Skip to contentSkip to conversation

cachestat: a new syscall for page cache state of files

PATCH Superseded Nhat Pham 4 participants 12 messages Jan 4, 2023 – Jan 13, 2023

Subsystems (22)

v5 of 13 Superseded Latest is v13 →

lore
Share & tools
lore

Nhat Pham

author maintainer
#0 lore raw

v5 cover cachestat: a new syscall for page cache state of files

Changelog:
v5:
* Separate first patch into its own series. (suggested by Andrew Morton)
* Expose filemap_cachestat() to non-syscall usage (patch 2) (suggested by Brian Foster).
* Fix some build errors from last version.

    (patch 2)

* Explain eviction and recent eviction in the draft man page and documentation (suggested by Andrew Morton).
(patch 2)
v4:
* Refactor cachestat and move it to mm/filemap.c (patch 3) (suggested by Brian Foster)
* Remove redundant checks (!folio, access_ok)
(patch 3) (suggested by Matthew Wilcox and Al Viro)
* Fix a bug in handling multipages folio.
(patch 3) (suggested by Matthew Wilcox)
* Add a selftest for shmem files, which can be used to test huge pages (patch 4) (suggested by Johannes Weiner)
v3:
* Fix some minor formatting issues and build errors.
* Add the new syscall entry to missing architecture syscall tables.

    (patch 3).

* Add flags argument for the syscall. (patch 3).
* Clean up the recency refactoring (patch 2) (suggested by Yu Zhao)
* Add the new Kconfig (CONFIG_CACHESTAT) to disable the syscall. (patch 3) (suggested by Josh Triplett)
v2:
* len == 0 means query to EOF. len < 0 is invalid.
(patch 3) (suggested by Brian Foster)
* Make cachestat extensible by adding the cstat_size argument in the syscall (patch 3)

There is currently no good way to query the page cache state of large file sets and directory trees. There is mincore(), but it scales poorly:
the kernel writes out a lot of bitmap data that userspace has to aggregate, when the user really doesn not care about per-page information in that case. The user also needs to mmap and unmap each file as it goes along, which can be quite slow as well.

This series of patches introduces a new system call, cachestat, that summarizes the page cache statistics (number of cached pages, dirty pages, pages marked for writeback, evicted pages etc.) of a file, in a specified range of bytes. It also include a selftest suite that tests some typical usage

This interface is inspired by past discussion and concerns with fincore, which has a similar design (and as a result, issues) as mincore. Relevant links:

https://lkml.indiana.edu/hypermail/linux/kernel/1302.1/04207.html
https://lkml.indiana.edu/hypermail/linux/kernel/1302.1/04209.html

For comparison with mincore, I ran both syscalls on a 2TB sparse file:

Using mincore:

real    0m37.510s
user    0m2.934s
sys     0m34.558s

Using cachestat:

real    0m0.009s
user    0m0.000s
sys     0m0.009s

This series should be applied on top of:

workingset: fix confusion around eviction vs refault container
https://lkml.org/lkml/2023/1/4/1066

This series consist of 3 patches:

Nhat Pham (3):
workingset: refactor LRU refault to expose refault recency check
cachestat: implement cachestat syscall
selftests: Add selftests for cachestat

 MAINTAINERS                                   |   7 +
 arch/alpha/kernel/syscalls/syscall.tbl        |   1 +
 arch/arm/tools/syscall.tbl                    |   1 +
 arch/ia64/kernel/syscalls/syscall.tbl         |   1 +
 arch/m68k/kernel/syscalls/syscall.tbl         |   1 +
 arch/microblaze/kernel/syscalls/syscall.tbl   |   1 +
 arch/parisc/kernel/syscalls/syscall.tbl       |   1 +
 arch/powerpc/kernel/syscalls/syscall.tbl      |   1 +
 arch/s390/kernel/syscalls/syscall.tbl         |   1 +
 arch/sh/kernel/syscalls/syscall.tbl           |   1 +
 arch/sparc/kernel/syscalls/syscall.tbl        |   1 +
 arch/x86/entry/syscalls/syscall_32.tbl        |   1 +
 arch/x86/entry/syscalls/syscall_64.tbl        |   1 +
 arch/xtensa/kernel/syscalls/syscall.tbl       |   1 +
 include/linux/fs.h                            |   3 +
 include/linux/swap.h                          |   1 +
 include/linux/syscalls.h                      |   3 +
 include/uapi/asm-generic/unistd.h             |   5 +-
 include/uapi/linux/mman.h                     |   9 +
 init/Kconfig                                  |  10 +
 kernel/sys_ni.c                               |   1 +
 mm/filemap.c                                  | 143 ++++++++++
 mm/workingset.c                               | 129 ++++++---
 tools/testing/selftests/Makefile              |   1 +
 tools/testing/selftests/cachestat/.gitignore  |   2 +
 tools/testing/selftests/cachestat/Makefile    |   8 +
 .../selftests/cachestat/test_cachestat.c      | 259 ++++++++++++++++++
 27 files changed, 555 insertions(+), 39 deletions(-)
 create mode 100644 tools/testing/selftests/cachestat/.gitignore
 create mode 100644 tools/testing/selftests/cachestat/Makefile
 create mode 100644 tools/testing/selftests/cachestat/test_cachestat.c

base-commit: 1440f576022887004f719883acb094e7e0dd4944
prerequisite-patch-id: 171a43d333e1b267ce14188a5beaea2f313787fb

Signature · 1 line
2.30.2
author maintainer
#1 lore raw

PATCH v5 1/3 workingset: refactor LRU refault to expose refault recency check

In preparation for computing recently evicted pages in cachestat, refactor workingset_refault and lru_gen_refault to expose a helper function that would test if an evicted page is recently evicted.

---
 include/linux/swap.h |   1 +
 mm/workingset.c      | 129 ++++++++++++++++++++++++++++++-------------
 2 files changed, 92 insertions(+), 38 deletions(-)
include/linux/swap.h +1 -0
index a18cf4b7c724..dae6f6f955eb 100644
@@ -361,6 +361,7 @@ static inline void folio_set_swap_entry(struct folio *folio, swp_entry_t entry)
 }
 
 /* linux/mm/workingset.c */
+bool workingset_test_recent(void *shadow, bool file, bool *workingset);
 void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages);
 void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg);
 void workingset_refault(struct folio *folio, void *shadow);
mm/workingset.c +91 -38

185 lines not on this page · raw message

Signature · 1 line
2.30.2
author maintainer
#2 lore raw

PATCH v5 2/3 cachestat: implement cachestat syscall

In reply to Nhat Pham

Implement a new syscall that queries cache state of a file and summarizes the number of cached pages, number of dirty pages, number of pages marked for writeback, number of (recently) evicted pages, etc. in a given range.

NAME
cachestat - query the page cache statistics of a file.

SYNOPSIS

    #include <sys/mman.h>

    struct cachestat {
        __u64 nr_cache;
        __u64 nr_dirty;
        __u64 nr_writeback;
        __u64 nr_evicted;
        __u64 nr_recently_evicted;
    };

    int cachestat(unsigned int fd, off_t off, size_t len,
          size_t cstat_size, struct cachestat *cstat,
          unsigned int flags);

DESCRIPTION
cachestat() queries the number of cached pages, number of dirty pages, number of pages marked for writeback, number of evicted pages, number of recently evicted pages, in the bytes range given by off and len.

An evicted page is a page that is previously in the page cache but has been evicted since. A page is recently evicted if its last eviction was recent enough that its reentry to the cache would indicate that it is actively being used by the system, and that there is memory pressure on the system.

These values are returned in a cachestat struct, whose address is given by the cstat argument.

The off and len arguments must be non-negative integers. If len > 0, the queried range is [off, off + len]. If len == 0, we will query in the range from off to the end of the file.

cstat_size allows users to obtain partial results. The syscall will copy the first csstat_size bytes to the specified userspace memory. cstat_size must be a non-negative value that is no larger than the current size of the cachestat struct.

The flags argument is unused for now, but is included for future extensibility. User should pass 0 (i.e no flag specified).

RETURN VALUE
On success, cachestat returns 0. On error, -1 is returned, and errno is set to indicate the error.

ERRORS
EFAULT cstat points to an invalid address.

EINVAL invalid cstat_size or flags

EBADF invalid file descriptor.

