[PATCH] libnvdimm: fix namespace object confusion in is_uuid_busy()
by Dan Williams
When btt devices were re-worked to be child devices of regions this
routine was overlooked. It mistakenly attempts to_nd_namespace_pmem()
or to_nd_namespace_blk() conversions on btt and pfn devices. By luck to
date we have happened to be hitting valid memory leading to a uuid
miscompare, but a recent change to struct nd_namespace_common causes:
BUG: unable to handle kernel NULL pointer dereference at 0000000000000001
IP: [<ffffffff814610dc>] memcmp+0xc/0x40
[..]
Call Trace:
[<ffffffffa0028631>] is_uuid_busy+0xc1/0x2a0 [libnvdimm]
[<ffffffffa0028570>] ? to_nd_blk_region+0x50/0x50 [libnvdimm]
[<ffffffff8158c9c0>] device_for_each_child+0x50/0x90
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Dan Williams <dan.j.williams(a)intel.com>
---
drivers/nvdimm/namespace_devs.c | 53 +++++++++++++++++++++++++++++++++++++
drivers/nvdimm/region_devs.c | 56 ---------------------------------------
2 files changed, 53 insertions(+), 56 deletions(-)
diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
index ee6dee41155a..8ebfcaae3f5a 100644
--- a/drivers/nvdimm/namespace_devs.c
+++ b/drivers/nvdimm/namespace_devs.c
@@ -77,6 +77,59 @@ static bool is_namespace_io(struct device *dev)
return dev ? dev->type == &namespace_io_device_type : false;
}
+static int is_uuid_busy(struct device *dev, void *data)
+{
+ u8 *uuid1 = data, *uuid2 = NULL;
+
+ if (is_namespace_pmem(dev)) {
+ struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
+
+ uuid2 = nspm->uuid;
+ } else if (is_namespace_blk(dev)) {
+ struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
+
+ uuid2 = nsblk->uuid;
+ } else if (is_nd_btt(dev)) {
+ struct nd_btt *nd_btt = to_nd_btt(dev);
+
+ uuid2 = nd_btt->uuid;
+ } else if (is_nd_pfn(dev)) {
+ struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+
+ uuid2 = nd_pfn->uuid;
+ }
+
+ if (uuid2 && memcmp(uuid1, uuid2, NSLABEL_UUID_LEN) == 0)
+ return -EBUSY;
+
+ return 0;
+}
+
+static int is_namespace_uuid_busy(struct device *dev, void *data)
+{
+ if (is_nd_pmem(dev) || is_nd_blk(dev))
+ return device_for_each_child(dev, data, is_uuid_busy);
+ return 0;
+}
+
+/**
+ * nd_is_uuid_unique - verify that no other namespace has @uuid
+ * @dev: any device on a nvdimm_bus
+ * @uuid: uuid to check
+ */
+bool nd_is_uuid_unique(struct device *dev, u8 *uuid)
+{
+ struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
+
+ if (!nvdimm_bus)
+ return false;
+ WARN_ON_ONCE(!is_nvdimm_bus_locked(&nvdimm_bus->dev));
+ if (device_for_each_child(&nvdimm_bus->dev, uuid,
+ is_namespace_uuid_busy) != 0)
+ return false;
+ return true;
+}
+
bool pmem_should_map_pages(struct device *dev)
{
struct nd_region *nd_region = to_nd_region(dev->parent);
diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
index 9c632f73915e..139bf71ca549 100644
--- a/drivers/nvdimm/region_devs.c
+++ b/drivers/nvdimm/region_devs.c
@@ -134,62 +134,6 @@ int nd_region_to_nstype(struct nd_region *nd_region)
}
EXPORT_SYMBOL(nd_region_to_nstype);
-static int is_uuid_busy(struct device *dev, void *data)
-{
- struct nd_region *nd_region = to_nd_region(dev->parent);
- u8 *uuid = data;
-
- switch (nd_region_to_nstype(nd_region)) {
- case ND_DEVICE_NAMESPACE_PMEM: {
- struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
-
- if (!nspm->uuid)
- break;
- if (memcmp(uuid, nspm->uuid, NSLABEL_UUID_LEN) == 0)
- return -EBUSY;
- break;
- }
- case ND_DEVICE_NAMESPACE_BLK: {
- struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
-
- if (!nsblk->uuid)
- break;
- if (memcmp(uuid, nsblk->uuid, NSLABEL_UUID_LEN) == 0)
- return -EBUSY;
- break;
- }
- default:
- break;
- }
-
- return 0;
-}
-
-static int is_namespace_uuid_busy(struct device *dev, void *data)
-{
- if (is_nd_pmem(dev) || is_nd_blk(dev))
- return device_for_each_child(dev, data, is_uuid_busy);
- return 0;
-}
-
-/**
- * nd_is_uuid_unique - verify that no other namespace has @uuid
- * @dev: any device on a nvdimm_bus
- * @uuid: uuid to check
- */
-bool nd_is_uuid_unique(struct device *dev, u8 *uuid)
-{
- struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
-
- if (!nvdimm_bus)
- return false;
- WARN_ON_ONCE(!is_nvdimm_bus_locked(&nvdimm_bus->dev));
- if (device_for_each_child(&nvdimm_bus->dev, uuid,
- is_namespace_uuid_busy) != 0)
- return false;
- return true;
-}
-
static ssize_t size_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
4 years, 5 months
You have received fax, document 000725278
by Interfax
You have a new fax!
