From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
To: "Theodore Ts'o" <tytso@mit.edu>,
Andreas Dilger <adilger.kernel@dilger.ca>,
Jan Kara <jack@suse.com>,
Andrew Morton <akpm@linux-foundation.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>,
Hugh Dickins <hughd@google.com>,
Andrea Arcangeli <aarcange@redhat.com>,
Dave Hansen <dave.hansen@intel.com>,
Vlastimil Babka <vbabka@suse.cz>,
Matthew Wilcox <willy@infradead.org>,
Ross Zwisler <ross.zwisler@linux.intel.com>,
linux-ext4@vger.kernel.org, linux-fsdevel@vger.kernel.org,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
linux-block@vger.kernel.org,
"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Subject: [PATCHv6 37/37] ext4, vfs: add huge= mount option
Date: Thu, 26 Jan 2017 14:58:19 +0300 [thread overview]
Message-ID: <20170126115819.58875-38-kirill.shutemov@linux.intel.com> (raw)
In-Reply-To: <20170126115819.58875-1-kirill.shutemov@linux.intel.com>
The same four values as in tmpfs case.
Encyption code is not yet ready to handle huge page, so we disable huge
pages support if the inode has EXT4_INODE_ENCRYPT.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
fs/ext4/ext4.h | 5 +++++
fs/ext4/inode.c | 32 +++++++++++++++++++++++---------
fs/ext4/super.c | 24 ++++++++++++++++++++++++
3 files changed, 52 insertions(+), 9 deletions(-)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 2163c1e69f2a..19bb9995fa96 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1134,6 +1134,11 @@ struct ext4_inode_info {
#define EXT4_MOUNT_DIOREAD_NOLOCK 0x400000 /* Enable support for dio read nolocking */
#define EXT4_MOUNT_JOURNAL_CHECKSUM 0x800000 /* Journal checksums */
#define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */
+#define EXT4_MOUNT_HUGE_MODE 0x6000000 /* Huge support mode: */
+#define EXT4_MOUNT_HUGE_NEVER 0x0000000
+#define EXT4_MOUNT_HUGE_ALWAYS 0x2000000
+#define EXT4_MOUNT_HUGE_WITHIN_SIZE 0x4000000
+#define EXT4_MOUNT_HUGE_ADVISE 0x6000000
#define EXT4_MOUNT_DELALLOC 0x8000000 /* Delalloc support */
#define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000 /* Abort on file data write */
#define EXT4_MOUNT_BLOCK_VALIDITY 0x20000000 /* Block validity checking */
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index e24ccf4c3694..120d32bcb6af 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4481,7 +4481,7 @@ int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc)
void ext4_set_inode_flags(struct inode *inode)
{
unsigned int flags = EXT4_I(inode)->i_flags;
- unsigned int new_fl = 0;
+ unsigned int mask, new_fl = 0;
if (flags & EXT4_SYNC_FL)
new_fl |= S_SYNC;
@@ -4493,11 +4493,25 @@ void ext4_set_inode_flags(struct inode *inode)
new_fl |= S_NOATIME;
if (flags & EXT4_DIRSYNC_FL)
new_fl |= S_DIRSYNC;
- if (test_opt(inode->i_sb, DAX) && S_ISREG(inode->i_mode) &&
- !ext4_should_journal_data(inode) && !ext4_has_inline_data(inode) &&
- !ext4_encrypted_inode(inode))
- new_fl |= S_DAX;
-
+ if (S_ISREG(inode->i_mode) && !ext4_encrypted_inode(inode)) {
+ if (test_opt(inode->i_sb, DAX) &&
+ !ext4_should_journal_data(inode) &&
+ !ext4_has_inline_data(inode))
+ new_fl |= S_DAX;
+ switch (test_opt(inode->i_sb, HUGE_MODE)) {
+ case EXT4_MOUNT_HUGE_NEVER:
+ break;
+ case EXT4_MOUNT_HUGE_ALWAYS:
+ new_fl |= S_HUGE_ALWAYS;
+ break;
+ case EXT4_MOUNT_HUGE_WITHIN_SIZE:
+ new_fl |= S_HUGE_WITHIN_SIZE;
+ break;
+ case EXT4_MOUNT_HUGE_ADVISE:
+ new_fl |= S_HUGE_ADVISE;
+ break;
+ }
+ }
if ((new_fl & S_HUGE_MODE) != S_HUGE_NEVER &&
EXT4_JOURNAL(inode) != NULL) {
int bpp = __ext4_journal_blocks_per_page(inode, true);
@@ -4511,9 +4525,9 @@ void ext4_set_inode_flags(struct inode *inode)
new_fl &= ~S_HUGE_MODE;
}
}
-
- inode_set_flags(inode, new_fl,
- S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX);
+ mask = S_SYNC | S_APPEND | S_IMMUTABLE | S_NOATIME |
+ S_DIRSYNC | S_DAX | S_HUGE_MODE;
+ inode_set_flags(inode, new_fl, mask);
}
/* Propagate flags from i_flags to EXT4_I(inode)->i_flags */
