* [PATCH v3 0/8] Support for transparent PUD pages for DAX files
@ 2016-01-08 19:49 ` Matthew Wilcox
0 siblings, 0 replies; 32+ messages in thread
From: Matthew Wilcox @ 2016-01-08 19:49 UTC (permalink / raw)
To: Andrew Morton
Cc: Matthew Wilcox, linux-mm, linux-nvdimm, linux-fsdevel, linux-kernel, x86
From: Matthew Wilcox <willy@linux.intel.com>
Andrew, I think this is ready for a spin in -mm.
v3: Rebased against current mmtom
v2: Reduced churn in filesystems by switching to ->huge_fault interface
Addressed concerns from Kirill
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 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 | 94 ++++++++++++
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 | 272 +++++++++++++++++++++++++---------
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 | 50 +++++++
include/linux/mm.h | 43 +++++-
include/linux/mmu_notifier.h | 13 ++
include/linux/pfn_t.h | 8 +
mm/huge_memory.c | 151 +++++++++++++++++++
mm/memory.c | 101 +++++++++++--
mm/mincore.c | 13 ++
mm/pagewalk.c | 19 ++-
mm/pgtable-generic.c | 14 ++
28 files changed, 980 insertions(+), 198 deletions(-)
--
2.6.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 32+ messages in thread
* [PATCH v3 0/8] Support for transparent PUD pages for DAX files
@ 2016-01-08 19:49 ` Matthew Wilcox
0 siblings, 0 replies; 32+ messages in thread
From: Matthew Wilcox @ 2016-01-08 19:49 UTC (permalink / raw)
To: Andrew Morton
Cc: Matthew Wilcox, linux-mm, linux-nvdimm, linux-fsdevel, linux-kernel, x86
From: Matthew Wilcox <willy@linux.intel.com>
Andrew, I think this is ready for a spin in -mm.
v3: Rebased against current mmtom
v2: Reduced churn in filesystems by switching to ->huge_fault interface
Addressed concerns from Kirill
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 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 | 94 ++++++++++++
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 | 272 +++++++++++++++++++++++++---------
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 | 50 +++++++
include/linux/mm.h | 43 +++++-
include/linux/mmu_notifier.h | 13 ++
include/linux/pfn_t.h | 8 +
mm/huge_memory.c | 151 +++++++++++++++++++
mm/memory.c | 101 +++++++++++--
mm/mincore.c | 13 ++
mm/pagewalk.c | 19 ++-
mm/pgtable-generic.c | 14 ++
28 files changed, 980 insertions(+), 198 deletions(-)
--
2.6.4
^ permalink raw reply [flat|nested] 32+ messages in thread
* [PATCH v3 1/8] mm: Convert an open-coded VM_BUG_ON_VMA
2016-01-08 19:49 ` Matthew Wilcox
@ 2016-01-08 19:49 ` Matthew Wilcox
-1 siblings, 0 replies; 32+ messages in thread
From: Matthew Wilcox @ 2016-01-08 19:49 UTC (permalink / raw)
To: Andrew Morton
Cc: Matthew Wilcox, linux-mm, linux-nvdimm, linux-fsdevel, linux-kernel, x86
From: Matthew Wilcox <willy@linux.intel.com>
Spotted during PUD support review.
Reported-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
---
mm/memory.c | 10 +---------
1 file changed, 1 insertion(+), 9 deletions(-)
diff --git a/mm/memory.c b/mm/memory.c
index f559e70..4150112 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1185,15 +1185,7 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
next = pmd_addr_end(addr, end);
if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) {
if (next - addr != HPAGE_PMD_SIZE) {
-#ifdef CONFIG_DEBUG_VM
- if (!rwsem_is_locked(&tlb->mm->mmap_sem)) {
- pr_err("%s: mmap_sem is unlocked! addr=0x%lx end=0x%lx vma->vm_start=0x%lx vma->vm_end=0x%lx\n",
- __func__, addr, end,
- vma->vm_start,
- vma->vm_end);
- BUG();
- }
-#endif
+ VM_BUG_ON_VMA(!rwsem_is_locked(&tlb->mm->mmap_sem), vma);
split_huge_pmd(vma, pmd, addr);
} else if (zap_huge_pmd(tlb, vma, pmd, addr))
goto next;
--
2.6.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [PATCH v3 1/8] mm: Convert an open-coded VM_BUG_ON_VMA
@ 2016-01-08 19:49 ` Matthew Wilcox
0 siblings, 0 replies; 32+ messages in thread
From: Matthew Wilcox @ 2016-01-08 19:49 UTC (permalink / raw)
To: Andrew Morton
Cc: Matthew Wilcox, linux-mm, linux-nvdimm, linux-fsdevel, linux-kernel, x86
From: Matthew Wilcox <willy@linux.intel.com>
Spotted during PUD support review.
Reported-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
---
mm/memory.c | 10 +---------
1 file changed, 1 insertion(+), 9 deletions(-)
diff --git a/mm/memory.c b/mm/memory.c
index f559e70..4150112 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1185,15 +1185,7 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
next = pmd_addr_end(addr, end);
if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) {
if (next - addr != HPAGE_PMD_SIZE) {
-#ifdef CONFIG_DEBUG_VM
- if (!rwsem_is_locked(&tlb->mm->mmap_sem)) {
- pr_err("%s: mmap_sem is unlocked! addr=0x%lx end=0x%lx vma->vm_start=0x%lx vma->vm_end=0x%lx\n",
- __func__, addr, end,
- vma->vm_start,
- vma->vm_end);
- BUG();
- }
-#endif
+ VM_BUG_ON_VMA(!rwsem_is_locked(&tlb->mm->mmap_sem), vma);
split_huge_pmd(vma, pmd, addr);
} else if (zap_huge_pmd(tlb, vma, pmd, addr))
goto next;
--
2.6.4
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [PATCH v3 2/8] mm,fs,dax: Change ->pmd_fault to ->huge_fault
2016-01-08 19:49 ` Matthew Wilcox
@ 2016-01-08 19:49 ` Matthew Wilcox
-1 siblings, 0 replies; 32+ messages in thread
From: Matthew Wilcox @ 2016-01-08 19:49 UTC (permalink / raw)
To: Andrew Morton
Cc: Matthew Wilcox, linux-mm, linux-nvdimm, linux-fsdevel, linux-kernel, x86
From: Matthew Wilcox <willy@linux.intel.com>
In preparation for adding the ability to handle PUD pages, convert
->pmd_fault to ->huge_fault. huge_fault() takes a vm_fault structure
instead of separate (address, pmd, flags) parameters. The vm_fault
structure is extended to include a union of the different page table
pointers that may be needed, and three flag bits are reserved to indicate
which type of pointer is in the union.
The DAX fault handlers are unified into one entry point, meaning that
the filesystems can be largely unconcerned with what size of fault they
are handling. ext4 needs to know in order to reserve enough blocks in
the journal, but ext2 and xfs are oblivious.
The existing dax_fault and dax_mkwrite had no callers, so rename the
__dax_fault and __dax_mkwrite to lose the initial underscores.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
---
Documentation/filesystems/dax.txt | 12 +++--
fs/block_dev.c | 10 +---
fs/dax.c | 97 +++++++++++++--------------------------
fs/ext2/file.c | 27 ++---------
fs/ext4/file.c | 56 +++++++---------------
fs/xfs/xfs_file.c | 25 +++++-----
fs/xfs/xfs_trace.h | 2 +-
include/linux/dax.h | 17 -------
include/linux/mm.h | 20 ++++++--
mm/memory.c | 20 ++++++--
10 files changed, 102 insertions(+), 184 deletions(-)
diff --git a/Documentation/filesystems/dax.txt b/Documentation/filesystems/dax.txt
index 7bde640..2fe9e74 100644
--- a/Documentation/filesystems/dax.txt
+++ b/Documentation/filesystems/dax.txt
@@ -49,6 +49,7 @@ These block devices may be used for inspiration:
- axonram: Axon DDR2 device driver
- brd: RAM backed block device driver
- dcssblk: s390 dcss block device driver
+- pmem: NV-DIMM Persistent Memory driver
Implementation Tips for Filesystem Writers
@@ -61,9 +62,9 @@ Filesystem support consists of
dax_do_io() instead of blockdev_direct_IO() if S_DAX is set
- implementing an mmap file operation for DAX files which sets the
VM_MIXEDMAP and VM_HUGEPAGE flags on the VMA, and setting the vm_ops to
- include handlers for fault, pmd_fault and page_mkwrite (which should
- probably call dax_fault(), dax_pmd_fault() and dax_mkwrite(), passing the
- appropriate get_block() callback)
+ include handlers for fault, huge_fault and page_mkwrite (which should
+ probably call dax_fault() and dax_mkwrite(), passing the appropriate
+ get_block() callback)
- calling dax_truncate_page() instead of block_truncate_page() for DAX files
- calling dax_zero_page_range() instead of zero_user() for DAX files
- ensuring that there is sufficient locking between reads, writes,
@@ -75,8 +76,9 @@ calls to get_block() (for example by a page-fault racing with a read()
or a write()) work correctly.
These filesystems may be used for inspiration:
-- ext2: the second extended filesystem, see Documentation/filesystems/ext2.txt
-- ext4: the fourth extended filesystem, see Documentation/filesystems/ext4.txt
+- ext2: see Documentation/filesystems/ext2.txt
+- ext4: see Documentation/filesystems/ext4.txt
+- xfs: see Documentation/filesystems/xfs.txt
Shortcomings
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 303b7cd..f56402d 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1733,13 +1733,7 @@ static const struct address_space_operations def_blk_aops = {
*/
static int blkdev_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
- return __dax_fault(vma, vmf, blkdev_get_block, NULL);
-}
-
-static int blkdev_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
- pmd_t *pmd, unsigned int flags)
-{
- return __dax_pmd_fault(vma, addr, pmd, flags, blkdev_get_block, NULL);
+ return dax_fault(vma, vmf, blkdev_get_block, NULL);
}
static void blkdev_vm_open(struct vm_area_struct *vma)
@@ -1766,7 +1760,7 @@ static const struct vm_operations_struct blkdev_dax_vm_ops = {
.open = blkdev_vm_open,
.close = blkdev_vm_close,
.fault = blkdev_dax_fault,
- .pmd_fault = blkdev_dax_pmd_fault,
+ .huge_fault = blkdev_dax_fault,
.pfn_mkwrite = blkdev_dax_fault,
};
diff --git a/fs/dax.c b/fs/dax.c
index 41cf4ee..05ed547 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -547,23 +547,7 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
return error;
}
-/**
- * __dax_fault - handle a page fault on a DAX file
- * @vma: The virtual memory area where the fault occurred
- * @vmf: The description of the fault
- * @get_block: The filesystem method used to translate file offsets to blocks
- * @complete_unwritten: The filesystem method used to convert unwritten blocks
- * to written so the data written to them is exposed. This is required for
- * required by write faults for filesystems that will return unwritten
- * extent mappings from @get_block, but it is optional for reads as
- * dax_insert_mapping() will always zero unwritten blocks. If the fs does
- * not support unwritten extents, the it should pass NULL.
- *
- * When a page fault occurs, filesystems may call this helper in their
- * fault handler for DAX files. __dax_fault() assumes the caller has done all
- * the necessary locking for the page fault to proceed successfully.
- */
-int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
+static int dax_pte_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
get_block_t get_block, dax_iodone_t complete_unwritten)
{
struct file *file = vma->vm_file;
@@ -699,34 +683,6 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
}
goto out;
}
-EXPORT_SYMBOL(__dax_fault);
-
-/**
- * dax_fault - handle a page fault on a DAX file
- * @vma: The virtual memory area where the fault occurred
- * @vmf: The description of the fault
- * @get_block: The filesystem method used to translate file offsets to blocks
- *
- * When a page fault occurs, filesystems may call this helper in their
- * fault handler for DAX files.
- */
-int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
- get_block_t get_block, dax_iodone_t complete_unwritten)
-{
- int result;
- struct super_block *sb = file_inode(vma->vm_file)->i_sb;
-
- if (vmf->flags & FAULT_FLAG_WRITE) {
- sb_start_pagefault(sb);
- file_update_time(vma->vm_file);
- }
- result = __dax_fault(vma, vmf, get_block, complete_unwritten);
- if (vmf->flags & FAULT_FLAG_WRITE)
- sb_end_pagefault(sb);
-
- return result;
-}
-EXPORT_SYMBOL_GPL(dax_fault);
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/*
@@ -753,7 +709,7 @@ static void __dax_dbg(struct buffer_head *bh, unsigned long address,
#define dax_pmd_dbg(bh, address, reason) __dax_dbg(bh, address, reason, "dax_pmd")
-int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
+static int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmd, unsigned int flags, get_block_t get_block,
dax_iodone_t complete_unwritten)
{
@@ -941,37 +897,46 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
result = VM_FAULT_FALLBACK;
goto out;
}
-EXPORT_SYMBOL_GPL(__dax_pmd_fault);
+#else /* !CONFIG_TRANSPARENT_HUGEPAGE */
+static int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
+ pmd_t *pmd, unsigned int flags, get_block_t get_block,
+ dax_iodone_t complete_unwritten)
+{
+ return VM_FAULT_FALLBACK;
+}
+#endif /* !CONFIG_TRANSPARENT_HUGEPAGE */
/**
- * dax_pmd_fault - handle a PMD fault on a DAX file
+ * dax_fault - handle a page fault on a DAX file
* @vma: The virtual memory area where the fault occurred
* @vmf: The description of the fault
* @get_block: The filesystem method used to translate file offsets to blocks
+ * @iodone: The filesystem method used to convert unwritten blocks
+ * to written so the data written to them is exposed. This is required
+ * by write faults for filesystems that will return unwritten extent
+ * mappings from @get_block, but it is optional for reads as
+ * dax_insert_mapping() will always zero unwritten blocks. If the fs
+ * does not support unwritten extents, then it should pass NULL.
*
* When a page fault occurs, filesystems may call this helper in their
- * pmd_fault handler for DAX files.
+ * fault handler for DAX files. dax_fault() assumes the caller has done all
+ * the necessary locking for the page fault to proceed successfully.
*/
-int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
- pmd_t *pmd, unsigned int flags, get_block_t get_block,
- dax_iodone_t complete_unwritten)
+int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
+ get_block_t get_block, dax_iodone_t iodone)
{
- int result;
- struct super_block *sb = file_inode(vma->vm_file)->i_sb;
-
- if (flags & FAULT_FLAG_WRITE) {
- sb_start_pagefault(sb);
- file_update_time(vma->vm_file);
+ unsigned long address = (unsigned long)vmf->virtual_address;
+ switch (vmf->flags & FAULT_FLAG_SIZE_MASK) {
+ case FAULT_FLAG_SIZE_PTE:
+ return dax_pte_fault(vma, vmf, get_block, iodone);
+ case FAULT_FLAG_SIZE_PMD:
+ return dax_pmd_fault(vma, address, vmf->pmd, vmf->flags,
+ get_block, iodone);
+ default:
+ return VM_FAULT_FALLBACK;
}
- result = __dax_pmd_fault(vma, address, pmd, flags, get_block,
- complete_unwritten);
- if (flags & FAULT_FLAG_WRITE)
- sb_end_pagefault(sb);
-
- return result;
}
-EXPORT_SYMBOL_GPL(dax_pmd_fault);
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+EXPORT_SYMBOL_GPL(dax_fault);
/**
* dax_pfn_mkwrite - handle first write to DAX page
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 2c88d68..cf6f78c 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -51,7 +51,7 @@ static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
}
down_read(&ei->dax_sem);
- ret = __dax_fault(vma, vmf, ext2_get_block, NULL);
+ ret = dax_fault(vma, vmf, ext2_get_block, NULL);
up_read(&ei->dax_sem);
if (vmf->flags & FAULT_FLAG_WRITE)
@@ -59,27 +59,6 @@ static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
return ret;
}
-static int ext2_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
- pmd_t *pmd, unsigned int flags)
-{
- struct inode *inode = file_inode(vma->vm_file);
- struct ext2_inode_info *ei = EXT2_I(inode);
- int ret;
-
- if (flags & FAULT_FLAG_WRITE) {
- sb_start_pagefault(inode->i_sb);
- file_update_time(vma->vm_file);
- }
- down_read(&ei->dax_sem);
-
- ret = __dax_pmd_fault(vma, addr, pmd, flags, ext2_get_block, NULL);
-
- up_read(&ei->dax_sem);
- if (flags & FAULT_FLAG_WRITE)
- sb_end_pagefault(inode->i_sb);
- return ret;
-}
-
static int ext2_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct inode *inode = file_inode(vma->vm_file);
@@ -90,7 +69,7 @@ static int ext2_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
file_update_time(vma->vm_file);
down_read(&ei->dax_sem);
- ret = __dax_mkwrite(vma, vmf, ext2_get_block, NULL);
+ ret = dax_mkwrite(vma, vmf, ext2_get_block, NULL);
up_read(&ei->dax_sem);
sb_end_pagefault(inode->i_sb);
@@ -123,7 +102,7 @@ static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
static const struct vm_operations_struct ext2_dax_vm_ops = {
.fault = ext2_dax_fault,
- .pmd_fault = ext2_dax_pmd_fault,
+ .huge_fault = ext2_dax_fault,
.page_mkwrite = ext2_dax_mkwrite,
.pfn_mkwrite = ext2_dax_pfn_mkwrite,
};
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index fa899c9..665fc4b 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -202,54 +202,30 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
bool write = vmf->flags & FAULT_FLAG_WRITE;
if (write) {
- sb_start_pagefault(sb);
- file_update_time(vma->vm_file);
- down_read(&EXT4_I(inode)->i_mmap_sem);
- handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
- EXT4_DATA_TRANS_BLOCKS(sb));
- } else
- down_read(&EXT4_I(inode)->i_mmap_sem);
-
- if (IS_ERR(handle))
- result = VM_FAULT_SIGBUS;
- else
- result = __dax_fault(vma, vmf, ext4_dax_mmap_get_block, NULL);
-
- if (write) {
- if (!IS_ERR(handle))
- ext4_journal_stop(handle);
- up_read(&EXT4_I(inode)->i_mmap_sem);
- sb_end_pagefault(sb);
- } else
- up_read(&EXT4_I(inode)->i_mmap_sem);
-
- return result;
-}
-
-static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
- pmd_t *pmd, unsigned int flags)
-{
- int result;
- handle_t *handle = NULL;
- struct inode *inode = file_inode(vma->vm_file);
- struct super_block *sb = inode->i_sb;
- bool write = flags & FAULT_FLAG_WRITE;
+ unsigned nblocks;
+ switch (vmf->flags & FAULT_FLAG_SIZE_MASK) {
+ case FAULT_FLAG_SIZE_PTE:
+ nblocks = EXT4_DATA_TRANS_BLOCKS(sb);
+ break;
+ case FAULT_FLAG_SIZE_PMD:
+ nblocks = ext4_chunk_trans_blocks(inode,
+ PMD_SIZE / PAGE_SIZE);
+ break;
+ default:
+ return VM_FAULT_FALLBACK;
+ }
- if (write) {
sb_start_pagefault(sb);
file_update_time(vma->vm_file);
down_read(&EXT4_I(inode)->i_mmap_sem);
- handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
- ext4_chunk_trans_blocks(inode,
- PMD_SIZE / PAGE_SIZE));
+ handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE, nblocks);
} else
down_read(&EXT4_I(inode)->i_mmap_sem);
if (IS_ERR(handle))
result = VM_FAULT_SIGBUS;
else
- result = __dax_pmd_fault(vma, addr, pmd, flags,
- ext4_dax_mmap_get_block, NULL);
+ result = dax_fault(vma, vmf, ext4_dax_mmap_get_block, NULL);
if (write) {
if (!IS_ERR(handle))
@@ -270,7 +246,7 @@ static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
sb_start_pagefault(inode->i_sb);
file_update_time(vma->vm_file);
down_read(&EXT4_I(inode)->i_mmap_sem);
- err = __dax_mkwrite(vma, vmf, ext4_dax_mmap_get_block, NULL);
+ err = dax_mkwrite(vma, vmf, ext4_dax_mmap_get_block, NULL);
up_read(&EXT4_I(inode)->i_mmap_sem);
sb_end_pagefault(inode->i_sb);
@@ -310,7 +286,7 @@ static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma,
static const struct vm_operations_struct ext4_dax_vm_ops = {
.fault = ext4_dax_fault,
- .pmd_fault = ext4_dax_pmd_fault,
+ .huge_fault = ext4_dax_fault,
.page_mkwrite = ext4_dax_mkwrite,
.pfn_mkwrite = ext4_dax_pfn_mkwrite,
};
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 55e16e2..6db703b 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1526,7 +1526,7 @@ xfs_filemap_page_mkwrite(
xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
if (IS_DAX(inode)) {
- ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault, NULL);
+ ret = dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault, NULL);
} else {
ret = block_page_mkwrite(vma, vmf, xfs_get_blocks);
ret = block_page_mkwrite_return(ret);
@@ -1560,7 +1560,7 @@ xfs_filemap_fault(
* changes to xfs_get_blocks_direct() to map unwritten extent
* ioend for conversion on read-only mappings.
*/
- ret = __dax_fault(vma, vmf, xfs_get_blocks_dax_fault, NULL);
+ ret = dax_fault(vma, vmf, xfs_get_blocks_dax_fault, NULL);
} else
ret = filemap_fault(vma, vmf);
xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
@@ -1571,16 +1571,14 @@ xfs_filemap_fault(
/*
* Similar to xfs_filemap_fault(), the DAX fault path can call into here on
* both read and write faults. Hence we need to handle both cases. There is no
- * ->pmd_mkwrite callout for huge pages, so we have a single function here to
+ * ->huge_mkwrite callout for huge pages, so we have a single function here to
* handle both cases here. @flags carries the information on the type of fault
* occuring.
*/
STATIC int
-xfs_filemap_pmd_fault(
+xfs_filemap_huge_fault(
struct vm_area_struct *vma,
- unsigned long addr,
- pmd_t *pmd,
- unsigned int flags)
+ struct vm_fault *vmf)
{
struct inode *inode = file_inode(vma->vm_file);
struct xfs_inode *ip = XFS_I(inode);
@@ -1589,26 +1587,25 @@ xfs_filemap_pmd_fault(
if (!IS_DAX(inode))
return VM_FAULT_FALLBACK;
- trace_xfs_filemap_pmd_fault(ip);
+ trace_xfs_filemap_huge_fault(ip);
- if (flags & FAULT_FLAG_WRITE) {
+ if (vmf->flags & FAULT_FLAG_WRITE) {
sb_start_pagefault(inode->i_sb);
file_update_time(vma->vm_file);
}
xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
- ret = __dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_dax_fault,
- NULL);
+ ret = dax_fault(vma, vmf, xfs_get_blocks_dax_fault, NULL);
xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
- if (flags & FAULT_FLAG_WRITE)
+ if (vmf->flags & FAULT_FLAG_WRITE)
sb_end_pagefault(inode->i_sb);
return ret;
}
/*
- * pfn_mkwrite was originally inteneded to ensure we capture time stamp
+ * pfn_mkwrite was originally intended to ensure we capture time stamp
* updates on write faults. In reality, it's need to serialise against
* truncate similar to page_mkwrite. Hence we cycle the XFS_MMAPLOCK_SHARED
* to ensure we serialise the fault barrier in place.