Please check your fax document in the attachment to this e-mail.
Filesize: 108 Kb
Filename: scan000725278.doc
Date of scan: Tue, 5 Jan 2016 06:19:21 +0300
Scan duration: 22 seconds
Number of pages: 12
Resolution: 300 DPI
Sender: Dwight Hawkins
Thank you for using Interfax!
4 years, 5 months
You have received a new fax, document 00204436
by Interfax
A new fax document for you.
Please check your fax document in the attachment to this e-mail.
Filesize: 102 Kb
Scanned in: 6 seconds
Fax name: scan-00204436.doc
Resolution: 600 DPI
Scanned by: Cory Blair
Scan date: Tue, 5 Jan 2016 08:05:08 +0300
Pages number: 10
Thanks for choosing Interfax!
4 years, 5 months
[PATCH v3 17/17] ACPI/EINJ: Allow memory error injection to NVDIMM
by Toshi Kani
In the case of memory error injection, einj_error_inject() checks
if a target address is System RAM. Change this check to allow
injecting a memory error to NVDIMM by calling region_intersects()
with IORES_DESC_PERSISTENT_MEMORY. This enables memory error
testing on both System RAM and NVDIMM.
In addition, page_is_ram() is replaced with region_intersects()
with IORESOURCE_SYSTEM_RAM, so that it can verify a target address
range with the requested size.
Cc: Rafael J. Wysocki <rjw(a)rjwysocki.net>
Cc: Borislav Petkov <bp(a)alien8.de>
Cc: Vishal Verma <vishal.l.verma(a)intel.com>
Cc: linux-nvdimm(a)lists.01.org
Cc: linux-acpi(a)vger.kernel.org
Acked-by: Tony Luck <tony.luck(a)intel.com>
Reviewed-by: Dan Williams <dan.j.williams(a)intel.com>
Signed-off-by: Toshi Kani <toshi.kani(a)hpe.com>
---
drivers/acpi/apei/einj.c | 15 +++++++++++----
1 file changed, 11 insertions(+), 4 deletions(-)
diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c
index 0431883..16cae66 100644
--- a/drivers/acpi/apei/einj.c
+++ b/drivers/acpi/apei/einj.c
@@ -519,7 +519,7 @@ static int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
u64 param3, u64 param4)
{
int rc;
- unsigned long pfn;
+ u64 base_addr, size;
/* If user manually set "flags", make sure it is legal */
if (flags && (flags &
@@ -545,10 +545,17 @@ static int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
/*
* Disallow crazy address masks that give BIOS leeway to pick
* injection address almost anywhere. Insist on page or
- * better granularity and that target address is normal RAM.
+ * better granularity and that target address is normal RAM or
+ * NVDIMM.
