From: Dan Williams <dan.j.williams@intel.com>
To: linux-nvdimm@lists.01.org
Cc: jack@suse.cz, Matthew Wilcox <mawilcox@microsoft.com>,
david@fromorbit.com, linux-kernel@vger.kernel.org,
linux-xfs@vger.kernel.org, linux-fsdevel@vger.kernel.org,
hch@lst.de
Subject: [PATCH v6 01/15] dax: store pfns in the radix
Date: Thu, 15 Mar 2018 08:51:28 -0700 [thread overview]
Message-ID: <152112908811.24669.5995044545442928838.stgit@dwillia2-desk3.amr.corp.intel.com> (raw)
In-Reply-To: <152112908134.24669.10222746224538377035.stgit@dwillia2-desk3.amr.corp.intel.com>
In preparation for examining the busy state of dax pages in the truncate
path, switch from sectors to pfns in the radix.
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Matthew Wilcox <mawilcox@microsoft.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
drivers/dax/super.c | 15 +++++++--
fs/dax.c | 83 +++++++++++++++++++--------------------------------
2 files changed, 43 insertions(+), 55 deletions(-)
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index ecdc292aa4e4..2b2332b605e4 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -124,10 +124,19 @@ int __bdev_dax_supported(struct super_block *sb, int blocksize)
return len < 0 ? len : -EIO;
}
- if ((IS_ENABLED(CONFIG_FS_DAX_LIMITED) && pfn_t_special(pfn))
- || pfn_t_devmap(pfn))
+ if (IS_ENABLED(CONFIG_FS_DAX_LIMITED) && pfn_t_special(pfn)) {
+ /*
+ * An arch that has enabled the pmem api should also
+ * have its drivers support pfn_t_devmap()
+ *
+ * This is a developer warning and should not trigger in
+ * production. dax_flush() will crash since it depends
+ * on being able to do (page_address(pfn_to_page())).
+ */
+ WARN_ON(IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API));
+ } else if (pfn_t_devmap(pfn)) {
/* pass */;
- else {
+ } else {
pr_debug("VFS (%s): error: dax support not enabled\n",
sb->s_id);
return -EOPNOTSUPP;
diff --git a/fs/dax.c b/fs/dax.c
index 0276df90e86c..b646a46e4d12 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -73,16 +73,15 @@ fs_initcall(init_dax_wait_table);
#define RADIX_DAX_ZERO_PAGE (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2))
#define RADIX_DAX_EMPTY (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 3))
-static unsigned long dax_radix_sector(void *entry)
+static unsigned long dax_radix_pfn(void *entry)
{
return (unsigned long)entry >> RADIX_DAX_SHIFT;
}
-static void *dax_radix_locked_entry(sector_t sector, unsigned long flags)
+static void *dax_radix_locked_entry(unsigned long pfn, unsigned long flags)
{
return (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | flags |
- ((unsigned long)sector << RADIX_DAX_SHIFT) |
- RADIX_DAX_ENTRY_LOCK);
+ (pfn << RADIX_DAX_SHIFT) | RADIX_DAX_ENTRY_LOCK);
}
static unsigned int dax_radix_order(void *entry)
@@ -526,12 +525,13 @@ static int copy_user_dax(struct block_device *bdev, struct dax_device *dax_dev,
*/
static void *dax_insert_mapping_entry(struct address_space *mapping,
struct vm_fault *vmf,
- void *entry, sector_t sector,
+ void *entry, pfn_t pfn_t,
unsigned long flags, bool dirty)
{
struct radix_tree_root *page_tree = &mapping->page_tree;
- void *new_entry;
+ unsigned long pfn = pfn_t_to_pfn(pfn_t);
pgoff_t index = vmf->pgoff;
+ void *new_entry;
if (dirty)
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
@@ -546,7 +546,7 @@ static void *dax_insert_mapping_entry(struct address_space *mapping,
}
spin_lock_irq(&mapping->tree_lock);
- new_entry = dax_radix_locked_entry(sector, flags);
+ new_entry = dax_radix_locked_entry(pfn, flags);
if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
/*
@@ -657,17 +657,14 @@ static void dax_mapping_entry_mkclean(struct address_space *mapping,
i_mmap_unlock_read(mapping);
}
-static int dax_writeback_one(struct block_device *bdev,
- struct dax_device *dax_dev, struct address_space *mapping,
- pgoff_t index, void *entry)
+static int dax_writeback_one(struct dax_device *dax_dev,
+ struct address_space *mapping, pgoff_t index, void *entry)
{
struct radix_tree_root *page_tree = &mapping->page_tree;
- void *entry2, **slot, *kaddr;
- long ret = 0, id;
- sector_t sector;
- pgoff_t pgoff;
+ void *entry2, **slot;
+ unsigned long pfn;
+ long ret = 0;
size_t size;
- pfn_t pfn;
/*
* A page got tagged dirty in DAX mapping? Something is seriously
@@ -683,10 +680,10 @@ static int dax_writeback_one(struct block_device *bdev,
goto put_unlocked;
/*
* Entry got reallocated elsewhere? No need to writeback. We have to
- * compare sectors as we must not bail out due to difference in lockbit
+ * compare pfns as we must not bail out due to difference in lockbit
* or entry type.