@@ -1644,7 +1641,7 @@ xfs_filemap_pfn_mkwrite(
static const struct vm_operations_struct xfs_file_vm_ops = {
.fault = xfs_filemap_fault,
- .pmd_fault = xfs_filemap_pmd_fault,
+ .huge_fault = xfs_filemap_huge_fault,
.map_pages = filemap_map_pages,
.page_mkwrite = xfs_filemap_page_mkwrite,
.pfn_mkwrite = xfs_filemap_pfn_mkwrite,
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 877079eb..8f810db 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -687,7 +687,7 @@ DEFINE_INODE_EVENT(xfs_inode_clear_eofblocks_tag);
DEFINE_INODE_EVENT(xfs_inode_free_eofblocks_invalid);
DEFINE_INODE_EVENT(xfs_filemap_fault);
-DEFINE_INODE_EVENT(xfs_filemap_pmd_fault);
+DEFINE_INODE_EVENT(xfs_filemap_huge_fault);
DEFINE_INODE_EVENT(xfs_filemap_page_mkwrite);
DEFINE_INODE_EVENT(xfs_filemap_pfn_mkwrite);
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 8204c3d..8e58c36 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -12,25 +12,8 @@ int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
int dax_truncate_page(struct inode *, loff_t from, get_block_t);
int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
dax_iodone_t);
-int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
- dax_iodone_t);
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-int dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,
- unsigned int flags, get_block_t, dax_iodone_t);
-int __dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,
- unsigned int flags, get_block_t, dax_iodone_t);
-#else
-static inline int dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
- pmd_t *pmd, unsigned int flags, get_block_t gb,
- dax_iodone_t di)
-{
- return VM_FAULT_FALLBACK;
-}
-#define __dax_pmd_fault dax_pmd_fault
-#endif
int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *);
#define dax_mkwrite(vma, vmf, gb, iod) dax_fault(vma, vmf, gb, iod)
-#define __dax_mkwrite(vma, vmf, gb, iod) __dax_fault(vma, vmf, gb, iod)
static inline bool vma_is_dax(struct vm_area_struct *vma)
{
diff --git a/include/linux/mm.h b/include/linux/mm.h
index e7f08d7..37e25f1 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -232,15 +232,21 @@ extern pgprot_t protection_map[16];
#define FAULT_FLAG_TRIED 0x20 /* Second try */
#define FAULT_FLAG_USER 0x40 /* The fault originated in userspace */
+#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_PGD 0x300 /* Fourth level (eg 512GB) */
+
/*
- * vm_fault is filled by the the pagefault handler and passed to the vma's
+ * vm_fault is filled in by the pagefault handler and passed to the vma's
* ->fault function. The vma's ->fault is responsible for returning a bitmask
* of VM_FAULT_xxx flags that give details about how the fault was handled.
*
* MM layer fills up gfp_mask for page allocations but fault handler might
* alter it if its implementation requires a different allocation context.
*
- * pgoff should be used in favour of virtual_address, if possible.
+ * pgoff should be used instead of virtual_address, if possible.
*/
struct vm_fault {
unsigned int flags; /* FAULT_FLAG_xxx flags */
@@ -257,7 +263,12 @@ struct vm_fault {
/* for ->map_pages() only */
pgoff_t max_pgoff; /* map pages for offset from pgoff till
* max_pgoff inclusive */
- pte_t *pte; /* pte entry associated with ->pgoff */
+ union {
+ pte_t *pte; /* pte entry associated with ->pgoff */
+ pmd_t *pmd;
+ pud_t *pud;
+ pgd_t *pgd;
+ };
};
/*
@@ -270,8 +281,7 @@ struct vm_operations_struct {
void (*close)(struct vm_area_struct * area);
int (*mremap)(struct vm_area_struct * area);
int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
- int (*pmd_fault)(struct vm_area_struct *, unsigned long address,
- pmd_t *, unsigned int flags);
+ int (*huge_fault)(struct vm_area_struct *, struct vm_fault *vmf);
void (*map_pages)(struct vm_area_struct *vma, struct vm_fault *vmf);
/* notification that a previously read-only page is about to become
diff --git a/mm/memory.c b/mm/memory.c
index 4150112..492a228 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3245,10 +3245,16 @@ out:
static int create_huge_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pmd_t *pmd, unsigned int flags)
{
+ struct vm_fault vmf = {
+ .virtual_address = (void __user *)address,
+ .flags = flags | FAULT_FLAG_SIZE_PMD,
+ .pmd = pmd,
+ };
+
if (vma_is_anonymous(vma))
return do_huge_pmd_anonymous_page(mm, vma, address, pmd, flags);
- if (vma->vm_ops->pmd_fault)
- return vma->vm_ops->pmd_fault(vma, address, pmd, flags);
+ if (vma->vm_ops->huge_fault)
+ return vma->vm_ops->huge_fault(vma, &vmf);
return VM_FAULT_FALLBACK;
}
@@ -3256,10 +3262,16 @@ static int wp_huge_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pmd_t *pmd, pmd_t orig_pmd,
unsigned int flags)
{
+ struct vm_fault vmf = {
+ .virtual_address = (void __user *)address,
+ .flags = flags | FAULT_FLAG_SIZE_PMD,
+ .pmd = pmd,
+ };
+
if (vma_is_anonymous(vma))
return do_huge_pmd_wp_page(mm, vma, address, pmd, orig_pmd);
- if (vma->vm_ops->pmd_fault)
- return vma->vm_ops->pmd_fault(vma, address, pmd, flags);
+ if (vma->vm_ops->huge_fault)
+ return vma->vm_ops->huge_fault(vma, &vmf);
return VM_FAULT_FALLBACK;
}
--
2.6.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [PATCH v3 2/8] mm,fs,dax: Change ->pmd_fault to ->huge_fault
@ 2016-01-08 19:49 ` Matthew Wilcox
0 siblings, 0 replies; 32+ messages in thread
From: Matthew Wilcox @ 2016-01-08 19:49 UTC (permalink / raw)
To: Andrew Morton
Cc: Matthew Wilcox, linux-mm, linux-nvdimm, linux-fsdevel, linux-kernel, x86
From: Matthew Wilcox <willy@linux.intel.com>
In preparation for adding the ability to handle PUD pages, convert
->pmd_fault to ->huge_fault. huge_fault() takes a vm_fault structure
instead of separate (address, pmd, flags) parameters. The vm_fault
structure is extended to include a union of the different page table
pointers that may be needed, and three flag bits are reserved to indicate
which type of pointer is in the union.
The DAX fault handlers are unified into one entry point, meaning that
the filesystems can be largely unconcerned with what size of fault they
are handling. ext4 needs to know in order to reserve enough blocks in
the journal, but ext2 and xfs are oblivious.
The existing dax_fault and dax_mkwrite had no callers, so rename the
__dax_fault and __dax_mkwrite to lose the initial underscores.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
---
Documentation/filesystems/dax.txt | 12 +++--
fs/block_dev.c | 10 +---
fs/dax.c | 97 +++++++++++++--------------------------
fs/ext2/file.c | 27 ++---------
fs/ext4/file.c | 56 +++++++---------------
fs/xfs/xfs_file.c | 25 +++++-----
fs/xfs/xfs_trace.h | 2 +-
include/linux/dax.h | 17 -------
include/linux/mm.h | 20 ++++++--
mm/memory.c | 20 ++++++--
10 files changed, 102 insertions(+), 184 deletions(-)
diff --git a/Documentation/filesystems/dax.txt b/Documentation/filesystems/dax.txt
index 7bde640..2fe9e74 100644
--- a/Documentation/filesystems/dax.txt
+++ b/Documentation/filesystems/dax.txt
@@ -49,6 +49,7 @@ These block devices may be used for inspiration:
- axonram: Axon DDR2 device driver
- brd: RAM backed block device driver
- dcssblk: s390 dcss block device driver
+- pmem: NV-DIMM Persistent Memory driver
Implementation Tips for Filesystem Writers
@@ -61,9 +62,9 @@ Filesystem support consists of
dax_do_io() instead of blockdev_direct_IO() if S_DAX is set
- implementing an mmap file operation for DAX files which sets the
VM_MIXEDMAP and VM_HUGEPAGE flags on the VMA, and setting the vm_ops to
- include handlers for fault, pmd_fault and page_mkwrite (which should
- probably call dax_fault(), dax_pmd_fault() and dax_mkwrite(), passing the
- appropriate get_block() callback)
+ include handlers for fault, huge_fault and page_mkwrite (which should
+ probably call dax_fault() and dax_mkwrite(), passing the appropriate
+ get_block() callback)
- calling dax_truncate_page() instead of block_truncate_page() for DAX files
- calling dax_zero_page_range() instead of zero_user() for DAX files
- ensuring that there is sufficient locking between reads, writes,
@@ -75,8 +76,9 @@ calls to get_block() (for example by a page-fault racing with a read()
or a write()) work correctly.
These filesystems may be used for inspiration:
-- ext2: the second extended filesystem, see Documentation/filesystems/ext2.txt
-- ext4: the fourth extended filesystem, see Documentation/filesystems/ext4.txt
+- ext2: see Documentation/filesystems/ext2.txt
+- ext4: see Documentation/filesystems/ext4.txt
+- xfs: see Documentation/filesystems/xfs.txt
Shortcomings
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 303b7cd..f56402d 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1733,13 +1733,7 @@ static const struct address_space_operations def_blk_aops = {
*/
static int blkdev_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
- return __dax_fault(vma, vmf, blkdev_get_block, NULL);
-}
-
-static int blkdev_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
- pmd_t *pmd, unsigned int flags)
-{
- return __dax_pmd_fault(vma, addr, pmd, flags, blkdev_get_block, NULL);
+ return dax_fault(vma, vmf, blkdev_get_block, NULL);
}
static void blkdev_vm_open(struct vm_area_struct *vma)
@@ -1766,7 +1760,7 @@ static const struct vm_operations_struct blkdev_dax_vm_ops = {
.open = blkdev_vm_open,
.close = blkdev_vm_close,
.fault = blkdev_dax_fault,
- .pmd_fault = blkdev_dax_pmd_fault,
+ .huge_fault = blkdev_dax_fault,
.pfn_mkwrite = blkdev_dax_fault,
};
diff --git a/fs/dax.c b/fs/dax.c
index 41cf4ee..05ed547 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -547,23 +547,7 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
return error;
}
-/**
- * __dax_fault - handle a page fault on a DAX file
- * @vma: The virtual memory area where the fault occurred
- * @vmf: The description of the fault
- * @get_block: The filesystem method used to translate file offsets to blocks
- * @complete_unwritten: The filesystem method used to convert unwritten blocks
- * to written so the data written to them is exposed. This is required for
- * required by write faults for filesystems that will return unwritten
- * extent mappings from @get_block, but it is optional for reads as
- * dax_insert_mapping() will always zero unwritten blocks. If the fs does
- * not support unwritten extents, the it should pass NULL.
- *
- * When a page fault occurs, filesystems may call this helper in their
- * fault handler for DAX files. __dax_fault() assumes the caller has done all
- * the necessary locking for the page fault to proceed successfully.
- */
-int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
+static int dax_pte_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
get_block_t get_block, dax_iodone_t complete_unwritten)
{
struct file *file = vma->vm_file;
@@ -699,34 +683,6 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
}
goto out;
}
-EXPORT_SYMBOL(__dax_fault);
-
-/**
- * dax_fault - handle a page fault on a DAX file
- * @vma: The virtual memory area where the fault occurred
- * @vmf: The description of the fault
- * @get_block: The filesystem method used to translate file offsets to blocks
- *
- * When a page fault occurs, filesystems may call this helper in their
- * fault handler for DAX files.
- */
-int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
- get_block_t get_block, dax_iodone_t complete_unwritten)
-{
- int result;
- struct super_block *sb = file_inode(vma->vm_file)->i_sb;
-
- if (vmf->flags & FAULT_FLAG_WRITE) {
- sb_start_pagefault(sb);
- file_update_time(vma->vm_file);
- }
- result = __dax_fault(vma, vmf, get_block, complete_unwritten);
- if (vmf->flags & FAULT_FLAG_WRITE)
- sb_end_pagefault(sb);
-
- return result;
-}
-EXPORT_SYMBOL_GPL(dax_fault);
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/*
@@ -753,7 +709,7 @@ static void __dax_dbg(struct buffer_head *bh, unsigned long address,
#define dax_pmd_dbg(bh, address, reason) __dax_dbg(bh, address, reason, "dax_pmd")
-int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
+static int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmd, unsigned int flags, get_block_t get_block,
dax_iodone_t complete_unwritten)
{
@@ -941,37 +897,46 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
result = VM_FAULT_FALLBACK;
goto out;
}
-EXPORT_SYMBOL_GPL(__dax_pmd_fault);
+#else /* !CONFIG_TRANSPARENT_HUGEPAGE */
+static int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
+ pmd_t *pmd, unsigned int flags, get_block_t get_block,
+ dax_iodone_t complete_unwritten)
+{
+ return VM_FAULT_FALLBACK;
+}
+#endif /* !CONFIG_TRANSPARENT_HUGEPAGE */
/**
- * dax_pmd_fault - handle a PMD fault on a DAX file
+ * dax_fault - handle a page fault on a DAX file
* @vma: The virtual memory area where the fault occurred
* @vmf: The description of the fault
* @get_block: The filesystem method used to translate file offsets to blocks
+ * @iodone: The filesystem method used to convert unwritten blocks
+ * to written so the data written to them is exposed. This is required
+ * by write faults for filesystems that will return unwritten extent
+ * mappings from @get_block, but it is optional for reads as
+ * dax_insert_mapping() will always zero unwritten blocks. If the fs
+ * does not support unwritten extents, then it should pass NULL.
*
* When a page fault occurs, filesystems may call this helper in their
- * pmd_fault handler for DAX files.
+ * fault handler for DAX files. dax_fault() assumes the caller has done all
+ * the necessary locking for the page fault to proceed successfully.
*/
-int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
- pmd_t *pmd, unsigned int flags, get_block_t get_block,
- dax_iodone_t complete_unwritten)
+int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
+ get_block_t get_block, dax_iodone_t iodone)
{
- int result;
- struct super_block *sb = file_inode(vma->vm_file)->i_sb;
-
- if (flags & FAULT_FLAG_WRITE) {
- sb_start_pagefault(sb);
- file_update_time(vma->vm_file);
+ unsigned long address = (unsigned long)vmf->virtual_address;
+ switch (vmf->flags & FAULT_FLAG_SIZE_MASK) {
+ case FAULT_FLAG_SIZE_PTE:
+ return dax_pte_fault(vma, vmf, get_block, iodone);
+ case FAULT_FLAG_SIZE_PMD:
+ return dax_pmd_fault(vma, address, vmf->pmd, vmf->flags,
+ get_block, iodone);
+ default:
+ return VM_FAULT_FALLBACK;
}
- result = __dax_pmd_fault(vma, address, pmd, flags, get_block,
- complete_unwritten);
- if (flags & FAULT_FLAG_WRITE)
- sb_end_pagefault(sb);
-
- return result;
}
-EXPORT_SYMBOL_GPL(dax_pmd_fault);
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+EXPORT_SYMBOL_GPL(dax_fault);
/**
* dax_pfn_mkwrite - handle first write to DAX page
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 2c88d68..cf6f78c 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -51,7 +51,7 @@ static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
}
down_read(&ei->dax_sem);
- ret = __dax_fault(vma, vmf, ext2_get_block, NULL);
+ ret = dax_fault(vma, vmf, ext2_get_block, NULL);
up_read(&ei->dax_sem);
if (vmf->flags & FAULT_FLAG_WRITE)
@@ -59,27 +59,6 @@ static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
return ret;
}
-static int ext2_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
- pmd_t *pmd, unsigned int flags)
-{
- struct inode *inode = file_inode(vma->vm_file);
- struct ext2_inode_info *ei = EXT2_I(inode);
- int ret;
-
- if (flags & FAULT_FLAG_WRITE) {
- sb_start_pagefault(inode->i_sb);
- file_update_time(vma->vm_file);
- }
- down_read(&ei->dax_sem);
-
- ret = __dax_pmd_fault(vma, addr, pmd, flags, ext2_get_block, NULL);
-
- up_read(&ei->dax_sem);
- if (flags & FAULT_FLAG_WRITE)
- sb_end_pagefault(inode->i_sb);
- return ret;
-}
-
static int ext2_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct inode *inode = file_inode(vma->vm_file);
@@ -90,7 +69,7 @@ static int ext2_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
file_update_time(vma->vm_file);
down_read(&ei->dax_sem);
- ret = __dax_mkwrite(vma, vmf, ext2_get_block, NULL);
+ ret = dax_mkwrite(vma, vmf, ext2_get_block, NULL);
up_read(&ei->dax_sem);
sb_end_pagefault(inode->i_sb);
@@ -123,7 +102,7 @@ static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
static const struct vm_operations_struct ext2_dax_vm_ops = {
.fault = ext2_dax_fault,
- .pmd_fault = ext2_dax_pmd_fault,
+ .huge_fault = ext2_dax_fault,
.page_mkwrite = ext2_dax_mkwrite,
.pfn_mkwrite = ext2_dax_pfn_mkwrite,
};
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index fa899c9..665fc4b 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -202,54 +202,30 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
bool write = vmf->flags & FAULT_FLAG_WRITE;
if (write) {
- sb_start_pagefault(sb);
- file_update_time(vma->vm_file);
- down_read(&EXT4_I(inode)->i_mmap_sem);
- handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
- EXT4_DATA_TRANS_BLOCKS(sb));
- } else
- down_read(&EXT4_I(inode)->i_mmap_sem);
-
- if (IS_ERR(handle))
- result = VM_FAULT_SIGBUS;
- else
- result = __dax_fault(vma, vmf, ext4_dax_mmap_get_block, NULL);
-
- if (write) {
- if (!IS_ERR(handle))
- ext4_journal_stop(handle);
- up_read(&EXT4_I(inode)->i_mmap_sem);
- sb_end_pagefault(sb);
- } else
- up_read(&EXT4_I(inode)->i_mmap_sem);
-
- return result;
-}
-
-static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
- pmd_t *pmd, unsigned int flags)
-{
- int result;
- handle_t *handle = NULL;
- struct inode *inode = file_inode(vma->vm_file);
- struct super_block *sb = inode->i_sb;
- bool write = flags & FAULT_FLAG_WRITE;
+ unsigned nblocks;
+ switch (vmf->flags & FAULT_FLAG_SIZE_MASK) {
+ case FAULT_FLAG_SIZE_PTE:
+ nblocks = EXT4_DATA_TRANS_BLOCKS(sb);
+ break;
+ case FAULT_FLAG_SIZE_PMD:
+ nblocks = ext4_chunk_trans_blocks(inode,
+ PMD_SIZE / PAGE_SIZE);
+ break;
+ default:
+ return VM_FAULT_FALLBACK;
+ }
- if (write) {
sb_start_pagefault(sb);
file_update_time(vma->vm_file);
down_read(&EXT4_I(inode)->i_mmap_sem);
- handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
- ext4_chunk_trans_blocks(inode,
- PMD_SIZE / PAGE_SIZE));
+ handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE, nblocks);
} else
down_read(&EXT4_I(inode)->i_mmap_sem);
if (IS_ERR(handle))
result = VM_FAULT_SIGBUS;
else
- result = __dax_pmd_fault(vma, addr, pmd, flags,
- ext4_dax_mmap_get_block, NULL);
+ result = dax_fault(vma, vmf, ext4_dax_mmap_get_block, NULL);
if (write) {
if (!IS_ERR(handle))
@@ -270,7 +246,7 @@ static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
sb_start_pagefault(inode->i_sb);
file_update_time(vma->vm_file);
down_read(&EXT4_I(inode)->i_mmap_sem);
- err = __dax_mkwrite(vma, vmf, ext4_dax_mmap_get_block, NULL);
+ err = dax_mkwrite(vma, vmf, ext4_dax_mmap_get_block, NULL);
up_read(&EXT4_I(inode)->i_mmap_sem);
sb_end_pagefault(inode->i_sb);
@@ -310,7 +286,7 @@ static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma,
static const struct vm_operations_struct ext4_dax_vm_ops = {
.fault = ext4_dax_fault,
- .pmd_fault = ext4_dax_pmd_fault,
+ .huge_fault = ext4_dax_fault,
.page_mkwrite = ext4_dax_mkwrite,
.pfn_mkwrite = ext4_dax_pfn_mkwrite,
};
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 55e16e2..6db703b 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1526,7 +1526,7 @@ xfs_filemap_page_mkwrite(
xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
if (IS_DAX(inode)) {
- ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault, NULL);
+ ret = dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault, NULL);
} else {
ret = block_page_mkwrite(vma, vmf, xfs_get_blocks);
ret = block_page_mkwrite_return(ret);
@@ -1560,7 +1560,7 @@ xfs_filemap_fault(
* changes to xfs_get_blocks_direct() to map unwritten extent
* ioend for conversion on read-only mappings.
*/
- ret = __dax_fault(vma, vmf, xfs_get_blocks_dax_fault, NULL);
+ ret = dax_fault(vma, vmf, xfs_get_blocks_dax_fault, NULL);
} else
ret = filemap_fault(vma, vmf);
xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
@@ -1571,16 +1571,14 @@ xfs_filemap_fault(
/*
* Similar to xfs_filemap_fault(), the DAX fault path can call into here on
* both read and write faults. Hence we need to handle both cases. There is no
- * ->pmd_mkwrite callout for huge pages, so we have a single function here to
+ * ->huge_mkwrite callout for huge pages, so we have a single function here to
* handle both cases here. @flags carries the information on the type of fault
* occuring.
*/
STATIC int
-xfs_filemap_pmd_fault(
+xfs_filemap_huge_fault(
struct vm_area_struct *vma,
- unsigned long addr,
- pmd_t *pmd,
- unsigned int flags)
+ struct vm_fault *vmf)
{
struct inode *inode = file_inode(vma->vm_file);
struct xfs_inode *ip = XFS_I(inode);
@@ -1589,26 +1587,25 @@ xfs_filemap_pmd_fault(
if (!IS_DAX(inode))
return VM_FAULT_FALLBACK;
- trace_xfs_filemap_pmd_fault(ip);
+ trace_xfs_filemap_huge_fault(ip);
- if (flags & FAULT_FLAG_WRITE) {
+ if (vmf->flags & FAULT_FLAG_WRITE) {
sb_start_pagefault(inode->i_sb);
file_update_time(vma->vm_file);
}
xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
- ret = __dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_dax_fault,
- NULL);
+ ret = dax_fault(vma, vmf, xfs_get_blocks_dax_fault, NULL);
xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
- if (flags & FAULT_FLAG_WRITE)
+ if (vmf->flags & FAULT_FLAG_WRITE)
sb_end_pagefault(inode->i_sb);
return ret;
}
/*
- * pfn_mkwrite was originally inteneded to ensure we capture time stamp
+ * pfn_mkwrite was originally intended to ensure we capture time stamp
* updates on write faults. In reality, it's need to serialise against
* truncate similar to page_mkwrite. Hence we cycle the XFS_MMAPLOCK_SHARED
* to ensure we serialise the fault barrier in place.
