Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-11-10 14:11:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

dax: provide diagnostics for pmd mapping failures

Browse Source 
There is a wide gamut of conditions that can trigger the dax pmd path to
fallback to pte mappings.  Ideally we'd have a syscall interface to
determine mapping characteristics after the fact.  In the meantime
provide debug messages.

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Suggested-by: Matthew Wilcox <willy@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Dan Williams 2016-01-15 16:56:58 -08:00 committed by Linus Torvalds
parent 3565fce3a6
commit cbb38e41a9
1 changed files with 57 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

65
fs/dax.c
View File

@ -558,6 +558,24 @@ EXPORT_SYMBOL_GPL(dax_fault);
*/
#define PG_PMD_COLOUR ((PMD_SIZE >> PAGE_SHIFT) - 1)
static void __dax_dbg(struct buffer_head *bh, unsigned long address,
const char *reason, const char *fn)
{
if (bh) {
char bname[BDEVNAME_SIZE];
bdevname(bh->b_bdev, bname);
pr_debug("%s: %s addr: %lx dev %s state %lx start %lld "
"length %zd fallback: %s\n", fn, current->comm,
address, bname, bh->b_state, (u64)bh->b_blocknr,
bh->b_size, reason);
} else {
pr_debug("%s: %s addr: %lx fallback: %s\n", fn,
current->comm, address, reason);
}
}
#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,
pmd_t *pmd, unsigned int flags, get_block_t get_block,
dax_iodone_t complete_unwritten)
@ -581,21 +599,29 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
/* Fall back to PTEs if we're going to COW */
if (write && !(vma->vm_flags & VM_SHARED)) {
split_huge_pmd(vma, pmd, address);
dax_pmd_dbg(NULL, address, "cow write");
return VM_FAULT_FALLBACK;
}
/* If the PMD would extend outside the VMA */
if (pmd_addr < vma->vm_start)
if (pmd_addr < vma->vm_start) {
dax_pmd_dbg(NULL, address, "vma start unaligned");
return VM_FAULT_FALLBACK;
if ((pmd_addr + PMD_SIZE) > vma->vm_end)
}
if ((pmd_addr + PMD_SIZE) > vma->vm_end) {
dax_pmd_dbg(NULL, address, "vma end unaligned");
return VM_FAULT_FALLBACK;
}
pgoff = linear_page_index(vma, pmd_addr);
size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (pgoff >= size)
return VM_FAULT_SIGBUS;
/* If the PMD would cover blocks out of the file */
if ((pgoff | PG_PMD_COLOUR) >= size)
if ((pgoff | PG_PMD_COLOUR) >= size) {
dax_pmd_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);
@ -611,8 +637,10 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
* just fall back to PTEs. Calling get_block 512 times in a loop
* would be silly.
*/
if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE)
if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE) {
dax_pmd_dbg(&bh, address, "allocated block too small");
goto fallback;
}
/*
* If we allocated new storage, make sure no process has any
@ -635,23 +663,33 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
result = VM_FAULT_SIGBUS;
goto out;
}
if ((pgoff | PG_PMD_COLOUR) >= size)
if ((pgoff | PG_PMD_COLOUR) >= size) {
dax_pmd_dbg(&bh, address, "pgoff unaligned");
goto fallback;
}
if (!write && !buffer_mapped(&bh) && buffer_uptodate(&bh)) {
spinlock_t *ptl;
pmd_t entry;
struct page *zero_page = get_huge_zero_page();
if (unlikely(!zero_page))
if (unlikely(!zero_page)) {
dax_pmd_dbg(&bh, address, "no zero page");
goto fallback;
}
ptl = pmd_lock(vma->vm_mm, pmd);
if (!pmd_none(*pmd)) {
spin_unlock(ptl);
dax_pmd_dbg(&bh, address, "pmd already present");
goto fallback;
}
dev_dbg(part_to_dev(bdev->bd_part),
"%s: %s addr: %lx pfn: <zero> sect: %llx\n",
__func__, current->comm, address,
(unsigned long long) to_sector(&bh, inode));
entry = mk_pmd(zero_page, vma->vm_page_prot);
entry = pmd_mkhuge(entry);
set_pmd_at(vma->vm_mm, pmd_addr, pmd, entry);
@ -668,8 +706,13 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
result = VM_FAULT_SIGBUS;
goto out;
}
if (length < PMD_SIZE
|| (pfn_t_to_pfn(dax.pfn) & PG_PMD_COLOUR)) {
if (length < PMD_SIZE) {
dax_pmd_dbg(&bh, address, "dax-length too small");
dax_unmap_atomic(bdev, &dax);
goto fallback;
}
if (pfn_t_to_pfn(dax.pfn) & PG_PMD_COLOUR) {
dax_pmd_dbg(&bh, address, "pfn unaligned");
dax_unmap_atomic(bdev, &dax);
goto fallback;
}
@ -680,6 +723,7 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
*/
if (pfn_t_has_page(dax.pfn)) {
dax_unmap_atomic(bdev, &dax);
dax_pmd_dbg(&bh, address, "pfn not in memmap");
goto fallback;
}
@ -692,6 +736,11 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
}
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_pmd(vma, address, pmd,
dax.pfn, write);
}