device_lock() debug sessions. Quoting Greg: "Yeah, it feels a bit hacky but it's really up to a subsystem to mess up using it as much as anything else, so user beware :) I don't object to it if it makes things easier for you to debug." Cc: Ingo Molnar <mingo@redhat.com> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Link: https://lore.kernel.org/r/156341210661.292348.7014034644265455704.stgit@dwillia2-desk3.amr.corp.intel.com
2019-07-18 09:08:26 +08:00
nd_device_unlock(dev);
return rc;
}
static DEVICE_ATTR_RW(namespace);
static ssize_t resource_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
ssize_t rc;
driver-core, libnvdimm: Let device subsystems add local lockdep coverage For good reason, the standard device_lock() is marked lockdep_set_novalidate_class() because there is simply no sane way to describe the myriad ways the device_lock() ordered with other locks. However, that leaves subsystems that know their own local device_lock() ordering rules to find lock ordering mistakes manually. Instead, introduce an optional / additional lockdep-enabled lock that a subsystem can acquire in all the same paths that the device_lock() is acquired. A conversion of the NFIT driver and NVDIMM subsystem to a lockdep-validate device_lock() scheme is included. The debug_nvdimm_lock() implementation implements the correct lock-class and stacking order for the libnvdimm device topology hierarchy. Yes, this is a hack, but hopefully it is a useful hack for other subsystems device_lock() debug sessions. Quoting Greg: "Yeah, it feels a bit hacky but it's really up to a subsystem to mess up using it as much as anything else, so user beware :) I don't object to it if it makes things easier for you to debug." Cc: Ingo Molnar <mingo@redhat.com> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Link: https://lore.kernel.org/r/156341210661.292348.7014034644265455704.stgit@dwillia2-desk3.amr.corp.intel.com
2019-07-18 09:08:26 +08:00
nd_device_lock(dev);
if (dev->driver) {
struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
u64 offset = __le64_to_cpu(pfn_sb->dataoff);
struct nd_namespace_common *ndns = nd_pfn->ndns;
u32 start_pad = __le32_to_cpu(pfn_sb->start_pad);
struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
rc = sprintf(buf, "%#llx\n", (unsigned long long) nsio->res.start
+ start_pad + offset);
} else {
/* no address to convey if the pfn instance is disabled */
rc = -ENXIO;
}
driver-core, libnvdimm: Let device subsystems add local lockdep coverage For good reason, the standard device_lock() is marked lockdep_set_novalidate_class() because there is simply no sane way to describe the myriad ways the device_lock() ordered with other locks. However, that leaves subsystems that know their own local device_lock() ordering rules to find lock ordering mistakes manually. Instead, introduce an optional / additional lockdep-enabled lock that a subsystem can acquire in all the same paths that the device_lock() is acquired. A conversion of the NFIT driver and NVDIMM subsystem to a lockdep-validate device_lock() scheme is included. The debug_nvdimm_lock() implementation implements the correct lock-class and stacking order for the libnvdimm device topology hierarchy. Yes, this is a hack, but hopefully it is a useful hack for other subsystems device_lock() debug sessions. Quoting Greg: "Yeah, it feels a bit hacky but it's really up to a subsystem to mess up using it as much as anything else, so user beware :) I don't object to it if it makes things easier for you to debug." Cc: Ingo Molnar <mingo@redhat.com> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Link: https://lore.kernel.org/r/156341210661.292348.7014034644265455704.stgit@dwillia2-desk3.amr.corp.intel.com
2019-07-18 09:08:26 +08:00
nd_device_unlock(dev);
return rc;
}
static DEVICE_ATTR_ADMIN_RO(resource);
static ssize_t size_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
ssize_t rc;
driver-core, libnvdimm: Let device subsystems add local lockdep coverage For good reason, the standard device_lock() is marked lockdep_set_novalidate_class() because there is simply no sane way to describe the myriad ways the device_lock() ordered with other locks. However, that leaves subsystems that know their own local device_lock() ordering rules to find lock ordering mistakes manually. Instead, introduce an optional / additional lockdep-enabled lock that a subsystem can acquire in all the same paths that the device_lock() is acquired. A conversion of the NFIT driver and NVDIMM subsystem to a lockdep-validate device_lock() scheme is included. The debug_nvdimm_lock() implementation implements the correct lock-class and stacking order for the libnvdimm device topology hierarchy. Yes, this is a hack, but hopefully it is a useful hack for other subsystems device_lock() debug sessions. Quoting Greg: "Yeah, it feels a bit hacky but it's really up to a subsystem to mess up using it as much as anything else, so user beware :) I don't object to it if it makes things easier for you to debug." Cc: Ingo Molnar <mingo@redhat.com> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Link: https://lore.kernel.org/r/156341210661.292348.7014034644265455704.stgit@dwillia2-desk3.amr.corp.intel.com
2019-07-18 09:08:26 +08:00
nd_device_lock(dev);
if (dev->driver) {
struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
u64 offset = __le64_to_cpu(pfn_sb->dataoff);
struct nd_namespace_common *ndns = nd_pfn->ndns;
u32 start_pad = __le32_to_cpu(pfn_sb->start_pad);
u32 end_trunc = __le32_to_cpu(pfn_sb->end_trunc);
struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
rc = sprintf(buf, "%llu\n", (unsigned long long)
resource_size(&nsio->res) - start_pad
- end_trunc - offset);
} else {
/* no size to convey if the pfn instance is disabled */
rc = -ENXIO;
}
driver-core, libnvdimm: Let device subsystems add local lockdep coverage For good reason, the standard device_lock() is marked lockdep_set_novalidate_class() because there is simply no sane way to describe the myriad ways the device_lock() ordered with other locks. However, that leaves subsystems that know their own local device_lock() ordering rules to find lock ordering mistakes manually. Instead, introduce an optional / additional lockdep-enabled lock that a subsystem can acquire in all the same paths that the device_lock() is acquired. A conversion of the NFIT driver and NVDIMM subsystem to a lockdep-validate device_lock() scheme is included. The debug_nvdimm_lock() implementation implements the correct lock-class and stacking order for the libnvdimm device topology hierarchy. Yes, this is a hack, but hopefully it is a useful hack for other subsystems device_lock() debug sessions. Quoting Greg: "Yeah, it feels a bit hacky but it's really up to a subsystem to mess up using it as much as anything else, so user beware :) I don't object to it if it makes things easier for you to debug." Cc: Ingo Molnar <mingo@redhat.com> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Link: https://lore.kernel.org/r/156341210661.292348.7014034644265455704.stgit@dwillia2-desk3.amr.corp.intel.com
2019-07-18 09:08:26 +08:00
nd_device_unlock(dev);
return rc;
}
static DEVICE_ATTR_RO(size);
static ssize_t supported_alignments_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