@@ -1644,7 +1641,7 @@ xfs_filemap_pfn_mkwrite(
static const struct vm_operations_struct xfs_file_vm_ops = {
.fault = xfs_filemap_fault,
- .pmd_fault = xfs_filemap_pmd_fault,
+ .huge_fault = xfs_filemap_huge_fault,
.map_pages = filemap_map_pages,
.page_mkwrite = xfs_filemap_page_mkwrite,
.pfn_mkwrite = xfs_filemap_pfn_mkwrite,
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 877079eb..8f810db 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -687,7 +687,7 @@ DEFINE_INODE_EVENT(xfs_inode_clear_eofblocks_tag);
DEFINE_INODE_EVENT(xfs_inode_free_eofblocks_invalid);
DEFINE_INODE_EVENT(xfs_filemap_fault);
-DEFINE_INODE_EVENT(xfs_filemap_pmd_fault);
+DEFINE_INODE_EVENT(xfs_filemap_huge_fault);
DEFINE_INODE_EVENT(xfs_filemap_page_mkwrite);
DEFINE_INODE_EVENT(xfs_filemap_pfn_mkwrite);
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 8204c3d..8e58c36 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -12,25 +12,8 @@ int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
int dax_truncate_page(struct inode *, loff_t from, get_block_t);
int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
dax_iodone_t);
-int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
- dax_iodone_t);
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-int dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,
- unsigned int flags, get_block_t, dax_iodone_t);
-int __dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,
- unsigned int flags, get_block_t, dax_iodone_t);
-#else
-static inline int dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
- pmd_t *pmd, unsigned int flags, get_block_t gb,
- dax_iodone_t di)
-{
- return VM_FAULT_FALLBACK;
-}
-#define __dax_pmd_fault dax_pmd_fault
-#endif
int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *);
#define dax_mkwrite(vma, vmf, gb, iod) dax_fault(vma, vmf, gb, iod)
-#define __dax_mkwrite(vma, vmf, gb, iod) __dax_fault(vma, vmf, gb, iod)
static inline bool vma_is_dax(struct vm_area_struct *vma)
{
diff --git a/include/linux/mm.h b/include/linux/mm.h
index e7f08d7..37e25f1 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -232,15 +232,21 @@ extern pgprot_t protection_map[16];
#define FAULT_FLAG_TRIED 0x20 /* Second try */
#define FAULT_FLAG_USER 0x40 /* The fault originated in userspace */
+#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_PGD 0x300 /* Fourth level (eg 512GB) */
+
/*
- * vm_fault is filled by the the pagefault handler and passed to the vma's
+ * vm_fault is filled in by the pagefault handler and passed to the vma's
* ->fault function. The vma's ->fault is responsible for returning a bitmask
* of VM_FAULT_xxx flags that give details about how the fault was handled.
*
* MM layer fills up gfp_mask for page allocations but fault handler might
* alter it if its implementation requires a different allocation context.
*
- * pgoff should be used in favour of virtual_address, if possible.
+ * pgoff should be used instead of virtual_address, if possible.
*/
struct vm_fault {
unsigned int flags; /* FAULT_FLAG_xxx flags */
@@ -257,7 +263,12 @@ struct vm_fault {
/* for ->map_pages() only */
pgoff_t max_pgoff; /* map pages for offset from pgoff till
* max_pgoff inclusive */
- pte_t *pte; /* pte entry associated with ->pgoff */
+ union {
+ pte_t *pte; /* pte entry associated with ->pgoff */
+ pmd_t *pmd;
+ pud_t *pud;
+ pgd_t *pgd;
+ };
};
/*
@@ -270,8 +281,7 @@ struct vm_operations_struct {
void (*close)(struct vm_area_struct * area);
int (*mremap)(struct vm_area_struct * area);
int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
- int (*pmd_fault)(struct vm_area_struct *, unsigned long address,
- pmd_t *, unsigned int flags);
+ int (*huge_fault)(struct vm_area_struct *, struct vm_fault *vmf);
void (*map_pages)(struct vm_area_struct *vma, struct vm_fault *vmf);
/* notification that a previously read-only page is about to become
diff --git a/mm/memory.c b/mm/memory.c
index 4150112..492a228 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3245,10 +3245,16 @@ out:
static int create_huge_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pmd_t *pmd, unsigned int flags)
{
+ struct vm_fault vmf = {
+ .virtual_address = (void __user *)address,
+ .flags = flags | FAULT_FLAG_SIZE_PMD,
+ .pmd = pmd,
+ };
+
if (vma_is_anonymous(vma))
return do_huge_pmd_anonymous_page(mm, vma, address, pmd, flags);
- if (vma->vm_ops->pmd_fault)
- return vma->vm_ops->pmd_fault(vma, address, pmd, flags);
+ if (vma->vm_ops->huge_fault)
+ return vma->vm_ops->huge_fault(vma, &vmf);
return VM_FAULT_FALLBACK;
}
@@ -3256,10 +3262,16 @@ static int wp_huge_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pmd_t *pmd, pmd_t orig_pmd,
unsigned int flags)
{
+ struct vm_fault vmf = {
+ .virtual_address = (void __user *)address,
+ .flags = flags | FAULT_FLAG_SIZE_PMD,
+ .pmd = pmd,
+ };
+
if (vma_is_anonymous(vma))
return do_huge_pmd_wp_page(mm, vma, address, pmd, orig_pmd);
- if (vma->vm_ops->pmd_fault)
- return vma->vm_ops->pmd_fault(vma, address, pmd, flags);
+ if (vma->vm_ops->huge_fault)
+ return vma->vm_ops->huge_fault(vma, &vmf);
return VM_FAULT_FALLBACK;
}
--
2.6.4
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [PATCH v3 3/8] mm: Add support for PUD-sized transparent hugepages
2016-01-08 19:49 ` Matthew Wilcox
@ 2016-01-08 19:49 ` Matthew Wilcox
-1 siblings, 0 replies; 32+ messages in thread
From: Matthew Wilcox @ 2016-01-08 19:49 UTC (permalink / raw)
To: Andrew Morton
Cc: Matthew Wilcox, linux-mm, linux-nvdimm, linux-fsdevel, linux-kernel, x86
From: Matthew Wilcox <willy@linux.intel.com>
The current transparent hugepage code only supports PMDs. This patch
adds support for transparent use of PUDs with DAX. It does not include
support for anonymous pages.
Most of this patch simply parallels the work that was done for huge PMDs.
The only major difference is how the new ->pud_entry method in mm_walk
works. The ->pmd_entry method replaces the ->pte_entry method, whereas
the ->pud_entry method works along with either ->pmd_entry or ->pte_entry.
The pagewalk code takes care of locking the PUD before calling ->pud_walk,
so handlers do not need to worry whether the PUD is stable.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
---
arch/Kconfig | 3 +
include/asm-generic/pgtable.h | 62 +++++++++++++++--
include/asm-generic/tlb.h | 14 ++++
include/linux/huge_mm.h | 50 ++++++++++++++
include/linux/mm.h | 23 +++++++
include/linux/mmu_notifier.h | 13 ++++
include/linux/pfn_t.h | 8 +++
mm/huge_memory.c | 151 ++++++++++++++++++++++++++++++++++++++++++
mm/memory.c | 71 ++++++++++++++++++++
mm/pagewalk.c | 19 +++++-
mm/pgtable-generic.c | 14 ++++
11 files changed, 423 insertions(+), 5 deletions(-)
diff --git a/arch/Kconfig b/arch/Kconfig
index 155e6cd..ab00f4f 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -459,6 +459,9 @@ config HAVE_IRQ_TIME_ACCOUNTING
config HAVE_ARCH_TRANSPARENT_HUGEPAGE
bool
+config HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+ bool
+
config HAVE_ARCH_HUGE_VMAP
bool
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index bdff35e..1127a24 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -36,6 +36,9 @@ extern int ptep_set_access_flags(struct vm_area_struct *vma,
extern int pmdp_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp,
pmd_t entry, int dirty);
+extern int pudp_set_access_flags(struct vm_area_struct *vma,
+ unsigned long address, pud_t *pudp,
+ pud_t entry, int dirty);
#else
static inline int pmdp_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp,
@@ -44,6 +47,13 @@ static inline int pmdp_set_access_flags(struct vm_area_struct *vma,
BUILD_BUG();
return 0;
}
+static inline int pudp_set_access_flags(struct vm_area_struct *vma,
+ unsigned long address, pud_t *pudp,
+ pud_t entry, int dirty)
+{
+ BUILD_BUG();
+ return 0;
+}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif
@@ -121,8 +131,8 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
}
#endif
-#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
unsigned long address,
pmd_t *pmdp)
@@ -131,20 +141,39 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
pmd_clear(pmdp);
return pmd;
}
+#endif /* __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR */
+#ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR
+static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm,
+ unsigned long address,
+ pud_t *pudp)
+{
+ pud_t pud = *pudp;
+ pud_clear(pudp);
+ return pud;
+}
+#endif /* __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR */
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-#endif
-#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR_FULL
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR_FULL
static inline pmd_t pmdp_huge_get_and_clear_full(struct mm_struct *mm,
unsigned long address, pmd_t *pmdp,
int full)
{
return pmdp_huge_get_and_clear(mm, address, pmdp);
}
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif
+#ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR_FULL
+static inline pud_t pudp_huge_get_and_clear_full(struct mm_struct *mm,
+ unsigned long address, pud_t *pudp,
+ int full)
+{
+ return pudp_huge_get_and_clear(mm, address, pudp);
+}
+#endif
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
#ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
unsigned long address, pte_t *ptep,
@@ -181,6 +210,9 @@ extern pte_t ptep_clear_flush(struct vm_area_struct *vma,
extern pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma,
unsigned long address,
pmd_t *pmdp);
+extern pud_t pudp_huge_clear_flush(struct vm_area_struct *vma,
+ unsigned long address,
+ pud_t *pudp);
#endif
#ifndef __HAVE_ARCH_PTEP_SET_WRPROTECT
@@ -265,12 +297,23 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
{
return pmd_val(pmd_a) == pmd_val(pmd_b);
}
+
+static inline int pud_same(pud_t pud_a, pud_t pud_b)
+{
+ return pud_val(pud_a) == pud_val(pud_b);
+}
#else /* CONFIG_TRANSPARENT_HUGEPAGE */
static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
{
BUILD_BUG();
return 0;
}
+
+static inline int pud_same(pud_t pud_a, pud_t pud_b)
+{
+ BUILD_BUG();
+ return 0;
+}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif
@@ -625,6 +668,17 @@ static inline int pmd_write(pmd_t pmd)
#endif /* __HAVE_ARCH_PMD_WRITE */
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#ifndef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+static inline int pud_trans_huge(pud_t pud)
+{
+ return 0;
+}
+static inline int pud_devmap(pud_t pud)
+{
+ return 0;
+}
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
#ifndef pmd_read_atomic
static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
{
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 9dbb739..9d310c8 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -196,6 +196,20 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb)
__tlb_remove_pmd_tlb_entry(tlb, pmdp, address); \
} while (0)
+/**
+ * tlb_remove_pud_tlb_entry - remember a pud mapping for later tlb invalidation
+ * This is a nop so far, because only x86 needs it.
+ */
+#ifndef __tlb_remove_pud_tlb_entry
+#define __tlb_remove_pud_tlb_entry(tlb, pudp, address) do {} while (0)
+#endif
+
+#define tlb_remove_pud_tlb_entry(tlb, pudp, address) \
+ do { \
+ __tlb_adjust_range(tlb, address); \
+ __tlb_remove_pud_tlb_entry(tlb, pudp, address); \
+ } while (0)
+
#define pte_free_tlb(tlb, ptep, address) \
do { \
__tlb_adjust_range(tlb, address); \
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index cfe81e1..d58cd19 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -12,6 +12,20 @@ extern void huge_pmd_set_accessed(struct mm_struct *mm,
struct vm_area_struct *vma,
unsigned long address, pmd_t *pmd,
pmd_t orig_pmd, int dirty);
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+extern void huge_pud_set_accessed(struct mm_struct *mm,
+ struct vm_area_struct *vma,
+ unsigned long address, pud_t *pud,
+ pud_t orig_pud, int dirty);
+#else
+static inline void huge_pud_set_accessed(struct mm_struct *mm,
+ struct vm_area_struct *vma,
+ unsigned long address, pud_t *pud,
+ pud_t orig_pud, int dirty)
+{
+}
+#endif
+
extern int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pmd_t *pmd,
pmd_t orig_pmd);
@@ -25,6 +39,9 @@ extern int madvise_free_huge_pmd(struct mmu_gather *tlb,
extern int zap_huge_pmd(struct mmu_gather *tlb,
struct vm_area_struct *vma,
pmd_t *pmd, unsigned long addr);
+extern int zap_huge_pud(struct mmu_gather *tlb,
+ struct vm_area_struct *vma,
+ pud_t *pud, unsigned long addr);
extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, unsigned long end,
unsigned char *vec);
@@ -38,6 +55,8 @@ extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
int prot_numa);
int vmf_insert_pfn_pmd(struct vm_area_struct *, unsigned long addr, pmd_t *,
pfn_t pfn, bool write);
+int vmf_insert_pfn_pud(struct vm_area_struct *, unsigned long addr, pud_t *,
+ pfn_t pfn, bool write);
enum transparent_hugepage_flag {
TRANSPARENT_HUGEPAGE_FLAG,
TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
@@ -61,6 +80,10 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
#define HPAGE_PMD_SIZE ((1UL) << HPAGE_PMD_SHIFT)
#define HPAGE_PMD_MASK (~(HPAGE_PMD_SIZE - 1))
+#define HPAGE_PUD_SHIFT PUD_SHIFT
+#define HPAGE_PUD_SIZE ((1UL) << HPAGE_PUD_SHIFT)
+#define HPAGE_PUD_MASK (~(HPAGE_PUD_SIZE - 1))
+
extern bool is_vma_temporary_stack(struct vm_area_struct *vma);
#define transparent_hugepage_enabled(__vma) \
@@ -111,6 +134,17 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
__split_huge_pmd(__vma, __pmd, __address); \
} while (0)
+void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud,
+ unsigned long address);
+
+#define split_huge_pud(__vma, __pud, __address) \
+ do { \
+ pud_t *____pud = (__pud); \
+ if (pud_trans_huge(*____pud) \
+ || pud_devmap(*____pud)) \
+ __split_huge_pud(__vma, __pud, __address); \
+ } while (0)
+
#if HPAGE_PMD_ORDER >= MAX_ORDER
#error "hugepages can't be allocated by the buddy allocator"
#endif
@@ -122,6 +156,8 @@ extern void vma_adjust_trans_huge(struct vm_area_struct *vma,
long adjust_next);
extern bool __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
spinlock_t **ptl);
+extern bool __pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma,
+ spinlock_t **ptl);
/* mmap_sem must be held on entry */
static inline bool pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
spinlock_t **ptl)
@@ -132,6 +168,15 @@ static inline bool pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
else
return false;
}
+static inline bool pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma,
+ spinlock_t **ptl)
+{
+ VM_BUG_ON_VMA(!rwsem_is_locked(&vma->vm_mm->mmap_sem), vma);
+ if (pud_trans_huge(*pud) || pud_devmap(*pud))
+ return __pud_trans_huge_lock(pud, vma, ptl);
+ else
+ return false;
+}
static inline int hpage_nr_pages(struct page *page)
{
if (unlikely(PageTransHuge(page)))
@@ -154,6 +199,11 @@ static inline bool is_huge_zero_pmd(pmd_t pmd)
return is_huge_zero_page(pmd_page(pmd));
}
+static inline bool is_huge_zero_pud(pud_t pud)
+{
+ return 0;
+}
+
struct page *get_huge_zero_page(void);
#else /* CONFIG_TRANSPARENT_HUGEPAGE */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 37e25f1..27dbd1b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -345,6 +345,10 @@ static inline int pmd_devmap(pmd_t pmd)
{
return 0;
}
+static inline int pud_devmap(pud_t pud)
+{
+ return 0;
+}
#endif
/*
@@ -1137,6 +1141,10 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
/**
* mm_walk - callbacks for walk_page_range
+ * @pud_entry: if set, called for each non-empty PUD (2nd-level) entry
+ * this handler should only handle pud_trans_huge() puds.
+ * the pmd_entry or pte_entry callbacks will be used for
+ * regular PUDs.
* @pmd_entry: if set, called for each non-empty PMD (3rd-level) entry
* this handler is required to be able to handle
* pmd_trans_huge() pmds. They may simply choose to
@@ -1156,6 +1164,8 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
* (see the comment on walk_page_range() for more details)
*/
struct mm_walk {
+ int (*pud_entry)(pud_t *pud, unsigned long addr,
+ unsigned long next, struct mm_walk *walk);
int (*pmd_entry)(pmd_t *pmd, unsigned long addr,
unsigned long next, struct mm_walk *walk);
int (*pte_entry)(pte_t *pte, unsigned long addr,
@@ -1736,6 +1746,19 @@ static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd)
return ptl;
}
+/*
+ * No scalability reason to split PUD locks yet, but follow the same pattern
+ * as the PMD locks to make it easier if we have to. There are places that
+ * will need to be converted to use pud_lock() instead of explicitly grabbing
+ * the page_table_lock, eg __pud_alloc().
+ */
+static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud)
+{
+ spinlock_t *ptl = &mm->page_table_lock;
+ spin_lock(ptl);
+ return ptl;
+}
+
extern void free_area_init(unsigned long * zones_size);
extern void free_area_init_node(int nid, unsigned long * zones_size,
unsigned long zone_start_pfn, unsigned long *zholes_size);
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index a1a210d..32be698 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -381,6 +381,19 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm)
___pmd; \
})
+#define pudp_huge_clear_flush_notify(__vma, __haddr, __pud) \
+({ \
+ unsigned long ___haddr = __haddr & HPAGE_PUD_MASK; \
+ struct mm_struct *___mm = (__vma)->vm_mm; \
+ pud_t ___pud; \
+ \
+ ___pud = pudp_huge_clear_flush(__vma, __haddr, __pud); \
+ mmu_notifier_invalidate_range(___mm, ___haddr, \
+ ___haddr + HPAGE_PUD_SIZE); \
+ \
+ ___pud; \
+})
+
#define pmdp_huge_get_and_clear_notify(__mm, __haddr, __pmd) \
({ \
unsigned long ___haddr = __haddr & HPAGE_PMD_MASK; \
diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h
index 0703b53..f0edac0 100644
--- a/include/linux/pfn_t.h
+++ b/include/linux/pfn_t.h
@@ -82,6 +82,13 @@ static inline pmd_t pfn_t_pmd(pfn_t pfn, pgprot_t pgprot)
{
return pfn_pmd(pfn_t_to_pfn(pfn), pgprot);
}
+
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+static inline pud_t pfn_t_pud(pfn_t pfn, pgprot_t pgprot)
+{
+ return pfn_pud(pfn_t_to_pfn(pfn), pgprot);
+}
+#endif
#endif
#ifdef __HAVE_ARCH_PTE_DEVMAP
@@ -98,5 +105,6 @@ static inline bool pfn_t_devmap(pfn_t pfn)
}
pte_t pte_mkdevmap(pte_t pte);
pmd_t pmd_mkdevmap(pmd_t pmd);
+pud_t pud_mkdevmap(pud_t pud);
#endif
#endif /* _LINUX_PFN_T_H_ */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 2238525..109be3d 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1005,6 +1005,58 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
return VM_FAULT_NOPAGE;
}
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+static pud_t maybe_pud_mkwrite(pud_t pud, struct vm_area_struct *vma)
+{
+ if (likely(vma->vm_flags & VM_WRITE))
+ pud = pud_mkwrite(pud);
+ return pud;
+}
+
+static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
+ pud_t *pud, pfn_t pfn, pgprot_t prot, bool write)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ pud_t entry;
+ spinlock_t *ptl;
+
+ ptl = pud_lock(mm, pud);
+ entry = pud_mkhuge(pfn_t_pud(pfn, prot));
+ if (pfn_t_devmap(pfn))
+ entry = pud_mkdevmap(entry);
+ if (write) {
+ entry = pud_mkyoung(pud_mkdirty(entry));
+ entry = maybe_pud_mkwrite(entry, vma);
+ }
+ set_pud_at(mm, addr, pud, entry);
+ update_mmu_cache_pud(vma, addr, pud);
+ spin_unlock(ptl);
+}
+
+int vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
+ pud_t *pud, pfn_t pfn, bool write)
+{
+ pgprot_t pgprot = vma->vm_page_prot;
+ /*
+ * If we had pud_special, we could avoid all these restrictions,
+ * but we need to be consistent with PTEs and architectures that
+ * can't support a 'special' bit.
+ */
+ BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)));
+ BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
+ (VM_PFNMAP|VM_MIXEDMAP));
+ BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));
+ BUG_ON(!pfn_t_devmap(pfn));
+
+ if (addr < vma->vm_start || addr >= vma->vm_end)
+ return VM_FAULT_SIGBUS;
+ if (track_pfn_insert(vma, &pgprot, pfn))
+ return VM_FAULT_SIGBUS;
+ insert_pfn_pud(vma, addr, pud, pfn, pgprot, write);
+ return VM_FAULT_NOPAGE;
+}
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
static void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
pmd_t *pmd)
{
@@ -1129,6 +1181,29 @@ out:
return ret;
}
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+void huge_pud_set_accessed(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long address, pud_t *pud, pud_t orig_pud,
+ int dirty)
+{
+ spinlock_t *ptl;
+ pud_t entry;
+ unsigned long haddr;
+
+ ptl = pud_lock(mm, pud);
+ if (unlikely(!pud_same(*pud, orig_pud)))
+ goto unlock;
+
+ entry = pud_mkyoung(orig_pud);
+ haddr = address & HPAGE_PMD_MASK;
+ if (pudp_set_access_flags(vma, haddr, pud, entry, dirty))
+ update_mmu_cache_pud(vma, address, pud);
+
+unlock:
+ spin_unlock(ptl);
+}
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
void huge_pmd_set_accessed(struct mm_struct *mm,
struct vm_area_struct *vma,
unsigned long address,
@@ -1800,6 +1875,22 @@ bool __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
return false;
}
+/*
+ * Returns true if a given pud maps a thp, false otherwise.