*/
- pfn = PFN_DOWN(param1 & param2);
- if (!page_is_ram(pfn) || ((param2 & PAGE_MASK) != PAGE_MASK))
+ base_addr = param1 & param2;
+ size = ~param2 + 1;
+
+ if (((param2 & PAGE_MASK) != PAGE_MASK) ||
+ ((region_intersects(base_addr, size, IORESOURCE_SYSTEM_RAM,
+ IORES_DESC_NONE) != REGION_INTERSECTS) &&
+ (region_intersects(base_addr, size, IORESOURCE_MEM,
+ IORES_DESC_PERSISTENT_MEMORY) != REGION_INTERSECTS)))
return -EINVAL;
inject:
4 years, 5 months
[PATCH v2 0/8] Support for transparent PUD pages for DAX files
by Matthew Wilcox
From: Matthew Wilcox <willy(a)linux.intel.com>
We have customer demand to use 1GB pages to map DAX files. Unlike the 2MB
page support, the Linux MM does not currently support PUD pages, so I have
attempted to add support for the necessary pieces for DAX huge PUD pages.
Filesystems still need work to allocate 1GB pages. With ext4, I can
only get 16MB of contiguous space, although it is aligned. With XFS,
I can get 80MB less than 1GB, and it's not aligned. The XFS problem
may be due to the small amount of RAM in my test machine.
This patch set is against something approximately current -mm. I'd like
to thank Dave Chinner & Kirill Shutemov for their reviews of v1.
The conversion of pmd_fault & pud_fault to huge_fault is thanks to
Dave's poking, and Kirill spotted a couple of problems in the MM code.
Version 2 of the patch set is about 200 lines smaller (1016 insertions,
23 deletions in v1).
I've done some light testing using a program to mmap a block device
with DAX enabled, calling mincore() and examining /proc/smaps and
/proc/pagemap.
Matthew Wilcox (8):
mm: Convert an open-coded VM_BUG_ON_VMA
mm,fs,dax: Change ->pmd_fault to ->huge_fault
mm: Add optional support for PUD-sized transparent hugepages
mincore: Add support for PUDs
procfs: Add support for PUDs to smaps, clear_refs and pagemap
x86: Add support for PUD-sized transparent hugepages
dax: Support for transparent PUD pages
ext4: Support for PUD-sized transparent huge pages
Documentation/filesystems/dax.txt | 12 +-
arch/Kconfig | 3 +
arch/x86/Kconfig | 1 +
arch/x86/include/asm/paravirt.h | 11 ++
arch/x86/include/asm/paravirt_types.h | 2 +
arch/x86/include/asm/pgtable.h | 95 ++++++++++
arch/x86/include/asm/pgtable_64.h | 13 ++
arch/x86/kernel/paravirt.c | 1 +
arch/x86/mm/pgtable.c | 31 ++++
fs/block_dev.c | 10 +-
fs/dax.c | 316 +++++++++++++++++++++++++---------
fs/ext2/file.c | 27 +--
fs/ext4/file.c | 60 +++----
fs/proc/task_mmu.c | 109 ++++++++++++
fs/xfs/xfs_file.c | 25 ++-
fs/xfs/xfs_trace.h | 2 +-
include/asm-generic/pgtable.h | 62 ++++++-
include/asm-generic/tlb.h | 14 ++
include/linux/dax.h | 17 --
include/linux/huge_mm.h | 52 +++++-
include/linux/mm.h | 50 +++++-
include/linux/mmu_notifier.h | 13 ++
mm/huge_memory.c | 151 ++++++++++++++++
mm/memory.c | 101 +++++++++--
mm/mincore.c | 13 ++
mm/pagewalk.c | 19 +-
mm/pgtable-generic.c | 14 ++
27 files changed, 1008 insertions(+), 216 deletions(-)
--
2.6.4
4 years, 5 months
[PATCH v6 0/4] Machine check recovery when kernel accesses poison
by Tony Luck
This series is initially targeted at the folks doing filesystems
on top of NVDIMMs. They really want to be able to return -EIO
when there is a h/w error (just like spinning rust, and SSD does).
I plan to use the same infrastructure to write a machine check aware
"copy_from_user()" that will SIGBUS the calling application when a
syscall touches poison in user space (just like we do when the application
touches the poison itself).
Changes V5-V6
Andy: Provoked massive re-write by providing what is now part1 of this
patch series. This frees up two bits in the exception table
fixup field that can be used to tag exception table entries
as different "classes". This means we don't need my separate
exception table fro machine checks. Also avoids duplicating
fixup actions for #PF and #MC cases that were in version 5.