---
 arch/alpha/kernel/syscalls/syscall.tbl      |   1 +
 arch/arm/tools/syscall.tbl                  |   1 +
 arch/ia64/kernel/syscalls/syscall.tbl       |   1 +
 arch/m68k/kernel/syscalls/syscall.tbl       |   1 +
 arch/microblaze/kernel/syscalls/syscall.tbl |   1 +
 arch/parisc/kernel/syscalls/syscall.tbl     |   1 +
 arch/powerpc/kernel/syscalls/syscall.tbl    |   1 +
 arch/s390/kernel/syscalls/syscall.tbl       |   1 +
 arch/sh/kernel/syscalls/syscall.tbl         |   1 +
 arch/sparc/kernel/syscalls/syscall.tbl      |   1 +
 arch/x86/entry/syscalls/syscall_32.tbl      |   1 +
 arch/x86/entry/syscalls/syscall_64.tbl      |   1 +
 arch/xtensa/kernel/syscalls/syscall.tbl     |   1 +
 include/linux/fs.h                          |   3 +
 include/linux/syscalls.h                    |   3 +
 include/uapi/asm-generic/unistd.h           |   5 +-
 include/uapi/linux/mman.h                   |   9 ++
 init/Kconfig                                |  10 ++
 kernel/sys_ni.c                             |   1 +
 mm/filemap.c                                | 143 ++++++++++++++++++++
 20 files changed, 186 insertions(+), 1 deletion(-)
arch/alpha/kernel/syscalls/syscall.tbl +1 -0
index 8ebacf37a8cf..1f13995d00d7 100644
@@ -490,3 +490,4 @@
 558	common	process_mrelease		sys_process_mrelease
 559	common  futex_waitv                     sys_futex_waitv
 560	common	set_mempolicy_home_node		sys_ni_syscall
+561	common	cachestat			sys_cachestat
arch/arm/tools/syscall.tbl +1 -0
index ac964612d8b0..8ebed8a13874 100644
@@ -464,3 +464,4 @@
 448	common	process_mrelease		sys_process_mrelease
 449	common	futex_waitv			sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
+451	common	cachestat			sys_cachestat
arch/ia64/kernel/syscalls/syscall.tbl +1 -0
index 72c929d9902b..f8c74ffeeefb 100644
@@ -371,3 +371,4 @@
 448	common	process_mrelease		sys_process_mrelease
 449	common  futex_waitv                     sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
+451	common	cachestat			sys_cachestat
arch/m68k/kernel/syscalls/syscall.tbl +1 -0
index b1f3940bc298..4f504783371f 100644
@@ -450,3 +450,4 @@
 448	common	process_mrelease		sys_process_mrelease
 449	common  futex_waitv                     sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
+451	common	cachestat			sys_cachestat
arch/microblaze/kernel/syscalls/syscall.tbl +1 -0
index 820145e47350..858d22bf275c 100644
@@ -456,3 +456,4 @@
 448	common	process_mrelease		sys_process_mrelease
 449	common  futex_waitv                     sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
+451	common	cachestat			sys_cachestat
arch/parisc/kernel/syscalls/syscall.tbl +1 -0
index 8a99c998da9b..7c84a72306d1 100644
@@ -448,3 +448,4 @@
 448	common	process_mrelease		sys_process_mrelease
 449	common	futex_waitv			sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
+451	common	cachestat			sys_cachestat
arch/powerpc/kernel/syscalls/syscall.tbl +1 -0
index 2bca64f96164..937460f0a8ec 100644
@@ -530,3 +530,4 @@
 448	common	process_mrelease		sys_process_mrelease
 449	common  futex_waitv                     sys_futex_waitv
 450 	nospu	set_mempolicy_home_node		sys_set_mempolicy_home_node
+451	common	cachestat			sys_cachestat
arch/s390/kernel/syscalls/syscall.tbl +1 -0
index 799147658dee..7df0329d46cb 100644
@@ -453,3 +453,4 @@
 448  common	process_mrelease	sys_process_mrelease		sys_process_mrelease
 449  common	futex_waitv		sys_futex_waitv			sys_futex_waitv
 450  common	set_mempolicy_home_node	sys_set_mempolicy_home_node	sys_set_mempolicy_home_node
+451  common	cachestat		sys_cachestat			sys_cachestat
arch/sh/kernel/syscalls/syscall.tbl +1 -0
index 2de85c977f54..97377e8c5025 100644
@@ -453,3 +453,4 @@
 448	common	process_mrelease		sys_process_mrelease
 449	common  futex_waitv                     sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
+451	common	cachestat			sys_cachestat
arch/sparc/kernel/syscalls/syscall.tbl +1 -0
index 4398cc6fb68d..faa835f3c54a 100644
@@ -496,3 +496,4 @@
 448	common	process_mrelease		sys_process_mrelease
 449	common  futex_waitv                     sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
+451	common	cachestat			sys_cachestat
arch/x86/entry/syscalls/syscall_32.tbl +1 -0
index 320480a8db4f..bc0a3c941b35 100644
@@ -455,3 +455,4 @@
 448	i386	process_mrelease	sys_process_mrelease
 449	i386	futex_waitv		sys_futex_waitv
 450	i386	set_mempolicy_home_node		sys_set_mempolicy_home_node
+451	i386	cachestat		sys_cachestat
arch/x86/entry/syscalls/syscall_64.tbl +1 -0
index c84d12608cd2..227538b0ce80 100644
@@ -372,6 +372,7 @@
 448	common	process_mrelease	sys_process_mrelease
 449	common	futex_waitv		sys_futex_waitv
 450	common	set_mempolicy_home_node	sys_set_mempolicy_home_node
+451	common	cachestat		sys_cachestat
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
arch/xtensa/kernel/syscalls/syscall.tbl +1 -0
index 52c94ab5c205..2b69c3c035b6 100644
@@ -421,3 +421,4 @@
 448	common	process_mrelease		sys_process_mrelease
 449	common  futex_waitv                     sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
+451	common	cachestat			sys_cachestat
include/linux/fs.h +3 -0
index e654435f1651..83300f1491e7 100644
@@ -75,6 +75,7 @@ struct fs_context;
 struct fs_parameter_spec;
 struct fileattr;
 struct iomap_ops;
+struct cachestat;
 
 extern void __init inode_init(void);
 extern void __init inode_init_early(void);
@@ -830,6 +831,8 @@ void filemap_invalidate_lock_two(struct address_space *mapping1,
 				 struct address_space *mapping2);
 void filemap_invalidate_unlock_two(struct address_space *mapping1,
 				   struct address_space *mapping2);
+void filemap_cachestat(struct address_space *mapping, pgoff_t first_index,
+		pgoff_t last_index, struct cachestat *cs);
 
 
 /*
include/linux/syscalls.h +3 -0
index a34b0f9a9972..50f8c6999d99 100644
@@ -72,6 +72,7 @@ struct open_how;
 struct mount_attr;
 struct landlock_ruleset_attr;
 enum landlock_rule_type;
+struct cachestat;
 
 #include <linux/types.h>
 #include <linux/aio_abi.h>
@@ -1056,6 +1057,8 @@ asmlinkage long sys_memfd_secret(unsigned int flags);
 asmlinkage long sys_set_mempolicy_home_node(unsigned long start, unsigned long len,
 					    unsigned long home_node,
 					    unsigned long flags);
+asmlinkage long sys_cachestat(unsigned int fd, off_t off, size_t len,
+		size_t cstat_size, struct cachestat __user *cstat, unsigned int flags);
 
 /*
  * Architecture-specific system calls
include/uapi/asm-generic/unistd.h +4 -1
index 45fa180cc56a..cd639fae9086 100644
@@ -886,8 +886,11 @@ __SYSCALL(__NR_futex_waitv, sys_futex_waitv)
 #define __NR_set_mempolicy_home_node 450
 __SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node)
 
+#define __NR_cachestat 451
+__SYSCALL(__NR_cachestat, sys_cachestat)
+
 #undef __NR_syscalls
-#define __NR_syscalls 451
+#define __NR_syscalls 452
 
 /*
  * 32 bit systems traditionally used different
include/uapi/linux/mman.h +9 -0
index f55bc680b5b0..fe03ed0b7587 100644
@@ -4,6 +4,7 @@
 
 #include <asm/mman.h>
 #include <asm-generic/hugetlb_encode.h>
+#include <linux/types.h>
 
 #define MREMAP_MAYMOVE		1
 #define MREMAP_FIXED		2
@@ -41,4 +42,12 @@
 #define MAP_HUGE_2GB	HUGETLB_FLAG_ENCODE_2GB
 #define MAP_HUGE_16GB	HUGETLB_FLAG_ENCODE_16GB
 
+struct cachestat {
+	__u64 nr_cache;
+	__u64 nr_dirty;
+	__u64 nr_writeback;
+	__u64 nr_evicted;
+	__u64 nr_recently_evicted;
+};
+
 #endif /* _UAPI_LINUX_MMAN_H */
init/Kconfig +10 -0
index 694f7c160c9c..da96ac29af1d 100644
@@ -1798,6 +1798,16 @@ config RSEQ
 
 	  If unsure, say Y.
 
+config CACHESTAT_SYSCALL
+	bool "Enable cachestat() system call" if EXPERT
+	default y
+	help
+	  Enable the cachestat system call, which queries the page cache
+	  statistics of a file (number of cached pages, dirty pages,
+	  pages marked for writeback, (recently) evicted pages).
+
+	  If unsure say Y here.
+
 config DEBUG_RSEQ
 	default n
 	bool "Enabled debugging of rseq() system call" if EXPERT
kernel/sys_ni.c +1 -0
index 860b2dcf3ac4..04bfb1e4d377 100644
@@ -299,6 +299,7 @@ COND_SYSCALL(set_mempolicy);
 COND_SYSCALL(migrate_pages);
 COND_SYSCALL(move_pages);
 COND_SYSCALL(set_mempolicy_home_node);
+COND_SYSCALL(cachestat);
 
 COND_SYSCALL(perf_event_open);
 COND_SYSCALL(accept4);
mm/filemap.c +143 -0

158 lines not on this page · raw message

Signature · 1 line
2.30.2
#3 lore raw

Re: [PATCH v5 2/3] cachestat: implement cachestat syscall

Quoted 85 lines · Nhat Pham

Implement a new syscall that queries cache state of a file and summarizes the number of cached pages, number of dirty pages, number of pages marked for writeback, number of (recently) evicted pages, etc. in a given range.