+ *
+ * Note that if it returns true, this routine returns without unlocking page
+ * table lock. So callers must unlock it.
+ */
+bool __pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma,
+ spinlock_t **ptl)
+{
+ *ptl = pud_lock(vma->vm_mm, pud);
+ if (likely(pud_trans_huge(*pud) || pud_devmap(*pud)))
+ return true;
+ spin_unlock(*ptl);
+ return false;
+}
+
#define VM_NO_THP (VM_SPECIAL | VM_HUGETLB | VM_SHARED | VM_MAYSHARE)
int hugepage_madvise(struct vm_area_struct *vma,
@@ -2870,6 +2961,66 @@ static int khugepaged(void *none)
return 0;
}
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
+ pud_t *pud, unsigned long addr)
+{
+ pud_t orig_pud;
+ spinlock_t *ptl;
+
+ if (!__pud_trans_huge_lock(pud, vma, &ptl))
+ return 0;
+ /*
+ * For architectures like ppc64 we look at deposited pgtable
+ * when calling pudp_huge_get_and_clear. So do the
+ * pgtable_trans_huge_withdraw after finishing pudp related
+ * operations.
+ */
+ orig_pud = pudp_huge_get_and_clear_full(tlb->mm, addr, pud,
+ tlb->fullmm);
+ tlb_remove_pud_tlb_entry(tlb, pud, addr);
+ if (vma_is_dax(vma)) {
+ spin_unlock(ptl);
+ /* No zero page support yet */
+ } else {
+ /* No support for anonymous PUD pages yet */
+ BUG();
+ }
+ return 1;
+}
+
+static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud,
+ unsigned long haddr)
+{
+ VM_BUG_ON(haddr & ~HPAGE_PUD_MASK);
+ VM_BUG_ON_VMA(vma->vm_start > haddr, vma);
+ VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PUD_SIZE, vma);
+ VM_BUG_ON(!pud_trans_huge(*pud) && !pud_devmap(*pud));
+
+ count_vm_event(THP_SPLIT_PMD);
+
+ pudp_huge_clear_flush_notify(vma, haddr, pud);
+}
+
+void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud,
+ unsigned long address)
+{
+ spinlock_t *ptl;
+ struct mm_struct *mm = vma->vm_mm;
+ unsigned long haddr = address & HPAGE_PUD_MASK;
+
+ mmu_notifier_invalidate_range_start(mm, haddr, haddr + HPAGE_PUD_SIZE);
+ ptl = pud_lock(mm, pud);
+ if (unlikely(!pud_trans_huge(*pud) && !pud_devmap(*pud)))
+ goto out;
+ __split_huge_pud_locked(vma, pud, haddr);
+
+out:
+ spin_unlock(ptl);
+ mmu_notifier_invalidate_range_end(mm, haddr, haddr + HPAGE_PUD_SIZE);
+}
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
unsigned long haddr, pmd_t *pmd)
{
diff --git a/mm/memory.c b/mm/memory.c
index 492a228..708a0c7c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1219,9 +1219,19 @@ static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
pud = pud_offset(pgd, addr);
do {
next = pud_addr_end(addr, end);
+ if (pud_trans_huge(*pud) || pud_devmap(*pud)) {
+ if (next - addr != HPAGE_PUD_SIZE) {
+ VM_BUG_ON_VMA(!rwsem_is_locked(&tlb->mm->mmap_sem), vma);
+ split_huge_pud(vma, pud, addr);
+ } else if (zap_huge_pud(tlb, vma, pud, addr))
+ goto next;
+ /* fall through */
+ }
if (pud_none_or_clear_bad(pud))
continue;
next = zap_pmd_range(tlb, vma, pud, addr, next, details);
+next:
+ cond_resched();
} while (pud++, addr = next, addr != end);
return addr;
@@ -3275,6 +3285,41 @@ static int wp_huge_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
return VM_FAULT_FALLBACK;
}
+static int create_huge_pud(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long address, pud_t *pud, unsigned int flags)
+{
+ struct vm_fault vmf = {
+ .virtual_address = (void __user *)address,
+ .flags = flags | FAULT_FLAG_SIZE_PUD,
+ .pud = pud,
+ };
+
+ /* No support for anonymous transparent PUD pages yet */
+ if (vma_is_anonymous(vma))
+ return VM_FAULT_FALLBACK;
+ if (vma->vm_ops->huge_fault)
+ return vma->vm_ops->huge_fault(vma, &vmf);
+ return VM_FAULT_FALLBACK;
+}
+
+static int wp_huge_pud(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long address, pud_t *pud, pud_t orig_pud,
+ unsigned int flags)
+{
+ struct vm_fault vmf = {
+ .virtual_address = (void __user *)address,
+ .flags = flags | FAULT_FLAG_SIZE_PUD,
+ .pud = pud,
+ };
+
+ /* No support for anonymous transparent PUD pages yet */
+ if (vma_is_anonymous(vma))
+ return VM_FAULT_FALLBACK;
+ if (vma->vm_ops->huge_fault)
+ return vma->vm_ops->huge_fault(vma, &vmf);
+ return VM_FAULT_FALLBACK;
+}
+
/*
* These routines also need to handle stuff like marking pages dirty
* and/or accessed for architectures that don't do it in hardware (most
@@ -3373,6 +3418,32 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
pud = pud_alloc(mm, pgd, address);
if (!pud)
return VM_FAULT_OOM;
+ if (pud_none(*pud) && transparent_hugepage_enabled(vma)) {
+ int ret = create_huge_pud(mm, vma, address, pud, flags);
+ if (!(ret & VM_FAULT_FALLBACK))
+ return ret;
+ } else {
+ pud_t orig_pud = *pud;
+ int ret;
+
+ barrier();
+ if (pud_trans_huge(orig_pud) || pud_devmap(orig_pud)) {
+ unsigned int dirty = flags & FAULT_FLAG_WRITE;
+
+ /* NUMA case for anonymous PUDs would go here */
+
+ if (dirty && !pud_write(orig_pud)) {
+ ret = wp_huge_pud(mm, vma, address, pud,
+ orig_pud, flags);
+ if (!(ret & VM_FAULT_FALLBACK))
+ return ret;
+ } else {
+ huge_pud_set_accessed(mm, vma, address, pud,
+ orig_pud, dirty);
+ return 0;
+ }
+ }
+ }
pmd = pmd_alloc(mm, pud, address);
if (!pmd)
return VM_FAULT_OOM;
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 2072444..200d771 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -78,14 +78,31 @@ static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end,
pud = pud_offset(pgd, addr);
do {
+ again:
next = pud_addr_end(addr, end);
- if (pud_none_or_clear_bad(pud)) {
+ if (pud_none(*pud) || !walk->vma) {
if (walk->pte_hole)
err = walk->pte_hole(addr, next, walk);
if (err)
break;
continue;
}
+
+ if (walk->pud_entry) {
+ spinlock_t *ptl;
+ if (pud_trans_huge_lock(pud, walk->vma, &ptl)) {
+ err = walk->pud_entry(pud, addr, next, walk);
+ spin_unlock(ptl);
+ if (err)
+ break;
+ continue;
+ }
+ }
+
+ split_huge_pud(walk->vma, pud, addr);
+ if (pud_none(*pud))
+ goto again;
+
if (walk->pmd_entry || walk->pte_entry)
err = walk_pmd_range(pud, addr, next, walk);
if (err)
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 9d47676..415fa5a 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -96,6 +96,7 @@ pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address,
* e.g. see arch/arc: flush_pmd_tlb_range
*/
#define flush_pmd_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end)
+#define flush_pud_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end)
#endif
#ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
@@ -137,6 +138,19 @@ pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address,
flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
return pmd;
}
+
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+pud_t pudp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address,
+ pud_t *pudp)
+{
+ pud_t pud;
+ VM_BUG_ON(address & ~HPAGE_PUD_MASK);
+ VM_BUG_ON(!pud_trans_huge(*pudp) && !pud_devmap(*pudp));
+ pud = pudp_huge_get_and_clear(vma->vm_mm, address, pudp);
+ flush_pud_tlb_range(vma, address, address + HPAGE_PUD_SIZE);
+ return pud;
+}
+#endif
#endif
#ifndef __HAVE_ARCH_PGTABLE_DEPOSIT
--
2.6.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [PATCH v3 3/8] mm: Add support for PUD-sized transparent hugepages
@ 2016-01-08 19:49 ` Matthew Wilcox
0 siblings, 0 replies; 32+ messages in thread
From: Matthew Wilcox @ 2016-01-08 19:49 UTC (permalink / raw)
To: Andrew Morton
Cc: Matthew Wilcox, linux-mm, linux-nvdimm, linux-fsdevel, linux-kernel, x86
From: Matthew Wilcox <willy@linux.intel.com>
The current transparent hugepage code only supports PMDs. This patch
adds support for transparent use of PUDs with DAX. It does not include
support for anonymous pages.
Most of this patch simply parallels the work that was done for huge PMDs.
The only major difference is how the new ->pud_entry method in mm_walk
works. The ->pmd_entry method replaces the ->pte_entry method, whereas
the ->pud_entry method works along with either ->pmd_entry or ->pte_entry.
The pagewalk code takes care of locking the PUD before calling ->pud_walk,
so handlers do not need to worry whether the PUD is stable.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
---
arch/Kconfig | 3 +
include/asm-generic/pgtable.h | 62 +++++++++++++++--
include/asm-generic/tlb.h | 14 ++++
include/linux/huge_mm.h | 50 ++++++++++++++
include/linux/mm.h | 23 +++++++
include/linux/mmu_notifier.h | 13 ++++
include/linux/pfn_t.h | 8 +++
mm/huge_memory.c | 151 ++++++++++++++++++++++++++++++++++++++++++
mm/memory.c | 71 ++++++++++++++++++++
mm/pagewalk.c | 19 +++++-
mm/pgtable-generic.c | 14 ++++
11 files changed, 423 insertions(+), 5 deletions(-)
diff --git a/arch/Kconfig b/arch/Kconfig
index 155e6cd..ab00f4f 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -459,6 +459,9 @@ config HAVE_IRQ_TIME_ACCOUNTING
config HAVE_ARCH_TRANSPARENT_HUGEPAGE
bool
+config HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+ bool
+
config HAVE_ARCH_HUGE_VMAP
bool
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index bdff35e..1127a24 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -36,6 +36,9 @@ extern int ptep_set_access_flags(struct vm_area_struct *vma,
extern int pmdp_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp,
pmd_t entry, int dirty);
+extern int pudp_set_access_flags(struct vm_area_struct *vma,
+ unsigned long address, pud_t *pudp,
+ pud_t entry, int dirty);
#else
static inline int pmdp_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp,
@@ -44,6 +47,13 @@ static inline int pmdp_set_access_flags(struct vm_area_struct *vma,
BUILD_BUG();
return 0;
}
+static inline int pudp_set_access_flags(struct vm_area_struct *vma,
+ unsigned long address, pud_t *pudp,
+ pud_t entry, int dirty)
+{
+ BUILD_BUG();
+ return 0;
+}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif
@@ -121,8 +131,8 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
}
#endif
-#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
unsigned long address,
pmd_t *pmdp)
@@ -131,20 +141,39 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
pmd_clear(pmdp);
return pmd;
}
+#endif /* __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR */
+#ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR
+static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm,
+ unsigned long address,
+ pud_t *pudp)
+{
+ pud_t pud = *pudp;
+ pud_clear(pudp);
+ return pud;
+}
+#endif /* __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR */
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-#endif
-#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR_FULL
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR_FULL
static inline pmd_t pmdp_huge_get_and_clear_full(struct mm_struct *mm,
unsigned long address, pmd_t *pmdp,
int full)
{
return pmdp_huge_get_and_clear(mm, address, pmdp);
}
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif
+#ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR_FULL
+static inline pud_t pudp_huge_get_and_clear_full(struct mm_struct *mm,
+ unsigned long address, pud_t *pudp,
+ int full)
+{
+ return pudp_huge_get_and_clear(mm, address, pudp);
+}
+#endif
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
#ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
unsigned long address, pte_t *ptep,
@@ -181,6 +210,9 @@ extern pte_t ptep_clear_flush(struct vm_area_struct *vma,
extern pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma,
unsigned long address,
pmd_t *pmdp);
+extern pud_t pudp_huge_clear_flush(struct vm_area_struct *vma,
+ unsigned long address,
+ pud_t *pudp);
#endif
#ifndef __HAVE_ARCH_PTEP_SET_WRPROTECT
@@ -265,12 +297,23 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
{
return pmd_val(pmd_a) == pmd_val(pmd_b);
}
+
+static inline int pud_same(pud_t pud_a, pud_t pud_b)
+{
+ return pud_val(pud_a) == pud_val(pud_b);
+}
#else /* CONFIG_TRANSPARENT_HUGEPAGE */
static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
{
BUILD_BUG();
return 0;
}
+
+static inline int pud_same(pud_t pud_a, pud_t pud_b)
+{
+ BUILD_BUG();
+ return 0;
+}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif
@@ -625,6 +668,17 @@ static inline int pmd_write(pmd_t pmd)
#endif /* __HAVE_ARCH_PMD_WRITE */
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#ifndef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+static inline int pud_trans_huge(pud_t pud)
+{
+ return 0;
+}
+static inline int pud_devmap(pud_t pud)
+{
+ return 0;
+}
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
#ifndef pmd_read_atomic
static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
{
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 9dbb739..9d310c8 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -196,6 +196,20 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb)
__tlb_remove_pmd_tlb_entry(tlb, pmdp, address); \
} while (0)
+/**
+ * tlb_remove_pud_tlb_entry - remember a pud mapping for later tlb invalidation
+ * This is a nop so far, because only x86 needs it.
+ */
+#ifndef __tlb_remove_pud_tlb_entry
+#define __tlb_remove_pud_tlb_entry(tlb, pudp, address) do {} while (0)
+#endif
+
+#define tlb_remove_pud_tlb_entry(tlb, pudp, address) \
+ do { \
+ __tlb_adjust_range(tlb, address); \
+ __tlb_remove_pud_tlb_entry(tlb, pudp, address); \
+ } while (0)
+
#define pte_free_tlb(tlb, ptep, address) \
do { \
__tlb_adjust_range(tlb, address); \
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index cfe81e1..d58cd19 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -12,6 +12,20 @@ extern void huge_pmd_set_accessed(struct mm_struct *mm,
struct vm_area_struct *vma,
unsigned long address, pmd_t *pmd,
pmd_t orig_pmd, int dirty);
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+extern void huge_pud_set_accessed(struct mm_struct *mm,
+ struct vm_area_struct *vma,
+ unsigned long address, pud_t *pud,
+ pud_t orig_pud, int dirty);
+#else
+static inline void huge_pud_set_accessed(struct mm_struct *mm,
+ struct vm_area_struct *vma,
+ unsigned long address, pud_t *pud,
+ pud_t orig_pud, int dirty)
+{
+}
+#endif
+
extern int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pmd_t *pmd,
pmd_t orig_pmd);
@@ -25,6 +39,9 @@ extern int madvise_free_huge_pmd(struct mmu_gather *tlb,
extern int zap_huge_pmd(struct mmu_gather *tlb,
struct vm_area_struct *vma,
pmd_t *pmd, unsigned long addr);
+extern int zap_huge_pud(struct mmu_gather *tlb,
+ struct vm_area_struct *vma,
+ pud_t *pud, unsigned long addr);
extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, unsigned long end,
unsigned char *vec);
@@ -38,6 +55,8 @@ extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
int prot_numa);
int vmf_insert_pfn_pmd(struct vm_area_struct *, unsigned long addr, pmd_t *,
pfn_t pfn, bool write);
+int vmf_insert_pfn_pud(struct vm_area_struct *, unsigned long addr, pud_t *,
+ pfn_t pfn, bool write);
enum transparent_hugepage_flag {
TRANSPARENT_HUGEPAGE_FLAG,
TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
@@ -61,6 +80,10 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
#define HPAGE_PMD_SIZE ((1UL) << HPAGE_PMD_SHIFT)
#define HPAGE_PMD_MASK (~(HPAGE_PMD_SIZE - 1))
+#define HPAGE_PUD_SHIFT PUD_SHIFT
+#define HPAGE_PUD_SIZE ((1UL) << HPAGE_PUD_SHIFT)
+#define HPAGE_PUD_MASK (~(HPAGE_PUD_SIZE - 1))
+
extern bool is_vma_temporary_stack(struct vm_area_struct *vma);
#define transparent_hugepage_enabled(__vma) \
@@ -111,6 +134,17 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
__split_huge_pmd(__vma, __pmd, __address); \
} while (0)
+void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud,
+ unsigned long address);
+
+#define split_huge_pud(__vma, __pud, __address) \
+ do { \
+ pud_t *____pud = (__pud); \
+ if (pud_trans_huge(*____pud) \
+ || pud_devmap(*____pud)) \
+ __split_huge_pud(__vma, __pud, __address); \
+ } while (0)
+
#if HPAGE_PMD_ORDER >= MAX_ORDER
#error "hugepages can't be allocated by the buddy allocator"
#endif
@@ -122,6 +156,8 @@ extern void vma_adjust_trans_huge(struct vm_area_struct *vma,
long adjust_next);
extern bool __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
spinlock_t **ptl);
+extern bool __pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma,
+ spinlock_t **ptl);
/* mmap_sem must be held on entry */
static inline bool pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
spinlock_t **ptl)
@@ -132,6 +168,15 @@ static inline bool pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
else
return false;
}
+static inline bool pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma,
+ spinlock_t **ptl)
+{
+ VM_BUG_ON_VMA(!rwsem_is_locked(&vma->vm_mm->mmap_sem), vma);
+ if (pud_trans_huge(*pud) || pud_devmap(*pud))
+ return __pud_trans_huge_lock(pud, vma, ptl);
+ else
+ return false;
+}
static inline int hpage_nr_pages(struct page *page)
{
if (unlikely(PageTransHuge(page)))
@@ -154,6 +199,11 @@ static inline bool is_huge_zero_pmd(pmd_t pmd)
return is_huge_zero_page(pmd_page(pmd));
}
+static inline bool is_huge_zero_pud(pud_t pud)
+{
+ return 0;
+}
+
struct page *get_huge_zero_page(void);
#else /* CONFIG_TRANSPARENT_HUGEPAGE */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 37e25f1..27dbd1b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -345,6 +345,10 @@ static inline int pmd_devmap(pmd_t pmd)
{
return 0;
}
+static inline int pud_devmap(pud_t pud)
+{
+ return 0;
+}
#endif
/*
@@ -1137,6 +1141,10 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
/**
* mm_walk - callbacks for walk_page_range
+ * @pud_entry: if set, called for each non-empty PUD (2nd-level) entry
+ * this handler should only handle pud_trans_huge() puds.
+ * the pmd_entry or pte_entry callbacks will be used for
+ * regular PUDs.
* @pmd_entry: if set, called for each non-empty PMD (3rd-level) entry
* this handler is required to be able to handle
* pmd_trans_huge() pmds. They may simply choose to
@@ -1156,6 +1164,8 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
* (see the comment on walk_page_range() for more details)
*/
struct mm_walk {
+ int (*pud_entry)(pud_t *pud, unsigned long addr,
+ unsigned long next, struct mm_walk *walk);
int (*pmd_entry)(pmd_t *pmd, unsigned long addr,
unsigned long next, struct mm_walk *walk);
int (*pte_entry)(pte_t *pte, unsigned long addr,
@@ -1736,6 +1746,19 @@ static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd)
return ptl;
}
+/*
+ * No scalability reason to split PUD locks yet, but follow the same pattern
+ * as the PMD locks to make it easier if we have to. There are places that
+ * will need to be converted to use pud_lock() instead of explicitly grabbing
+ * the page_table_lock, eg __pud_alloc().
+ */
+static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud)
+{
+ spinlock_t *ptl = &mm->page_table_lock;
+ spin_lock(ptl);
+ return ptl;
+}
+
extern void free_area_init(unsigned long * zones_size);
extern void free_area_init_node(int nid, unsigned long * zones_size,
unsigned long zone_start_pfn, unsigned long *zholes_size);
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index a1a210d..32be698 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -381,6 +381,19 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm)
___pmd; \
})
+#define pudp_huge_clear_flush_notify(__vma, __haddr, __pud) \
+({ \
+ unsigned long ___haddr = __haddr & HPAGE_PUD_MASK; \
+ struct mm_struct *___mm = (__vma)->vm_mm; \
+ pud_t ___pud; \
+ \
+ ___pud = pudp_huge_clear_flush(__vma, __haddr, __pud); \
+ mmu_notifier_invalidate_range(___mm, ___haddr, \
+ ___haddr + HPAGE_PUD_SIZE); \
+ \
+ ___pud; \
+})
+
#define pmdp_huge_get_and_clear_notify(__mm, __haddr, __pmd) \
({ \
unsigned long ___haddr = __haddr & HPAGE_PMD_MASK; \
diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h
index 0703b53..f0edac0 100644
--- a/include/linux/pfn_t.h
+++ b/include/linux/pfn_t.h
@@ -82,6 +82,13 @@ static inline pmd_t pfn_t_pmd(pfn_t pfn, pgprot_t pgprot)
{
return pfn_pmd(pfn_t_to_pfn(pfn), pgprot);
}
+
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+static inline pud_t pfn_t_pud(pfn_t pfn, pgprot_t pgprot)
+{
+ return pfn_pud(pfn_t_to_pfn(pfn), pgprot);
+}
+#endif
#endif
#ifdef __HAVE_ARCH_PTE_DEVMAP
@@ -98,5 +105,6 @@ static inline bool pfn_t_devmap(pfn_t pfn)
}
pte_t pte_mkdevmap(pte_t pte);
pmd_t pmd_mkdevmap(pmd_t pmd);
+pud_t pud_mkdevmap(pud_t pud);
#endif
#endif /* _LINUX_PFN_T_H_ */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 2238525..109be3d 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1005,6 +1005,58 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
return VM_FAULT_NOPAGE;
}
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+static pud_t maybe_pud_mkwrite(pud_t pud, struct vm_area_struct *vma)
+{
+ if (likely(vma->vm_flags & VM_WRITE))
+ pud = pud_mkwrite(pud);
+ return pud;
+}
+
+static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
+ pud_t *pud, pfn_t pfn, pgprot_t prot, bool write)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ pud_t entry;
+ spinlock_t *ptl;
+
+ ptl = pud_lock(mm, pud);
+ entry = pud_mkhuge(pfn_t_pud(pfn, prot));
+ if (pfn_t_devmap(pfn))
+ entry = pud_mkdevmap(entry);
+ if (write) {
+ entry = pud_mkyoung(pud_mkdirty(entry));
+ entry = maybe_pud_mkwrite(entry, vma);
+ }
+ set_pud_at(mm, addr, pud, entry);
+ update_mmu_cache_pud(vma, addr, pud);
+ spin_unlock(ptl);
+}
+
+int vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
+ pud_t *pud, pfn_t pfn, bool write)
+{
+ pgprot_t pgprot = vma->vm_page_prot;
+ /*
+ * If we had pud_special, we could avoid all these restrictions,
+ * but we need to be consistent with PTEs and architectures that
+ * can't support a 'special' bit.
