From: Jens Axboe <axboe@kernel.dk>
To: linux-mm@kvack.org, linux-fsdevel@vger.kernel.org,
linux-block@vger.kernel.org
Cc: willy@infradead.org, clm@fb.com, torvalds@linux-foundation.org,
david@fromorbit.com, Jens Axboe <axboe@kernel.dk>
Subject: [PATCH 1/5] fs: add read support for RWF_UNCACHED
Date: Wed, 11 Dec 2019 08:29:39 -0700 [thread overview]
Message-ID: <20191211152943.2933-2-axboe@kernel.dk> (raw)
In-Reply-To: <20191211152943.2933-1-axboe@kernel.dk>
If RWF_UNCACHED is set for io_uring (or preadv2(2)), we'll drop the
cache for buffered reads if we are the ones instantiating it. If the
data is already cached, we leave it cached.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
include/linux/fs.h | 3 +++
include/uapi/linux/fs.h | 5 ++++-
mm/filemap.c | 46 ++++++++++++++++++++++++++++++++++++-----
3 files changed, 48 insertions(+), 6 deletions(-)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 98e0349adb52..092ea2a4319b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -314,6 +314,7 @@ enum rw_hint {
#define IOCB_SYNC (1 << 5)
#define IOCB_WRITE (1 << 6)
#define IOCB_NOWAIT (1 << 7)
+#define IOCB_UNCACHED (1 << 8)
struct kiocb {
struct file *ki_filp;
@@ -3418,6 +3419,8 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
ki->ki_flags |= (IOCB_DSYNC | IOCB_SYNC);
if (flags & RWF_APPEND)
ki->ki_flags |= IOCB_APPEND;
+ if (flags & RWF_UNCACHED)
+ ki->ki_flags |= IOCB_UNCACHED;
return 0;
}
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 379a612f8f1d..357ebb0e0c5d 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -299,8 +299,11 @@ typedef int __bitwise __kernel_rwf_t;
/* per-IO O_APPEND */
#define RWF_APPEND ((__force __kernel_rwf_t)0x00000010)
+/* drop cache after reading or writing data */
+#define RWF_UNCACHED ((__force __kernel_rwf_t)0x00000040)
+
/* mask of flags supported by the kernel */
#define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
- RWF_APPEND)
+ RWF_APPEND | RWF_UNCACHED)
#endif /* _UAPI_LINUX_FS_H */
diff --git a/mm/filemap.c b/mm/filemap.c
index bf6aa30be58d..ed23a11b3e34 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -933,8 +933,8 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
}
EXPORT_SYMBOL(add_to_page_cache_locked);
-int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
- pgoff_t offset, gfp_t gfp_mask)
+static int __add_to_page_cache(struct page *page, struct address_space *mapping,
+ pgoff_t offset, gfp_t gfp_mask, bool lru)
{
void *shadow = NULL;
int ret;
@@ -956,9 +956,17 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
WARN_ON_ONCE(PageActive(page));
if (!(gfp_mask & __GFP_WRITE) && shadow)
workingset_refault(page, shadow);
- lru_cache_add(page);
+ if (lru)
+ lru_cache_add(page);
}
return ret;
+
+}
+
+int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
+ pgoff_t offset, gfp_t gfp_mask)
+{
+ return __add_to_page_cache(page, mapping, offset, gfp_mask, true);
}
EXPORT_SYMBOL_GPL(add_to_page_cache_lru);
@@ -2032,6 +2040,7 @@ static ssize_t generic_file_buffered_read(struct kiocb *iocb,
offset = *ppos & ~PAGE_MASK;
for (;;) {
+ bool drop_page = false;
struct page *page;
pgoff_t end_index;
loff_t isize;
@@ -2048,6 +2057,9 @@ static ssize_t generic_file_buffered_read(struct kiocb *iocb,
if (!page) {
if (iocb->ki_flags & IOCB_NOWAIT)
goto would_block;
+ /* UNCACHED implies no read-ahead */
+ if (iocb->ki_flags & IOCB_UNCACHED)
+ goto no_cached_page;
page_cache_sync_readahead(mapping,
ra, filp,
index, last_index - index);
@@ -2147,6 +2159,26 @@ static ssize_t generic_file_buffered_read(struct kiocb *iocb,
offset &= ~PAGE_MASK;
prev_offset = offset;
+ /*
+ * If we're dropping this page due to drop-behind, then
+ * lock it first. Ignore errors here, we can just leave it
+ * in the page cache. Note that we didn't add this page to
+ * the LRU when we added it to the page cache. So if we
+ * fail removing it, or lock it, add to the LRU.