Andy: Use C99 array initializers to tie the various class fixup
functions back to the defintions of each class. Also give the
functions meanningful names (not fixup_class0() etc.).
Boris: Cleaned up my lousy assembly code removing many spurious 'l'
modifiers on instructions.
Boris: Provided some helper functions for the machine check severity
calculation that make the code more readable.
Boris: Have __mcsafe_copy() return a structure with the 'remaining bytes'
in a separate field from the fault indicator. Boris had suggested
Linux -EFAULT/-EINVAL ... but I thought it made more sense to return
the exception number (X86_TRAP_MC, etc.) This finally kills off
BIT(63) which has been controversial throughout all the early versions
of this patch series.
Changes V4-V5
Tony: Extended __mcsafe_copy() to have fixup entries for both machine
check and page fault.
Changes V3-V4:
Andy: Simplify fixup_mcexception() by dropping used-once local variable
Andy: "Reviewed-by" tag added to part1
Boris: Moved new functions to memcpy_64.S and declaration to asm/string_64.h
Boris: Changed name s/mcsafe_memcpy/__mcsafe_copy/ to make it clear that this
is an internal function and that return value doesn't follow memcpy() semantics.
Boris: "Reviewed-by" tag added to parts 1&2
Changes V2-V3:
Andy: Don't hack "regs->ax = BIT(63) | addr;" in the machine check
handler. Now have better fixup code that computes the number
of remaining bytes (just like page-fault fixup).
Andy: #define for BIT(63). Done, plus couple of extra macros using it.
Boris: Don't clutter up generic code (like mm/extable.c) with this.
I moved everything under arch/x86 (the asm-generic change is
a more generic #define).
Boris: Dependencies for CONFIG_MCE_KERNEL_RECOVERY are too generic.
I made it a real menu item with default "n". Dan Williams
will use "select MCE_KERNEL_RECOVERY" from his persistent
filesystem code.
Boris: Simplify conditionals in mce.c by moving tolerant/kill_it
checks earlier, with a skip to end if they aren't set.
Boris: Miscellaneous grammar/punctuation. Fixed.
Boris: Don't leak spurious __start_mcextable symbols into kernels
that didn't configure MCE_KERNEL_RECOVERY. Done.
Tony: New code doesn't belong in user_copy_64.S/uaccess*.h. Moved
to new .S/.h files
Elliott:Cacheing behavior non-optimal. Could use movntdqa, vmovntdqa
or vmovntdqa on source addresses. I didn't fix this yet. Think
of the current mcsafe_memcpy() as the first of several functions.
This one is useful for small copies (meta-data) where the overhead
of saving SSE/AVX state isn't justified.
Changes V1->V2:
0-day: Reported build errors and warnings on 32-bit systems. Fixed
0-day: Reported bloat to tinyconfig. Fixed
Boris: Suggestions to use extra macros to reduce code duplication in _ASM_*EXTABLE. Done
Boris: Re-write "tolerant==3" check to reduce indentation level. See below.
Andy: Check IP is valid before searching kernel exception tables. Done.
Andy: Explain use of BIT(63) on return value from mcsafe_memcpy(). Done (added decode macros).
Andy: Untangle mess of code in tail of do_machine_check() to make it
clear what is going on (e.g. that we only enter the ist_begin_non_atomic()
if we were called from user code, not from kernel!). Done.
Andy Lutomirski (1):
x86: Clean up extable entry format (and free up a bit)
Tony Luck (3):
x86: Cleanup and add a new exception class
x86, mce: Check for faults tagged in EXTABLE_CLASS_FAULT exception
table entries
x86, mce: Add __mcsafe_copy()
arch/x86/Kconfig | 10 +++
arch/x86/include/asm/asm.h | 80 ++++++++++++------
arch/x86/include/asm/string_64.h | 10 +++
arch/x86/include/asm/uaccess.h | 17 +++-
arch/x86/kernel/cpu/mcheck/mce-severity.c | 32 ++++++-
arch/x86/kernel/cpu/mcheck/mce.c | 71 ++++++++--------
arch/x86/kernel/kprobes/core.c | 2 +-
arch/x86/kernel/traps.c | 6 +-
arch/x86/kernel/x8664_ksyms_64.c | 4 +
arch/x86/lib/memcpy_64.S | 136 ++++++++++++++++++++++++++++++
arch/x86/mm/extable.c | 66 ++++++++++-----
arch/x86/mm/fault.c | 2 +-
12 files changed, 347 insertions(+), 89 deletions(-)
--
2.1.4
4 years, 5 months
[PATCH v2 14/16] x86, nvdimm, kexec: Use walk_iomem_res_desc() for iomem search
by Toshi Kani
Change to call walk_iomem_res_desc() for searching resource entries
with the following names:
"ACPI Tables"
"ACPI Non-volatile Storage"
"Persistent Memory (legacy)"
"Crash kernel"
Note, the caller of walk_iomem_res() with "GART" is left unchanged
because this entry may be initialized by out-of-tree drivers, which
do not have 'desc' set to IORES_DESC_GART.