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 66845a08a87a..13376a72050c 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1296,6 +1296,7 @@ enum {
Opt_dioread_nolock, Opt_dioread_lock,
Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable,
Opt_max_dir_size_kb, Opt_nojournal_checksum,
+ Opt_huge_never, Opt_huge_always, Opt_huge_within_size, Opt_huge_advise,
};
static const match_table_t tokens = {
@@ -1376,6 +1377,10 @@ static const match_table_t tokens = {
{Opt_init_itable, "init_itable"},
{Opt_noinit_itable, "noinit_itable"},
{Opt_max_dir_size_kb, "max_dir_size_kb=%u"},
+ {Opt_huge_never, "huge=never"},
+ {Opt_huge_always, "huge=always"},
+ {Opt_huge_within_size, "huge=within_size"},
+ {Opt_huge_advise, "huge=advise"},
{Opt_test_dummy_encryption, "test_dummy_encryption"},
{Opt_removed, "check=none"}, /* mount option from ext2/3 */
{Opt_removed, "nocheck"}, /* mount option from ext2/3 */
@@ -1494,6 +1499,11 @@ static int clear_qf_name(struct super_block *sb, int qtype)
#define MOPT_NO_EXT3 0x0200
#define MOPT_EXT4_ONLY (MOPT_NO_EXT2 | MOPT_NO_EXT3)
#define MOPT_STRING 0x0400
+#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE
+#define MOPT_HUGE 0x1000
+#else
+#define MOPT_HUGE MOPT_NOSUPPORT
+#endif
static const struct mount_opts {
int token;
@@ -1581,6 +1591,10 @@ static const struct mount_opts {
{Opt_jqfmt_vfsv0, QFMT_VFS_V0, MOPT_QFMT},
{Opt_jqfmt_vfsv1, QFMT_VFS_V1, MOPT_QFMT},
{Opt_max_dir_size_kb, 0, MOPT_GTE0},
+ {Opt_huge_never, EXT4_MOUNT_HUGE_NEVER, MOPT_HUGE},
+ {Opt_huge_always, EXT4_MOUNT_HUGE_ALWAYS, MOPT_HUGE},
+ {Opt_huge_within_size, EXT4_MOUNT_HUGE_WITHIN_SIZE, MOPT_HUGE},
+ {Opt_huge_advise, EXT4_MOUNT_HUGE_ADVISE, MOPT_HUGE},
{Opt_test_dummy_encryption, 0, MOPT_GTE0},
{Opt_err, 0, 0}
};
@@ -1662,6 +1676,16 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
} else
return -1;
}
+ if (MOPT_HUGE != MOPT_NOSUPPORT && m->flags & MOPT_HUGE) {
+ sbi->s_mount_opt &= ~EXT4_MOUNT_HUGE_MODE;
+ sbi->s_mount_opt |= m->mount_opt;
+ if (m->mount_opt) {
+ ext4_msg(sb, KERN_WARNING, "Warning: "
+ "Support of huge pages is EXPERIMENTAL,"
+ " use at your own risk");
+ }
+ return 1;
+ }
if (m->flags & MOPT_CLEAR_ERR)
clear_opt(sb, ERRORS_MASK);
if (token == Opt_noquota && sb_any_quota_loaded(sb)) {
--
2.11.0
prev parent reply other threads:[~2017-01-26 12:04 UTC|newest]
Thread overview: 67+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-01-26 11:57 [PATCHv6 00/37] ext4: support of huge pages Kirill A. Shutemov
2017-01-26 11:57 ` [PATCHv6 01/37] mm, shmem: swich huge tmpfs to multi-order radix-tree entries Kirill A. Shutemov
2017-02-09 3:57 ` Matthew Wilcox
2017-02-09 16:58 ` Kirill A. Shutemov
2017-02-13 13:43 ` Kirill A. Shutemov
2017-01-26 11:57 ` [PATCHv6 02/37] Revert "radix-tree: implement radix_tree_maybe_preload_order()" Kirill A. Shutemov
2017-01-26 15:38 ` Matthew Wilcox
2017-01-26 11:57 ` [PATCHv6 03/37] page-flags: relax page flag policy for few flags Kirill A. Shutemov
2017-02-09 4:01 ` Matthew Wilcox
2017-02-13 13:59 ` Kirill A. Shutemov
2017-01-26 11:57 ` [PATCHv6 04/37] mm, rmap: account file thp pages Kirill A. Shutemov
2017-02-09 20:17 ` Matthew Wilcox
2017-01-26 11:57 ` [PATCHv6 05/37] thp: try to free page's buffers before attempt split Kirill A. Shutemov
2017-02-09 20:14 ` Matthew Wilcox
2017-02-13 14:32 ` Kirill A. Shutemov
2017-01-26 11:57 ` [PATCHv6 06/37] thp: handle write-protection faults for file THP Kirill A. Shutemov
2017-01-26 15:44 ` Matthew Wilcox
2017-01-26 15:57 ` Kirill A. Shutemov
2017-02-09 20:19 ` Matthew Wilcox
2017-01-26 11:57 ` [PATCHv6 07/37] filemap: allocate huge page in page_cache_read(), if allowed Kirill A. Shutemov
2017-02-09 21:18 ` Matthew Wilcox
2017-02-13 15:17 ` Kirill A. Shutemov
2017-01-26 11:57 ` [PATCHv6 08/37] filemap: handle huge pages in do_generic_file_read() Kirill A. Shutemov
2017-02-09 21:55 ` Matthew Wilcox
2017-02-13 15:33 ` Kirill A. Shutemov
2017-02-13 16:01 ` Matthew Wilcox
2017-02-13 16:09 ` Matthew Wilcox
2017-02-13 16:28 ` Matthew Wilcox
