[PATCH] mm,x86: native_pud_clear missing on i386 build
by Dave Jiang
Missing dummy function native_pud_clear() for 32bit x86 build caught
by 0-day build.
Fix: a10a1701 mm, x86: add support for PUD-sized transparent hugepages
Signed-off-by: Dave Jiang <dave.jiang(a)intel.com>
---
arch/x86/include/asm/pgtable-3level.h | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index be759ff..50d35e3 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -121,6 +121,10 @@ static inline void native_pmd_clear(pmd_t *pmd)
*(tmp + 1) = 0;
}
+static inline void native_pud_clear(pud_t *pudp)
+{
+}
+
static inline void pud_clear(pud_t *pudp)
{
set_pud(pudp, __pud(0));
5 years, 4 months
Notification status of your delivery (UPS 005440892)
by anonymous＠parso11m.easydservers.com
Dear Customer,
We can not deliver your parcel arrived at February 04.
Please check the attachment for complete details!
Best regards,
Hector Leach,
UPS Mail Delivery Manager.
5 years, 4 months
[ndctl PATCH 1/2] util: add a common ALIGN macro
by Dan Williams
There are a couple locations where we locally define ALIGN(), add a
global definition before adding another local one.
Signed-off-by: Dan Williams <dan.j.williams(a)intel.com>
---
ndctl/builtin-dimm.c | 3 +--
test/dax-pmd.c | 3 +--
util/size.h | 4 ++++
3 files changed, 6 insertions(+), 4 deletions(-)
diff --git a/ndctl/builtin-dimm.c b/ndctl/builtin-dimm.c
index 8a041cee8cab..637b10b47abf 100644
--- a/ndctl/builtin-dimm.c
+++ b/ndctl/builtin-dimm.c
@@ -17,6 +17,7 @@
#include <limits.h>
#include <syslog.h>
#include <util/log.h>
+#include <util/size.h>
#include <uuid/uuid.h>
#include <util/json.h>
#include <util/filter.h>
@@ -605,8 +606,6 @@ static struct namespace_label *label_base(struct nvdimm_data *ndd)
return (struct namespace_label *) base;
}
-#define ALIGN(x, a) ((((unsigned long long) x) + (a - 1)) & ~(a - 1))
-#define BITS_PER_LONG (sizeof(unsigned long) * 8)
static int label_write_index(struct nvdimm_data *ndd, int index, u32 seq)
{
struct namespace_index *nsindex;
diff --git a/test/dax-pmd.c b/test/dax-pmd.c
index 47f254e398b2..831b1f0a6572 100644
--- a/test/dax-pmd.c
+++ b/test/dax-pmd.c
@@ -11,11 +11,10 @@
#include <stdlib.h>
#include <linux/fs.h>
#include <test.h>
+#include <util/size.h>
#include <linux/fiemap.h>
#define NUM_EXTENTS 5
-#define HPAGE_SIZE (2 << 20)
-#define ALIGN(x, a) ((((unsigned long long) x) + (a - 1)) & ~(a - 1))
#define fail() fprintf(stderr, "%s: failed at: %d\n", __func__, __LINE__)
#define faili(i) fprintf(stderr, "%s: failed at: %d: %d\n", __func__, __LINE__, i)
#define TEST_FILE "test_dax_data"
diff --git a/util/size.h b/util/size.h
index 776363fd19e9..4af14eb7d150 100644
--- a/util/size.h
+++ b/util/size.h
@@ -14,4 +14,8 @@
unsigned long long parse_size64(const char *str);
unsigned long long __parse_size64(const char *str, unsigned long long *units);
+#define ALIGN(x, a) ((((unsigned long long) x) + (a - 1)) & ~(a - 1))
+#define BITS_PER_LONG (sizeof(unsigned long) * 8)
+#define HPAGE_SIZE (2 << 20)
+
#endif /* _NDCTL_SIZE_H_ */
5 years, 4 months
[PATCH] libnvdimm, pfn: fix memmap reservation size versus 4K alignment
by Dan Williams
When vmemmap_populate() allocates space for the memmap it does so in 2MB
sized chunks. The libnvdimm-pfn driver incorrectly accounts for this
when the alignment of the device is set to 4K. When this happens we
trigger memory allocation failures in altmap_alloc_block_buf() and
trigger warnings of the form:
WARNING: CPU: 0 PID: 3376 at arch/x86/mm/init_64.c:656 arch_add_memory+0xe4/0xf0
[..]