Cc: Borislav Petkov <bp(a)alien8.de>
Cc: Dan Williams <dan.j.williams(a)intel.com>
Cc: Dave Young <dyoung(a)redhat.com>
Cc: x86(a)kernel.org
Cc: linux-nvdimm(a)lists.01.org
Signed-off-by: Toshi Kani <toshi.kani(a)hpe.com>
---
arch/x86/kernel/crash.c | 4 ++--
arch/x86/kernel/pmem.c | 4 ++--
drivers/nvdimm/e820.c | 2 +-
kernel/kexec_file.c | 8 ++++----
4 files changed, 9 insertions(+), 9 deletions(-)
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 2c1910f..082373b 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -588,12 +588,12 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params)
/* Add ACPI tables */
cmd.type = E820_ACPI;
flags = IORESOURCE_MEM | IORESOURCE_BUSY;
- walk_iomem_res("ACPI Tables", flags, 0, -1, &cmd,
+ walk_iomem_res_desc(IORES_DESC_ACPI_TABLES, flags, 0, -1, &cmd,
memmap_entry_callback);
/* Add ACPI Non-volatile Storage */
cmd.type = E820_NVS;
- walk_iomem_res("ACPI Non-volatile Storage", flags, 0, -1, &cmd,
+ walk_iomem_res_desc(IORES_DESC_ACPI_NV_STORAGE, flags, 0, -1, &cmd,
memmap_entry_callback);
/* Add crashk_low_res region */
diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c
index 14415af..92f7014 100644
--- a/arch/x86/kernel/pmem.c
+++ b/arch/x86/kernel/pmem.c
@@ -13,11 +13,11 @@ static int found(u64 start, u64 end, void *data)
static __init int register_e820_pmem(void)
{
- char *pmem = "Persistent Memory (legacy)";
struct platform_device *pdev;
int rc;
- rc = walk_iomem_res(pmem, IORESOURCE_MEM, 0, -1, NULL, found);
+ rc = walk_iomem_res_desc(IORES_DESC_PERSISTENT_MEMORY_LEGACY,
+ IORESOURCE_MEM, 0, -1, NULL, found);
if (rc <= 0)
return 0;
diff --git a/drivers/nvdimm/e820.c b/drivers/nvdimm/e820.c
index b0045a5..95825b3 100644
--- a/drivers/nvdimm/e820.c
+++ b/drivers/nvdimm/e820.c
@@ -55,7 +55,7 @@ static int e820_pmem_probe(struct platform_device *pdev)
for (p = iomem_resource.child; p ; p = p->sibling) {
struct nd_region_desc ndr_desc;
- if (strncmp(p->name, "Persistent Memory (legacy)", 26) != 0)
+ if (p->desc != IORES_DESC_PERSISTENT_MEMORY_LEGACY)
continue;
memset(&ndr_desc, 0, sizeof(ndr_desc));
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index c245085..e2bd737 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -522,10 +522,10 @@ int kexec_add_buffer(struct kimage *image, char *buffer, unsigned long bufsz,
/* Walk the RAM ranges and allocate a suitable range for the buffer */
if (image->type == KEXEC_TYPE_CRASH)
- ret = walk_iomem_res("Crash kernel",
- IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY,
- crashk_res.start, crashk_res.end, kbuf,
- locate_mem_hole_callback);
+ ret = walk_iomem_res_desc(IORES_DESC_CRASH_KERNEL,
+ IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY,
+ crashk_res.start, crashk_res.end, kbuf,
+ locate_mem_hole_callback);
else
ret = walk_system_ram_res(0, -1, kbuf,
locate_mem_hole_callback);
4 years, 5 months
[PATCH 0/8] Support for transparent PUD pages
by Matthew Wilcox
From: Matthew Wilcox <willy(a)linux.intel.com>
We have customer demand to use 1GB pages to map DAX files. Unlike the 2MB
page support, the Linux MM does not currently support PUD pages, so I have
attempted to add support for the necessary pieces for DAX huge PUD pages.