libnvdimm/dax: Pick the right alignment default when creating dax devices Allow arch to provide the supported alignments and use hugepage alignment only if we support hugepage. Right now we depend on compile time configs whereas this patch switch this to runtime discovery. Architectures like ppc64 can have THP enabled in code, but then can have hugepage size disabled by the hypervisor. This allows us to create dax devices with PAGE_SIZE alignment in this case. Existing dax namespace with alignment larger than PAGE_SIZE will fail to initialize in this specific case. We still allow fsdax namespace initialization. With respect to identifying whether to enable hugepage fault for a dax device, if THP is enabled during compile, we default to taking hugepage fault and in dax fault handler if we find the fault size > alignment we retry with PAGE_SIZE fault size. This also addresses the below failure scenario on ppc64 ndctl create-namespace --mode=devdax | grep align "align":16777216, "align":16777216 cat /sys/devices/ndbus0/region0/dax0.0/supported_alignments 65536 16777216 daxio.static-debug -z -o /dev/dax0.0 Bus error (core dumped) $ dmesg | tail lpar: Failed hash pte insert with error -4 hash-mmu: mm: Hashing failure ! EA=0x7fff17000000 access=0x8000000000000006 current=daxio hash-mmu: trap=0x300 vsid=0x22cb7a3 ssize=1 base psize=2 psize 10 pte=0xc000000501002b86 daxio[3860]: bus error (7) at 7fff17000000 nip 7fff973c007c lr 7fff973bff34 code 2 in libpmem.so.1.0.0[7fff973b0000+20000] daxio[3860]: code: 792945e4 7d494b78 e95f0098 7d494b78 f93f00a0 4800012c e93f0088 f93f0120 daxio[3860]: code: e93f00a0 f93f0128 e93f0120 e95f0128 <f9490000> e93f0088 39290008 f93f0110 The failure was due to guest kernel using wrong page size. The namespaces created with 16M alignment will appear as below on a config with 16M page size disabled. $ ndctl list -Ni [ { "dev":"namespace0.1", "mode":"fsdax", "map":"dev", "size":5351931904, "uuid":"fc6e9667-461a-4718-82b4-69b24570bddb", "align":16777216, "blockdev":"pmem0.1", "supported_alignments":[ 65536 ] }, { "dev":"namespace0.0", "mode":"fsdax", <==== devdax 16M alignment marked disabled. "map":"mem", "size":5368709120, "uuid":"a4bdf81a-f2ee-4bc6-91db-7b87eddd0484", "state":"disabled" } ] Cc: linux-mm@kvack.org Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Link: https://lore.kernel.org/r/20190905154603.10349-8-aneesh.kumar@linux.ibm.com Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2019-09-05 23:46:03 +08:00
unsigned long aligns[MAX_NVDIMM_ALIGN] = { [0] = 0, };
return nd_size_select_show(0,
nd_pfn_supported_alignments(aligns), buf);
}
static DEVICE_ATTR_RO(supported_alignments);
static struct attribute *nd_pfn_attributes[] = {
&dev_attr_mode.attr,
&dev_attr_namespace.attr,
&dev_attr_uuid.attr,
&dev_attr_align.attr,
&dev_attr_resource.attr,
&dev_attr_size.attr,
&dev_attr_supported_alignments.attr,
NULL,
};
static struct attribute_group nd_pfn_attribute_group = {
.attrs = nd_pfn_attributes,
};
const struct attribute_group *nd_pfn_attribute_groups[] = {
&nd_pfn_attribute_group,
&nd_device_attribute_group,
&nd_numa_attribute_group,
NULL,
};
static const struct device_type nd_pfn_device_type = {
.name = "nd_pfn",
.release = nd_pfn_release,
.groups = nd_pfn_attribute_groups,
};
bool is_nd_pfn(struct device *dev)
{
return dev ? dev->type == &nd_pfn_device_type : false;
}
EXPORT_SYMBOL(is_nd_pfn);
struct device *nd_pfn_devinit(struct nd_pfn *nd_pfn,
struct nd_namespace_common *ndns)
{
struct device *dev;
if (!nd_pfn)
return NULL;
nd_pfn->mode = PFN_MODE_NONE;
libnvdimm/dax: Pick the right alignment default when creating dax devices Allow arch to provide the supported alignments and use hugepage alignment only if we support hugepage. Right now we depend on compile time configs whereas this patch switch this to runtime discovery. Architectures like ppc64 can have THP enabled in code, but then can have hugepage size disabled by the hypervisor. This allows us to create dax devices with PAGE_SIZE alignment in this case. Existing dax namespace with alignment larger than PAGE_SIZE will fail to initialize in this specific case. We still allow fsdax namespace initialization. With respect to identifying whether to enable hugepage fault for a dax device, if THP is enabled during compile, we default to taking hugepage fault and in dax fault handler if we find the fault size > alignment we retry with PAGE_SIZE fault size. This also addresses the below failure scenario on ppc64 ndctl create-namespace --mode=devdax | grep align "align":16777216, "align":16777216 cat /sys/devices/ndbus0/region0/dax0.0/supported_alignments 65536 16777216 daxio.static-debug -z -o /dev/dax0.0 Bus error (core dumped) $ dmesg | tail lpar: Failed hash pte insert with error -4 hash-mmu: mm: Hashing failure ! EA=0x7fff17000000 access=0x8000000000000006 current=daxio hash-mmu: trap=0x300 vsid=0x22cb7a3 ssize=1 base psize=2 psize 10 pte=0xc000000501002b86 daxio[3860]: bus error (7) at 7fff17000000 nip 7fff973c007c lr 7fff973bff34 code 2 in libpmem.so.1.0.0[7fff973b0000+20000] daxio[3860]: code: 792945e4 7d494b78 e95f0098 7d494b78 f93f00a0 4800012c e93f0088 f93f0120 daxio[3860]: code: e93f00a0 f93f0128 e93f0120 e95f0128 <f9490000> e93f0088 39290008 f93f0110 The failure was due to guest kernel using wrong page size. The namespaces created with 16M alignment will appear as below on a config with 16M page size disabled. $ ndctl list -Ni [ { "dev":"namespace0.1", "mode":"fsdax", "map":"dev", "size":5351931904, "uuid":"fc6e9667-461a-4718-82b4-69b24570bddb", "align":16777216, "blockdev":"pmem0.1", "supported_alignments":[ 65536 ] }, { "dev":"namespace0.0", "mode":"fsdax", <==== devdax 16M alignment marked disabled. "map":"mem", "size":5368709120, "uuid":"a4bdf81a-f2ee-4bc6-91db-7b87eddd0484", "state":"disabled" } ] Cc: linux-mm@kvack.org Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Link: https://lore.kernel.org/r/20190905154603.10349-8-aneesh.kumar@linux.ibm.com Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2019-09-05 23:46:03 +08:00
nd_pfn->align = nd_pfn_default_alignment();
dev = &nd_pfn->dev;
device_initialize(&nd_pfn->dev);
if (ndns && !__nd_attach_ndns(&nd_pfn->dev, ndns, &nd_pfn->ndns)) {
dev_dbg(&ndns->dev, "failed, already claimed by %s\n",
dev_name(ndns->claim));
put_device(dev);
return NULL;
}
return dev;
}
static struct nd_pfn *nd_pfn_alloc(struct nd_region *nd_region)
{
struct nd_pfn *nd_pfn;
struct device *dev;
nd_pfn = kzalloc(sizeof(*nd_pfn), GFP_KERNEL);
if (!nd_pfn)
return NULL;
nd_pfn->id = ida_simple_get(&nd_region->pfn_ida, 0, 0, GFP_KERNEL);
if (nd_pfn->id < 0) {
kfree(nd_pfn);
return NULL;
}
dev = &nd_pfn->dev;
dev_set_name(dev, "pfn%d.%d", nd_region->id, nd_pfn->id);
dev->type = &nd_pfn_device_type;
dev->parent = &nd_region->dev;
return nd_pfn;
}
struct device *nd_pfn_create(struct nd_region *nd_region)
{
struct nd_pfn *nd_pfn;
struct device *dev;
if (!is_memory(&nd_region->dev))
return NULL;
nd_pfn = nd_pfn_alloc(nd_region);
dev = nd_pfn_devinit(nd_pfn, NULL);
__nd_device_register(dev);
return dev;
}
/*
* nd_pfn_clear_memmap_errors() clears any errors in the volatile memmap
* space associated with the namespace. If the memmap is set to DRAM, then
* this is a no-op. Since the memmap area is freshly initialized during
* probe, we have an opportunity to clear any badblocks in this area.