+ */
+ BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)));
+ BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
+ (VM_PFNMAP|VM_MIXEDMAP));
+ BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));
+ BUG_ON(!pfn_t_devmap(pfn));
+
+ if (addr < vma->vm_start || addr >= vma->vm_end)
+ return VM_FAULT_SIGBUS;
+ if (track_pfn_insert(vma, &pgprot, pfn))
+ return VM_FAULT_SIGBUS;
+ insert_pfn_pud(vma, addr, pud, pfn, pgprot, write);
+ return VM_FAULT_NOPAGE;
+}
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
static void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
pmd_t *pmd)
{
@@ -1129,6 +1181,29 @@ out:
return ret;
}
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+void huge_pud_set_accessed(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long address, pud_t *pud, pud_t orig_pud,
+ int dirty)
+{
+ spinlock_t *ptl;
+ pud_t entry;
+ unsigned long haddr;
+
+ ptl = pud_lock(mm, pud);
+ if (unlikely(!pud_same(*pud, orig_pud)))
+ goto unlock;
+
+ entry = pud_mkyoung(orig_pud);
+ haddr = address & HPAGE_PMD_MASK;
+ if (pudp_set_access_flags(vma, haddr, pud, entry, dirty))
+ update_mmu_cache_pud(vma, address, pud);
+
+unlock:
+ spin_unlock(ptl);
+}
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
void huge_pmd_set_accessed(struct mm_struct *mm,
struct vm_area_struct *vma,
unsigned long address,
@@ -1800,6 +1875,22 @@ bool __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
return false;
}
+/*
+ * Returns true if a given pud maps a thp, false otherwise.
+ *
+ * Note that if it returns true, this routine returns without unlocking page
+ * table lock. So callers must unlock it.
+ */
+bool __pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma,
+ spinlock_t **ptl)
+{
+ *ptl = pud_lock(vma->vm_mm, pud);
+ if (likely(pud_trans_huge(*pud) || pud_devmap(*pud)))
+ return true;
+ spin_unlock(*ptl);
+ return false;
+}
+
#define VM_NO_THP (VM_SPECIAL | VM_HUGETLB | VM_SHARED | VM_MAYSHARE)
int hugepage_madvise(struct vm_area_struct *vma,
@@ -2870,6 +2961,66 @@ static int khugepaged(void *none)
return 0;
}
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
+ pud_t *pud, unsigned long addr)
+{
+ pud_t orig_pud;
+ spinlock_t *ptl;
+
+ if (!__pud_trans_huge_lock(pud, vma, &ptl))
+ return 0;
+ /*
+ * For architectures like ppc64 we look at deposited pgtable
+ * when calling pudp_huge_get_and_clear. So do the
+ * pgtable_trans_huge_withdraw after finishing pudp related
+ * operations.
+ */
+ orig_pud = pudp_huge_get_and_clear_full(tlb->mm, addr, pud,
+ tlb->fullmm);
+ tlb_remove_pud_tlb_entry(tlb, pud, addr);
+ if (vma_is_dax(vma)) {
+ spin_unlock(ptl);
+ /* No zero page support yet */
+ } else {
+ /* No support for anonymous PUD pages yet */
+ BUG();
+ }
+ return 1;
+}
+
+static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud,
+ unsigned long haddr)
+{
+ VM_BUG_ON(haddr & ~HPAGE_PUD_MASK);
+ VM_BUG_ON_VMA(vma->vm_start > haddr, vma);
+ VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PUD_SIZE, vma);
+ VM_BUG_ON(!pud_trans_huge(*pud) && !pud_devmap(*pud));
+
+ count_vm_event(THP_SPLIT_PMD);
+
+ pudp_huge_clear_flush_notify(vma, haddr, pud);
+}
+
+void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud,
+ unsigned long address)
+{
+ spinlock_t *ptl;
+ struct mm_struct *mm = vma->vm_mm;
+ unsigned long haddr = address & HPAGE_PUD_MASK;
+
+ mmu_notifier_invalidate_range_start(mm, haddr, haddr + HPAGE_PUD_SIZE);
+ ptl = pud_lock(mm, pud);
+ if (unlikely(!pud_trans_huge(*pud) && !pud_devmap(*pud)))
+ goto out;
+ __split_huge_pud_locked(vma, pud, haddr);
+
+out:
+ spin_unlock(ptl);
+ mmu_notifier_invalidate_range_end(mm, haddr, haddr + HPAGE_PUD_SIZE);
+}
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
unsigned long haddr, pmd_t *pmd)
{
diff --git a/mm/memory.c b/mm/memory.c
index 492a228..708a0c7c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1219,9 +1219,19 @@ static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
pud = pud_offset(pgd, addr);
do {
next = pud_addr_end(addr, end);
+ if (pud_trans_huge(*pud) || pud_devmap(*pud)) {
+ if (next - addr != HPAGE_PUD_SIZE) {
+ VM_BUG_ON_VMA(!rwsem_is_locked(&tlb->mm->mmap_sem), vma);
+ split_huge_pud(vma, pud, addr);
+ } else if (zap_huge_pud(tlb, vma, pud, addr))
+ goto next;
+ /* fall through */
+ }
if (pud_none_or_clear_bad(pud))
continue;
next = zap_pmd_range(tlb, vma, pud, addr, next, details);
+next:
+ cond_resched();
} while (pud++, addr = next, addr != end);
return addr;
@@ -3275,6 +3285,41 @@ static int wp_huge_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
return VM_FAULT_FALLBACK;
}
+static int create_huge_pud(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long address, pud_t *pud, unsigned int flags)
+{
+ struct vm_fault vmf = {
+ .virtual_address = (void __user *)address,
+ .flags = flags | FAULT_FLAG_SIZE_PUD,
+ .pud = pud,
+ };
+
+ /* No support for anonymous transparent PUD pages yet */
+ if (vma_is_anonymous(vma))
+ return VM_FAULT_FALLBACK;
+ if (vma->vm_ops->huge_fault)
+ return vma->vm_ops->huge_fault(vma, &vmf);
+ return VM_FAULT_FALLBACK;
+}
+
+static int wp_huge_pud(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long address, pud_t *pud, pud_t orig_pud,
+ unsigned int flags)
+{
+ struct vm_fault vmf = {
+ .virtual_address = (void __user *)address,
+ .flags = flags | FAULT_FLAG_SIZE_PUD,
+ .pud = pud,
+ };
+
+ /* No support for anonymous transparent PUD pages yet */
+ if (vma_is_anonymous(vma))
+ return VM_FAULT_FALLBACK;
+ if (vma->vm_ops->huge_fault)
+ return vma->vm_ops->huge_fault(vma, &vmf);
+ return VM_FAULT_FALLBACK;
+}
+
/*
* These routines also need to handle stuff like marking pages dirty
* and/or accessed for architectures that don't do it in hardware (most
@@ -3373,6 +3418,32 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
pud = pud_alloc(mm, pgd, address);
if (!pud)
return VM_FAULT_OOM;
+ if (pud_none(*pud) && transparent_hugepage_enabled(vma)) {
+ int ret = create_huge_pud(mm, vma, address, pud, flags);
+ if (!(ret & VM_FAULT_FALLBACK))
+ return ret;
+ } else {
+ pud_t orig_pud = *pud;
+ int ret;
+
+ barrier();
+ if (pud_trans_huge(orig_pud) || pud_devmap(orig_pud)) {
+ unsigned int dirty = flags & FAULT_FLAG_WRITE;
+
+ /* NUMA case for anonymous PUDs would go here */
+
+ if (dirty && !pud_write(orig_pud)) {
+ ret = wp_huge_pud(mm, vma, address, pud,
+ orig_pud, flags);
+ if (!(ret & VM_FAULT_FALLBACK))
+ return ret;
+ } else {
+ huge_pud_set_accessed(mm, vma, address, pud,
+ orig_pud, dirty);
+ return 0;
+ }
+ }
+ }
pmd = pmd_alloc(mm, pud, address);
if (!pmd)
return VM_FAULT_OOM;
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 2072444..200d771 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -78,14 +78,31 @@ static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end,
pud = pud_offset(pgd, addr);
do {
+ again:
next = pud_addr_end(addr, end);
- if (pud_none_or_clear_bad(pud)) {
+ if (pud_none(*pud) || !walk->vma) {
if (walk->pte_hole)
err = walk->pte_hole(addr, next, walk);
if (err)
break;
continue;
}
+
+ if (walk->pud_entry) {
+ spinlock_t *ptl;
+ if (pud_trans_huge_lock(pud, walk->vma, &ptl)) {
+ err = walk->pud_entry(pud, addr, next, walk);
+ spin_unlock(ptl);
+ if (err)
+ break;
+ continue;
+ }
+ }
+
+ split_huge_pud(walk->vma, pud, addr);
+ if (pud_none(*pud))
+ goto again;
+
if (walk->pmd_entry || walk->pte_entry)
err = walk_pmd_range(pud, addr, next, walk);
if (err)
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 9d47676..415fa5a 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -96,6 +96,7 @@ pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address,
* e.g. see arch/arc: flush_pmd_tlb_range
*/
#define flush_pmd_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end)
+#define flush_pud_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end)
#endif
#ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
@@ -137,6 +138,19 @@ pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address,
flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
return pmd;
}
+
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+pud_t pudp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address,
+ pud_t *pudp)
+{
+ pud_t pud;
+ VM_BUG_ON(address & ~HPAGE_PUD_MASK);
+ VM_BUG_ON(!pud_trans_huge(*pudp) && !pud_devmap(*pudp));
+ pud = pudp_huge_get_and_clear(vma->vm_mm, address, pudp);
+ flush_pud_tlb_range(vma, address, address + HPAGE_PUD_SIZE);
+ return pud;
+}
+#endif
#endif
#ifndef __HAVE_ARCH_PGTABLE_DEPOSIT
--
2.6.4
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [PATCH v3 4/8] mincore: Add support for PUDs
2016-01-08 19:49 ` Matthew Wilcox
@ 2016-01-08 19:49 ` Matthew Wilcox
-1 siblings, 0 replies; 32+ messages in thread
From: Matthew Wilcox @ 2016-01-08 19:49 UTC (permalink / raw)
To: Andrew Morton
Cc: Matthew Wilcox, linux-mm, linux-nvdimm, linux-fsdevel, linux-kernel, x86
From: Matthew Wilcox <willy@linux.intel.com>
We don't actually care about the contents of the PUD, as long as it's
present (which is checked by the pagewalk code), so just set the bits
to indicate presence and return.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
---
mm/mincore.c | 13 +++++++++++++
1 file changed, 13 insertions(+)
diff --git a/mm/mincore.c b/mm/mincore.c
index 2a565ed..8e6ce12 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -108,6 +108,18 @@ static int mincore_unmapped_range(unsigned long addr, unsigned long end,
return 0;
}
+static int mincore_pud_range(pud_t *pud, unsigned long addr, unsigned long end,
+ struct mm_walk *walk)
+{
+ unsigned char *vec = walk->private;
+ int nr = (end - addr) >> PAGE_SHIFT;
+
+ memset(vec, 1, nr);
+ walk->private += nr;
+
+ return 0;
+}
+
static int mincore_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
@@ -176,6 +188,7 @@ static long do_mincore(unsigned long addr, unsigned long pages, unsigned char *v
unsigned long end;
int err;
struct mm_walk mincore_walk = {
+ .pud_entry = mincore_pud_range,
.pmd_entry = mincore_pte_range,
.pte_hole = mincore_unmapped_range,
.hugetlb_entry = mincore_hugetlb,
--
2.6.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [PATCH v3 4/8] mincore: Add support for PUDs
@ 2016-01-08 19:49 ` Matthew Wilcox
0 siblings, 0 replies; 32+ messages in thread
From: Matthew Wilcox @ 2016-01-08 19:49 UTC (permalink / raw)
To: Andrew Morton
Cc: Matthew Wilcox, linux-mm, linux-nvdimm, linux-fsdevel, linux-kernel, x86
From: Matthew Wilcox <willy@linux.intel.com>
We don't actually care about the contents of the PUD, as long as it's
present (which is checked by the pagewalk code), so just set the bits
to indicate presence and return.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
---
mm/mincore.c | 13 +++++++++++++
1 file changed, 13 insertions(+)
diff --git a/mm/mincore.c b/mm/mincore.c
index 2a565ed..8e6ce12 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -108,6 +108,18 @@ static int mincore_unmapped_range(unsigned long addr, unsigned long end,
return 0;
}
+static int mincore_pud_range(pud_t *pud, unsigned long addr, unsigned long end,
+ struct mm_walk *walk)
+{
+ unsigned char *vec = walk->private;
+ int nr = (end - addr) >> PAGE_SHIFT;
+
+ memset(vec, 1, nr);
+ walk->private += nr;
+
+ return 0;
+}
+
static int mincore_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
@@ -176,6 +188,7 @@ static long do_mincore(unsigned long addr, unsigned long pages, unsigned char *v
unsigned long end;
int err;
struct mm_walk mincore_walk = {
+ .pud_entry = mincore_pud_range,
.pmd_entry = mincore_pte_range,
.pte_hole = mincore_unmapped_range,
.hugetlb_entry = mincore_hugetlb,
--
2.6.4
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [PATCH v3 5/8] procfs: Add support for PUDs to smaps, clear_refs and pagemap
2016-01-08 19:49 ` Matthew Wilcox
@ 2016-01-08 19:49 ` Matthew Wilcox
-1 siblings, 0 replies; 32+ messages in thread
From: Matthew Wilcox @ 2016-01-08 19:49 UTC (permalink / raw)
To: Andrew Morton
Cc: Matthew Wilcox, linux-mm, linux-nvdimm, linux-fsdevel, linux-kernel, x86
From: Matthew Wilcox <willy@linux.intel.com>
Because there's no 'struct page' for DAX THPs, a lot of this code is
simpler than the PMD code it mimics. Extra code would need to be added
to support PUDs of anonymous or page-cache THPs.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
---
fs/proc/task_mmu.c | 109 +++++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 109 insertions(+)
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 65a1b6c..e45cbc2 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -595,6 +595,33 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
}
#endif
+static int smaps_pud_range(pud_t *pud, unsigned long addr, unsigned long end,
+ struct mm_walk *walk)
+{
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+ struct vm_area_struct *vma = walk->vma;
+ struct mem_size_stats *mss = walk->private;
+
+ if (is_huge_zero_pud(*pud))
+ return 0;
+
+ mss->resident += HPAGE_PUD_SIZE;
+ if (vma->vm_flags & VM_SHARED) {
+ if (pud_dirty(*pud))
+ mss->shared_dirty += HPAGE_PUD_SIZE;
+ else
+ mss->shared_clean += HPAGE_PUD_SIZE;
+ } else {
+ if (pud_dirty(*pud))
+ mss->private_dirty += HPAGE_PUD_SIZE;
+ else
+ mss->private_clean += HPAGE_PUD_SIZE;
+ }
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
+ return 0;
+}
+
static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
@@ -715,6 +742,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
struct vm_area_struct *vma = v;
struct mem_size_stats mss;
struct mm_walk smaps_walk = {
+ .pud_entry = smaps_pud_range,
.pmd_entry = smaps_pte_range,
#ifdef CONFIG_HUGETLB_PAGE
.hugetlb_entry = smaps_hugetlb_range,
@@ -897,13 +925,50 @@ static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
set_pmd_at(vma->vm_mm, addr, pmdp, pmd);
}
+static inline void clear_soft_dirty_pud(struct vm_area_struct *vma,
+ unsigned long addr, pud_t *pudp)
+{
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+ pud_t pud = pudp_huge_get_and_clear(vma->vm_mm, addr, pudp);
+
+ pud = pud_wrprotect(pud);
+ pud = pud_clear_soft_dirty(pud);
+
+ if (vma->vm_flags & VM_SOFTDIRTY)
+ vma->vm_flags &= ~VM_SOFTDIRTY;
+
+ set_pud_at(vma->vm_mm, addr, pudp, pud);
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+}
#else
static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
unsigned long addr, pmd_t *pmdp)
{
}
+static inline void clear_soft_dirty_pud(struct vm_area_struct *vma,
+ unsigned long addr, pud_t *pudp)
+{
+}
#endif
+static int clear_refs_pud_range(pud_t *pud, unsigned long addr,
+ unsigned long end, struct mm_walk *walk)
+{
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+ struct clear_refs_private *cp = walk->private;
+ struct vm_area_struct *vma = walk->vma;
+
+ if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
+ clear_soft_dirty_pud(vma, addr, pud);
+ } else {
+ /* Clear accessed and referenced bits. */
+ pudp_test_and_clear_young(vma, addr, pud);
+ }
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
+ return 0;
+}
+
static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
unsigned long end, struct mm_walk *walk)
{
@@ -1013,6 +1078,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
.type = type,
};
struct mm_walk clear_refs_walk = {
+ .pud_entry = clear_refs_pud_range,
.pmd_entry = clear_refs_pte_range,
.test_walk = clear_refs_test_walk,
.mm = mm,
@@ -1177,6 +1243,48 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
return make_pme(frame, flags);
}
+static int pagemap_pud_range(pud_t *pudp, unsigned long addr, unsigned long end,
+ struct mm_walk *walk)
+{
+ int err = 0;
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+ struct vm_area_struct *vma = walk->vma;
+ struct pagemapread *pm = walk->private;
+ u64 flags = 0, frame = 0;
+ pud_t pud = *pudp;
+
+ if ((vma->vm_flags & VM_SOFTDIRTY) || pud_soft_dirty(pud))
+ flags |= PM_SOFT_DIRTY;
+
+ /*
+ * Currently pud for thp is always present because thp
+ * can not be swapped-out, migrated, or HWPOISONed
+ * (split in such cases instead.)
+ * This if-check is just to prepare for future implementation.
+ */
+ if (pud_present(pud)) {
+ flags |= PM_PRESENT;
+ if (!(vma->vm_flags & VM_SHARED))
+ flags |= PM_MMAP_EXCLUSIVE;
+
+ if (pm->show_pfn)
+ frame = pud_pfn(pud) +
+ ((addr & ~PUD_MASK) >> PAGE_SHIFT);
+
+ for (; addr != end; addr += PAGE_SIZE) {
+ pagemap_entry_t pme = make_pme(frame, flags);
+
+ err = add_to_pagemap(addr, &pme, pm);
+ if (err)
+ break;
+ if (pm->show_pfn && (flags & PM_PRESENT))
+ frame++;
+ }
+ }
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+ return err;
+}
+
static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
@@ -1355,6 +1463,7 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
if (!pm.buffer)
goto out_mm;
+ pagemap_walk.pud_entry = pagemap_pud_range;
pagemap_walk.pmd_entry = pagemap_pmd_range;
pagemap_walk.pte_hole = pagemap_pte_hole;
#ifdef CONFIG_HUGETLB_PAGE
--
2.6.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [PATCH v3 5/8] procfs: Add support for PUDs to smaps, clear_refs and pagemap
@ 2016-01-08 19:49 ` Matthew Wilcox
0 siblings, 0 replies; 32+ messages in thread
From: Matthew Wilcox @ 2016-01-08 19:49 UTC (permalink / raw)
To: Andrew Morton
Cc: Matthew Wilcox, linux-mm, linux-nvdimm, linux-fsdevel, linux-kernel, x86
From: Matthew Wilcox <willy@linux.intel.com>
Because there's no 'struct page' for DAX THPs, a lot of this code is
simpler than the PMD code it mimics. Extra code would need to be added
to support PUDs of anonymous or page-cache THPs.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
---
fs/proc/task_mmu.c | 109 +++++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 109 insertions(+)
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 65a1b6c..e45cbc2 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -595,6 +595,33 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
}
#endif
+static int smaps_pud_range(pud_t *pud, unsigned long addr, unsigned long end,
+ struct mm_walk *walk)
+{
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+ struct vm_area_struct *vma = walk->vma;
+ struct mem_size_stats *mss = walk->private;
+
+ if (is_huge_zero_pud(*pud))
+ return 0;
+
+ mss->resident += HPAGE_PUD_SIZE;
+ if (vma->vm_flags & VM_SHARED) {
+ if (pud_dirty(*pud))
+ mss->shared_dirty += HPAGE_PUD_SIZE;
+ else
+ mss->shared_clean += HPAGE_PUD_SIZE;
+ } else {
+ if (pud_dirty(*pud))
+ mss->private_dirty += HPAGE_PUD_SIZE;
+ else
+ mss->private_clean += HPAGE_PUD_SIZE;
+ }
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
+ return 0;
+}
+
static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
@@ -715,6 +742,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
struct vm_area_struct *vma = v;
struct mem_size_stats mss;
struct mm_walk smaps_walk = {
+ .pud_entry = smaps_pud_range,
.pmd_entry = smaps_pte_range,
#ifdef CONFIG_HUGETLB_PAGE
.hugetlb_entry = smaps_hugetlb_range,
@@ -897,13 +925,50 @@ static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
set_pmd_at(vma->vm_mm, addr, pmdp, pmd);
}
+static inline void clear_soft_dirty_pud(struct vm_area_struct *vma,
+ unsigned long addr, pud_t *pudp)
+{
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+ pud_t pud = pudp_huge_get_and_clear(vma->vm_mm, addr, pudp);
+
+ pud = pud_wrprotect(pud);
+ pud = pud_clear_soft_dirty(pud);
+
+ if (vma->vm_flags & VM_SOFTDIRTY)
+ vma->vm_flags &= ~VM_SOFTDIRTY;
+
+ set_pud_at(vma->vm_mm, addr, pudp, pud);
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+}
#else
static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
unsigned long addr, pmd_t *pmdp)
{
}
+static inline void clear_soft_dirty_pud(struct vm_area_struct *vma,
+ unsigned long addr, pud_t *pudp)
+{
+}
#endif
+static int clear_refs_pud_range(pud_t *pud, unsigned long addr,
+ unsigned long end, struct mm_walk *walk)
+{
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+ struct clear_refs_private *cp = walk->private;
+ struct vm_area_struct *vma = walk->vma;
+
+ if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
+ clear_soft_dirty_pud(vma, addr, pud);
+ } else {
+ /* Clear accessed and referenced bits. */
+ pudp_test_and_clear_young(vma, addr, pud);
+ }
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
+ return 0;
+}
+
static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
unsigned long end, struct mm_walk *walk)
{
@@ -1013,6 +1078,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
.type = type,
};
struct mm_walk clear_refs_walk = {
+ .pud_entry = clear_refs_pud_range,
.pmd_entry = clear_refs_pte_range,
.test_walk = clear_refs_test_walk,
.mm = mm,
@@ -1177,6 +1243,48 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
return make_pme(frame, flags);
}
+static int pagemap_pud_range(pud_t *pudp, unsigned long addr, unsigned long end,
+ struct mm_walk *walk)
+{
+ int err = 0;
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+ struct vm_area_struct *vma = walk->vma;
+ struct pagemapread *pm = walk->private;
+ u64 flags = 0, frame = 0;
+ pud_t pud = *pudp;
+
+ if ((vma->vm_flags & VM_SOFTDIRTY) || pud_soft_dirty(pud))
+ flags |= PM_SOFT_DIRTY;
+
+ /*
+ * Currently pud for thp is always present because thp
+ * can not be swapped-out, migrated, or HWPOISONed
+ * (split in such cases instead.)