NAME
cachestat - query the page cache statistics of a file.

SYNOPSIS

    #include <sys/mman.h>

    struct cachestat {
        __u64 nr_cache;
        __u64 nr_dirty;
        __u64 nr_writeback;
        __u64 nr_evicted;
        __u64 nr_recently_evicted;
    };

    int cachestat(unsigned int fd, off_t off, size_t len,
          size_t cstat_size, struct cachestat *cstat,
          unsigned int flags);

DESCRIPTION
cachestat() queries the number of cached pages, number of dirty pages, number of pages marked for writeback, number of evicted pages, number of recently evicted pages, in the bytes range given by off and len.

An evicted page is a page that is previously in the page cache but has been evicted since. A page is recently evicted if its last eviction was recent enough that its reentry to the cache would indicate that it is actively being used by the system, and that there is memory pressure on the system.

These values are returned in a cachestat struct, whose address is given by the cstat argument.

The off and len arguments must be non-negative integers. If len > 0, the queried range is [off, off + len]. If len == 0, we will query in the range from off to the end of the file.

cstat_size allows users to obtain partial results. The syscall will copy the first csstat_size bytes to the specified userspace memory. cstat_size must be a non-negative value that is no larger than the current size of the cachestat struct.

The flags argument is unused for now, but is included for future extensibility. User should pass 0 (i.e no flag specified).

RETURN VALUE
On success, cachestat returns 0. On error, -1 is returned, and errno is set to indicate the error.

ERRORS
EFAULT cstat points to an invalid address.

EINVAL invalid cstat_size or flags

EBADF invalid file descriptor.

---
 arch/alpha/kernel/syscalls/syscall.tbl      |   1 +
 arch/arm/tools/syscall.tbl                  |   1 +
 arch/ia64/kernel/syscalls/syscall.tbl       |   1 +
 arch/m68k/kernel/syscalls/syscall.tbl       |   1 +
 arch/microblaze/kernel/syscalls/syscall.tbl |   1 +
 arch/parisc/kernel/syscalls/syscall.tbl     |   1 +
 arch/powerpc/kernel/syscalls/syscall.tbl    |   1 +
 arch/s390/kernel/syscalls/syscall.tbl       |   1 +
 arch/sh/kernel/syscalls/syscall.tbl         |   1 +
 arch/sparc/kernel/syscalls/syscall.tbl      |   1 +
 arch/x86/entry/syscalls/syscall_32.tbl      |   1 +
 arch/x86/entry/syscalls/syscall_64.tbl      |   1 +
 arch/xtensa/kernel/syscalls/syscall.tbl     |   1 +
 include/linux/fs.h                          |   3 +
 include/linux/syscalls.h                    |   3 +
 include/uapi/asm-generic/unistd.h           |   5 +-
 include/uapi/linux/mman.h                   |   9 ++
 init/Kconfig                                |  10 ++
 kernel/sys_ni.c                             |   1 +
 mm/filemap.c                                | 143 ++++++++++++++++++++
 20 files changed, 186 insertions(+), 1 deletion(-)

...

Quoted 4 lines
mm/filemap.c +0 -0
index 08341616ae7a..d70d47b20700 100644

...

Quoted 4 lines
mm/filemap.c +0 -0
@@ -3949,3 +3953,142 @@ bool filemap_release_folio(struct folio *folio, gfp_t gfp)
 	return try_to_free_buffers(folio);
 }
 EXPORT_SYMBOL(filemap_release_folio);

...

Quoted 46 lines
mm/filemap.c +46 -0
+#ifdef CONFIG_CACHESTAT_SYSCALL
+/*
+ * The cachestat(5) system call.
+ *
+ * cachestat() returns the page cache statistics of a file in the
+ * bytes range specified by `off` and `len`: number of cached pages,
+ * number of dirty pages, number of pages marked for writeback,
+ * number of evicted pages, and number of recently evicted pages.
+ *
+ * An evicted page is a page that is previously in the page cache
+ * but has been evicted since. A page is recently evicted if its last
+ * eviction was recent enough that its reentry to the cache would
+ * indicate that it is actively being used by the system, and that
+ * there is memory pressure on the system.
+ *
+ * `off` and `len` must be non-negative integers. If `len` > 0,
+ * the queried range is [`off`, `off` + `len`]. If `len` == 0,
+ * we will query in the range from `off` to the end of the file.
+ *
+ * `cstat_size` allows users to obtain partial results. The syscall
+ * will copy the first `csstat_size` bytes to the specified userspace
+ * memory. It also makes the cachestat struct extensible - new fields
+ * can be added in the future without breaking existing usage.
+ * `cstat_size` must be a non-negative value that is no larger than
+ * the current size of the cachestat struct.
+ *
+ * The `flags` argument is unused for now, but is included for future
+ * extensibility. User should pass 0 (i.e no flag specified).
+ *
+ * Because the status of a page can change after cachestat() checks it
+ * but before it returns to the application, the returned values may
+ * contain stale information.
+ *
+ * return values:
+ *  zero    - success
+ *  -EFAULT - cstat points to an illegal address
+ *  -EINVAL - invalid arguments
+ *  -EBADF	- invalid file descriptor
+ */
+SYSCALL_DEFINE6(cachestat, unsigned int, fd, off_t, off, size_t, len,
+		size_t, cstat_size, struct cachestat __user *, cstat,
+		unsigned int, flags)
+{
+	struct fd f = fdget(fd);
+	struct address_space *mapping;
+	struct cachestat cs;

mm/filemap.c bool filemap_release_folio(struct folio *folio, gfp_t gfp) · line 4083

Quoted 10 lines
mm/filemap.c +10 -0
+	pgoff_t first_index = off >> PAGE_SHIFT;
+	pgoff_t last_index =
+		len == 0 ? ULONG_MAX : (off + len - 1) >> PAGE_SHIFT;
+
+	if (off < 0 || cstat_size > sizeof(struct cachestat) || flags != 0)
+		return -EINVAL;
+
+	if (!f.file)
+		return -EBADF;
+

It looks like we miss an fdput() before returning via the above error checks.

The only other thing that stands out as a bit odd to me is the cstat_size check and associated ability to return a partial cachestat struct. Do other syscalls do anything like that? I'd think we'd want to ensure we always at least return a fully populated cachestat struct, even if it happened to be an old/compat version if the size does ever increase. Hm?

Brian

Quoted 14 lines
mm/filemap.c +11 -0
+	memset(&cs, 0, sizeof(struct cachestat));
+	mapping = f.file->f_mapping;
+	filemap_cachestat(mapping, first_index, last_index, &cs);
+	fdput(f);
+
+	if (copy_to_user(cstat, &cs, cstat_size))
+		return -EFAULT;
+
+	return 0;
+}
+#endif /* CONFIG_CACHESTAT_SYSCALL */
Signature · 1 line
2.30.2
author maintainer
#4 lore raw

Re: [PATCH v5 2/3] cachestat: implement cachestat syscall

Quoted 149 lines · Brian Foster
Quoted 85 lines · Nhat Pham

Implement a new syscall that queries cache state of a file and summarizes the number of cached pages, number of dirty pages, number of pages marked for writeback, number of (recently) evicted pages, etc. in a given range.

NAME
cachestat - query the page cache statistics of a file.

SYNOPSIS

    #include <sys/mman.h>

    struct cachestat {
        __u64 nr_cache;
        __u64 nr_dirty;
        __u64 nr_writeback;
        __u64 nr_evicted;
        __u64 nr_recently_evicted;
    };

    int cachestat(unsigned int fd, off_t off, size_t len,
          size_t cstat_size, struct cachestat *cstat,
          unsigned int flags);

DESCRIPTION
cachestat() queries the number of cached pages, number of dirty pages, number of pages marked for writeback, number of evicted pages, number of recently evicted pages, in the bytes range given by off and len.

An evicted page is a page that is previously in the page cache but has been evicted since. A page is recently evicted if its last eviction was recent enough that its reentry to the cache would indicate that it is actively being used by the system, and that there is memory pressure on the system.

These values are returned in a cachestat struct, whose address is given by the cstat argument.

The off and len arguments must be non-negative integers. If len > 0, the queried range is [off, off + len]. If len == 0, we will query in the range from off to the end of the file.

cstat_size allows users to obtain partial results. The syscall will copy the first csstat_size bytes to the specified userspace memory. cstat_size must be a non-negative value that is no larger than the current size of the cachestat struct.

The flags argument is unused for now, but is included for future extensibility. User should pass 0 (i.e no flag specified).