Call Trace:
dump_stack+0x86/0xc3
__warn+0xcb/0xf0
warn_slowpath_null+0x1d/0x20
arch_add_memory+0xe4/0xf0
devm_memremap_pages+0x29b/0x4e0
Fixes: 315c562536c4 ("libnvdimm, pfn: add 'align' attribute, default to HPAGE_SIZE")
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Dan Williams <dan.j.williams(a)intel.com>
---
drivers/nvdimm/pfn_devs.c | 7 ++-----
1 file changed, 2 insertions(+), 5 deletions(-)
diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index a2ac9e641aa9..6c033c9a2f06 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -627,15 +627,12 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn)
size = resource_size(&nsio->res);
npfns = (size - start_pad - end_trunc - SZ_8K) / SZ_4K;
if (nd_pfn->mode == PFN_MODE_PMEM) {
- unsigned long memmap_size;
-
/*
* vmemmap_populate_hugepages() allocates the memmap array in
* HPAGE_SIZE chunks.
*/
- memmap_size = ALIGN(64 * npfns, HPAGE_SIZE);
- offset = ALIGN(start + SZ_8K + memmap_size + dax_label_reserve,
- nd_pfn->align) - start;
+ offset = ALIGN(start + SZ_8K + 64 * npfns + dax_label_reserve,
+ max(nd_pfn->align, HPAGE_SIZE)) - start;
} else if (nd_pfn->mode == PFN_MODE_RAM)
offset = ALIGN(start + SZ_8K + dax_label_reserve,
nd_pfn->align) - start;
5 years, 4 months
[PATCH] mm, dax: clear PMD or PUD size flags when in fall through path
by Dave Jiang
Ross reported that:
Running xfstests generic/030 with XFS + DAX gives me the following kernel BUG,
which I bisected to this commit: mm,fs,dax: Change ->pmd_fault to ->huge_fault
[ 370.086205] ------------[ cut here ]------------
[ 370.087182] kernel BUG at arch/x86/mm/fault.c:1038!
[ 370.088336] invalid opcode: 0000 [#3] PREEMPT SMP
[ 370.089073] Modules linked in: dax_pmem nd_pmem dax nd_btt nd_e820 libnvdimm
[ 370.090212] CPU: 0 PID: 12415 Comm: xfs_io Tainted: G D 4.10.0-rc5-mm1-00202-g7e90fc0 #10
[ 370.091648] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.9.1-1.fc24 04/01/2014
[ 370.092946] task: ffff8800ac4f8000 task.stack: ffffc9001148c000
[ 370.093769] RIP: 0010:mm_fault_error+0x15e/0x190
[ 370.094410] RSP: 0000:ffffc9001148fe60 EFLAGS: 00010246
[ 370.095135] RAX: 0000000000000000 RBX: 0000000000000006 RCX: ffff8800ac4f8000
[ 370.096107] RDX: 00007f111c8e6400 RSI: 0000000000000006 RDI: ffffc9001148ff58
[ 370.097087] RBP: ffffc9001148fe88 R08: 0000000000000000 R09: ffff880510bd3300
[ 370.098072] R10: ffff8800ac4f8000 R11: 0000000000000000 R12: 00007f111c8e6400
[ 370.099057] R13: 00007f111c8e6400 R14: ffff880510bd3300 R15: 0000000000000055
[ 370.100135] FS: 00007f111d95e700(0000) GS:ffff880514800000(0000) knlGS:0000000000000000
[ 370.101238] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 370.102021] CR2: 00007f111c8e6400 CR3: 00000000add00000 CR4: 00000000001406f0
[ 370.103189] Call Trace:
[ 370.103537] __do_page_fault+0x54e/0x590
[ 370.104090] trace_do_page_fault+0x58/0x2c0
[ 370.104675] do_async_page_fault+0x2c/0x90
[ 370.105342] async_page_fault+0x28/0x30
[ 370.106044] RIP: 0033:0x405e9a
[ 370.106470] RSP: 002b:00007fffb7f30590 EFLAGS: 00010287
[ 370.107185] RAX: 00000000004e6400 RBX: 0000000000000057 RCX: 00000000004e7000
[ 370.108155] RDX: 00007f111c400000 RSI: 00000000004e7000 RDI: 0000000001c35080
[ 370.109157] RBP: 00000000004e6400 R08: 0000000000000014 R09: 1999999999999999
[ 370.110158] R10: 00007f111d2dc200 R11: 0000000000000000 R12: 0000000001c32fc0
[ 370.111165] R13: 0000000000000000 R14: 0000000000000c00 R15: 0000000000000005
[ 370.112171] Code: 07 00 00 00 e8 a4 ee ff ff e9 11 ff ff ff 4c 89 ea 48 89 de 45 31 c0 31 c9 e8 8f f7 ff ff 48 83 c4 08 5b 41 5c 41 5d 41 5e 5d c3 <0f> 0b 41 8b 94 24 80 04 00 00 49 8d b4 24 b0 06 00 00 4c 89 e9
[ 370.114823] RIP: mm_fault_error+0x15e/0x190 RSP: ffffc9001148fe60
[ 370.115722] ---[ end trace 2ce10d930638254d ]---
It appears that there are 2 issues. First, the size bits used for vm_fault
needs to be shifted over. Otherwise, FAULT_FLAG_SIZE_PMD is clobbering
FAULT_FLAG_INSTRUCTION. Second issue, after create_huge_pmd() is being
called and is falling back to the pte fault handler, the FAULT_FLAG_SIZE_PMD
flag remains and that causes the dax fault handler to go towards the pmd
fault handler instead of the pte fault handler. Fixes are made for the pud
and pmd fall through paths.
