From: "Darrick J. Wong" <djwong@kernel.org>
To: djwong@kernel.org, cem@kernel.org
Cc: cmaiolino@redhat.com, linux-xfs@vger.kernel.org, hch@infradead.org
Subject: [PATCH 090/111] libxfs: partition memfd files to avoid using too many fds
Date: Mon, 15 Apr 2024 18:00:39 -0700 [thread overview]
Message-ID: <171322883514.211103.15800307559901643828.stgit@frogsfrogsfrogs> (raw)
In-Reply-To: <171322882240.211103.3776766269442402814.stgit@frogsfrogsfrogs>
From: Darrick J. Wong <djwong@kernel.org>
Make it so that we can partition a memfd file to avoid running out of
file descriptors.
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
libxfs/xfile.c | 197 ++++++++++++++++++++++++++++++++++++++++++++++++++++++--
libxfs/xfile.h | 17 ++++-
2 files changed, 205 insertions(+), 9 deletions(-)
diff --git a/libxfs/xfile.c b/libxfs/xfile.c
index cba173cc17f1..fdb76f406647 100644
--- a/libxfs/xfile.c
+++ b/libxfs/xfile.c
@@ -97,6 +97,149 @@ xfile_create_fd(
return fd;
}
+static LIST_HEAD(fcb_list);
+static pthread_mutex_t fcb_mutex = PTHREAD_MUTEX_INITIALIZER;
+
+/* Create a new memfd. */
+static inline int
+xfile_fcb_create(
+ const char *description,
+ struct xfile_fcb **fcbp)
+{
+ struct xfile_fcb *fcb;
+ int fd;
+
+ fd = xfile_create_fd(description);
+ if (fd < 0)
+ return -errno;
+
+ fcb = malloc(sizeof(struct xfile_fcb));
+ if (!fcb) {
+ close(fd);
+ return -ENOMEM;
+ }
+
+ list_head_init(&fcb->fcb_list);
+ fcb->fd = fd;
+ fcb->refcount = 1;
+
+ *fcbp = fcb;
+ return 0;
+}
+
+/* Release an xfile control block */
+static void
+xfile_fcb_irele(
+ struct xfile_fcb *fcb,
+ loff_t pos,
+ uint64_t len)
+{
+ /*
+ * If this memfd is linked only to itself, it's private, so we can
+ * close it without taking any locks.
+ */
+ if (list_empty(&fcb->fcb_list)) {
+ close(fcb->fd);
+ free(fcb);
+ return;
+ }
+
+ pthread_mutex_lock(&fcb_mutex);
+ if (--fcb->refcount == 0) {
+ /* If we're the last user of this memfd file, kill it fast. */
+ list_del(&fcb->fcb_list);
+ close(fcb->fd);
+ free(fcb);
+ } else if (len > 0) {
+ struct stat statbuf;
+ int ret;
+
+ /*
+ * If we were using the end of a partitioned file, free the
+ * address space. IOWs, bonus points if you delete these in
+ * reverse-order of creation.
+ */
+ ret = fstat(fcb->fd, &statbuf);
+ if (!ret && statbuf.st_size == pos + len) {
+ ret = ftruncate(fcb->fd, pos);
+ }
+ }
+ pthread_mutex_unlock(&fcb_mutex);
+}
+
+/*
+ * Find an memfd that can accomodate the given amount of address space.
+ */
+static int
+xfile_fcb_find(
+ const char *description,
+ uint64_t maxbytes,
+ loff_t *posp,
+ struct xfile_fcb **fcbp)
+{
+ struct xfile_fcb *fcb;
+ int ret;
+ int error;
+
+ /* No maximum range means that the caller gets a private memfd. */
+ if (maxbytes == 0) {
+ *posp = 0;
+ return xfile_fcb_create(description, fcbp);
+ }
+
+ /* round up to page granularity so we can do mmap */
+ maxbytes = roundup_64(maxbytes, PAGE_SIZE);
+
+ pthread_mutex_lock(&fcb_mutex);
+
+ /*
+ * If we only need a certain number of byte range, look for one with
+ * available file range.
+ */
+ list_for_each_entry(fcb, &fcb_list, fcb_list) {
+ struct stat statbuf;
+ loff_t pos;
+
+ ret = fstat(fcb->fd, &statbuf);
+ if (ret)
+ continue;
+ pos = roundup_64(statbuf.st_size, PAGE_SIZE);
+
+ /*
+ * Truncate up to ensure that the memfd can actually handle
+ * writes to the end of the range.