*/
static int nd_pfn_clear_memmap_errors(struct nd_pfn *nd_pfn)
{
struct nd_region *nd_region = to_nd_region(nd_pfn->dev.parent);
struct nd_namespace_common *ndns = nd_pfn->ndns;
void *zero_page = page_address(ZERO_PAGE(0));
struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
int num_bad, meta_num, rc, bb_present;
sector_t first_bad, meta_start;
struct nd_namespace_io *nsio;
if (nd_pfn->mode != PFN_MODE_PMEM)
return 0;
nsio = to_nd_namespace_io(&ndns->dev);
meta_start = (SZ_4K + sizeof(*pfn_sb)) >> 9;
meta_num = (le64_to_cpu(pfn_sb->dataoff) >> 9) - meta_start;
/*
* re-enable the namespace with correct size so that we can access
* the device memmap area.
*/
devm_namespace_disable(&nd_pfn->dev, ndns);
rc = devm_namespace_enable(&nd_pfn->dev, ndns, le64_to_cpu(pfn_sb->dataoff));
if (rc)
return rc;
do {
unsigned long zero_len;
u64 nsoff;
bb_present = badblocks_check(&nd_region->bb, meta_start,
meta_num, &first_bad, &num_bad);
if (bb_present) {
dev_dbg(&nd_pfn->dev, "meta: %x badblocks at %llx\n",
num_bad, first_bad);
nsoff = ALIGN_DOWN((nd_region->ndr_start
+ (first_bad << 9)) - nsio->res.start,
PAGE_SIZE);
zero_len = ALIGN(num_bad << 9, PAGE_SIZE);
while (zero_len) {
unsigned long chunk = min(zero_len, PAGE_SIZE);
rc = nvdimm_write_bytes(ndns, nsoff, zero_page,
chunk, 0);
if (rc)
break;
zero_len -= chunk;
nsoff += chunk;
}
if (rc) {
dev_err(&nd_pfn->dev,
"error clearing %x badblocks at %llx\n",
num_bad, first_bad);
return rc;
}
}
} while (bb_present);
return 0;
}
libnvdimm/dax: Pick the right alignment default when creating dax devices Allow arch to provide the supported alignments and use hugepage alignment only if we support hugepage. Right now we depend on compile time configs whereas this patch switch this to runtime discovery. Architectures like ppc64 can have THP enabled in code, but then can have hugepage size disabled by the hypervisor. This allows us to create dax devices with PAGE_SIZE alignment in this case. Existing dax namespace with alignment larger than PAGE_SIZE will fail to initialize in this specific case. We still allow fsdax namespace initialization. With respect to identifying whether to enable hugepage fault for a dax device, if THP is enabled during compile, we default to taking hugepage fault and in dax fault handler if we find the fault size > alignment we retry with PAGE_SIZE fault size. This also addresses the below failure scenario on ppc64 ndctl create-namespace --mode=devdax | grep align "align":16777216, "align":16777216 cat /sys/devices/ndbus0/region0/dax0.0/supported_alignments 65536 16777216 daxio.static-debug -z -o /dev/dax0.0 Bus error (core dumped) $ dmesg | tail lpar: Failed hash pte insert with error -4 hash-mmu: mm: Hashing failure ! EA=0x7fff17000000 access=0x8000000000000006 current=daxio hash-mmu: trap=0x300 vsid=0x22cb7a3 ssize=1 base psize=2 psize 10 pte=0xc000000501002b86 daxio[3860]: bus error (7) at 7fff17000000 nip 7fff973c007c lr 7fff973bff34 code 2 in libpmem.so.1.0.0[7fff973b0000+20000] daxio[3860]: code: 792945e4 7d494b78 e95f0098 7d494b78 f93f00a0 4800012c e93f0088 f93f0120 daxio[3860]: code: e93f00a0 f93f0128 e93f0120 e95f0128 <f9490000> e93f0088 39290008 f93f0110 The failure was due to guest kernel using wrong page size. The namespaces created with 16M alignment will appear as below on a config with 16M page size disabled. $ ndctl list -Ni [ { "dev":"namespace0.1", "mode":"fsdax", "map":"dev", "size":5351931904, "uuid":"fc6e9667-461a-4718-82b4-69b24570bddb", "align":16777216, "blockdev":"pmem0.1", "supported_alignments":[ 65536 ] }, { "dev":"namespace0.0", "mode":"fsdax", <==== devdax 16M alignment marked disabled. "map":"mem", "size":5368709120, "uuid":"a4bdf81a-f2ee-4bc6-91db-7b87eddd0484", "state":"disabled" } ] Cc: linux-mm@kvack.org Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Link: https://lore.kernel.org/r/20190905154603.10349-8-aneesh.kumar@linux.ibm.com Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2019-09-05 23:46:03 +08:00
static bool nd_supported_alignment(unsigned long align)
{
int i;
unsigned long supported[MAX_NVDIMM_ALIGN] = { [0] = 0, };
if (align == 0)
return false;
nd_pfn_supported_alignments(supported);
for (i = 0; supported[i]; i++)
if (align == supported[i])
return true;
return false;
}
libnvdimm/pfn: fix fsdax-mode namespace info-block zero-fields At namespace creation time there is the potential for the "expected to be zero" fields of a 'pfn' info-block to be filled with indeterminate data. While the kernel buffer is zeroed on allocation it is immediately overwritten by nd_pfn_validate() filling it with the current contents of the on-media info-block location. For fields like, 'flags' and the 'padding' it potentially means that future implementations can not rely on those fields being zero. In preparation to stop using the 'start_pad' and 'end_trunc' fields for section alignment, arrange for fields that are not explicitly initialized to be guaranteed zero. Bump the minor version to indicate it is safe to assume the 'padding' and 'flags' are zero. Otherwise, this corruption is expected to benign since all other critical fields are explicitly initialized. Note The cc: stable is about spreading this new policy to as many kernels as possible not fixing an issue in those kernels. It is not until the change titled "libnvdimm/pfn: Stop padding pmem namespaces to section alignment" where this improper initialization becomes a problem. So if someone decides to backport "libnvdimm/pfn: Stop padding pmem namespaces to section alignment" (which is not tagged for stable), make sure this pre-requisite is flagged. Link: http://lkml.kernel.org/r/156092356065.979959.6681003754765958296.stgit@dwillia2-desk3.amr.corp.intel.com Fixes: 32ab0a3f5170 ("libnvdimm, pmem: 'struct page' for pmem") Signed-off-by: Dan Williams <dan.j.williams@intel.com> Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> [ppc64] Cc: <stable@vger.kernel.org> Cc: David Hildenbrand <david@redhat.com> Cc: Jane Chu <jane.chu@oracle.com> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Logan Gunthorpe <logang@deltatee.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Toshi Kani <toshi.kani@hpe.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Wei Yang <richardw.yang@linux.intel.com> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-19 06:58:36 +08:00
/**
* nd_pfn_validate - read and validate info-block
* @nd_pfn: fsdax namespace runtime state / properties
* @sig: 'devdax' or 'fsdax' signature
*
* Upon return the info-block buffer contents (->pfn_sb) are
* indeterminate when validation fails, and a coherent info-block
* otherwise.