Reported-by: Ross Zwisler <ross.zwisler(a)linux.intel.com>
Signed-off-by: Dave Jiang <dave.jiang(a)intel.com>
---
include/linux/mm.h | 8 ++++----
mm/memory.c | 4 ++++
2 files changed, 8 insertions(+), 4 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index f50e730..6194aeb 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -285,10 +285,10 @@ extern pgprot_t protection_map[16];
#define FAULT_FLAG_REMOTE 0x80 /* faulting for non current tsk/mm */
#define FAULT_FLAG_INSTRUCTION 0x100 /* The fault was during an instruction fetch */
-#define FAULT_FLAG_SIZE_MASK 0x700 /* Support up to 8-level page tables */
-#define FAULT_FLAG_SIZE_PTE 0x000 /* First level (eg 4k) */
-#define FAULT_FLAG_SIZE_PMD 0x100 /* Second level (eg 2MB) */
-#define FAULT_FLAG_SIZE_PUD 0x200 /* Third level (eg 1GB) */
+#define FAULT_FLAG_SIZE_MASK 0x7000 /* Support up to 8-level page tables */
+#define FAULT_FLAG_SIZE_PTE 0x0000 /* First level (eg 4k) */
+#define FAULT_FLAG_SIZE_PMD 0x1000 /* Second level (eg 2MB) */
+#define FAULT_FLAG_SIZE_PUD 0x2000 /* Third level (eg 1GB) */
#define FAULT_FLAG_TRACE \
{ FAULT_FLAG_WRITE, "WRITE" }, \
diff --git a/mm/memory.c b/mm/memory.c
index d465806..bdf1661 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3663,6 +3663,8 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
ret = create_huge_pud(&vmf);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
+ /* fall through path, remove PUD flag */
+ vmf.flags &= ~FAULT_FLAG_SIZE_PUD;
} else {
pud_t orig_pud = *vmf.pud;
@@ -3693,6 +3695,8 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
ret = create_huge_pmd(&vmf);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
+ /* fall through path, remove PMD flag */
+ vmf.flags &= ~FAULT_FLAG_SIZE_PMD;
} else {
pmd_t orig_pmd = *vmf.pmd;
5 years, 4 months
[PATCH] acpi, nfit: fix acpi_nfit_flush_probe() crash
by Dan Williams
We queue an on-stack work item to 'nfit_wq' and wait for it to complete
as part of a 'flush_probe' request. However, if the user cancels the
wait we need to make sure the item is flushed from the queue otherwise
we are leaving an out-of-scope stack address on the work list.
BUG: unable to handle kernel paging request at ffffbcb3c72f7cd0
IP: [<ffffffffa9413a7b>] __list_add+0x1b/0xb0
[..]
RIP: 0010:[<ffffffffa9413a7b>] [<ffffffffa9413a7b>] __list_add+0x1b/0xb0
RSP: 0018:ffffbcb3c7ba7c00 EFLAGS: 00010046
[..]