Filesystem support is a bit sticky. I have not been able to persuade ext4
to give me more than 16MB of contiguous space, although it is aligned.
XFS will give me 80MB short of 1GB, but it's not aligned. I'm in no
hurry to get patches 7 & 8 merged until the block allocation problem is
solved in those filesystems.
This patch set is against something approximately current -mm. At this
point, I would be most grateful for MM developers to give feedback on
the first three patches. Review from X86 maintainers on patch 4 would
also be welcome. I'd like to thank Ross Zwisler for his helpful review
during development.
I've done some light testing using a program to mmap a block device
with DAX enabled, calling mincore() and examining /proc/smaps and
/proc/pagemap.
Matthew Wilcox (8):
mm: Add optional support for PUD-sized transparent hugepages
mincore: Add support for PUDs
procfs: Add support for PUDs to smaps, clear_refs and pagemap
x86: Add support for PUD-sized transparent hugepages
dax: Support for transparent PUD pages
block_dev: Support PUD DAX mappings
xfs: Support for transparent PUD pages
ext4: Transparent support for PUD-sized transparent huge pages
arch/Kconfig | 3 +
arch/x86/Kconfig | 1 +
arch/x86/include/asm/paravirt.h | 11 ++
arch/x86/include/asm/paravirt_types.h | 2 +
arch/x86/include/asm/pgtable.h | 95 ++++++++++++++
arch/x86/include/asm/pgtable_64.h | 13 ++
arch/x86/kernel/paravirt.c | 1 +
arch/x86/mm/pgtable.c | 31 +++++
fs/block_dev.c | 7 +
fs/dax.c | 239 +++++++++++++++++++++++++++++++---
fs/ext4/file.c | 37 ++++++
fs/proc/task_mmu.c | 109 ++++++++++++++++
fs/xfs/xfs_file.c | 33 +++++
fs/xfs/xfs_trace.h | 1 +
include/asm-generic/pgtable.h | 62 ++++++++-
include/asm-generic/tlb.h | 14 ++
include/linux/dax.h | 21 +++
include/linux/huge_mm.h | 52 +++++++-
include/linux/mm.h | 30 +++++
include/linux/mmu_notifier.h | 13 ++
mm/huge_memory.c | 151 +++++++++++++++++++++
mm/memory.c | 67 ++++++++++
mm/mincore.c | 13 ++
mm/pagewalk.c | 19 ++-
mm/pgtable-generic.c | 14 ++
25 files changed, 1016 insertions(+), 23 deletions(-)
--
2.6.2
4 years, 5 months
[PATCH] ndctl: fix test file paths, fix test bug
by Ross Zwisler
Fix some paths that were recently changed from using 'lib' to 'test'.
Also provide another argument to open() in the dax-pmd.c test so that if
the file is created via O_CREAT, it doesn't end up with zeroed out
permissions which would make it unusable.