*/
int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
{
u64 checksum, offset;
struct resource *res;
enum nd_pfn_mode mode;
struct nd_namespace_io *nsio;
unsigned long align, start_pad;
struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
struct nd_namespace_common *ndns = nd_pfn->ndns;
const u8 *parent_uuid = nd_dev_to_uuid(&ndns->dev);
if (!pfn_sb || !ndns)
return -ENODEV;
if (!is_memory(nd_pfn->dev.parent))
return -ENODEV;
if (nvdimm_read_bytes(ndns, SZ_4K, pfn_sb, sizeof(*pfn_sb), 0))
return -ENXIO;
if (memcmp(pfn_sb->signature, sig, PFN_SIG_LEN) != 0)
return -ENODEV;
checksum = le64_to_cpu(pfn_sb->checksum);
pfn_sb->checksum = 0;
if (checksum != nd_sb_checksum((struct nd_gen_sb *) pfn_sb))
return -ENODEV;
pfn_sb->checksum = cpu_to_le64(checksum);
if (memcmp(pfn_sb->parent_uuid, parent_uuid, 16) != 0)
return -ENODEV;
if (__le16_to_cpu(pfn_sb->version_minor) < 1) {
pfn_sb->start_pad = 0;
pfn_sb->end_trunc = 0;
}
if (__le16_to_cpu(pfn_sb->version_minor) < 2)
pfn_sb->align = 0;
if (__le16_to_cpu(pfn_sb->version_minor) < 4) {
pfn_sb->page_struct_size = cpu_to_le16(64);
pfn_sb->page_size = cpu_to_le32(PAGE_SIZE);
}
switch (le32_to_cpu(pfn_sb->mode)) {
case PFN_MODE_RAM:
case PFN_MODE_PMEM:
break;
default:
return -ENXIO;
}
align = le32_to_cpu(pfn_sb->align);
offset = le64_to_cpu(pfn_sb->dataoff);
start_pad = le32_to_cpu(pfn_sb->start_pad);
if (align == 0)
align = 1UL << ilog2(offset);
mode = le32_to_cpu(pfn_sb->mode);
if ((le32_to_cpu(pfn_sb->page_size) > PAGE_SIZE) &&
(mode == PFN_MODE_PMEM)) {
dev_err(&nd_pfn->dev,
"init failed, page size mismatch %d\n",
le32_to_cpu(pfn_sb->page_size));
return -EOPNOTSUPP;
}
if ((le16_to_cpu(pfn_sb->page_struct_size) < sizeof(struct page)) &&
(mode == PFN_MODE_PMEM)) {
dev_err(&nd_pfn->dev,
"init failed, struct page size mismatch %d\n",
le16_to_cpu(pfn_sb->page_struct_size));
return -EOPNOTSUPP;
}
libnvdimm/dax: Pick the right alignment default when creating dax devices Allow arch to provide the supported alignments and use hugepage alignment only if we support hugepage. Right now we depend on compile time configs whereas this patch switch this to runtime discovery. Architectures like ppc64 can have THP enabled in code, but then can have hugepage size disabled by the hypervisor. This allows us to create dax devices with PAGE_SIZE alignment in this case. Existing dax namespace with alignment larger than PAGE_SIZE will fail to initialize in this specific case. We still allow fsdax namespace initialization. With respect to identifying whether to enable hugepage fault for a dax device, if THP is enabled during compile, we default to taking hugepage fault and in dax fault handler if we find the fault size > alignment we retry with PAGE_SIZE fault size. This also addresses the below failure scenario on ppc64 ndctl create-namespace --mode=devdax | grep align "align":16777216, "align":16777216 cat /sys/devices/ndbus0/region0/dax0.0/supported_alignments 65536 16777216 daxio.static-debug -z -o /dev/dax0.0 Bus error (core dumped) $ dmesg | tail lpar: Failed hash pte insert with error -4 hash-mmu: mm: Hashing failure ! EA=0x7fff17000000 access=0x8000000000000006 current=daxio hash-mmu: trap=0x300 vsid=0x22cb7a3 ssize=1 base psize=2 psize 10 pte=0xc000000501002b86 daxio[3860]: bus error (7) at 7fff17000000 nip 7fff973c007c lr 7fff973bff34 code 2 in libpmem.so.1.0.0[7fff973b0000+20000] daxio[3860]: code: 792945e4 7d494b78 e95f0098 7d494b78 f93f00a0 4800012c e93f0088 f93f0120 daxio[3860]: code: e93f00a0 f93f0128 e93f0120 e95f0128 <f9490000> e93f0088 39290008 f93f0110 The failure was due to guest kernel using wrong page size. The namespaces created with 16M alignment will appear as below on a config with 16M page size disabled. $ ndctl list -Ni [ { "dev":"namespace0.1", "mode":"fsdax", "map":"dev", "size":5351931904, "uuid":"fc6e9667-461a-4718-82b4-69b24570bddb", "align":16777216, "blockdev":"pmem0.1", "supported_alignments":[ 65536 ] }, { "dev":"namespace0.0", "mode":"fsdax", <==== devdax 16M alignment marked disabled. "map":"mem", "size":5368709120, "uuid":"a4bdf81a-f2ee-4bc6-91db-7b87eddd0484", "state":"disabled" } ] Cc: linux-mm@kvack.org Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Link: https://lore.kernel.org/r/20190905154603.10349-8-aneesh.kumar@linux.ibm.com Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2019-09-05 23:46:03 +08:00
/*
* Check whether the we support the alignment. For Dax if the
* superblock alignment is not matching, we won't initialize
* the device.
*/
if (!nd_supported_alignment(align) &&
!memcmp(pfn_sb->signature, DAX_SIG, PFN_SIG_LEN)) {
dev_err(&nd_pfn->dev, "init failed, alignment mismatch: "
"%ld:%ld\n", nd_pfn->align, align);
return -EOPNOTSUPP;
}
if (!nd_pfn->uuid) {
/*
* When probing a namepace via nd_pfn_probe() the uuid
* is NULL (see: nd_pfn_devinit()) we init settings from
* pfn_sb
*/
nd_pfn->uuid = kmemdup(pfn_sb->uuid, 16, GFP_KERNEL);
if (!nd_pfn->uuid)
return -ENOMEM;
nd_pfn->align = align;
nd_pfn->mode = mode;
} else {
/*
* When probing a pfn / dax instance we validate the
* live settings against the pfn_sb
*/
if (memcmp(nd_pfn->uuid, pfn_sb->uuid, 16) != 0)
return -ENODEV;
/*
* If the uuid validates, but other settings mismatch
* return EINVAL because userspace has managed to change
* the configuration without specifying new
* identification.
*/
if (nd_pfn->align != align || nd_pfn->mode != mode) {
dev_err(&nd_pfn->dev,
"init failed, settings mismatch\n");
dev_dbg(&nd_pfn->dev, "align: %lx:%lx mode: %d:%d\n",
nd_pfn->align, align, nd_pfn->mode,
mode);
return -EOPNOTSUPP;
}
}
if (align > nvdimm_namespace_capacity(ndns)) {
dev_err(&nd_pfn->dev, "alignment: %lx exceeds capacity %llx\n",
align, nvdimm_namespace_capacity(ndns));
return -EOPNOTSUPP;
}
/*
* These warnings are verbose because they can only trigger in
* the case where the physical address alignment of the
* namespace has changed since the pfn superblock was
* established.