RETURN VALUE
On success, cachestat returns 0. On error, -1 is returned, and errno is set to indicate the error.

ERRORS
EFAULT cstat points to an invalid address.

EINVAL invalid cstat_size or flags

EBADF invalid file descriptor.

---
 arch/alpha/kernel/syscalls/syscall.tbl      |   1 +
 arch/arm/tools/syscall.tbl                  |   1 +
 arch/ia64/kernel/syscalls/syscall.tbl       |   1 +
 arch/m68k/kernel/syscalls/syscall.tbl       |   1 +
 arch/microblaze/kernel/syscalls/syscall.tbl |   1 +
 arch/parisc/kernel/syscalls/syscall.tbl     |   1 +
 arch/powerpc/kernel/syscalls/syscall.tbl    |   1 +
 arch/s390/kernel/syscalls/syscall.tbl       |   1 +
 arch/sh/kernel/syscalls/syscall.tbl         |   1 +
 arch/sparc/kernel/syscalls/syscall.tbl      |   1 +
 arch/x86/entry/syscalls/syscall_32.tbl      |   1 +
 arch/x86/entry/syscalls/syscall_64.tbl      |   1 +
 arch/xtensa/kernel/syscalls/syscall.tbl     |   1 +
 include/linux/fs.h                          |   3 +
 include/linux/syscalls.h                    |   3 +
 include/uapi/asm-generic/unistd.h           |   5 +-
 include/uapi/linux/mman.h                   |   9 ++
 init/Kconfig                                |  10 ++
 kernel/sys_ni.c                             |   1 +
 mm/filemap.c                                | 143 ++++++++++++++++++++
 20 files changed, 186 insertions(+), 1 deletion(-)

...

Quoted 4 lines
mm/filemap.c +0 -0
index 08341616ae7a..d70d47b20700 100644

...

Quoted 4 lines
mm/filemap.c +0 -0
@@ -3949,3 +3953,142 @@ bool filemap_release_folio(struct folio *folio, gfp_t gfp)
      return try_to_free_buffers(folio);
 }
 EXPORT_SYMBOL(filemap_release_folio);

...

Quoted 51 lines
mm/filemap.c +51 -0
+#ifdef CONFIG_CACHESTAT_SYSCALL
+/*
+ * The cachestat(5) system call.
+ *
+ * cachestat() returns the page cache statistics of a file in the
+ * bytes range specified by `off` and `len`: number of cached pages,
+ * number of dirty pages, number of pages marked for writeback,
+ * number of evicted pages, and number of recently evicted pages.
+ *
+ * An evicted page is a page that is previously in the page cache
+ * but has been evicted since. A page is recently evicted if its last
+ * eviction was recent enough that its reentry to the cache would
+ * indicate that it is actively being used by the system, and that
+ * there is memory pressure on the system.
+ *
+ * `off` and `len` must be non-negative integers. If `len` > 0,
+ * the queried range is [`off`, `off` + `len`]. If `len` == 0,
+ * we will query in the range from `off` to the end of the file.
+ *
+ * `cstat_size` allows users to obtain partial results. The syscall
+ * will copy the first `csstat_size` bytes to the specified userspace
+ * memory. It also makes the cachestat struct extensible - new fields
+ * can be added in the future without breaking existing usage.
+ * `cstat_size` must be a non-negative value that is no larger than
+ * the current size of the cachestat struct.
+ *
+ * The `flags` argument is unused for now, but is included for future
+ * extensibility. User should pass 0 (i.e no flag specified).
+ *
+ * Because the status of a page can change after cachestat() checks it
+ * but before it returns to the application, the returned values may
+ * contain stale information.
+ *
+ * return values:
+ *  zero    - success
+ *  -EFAULT - cstat points to an illegal address
+ *  -EINVAL - invalid arguments
+ *  -EBADF   - invalid file descriptor
+ */
+SYSCALL_DEFINE6(cachestat, unsigned int, fd, off_t, off, size_t, len,
+             size_t, cstat_size, struct cachestat __user *, cstat,
+             unsigned int, flags)
+{
+     struct fd f = fdget(fd);
+     struct address_space *mapping;
+     struct cachestat cs;
+     pgoff_t first_index = off >> PAGE_SHIFT;
+     pgoff_t last_index =
+             len == 0 ? ULONG_MAX : (off + len - 1) >> PAGE_SHIFT;
+
+     if (off < 0 || cstat_size > sizeof(struct cachestat) || flags != 0)
Quoted 8 lines

mm/filemap.c bool filemap_release_folio(struct folio *folio, gfp_t gfp) · line 4083

Quoted 5 lines
mm/filemap.c +5 -0
+             return -EINVAL;
+
+     if (!f.file)
+             return -EBADF;
+

It looks like we miss an fdput() before returning via the above error checks.

Ooops yeah I missed that. I'll fix it.

Quoted 7 lines

The only other thing that stands out as a bit odd to me is the cstat_size check and associated ability to return a partial cachestat struct. Do other syscalls do anything like that? I'd think we'd want to ensure we always at least return a fully populated cachestat struct, even if it happened to be an old/compat version if the size does ever increase. Hm?

Not that I know of, but the idea is that the user might expect a smaller struct cachestat in their code (and allocate memory accordingly). With this cstat_size, we can make sure that the expansion of cachestat struct (with new fields) does not break existing user's code - we only copy part of the struct.

Quoted 18 lines

Brian

Quoted 14 lines
mm/filemap.c +11 -1
+     memset(&cs, 0, sizeof(struct cachestat));
+     mapping = f.file->f_mapping;
+     filemap_cachestat(mapping, first_index, last_index, &cs);
+     fdput(f);
+
+     if (copy_to_user(cstat, &cs, cstat_size))
+             return -EFAULT;
+
+     return 0;
+}
+#endif /* CONFIG_CACHESTAT_SYSCALL */
--

2.30.2

#5 lore raw

Re: [PATCH v5 2/3] cachestat: implement cachestat syscall

Quoted 169 lines · Nhat Pham
Quoted 149 lines · Brian Foster
Quoted 85 lines · Nhat Pham

Implement a new syscall that queries cache state of a file and summarizes the number of cached pages, number of dirty pages, number of pages marked for writeback, number of (recently) evicted pages, etc. in a given range.

NAME
cachestat - query the page cache statistics of a file.

SYNOPSIS

    #include <sys/mman.h>

    struct cachestat {
        __u64 nr_cache;
        __u64 nr_dirty;
        __u64 nr_writeback;
        __u64 nr_evicted;
        __u64 nr_recently_evicted;
    };

    int cachestat(unsigned int fd, off_t off, size_t len,
          size_t cstat_size, struct cachestat *cstat,
          unsigned int flags);

DESCRIPTION
cachestat() queries the number of cached pages, number of dirty pages, number of pages marked for writeback, number of evicted pages, number of recently evicted pages, in the bytes range given by off and len.

An evicted page is a page that is previously in the page cache but has been evicted since. A page is recently evicted if its last eviction was recent enough that its reentry to the cache would indicate that it is actively being used by the system, and that there is memory pressure on the system.

These values are returned in a cachestat struct, whose address is given by the cstat argument.

The off and len arguments must be non-negative integers. If len > 0, the queried range is [off, off + len]. If len == 0, we will query in the range from off to the end of the file.

cstat_size allows users to obtain partial results. The syscall will copy the first csstat_size bytes to the specified userspace memory. cstat_size must be a non-negative value that is no larger than the current size of the cachestat struct.

The flags argument is unused for now, but is included for future extensibility. User should pass 0 (i.e no flag specified).

RETURN VALUE
On success, cachestat returns 0. On error, -1 is returned, and errno is set to indicate the error.

ERRORS
EFAULT cstat points to an invalid address.

EINVAL invalid cstat_size or flags

EBADF invalid file descriptor.

---
 arch/alpha/kernel/syscalls/syscall.tbl      |   1 +
 arch/arm/tools/syscall.tbl                  |   1 +
 arch/ia64/kernel/syscalls/syscall.tbl       |   1 +
 arch/m68k/kernel/syscalls/syscall.tbl       |   1 +
 arch/microblaze/kernel/syscalls/syscall.tbl |   1 +
 arch/parisc/kernel/syscalls/syscall.tbl     |   1 +
 arch/powerpc/kernel/syscalls/syscall.tbl    |   1 +
 arch/s390/kernel/syscalls/syscall.tbl       |   1 +
 arch/sh/kernel/syscalls/syscall.tbl         |   1 +
 arch/sparc/kernel/syscalls/syscall.tbl      |   1 +
 arch/x86/entry/syscalls/syscall_32.tbl      |   1 +
 arch/x86/entry/syscalls/syscall_64.tbl      |   1 +
 arch/xtensa/kernel/syscalls/syscall.tbl     |   1 +
 include/linux/fs.h                          |   3 +
 include/linux/syscalls.h                    |   3 +
 include/uapi/asm-generic/unistd.h           |   5 +-
 include/uapi/linux/mman.h                   |   9 ++
 init/Kconfig                                |  10 ++
 kernel/sys_ni.c                             |   1 +
 mm/filemap.c                                | 143 ++++++++++++++++++++
 20 files changed, 186 insertions(+), 1 deletion(-)

...