+ * This if-check is just to prepare for future implementation.
+ */
+ if (pud_present(pud)) {
+ flags |= PM_PRESENT;
+ if (!(vma->vm_flags & VM_SHARED))
+ flags |= PM_MMAP_EXCLUSIVE;
+
+ if (pm->show_pfn)
+ frame = pud_pfn(pud) +
+ ((addr & ~PUD_MASK) >> PAGE_SHIFT);
+
+ for (; addr != end; addr += PAGE_SIZE) {
+ pagemap_entry_t pme = make_pme(frame, flags);
+
+ err = add_to_pagemap(addr, &pme, pm);
+ if (err)
+ break;
+ if (pm->show_pfn && (flags & PM_PRESENT))
+ frame++;
+ }
+ }
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+ return err;
+}
+
static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
@@ -1355,6 +1463,7 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
if (!pm.buffer)
goto out_mm;
+ pagemap_walk.pud_entry = pagemap_pud_range;
pagemap_walk.pmd_entry = pagemap_pmd_range;
pagemap_walk.pte_hole = pagemap_pte_hole;
#ifdef CONFIG_HUGETLB_PAGE
--
2.6.4
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [PATCH v3 6/8] x86: Add support for PUD-sized transparent hugepages
2016-01-08 19:49 ` Matthew Wilcox
@ 2016-01-08 19:49 ` Matthew Wilcox
-1 siblings, 0 replies; 32+ messages in thread
From: Matthew Wilcox @ 2016-01-08 19:49 UTC (permalink / raw)
To: Andrew Morton
Cc: Matthew Wilcox, linux-mm, linux-nvdimm, linux-fsdevel, linux-kernel, x86
From: Matthew Wilcox <willy@linux.intel.com>
The x86-specific code needed to support the PUD uses in the transparent
hugepages code.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
---
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 | 94 +++++++++++++++++++++++++++++++++++
arch/x86/include/asm/pgtable_64.h | 13 +++++
arch/x86/kernel/paravirt.c | 1 +
arch/x86/mm/pgtable.c | 31 ++++++++++++
7 files changed, 153 insertions(+)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 497b8ff..c40e60c 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -90,6 +90,7 @@ config X86
select HAVE_ARCH_SOFT_DIRTY if X86_64
select HAVE_ARCH_TRACEHOOK
select HAVE_ARCH_TRANSPARENT_HUGEPAGE
+ select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD if X86_64
select HAVE_BPF_JIT if X86_64
select HAVE_CC_STACKPROTECTOR
select HAVE_CMPXCHG_DOUBLE
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index f619250..46fd557 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -485,6 +485,17 @@ static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
native_pmd_val(pmd));
}
+static inline void set_pud_at(struct mm_struct *mm, unsigned long addr,
+ pud_t *pudp, pud_t pud)
+{
+ if (sizeof(pudval_t) > sizeof(long))
+ /* 5 arg words */
+ pv_mmu_ops.set_pud_at(mm, addr, pudp, pud);
+ else
+ PVOP_VCALL4(pv_mmu_ops.set_pud_at, mm, addr, pudp,
+ native_pud_val(pud));
+}
+
static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
{
pmdval_t val = native_pmd_val(pmd);
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 77db561..56e27e2 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -252,6 +252,8 @@ struct pv_mmu_ops {
void (*set_pmd)(pmd_t *pmdp, pmd_t pmdval);
void (*set_pmd_at)(struct mm_struct *mm, unsigned long addr,
pmd_t *pmdp, pmd_t pmdval);
+ void (*set_pud_at)(struct mm_struct *mm, unsigned long addr,
+ pud_t *pudp, pud_t pudval);
void (*pte_update)(struct mm_struct *mm, unsigned long addr,
pte_t *ptep);
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 0687c47..57f0eed 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -46,6 +46,7 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page);
#define set_pte(ptep, pte) native_set_pte(ptep, pte)
#define set_pte_at(mm, addr, ptep, pte) native_set_pte_at(mm, addr, ptep, pte)
#define set_pmd_at(mm, addr, pmdp, pmd) native_set_pmd_at(mm, addr, pmdp, pmd)
+#define set_pud_at(mm, addr, pudp, pud) native_set_pud_at(mm, addr, pudp, pud)
#define set_pte_atomic(ptep, pte) \
native_set_pte_atomic(ptep, pte)
@@ -114,6 +115,16 @@ static inline int pmd_young(pmd_t pmd)
return pmd_flags(pmd) & _PAGE_ACCESSED;
}
+static inline int pud_dirty(pud_t pud)
+{
+ return pud_flags(pud) & _PAGE_DIRTY;
+}
+
+static inline int pud_young(pud_t pud)
+{
+ return pud_flags(pud) & _PAGE_ACCESSED;
+}
+
static inline int pte_write(pte_t pte)
{
return pte_flags(pte) & _PAGE_RW;
@@ -167,6 +178,11 @@ static inline int pmd_trans_huge(pmd_t pmd)
return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE;
}
+static inline int pud_trans_huge(pud_t pud)
+{
+ return (pud_val(pud) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE;
+}
+
static inline int has_transparent_hugepage(void)
{
return cpu_has_pse;
@@ -177,6 +193,11 @@ static inline int pmd_devmap(pmd_t pmd)
{
return !!(pmd_val(pmd) & _PAGE_DEVMAP);
}
+
+static inline int pud_devmap(pud_t pud)
+{
+ return !!(pud_val(pud) & _PAGE_DEVMAP);
+}
#endif
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
@@ -318,6 +339,45 @@ static inline pmd_t pmd_mknotpresent(pmd_t pmd)
return pmd_clear_flags(pmd, _PAGE_PRESENT | _PAGE_PROTNONE);
}
+static inline pud_t pud_set_flags(pud_t pud, pudval_t set)
+{
+ pudval_t v = native_pud_val(pud);
+
+ return __pud(v | set);
+}
+
+static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear)
+{
+ pudval_t v = native_pud_val(pud);
+
+ return __pud(v & ~clear);
+}
+
+static inline pud_t pud_mkdevmap(pud_t pud)
+{
+ return pud_set_flags(pud, _PAGE_DEVMAP);
+}
+
+static inline pud_t pud_mkhuge(pud_t pud)
+{
+ return pud_set_flags(pud, _PAGE_PSE);
+}
+
+static inline pud_t pud_mkdirty(pud_t pud)
+{
+ return pud_set_flags(pud, _PAGE_DIRTY | _PAGE_SOFT_DIRTY);
+}
+
+static inline pud_t pud_mkyoung(pud_t pud)
+{
+ return pud_set_flags(pud, _PAGE_ACCESSED);
+}
+
+static inline pud_t pud_mkwrite(pud_t pud)
+{
+ return pud_set_flags(pud, _PAGE_RW);
+}
+
#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
static inline int pte_soft_dirty(pte_t pte)
{
@@ -329,6 +389,11 @@ static inline int pmd_soft_dirty(pmd_t pmd)
return pmd_flags(pmd) & _PAGE_SOFT_DIRTY;
}
+static inline int pud_soft_dirty(pud_t pud)
+{
+ return pud_flags(pud) & _PAGE_SOFT_DIRTY;
+}
+
static inline pte_t pte_mksoft_dirty(pte_t pte)
{
return pte_set_flags(pte, _PAGE_SOFT_DIRTY);
@@ -377,6 +442,13 @@ static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
massage_pgprot(pgprot));
}
+#define pfn_pud pfn_pud
+static inline pud_t pfn_pud(unsigned long page_nr, pgprot_t pgprot)
+{
+ return __pud(((phys_addr_t)page_nr << PAGE_SHIFT) |
+ massage_pgprot(pgprot));
+}
+
static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
{
pteval_t val = pte_val(pte);
@@ -744,6 +816,12 @@ static inline void native_set_pmd_at(struct mm_struct *mm, unsigned long addr,
native_set_pmd(pmdp, pmd);
}
+static inline void native_set_pud_at(struct mm_struct *mm, unsigned long addr,
+ pud_t *pudp , pud_t pud)
+{
+ native_set_pud(pudp, pud);
+}
+
#ifndef CONFIG_PARAVIRT
/*
* Rules for using pte_update - it must be called after any PTE update which
@@ -822,10 +900,15 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm,
extern int pmdp_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp,
pmd_t entry, int dirty);
+extern int pudp_set_access_flags(struct vm_area_struct *vma,
+ unsigned long address, pud_t *pudp,
+ pud_t entry, int dirty);
#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
extern int pmdp_test_and_clear_young(struct vm_area_struct *vma,
unsigned long addr, pmd_t *pmdp);
+extern int pudp_test_and_clear_young(struct vm_area_struct *vma,
+ unsigned long addr, pud_t *pudp);
#define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
@@ -845,6 +928,13 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long
return native_pmdp_get_and_clear(pmdp);
}
+#define __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR
+static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr,
+ pud_t *pudp)
+{
+ return native_pudp_get_and_clear(pudp);
+}
+
#define __HAVE_ARCH_PMDP_SET_WRPROTECT
static inline void pmdp_set_wrprotect(struct mm_struct *mm,
unsigned long addr, pmd_t *pmdp)
@@ -893,6 +983,10 @@ static inline void update_mmu_cache_pmd(struct vm_area_struct *vma,
unsigned long addr, pmd_t *pmd)
{
}
+static inline void update_mmu_cache_pud(struct vm_area_struct *vma,
+ unsigned long addr, pud_t *pud)
+{
+}
#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 2ee7811..a3aa6b7 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -106,6 +106,19 @@ static inline void native_pud_clear(pud_t *pud)
native_set_pud(pud, native_make_pud(0));
}
+static inline pud_t native_pudp_get_and_clear(pud_t *pudp)
+{
+#ifdef CONFIG_SMP
+ return native_make_pud(xchg(&pudp->pud, 0));
+#else
+ /* native_local_pudp_get_and_clear,
+ but duplicated because of cyclic dependency */
+ pud_t ret = *pudp;
+ native_pud_clear(pudp);
+ return ret;
+#endif
+}
+
static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
{
*pgdp = pgd;
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index f08ac28..24d61f2 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -425,6 +425,7 @@ struct pv_mmu_ops pv_mmu_ops = {
.pmd_clear = native_pmd_clear,
#endif
.set_pud = native_set_pud,
+ .set_pud_at = native_set_pud_at,
.pmd_val = PTE_IDENT,
.make_pmd = PTE_IDENT,
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 4eb287e..b7c8df6 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -441,6 +441,26 @@ int pmdp_set_access_flags(struct vm_area_struct *vma,
return changed;
}
+
+int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address,
+ pud_t *pudp, pud_t entry, int dirty)
+{
+ int changed = !pud_same(*pudp, entry);
+
+ VM_BUG_ON(address & ~HPAGE_PUD_MASK);
+
+ if (changed && dirty) {
+ *pudp = entry;
+ /*
+ * We had a write-protection fault here and changed the pud
+ * to to more permissive. No need to flush the TLB for that,
+ * #PF is architecturally guaranteed to do that and in the
+ * worst-case we'll generate a spurious fault.
+ */
+ }
+
+ return changed;
+}
#endif
int ptep_test_and_clear_young(struct vm_area_struct *vma,
@@ -470,6 +490,17 @@ int pmdp_test_and_clear_young(struct vm_area_struct *vma,
return ret;
}
+int pudp_test_and_clear_young(struct vm_area_struct *vma,
+ unsigned long addr, pud_t *pudp)
+{
+ int ret = 0;
+
+ if (pud_young(*pudp))
+ ret = test_and_clear_bit(_PAGE_BIT_ACCESSED,
+ (unsigned long *)pudp);
+
+ return ret;
+}
#endif
int ptep_clear_flush_young(struct vm_area_struct *vma,
--
2.6.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [PATCH v3 6/8] x86: Add support for PUD-sized transparent hugepages
@ 2016-01-08 19:49 ` Matthew Wilcox
0 siblings, 0 replies; 32+ messages in thread
From: Matthew Wilcox @ 2016-01-08 19:49 UTC (permalink / raw)
To: Andrew Morton
Cc: Matthew Wilcox, linux-mm, linux-nvdimm, linux-fsdevel, linux-kernel, x86
From: Matthew Wilcox <willy@linux.intel.com>
The x86-specific code needed to support the PUD uses in the transparent
hugepages code.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
---
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 | 94 +++++++++++++++++++++++++++++++++++
arch/x86/include/asm/pgtable_64.h | 13 +++++
arch/x86/kernel/paravirt.c | 1 +
arch/x86/mm/pgtable.c | 31 ++++++++++++
7 files changed, 153 insertions(+)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 497b8ff..c40e60c 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -90,6 +90,7 @@ config X86
select HAVE_ARCH_SOFT_DIRTY if X86_64
select HAVE_ARCH_TRACEHOOK
select HAVE_ARCH_TRANSPARENT_HUGEPAGE
+ select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD if X86_64
select HAVE_BPF_JIT if X86_64
select HAVE_CC_STACKPROTECTOR
select HAVE_CMPXCHG_DOUBLE
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index f619250..46fd557 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -485,6 +485,17 @@ static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
native_pmd_val(pmd));
}
+static inline void set_pud_at(struct mm_struct *mm, unsigned long addr,
+ pud_t *pudp, pud_t pud)
+{
+ if (sizeof(pudval_t) > sizeof(long))
+ /* 5 arg words */
+ pv_mmu_ops.set_pud_at(mm, addr, pudp, pud);
+ else
+ PVOP_VCALL4(pv_mmu_ops.set_pud_at, mm, addr, pudp,
+ native_pud_val(pud));
+}
+
static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
{
pmdval_t val = native_pmd_val(pmd);
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 77db561..56e27e2 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -252,6 +252,8 @@ struct pv_mmu_ops {
void (*set_pmd)(pmd_t *pmdp, pmd_t pmdval);
void (*set_pmd_at)(struct mm_struct *mm, unsigned long addr,
pmd_t *pmdp, pmd_t pmdval);
+ void (*set_pud_at)(struct mm_struct *mm, unsigned long addr,
+ pud_t *pudp, pud_t pudval);
void (*pte_update)(struct mm_struct *mm, unsigned long addr,
pte_t *ptep);
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 0687c47..57f0eed 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -46,6 +46,7 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page);
#define set_pte(ptep, pte) native_set_pte(ptep, pte)
#define set_pte_at(mm, addr, ptep, pte) native_set_pte_at(mm, addr, ptep, pte)
#define set_pmd_at(mm, addr, pmdp, pmd) native_set_pmd_at(mm, addr, pmdp, pmd)
+#define set_pud_at(mm, addr, pudp, pud) native_set_pud_at(mm, addr, pudp, pud)
#define set_pte_atomic(ptep, pte) \
native_set_pte_atomic(ptep, pte)
@@ -114,6 +115,16 @@ static inline int pmd_young(pmd_t pmd)
return pmd_flags(pmd) & _PAGE_ACCESSED;
}
+static inline int pud_dirty(pud_t pud)
+{
+ return pud_flags(pud) & _PAGE_DIRTY;
+}
+
+static inline int pud_young(pud_t pud)
+{
+ return pud_flags(pud) & _PAGE_ACCESSED;
+}
+
static inline int pte_write(pte_t pte)
{
return pte_flags(pte) & _PAGE_RW;
@@ -167,6 +178,11 @@ static inline int pmd_trans_huge(pmd_t pmd)
return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE;
}
+static inline int pud_trans_huge(pud_t pud)
+{
+ return (pud_val(pud) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE;
+}
+
static inline int has_transparent_hugepage(void)
{
return cpu_has_pse;
@@ -177,6 +193,11 @@ static inline int pmd_devmap(pmd_t pmd)
{
return !!(pmd_val(pmd) & _PAGE_DEVMAP);
}
+
+static inline int pud_devmap(pud_t pud)
+{
+ return !!(pud_val(pud) & _PAGE_DEVMAP);
+}
#endif
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
@@ -318,6 +339,45 @@ static inline pmd_t pmd_mknotpresent(pmd_t pmd)
return pmd_clear_flags(pmd, _PAGE_PRESENT | _PAGE_PROTNONE);
}
+static inline pud_t pud_set_flags(pud_t pud, pudval_t set)
+{
+ pudval_t v = native_pud_val(pud);
+
+ return __pud(v | set);
+}
+
+static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear)
+{
+ pudval_t v = native_pud_val(pud);
+
+ return __pud(v & ~clear);
+}
+
+static inline pud_t pud_mkdevmap(pud_t pud)
+{
+ return pud_set_flags(pud, _PAGE_DEVMAP);
+}
+
+static inline pud_t pud_mkhuge(pud_t pud)
+{
+ return pud_set_flags(pud, _PAGE_PSE);
+}
+
+static inline pud_t pud_mkdirty(pud_t pud)
+{
+ return pud_set_flags(pud, _PAGE_DIRTY | _PAGE_SOFT_DIRTY);
+}
+
+static inline pud_t pud_mkyoung(pud_t pud)
+{
+ return pud_set_flags(pud, _PAGE_ACCESSED);
+}
+
+static inline pud_t pud_mkwrite(pud_t pud)
+{
+ return pud_set_flags(pud, _PAGE_RW);
+}
+
#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
static inline int pte_soft_dirty(pte_t pte)
{
@@ -329,6 +389,11 @@ static inline int pmd_soft_dirty(pmd_t pmd)
return pmd_flags(pmd) & _PAGE_SOFT_DIRTY;
}
+static inline int pud_soft_dirty(pud_t pud)
+{
+ return pud_flags(pud) & _PAGE_SOFT_DIRTY;
+}
+
static inline pte_t pte_mksoft_dirty(pte_t pte)
{
return pte_set_flags(pte, _PAGE_SOFT_DIRTY);
@@ -377,6 +442,13 @@ static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
massage_pgprot(pgprot));
}
+#define pfn_pud pfn_pud
+static inline pud_t pfn_pud(unsigned long page_nr, pgprot_t pgprot)
+{
+ return __pud(((phys_addr_t)page_nr << PAGE_SHIFT) |
+ massage_pgprot(pgprot));
+}
+
static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
{
pteval_t val = pte_val(pte);
@@ -744,6 +816,12 @@ static inline void native_set_pmd_at(struct mm_struct *mm, unsigned long addr,
native_set_pmd(pmdp, pmd);
}
+static inline void native_set_pud_at(struct mm_struct *mm, unsigned long addr,
+ pud_t *pudp , pud_t pud)
+{
+ native_set_pud(pudp, pud);
+}
+
#ifndef CONFIG_PARAVIRT
/*
* Rules for using pte_update - it must be called after any PTE update which
@@ -822,10 +900,15 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm,
extern int pmdp_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp,
pmd_t entry, int dirty);
+extern int pudp_set_access_flags(struct vm_area_struct *vma,
+ unsigned long address, pud_t *pudp,
+ pud_t entry, int dirty);
#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
extern int pmdp_test_and_clear_young(struct vm_area_struct *vma,
unsigned long addr, pmd_t *pmdp);
+extern int pudp_test_and_clear_young(struct vm_area_struct *vma,
+ unsigned long addr, pud_t *pudp);
#define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
@@ -845,6 +928,13 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long
return native_pmdp_get_and_clear(pmdp);
}
+#define __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR
+static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr,
+ pud_t *pudp)
+{
+ return native_pudp_get_and_clear(pudp);
+}
+
#define __HAVE_ARCH_PMDP_SET_WRPROTECT
static inline void pmdp_set_wrprotect(struct mm_struct *mm,
unsigned long addr, pmd_t *pmdp)
@@ -893,6 +983,10 @@ static inline void update_mmu_cache_pmd(struct vm_area_struct *vma,
unsigned long addr, pmd_t *pmd)
{
}
+static inline void update_mmu_cache_pud(struct vm_area_struct *vma,
+ unsigned long addr, pud_t *pud)
+{
+}
#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 2ee7811..a3aa6b7 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -106,6 +106,19 @@ static inline void native_pud_clear(pud_t *pud)
native_set_pud(pud, native_make_pud(0));
}
+static inline pud_t native_pudp_get_and_clear(pud_t *pudp)
+{
+#ifdef CONFIG_SMP
+ return native_make_pud(xchg(&pudp->pud, 0));
+#else
+ /* native_local_pudp_get_and_clear,
+ but duplicated because of cyclic dependency */
+ pud_t ret = *pudp;
+ native_pud_clear(pudp);
+ return ret;
+#endif
+}
+
static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
{
*pgdp = pgd;
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index f08ac28..24d61f2 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -425,6 +425,7 @@ struct pv_mmu_ops pv_mmu_ops = {
.pmd_clear = native_pmd_clear,
#endif
.set_pud = native_set_pud,
+ .set_pud_at = native_set_pud_at,
.pmd_val = PTE_IDENT,
.make_pmd = PTE_IDENT,
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 4eb287e..b7c8df6 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -441,6 +441,26 @@ int pmdp_set_access_flags(struct vm_area_struct *vma,
return changed;
}
+
+int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address,
+ pud_t *pudp, pud_t entry, int dirty)
+{
+ int changed = !pud_same(*pudp, entry);
+
+ VM_BUG_ON(address & ~HPAGE_PUD_MASK);
+
+ if (changed && dirty) {
+ *pudp = entry;
+ /*
+ * We had a write-protection fault here and changed the pud
+ * to to more permissive. No need to flush the TLB for that,
+ * #PF is architecturally guaranteed to do that and in the
+ * worst-case we'll generate a spurious fault.
+ */
+ }
+
+ return changed;
+}
#endif
int ptep_test_and_clear_young(struct vm_area_struct *vma,
@@ -470,6 +490,17 @@ int pmdp_test_and_clear_young(struct vm_area_struct *vma,
return ret;
}
+int pudp_test_and_clear_young(struct vm_area_struct *vma,
+ unsigned long addr, pud_t *pudp)
+{
+ int ret = 0;
+
+ if (pud_young(*pudp))
+ ret = test_and_clear_bit(_PAGE_BIT_ACCESSED,
+ (unsigned long *)pudp);
+
+ return ret;
+}
#endif
int ptep_clear_flush_young(struct vm_area_struct *vma,
--
2.6.4
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [PATCH v3 7/8] dax: Support for transparent PUD pages
2016-01-08 19:49 ` Matthew Wilcox
@ 2016-01-08 19:49 ` Matthew Wilcox
-1 siblings, 0 replies; 32+ messages in thread
From: Matthew Wilcox @ 2016-01-08 19:49 UTC (permalink / raw)
To: Andrew Morton
Cc: Matthew Wilcox, linux-mm, linux-nvdimm, linux-fsdevel, linux-kernel, x86
From: Matthew Wilcox <willy@linux.intel.com>
The DAX support for transparent huge PUD pages
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
---
fs/dax.c | 175 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 175 insertions(+)
diff --git a/fs/dax.c b/fs/dax.c
index 05ed547..f4cb4dd 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -906,6 +906,178 @@ static int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
}
#endif /* !CONFIG_TRANSPARENT_HUGEPAGE */
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+/*
+ * The 'colour' (ie low bits) within a PUD of a page offset. This comes up
+ * more often than one might expect in the below function.