+ */
+ if (drop_page) {
+ bool addlru = true;
+
+ if (!lock_page_killable(page)) {
+ if (page->mapping == mapping)
+ addlru = !remove_mapping(mapping, page);
+ else
+ addlru = false;
+ unlock_page(page);
+ }
+ if (addlru)
+ lru_cache_add(page);
+ }
put_page(page);
written += ret;
if (!iov_iter_count(iter))
@@ -2234,8 +2266,12 @@ static ssize_t generic_file_buffered_read(struct kiocb *iocb,
error = -ENOMEM;
goto out;
}
- error = add_to_page_cache_lru(page, mapping, index,
- mapping_gfp_constraint(mapping, GFP_KERNEL));
+ if (iocb->ki_flags & IOCB_UNCACHED)
+ drop_page = true;
+
+ error = __add_to_page_cache(page, mapping, index,
+ mapping_gfp_constraint(mapping, GFP_KERNEL),
+ !drop_page);
if (error) {
put_page(page);
if (error == -EEXIST) {
--
2.24.0
next prev parent reply other threads:[~2019-12-11 15:30 UTC|newest]
Thread overview: 60+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-12-11 15:29 [PATCHSET v3 0/5] Support for RWF_UNCACHED Jens Axboe
2019-12-11 15:29 ` Jens Axboe [this message]
2019-12-11 15:29 ` [PATCH 2/5] mm: make generic_perform_write() take a struct kiocb Jens Axboe
2019-12-11 15:29 ` [PATCH 3/5] mm: make buffered writes work with RWF_UNCACHED Jens Axboe
2019-12-11 15:29 ` [PATCH 4/5] iomap: pass in the write_begin/write_end flags to iomap_actor Jens Axboe
2019-12-11 17:19 ` Linus Torvalds
2019-12-11 15:29 ` [PATCH 5/5] iomap: support RWF_UNCACHED for buffered writes Jens Axboe
2019-12-11 17:19 ` Matthew Wilcox
2019-12-11 18:05 ` Jens Axboe
2019-12-12 22:34 ` Dave Chinner
2019-12-13 0:54 ` Jens Axboe
2019-12-13 0:57 ` Jens Axboe
2019-12-16 4:17 ` Dave Chinner
2019-12-17 14:31 ` Jens Axboe
2019-12-18 0:49 ` Dave Chinner
2019-12-18 1:01 ` Jens Axboe
2019-12-11 17:37 ` [PATCHSET v3 0/5] Support for RWF_UNCACHED Linus Torvalds
2019-12-11 17:56 ` Jens Axboe
2019-12-11 19:14 ` Linus Torvalds
2019-12-11 19:34 ` Jens Axboe
2019-12-11 20:03 ` Linus Torvalds
2019-12-11 20:08 ` Jens Axboe
2019-12-11 20:18 ` Linus Torvalds
2019-12-11 21:04 ` Johannes Weiner
2019-12-12 1:30 ` Jens Axboe
2019-12-11 23:41 ` Jens Axboe
2019-12-12 1:08 ` Linus Torvalds
2019-12-12 1:11 ` Jens Axboe
2019-12-12 1:22 ` Linus Torvalds
2019-12-12 1:29 ` Jens Axboe
2019-12-12 1:41 ` Linus Torvalds
2019-12-12 1:56 ` Matthew Wilcox
2019-12-12 2:47 ` Linus Torvalds
2019-12-12 17:52 ` Matthew Wilcox
2019-12-12 18:29 ` Linus Torvalds
2019-12-12 20:05 ` Matthew Wilcox
2019-12-12 1:41 ` Jens Axboe
2019-12-12 1:49 ` Linus Torvalds
2019-12-12 1:09 ` Jens Axboe
2019-12-12 2:03 ` Jens Axboe
2019-12-12 2:10 ` Jens Axboe
2019-12-12 2:21 ` Matthew Wilcox
2019-12-12 2:38 ` Jens Axboe
2019-12-12 22:18 ` Dave Chinner
2019-12-13 1:32 ` Chris Mason
2020-01-07 17:42 ` Christoph Hellwig
2020-01-08 14:09 ` Chris Mason
2020-02-01 10:33 ` Andres Freund
2019-12-11 20:43 ` Matthew Wilcox
2019-12-11 20:04 ` Jens Axboe
2019-12-12 10:44 ` Martin Steigerwald
2019-12-12 15:16 ` Jens Axboe
2019-12-12 21:45 ` Martin Steigerwald
2019-12-12 22:15 ` Jens Axboe
2019-12-12 22:18 ` Linus Torvalds
-- strict thread matches above, loose matches on Subject: below --
2019-12-12 19:01 [PATCHSET v4 " Jens Axboe
2019-12-12 19:01 ` [PATCH 1/5] fs: add read support " Jens Axboe
2019-12-12 21:21 ` Matthew Wilcox
2019-12-12 21:27 ` Jens Axboe
2019-12-10 20:42 [PATCHSET v2 0/5] Support " Jens Axboe
2019-12-10 20:43 ` [PATCH 1/5] fs: add read support " Jens Axboe
2019-12-10 16:24 [PATCHSET 0/5] Support " Jens Axboe
2019-12-10 16:24 ` [PATCH 1/5] fs: add read support " Jens Axboe
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=20191211152943.2933-2-axboe@kernel.dk \
--to=axboe@kernel.dk \
--cc=clm@fb.com \
--cc=david@fromorbit.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=torvalds@linux-foundation.org \
--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).