Signed-off-by: Ross Zwisler <ross.zwisler(a)linux.intel.com>
---
This patch is against the current 'pending' branch tip on github:
4872e0175a12 ("ndctl: create namespace")
---
test/dax-pmd.c | 3 ++-
test/dax.sh | 4 ++--
test/mmap.sh | 2 +-
3 files changed, 5 insertions(+), 4 deletions(-)
diff --git a/test/dax-pmd.c b/test/dax-pmd.c
index bf21160..ff0c70e 100644
--- a/test/dax-pmd.c
+++ b/test/dax-pmd.c
@@ -89,7 +89,8 @@ static int test_pmd(int fd)
break;
}
- fd2 = open(TEST_FILE, O_CREAT|O_TRUNC|O_DIRECT|O_RDWR);
+ fd2 = open(TEST_FILE, O_CREAT|O_TRUNC|O_DIRECT|O_RDWR,
+ DEFFILEMODE);
if (fd2 < 0) {
faili(i);
munmap(addr, 2*HPAGE_SIZE);
diff --git a/test/dax.sh b/test/dax.sh
index e83e76d..c5fce47 100755
--- a/test/dax.sh
+++ b/test/dax.sh
@@ -24,11 +24,11 @@ DEV=$(test/dax-dev)
mkfs.ext4 $DEV
mount $DEV $MNT -o dax
fallocate -l 1GiB $MNT/$FILE
-lib/test-dax-pmd $MNT/$FILE
+test/dax-pmd $MNT/$FILE
umount $MNT
mkfs.xfs -f $DEV
mount $DEV $MNT -o dax
fallocate -l 1GiB $MNT/$FILE
-lib/test-dax-pmd $MNT/$FILE
+test/dax-pmd $MNT/$FILE
umount $MNT
diff --git a/test/mmap.sh b/test/mmap.sh
index 84725ab..745962b 100755
--- a/test/mmap.sh
+++ b/test/mmap.sh
@@ -2,7 +2,7 @@
MNT=test_mmap_mnt
FILE=image
DEV=""
-TEST=lib/test-mmap
+TEST=test/mmap
err() {
rc=1
--
2.5.0
4 years, 5 months
[PATCH] ext2, ext4: include filesystem block size in error messages
by Robert Elliott
Print the problematic value in messages about the filesystem
block size.
Normalize all of the blocksize messages that use "blocksize" to
use "filesystem block size". This helps distinguish this block size
from the underlying block device's logical block size (i.e.,
sector size) and physical block size.
Example old messages:
EXT2-fs (pmem0): unable to set blocksize
EXT4-fs (pmem0): error: unsupported blocksize for dax
EXT4-fs (pmem0): unsupported blocksize for fs encryption
EXT2-fs (pmem0): bad blocksize %d
Example new message:
EXT4-fs (pmem0): error: unsupported filesystem block size 2048 for dax
Signed-off-by: Robert Elliott <elliott(a)hpe.com>
---
fs/ext2/super.c | 17 +++++++++++------
fs/ext4/super.c | 33 ++++++++++++++++++++-------------
2 files changed, 31 insertions(+), 19 deletions(-)
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 748d35a..1186a5b 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -31,6 +31,7 @@
#include <linux/mount.h>
#include <linux/log2.h>
#include <linux/quotaops.h>
+#include <linux/stringify.h>
#include <asm/uaccess.h>
#include "ext2.h"
#include "xattr.h"
@@ -822,7 +823,9 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
*/
blocksize = sb_min_blocksize(sb, BLOCK_SIZE);
if (!blocksize) {
- ext2_msg(sb, KERN_ERR, "error: unable to set blocksize");
+ ext2_msg(sb, KERN_ERR,
+ "error: unable to set filesystem block size "
+ __stringify(BLOCK_SIZE));
goto failed_sbi;
}
@@ -921,7 +924,8 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
if (sbi->s_mount_opt & EXT2_MOUNT_DAX) {
if (blocksize != PAGE_SIZE) {
ext2_msg(sb, KERN_ERR,
- "error: unsupported blocksize for dax");
+ "error: unsupported filesystem block size %d for dax",
+ blocksize);
goto failed_mount;
}
if (!sb->s_bdev->bd_disk->fops->direct_access) {
@@ -937,7 +941,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
if (!sb_set_blocksize(sb, blocksize)) {
ext2_msg(sb, KERN_ERR,
- "error: bad blocksize %d", blocksize);
+ "error: bad filesystem block size %d", blocksize);
goto failed_sbi;
}
@@ -1007,14 +1011,15 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
if (sb->s_blocksize != bh->b_size) {
if (!silent)
- ext2_msg(sb, KERN_ERR, "error: unsupported blocksize");
+ ext2_msg(sb, KERN_ERR,
+ "error: unsupported filesystem block size %lu",