*/
nsio = to_nd_namespace_io(&ndns->dev);
res = &nsio->res;
if (offset >= resource_size(res)) {
dev_err(&nd_pfn->dev, "pfn array size exceeds capacity of %s\n",
dev_name(&ndns->dev));
return -EOPNOTSUPP;
}
if ((align && !IS_ALIGNED(res->start + offset + start_pad, align))
|| !IS_ALIGNED(offset, PAGE_SIZE)) {
dev_err(&nd_pfn->dev,
"bad offset: %#llx dax disabled align: %#lx\n",
offset, align);
return -EOPNOTSUPP;
}
if (!IS_ALIGNED(res->start + le32_to_cpu(pfn_sb->start_pad),
memremap_compat_align())) {
dev_err(&nd_pfn->dev, "resource start misaligned\n");
return -EOPNOTSUPP;
}
if (!IS_ALIGNED(res->end + 1 - le32_to_cpu(pfn_sb->end_trunc),
memremap_compat_align())) {
dev_err(&nd_pfn->dev, "resource end misaligned\n");
return -EOPNOTSUPP;
}
return 0;
}
EXPORT_SYMBOL(nd_pfn_validate);
int nd_pfn_probe(struct device *dev, struct nd_namespace_common *ndns)
{
int rc;
struct nd_pfn *nd_pfn;
struct device *pfn_dev;
struct nd_pfn_sb *pfn_sb;
struct nd_region *nd_region = to_nd_region(ndns->dev.parent);
if (ndns->force_raw)
return -ENODEV;
switch (ndns->claim_class) {
case NVDIMM_CCLASS_NONE:
case NVDIMM_CCLASS_PFN:
break;
default:
return -ENODEV;
}
nvdimm_bus_lock(&ndns->dev);
nd_pfn = nd_pfn_alloc(nd_region);
pfn_dev = nd_pfn_devinit(nd_pfn, ndns);
nvdimm_bus_unlock(&ndns->dev);
if (!pfn_dev)
return -ENOMEM;
libnvdimm/pfn: fix fsdax-mode namespace info-block zero-fields At namespace creation time there is the potential for the "expected to be zero" fields of a 'pfn' info-block to be filled with indeterminate data. While the kernel buffer is zeroed on allocation it is immediately overwritten by nd_pfn_validate() filling it with the current contents of the on-media info-block location. For fields like, 'flags' and the 'padding' it potentially means that future implementations can not rely on those fields being zero. In preparation to stop using the 'start_pad' and 'end_trunc' fields for section alignment, arrange for fields that are not explicitly initialized to be guaranteed zero. Bump the minor version to indicate it is safe to assume the 'padding' and 'flags' are zero. Otherwise, this corruption is expected to benign since all other critical fields are explicitly initialized. Note The cc: stable is about spreading this new policy to as many kernels as possible not fixing an issue in those kernels. It is not until the change titled "libnvdimm/pfn: Stop padding pmem namespaces to section alignment" where this improper initialization becomes a problem. So if someone decides to backport "libnvdimm/pfn: Stop padding pmem namespaces to section alignment" (which is not tagged for stable), make sure this pre-requisite is flagged. Link: http://lkml.kernel.org/r/156092356065.979959.6681003754765958296.stgit@dwillia2-desk3.amr.corp.intel.com Fixes: 32ab0a3f5170 ("libnvdimm, pmem: 'struct page' for pmem") Signed-off-by: Dan Williams <dan.j.williams@intel.com> Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> [ppc64] Cc: <stable@vger.kernel.org> Cc: David Hildenbrand <david@redhat.com> Cc: Jane Chu <jane.chu@oracle.com> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Logan Gunthorpe <logang@deltatee.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Toshi Kani <toshi.kani@hpe.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Wei Yang <richardw.yang@linux.intel.com> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-19 06:58:36 +08:00
pfn_sb = devm_kmalloc(dev, sizeof(*pfn_sb), GFP_KERNEL);
nd_pfn = to_nd_pfn(pfn_dev);
nd_pfn->pfn_sb = pfn_sb;
rc = nd_pfn_validate(nd_pfn, PFN_SIG);
dev_dbg(dev, "pfn: %s\n", rc == 0 ? dev_name(pfn_dev) : "<none>");
if (rc < 0) {
libnvdimm: fix nvdimm_bus_lock() vs device_lock() ordering A debug patch to turn the standard device_lock() into something that lockdep can analyze yielded the following: ====================================================== [ INFO: possible circular locking dependency detected ] 4.11.0-rc4+ #106 Tainted: G O ------------------------------------------------------- lt-libndctl/1898 is trying to acquire lock: (&dev->nvdimm_mutex/3){+.+.+.}, at: [<ffffffffc023c948>] nd_attach_ndns+0x178/0x1b0 [libnvdimm] but task is already holding lock: (&nvdimm_bus->reconfig_mutex){+.+.+.}, at: [<ffffffffc022e0b1>] nvdimm_bus_lock+0x21/0x30 [libnvdimm] which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&nvdimm_bus->reconfig_mutex){+.+.+.}: lock_acquire+0xf6/0x1f0 __mutex_lock+0x88/0x980 mutex_lock_nested+0x1b/0x20 nvdimm_bus_lock+0x21/0x30 [libnvdimm] nvdimm_namespace_capacity+0x1b/0x40 [libnvdimm] nvdimm_namespace_common_probe+0x230/0x510 [libnvdimm] nd_pmem_probe+0x14/0x180 [nd_pmem] nvdimm_bus_probe+0xa9/0x260 [libnvdimm] -> #0 (&dev->nvdimm_mutex/3){+.+.+.}: __lock_acquire+0x1107/0x1280 lock_acquire+0xf6/0x1f0 __mutex_lock+0x88/0x980 mutex_lock_nested+0x1b/0x20 nd_attach_ndns+0x178/0x1b0 [libnvdimm] nd_namespace_store+0x308/0x3c0 [libnvdimm] namespace_store+0x87/0x220 [libnvdimm] In this case '&dev->nvdimm_mutex/3' mirrors '&dev->mutex'. Fix this by replacing the use of device_lock() with nvdimm_bus_lock() to protect nd_{attach,detach}_ndns() operations. Cc: <stable@vger.kernel.org> Fixes: 8c2f7e8658df ("libnvdimm: infrastructure for btt devices") Reported-by: Yi Zhang <yizhan@redhat.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2017-04-29 13:05:14 +08:00
nd_detach_ndns(pfn_dev, &nd_pfn->ndns);
put_device(pfn_dev);
} else
__nd_device_register(pfn_dev);
return rc;
}
EXPORT_SYMBOL(nd_pfn_probe);
/*
* We hotplug memory at sub-section granularity, pad the reserved area
* from the previous section base to the namespace base address.