Quoted 4 lines
mm/filemap.c +0 -0
index 08341616ae7a..d70d47b20700 100644

...

Quoted 4 lines
mm/filemap.c +0 -0
@@ -3949,3 +3953,142 @@ bool filemap_release_folio(struct folio *folio, gfp_t gfp)
      return try_to_free_buffers(folio);
 }
 EXPORT_SYMBOL(filemap_release_folio);

...

Quoted 51 lines
mm/filemap.c +51 -0
+#ifdef CONFIG_CACHESTAT_SYSCALL
+/*
+ * The cachestat(5) system call.
+ *
+ * cachestat() returns the page cache statistics of a file in the
+ * bytes range specified by `off` and `len`: number of cached pages,
+ * number of dirty pages, number of pages marked for writeback,
+ * number of evicted pages, and number of recently evicted pages.
+ *
+ * An evicted page is a page that is previously in the page cache
+ * but has been evicted since. A page is recently evicted if its last
+ * eviction was recent enough that its reentry to the cache would
+ * indicate that it is actively being used by the system, and that
+ * there is memory pressure on the system.
+ *
+ * `off` and `len` must be non-negative integers. If `len` > 0,
+ * the queried range is [`off`, `off` + `len`]. If `len` == 0,
+ * we will query in the range from `off` to the end of the file.
+ *
+ * `cstat_size` allows users to obtain partial results. The syscall
+ * will copy the first `csstat_size` bytes to the specified userspace
+ * memory. It also makes the cachestat struct extensible - new fields
+ * can be added in the future without breaking existing usage.
+ * `cstat_size` must be a non-negative value that is no larger than
+ * the current size of the cachestat struct.
+ *
+ * The `flags` argument is unused for now, but is included for future
+ * extensibility. User should pass 0 (i.e no flag specified).
+ *
+ * Because the status of a page can change after cachestat() checks it
+ * but before it returns to the application, the returned values may
+ * contain stale information.
+ *
+ * return values:
+ *  zero    - success
+ *  -EFAULT - cstat points to an illegal address
+ *  -EINVAL - invalid arguments
+ *  -EBADF   - invalid file descriptor
+ */
+SYSCALL_DEFINE6(cachestat, unsigned int, fd, off_t, off, size_t, len,
+             size_t, cstat_size, struct cachestat __user *, cstat,
+             unsigned int, flags)
+{
+     struct fd f = fdget(fd);
+     struct address_space *mapping;
+     struct cachestat cs;
+     pgoff_t first_index = off >> PAGE_SHIFT;
+     pgoff_t last_index =
+             len == 0 ? ULONG_MAX : (off + len - 1) >> PAGE_SHIFT;
+
+     if (off < 0 || cstat_size > sizeof(struct cachestat) || flags != 0)
Quoted 8 lines

mm/filemap.c bool filemap_release_folio(struct folio *folio, gfp_t gfp) · line 4083

Quoted 5 lines
mm/filemap.c +5 -0
+             return -EINVAL;
+
+     if (!f.file)
+             return -EBADF;
+

It looks like we miss an fdput() before returning via the above error checks.

Ooops yeah I missed that. I'll fix it.

Quoted 7 lines

The only other thing that stands out as a bit odd to me is the cstat_size check and associated ability to return a partial cachestat struct. Do other syscalls do anything like that? I'd think we'd want to ensure we always at least return a fully populated cachestat struct, even if it happened to be an old/compat version if the size does ever increase. Hm?

Quoted 6 lines

Not that I know of, but the idea is that the user might expect a smaller struct cachestat in their code (and allocate memory accordingly). With this cstat_size, we can make sure that the expansion of cachestat struct (with new fields) does not break existing user's code - we only copy part of the struct.

Yup, I get the idea of supporting future expansion. The part that doesn't make sense to me is allowing a partial copy of struct cachestat. For example, what happens if the user passes a cstat_size of 2? We copy out two bytes of the first field of the struct and return 0 for "success?"

The way I've commonly seen this sort of support for future expansion is by versioning the structure and providing backwards compatibility for old versions of the structure. I'd guess there are various ways to implement that, but a simple example that comes to mind for me is xfs_ioc_fsgeometry(). The caveat there is that it's an ioctl where IIRC the command essentially changes when the structure size does, which allows the kernel to determine what version is being used.

I'm not quite sure what the ideal way to do that for a syscall is. I suppose the kernel could just check that the size param matches some version of the structure it knows about and assume that. Or since you have the flags field, you could require a flag to be passed in to return values for any new fields. Or yet another option could be to pad out the size of the userspace structure to support future expansion for the foreseeable future without the need for such a flag.

Perhaps this is something linux-api can help with?

Brian

Quoted 19 lines
Quoted 18 lines

Brian

Quoted 14 lines
mm/filemap.c +11 -1
+     memset(&cs, 0, sizeof(struct cachestat));
+     mapping = f.file->f_mapping;
+     filemap_cachestat(mapping, first_index, last_index, &cs);
+     fdput(f);
+
+     if (copy_to_user(cstat, &cs, cstat_size))
+             return -EFAULT;
+
+     return 0;
+}
+#endif /* CONFIG_CACHESTAT_SYSCALL */
--

2.30.2

author maintainer
#6 lore raw

Re: [PATCH v5 2/3] cachestat: implement cachestat syscall

Quoted 171 lines · Brian Foster
Quoted 169 lines · Nhat Pham
Quoted 149 lines · Brian Foster
Quoted 85 lines · Nhat Pham

Implement a new syscall that queries cache state of a file and summarizes the number of cached pages, number of dirty pages, number of pages marked for writeback, number of (recently) evicted pages, etc. in a given range.

NAME
cachestat - query the page cache statistics of a file.

SYNOPSIS

    #include <sys/mman.h>

    struct cachestat {
        __u64 nr_cache;
        __u64 nr_dirty;
        __u64 nr_writeback;
        __u64 nr_evicted;
        __u64 nr_recently_evicted;
    };

    int cachestat(unsigned int fd, off_t off, size_t len,
          size_t cstat_size, struct cachestat *cstat,
          unsigned int flags);

DESCRIPTION
cachestat() queries the number of cached pages, number of dirty pages, number of pages marked for writeback, number of evicted pages, number of recently evicted pages, in the bytes range given by off and len.

An evicted page is a page that is previously in the page cache but has been evicted since. A page is recently evicted if its last eviction was recent enough that its reentry to the cache would indicate that it is actively being used by the system, and that there is memory pressure on the system.

These values are returned in a cachestat struct, whose address is given by the cstat argument.

The off and len arguments must be non-negative integers. If len > 0, the queried range is [off, off + len]. If len == 0, we will query in the range from off to the end of the file.

cstat_size allows users to obtain partial results. The syscall will copy the first csstat_size bytes to the specified userspace memory. cstat_size must be a non-negative value that is no larger than the current size of the cachestat struct.

The flags argument is unused for now, but is included for future extensibility. User should pass 0 (i.e no flag specified).

RETURN VALUE
On success, cachestat returns 0. On error, -1 is returned, and errno is set to indicate the error.

ERRORS
EFAULT cstat points to an invalid address.

EINVAL invalid cstat_size or flags

EBADF invalid file descriptor.

---
 arch/alpha/kernel/syscalls/syscall.tbl      |   1 +
 arch/arm/tools/syscall.tbl                  |   1 +
 arch/ia64/kernel/syscalls/syscall.tbl       |   1 +
 arch/m68k/kernel/syscalls/syscall.tbl       |   1 +
 arch/microblaze/kernel/syscalls/syscall.tbl |   1 +
 arch/parisc/kernel/syscalls/syscall.tbl     |   1 +
 arch/powerpc/kernel/syscalls/syscall.tbl    |   1 +
 arch/s390/kernel/syscalls/syscall.tbl       |   1 +
 arch/sh/kernel/syscalls/syscall.tbl         |   1 +
 arch/sparc/kernel/syscalls/syscall.tbl      |   1 +
 arch/x86/entry/syscalls/syscall_32.tbl      |   1 +
 arch/x86/entry/syscalls/syscall_64.tbl      |   1 +
 arch/xtensa/kernel/syscalls/syscall.tbl     |   1 +
 include/linux/fs.h                          |   3 +
 include/linux/syscalls.h                    |   3 +
 include/uapi/asm-generic/unistd.h           |   5 +-
 include/uapi/linux/mman.h                   |   9 ++
 init/Kconfig                                |  10 ++
 kernel/sys_ni.c                             |   1 +
 mm/filemap.c                                | 143 ++++++++++++++++++++
 20 files changed, 186 insertions(+), 1 deletion(-)

...

Quoted 4 lines
mm/filemap.c +0 -0
index 08341616ae7a..d70d47b20700 100644

...

Quoted 4 lines
mm/filemap.c +0 -0
@@ -3949,3 +3953,142 @@ bool filemap_release_folio(struct folio *folio, gfp_t gfp)
      return try_to_free_buffers(folio);
 }
 EXPORT_SYMBOL(filemap_release_folio);

...