+ */
+ ret = ftruncate(fcb->fd, pos + maxbytes);
+ if (ret)
+ continue;
+
+ fcb->refcount++;
+ *posp = pos;
+ *fcbp = fcb;
+ goto out_unlock;
+ }
+
+ /* Otherwise, open a new memfd and add it to our list. */
+ error = xfile_fcb_create(description, &fcb);
+ if (error)
+ return error;
+
+ ret = ftruncate(fcb->fd, maxbytes);
+ if (ret) {
+ error = -errno;
+ xfile_fcb_irele(fcb, 0, maxbytes);
+ return error;
+ }
+
+ list_add_tail(&fcb->fcb_list, &fcb_list);
+ *posp = 0;
+ *fcbp = fcb;
+
+out_unlock:
+ pthread_mutex_unlock(&fcb_mutex);
+ return error;
+}
+
/*
* Create an xfile of the given size. The description will be used in the
* trace output.
@@ -104,6 +247,7 @@ xfile_create_fd(
int
xfile_create(
const char *description,
+ unsigned long long maxbytes,
struct xfile **xfilep)
{
struct xfile *xf;
@@ -113,13 +257,14 @@ xfile_create(
if (!xf)
return -ENOMEM;
- xf->fd = xfile_create_fd(description);
- if (xf->fd < 0) {
- error = -errno;
+ error = xfile_fcb_find(description, maxbytes, &xf->partition_pos,
+ &xf->fcb);
+ if (error) {
kfree(xf);
return error;
}
+ xf->maxbytes = maxbytes;
*xfilep = xf;
return 0;
}
@@ -129,7 +274,7 @@ void
xfile_destroy(
struct xfile *xf)
{
- close(xf->fd);
+ xfile_fcb_irele(xf->fcb, xf->partition_pos, xf->maxbytes);
kfree(xf);
}
@@ -137,6 +282,9 @@ static inline loff_t
xfile_maxbytes(
struct xfile *xf)
{
+ if (xf->maxbytes > 0)
+ return xf->maxbytes;
+
if (sizeof(loff_t) == 8)
return LLONG_MAX;
return LONG_MAX;
@@ -160,7 +308,7 @@ xfile_load(
if (xfile_maxbytes(xf) - pos < count)
return -ENOMEM;
- ret = pread(xf->fd, buf, count, pos);
+ ret = pread(xf->fcb->fd, buf, count, pos + xf->partition_pos);
if (ret < 0)
return -errno;
if (ret != count)
@@ -186,7 +334,7 @@ xfile_store(
if (xfile_maxbytes(xf) - pos < count)
return -EFBIG;
- ret = pwrite(xf->fd, buf, count, pos);
+ ret = pwrite(xf->fcb->fd, buf, count, pos + xf->partition_pos);
if (ret < 0)
return -errno;
if (ret != count)
@@ -194,6 +342,38 @@ xfile_store(
return 0;
}
+/* Compute the number of bytes used by a partitioned xfile. */
+static unsigned long long
+xfile_partition_bytes(
+ struct xfile *xf)
+{
+ loff_t data_pos = xf->partition_pos;
+ loff_t stop_pos = data_pos + xf->maxbytes;
+ loff_t hole_pos;
+ unsigned long long bytes = 0;
+
+ data_pos = lseek(xf->fcb->fd, data_pos, SEEK_DATA);
+ while (data_pos >= 0 && data_pos < stop_pos) {
+ hole_pos = lseek(xf->fcb->fd, data_pos, SEEK_HOLE);
+ if (hole_pos < 0) {
+ /* save error, break */
+ data_pos = hole_pos;
+ break;
+ }
+ if (hole_pos >= stop_pos) {
+ bytes += stop_pos - data_pos;
+ return bytes;
+ }
+ bytes += hole_pos - data_pos;
+
+ data_pos = lseek(xf->fcb->fd, hole_pos, SEEK_DATA);
+ }
+ if (data_pos < 0 && errno != ENXIO)
+ return xf->maxbytes;
+
+ return bytes;
+}
+
/* Compute the number of bytes used by a xfile. */
unsigned long long
xfile_bytes(
@@ -202,7 +382,10 @@ xfile_bytes(
struct stat statbuf;
int error;
- error = fstat(xf->fd, &statbuf);
+ if (xf->maxbytes > 0)
+ return xfile_partition_bytes(xf);
+
+ error = fstat(xf->fcb->fd, &statbuf);
if (error)
return -errno;
diff --git a/libxfs/xfile.h b/libxfs/xfile.h
index d60084011357..180a42bbbaa2 100644
--- a/libxfs/xfile.h
+++ b/libxfs/xfile.h
@@ -6,11 +6,24 @@
#ifndef __LIBXFS_XFILE_H__
#define __LIBXFS_XFILE_H__
-struct xfile {
+struct xfile_fcb {
+ struct list_head fcb_list;
int fd;
+ unsigned int refcount;
};