+ */
+#define PG_PUD_COLOUR ((PUD_SIZE >> PAGE_SHIFT) - 1)
+
+#define dax_pud_dbg(bh, address, reason) __dax_dbg(bh, address, reason, "dax_pud")
+
+static int dax_pud_fault(struct vm_area_struct *vma, unsigned long address,
+ pud_t *pud, unsigned int flags, get_block_t get_block,
+ dax_iodone_t complete_unwritten)
+{
+ struct file *file = vma->vm_file;
+ struct address_space *mapping = file->f_mapping;
+ struct inode *inode = mapping->host;
+ struct buffer_head bh;
+ unsigned blkbits = inode->i_blkbits;
+ unsigned long pud_addr = address & PUD_MASK;
+ bool write = flags & FAULT_FLAG_WRITE;
+ struct block_device *bdev = NULL;
+ pgoff_t size, pgoff;
+ sector_t block;
+ int result = 0;
+
+ /* dax pud mappings require pfn_t_devmap() */
+ if (!IS_ENABLED(CONFIG_FS_DAX_PMD))
+ return VM_FAULT_FALLBACK;
+
+ /* Fall back to PTEs if we're going to COW */
+ if (write && !(vma->vm_flags & VM_SHARED)) {
+ split_huge_pud(vma, pud, address);
+ dax_pud_dbg(NULL, address, "cow write");
+ return VM_FAULT_FALLBACK;
+ }
+ /* If the PUD would extend outside the VMA */
+ if (pud_addr < vma->vm_start) {
+ dax_pud_dbg(NULL, address, "vma start unaligned");
+ return VM_FAULT_FALLBACK;
+ }
+ if ((pud_addr + PUD_SIZE) > vma->vm_end) {
+ dax_pud_dbg(NULL, address, "vma end unaligned");
+ return VM_FAULT_FALLBACK;
+ }
+
+ pgoff = linear_page_index(vma, pud_addr);
+ size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ if (pgoff >= size)
+ return VM_FAULT_SIGBUS;
+ /* If the PUD would cover blocks out of the file */
+ if ((pgoff | PG_PUD_COLOUR) >= size) {
+ dax_pud_dbg(NULL, address,
+ "offset + huge page size > file size");
+ return VM_FAULT_FALLBACK;
+ }
+
+ memset(&bh, 0, sizeof(bh));
+ block = (sector_t)pgoff << (PAGE_SHIFT - blkbits);
+
+ bh.b_size = PUD_SIZE;
+ if (get_block(inode, block, &bh, write) != 0)
+ return VM_FAULT_SIGBUS;
+ bdev = bh.b_bdev;
+ i_mmap_lock_read(mapping);
+
+ /*
+ * If the filesystem isn't willing to tell us the length of a hole,
+ * just fall back to PTEs. Calling get_block 512 times in a loop
+ * would be silly.
+ */
+ if (!buffer_size_valid(&bh) || bh.b_size < PUD_SIZE) {
+ dax_pud_dbg(&bh, address, "allocated block too small");
+ goto fallback;
+ }
+
+ /*
+ * If we allocated new storage, make sure no process has any
+ * zero pages covering this hole
+ */
+ if (buffer_new(&bh)) {
+ i_mmap_unlock_read(mapping);
+ unmap_mapping_range(mapping, pgoff << PAGE_SHIFT, PUD_SIZE, 0);
+ i_mmap_lock_read(mapping);
+ }
+
+ /*
+ * If a truncate happened while we were allocating blocks, we may
+ * leave blocks allocated to the file that are beyond EOF. We can't
+ * take i_mutex here, so just leave them hanging; they'll be freed
+ * when the file is deleted.
+ */
+ size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ if (pgoff >= size) {
+ result = VM_FAULT_SIGBUS;
+ goto out;
+ }
+ if ((pgoff | PG_PUD_COLOUR) >= size) {
+ dax_pud_dbg(&bh, address, "pgoff unaligned");
+ goto fallback;
+ }
+
+ if (!write && !buffer_mapped(&bh) && buffer_uptodate(&bh)) {
+ dax_pud_dbg(&bh, address, "no zero page");
+ goto fallback;
+ } else {
+ struct blk_dax_ctl dax = {
+ .sector = to_sector(&bh, inode),
+ .size = PUD_SIZE,
+ };
+ long length = dax_map_atomic(bdev, &dax);
+
+ if (length < 0) {
+ result = VM_FAULT_SIGBUS;
+ goto out;
+ }
+ if (length < PUD_SIZE) {
+ dax_pud_dbg(&bh, address, "dax-length too small");
+ dax_unmap_atomic(bdev, &dax);
+ goto fallback;
+ }
+ if (pfn_t_to_pfn(dax.pfn) & PG_PUD_COLOUR) {
+ dax_pud_dbg(&bh, address, "pfn unaligned");
+ dax_unmap_atomic(bdev, &dax);
+ goto fallback;
+ }
+
+ if (!pfn_t_devmap(dax.pfn)) {
+ dax_unmap_atomic(bdev, &dax);
+ dax_pud_dbg(&bh, address, "pfn not in memmap");
+ goto fallback;
+ }
+
+ if (buffer_unwritten(&bh) || buffer_new(&bh)) {
+ clear_pmem(dax.addr, PUD_SIZE);
+ wmb_pmem();
+ count_vm_event(PGMAJFAULT);
+ mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
+ result |= VM_FAULT_MAJOR;
+ }
+ dax_unmap_atomic(bdev, &dax);
+
+ dev_dbg(part_to_dev(bdev->bd_part),
+ "%s: %s addr: %lx pfn: %lx sect: %llx\n",
+ __func__, current->comm, address,
+ pfn_t_to_pfn(dax.pfn),
+ (unsigned long long) dax.sector);
+ result |= vmf_insert_pfn_pud(vma, address, pud,
+ dax.pfn, write);
+ }
+
+ out:
+ i_mmap_unlock_read(mapping);
+
+ if (buffer_unwritten(&bh))
+ complete_unwritten(&bh, !(result & VM_FAULT_ERROR));
+
+ return result;
+
+ fallback:
+ count_vm_event(THP_FAULT_FALLBACK);
+ result = VM_FAULT_FALLBACK;
+ goto out;
+}
+#else /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+static int dax_pud_fault(struct vm_area_struct *vma, unsigned long address,
+ pud_t *pud, unsigned int flags, get_block_t get_block,
+ dax_iodone_t complete_unwritten)
+{
+ return VM_FAULT_FALLBACK;
+}
+#endif /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
/**
* dax_fault - handle a page fault on a DAX file
* @vma: The virtual memory area where the fault occurred
@@ -932,6 +1104,9 @@ int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
case FAULT_FLAG_SIZE_PMD:
return dax_pmd_fault(vma, address, vmf->pmd, vmf->flags,
get_block, iodone);
+ case FAULT_FLAG_SIZE_PUD:
+ return dax_pud_fault(vma, address, vmf->pud, vmf->flags,
+ get_block, iodone);
default:
return VM_FAULT_FALLBACK;
}
--
2.6.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [PATCH v3 7/8] dax: Support for transparent PUD pages
@ 2016-01-08 19:49 ` Matthew Wilcox
0 siblings, 0 replies; 32+ messages in thread
From: Matthew Wilcox @ 2016-01-08 19:49 UTC (permalink / raw)
To: Andrew Morton
Cc: Matthew Wilcox, linux-mm, linux-nvdimm, linux-fsdevel, linux-kernel, x86
From: Matthew Wilcox <willy@linux.intel.com>
The DAX support for transparent huge PUD pages
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
---
fs/dax.c | 175 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 175 insertions(+)
diff --git a/fs/dax.c b/fs/dax.c
index 05ed547..f4cb4dd 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -906,6 +906,178 @@ static int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
}
#endif /* !CONFIG_TRANSPARENT_HUGEPAGE */
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+/*
+ * The 'colour' (ie low bits) within a PUD of a page offset. This comes up
+ * more often than one might expect in the below function.
+ */
+#define PG_PUD_COLOUR ((PUD_SIZE >> PAGE_SHIFT) - 1)
+
+#define dax_pud_dbg(bh, address, reason) __dax_dbg(bh, address, reason, "dax_pud")
+
+static int dax_pud_fault(struct vm_area_struct *vma, unsigned long address,
+ pud_t *pud, unsigned int flags, get_block_t get_block,
+ dax_iodone_t complete_unwritten)
+{
+ struct file *file = vma->vm_file;
+ struct address_space *mapping = file->f_mapping;
+ struct inode *inode = mapping->host;
+ struct buffer_head bh;
+ unsigned blkbits = inode->i_blkbits;
+ unsigned long pud_addr = address & PUD_MASK;
+ bool write = flags & FAULT_FLAG_WRITE;
+ struct block_device *bdev = NULL;
+ pgoff_t size, pgoff;
+ sector_t block;
+ int result = 0;
+
+ /* dax pud mappings require pfn_t_devmap() */
+ if (!IS_ENABLED(CONFIG_FS_DAX_PMD))
+ return VM_FAULT_FALLBACK;
+
+ /* Fall back to PTEs if we're going to COW */
+ if (write && !(vma->vm_flags & VM_SHARED)) {
+ split_huge_pud(vma, pud, address);
+ dax_pud_dbg(NULL, address, "cow write");
+ return VM_FAULT_FALLBACK;
+ }
+ /* If the PUD would extend outside the VMA */
+ if (pud_addr < vma->vm_start) {
+ dax_pud_dbg(NULL, address, "vma start unaligned");
+ return VM_FAULT_FALLBACK;
+ }
+ if ((pud_addr + PUD_SIZE) > vma->vm_end) {
+ dax_pud_dbg(NULL, address, "vma end unaligned");
+ return VM_FAULT_FALLBACK;
+ }
+
+ pgoff = linear_page_index(vma, pud_addr);
+ size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ if (pgoff >= size)
+ return VM_FAULT_SIGBUS;
+ /* If the PUD would cover blocks out of the file */
+ if ((pgoff | PG_PUD_COLOUR) >= size) {
+ dax_pud_dbg(NULL, address,
+ "offset + huge page size > file size");
+ return VM_FAULT_FALLBACK;
+ }
+
+ memset(&bh, 0, sizeof(bh));
+ block = (sector_t)pgoff << (PAGE_SHIFT - blkbits);
+
+ bh.b_size = PUD_SIZE;
+ if (get_block(inode, block, &bh, write) != 0)
+ return VM_FAULT_SIGBUS;
+ bdev = bh.b_bdev;
+ i_mmap_lock_read(mapping);
+
+ /*
+ * If the filesystem isn't willing to tell us the length of a hole,
+ * just fall back to PTEs. Calling get_block 512 times in a loop
+ * would be silly.
+ */
+ if (!buffer_size_valid(&bh) || bh.b_size < PUD_SIZE) {
+ dax_pud_dbg(&bh, address, "allocated block too small");
+ goto fallback;
+ }
+
+ /*
+ * If we allocated new storage, make sure no process has any
+ * zero pages covering this hole
+ */
+ if (buffer_new(&bh)) {
+ i_mmap_unlock_read(mapping);
+ unmap_mapping_range(mapping, pgoff << PAGE_SHIFT, PUD_SIZE, 0);
+ i_mmap_lock_read(mapping);
+ }
+
+ /*
+ * If a truncate happened while we were allocating blocks, we may
+ * leave blocks allocated to the file that are beyond EOF. We can't
+ * take i_mutex here, so just leave them hanging; they'll be freed
+ * when the file is deleted.
+ */
+ size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ if (pgoff >= size) {
+ result = VM_FAULT_SIGBUS;
+ goto out;
+ }
+ if ((pgoff | PG_PUD_COLOUR) >= size) {
+ dax_pud_dbg(&bh, address, "pgoff unaligned");
+ goto fallback;
+ }
+
+ if (!write && !buffer_mapped(&bh) && buffer_uptodate(&bh)) {
+ dax_pud_dbg(&bh, address, "no zero page");
+ goto fallback;
+ } else {
+ struct blk_dax_ctl dax = {
+ .sector = to_sector(&bh, inode),
+ .size = PUD_SIZE,
+ };
+ long length = dax_map_atomic(bdev, &dax);
+
+ if (length < 0) {
+ result = VM_FAULT_SIGBUS;
+ goto out;
+ }
+ if (length < PUD_SIZE) {
+ dax_pud_dbg(&bh, address, "dax-length too small");
+ dax_unmap_atomic(bdev, &dax);
+ goto fallback;
+ }
+ if (pfn_t_to_pfn(dax.pfn) & PG_PUD_COLOUR) {
+ dax_pud_dbg(&bh, address, "pfn unaligned");
+ dax_unmap_atomic(bdev, &dax);
+ goto fallback;
+ }
+
+ if (!pfn_t_devmap(dax.pfn)) {
+ dax_unmap_atomic(bdev, &dax);
+ dax_pud_dbg(&bh, address, "pfn not in memmap");
+ goto fallback;
+ }
+
+ if (buffer_unwritten(&bh) || buffer_new(&bh)) {
+ clear_pmem(dax.addr, PUD_SIZE);
+ wmb_pmem();
+ count_vm_event(PGMAJFAULT);
+ mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
+ result |= VM_FAULT_MAJOR;
+ }
+ dax_unmap_atomic(bdev, &dax);
+
+ dev_dbg(part_to_dev(bdev->bd_part),
+ "%s: %s addr: %lx pfn: %lx sect: %llx\n",
+ __func__, current->comm, address,
+ pfn_t_to_pfn(dax.pfn),
+ (unsigned long long) dax.sector);
+ result |= vmf_insert_pfn_pud(vma, address, pud,
+ dax.pfn, write);
+ }
+
+ out:
+ i_mmap_unlock_read(mapping);
+
+ if (buffer_unwritten(&bh))
+ complete_unwritten(&bh, !(result & VM_FAULT_ERROR));
+
+ return result;
+
+ fallback:
+ count_vm_event(THP_FAULT_FALLBACK);
+ result = VM_FAULT_FALLBACK;
+ goto out;
+}
+#else /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+static int dax_pud_fault(struct vm_area_struct *vma, unsigned long address,
+ pud_t *pud, unsigned int flags, get_block_t get_block,
+ dax_iodone_t complete_unwritten)
+{
+ return VM_FAULT_FALLBACK;
+}
+#endif /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
/**
* dax_fault - handle a page fault on a DAX file
* @vma: The virtual memory area where the fault occurred
@@ -932,6 +1104,9 @@ int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
case FAULT_FLAG_SIZE_PMD:
return dax_pmd_fault(vma, address, vmf->pmd, vmf->flags,
get_block, iodone);
+ case FAULT_FLAG_SIZE_PUD:
+ return dax_pud_fault(vma, address, vmf->pud, vmf->flags,
+ get_block, iodone);
default:
return VM_FAULT_FALLBACK;
}
--
2.6.4
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [PATCH v3 8/8] ext4: Support for PUD-sized transparent huge pages
2016-01-08 19:49 ` Matthew Wilcox
@ 2016-01-08 19:49 ` Matthew Wilcox
-1 siblings, 0 replies; 32+ messages in thread
From: Matthew Wilcox @ 2016-01-08 19:49 UTC (permalink / raw)
To: Andrew Morton
Cc: Matthew Wilcox, linux-mm, linux-nvdimm, linux-fsdevel, linux-kernel, x86
From: Matthew Wilcox <willy@linux.intel.com>
ext4 needs to reserve enough space in the journal to allocate a PUD-sized
page.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
---
fs/ext4/file.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 665fc4b..cec5fa7 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -211,6 +211,10 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
nblocks = ext4_chunk_trans_blocks(inode,
PMD_SIZE / PAGE_SIZE);
break;
+ case FAULT_FLAG_SIZE_PUD:
+ nblocks = ext4_chunk_trans_blocks(inode,
+ PUD_SIZE / PAGE_SIZE);
+ break;
default:
return VM_FAULT_FALLBACK;
}
--
2.6.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [PATCH v3 8/8] ext4: Support for PUD-sized transparent huge pages
@ 2016-01-08 19:49 ` Matthew Wilcox
0 siblings, 0 replies; 32+ messages in thread
From: Matthew Wilcox @ 2016-01-08 19:49 UTC (permalink / raw)
To: Andrew Morton
Cc: Matthew Wilcox, linux-mm, linux-nvdimm, linux-fsdevel, linux-kernel, x86
From: Matthew Wilcox <willy@linux.intel.com>
ext4 needs to reserve enough space in the journal to allocate a PUD-sized
page.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
---
fs/ext4/file.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 665fc4b..cec5fa7 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -211,6 +211,10 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
nblocks = ext4_chunk_trans_blocks(inode,
PMD_SIZE / PAGE_SIZE);
break;
+ case FAULT_FLAG_SIZE_PUD:
+ nblocks = ext4_chunk_trans_blocks(inode,
+ PUD_SIZE / PAGE_SIZE);
+ break;
default:
return VM_FAULT_FALLBACK;
}
--
2.6.4
^ permalink raw reply related [flat|nested] 32+ messages in thread
* Re: [PATCH v3 0/8] Support for transparent PUD pages for DAX files
2016-01-08 19:49 ` Matthew Wilcox
@ 2016-01-15 19:41 ` Darrick J. Wong
-1 siblings, 0 replies; 32+ messages in thread
From: Darrick J. Wong @ 2016-01-15 19:41 UTC (permalink / raw)
To: Matthew Wilcox
Cc: Andrew Morton, Matthew Wilcox, linux-mm, linux-nvdimm,
linux-fsdevel, linux-kernel, x86
On Fri, Jan 08, 2016 at 02:49:44PM -0500, Matthew Wilcox wrote:
> From: Matthew Wilcox <willy@linux.intel.com>
>
> Andrew, I think this is ready for a spin in -mm.
>
> v3: Rebased against current mmtom
> v2: Reduced churn in filesystems by switching to ->huge_fault interface
> Addressed concerns from Kirill
>
> 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.
"It's not aligned"... I don't know the details of what you're trying to do, but
are you trying to create a file where each GB of logical address space maps to
a contiguous GB of physical space, and both logical and physical offsets align
to a 1GB boundary?
If the XFS is formatted with stripe unit/width of 1G, an extent size hint of 1G
is put on the file, and the whole file is allocated in 1G chunks, I think
you're supposed to be able to make the above happen:
# mkfs.xfs /dev/mapper/moo -f -d su=1g,sw=1
meta-data=/dev/mapper/moo isize=512 agcount=34, agsize=8126464 blks
= sectsz=512 attr=2, projid32bit=1
= crc=1 finobt=1, sparse=0, rmapbt=0, reflink=0
data = bsize=4096 blocks=268435456, imaxpct=5
= sunit=262144 swidth=262144 blks
naming =version 2 bsize=4096 ascii-ci=0 ftype=1
log =internal log bsize=4096 blocks=131072, version=2
= sectsz=512 sunit=8 blks, lazy-count=1
realtime =none extsz=4096 blocks=0, rtextents=0
# mount /dev/mapper/moo /mnt
# xfs_io -f -c 'extsize 1g' -c 'falloc 0 200g' /mnt/urk
# filefrag -v /mnt/urk
Filesystem type is: 58465342
File size of /mnt/urk is 214748364800 (52428800 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 7340031: 524288.. 7864319: 7340032: unwritten
1: 7340032..14680063: 8388608.. 15728639: 7340032: 7864320: unwritten
2: 14680064..22020095: 16515072.. 23855103: 7340032: 15728640: unwritten
3: 22020096..29360127: 24641536.. 31981567: 7340032: 23855104: unwritten
4: 29360128..36700159: 32768000.. 40108031: 7340032: 31981568: unwritten
5: 36700160..40370175: 40894464.. 44564479: 3670016: 40108032: unwritten
6: 40370176..44040191: 44826624.. 48496639: 3670016: 44564480: unwritten
7: 44040192..51380223: 49020928.. 56360959: 7340032: 48496640: unwritten
8: 51380224..52428799: 57147392.. 58195967: 1048576: 56360960: last,unwritten,eof
/mnt/urk: 9 extents found
AFAICT each extent's logical and physical offsets are aligned to a 1G boundary.
<shrug> Just a shot in the dark.
(This VM has 2G of memory and 1T of fake disk.)
--D
>
> 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 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 | 94 ++++++++++++
> 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 | 272 +++++++++++++++++++++++++---------
> 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 | 50 +++++++
> include/linux/mm.h | 43 +++++-
> include/linux/mmu_notifier.h | 13 ++
> include/linux/pfn_t.h | 8 +
> mm/huge_memory.c | 151 +++++++++++++++++++
> mm/memory.c | 101 +++++++++++--
> mm/mincore.c | 13 ++
> mm/pagewalk.c | 19 ++-
> mm/pgtable-generic.c | 14 ++
> 28 files changed, 980 insertions(+), 198 deletions(-)
>
> --
> 2.6.4
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] 32+ messages in thread
* Re: [PATCH v3 0/8] Support for transparent PUD pages for DAX files
@ 2016-01-15 19:41 ` Darrick J. Wong
0 siblings, 0 replies; 32+ messages in thread
From: Darrick J. Wong @ 2016-01-15 19:41 UTC (permalink / raw)
To: Matthew Wilcox
Cc: Andrew Morton, Matthew Wilcox, linux-mm, linux-nvdimm,
linux-fsdevel, linux-kernel, x86
On Fri, Jan 08, 2016 at 02:49:44PM -0500, Matthew Wilcox wrote:
> From: Matthew Wilcox <willy@linux.intel.com>
>
> Andrew, I think this is ready for a spin in -mm.
>
> v3: Rebased against current mmtom
> v2: Reduced churn in filesystems by switching to ->huge_fault interface
> Addressed concerns from Kirill
>
> 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.
"It's not aligned"... I don't know the details of what you're trying to do, but
are you trying to create a file where each GB of logical address space maps to
a contiguous GB of physical space, and both logical and physical offsets align
to a 1GB boundary?