Quoted 51 lines
mm/filemap.c +51 -0
+#ifdef CONFIG_CACHESTAT_SYSCALL
+/*
+ * The cachestat(5) system call.
+ *
+ * cachestat() returns the page cache statistics of a file in the
+ * bytes range specified by `off` and `len`: number of cached pages,
+ * number of dirty pages, number of pages marked for writeback,
+ * number of evicted pages, and number of recently evicted pages.
+ *
+ * An evicted page is a page that is previously in the page cache
+ * but has been evicted since. A page is recently evicted if its last
+ * eviction was recent enough that its reentry to the cache would
+ * indicate that it is actively being used by the system, and that
+ * there is memory pressure on the system.
+ *
+ * `off` and `len` must be non-negative integers. If `len` > 0,
+ * the queried range is [`off`, `off` + `len`]. If `len` == 0,
+ * we will query in the range from `off` to the end of the file.
+ *
+ * `cstat_size` allows users to obtain partial results. The syscall
+ * will copy the first `csstat_size` bytes to the specified userspace
+ * memory. It also makes the cachestat struct extensible - new fields
+ * can be added in the future without breaking existing usage.
+ * `cstat_size` must be a non-negative value that is no larger than
+ * the current size of the cachestat struct.
+ *
+ * The `flags` argument is unused for now, but is included for future
+ * extensibility. User should pass 0 (i.e no flag specified).
+ *
+ * Because the status of a page can change after cachestat() checks it
+ * but before it returns to the application, the returned values may
+ * contain stale information.
+ *
+ * return values:
+ *  zero    - success
+ *  -EFAULT - cstat points to an illegal address
+ *  -EINVAL - invalid arguments
+ *  -EBADF   - invalid file descriptor
+ */
+SYSCALL_DEFINE6(cachestat, unsigned int, fd, off_t, off, size_t, len,
+             size_t, cstat_size, struct cachestat __user *, cstat,
+             unsigned int, flags)
+{
+     struct fd f = fdget(fd);
+     struct address_space *mapping;
+     struct cachestat cs;
+     pgoff_t first_index = off >> PAGE_SHIFT;
+     pgoff_t last_index =
+             len == 0 ? ULONG_MAX : (off + len - 1) >> PAGE_SHIFT;
+
+     if (off < 0 || cstat_size > sizeof(struct cachestat) || flags != 0)
Quoted 8 lines

mm/filemap.c bool filemap_release_folio(struct folio *folio, gfp_t gfp) · line 4083

Quoted 5 lines
mm/filemap.c +5 -0
+             return -EINVAL;
+
+     if (!f.file)
+             return -EBADF;
+

It looks like we miss an fdput() before returning via the above error checks.

Ooops yeah I missed that. I'll fix it.

Quoted 7 lines

The only other thing that stands out as a bit odd to me is the cstat_size check and associated ability to return a partial cachestat struct. Do other syscalls do anything like that? I'd think we'd want to ensure we always at least return a fully populated cachestat struct, even if it happened to be an old/compat version if the size does ever increase. Hm?

Quoted 7 lines
Quoted 6 lines

Not that I know of, but the idea is that the user might expect a smaller struct cachestat in their code (and allocate memory accordingly). With this cstat_size, we can make sure that the expansion of cachestat struct (with new fields) does not break existing user's code - we only copy part of the struct.

I found a couple of syscalls doing something similar:

statfs64
https://github.com/torvalds/linux/blob/master/fs/statfs.c#L168-L190

io_uring_enter:
https://github.com/torvalds/linux/blob/master/io_uring/io_uring.c#L3232-L3243

It looks like these syscalls just error-out if the size argument does not match with the size of the kernel struct.

Quoted 6 lines

Yup, I get the idea of supporting future expansion. The part that doesn't make sense to me is allowing a partial copy of struct cachestat. For example, what happens if the user passes a cstat_size of 2? We copy out two bytes of the first field of the struct and return 0 for "success?"

Quoted 7 lines

The way I've commonly seen this sort of support for future expansion is by versioning the structure and providing backwards compatibility for old versions of the structure. I'd guess there are various ways to implement that, but a simple example that comes to mind for me is xfs_ioc_fsgeometry(). The caveat there is that it's an ioctl where IIRC the command essentially changes when the structure size does, which allows the kernel to determine what version is being used.

Hmm xfs_ioc_fsgeometry looks interesting. From my understanding, it basically has an argument that can take on a couple of values, each of which delineates a version, right? I can give that a try and see if it looks better (and maybe send a new version with this updated API).

Quoted 10 lines

I'm not quite sure what the ideal way to do that for a syscall is. I suppose the kernel could just check that the size param matches some version of the structure it knows about and assume that. Or since you have the flags field, you could require a flag to be passed in to return values for any new fields. Or yet another option could be to pad out the size of the userspace structure to support future expansion for the foreseeable future without the need for such a flag.

Perhaps this is something linux-api can help with?

I think I should definitely forward my patch series to linux-api. Thanks for the suggestion, Brian!

Quoted 23 lines

Brian

Quoted 19 lines
Quoted 18 lines

Brian

Quoted 14 lines
mm/filemap.c +11 -1
+     memset(&cs, 0, sizeof(struct cachestat));
+     mapping = f.file->f_mapping;
+     filemap_cachestat(mapping, first_index, last_index, &cs);
+     fdput(f);
+
+     if (copy_to_user(cstat, &cs, cstat_size))
+             return -EFAULT;
+
+     return 0;
+}
+#endif /* CONFIG_CACHESTAT_SYSCALL */
--

2.30.2

#7 lore raw

Re: [PATCH v5 2/3] cachestat: implement cachestat syscall

Quoted 205 lines · Nhat Pham
Quoted 171 lines · Brian Foster
Quoted 169 lines · Nhat Pham
Quoted 149 lines · Brian Foster
Quoted 85 lines · Nhat Pham

Implement a new syscall that queries cache state of a file and summarizes the number of cached pages, number of dirty pages, number of pages marked for writeback, number of (recently) evicted pages, etc. in a given range.

NAME
cachestat - query the page cache statistics of a file.

SYNOPSIS

    #include <sys/mman.h>

    struct cachestat {
        __u64 nr_cache;
        __u64 nr_dirty;
        __u64 nr_writeback;
        __u64 nr_evicted;
        __u64 nr_recently_evicted;
    };

    int cachestat(unsigned int fd, off_t off, size_t len,
          size_t cstat_size, struct cachestat *cstat,
          unsigned int flags);

DESCRIPTION
cachestat() queries the number of cached pages, number of dirty pages, number of pages marked for writeback, number of evicted pages, number of recently evicted pages, in the bytes range given by off and len.

An evicted page is a page that is previously in the page cache but has been evicted since. A page is recently evicted if its last eviction was recent enough that its reentry to the cache would indicate that it is actively being used by the system, and that there is memory pressure on the system.

These values are returned in a cachestat struct, whose address is given by the cstat argument.

The off and len arguments must be non-negative integers. If len > 0, the queried range is [off, off + len]. If len == 0, we will query in the range from off to the end of the file.

cstat_size allows users to obtain partial results. The syscall will copy the first csstat_size bytes to the specified userspace memory. cstat_size must be a non-negative value that is no larger than the current size of the cachestat struct.

The flags argument is unused for now, but is included for future extensibility. User should pass 0 (i.e no flag specified).

RETURN VALUE
On success, cachestat returns 0. On error, -1 is returned, and errno is set to indicate the error.

ERRORS
EFAULT cstat points to an invalid address.

EINVAL invalid cstat_size or flags

EBADF invalid file descriptor.

---
 arch/alpha/kernel/syscalls/syscall.tbl      |   1 +
 arch/arm/tools/syscall.tbl                  |   1 +
 arch/ia64/kernel/syscalls/syscall.tbl       |   1 +
 arch/m68k/kernel/syscalls/syscall.tbl       |   1 +
 arch/microblaze/kernel/syscalls/syscall.tbl |   1 +
 arch/parisc/kernel/syscalls/syscall.tbl     |   1 +
 arch/powerpc/kernel/syscalls/syscall.tbl    |   1 +
 arch/s390/kernel/syscalls/syscall.tbl       |   1 +
 arch/sh/kernel/syscalls/syscall.tbl         |   1 +
 arch/sparc/kernel/syscalls/syscall.tbl      |   1 +
 arch/x86/entry/syscalls/syscall_32.tbl      |   1 +
 arch/x86/entry/syscalls/syscall_64.tbl      |   1 +
 arch/xtensa/kernel/syscalls/syscall.tbl     |   1 +
 include/linux/fs.h                          |   3 +
 include/linux/syscalls.h                    |   3 +
 include/uapi/asm-generic/unistd.h           |   5 +-
 include/uapi/linux/mman.h                   |   9 ++
 init/Kconfig                                |  10 ++
 kernel/sys_ni.c                             |   1 +
 mm/filemap.c                                | 143 ++++++++++++++++++++
 20 files changed, 186 insertions(+), 1 deletion(-)

...

Quoted 4 lines
mm/filemap.c +0 -0
index 08341616ae7a..d70d47b20700 100644

...