*/
static unsigned long init_altmap_base(resource_size_t base)
{
unsigned long base_pfn = PHYS_PFN(base);
return SUBSECTION_ALIGN_DOWN(base_pfn);
}
static unsigned long init_altmap_reserve(resource_size_t base)
{
unsigned long reserve = nd_info_block_reserve() >> PAGE_SHIFT;
unsigned long base_pfn = PHYS_PFN(base);
reserve += base_pfn - SUBSECTION_ALIGN_DOWN(base_pfn);
return reserve;
}
static int __nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap)
{
mm/memremap_pages: convert to 'struct range' The 'struct resource' in 'struct dev_pagemap' is only used for holding resource span information. The other fields, 'name', 'flags', 'desc', 'parent', 'sibling', and 'child' are all unused wasted space. This is in preparation for introducing a multi-range extension of devm_memremap_pages(). The bulk of this change is unwinding all the places internal to libnvdimm that used 'struct resource' unnecessarily, and replacing instances of 'struct dev_pagemap'.res with 'struct dev_pagemap'.range. P2PDMA had a minor usage of the resource flags field, but only to report failures with "%pR". That is replaced with an open coded print of the range. [dan.carpenter@oracle.com: mm/hmm/test: use after free in dmirror_allocate_chunk()] Link: https://lkml.kernel.org/r/20200926121402.GA7467@kadam Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> [xen] Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Juergen Gross <jgross@suse.com> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brice Goglin <Brice.Goglin@inria.fr> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Hulk Robot <hulkci@huawei.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Jason Yan <yanaijie@huawei.com> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Jia He <justin.he@arm.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: kernel test robot <lkp@intel.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Wei Yang <richard.weiyang@linux.alibaba.com> Cc: Will Deacon <will@kernel.org> Link: https://lkml.kernel.org/r/159643103173.4062302.768998885691711532.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/160106115761.30709.13539840236873663620.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-14 07:50:29 +08:00
struct range *range = &pgmap->range;
struct vmem_altmap *altmap = &pgmap->altmap;
struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
u64 offset = le64_to_cpu(pfn_sb->dataoff);
u32 start_pad = __le32_to_cpu(pfn_sb->start_pad);
u32 end_trunc = __le32_to_cpu(pfn_sb->end_trunc);
u32 reserve = nd_info_block_reserve();
struct nd_namespace_common *ndns = nd_pfn->ndns;
struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
resource_size_t base = nsio->res.start + start_pad;
libnvdimm/altmap: Track namespace boundaries in altmap With PFN_MODE_PMEM namespace, the memmap area is allocated from the device area. Some architectures map the memmap area with large page size. On architectures like ppc64, 16MB page for memap mapping can map 262144 pfns. This maps a namespace size of 16G. When populating memmap region with 16MB page from the device area, make sure the allocated space is not used to map resources outside this namespace. Such usage of device area will prevent a namespace destroy. Add resource end pnf in altmap and use that to check if the memmap area allocation can map pfn outside the namespace. On ppc64 in such case we fallback to allocation from memory. This fix kernel crash reported below: [ 132.034989] WARNING: CPU: 13 PID: 13719 at mm/memremap.c:133 devm_memremap_pages_release+0x2d8/0x2e0 [ 133.464754] BUG: Unable to handle kernel data access at 0xc00c00010b204000 [ 133.464760] Faulting instruction address: 0xc00000000007580c [ 133.464766] Oops: Kernel access of bad area, sig: 11 [#1] [ 133.464771] LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries ..... [ 133.464901] NIP [c00000000007580c] vmemmap_free+0x2ac/0x3d0 [ 133.464906] LR [c0000000000757f8] vmemmap_free+0x298/0x3d0 [ 133.464910] Call Trace: [ 133.464914] [c000007cbfd0f7b0] [c0000000000757f8] vmemmap_free+0x298/0x3d0 (unreliable) [ 133.464921] [c000007cbfd0f8d0] [c000000000370a44] section_deactivate+0x1a4/0x240 [ 133.464928] [c000007cbfd0f980] [c000000000386270] __remove_pages+0x3a0/0x590 [ 133.464935] [c000007cbfd0fa50] [c000000000074158] arch_remove_memory+0x88/0x160 [ 133.464942] [c000007cbfd0fae0] [c0000000003be8c0] devm_memremap_pages_release+0x150/0x2e0 [ 133.464949] [c000007cbfd0fb70] [c000000000738ea0] devm_action_release+0x30/0x50 [ 133.464955] [c000007cbfd0fb90] [c00000000073a5a4] release_nodes+0x344/0x400 [ 133.464961] [c000007cbfd0fc40] [c00000000073378c] device_release_driver_internal+0x15c/0x250 [ 133.464968] [c000007cbfd0fc80] [c00000000072fd14] unbind_store+0x104/0x110 [ 133.464973] [c000007cbfd0fcd0] [c00000000072ee24] drv_attr_store+0x44/0x70 [ 133.464981] [c000007cbfd0fcf0] [c0000000004a32bc] sysfs_kf_write+0x6c/0xa0 [ 133.464987] [c000007cbfd0fd10] [c0000000004a1dfc] kernfs_fop_write+0x17c/0x250 [ 133.464993] [c000007cbfd0fd60] [c0000000003c348c] __vfs_write+0x3c/0x70 [ 133.464999] [c000007cbfd0fd80] [c0000000003c75d0] vfs_write+0xd0/0x250 djbw: Aneesh notes that this crash can likely be triggered in any kernel that supports 'papr_scm', so flagging that commit for -stable consideration. Fixes: b5beae5e224f ("powerpc/pseries: Add driver for PAPR SCM regions") Cc: <stable@vger.kernel.org> Reported-by: Sachin Sant <sachinp@linux.vnet.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Reviewed-by: Pankaj Gupta <pagupta@redhat.com> Tested-by: Santosh Sivaraj <santosh@fossix.org> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de> Link: https://lore.kernel.org/r/20190910062826.10041-1-aneesh.kumar@linux.ibm.com Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2019-09-10 14:28:25 +08:00
resource_size_t end = nsio->res.end - end_trunc;
struct vmem_altmap __altmap = {
.base_pfn = init_altmap_base(base),
.reserve = init_altmap_reserve(base),
libnvdimm/altmap: Track namespace boundaries in altmap With PFN_MODE_PMEM namespace, the memmap area is allocated from the device area. Some architectures map the memmap area with large page size. On architectures like ppc64, 16MB page for memap mapping can map 262144 pfns. This maps a namespace size of 16G. When populating memmap region with 16MB page from the device area, make sure the allocated space is not used to map resources outside this namespace. Such usage of device area will prevent a namespace destroy. Add resource end pnf in altmap and use that to check if the memmap area allocation can map pfn outside the namespace. On ppc64 in such case we fallback to allocation from memory. This fix kernel crash reported below: [ 132.034989] WARNING: CPU: 13 PID: 13719 at mm/memremap.c:133 devm_memremap_pages_release+0x2d8/0x2e0 [ 133.464754] BUG: Unable to handle kernel data access at 0xc00c00010b204000 [ 133.464760] Faulting instruction address: 0xc00000000007580c [ 133.464766] Oops: Kernel access of bad area, sig: 11 [#1] [ 133.464771] LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries ..... [ 133.464901] NIP [c00000000007580c] vmemmap_free+0x2ac/0x3d0 [ 133.464906] LR [c0000000000757f8] vmemmap_free+0x298/0x3d0 [ 133.464910] Call Trace: [ 133.464914] [c000007cbfd0f7b0] [c0000000000757f8] vmemmap_free+0x298/0x3d0 (unreliable) [ 133.464921] [c000007cbfd0f8d0] [c000000000370a44] section_deactivate+0x1a4/0x240 [ 133.464928] [c000007cbfd0f980] [c000000000386270] __remove_pages+0x3a0/0x590 [ 133.464935] [c000007cbfd0fa50] [c000000000074158] arch_remove_memory+0x88/0x160 [ 133.464942] [c000007cbfd0fae0] [c0000000003be8c0] devm_memremap_pages_release+0x150/0x2e0 [ 133.464949] [c000007cbfd0fb70] [c000000000738ea0] devm_action_release+0x30/0x50 [ 133.464955] [c000007cbfd0fb90] [c00000000073a5a4] release_nodes+0x344/0x400 [ 133.464961] [c000007cbfd0fc40] [c00000000073378c] device_release_driver_internal+0x15c/0x250 [ 133.464968] [c000007cbfd0fc80] [c00000000072fd14] unbind_store+0x104/0x110 [ 133.464973] [c000007cbfd0fcd0] [c00000000072ee24] drv_attr_store+0x44/0x70 [ 133.464981] [c000007cbfd0fcf0] [c0000000004a32bc] sysfs_kf_write+0x6c/0xa0 [ 133.464987] [c000007cbfd0fd10] [c0000000004a1dfc] kernfs_fop_write+0x17c/0x250 [ 133.464993] [c000007cbfd0fd60] [c0000000003c348c] __vfs_write+0x3c/0x70 [ 133.464999] [c000007cbfd0fd80] [c0000000003c75d0] vfs_write+0xd0/0x250 djbw: Aneesh notes that this crash can likely be triggered in any kernel that supports 'papr_scm', so flagging that commit for -stable consideration. Fixes: b5beae5e224f ("powerpc/pseries: Add driver for PAPR SCM regions") Cc: <stable@vger.kernel.org> Reported-by: Sachin Sant <sachinp@linux.vnet.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Reviewed-by: Pankaj Gupta <pagupta@redhat.com> Tested-by: Santosh Sivaraj <santosh@fossix.org> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de> Link: https://lore.kernel.org/r/20190910062826.10041-1-aneesh.kumar@linux.ibm.com Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2019-09-10 14:28:25 +08:00