Call Trace:
[<ffffffffa90bb11a>] insert_work+0x3a/0xc0
[<ffffffffa927fdda>] ? seq_open+0x5a/0xa0
[<ffffffffa90bb30a>] __queue_work+0x16a/0x460
[<ffffffffa90bbb08>] queue_work_on+0x38/0x40
[<ffffffffc0cf2685>] acpi_nfit_flush_probe+0x95/0xc0 [nfit]
[<ffffffffc0cf25d0>] ? nfit_visible+0x40/0x40 [nfit]
[<ffffffffa9571495>] wait_probe_show+0x25/0x60
[<ffffffffa9546b30>] dev_attr_show+0x20/0x50
Fixes: 7ae0fa439faf ("nfit, libnvdimm: async region scrub workqueue")
Cc: <stable(a)vger.kernel.org>
Cc: Vishal Verma <vishal.l.verma(a)intel.com>
Signed-off-by: Dan Williams <dan.j.williams(a)intel.com>
---
drivers/acpi/nfit/core.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index 2f82b8eba360..7361d00818e2 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -2704,6 +2704,7 @@ static int acpi_nfit_flush_probe(struct nvdimm_bus_descriptor *nd_desc)
struct acpi_nfit_desc *acpi_desc = to_acpi_nfit_desc(nd_desc);
struct device *dev = acpi_desc->dev;
struct acpi_nfit_flush_work flush;
+ int rc;
/* bounce the device lock to flush acpi_nfit_add / acpi_nfit_notify */
device_lock(dev);
@@ -2716,7 +2717,10 @@ static int acpi_nfit_flush_probe(struct nvdimm_bus_descriptor *nd_desc)
INIT_WORK_ONSTACK(&flush.work, flush_probe);
COMPLETION_INITIALIZER_ONSTACK(flush.cmp);
queue_work(nfit_wq, &flush.work);
- return wait_for_completion_interruptible(&flush.cmp);
+
+ rc = wait_for_completion_interruptible(&flush.cmp);
+ cancel_work_sync(&flush.work);
+ return rc;
}
static int acpi_nfit_clear_to_send(struct nvdimm_bus_descriptor *nd_desc,
5 years, 4 months
[PATCH] libnvdimm, namespace: do not delete namespace-id 0
by Dan Williams
Given that the naming of pmem devices changes from the pmemX form to the
pmemX.Y form when namespace id is greater than 0, arrange for namespaces
with id-0 to be exempt from deletion. Otherwise a simple reconfiguration
of an existing namespace to a new mode results in a name change of the
resulting block device:
# ndctl list --namespace=namespace1.0
{
"dev":"namespace1.0",
"mode":"raw",
"size":2147483648,
"uuid":"3dadf3dc-89b9-4b24-b20e-abc8a4707ce3",
"blockdev":"pmem1"
}
# ndctl create-namespace --reconfig=namespace1.0 --mode=memory --force
{
"dev":"namespace1.1",
"mode":"memory",
"size":2111832064,
"uuid":"7b4a6341-7318-4219-a02c-fb57c0bbf613",
"blockdev":"pmem1.1"
}
This change does require tooling changes to explicitly look for
namespaceX.0 if the seed has already advanced to another namespace.
Cc: <stable(a)vger.kernel.org>
Fixes: 98a29c39dc68 ("libnvdimm, namespace: allow creation of multiple pmem-namespaces per region")
Signed-off-by: Dan Williams <dan.j.williams(a)intel.com>
---
drivers/nvdimm/namespace_devs.c | 11 +++++++----
1 file changed, 7 insertions(+), 4 deletions(-)
diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
index eda027db0918..ce3e8dfa10ad 100644
--- a/drivers/nvdimm/namespace_devs.c
+++ b/drivers/nvdimm/namespace_devs.c
@@ -962,8 +962,8 @@ static ssize_t __size_store(struct device *dev, unsigned long long val)
struct nvdimm_drvdata *ndd;
struct nd_label_id label_id;
u32 flags = 0, remainder;
+ int rc, i, id = -1;
u8 *uuid = NULL;
- int rc, i;
if (dev->driver || ndns->claim)
return -EBUSY;
@@ -972,11 +972,13 @@ static ssize_t __size_store(struct device *dev, unsigned long long val)
struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
uuid = nspm->uuid;
+ id = nspm->id;
} else if (is_namespace_blk(dev)) {
struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
uuid = nsblk->uuid;
flags = NSLABEL_FLAG_LOCAL;
+ id = nsblk->id;
}
/*
@@ -1039,10 +1041,11 @@ static ssize_t __size_store(struct device *dev, unsigned long long val)
/*
* Try to delete the namespace if we deleted all of its
- * allocation, this is not the seed device for the region, and
- * it is not actively claimed by a btt instance.
+ * allocation, this is not the seed or 0th device for the
+ * region, and it is not actively claimed by a btt, pfn, or dax
+ * instance.
*/
- if (val == 0 && nd_region->ns_seed != dev && !ndns->claim)
+ if (val == 0 && id != 0 && nd_region->ns_seed != dev && !ndns->claim)
nd_device_unregister(dev, ND_ASYNC);
return rc;
5 years, 4 months