Quoted 4 lines
mm/filemap.c +0 -0
@@ -3949,3 +3953,142 @@ bool filemap_release_folio(struct folio *folio, gfp_t gfp)
      return try_to_free_buffers(folio);
 }
 EXPORT_SYMBOL(filemap_release_folio);

...

Quoted 51 lines
mm/filemap.c +51 -0
+#ifdef CONFIG_CACHESTAT_SYSCALL
+/*
+ * The cachestat(5) system call.
+ *
+ * cachestat() returns the page cache statistics of a file in the
+ * bytes range specified by `off` and `len`: number of cached pages,
+ * number of dirty pages, number of pages marked for writeback,
+ * number of evicted pages, and number of recently evicted pages.
+ *
+ * An evicted page is a page that is previously in the page cache
+ * but has been evicted since. A page is recently evicted if its last
+ * eviction was recent enough that its reentry to the cache would
+ * indicate that it is actively being used by the system, and that
+ * there is memory pressure on the system.
+ *
+ * `off` and `len` must be non-negative integers. If `len` > 0,
+ * the queried range is [`off`, `off` + `len`]. If `len` == 0,
+ * we will query in the range from `off` to the end of the file.
+ *
+ * `cstat_size` allows users to obtain partial results. The syscall
+ * will copy the first `csstat_size` bytes to the specified userspace
+ * memory. It also makes the cachestat struct extensible - new fields
+ * can be added in the future without breaking existing usage.
+ * `cstat_size` must be a non-negative value that is no larger than
+ * the current size of the cachestat struct.
+ *
+ * The `flags` argument is unused for now, but is included for future
+ * extensibility. User should pass 0 (i.e no flag specified).
+ *
+ * Because the status of a page can change after cachestat() checks it
+ * but before it returns to the application, the returned values may
+ * contain stale information.
+ *
+ * return values:
+ *  zero    - success
+ *  -EFAULT - cstat points to an illegal address
+ *  -EINVAL - invalid arguments
+ *  -EBADF   - invalid file descriptor
+ */
+SYSCALL_DEFINE6(cachestat, unsigned int, fd, off_t, off, size_t, len,
+             size_t, cstat_size, struct cachestat __user *, cstat,
+             unsigned int, flags)
+{
+     struct fd f = fdget(fd);
+     struct address_space *mapping;
+     struct cachestat cs;
+     pgoff_t first_index = off >> PAGE_SHIFT;
+     pgoff_t last_index =
+             len == 0 ? ULONG_MAX : (off + len - 1) >> PAGE_SHIFT;
+
+     if (off < 0 || cstat_size > sizeof(struct cachestat) || flags != 0)
Quoted 8 lines

mm/filemap.c bool filemap_release_folio(struct folio *folio, gfp_t gfp) · line 4083

Quoted 5 lines
mm/filemap.c +5 -0
+             return -EINVAL;
+
+     if (!f.file)
+             return -EBADF;
+

It looks like we miss an fdput() before returning via the above error checks.

Ooops yeah I missed that. I'll fix it.

Quoted 7 lines

The only other thing that stands out as a bit odd to me is the cstat_size check and associated ability to return a partial cachestat struct. Do other syscalls do anything like that? I'd think we'd want to ensure we always at least return a fully populated cachestat struct, even if it happened to be an old/compat version if the size does ever increase. Hm?

Quoted 7 lines
Quoted 6 lines

Not that I know of, but the idea is that the user might expect a smaller struct cachestat in their code (and allocate memory accordingly). With this cstat_size, we can make sure that the expansion of cachestat struct (with new fields) does not break existing user's code - we only copy part of the struct.

I found a couple of syscalls doing something similar:

statfs64
https://github.com/torvalds/linux/blob/master/fs/statfs.c#L168-L190

io_uring_enter:
https://github.com/torvalds/linux/blob/master/io_uring/io_uring.c#L3232-L3243

It looks like these syscalls just error-out if the size argument does not match with the size of the kernel struct.

Quoted 6 lines

Yup, I get the idea of supporting future expansion. The part that doesn't make sense to me is allowing a partial copy of struct cachestat. For example, what happens if the user passes a cstat_size of 2? We copy out two bytes of the first field of the struct and return 0 for "success?"

Quoted 7 lines

The way I've commonly seen this sort of support for future expansion is by versioning the structure and providing backwards compatibility for old versions of the structure. I'd guess there are various ways to implement that, but a simple example that comes to mind for me is xfs_ioc_fsgeometry(). The caveat there is that it's an ioctl where IIRC the command essentially changes when the structure size does, which allows the kernel to determine what version is being used.

Quoted 5 lines

Hmm xfs_ioc_fsgeometry looks interesting. From my understanding, it basically has an argument that can take on a couple of values, each of which delineates a version, right? I can give that a try and see if it looks better (and maybe send a new version with this updated API).

Yeah, though the difference is that the caller can determine the version of struct to use based on the different ioctl command. We don't have that luxury with the syscall, so I'm not sure the same kind of factoring would make sense here.

From your examples above, I think it probably makes sense to enforce that the size matches the actual structure. The question is if you want to plan for future expansion and adding fields to the struct, what's the accepted way to prepare for that now and design it into the api? If nobody else can chime in with suggestions in the meantime, hopefully linux-api can help. :)

Brian

Quoted 38 lines
Quoted 10 lines

I'm not quite sure what the ideal way to do that for a syscall is. I suppose the kernel could just check that the size param matches some version of the structure it knows about and assume that. Or since you have the flags field, you could require a flag to be passed in to return values for any new fields. Or yet another option could be to pad out the size of the userspace structure to support future expansion for the foreseeable future without the need for such a flag.

Perhaps this is something linux-api can help with?

I think I should definitely forward my patch series to linux-api. Thanks for the suggestion, Brian!

Quoted 23 lines

Brian

Quoted 19 lines
Quoted 18 lines

Brian

Quoted 14 lines
mm/filemap.c +11 -1
+     memset(&cs, 0, sizeof(struct cachestat));
+     mapping = f.file->f_mapping;
+     filemap_cachestat(mapping, first_index, last_index, &cs);
+     fdput(f);
+
+     if (copy_to_user(cstat, &cs, cstat_size))
+             return -EFAULT;
+
+     return 0;
+}
+#endif /* CONFIG_CACHESTAT_SYSCALL */
--

2.30.2

#8 lore raw

Re: [PATCH v5 2/3] cachestat: implement cachestat syscall

In reply to Nhat Pham

On 4 Jan 2023 15:11:26 -0800 Nhat Pham <[email protected]>

Quoted 4 lines

Implement a new syscall that queries cache state of a file and summarizes the number of cached pages, number of dirty pages, number of pages marked for writeback, number of (recently) evicted pages, etc. in a given range.

Feel free to add why. Do copy-and-paste if it is in the cover letter.

Quoted 11 lines
mm/filemap.c +10 -0
+/**
+ * filemap_cachestat() - compute the page cache statistics of a mapping
+ * @mapping:	The mapping to compute the statistics for.
+ * @first_index:	The starting page cache index.
+ * @last_index:	The final page index (inclusive).
+ * @cs:	the cachestat struct to write the result to.
+ *
+ * This will query the page cache statistics of a mapping in the
+ * page range of [first_index, last_index] (inclusive). The statistics
+ * queried include: number of dirty pages, number of pages marked for

mm/filemap.c bool filemap_release_folio(struct folio *folio, gfp_t gfp) · line 3976

Quoted 10 lines
mm/filemap.c +10 -0
+ * writeback, and the number of (recently) evicted pages.
+ */
+void filemap_cachestat(struct address_space *mapping, pgoff_t first_index,
+		pgoff_t last_index, struct cachestat *cs)
+{
+	XA_STATE(xas, &mapping->i_pages, first_index);
+	struct folio *folio;
+
+	rcu_read_lock();
+	xas_for_each(&xas, folio, last_index) {

It does not make sense to take more than two ticks to walk the xarray with rcu read lock held.

Add stats to mapping instead if CONFIG_CACHESTAT_SYSCALL is enabled, in case of difficulty handling rcu read lock.

maintainer Acked-by on v5 2/3
#9 lore raw

Re: [PATCH v5 2/3] cachestat: implement cachestat syscall

In reply to Nhat Pham
Quoted 57 lines · Nhat Pham

Implement a new syscall that queries cache state of a file and summarizes the number of cached pages, number of dirty pages, number of pages marked for writeback, number of (recently) evicted pages, etc. in a given range.

NAME
cachestat - query the page cache statistics of a file.

SYNOPSIS

    #include <sys/mman.h>

    struct cachestat {
        __u64 nr_cache;
        __u64 nr_dirty;
        __u64 nr_writeback;
        __u64 nr_evicted;
        __u64 nr_recently_evicted;
    };

    int cachestat(unsigned int fd, off_t off, size_t len,
          size_t cstat_size, struct cachestat *cstat,
          unsigned int flags);

DESCRIPTION
cachestat() queries the number of cached pages, number of dirty pages, number of pages marked for writeback, number of evicted pages, number of recently evicted pages, in the bytes range given by off and len.