*/
- if (dax_radix_sector(entry2) != dax_radix_sector(entry))
+ if (dax_radix_pfn(entry2) != dax_radix_pfn(entry))
goto put_unlocked;
if (WARN_ON_ONCE(dax_is_empty_entry(entry) ||
dax_is_zero_entry(entry))) {
@@ -712,33 +709,15 @@ static int dax_writeback_one(struct block_device *bdev,
/*
* Even if dax_writeback_mapping_range() was given a wbc->range_start
* in the middle of a PMD, the 'index' we are given will be aligned to
- * the start index of the PMD, as will the sector we pull from
- * 'entry'. This allows us to flush for PMD_SIZE and not have to
- * worry about partial PMD writebacks.
+ * the start index of the PMD, as will the pfn we pull from 'entry'.
+ * This allows us to flush for PMD_SIZE and not have to worry about
+ * partial PMD writebacks.
*/
- sector = dax_radix_sector(entry);
+ pfn = dax_radix_pfn(entry);
size = PAGE_SIZE << dax_radix_order(entry);
- id = dax_read_lock();
- ret = bdev_dax_pgoff(bdev, sector, size, &pgoff);
- if (ret)
- goto dax_unlock;
-
- /*
- * dax_direct_access() may sleep, so cannot hold tree_lock over
- * its invocation.
- */
- ret = dax_direct_access(dax_dev, pgoff, size / PAGE_SIZE, &kaddr, &pfn);
- if (ret < 0)
- goto dax_unlock;
-
- if (WARN_ON_ONCE(ret < size / PAGE_SIZE)) {
- ret = -EIO;
- goto dax_unlock;
- }
-
- dax_mapping_entry_mkclean(mapping, index, pfn_t_to_pfn(pfn));
- dax_flush(dax_dev, kaddr, size);
+ dax_mapping_entry_mkclean(mapping, index, pfn);
+ dax_flush(dax_dev, page_address(pfn_to_page(pfn)), size);
/*
* After we have flushed the cache, we can clear the dirty tag. There
* cannot be new dirty data in the pfn after the flush has completed as
@@ -749,8 +728,6 @@ static int dax_writeback_one(struct block_device *bdev,
radix_tree_tag_clear(page_tree, index, PAGECACHE_TAG_DIRTY);
spin_unlock_irq(&mapping->tree_lock);
trace_dax_writeback_one(mapping->host, index, size >> PAGE_SHIFT);
- dax_unlock:
- dax_read_unlock(id);
put_locked_mapping_entry(mapping, index);
return ret;
@@ -808,8 +785,8 @@ int dax_writeback_mapping_range(struct address_space *mapping,
break;
}
- ret = dax_writeback_one(bdev, dax_dev, mapping,
- indices[i], pvec.pages[i]);
+ ret = dax_writeback_one(dax_dev, mapping, indices[i],
+ pvec.pages[i]);
if (ret < 0) {
mapping_set_error(mapping, ret);
goto out;
@@ -877,6 +854,7 @@ static int dax_load_hole(struct address_space *mapping, void *entry,
int ret = VM_FAULT_NOPAGE;
struct page *zero_page;
void *entry2;
+ pfn_t pfn;
zero_page = ZERO_PAGE(0);
if (unlikely(!zero_page)) {
@@ -884,14 +862,15 @@ static int dax_load_hole(struct address_space *mapping, void *entry,
goto out;
}
- entry2 = dax_insert_mapping_entry(mapping, vmf, entry, 0,
+ pfn = page_to_pfn_t(zero_page);
+ entry2 = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
RADIX_DAX_ZERO_PAGE, false);
if (IS_ERR(entry2)) {
ret = VM_FAULT_SIGBUS;
goto out;
}
- vm_insert_mixed(vmf->vma, vaddr, page_to_pfn_t(zero_page));
+ vm_insert_mixed(vmf->vma, vaddr, pfn);
out:
trace_dax_load_hole(inode, vmf, ret);
return ret;
@@ -1200,8 +1179,7 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
if (error < 0)
goto error_finish_iomap;
- entry = dax_insert_mapping_entry(mapping, vmf, entry,
- dax_iomap_sector(&iomap, pos),
+ entry = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
0, write && !sync);
if (IS_ERR(entry)) {
error = PTR_ERR(entry);
@@ -1280,13 +1258,15 @@ static int dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap,
void *ret = NULL;
spinlock_t *ptl;
pmd_t pmd_entry;
+ pfn_t pfn;
zero_page = mm_get_huge_zero_page(vmf->vma->vm_mm);
if (unlikely(!zero_page))
goto fallback;
- ret = dax_insert_mapping_entry(mapping, vmf, entry, 0,