+ sb->s_blocksize);
goto failed_mount;
}
if (sb->s_blocksize != sbi->s_frag_size) {
ext2_msg(sb, KERN_ERR,
- "error: fragsize %lu != blocksize %lu"
- "(not supported yet)",
+ "error: fragsize %lu != filesystem block size %lu (not supported yet)",
sbi->s_frag_size, sb->s_blocksize);
goto failed_mount;
}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index c9ab67d..9e1c049 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -42,6 +42,7 @@
#include <linux/kthread.h>
#include <linux/freezer.h>
+#include <linux/stringify.h>
#include "ext4.h"
#include "ext4_extents.h" /* Needed for trace points definition */
@@ -1750,8 +1751,9 @@ static int parse_options(char *options, struct super_block *sb,
BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);
if (blocksize < PAGE_CACHE_SIZE) {
- ext4_msg(sb, KERN_ERR, "can't mount with "
- "dioread_nolock if block size != PAGE_SIZE");
+ ext4_msg(sb, KERN_ERR,
+ "can't mount with dioread_nolock if filesystem block size %d != PAGE_SIZE",
+ blocksize);
return 0;
}
}
@@ -3147,7 +3149,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
ret = -EINVAL;
blocksize = sb_min_blocksize(sb, EXT4_MIN_BLOCK_SIZE);
if (!blocksize) {
- ext4_msg(sb, KERN_ERR, "unable to set blocksize");
+ ext4_msg(sb, KERN_ERR,
+ "unable to set filesystem block size "
+ __stringify(EXT4_MIN_BLOCK_SIZE));
goto out_fail;
}
@@ -3367,14 +3371,15 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
if (blocksize < EXT4_MIN_BLOCK_SIZE ||
blocksize > EXT4_MAX_BLOCK_SIZE) {
ext4_msg(sb, KERN_ERR,
- "Unsupported filesystem blocksize %d", blocksize);
+ "Unsupported filesystem block size %d", blocksize);
goto failed_mount;
}
if (sbi->s_mount_opt & EXT4_MOUNT_DAX) {
if (blocksize != PAGE_SIZE) {
ext4_msg(sb, KERN_ERR,
- "error: unsupported blocksize for dax");
+ "error: unsupported filesystem block size %d for dax",
+ blocksize);
goto failed_mount;
}
if (!sb->s_bdev->bd_disk->fops->direct_access) {
@@ -3393,7 +3398,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
if (sb->s_blocksize != blocksize) {
/* Validate the filesystem blocksize */
if (!sb_set_blocksize(sb, blocksize)) {
- ext4_msg(sb, KERN_ERR, "bad block size %d",
+ ext4_msg(sb, KERN_ERR, "bad filesystem block size %d",
blocksize);
goto failed_mount;
}
@@ -3495,8 +3500,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
if (has_bigalloc) {
if (clustersize < blocksize) {
ext4_msg(sb, KERN_ERR,
- "cluster size (%d) smaller than "
- "block size (%d)", clustersize, blocksize);
+ "cluster size (%d) smaller than filesystem block size (%d)",
+ clustersize, blocksize);
goto failed_mount;
}
sbi->s_cluster_bits = le32_to_cpu(es->s_log_cluster_size) -
@@ -3519,9 +3524,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
}
} else {
if (clustersize != blocksize) {
- ext4_warning(sb, "fragment/cluster size (%d) != "
- "block size (%d)", clustersize,
- blocksize);
+ ext4_warning(sb,
+ "fragment/cluster size (%d) != filesystem block size (%d)",
+ clustersize, blocksize);
clustersize = blocksize;
}
if (sbi->s_blocks_per_group > blocksize * 8) {
@@ -3769,7 +3774,8 @@ no_journal:
if ((DUMMY_ENCRYPTION_ENABLED(sbi) || ext4_has_feature_encrypt(sb)) &&
(blocksize != PAGE_CACHE_SIZE)) {
ext4_msg(sb, KERN_ERR,
- "Unsupported blocksize for fs encryption");
+ "Unsupported filesystem block size %d for fs encryption",
+ blocksize);
goto failed_mount_wq;
}
@@ -4112,7 +4118,8 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb,
hblock = bdev_logical_block_size(bdev);
if (blocksize < hblock) {
ext4_msg(sb, KERN_ERR,
- "blocksize too small for journal device");
+ "filesystem block size %d too small for journal device",
+ blocksize);
goto out_bdev;
}
--
2.4.3
4 years, 5 months