.end_pfn = PHYS_PFN(end),
};
mm/memremap_pages: convert to 'struct range' The 'struct resource' in 'struct dev_pagemap' is only used for holding resource span information. The other fields, 'name', 'flags', 'desc', 'parent', 'sibling', and 'child' are all unused wasted space. This is in preparation for introducing a multi-range extension of devm_memremap_pages(). The bulk of this change is unwinding all the places internal to libnvdimm that used 'struct resource' unnecessarily, and replacing instances of 'struct dev_pagemap'.res with 'struct dev_pagemap'.range. P2PDMA had a minor usage of the resource flags field, but only to report failures with "%pR". That is replaced with an open coded print of the range. [dan.carpenter@oracle.com: mm/hmm/test: use after free in dmirror_allocate_chunk()] Link: https://lkml.kernel.org/r/20200926121402.GA7467@kadam Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> [xen] Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Juergen Gross <jgross@suse.com> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brice Goglin <Brice.Goglin@inria.fr> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Hulk Robot <hulkci@huawei.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Jason Yan <yanaijie@huawei.com> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Jia He <justin.he@arm.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: kernel test robot <lkp@intel.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Wei Yang <richard.weiyang@linux.alibaba.com> Cc: Will Deacon <will@kernel.org> Link: https://lkml.kernel.org/r/159643103173.4062302.768998885691711532.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/160106115761.30709.13539840236873663620.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-14 07:50:29 +08:00
*range = (struct range) {
.start = nsio->res.start + start_pad,
.end = nsio->res.end - end_trunc,
};
mm/memremap_pages: support multiple ranges per invocation In support of device-dax growing the ability to front physically dis-contiguous ranges of memory, update devm_memremap_pages() to track multiple ranges with a single reference counter and devm instance. Convert all [devm_]memremap_pages() users to specify the number of ranges they are mapping in their 'struct dev_pagemap' instance. Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Juergen Gross <jgross@suse.com> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: "Jérôme Glisse" <jglisse@redhat.co Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brice Goglin <Brice.Goglin@inria.fr> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Hulk Robot <hulkci@huawei.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Jason Yan <yanaijie@huawei.com> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Jia He <justin.he@arm.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: kernel test robot <lkp@intel.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Wei Yang <richard.weiyang@linux.alibaba.com> Cc: Will Deacon <will@kernel.org> Link: https://lkml.kernel.org/r/159643103789.4062302.18426128170217903785.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/160106116293.30709.13350662794915396198.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-14 07:50:34 +08:00
pgmap->nr_range = 1;
if (nd_pfn->mode == PFN_MODE_RAM) {
if (offset < reserve)
return -EINVAL;
nd_pfn->npfns = le64_to_cpu(pfn_sb->npfns);
} else if (nd_pfn->mode == PFN_MODE_PMEM) {
mm/memremap_pages: convert to 'struct range' The 'struct resource' in 'struct dev_pagemap' is only used for holding resource span information. The other fields, 'name', 'flags', 'desc', 'parent', 'sibling', and 'child' are all unused wasted space. This is in preparation for introducing a multi-range extension of devm_memremap_pages(). The bulk of this change is unwinding all the places internal to libnvdimm that used 'struct resource' unnecessarily, and replacing instances of 'struct dev_pagemap'.res with 'struct dev_pagemap'.range. P2PDMA had a minor usage of the resource flags field, but only to report failures with "%pR". That is replaced with an open coded print of the range. [dan.carpenter@oracle.com: mm/hmm/test: use after free in dmirror_allocate_chunk()] Link: https://lkml.kernel.org/r/20200926121402.GA7467@kadam Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> [xen] Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Juergen Gross <jgross@suse.com> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brice Goglin <Brice.Goglin@inria.fr> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Hulk Robot <hulkci@huawei.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Jason Yan <yanaijie@huawei.com> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Jia He <justin.he@arm.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: kernel test robot <lkp@intel.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Wei Yang <richard.weiyang@linux.alibaba.com> Cc: Will Deacon <will@kernel.org> Link: https://lkml.kernel.org/r/159643103173.4062302.768998885691711532.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/160106115761.30709.13539840236873663620.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-14 07:50:29 +08:00
nd_pfn->npfns = PHYS_PFN((range_len(range) - offset));
if (le64_to_cpu(nd_pfn->pfn_sb->npfns) > nd_pfn->npfns)
dev_info(&nd_pfn->dev,
"number of pfns truncated from %lld to %ld\n",
le64_to_cpu(nd_pfn->pfn_sb->npfns),
nd_pfn->npfns);
memcpy(altmap, &__altmap, sizeof(*altmap));
altmap->free = PHYS_PFN(offset - reserve);
altmap->alloc = 0;
pgmap->flags |= PGMAP_ALTMAP_VALID;
} else
return -ENXIO;
return 0;
}
static int nd_pfn_init(struct nd_pfn *nd_pfn)
{
struct nd_namespace_common *ndns = nd_pfn->ndns;
struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
resource_size_t start, size;
struct nd_region *nd_region;
unsigned long npfns, align;
u32 end_trunc;
struct nd_pfn_sb *pfn_sb;
phys_addr_t offset;
const char *sig;
u64 checksum;
int rc;
libnvdimm/pfn: fix fsdax-mode namespace info-block zero-fields At namespace creation time there is the potential for the "expected to be zero" fields of a 'pfn' info-block to be filled with indeterminate data. While the kernel buffer is zeroed on allocation it is immediately overwritten by nd_pfn_validate() filling it with the current contents of the on-media info-block location. For fields like, 'flags' and the 'padding' it potentially means that future implementations can not rely on those fields being zero. In preparation to stop using the 'start_pad' and 'end_trunc' fields for section alignment, arrange for fields that are not explicitly initialized to be guaranteed zero. Bump the minor version to indicate it is safe to assume the 'padding' and 'flags' are zero. Otherwise, this corruption is expected to benign since all other critical fields are explicitly initialized. Note The cc: stable is about spreading this new policy to as many kernels as possible not fixing an issue in those kernels. It is not until the change titled "libnvdimm/pfn: Stop padding pmem namespaces to section alignment" where this improper initialization becomes a problem. So if someone decides to backport "libnvdimm/pfn: Stop padding pmem namespaces to section alignment" (which is not tagged for stable), make sure this pre-requisite is flagged. Link: http://lkml.kernel.org/r/156092356065.979959.6681003754765958296.stgit@dwillia2-desk3.amr.corp.intel.com Fixes: 32ab0a3f5170 ("libnvdimm, pmem: 'struct page' for pmem") Signed-off-by: Dan Williams <dan.j.williams@intel.com> Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> [ppc64] Cc: <stable@vger.kernel.org> Cc: David Hildenbrand <david@redhat.com> Cc: Jane Chu <jane.chu@oracle.com> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Logan Gunthorpe <logang@deltatee.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Toshi Kani <toshi.kani@hpe.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Wei Yang <richardw.yang@linux.intel.com> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-19 06:58:36 +08:00