+ pfn = page_to_pfn_t(zero_page);
+ ret = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
RADIX_DAX_PMD | RADIX_DAX_ZERO_PAGE, false);
if (IS_ERR(ret))
goto fallback;
@@ -1409,8 +1389,7 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
if (error < 0)
goto finish_iomap;
- entry = dax_insert_mapping_entry(mapping, vmf, entry,
- dax_iomap_sector(&iomap, pos),
+ entry = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
RADIX_DAX_PMD, write && !sync);
if (IS_ERR(entry))
goto finish_iomap;
_______________________________________________
Linux-nvdimm mailing list
Linux-nvdimm@lists.01.org
https://lists.01.org/mailman/listinfo/linux-nvdimm
next prev parent reply other threads:[~2018-03-15 15:54 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-03-15 15:51 [PATCH v6 00/15] dax: fix dma vs truncate/hole-punch Dan Williams
2018-03-15 15:51 ` Dan Williams [this message]
2018-03-15 15:51 ` [PATCH v6 02/15] fs, dax: prepare for dax-specific address_space_operations Dan Williams
2018-03-16 18:59 ` Christoph Hellwig
2018-03-15 15:51 ` [PATCH v6 03/15] block, dax: remove dead code in blkdev_writepages() Dan Williams
2018-03-16 18:59 ` Christoph Hellwig
2018-03-15 15:51 ` [PATCH v6 04/15] xfs, dax: introduce xfs_dax_aops Dan Williams
2018-03-16 19:00 ` Christoph Hellwig
2018-03-15 15:51 ` [PATCH v6 05/15] ext4, dax: introduce ext4_dax_aops Dan Williams
2018-03-15 15:51 ` [PATCH v6 06/15] ext2, dax: introduce ext2_dax_aops Dan Williams
2018-03-18 4:02 ` kbuild test robot
2018-03-18 4:02 ` [RFC PATCH] ext2, dax: ext2_dax_aops can be static kbuild test robot
2018-03-15 15:52 ` [PATCH v6 07/15] fs, dax: use page->mapping to warn if truncate collides with a busy page Dan Williams
2018-03-18 6:26 ` kbuild test robot
2018-03-15 15:52 ` [PATCH v6 08/15] mm, dax: enable filesystems to trigger dev_pagemap ->page_free callbacks Dan Williams
2018-03-15 15:52 ` [PATCH v6 09/15] mm, dev_pagemap: introduce CONFIG_DEV_PAGEMAP_OPS Dan Williams
2018-03-15 15:52 ` [PATCH v6 10/15] memremap: mark devm_memremap_pages() EXPORT_SYMBOL_GPL Dan Williams
2018-03-15 15:52 ` [PATCH v6 11/15] mm, fs, dax: handle layout changes to pinned dax mappings Dan Williams
2018-03-16 19:01 ` Christoph Hellwig
2018-03-17 22:14 ` kbuild test robot
2018-03-15 15:52 ` [PATCH v6 12/15] xfs: require mmap lock for xfs_break_layouts() Dan Williams
2018-03-16 19:04 ` Christoph Hellwig
2018-03-16 19:10 ` Dan Williams
2018-03-19 17:33 ` Darrick J. Wong
2018-03-19 17:57 ` Dan Williams
2018-03-19 18:19 ` Darrick J. Wong
2018-03-19 18:34 ` Dan Williams
2018-03-19 19:45 ` Christoph Hellwig
2018-03-19 20:10 ` Dan Williams
2018-03-19 21:14 ` Christoph Hellwig
2018-03-15 15:52 ` [PATCH v6 13/15] xfs: communicate lock drop events from xfs_break_layouts() Dan Williams
2018-03-16 19:08 ` Christoph Hellwig
2018-03-15 15:52 ` [PATCH v6 14/15] xfs: prepare xfs_break_layouts() for another layout type Dan Williams
2018-03-16 19:08 ` Christoph Hellwig
2018-03-19 17:45 ` Darrick J. Wong
2018-03-19 18:09 ` Dan Williams
2018-03-15 15:52 ` [PATCH v6 15/15] xfs, dax: introduce xfs_break_dax_layouts() Dan Williams
2018-03-16 19:09 ` Christoph Hellwig
2018-03-17 22:11 ` kbuild test robot
2018-03-17 23:47 ` kbuild test robot
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=152112908811.24669.5995044545442928838.stgit@dwillia2-desk3.amr.corp.intel.com \
--to=dan.j.williams@intel.com \
--cc=david@fromorbit.com \
--cc=hch@lst.de \
--cc=jack@suse.cz \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nvdimm@lists.01.org \
--cc=linux-xfs@vger.kernel.org \
--cc=mawilcox@microsoft.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).