-int xfile_create(const char *description, struct xfile **xfilep);
+struct xfile {
+ struct xfile_fcb *fcb;
+
+ /* File position within fcb->fd where this partition starts */
+ loff_t partition_pos;
+
+ /* Maximum number of bytes that can be written to the partition. */
+ uint64_t maxbytes;
+};
+
+int xfile_create(const char *description, unsigned long long maxbytes,
+ struct xfile **xfilep);
void xfile_destroy(struct xfile *xf);
ssize_t xfile_load(struct xfile *xf, void *buf, size_t count, loff_t pos);
next prev parent reply other threads:[~2024-04-16 1:00 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-04-16 0:51 [PATCHBOMB v3] xfsprogs: everything headed towards 6.9 Darrick J. Wong
2024-04-16 0:57 ` [PATCHSET 1/4] xfsprogs: bug fixes for 6.8 Darrick J. Wong
2024-04-16 0:58 ` [PATCH 1/5] xfs_repair: double-check with shortform attr verifiers Darrick J. Wong
2024-04-16 0:59 ` [PATCH 2/5] xfs_db: improve number extraction in getbitval Darrick J. Wong
2024-04-16 4:53 ` Christoph Hellwig
2024-04-16 0:59 ` [PATCH 3/5] xfs_scrub: fix threadcount estimates for phase 6 Darrick J. Wong
2024-04-16 4:53 ` Christoph Hellwig
2024-04-16 0:59 ` [PATCH 4/5] xfs_scrub: don't fail while reporting media scan errors Darrick J. Wong
2024-04-16 0:59 ` [PATCH 5/5] xfs_io: add linux madvise advice codes Darrick J. Wong
2024-04-17 7:34 ` [PATCHSET 1/4] xfsprogs: bug fixes for 6.8 Carlos Maiolino
2024-04-17 15:30 ` Darrick J. Wong
2024-04-16 0:58 ` [PATCHSET 2/4] libxfs: sync with 6.9 Darrick J. Wong
2024-04-16 1:00 ` [PATCH 088/111] libxfs: teach buftargs to maintain their own buffer hashtable Darrick J. Wong
2024-04-16 1:00 ` [PATCH 089/111] libxfs: add xfile support Darrick J. Wong
2024-04-16 1:00 ` Darrick J. Wong [this message]
2024-04-16 4:55 ` [PATCH 090/111] libxfs: partition memfd files to avoid using too many fds Christoph Hellwig
2024-04-16 15:49 ` Darrick J. Wong
2024-04-16 16:29 ` Christoph Hellwig
2024-04-16 16:57 ` Darrick J. Wong
2024-04-16 18:47 ` Christoph Hellwig
2024-04-16 18:55 ` Darrick J. Wong
2024-04-24 17:20 ` [PATCH v3.1 " Darrick J. Wong
2024-04-16 1:00 ` [PATCH 091/111] xfs: teach buftargs to maintain their own buffer hashtable Darrick J. Wong
2024-04-16 1:01 ` [PATCH 092/111] libxfs: support in-memory buffer cache targets Darrick J. Wong
2024-04-16 0:58 ` [PATCHSET v30.3 3/4] xfsprogs: bmap log intent cleanups Darrick J. Wong
2024-04-16 1:01 ` [PATCH 1/4] libxfs: remove kmem_alloc, kmem_zalloc, and kmem_free Darrick J. Wong
2024-04-16 4:55 ` Christoph Hellwig
2024-04-16 1:01 ` [PATCH 2/4] libxfs: add a bi_entry helper Darrick J. Wong
2024-04-16 4:55 ` Christoph Hellwig
2024-04-16 1:01 ` [PATCH 3/4] libxfs: reuse xfs_bmap_update_cancel_item Darrick J. Wong
2024-04-16 4:55 ` Christoph Hellwig
2024-04-16 1:02 ` [PATCH 4/4] libxfs: add a xattr_entry helper Darrick J. Wong
2024-04-16 4:56 ` Christoph Hellwig
2024-04-16 0:58 ` [PATCHSET v30.3 4/4] xfs_repair: minor fixes Darrick J. Wong
2024-04-16 1:02 ` [PATCH 1/1] xfs_repair: check num before bplist[num] Darrick J. Wong
2024-04-16 4:56 ` Christoph Hellwig
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=171322883514.211103.15800307559901643828.stgit@frogsfrogsfrogs \
--to=djwong@kernel.org \
--cc=cem@kernel.org \
--cc=cmaiolino@redhat.com \
--cc=hch@infradead.org \
--cc=linux-xfs@vger.kernel.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 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.