pfn_sb = devm_kmalloc(&nd_pfn->dev, sizeof(*pfn_sb), GFP_KERNEL);
if (!pfn_sb)
return -ENOMEM;
nd_pfn->pfn_sb = pfn_sb;
if (is_nd_dax(&nd_pfn->dev))
sig = DAX_SIG;
else
sig = PFN_SIG;
libnvdimm/pfn: fix fsdax-mode namespace info-block zero-fields At namespace creation time there is the potential for the "expected to be zero" fields of a 'pfn' info-block to be filled with indeterminate data. While the kernel buffer is zeroed on allocation it is immediately overwritten by nd_pfn_validate() filling it with the current contents of the on-media info-block location. For fields like, 'flags' and the 'padding' it potentially means that future implementations can not rely on those fields being zero. In preparation to stop using the 'start_pad' and 'end_trunc' fields for section alignment, arrange for fields that are not explicitly initialized to be guaranteed zero. Bump the minor version to indicate it is safe to assume the 'padding' and 'flags' are zero. Otherwise, this corruption is expected to benign since all other critical fields are explicitly initialized. Note The cc: stable is about spreading this new policy to as many kernels as possible not fixing an issue in those kernels. It is not until the change titled "libnvdimm/pfn: Stop padding pmem namespaces to section alignment" where this improper initialization becomes a problem. So if someone decides to backport "libnvdimm/pfn: Stop padding pmem namespaces to section alignment" (which is not tagged for stable), make sure this pre-requisite is flagged. Link: http://lkml.kernel.org/r/156092356065.979959.6681003754765958296.stgit@dwillia2-desk3.amr.corp.intel.com Fixes: 32ab0a3f5170 ("libnvdimm, pmem: 'struct page' for pmem") Signed-off-by: Dan Williams <dan.j.williams@intel.com> Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> [ppc64] Cc: <stable@vger.kernel.org> Cc: David Hildenbrand <david@redhat.com> Cc: Jane Chu <jane.chu@oracle.com> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Logan Gunthorpe <logang@deltatee.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Toshi Kani <toshi.kani@hpe.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Wei Yang <richardw.yang@linux.intel.com> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-19 06:58:36 +08:00
rc = nd_pfn_validate(nd_pfn, sig);
if (rc == 0)
return nd_pfn_clear_memmap_errors(nd_pfn);
if (rc != -ENODEV)
return rc;
/* no info block, do init */;
libnvdimm/pfn: fix fsdax-mode namespace info-block zero-fields At namespace creation time there is the potential for the "expected to be zero" fields of a 'pfn' info-block to be filled with indeterminate data. While the kernel buffer is zeroed on allocation it is immediately overwritten by nd_pfn_validate() filling it with the current contents of the on-media info-block location. For fields like, 'flags' and the 'padding' it potentially means that future implementations can not rely on those fields being zero. In preparation to stop using the 'start_pad' and 'end_trunc' fields for section alignment, arrange for fields that are not explicitly initialized to be guaranteed zero. Bump the minor version to indicate it is safe to assume the 'padding' and 'flags' are zero. Otherwise, this corruption is expected to benign since all other critical fields are explicitly initialized. Note The cc: stable is about spreading this new policy to as many kernels as possible not fixing an issue in those kernels. It is not until the change titled "libnvdimm/pfn: Stop padding pmem namespaces to section alignment" where this improper initialization becomes a problem. So if someone decides to backport "libnvdimm/pfn: Stop padding pmem namespaces to section alignment" (which is not tagged for stable), make sure this pre-requisite is flagged. Link: http://lkml.kernel.org/r/156092356065.979959.6681003754765958296.stgit@dwillia2-desk3.amr.corp.intel.com Fixes: 32ab0a3f5170 ("libnvdimm, pmem: 'struct page' for pmem") Signed-off-by: Dan Williams <dan.j.williams@intel.com> Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> [ppc64] Cc: <stable@vger.kernel.org> Cc: David Hildenbrand <david@redhat.com> Cc: Jane Chu <jane.chu@oracle.com> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Logan Gunthorpe <logang@deltatee.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Toshi Kani <toshi.kani@hpe.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Wei Yang <richardw.yang@linux.intel.com> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-19 06:58:36 +08:00
memset(pfn_sb, 0, sizeof(*pfn_sb));
nd_region = to_nd_region(nd_pfn->dev.parent);
if (nd_region->ro) {
dev_info(&nd_pfn->dev,
"%s is read-only, unable to init metadata\n",
dev_name(&nd_region->dev));
return -ENXIO;
}
/*
* Note, we use 64 here for the standard size of struct page,
* debugging options may cause it to be larger in which case the
* implementation will limit the pfns advertised through
* ->direct_access() to those that are included in the memmap.
*/
start = nsio->res.start;
size = resource_size(&nsio->res);
npfns = PHYS_PFN(size - SZ_8K);
align = max(nd_pfn->align, memremap_compat_align());
/*
* When @start is misaligned fail namespace creation. See
* the 'struct nd_pfn_sb' commentary on why ->start_pad is not
* an option.
*/
if (!IS_ALIGNED(start, memremap_compat_align())) {
dev_err(&nd_pfn->dev, "%s: start %pa misaligned to %#lx\n",
dev_name(&ndns->dev), &start,
memremap_compat_align());
return -EINVAL;
}
end_trunc = start + size - ALIGN_DOWN(start + size, align);
if (nd_pfn->mode == PFN_MODE_PMEM) {
/*
* The altmap should be padded out to the block size used
* when populating the vmemmap. This *should* be equal to
* PMD_SIZE for most architectures.
*
* Also make sure size of struct page is less than 64. We
* want to make sure we use large enough size here so that
* we don't have a dynamic reserve space depending on
* struct page size. But we also want to make sure we notice
* when we end up adding new elements to struct page.
*/
BUILD_BUG_ON(sizeof(struct page) > MAX_STRUCT_PAGE_SIZE);
offset = ALIGN(start + SZ_8K + MAX_STRUCT_PAGE_SIZE * npfns, align)
- start;
} else if (nd_pfn->mode == PFN_MODE_RAM)
offset = ALIGN(start + SZ_8K, align) - start;
else
return -ENXIO;
if (offset >= size) {
dev_err(&nd_pfn->dev, "%s unable to satisfy requested alignment\n",
dev_name(&ndns->dev));
return -ENXIO;
}
npfns = PHYS_PFN(size - offset - end_trunc);
pfn_sb->mode = cpu_to_le32(nd_pfn->mode);
pfn_sb->dataoff = cpu_to_le64(offset);
pfn_sb->npfns = cpu_to_le64(npfns);
memcpy(pfn_sb->signature, sig, PFN_SIG_LEN);
memcpy(pfn_sb->uuid, nd_pfn->uuid, 16);
memcpy(pfn_sb->parent_uuid, nd_dev_to_uuid(&ndns->dev), 16);
pfn_sb->version_major = cpu_to_le16(1);
pfn_sb->version_minor = cpu_to_le16(4);
pfn_sb->end_trunc = cpu_to_le32(end_trunc);
pfn_sb->align = cpu_to_le32(nd_pfn->align);
pfn_sb->page_struct_size = cpu_to_le16(MAX_STRUCT_PAGE_SIZE);
pfn_sb->page_size = cpu_to_le32(PAGE_SIZE);
checksum = nd_sb_checksum((struct nd_gen_sb *) pfn_sb);
pfn_sb->checksum = cpu_to_le64(checksum);
rc = nd_pfn_clear_memmap_errors(nd_pfn);
if (rc)
return rc;
return nvdimm_write_bytes(ndns, SZ_4K, pfn_sb, sizeof(*pfn_sb), 0);
}
/*
* Determine the effective resource range and vmem_altmap from an nd_pfn
* instance.
*/
int nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap)
{
int rc;
if (!nd_pfn->uuid || !nd_pfn->ndns)
return -ENODEV;
rc = nd_pfn_init(nd_pfn);
if (rc)
return rc;
/* we need a valid pfn_sb before we can init a dev_pagemap */
return __nvdimm_setup_pfn(nd_pfn, pgmap);
}
EXPORT_SYMBOL_GPL(nvdimm_setup_pfn);