If the XFS is formatted with stripe unit/width of 1G, an extent size hint of 1G
is put on the file, and the whole file is allocated in 1G chunks, I think
you're supposed to be able to make the above happen:
# mkfs.xfs /dev/mapper/moo -f -d su=1g,sw=1
meta-data=/dev/mapper/moo isize=512 agcount=34, agsize=8126464 blks
= sectsz=512 attr=2, projid32bit=1
= crc=1 finobt=1, sparse=0, rmapbt=0, reflink=0
data = bsize=4096 blocks=268435456, imaxpct=5
= sunit=262144 swidth=262144 blks
naming =version 2 bsize=4096 ascii-ci=0 ftype=1
log =internal log bsize=4096 blocks=131072, version=2
= sectsz=512 sunit=8 blks, lazy-count=1
realtime =none extsz=4096 blocks=0, rtextents=0
# mount /dev/mapper/moo /mnt
# xfs_io -f -c 'extsize 1g' -c 'falloc 0 200g' /mnt/urk
# filefrag -v /mnt/urk
Filesystem type is: 58465342
File size of /mnt/urk is 214748364800 (52428800 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 7340031: 524288.. 7864319: 7340032: unwritten
1: 7340032..14680063: 8388608.. 15728639: 7340032: 7864320: unwritten
2: 14680064..22020095: 16515072.. 23855103: 7340032: 15728640: unwritten
3: 22020096..29360127: 24641536.. 31981567: 7340032: 23855104: unwritten
4: 29360128..36700159: 32768000.. 40108031: 7340032: 31981568: unwritten
5: 36700160..40370175: 40894464.. 44564479: 3670016: 40108032: unwritten
6: 40370176..44040191: 44826624.. 48496639: 3670016: 44564480: unwritten
7: 44040192..51380223: 49020928.. 56360959: 7340032: 48496640: unwritten
8: 51380224..52428799: 57147392.. 58195967: 1048576: 56360960: last,unwritten,eof
/mnt/urk: 9 extents found
AFAICT each extent's logical and physical offsets are aligned to a 1G boundary.
<shrug> Just a shot in the dark.
(This VM has 2G of memory and 1T of fake disk.)
--D
>
> 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 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 | 94 ++++++++++++
> 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 | 272 +++++++++++++++++++++++++---------
> 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 | 50 +++++++
> include/linux/mm.h | 43 +++++-
> include/linux/mmu_notifier.h | 13 ++
> include/linux/pfn_t.h | 8 +
> mm/huge_memory.c | 151 +++++++++++++++++++
> mm/memory.c | 101 +++++++++++--
> mm/mincore.c | 13 ++
> mm/pagewalk.c | 19 ++-
> mm/pgtable-generic.c | 14 ++
> 28 files changed, 980 insertions(+), 198 deletions(-)
>
> --
> 2.6.4
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 32+ messages in thread
* Re: [PATCH v3 0/8] Support for transparent PUD pages for DAX files
2016-01-08 19:49 ` Matthew Wilcox
@ 2016-01-21 22:48 ` mingming cao
-1 siblings, 0 replies; 32+ messages in thread
From: mingming cao @ 2016-01-21 22:48 UTC (permalink / raw)
To: Matthew Wilcox
Cc: Andrew Morton, Matthew Wilcox, linux-mm, linux-nvdimm,
linux-fsdevel, linux-kernel, x86
On 01/08/2016 11:49 AM, Matthew Wilcox wrote:
> From: Matthew Wilcox <willy@linux.intel.com>
>
> Andrew, I think this is ready for a spin in -mm.
>
> v3: Rebased against current mmtom
> v2: Reduced churn in filesystems by switching to ->huge_fault interface
> Addressed concerns from Kirill
>
> 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.
>
I dont think ext4 can do 1G at this time due to extent length bits (15 for unwritten) and block group size bundary (well, with flex bg we may able to relax this ). I have seen about 125M of contiguous space allocated on my fresh new ext4 filesystem. I do remember mballoc in ext4 used to normalize the allocation request up to 8 or 16M, but it appears not that small any more.
Thanks,
Mingming
> 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 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 | 94 ++++++++++++
> 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 | 272 +++++++++++++++++++++++++---------
> 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 | 50 +++++++
> include/linux/mm.h | 43 +++++-
> include/linux/mmu_notifier.h | 13 ++
> include/linux/pfn_t.h | 8 +
> mm/huge_memory.c | 151 +++++++++++++++++++
> mm/memory.c | 101 +++++++++++--
> mm/mincore.c | 13 ++
> mm/pagewalk.c | 19 ++-
> mm/pgtable-generic.c | 14 ++
> 28 files changed, 980 insertions(+), 198 deletions(-)
>
^ permalink raw reply [flat|nested] 32+ messages in thread
* Re: [PATCH v3 0/8] Support for transparent PUD pages for DAX files
@ 2016-01-21 22:48 ` mingming cao
0 siblings, 0 replies; 32+ messages in thread
From: mingming cao @ 2016-01-21 22:48 UTC (permalink / raw)
To: Matthew Wilcox
Cc: Andrew Morton, Matthew Wilcox, linux-mm, linux-nvdimm,
linux-fsdevel, linux-kernel, x86
On 01/08/2016 11:49 AM, Matthew Wilcox wrote:
> From: Matthew Wilcox <willy@linux.intel.com>
>
> Andrew, I think this is ready for a spin in -mm.
>
> v3: Rebased against current mmtom
> v2: Reduced churn in filesystems by switching to ->huge_fault interface
> Addressed concerns from Kirill
>
> 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.
>
I dont think ext4 can do 1G at this time due to extent length bits (15 for unwritten) and block group size bundary (well, with flex bg we may able to relax this ). I have seen about 125M of contiguous space allocated on my fresh new ext4 filesystem. I do remember mballoc in ext4 used to normalize the allocation request up to 8 or 16M, but it appears not that small any more.
Thanks,
Mingming
> 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 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 | 94 ++++++++++++
> 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 | 272 +++++++++++++++++++++++++---------
> 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 | 50 +++++++
> include/linux/mm.h | 43 +++++-
> include/linux/mmu_notifier.h | 13 ++
> include/linux/pfn_t.h | 8 +
> mm/huge_memory.c | 151 +++++++++++++++++++
> mm/memory.c | 101 +++++++++++--
> mm/mincore.c | 13 ++
> mm/pagewalk.c | 19 ++-
> mm/pgtable-generic.c | 14 ++
> 28 files changed, 980 insertions(+), 198 deletions(-)
>
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 32+ messages in thread
* Re: [PATCH v3 0/8] Support for transparent PUD pages for DAX files
2016-01-15 19:41 ` Darrick J. Wong
@ 2016-01-22 11:26 ` Dave Chinner
-1 siblings, 0 replies; 32+ messages in thread
From: Dave Chinner @ 2016-01-22 11:26 UTC (permalink / raw)
To: Darrick J. Wong
Cc: Matthew Wilcox, Andrew Morton, Matthew Wilcox, linux-mm,
linux-nvdimm, linux-fsdevel, linux-kernel, x86
On Fri, Jan 15, 2016 at 11:41:50AM -0800, Darrick J. Wong wrote:
> On Fri, Jan 08, 2016 at 02:49:44PM -0500, Matthew Wilcox wrote:
> > From: Matthew Wilcox <willy@linux.intel.com>
> >
> > Andrew, I think this is ready for a spin in -mm.
> >
> > v3: Rebased against current mmtom
> > v2: Reduced churn in filesystems by switching to ->huge_fault interface
> > Addressed concerns from Kirill
> >
> > 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.
>
> "It's not aligned"... I don't know the details of what you're trying to do, but
> are you trying to create a file where each GB of logical address space maps to
> a contiguous GB of physical space, and both logical and physical offsets align
> to a 1GB boundary?
>
> If the XFS is formatted with stripe unit/width of 1G, an extent size hint of 1G
> is put on the file, and the whole file is allocated in 1G chunks, I think
> you're supposed to be able to make the above happen:
If you really, really want to guarantee 1GB aligned extents for file
data on XFS, use the realtime device with a 1GB extent size.....
Cheers,
Dave.
--
Dave Chinner
david@fromorbit.com
^ permalink raw reply [flat|nested] 32+ messages in thread
* Re: [PATCH v3 0/8] Support for transparent PUD pages for DAX files
@ 2016-01-22 11:26 ` Dave Chinner
0 siblings, 0 replies; 32+ messages in thread
From: Dave Chinner @ 2016-01-22 11:26 UTC (permalink / raw)
To: Darrick J. Wong
Cc: Matthew Wilcox, Andrew Morton, Matthew Wilcox, linux-mm,
linux-nvdimm, linux-fsdevel, linux-kernel, x86
On Fri, Jan 15, 2016 at 11:41:50AM -0800, Darrick J. Wong wrote:
> On Fri, Jan 08, 2016 at 02:49:44PM -0500, Matthew Wilcox wrote:
> > From: Matthew Wilcox <willy@linux.intel.com>
> >
> > Andrew, I think this is ready for a spin in -mm.
> >
> > v3: Rebased against current mmtom
> > v2: Reduced churn in filesystems by switching to ->huge_fault interface
> > Addressed concerns from Kirill
> >
> > 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.
>
> "It's not aligned"... I don't know the details of what you're trying to do, but
> are you trying to create a file where each GB of logical address space maps to
> a contiguous GB of physical space, and both logical and physical offsets align
> to a 1GB boundary?
>
> If the XFS is formatted with stripe unit/width of 1G, an extent size hint of 1G
> is put on the file, and the whole file is allocated in 1G chunks, I think
> you're supposed to be able to make the above happen:
If you really, really want to guarantee 1GB aligned extents for file
data on XFS, use the realtime device with a 1GB extent size.....
Cheers,
Dave.
--
Dave Chinner
david@fromorbit.com
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 32+ messages in thread
* Re: [PATCH v3 0/8] Support for transparent PUD pages for DAX files
2016-01-21 22:48 ` mingming cao
@ 2016-01-22 14:11 ` Matthew Wilcox
-1 siblings, 0 replies; 32+ messages in thread
From: Matthew Wilcox @ 2016-01-22 14:11 UTC (permalink / raw)
To: mingming cao
Cc: Matthew Wilcox, Andrew Morton, linux-mm, linux-nvdimm,
linux-fsdevel, linux-kernel, x86
On Thu, Jan 21, 2016 at 02:48:58PM -0800, mingming cao wrote:
> On 01/08/2016 11:49 AM, Matthew Wilcox wrote:
> > 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.
>
> I dont think ext4 can do 1G at this time due to extent length bits
> (15 for unwritten) and block group size bundary (well, with flex bg we
> may able to relax this ). I have seen about 125M of contiguous space
> allocated on my fresh new ext4 filesystem. I do remember mballoc in ext4
> used to normalize the allocation request up to 8 or 16M, but it appears
> not that small any more.
I agree that the on-disk ext4 format can't represent a single 1GB
extent (ext4_extent's ee_len is 16 bits), but the in-memory extent tree
(extent_status's es_len) uses a 32-bit block count field, which can
represent an 8TB length extent with 4kB blocks.
It seems that at the moment, something is constraining allocations to be
at most 16MB, so that we can convert one extent_status to one ext4_extent.
What I'd like to see is code to convert one extent_status into multiple
ext4_extents on disc, and recombine multiple ext4_extents into a single
extent_status when the inode is read back in later.
Then we can start looking at places where ext4 puts metadata in the
middle of 1GB regions, preventing them from being used ... that'll be
a separate bag of issues, no doubt.
^ permalink raw reply [flat|nested] 32+ messages in thread
* Re: [PATCH v3 0/8] Support for transparent PUD pages for DAX files
@ 2016-01-22 14:11 ` Matthew Wilcox
0 siblings, 0 replies; 32+ messages in thread
From: Matthew Wilcox @ 2016-01-22 14:11 UTC (permalink / raw)
To: mingming cao
Cc: Matthew Wilcox, Andrew Morton, linux-mm, linux-nvdimm,
linux-fsdevel, linux-kernel, x86
On Thu, Jan 21, 2016 at 02:48:58PM -0800, mingming cao wrote:
> On 01/08/2016 11:49 AM, Matthew Wilcox wrote:
> > 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.
>
> I dont think ext4 can do 1G at this time due to extent length bits
> (15 for unwritten) and block group size bundary (well, with flex bg we
> may able to relax this ). I have seen about 125M of contiguous space
> allocated on my fresh new ext4 filesystem. I do remember mballoc in ext4
> used to normalize the allocation request up to 8 or 16M, but it appears
> not that small any more.
I agree that the on-disk ext4 format can't represent a single 1GB
extent (ext4_extent's ee_len is 16 bits), but the in-memory extent tree
(extent_status's es_len) uses a 32-bit block count field, which can
represent an 8TB length extent with 4kB blocks.
It seems that at the moment, something is constraining allocations to be
at most 16MB, so that we can convert one extent_status to one ext4_extent.
What I'd like to see is code to convert one extent_status into multiple
ext4_extents on disc, and recombine multiple ext4_extents into a single
extent_status when the inode is read back in later.
Then we can start looking at places where ext4 puts metadata in the
middle of 1GB regions, preventing them from being used ... that'll be
a separate bag of issues, no doubt.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 32+ messages in thread
* Re: [PATCH v3 0/8] Support for transparent PUD pages for DAX files
2016-01-08 19:49 ` Matthew Wilcox
@ 2016-01-27 20:31 ` Andrew Morton
-1 siblings, 0 replies; 32+ messages in thread
From: Andrew Morton @ 2016-01-27 20:31 UTC (permalink / raw)
To: Matthew Wilcox
Cc: Matthew Wilcox, linux-mm, linux-nvdimm, linux-fsdevel, linux-kernel, x86
On Fri, 8 Jan 2016 14:49:44 -0500 Matthew Wilcox <matthew.r.wilcox@intel.com> wrote:
> Andrew, I think this is ready for a spin in -mm.
Let's see what happens.
Just from eyeballing the patches, I'm expecting build errors ;) I'm
about to vanish until Monday so please cc Stephen on any fixes so he
can get linux-next back into shape.
^ permalink raw reply [flat|nested] 32+ messages in thread
* Re: [PATCH v3 0/8] Support for transparent PUD pages for DAX files
@ 2016-01-27 20:31 ` Andrew Morton
0 siblings, 0 replies; 32+ messages in thread
From: Andrew Morton @ 2016-01-27 20:31 UTC (permalink / raw)
To: Matthew Wilcox
Cc: Matthew Wilcox, linux-mm, linux-nvdimm, linux-fsdevel, linux-kernel, x86
On Fri, 8 Jan 2016 14:49:44 -0500 Matthew Wilcox <matthew.r.wilcox@intel.com> wrote:
> Andrew, I think this is ready for a spin in -mm.
Let's see what happens.
Just from eyeballing the patches, I'm expecting build errors ;) I'm
about to vanish until Monday so please cc Stephen on any fixes so he
can get linux-next back into shape.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 32+ messages in thread
* Re: [PATCH v3 0/8] Support for transparent PUD pages for DAX files
2016-01-27 20:31 ` Andrew Morton
@ 2016-01-27 20:39 ` Andrew Morton
-1 siblings, 0 replies; 32+ messages in thread
From: Andrew Morton @ 2016-01-27 20:39 UTC (permalink / raw)
To: Matthew Wilcox, Matthew Wilcox, linux-mm, linux-nvdimm,
linux-fsdevel, linux-kernel, x86
On Wed, 27 Jan 2016 12:31:31 -0800 Andrew Morton <akpm@linux-foundation.org> wrote:
> Just from eyeballing the patches, I'm expecting build errors ;)
Didn't take long :(
mm/memory.c: In function 'zap_pud_range':
mm/memory.c:1216: error: implicit declaration of function 'pud_trans_huge'
mm/memory.c:1217: error: 'HPAGE_PUD_SIZE' undeclared (first use in this function)
and, midway:
include/linux/mm.h:348: error: redefinition of 'pud_devmap'
include/asm-generic/pgtable.h:684: note: previous definition of 'pud_devmap' was here
Please run x86_64 allnoconfig at each step of the series, fix and
respin? It only takes 30s to compile.
^ permalink raw reply [flat|nested] 32+ messages in thread
* Re: [PATCH v3 0/8] Support for transparent PUD pages for DAX files
@ 2016-01-27 20:39 ` Andrew Morton
0 siblings, 0 replies; 32+ messages in thread
From: Andrew Morton @ 2016-01-27 20:39 UTC (permalink / raw)
To: Matthew Wilcox, Matthew Wilcox, linux-mm, linux-nvdimm,
linux-fsdevel, linux-kernel, x86
On Wed, 27 Jan 2016 12:31:31 -0800 Andrew Morton <akpm@linux-foundation.org> wrote:
> Just from eyeballing the patches, I'm expecting build errors ;)
Didn't take long :(
mm/memory.c: In function 'zap_pud_range':
mm/memory.c:1216: error: implicit declaration of function 'pud_trans_huge'
mm/memory.c:1217: error: 'HPAGE_PUD_SIZE' undeclared (first use in this function)
and, midway:
include/linux/mm.h:348: error: redefinition of 'pud_devmap'
include/asm-generic/pgtable.h:684: note: previous definition of 'pud_devmap' was here
Please run x86_64 allnoconfig at each step of the series, fix and
respin? It only takes 30s to compile.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 32+ messages in thread
* RE: [PATCH v3 0/8] Support for transparent PUD pages for DAX files
2016-01-27 20:39 ` Andrew Morton
@ 2016-01-27 20:53 ` Wilcox, Matthew R
-1 siblings, 0 replies; 32+ messages in thread
From: Wilcox, Matthew R @ 2016-01-27 20:53 UTC (permalink / raw)
To: Andrew Morton, Matthew Wilcox, linux-mm, linux-nvdimm,
linux-fsdevel, linux-kernel, x86
Yeah, I need to rebase. Please drop for now, I'll resend tomorrow.
See you Monday, I assume ;-)
-----Original Message-----
From: Andrew Morton [mailto:akpm@linux-foundation.org]
Sent: Wednesday, January 27, 2016 12:40 PM
To: Wilcox, Matthew R; Matthew Wilcox; linux-mm@kvack.org; linux-nvdimm@ml01.01.org; linux-fsdevel@vger.kernel.org; linux-kernel@vger.kernel.org; x86@kernel.org
Subject: Re: [PATCH v3 0/8] Support for transparent PUD pages for DAX files
On Wed, 27 Jan 2016 12:31:31 -0800 Andrew Morton <akpm@linux-foundation.org> wrote:
> Just from eyeballing the patches, I'm expecting build errors ;)
Didn't take long :(
mm/memory.c: In function 'zap_pud_range':
mm/memory.c:1216: error: implicit declaration of function 'pud_trans_huge'
mm/memory.c:1217: error: 'HPAGE_PUD_SIZE' undeclared (first use in this function)
and, midway:
include/linux/mm.h:348: error: redefinition of 'pud_devmap'
include/asm-generic/pgtable.h:684: note: previous definition of 'pud_devmap' was here
Please run x86_64 allnoconfig at each step of the series, fix and
respin? It only takes 30s to compile.
^ permalink raw reply [flat|nested] 32+ messages in thread
* RE: [PATCH v3 0/8] Support for transparent PUD pages for DAX files
@ 2016-01-27 20:53 ` Wilcox, Matthew R
0 siblings, 0 replies; 32+ messages in thread
From: Wilcox, Matthew R @ 2016-01-27 20:53 UTC (permalink / raw)
To: Andrew Morton, Matthew Wilcox, linux-mm, linux-nvdimm,
linux-fsdevel, linux-kernel, x86
Yeah, I need to rebase. Please drop for now, I'll resend tomorrow.
See you Monday, I assume ;-)
-----Original Message-----
From: Andrew Morton [mailto:akpm@linux-foundation.org]
Sent: Wednesday, January 27, 2016 12:40 PM
To: Wilcox, Matthew R; Matthew Wilcox; linux-mm@kvack.org; linux-nvdimm@ml01.01.org; linux-fsdevel@vger.kernel.org; linux-kernel@vger.kernel.org; x86@kernel.org
Subject: Re: [PATCH v3 0/8] Support for transparent PUD pages for DAX files
On Wed, 27 Jan 2016 12:31:31 -0800 Andrew Morton <akpm@linux-foundation.org> wrote:
> Just from eyeballing the patches, I'm expecting build errors ;)
Didn't take long :(
mm/memory.c: In function 'zap_pud_range':
mm/memory.c:1216: error: implicit declaration of function 'pud_trans_huge'
mm/memory.c:1217: error: 'HPAGE_PUD_SIZE' undeclared (first use in this function)
and, midway:
include/linux/mm.h:348: error: redefinition of 'pud_devmap'
include/asm-generic/pgtable.h:684: note: previous definition of 'pud_devmap' was here
Please run x86_64 allnoconfig at each step of the series, fix and
respin? It only takes 30s to compile.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 32+ messages in thread
end of thread, other threads:[~2016-01-27 21:07 UTC | newest]
Thread overview: 32+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2016-01-08 19:49 [PATCH v3 0/8] Support for transparent PUD pages for DAX files Matthew Wilcox
2016-01-08 19:49 ` Matthew Wilcox
2016-01-08 19:49 ` [PATCH v3 1/8] mm: Convert an open-coded VM_BUG_ON_VMA Matthew Wilcox
2016-01-08 19:49 ` Matthew Wilcox
2016-01-08 19:49 ` [PATCH v3 2/8] mm,fs,dax: Change ->pmd_fault to ->huge_fault Matthew Wilcox
2016-01-08 19:49 ` Matthew Wilcox
2016-01-08 19:49 ` [PATCH v3 3/8] mm: Add support for PUD-sized transparent hugepages Matthew Wilcox
2016-01-08 19:49 ` Matthew Wilcox
2016-01-08 19:49 ` [PATCH v3 4/8] mincore: Add support for PUDs Matthew Wilcox
2016-01-08 19:49 ` Matthew Wilcox
2016-01-08 19:49 ` [PATCH v3 5/8] procfs: Add support for PUDs to smaps, clear_refs and pagemap Matthew Wilcox
2016-01-08 19:49 ` Matthew Wilcox
2016-01-08 19:49 ` [PATCH v3 6/8] x86: Add support for PUD-sized transparent hugepages Matthew Wilcox
2016-01-08 19:49 ` Matthew Wilcox
2016-01-08 19:49 ` [PATCH v3 7/8] dax: Support for transparent PUD pages Matthew Wilcox
2016-01-08 19:49 ` Matthew Wilcox
2016-01-08 19:49 ` [PATCH v3 8/8] ext4: Support for PUD-sized transparent huge pages Matthew Wilcox
2016-01-08 19:49 ` Matthew Wilcox
2016-01-15 19:41 ` [PATCH v3 0/8] Support for transparent PUD pages for DAX files Darrick J. Wong
2016-01-15 19:41 ` Darrick J. Wong
2016-01-22 11:26 ` Dave Chinner
2016-01-22 11:26 ` Dave Chinner
2016-01-21 22:48 ` mingming cao
2016-01-21 22:48 ` mingming cao
2016-01-22 14:11 ` Matthew Wilcox
2016-01-22 14:11 ` Matthew Wilcox
2016-01-27 20:31 ` Andrew Morton
2016-01-27 20:31 ` Andrew Morton
2016-01-27 20:39 ` Andrew Morton
2016-01-27 20:39 ` Andrew Morton
2016-01-27 20:53 ` Wilcox, Matthew R
2016-01-27 20:53 ` Wilcox, Matthew R
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.