An evicted page is a page that is previously in the page cache but has been evicted since. A page is recently evicted if its last eviction was recent enough that its reentry to the cache would indicate that it is actively being used by the system, and that there is memory pressure on the system.

These values are returned in a cachestat struct, whose address is given by the cstat argument.

The off and len arguments must be non-negative integers. If len > 0, the queried range is [off, off + len]. If len == 0, we will query in the range from off to the end of the file.

cstat_size allows users to obtain partial results. The syscall will copy the first csstat_size bytes to the specified userspace memory. cstat_size must be a non-negative value that is no larger than the current size of the cachestat struct.

The flags argument is unused for now, but is included for future extensibility. User should pass 0 (i.e no flag specified).

RETURN VALUE
On success, cachestat returns 0. On error, -1 is returned, and errno is set to indicate the error.

ERRORS
EFAULT cstat points to an invalid address.

Quoted 7 lines

EINVAL invalid cstat_size or flags

EBADF invalid file descriptor.

 arch/m68k/kernel/syscalls/syscall.tbl       |   1 +

Gr{oetje,eeting}s,

Geert

--
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- [email protected]

In personal conversations with technical people, I call myself a hacker. But when I'm talking to journalists I just say "programmer" or something like that.
-- Linus Torvalds

author maintainer
#10 lore raw

PATCH v5 3/3 selftests: Add selftests for cachestat

In reply to Nhat Pham

Test cachestat on a newly created file, /dev/ files, and /proc/ files. Also test on a shmem file (which can also be tested with huge pages since tmpfs supports huge pages).

---
 MAINTAINERS                                   |   7 +
 tools/testing/selftests/Makefile              |   1 +
 tools/testing/selftests/cachestat/.gitignore  |   2 +
 tools/testing/selftests/cachestat/Makefile    |   8 +
 .../selftests/cachestat/test_cachestat.c      | 259 ++++++++++++++++++
 5 files changed, 277 insertions(+)
 create mode 100644 tools/testing/selftests/cachestat/.gitignore
 create mode 100644 tools/testing/selftests/cachestat/Makefile
 create mode 100644 tools/testing/selftests/cachestat/test_cachestat.c
MAINTAINERS +7 -0
index a198da986146..792a866353ec 100644
@@ -4552,6 +4552,13 @@ S:	Supported
 F:	Documentation/filesystems/caching/cachefiles.rst
 F:	fs/cachefiles/
 
+CACHESTAT: PAGE CACHE STATS FOR A FILE
+M:	Nhat Pham <[email protected]>
+M:	Johannes Weiner <[email protected]>
+L:	[email protected]
+S:	Maintained
+F:	tools/testing/selftests/cachestat/test_cachestat.c
+
 CADENCE MIPI-CSI2 BRIDGES
 M:	Maxime Ripard <[email protected]>
 L:	[email protected]
tools/testing/selftests/Makefile +1 -0
index 0464b2c6c1e4..3cad0b38c5c2 100644
@@ -4,6 +4,7 @@ TARGETS += amd-pstate
 TARGETS += arm64
 TARGETS += bpf
 TARGETS += breakpoints
+TARGETS += cachestat
 TARGETS += capabilities
 TARGETS += cgroup
 TARGETS += clone3
tools/testing/selftests/cachestat/.gitignore new file +2 -0
new file mode 100644
index 000000000000..d6c30b43a4bb
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+test_cachestat
tools/testing/selftests/cachestat/Makefile new file +8 -0
new file mode 100644
index 000000000000..fca73aaa7d14
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+TEST_GEN_PROGS := test_cachestat
+
+CFLAGS += $(KHDR_INCLUDES)
+CFLAGS += -Wall
+CFLAGS += -lrt
+
+include ../lib.mk
tools/testing/selftests/cachestat/test_cachestat.c new file +259 -0

259 lines not on this page · raw message

Signature · 1 line
2.30.2
author maintainer
#11 lore raw
In reply to Nhat Pham
Quoted 112 lines · Nhat Pham

Changelog:
v5:
* Separate first patch into its own series. (suggested by Andrew Morton)
* Expose filemap_cachestat() to non-syscall usage (patch 2) (suggested by Brian Foster).
* Fix some build errors from last version.

    (patch 2)

* Explain eviction and recent eviction in the draft man page and documentation (suggested by Andrew Morton).
(patch 2)
v4:
* Refactor cachestat and move it to mm/filemap.c (patch 3) (suggested by Brian Foster)
* Remove redundant checks (!folio, access_ok)
(patch 3) (suggested by Matthew Wilcox and Al Viro)
* Fix a bug in handling multipages folio.
(patch 3) (suggested by Matthew Wilcox)
* Add a selftest for shmem files, which can be used to test huge pages (patch 4) (suggested by Johannes Weiner)
v3:
* Fix some minor formatting issues and build errors.
* Add the new syscall entry to missing architecture syscall tables.

    (patch 3).

* Add flags argument for the syscall. (patch 3).
* Clean up the recency refactoring (patch 2) (suggested by Yu Zhao)
* Add the new Kconfig (CONFIG_CACHESTAT) to disable the syscall. (patch 3) (suggested by Josh Triplett)
v2:
* len == 0 means query to EOF. len < 0 is invalid.
(patch 3) (suggested by Brian Foster)
* Make cachestat extensible by adding the cstat_size argument in the syscall (patch 3)

There is currently no good way to query the page cache state of large file sets and directory trees. There is mincore(), but it scales poorly:
the kernel writes out a lot of bitmap data that userspace has to aggregate, when the user really doesn not care about per-page information in that case. The user also needs to mmap and unmap each file as it goes along, which can be quite slow as well.

This series of patches introduces a new system call, cachestat, that summarizes the page cache statistics (number of cached pages, dirty pages, pages marked for writeback, evicted pages etc.) of a file, in a specified range of bytes. It also include a selftest suite that tests some typical usage

This interface is inspired by past discussion and concerns with fincore, which has a similar design (and as a result, issues) as mincore. Relevant links:

https://lkml.indiana.edu/hypermail/linux/kernel/1302.1/04207.html
https://lkml.indiana.edu/hypermail/linux/kernel/1302.1/04209.html

For comparison with mincore, I ran both syscalls on a 2TB sparse file:

Using mincore:

real    0m37.510s
user    0m2.934s
sys     0m34.558s

Using cachestat:

real    0m0.009s
user    0m0.000s
sys     0m0.009s

This series should be applied on top of:

workingset: fix confusion around eviction vs refault container
https://lkml.org/lkml/2023/1/4/1066

This series consist of 3 patches:

Nhat Pham (3):
workingset: refactor LRU refault to expose refault recency check
cachestat: implement cachestat syscall
selftests: Add selftests for cachestat

 MAINTAINERS                                   |   7 +
 arch/alpha/kernel/syscalls/syscall.tbl        |   1 +
 arch/arm/tools/syscall.tbl                    |   1 +
 arch/ia64/kernel/syscalls/syscall.tbl         |   1 +
 arch/m68k/kernel/syscalls/syscall.tbl         |   1 +
 arch/microblaze/kernel/syscalls/syscall.tbl   |   1 +
 arch/parisc/kernel/syscalls/syscall.tbl       |   1 +
 arch/powerpc/kernel/syscalls/syscall.tbl      |   1 +
 arch/s390/kernel/syscalls/syscall.tbl         |   1 +
 arch/sh/kernel/syscalls/syscall.tbl           |   1 +
 arch/sparc/kernel/syscalls/syscall.tbl        |   1 +
 arch/x86/entry/syscalls/syscall_32.tbl        |   1 +
 arch/x86/entry/syscalls/syscall_64.tbl        |   1 +
 arch/xtensa/kernel/syscalls/syscall.tbl       |   1 +
 include/linux/fs.h                            |   3 +
 include/linux/swap.h                          |   1 +
 include/linux/syscalls.h                      |   3 +
 include/uapi/asm-generic/unistd.h             |   5 +-
 include/uapi/linux/mman.h                     |   9 +
 init/Kconfig                                  |  10 +
 kernel/sys_ni.c                               |   1 +
 mm/filemap.c                                  | 143 ++++++++++
 mm/workingset.c                               | 129 ++++++---
 tools/testing/selftests/Makefile              |   1 +
 tools/testing/selftests/cachestat/.gitignore  |   2 +
 tools/testing/selftests/cachestat/Makefile    |   8 +
 .../selftests/cachestat/test_cachestat.c      | 259 ++++++++++++++++++
 27 files changed, 555 insertions(+), 39 deletions(-)
 create mode 100644 tools/testing/selftests/cachestat/.gitignore
 create mode 100644 tools/testing/selftests/cachestat/Makefile
 create mode 100644 tools/testing/selftests/cachestat/test_cachestat.c
Quoted 4 lines

base-commit: 1440f576022887004f719883acb094e7e0dd4944
prerequisite-patch-id: 171a43d333e1b267ce14188a5beaea2f313787fb --
2.30.2

Oops, I think I accidentally sent out v5 twice :(

Please ignore the first set of emails and review this one only,

LKML link for convenience:
https://lkml.org/lkml/2023/1/4/1095