2017-01-26 11:57 ` [PATCHv6 09/37] filemap: allocate huge page in pagecache_get_page(), if allowed Kirill A. Shutemov
2017-02-09 21:59 ` Matthew Wilcox
2017-01-26 11:57 ` [PATCHv6 10/37] filemap: handle huge pages in filemap_fdatawait_range() Kirill A. Shutemov
2017-02-09 23:03 ` Matthew Wilcox
2017-01-26 11:57 ` [PATCHv6 11/37] HACK: readahead: alloc huge pages, if allowed Kirill A. Shutemov
2017-02-09 23:34 ` Matthew Wilcox
2017-02-10 0:23 ` Andreas Dilger
2017-02-10 14:51 ` Matthew Wilcox
2017-01-26 11:57 ` [PATCHv6 12/37] brd: make it handle huge pages Kirill A. Shutemov
2017-02-10 17:24 ` Matthew Wilcox
2017-01-26 11:57 ` [PATCHv6 13/37] mm: make write_cache_pages() work on " Kirill A. Shutemov
2017-02-10 17:46 ` Matthew Wilcox
2017-01-26 11:57 ` [PATCHv6 14/37] thp: introduce hpage_size() and hpage_mask() Kirill A. Shutemov
2017-01-26 11:57 ` [PATCHv6 15/37] thp: do not threat slab pages as huge in hpage_{nr_pages,size,mask} Kirill A. Shutemov
2017-02-10 22:13 ` Matthew Wilcox
2017-01-26 11:57 ` [PATCHv6 16/37] thp: make thp_get_unmapped_area() respect S_HUGE_MODE Kirill A. Shutemov
2017-02-10 17:50 ` Matthew Wilcox
2017-01-26 11:57 ` [PATCHv6 17/37] fs: make block_read_full_page() be able to read huge page Kirill A. Shutemov
2017-02-10 17:58 ` Matthew Wilcox
2017-01-26 11:58 ` [PATCHv6 18/37] fs: make block_write_{begin,end}() be able to handle huge pages Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 19/37] fs: make block_page_mkwrite() aware about " Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 20/37] truncate: make truncate_inode_pages_range() " Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 21/37] truncate: make invalidate_inode_pages2_range() " Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 22/37] mm, hugetlb: switch hugetlbfs to multi-order radix-tree entries Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 23/37] mm: account huge pages to dirty, writaback, reclaimable, etc Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 24/37] ext4: make ext4_mpage_readpages() hugepage-aware Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 25/37] ext4: make ext4_writepage() work on huge pages Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 26/37] ext4: handle huge pages in ext4_page_mkwrite() Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 27/37] ext4: handle huge pages in __ext4_block_zero_page_range() Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 28/37] ext4: make ext4_block_write_begin() aware about huge pages Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 29/37] ext4: handle huge pages in ext4_da_write_end() Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 30/37] ext4: make ext4_da_page_release_reservation() aware about huge pages Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 31/37] ext4: handle writeback with " Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 32/37] ext4: make EXT4_IOC_MOVE_EXT work " Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 33/37] ext4: fix SEEK_DATA/SEEK_HOLE for " Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 34/37] ext4: make fallocate() operations work with " Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 35/37] ext4: reserve larger jounral transaction for " Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 36/37] mm, fs, ext4: expand use of page_mapping() and page_to_pgoff() Kirill A. Shutemov
2017-01-26 11:58 ` Kirill A. Shutemov [this message]
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=20170126115819.58875-38-kirill.shutemov@linux.intel.com \
--to=kirill.shutemov@linux.intel.com \
--cc=aarcange@redhat.com \
--cc=adilger.kernel@dilger.ca \
--cc=akpm@linux-foundation.org \
--cc=dave.hansen@intel.com \
--cc=hughd@google.com \
--cc=jack@suse.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-ext4@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=ross.zwisler@linux.intel.com \
--cc=tytso@mit.edu \
--cc=vbabka@suse.cz \
--cc=viro@zeniv.linux.org.uk \
--cc=willy@infradead.org \
/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).