* [PATCH v5 1/3] workingset: refactor LRU refault to expose refault recency check
2023-01-04 23:10 [PATCH v5 0/3] cachestat: a new syscall for page cache state of files Nhat Pham
@ 2023-01-04 23:10 ` Nhat Pham
2023-01-04 23:10 ` [PATCH v5 2/3] cachestat: implement cachestat syscall Nhat Pham
2023-01-04 23:10 ` [PATCH v5 3/3] selftests: Add selftests for cachestat Nhat Pham
2 siblings, 0 replies; 6+ messages in thread
From: Nhat Pham @ 2023-01-04 23:10 UTC (permalink / raw)
To: akpm; +Cc: hannes, linux-mm, linux-kernel, bfoster, willy, kernel-team
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.
Signed-off-by: Nhat Pham <nphamcs@gmail.com>
---
include/linux/swap.h | 1 +
mm/workingset.c | 129 ++++++++++++++++++++++++++++++-------------
2 files changed, 92 insertions(+), 38 deletions(-)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index a18cf4b7c724..dae6f6f955eb 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -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);
diff --git a/mm/workingset.c b/mm/workingset.c
index 79585d55c45d..006482c4e0bd 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -244,6 +244,33 @@ static void *lru_gen_eviction(struct folio *folio)
return pack_shadow(mem_cgroup_id(memcg), pgdat, token, refs);
}
+/*
+ * Test if the folio is recently evicted.
+ *
+ * As a side effect, also populates the references with
+ * values unpacked from the shadow of the evicted folio.
+ */
+static bool lru_gen_test_recent(void *shadow, bool file, bool *workingset)
+{
+ struct mem_cgroup *eviction_memcg;
+ struct lruvec *lruvec;
+ struct lru_gen_struct *lrugen;
+ unsigned long min_seq;
+
+ int memcgid;
+ struct pglist_data *pgdat;
+ unsigned long token;
+
+ unpack_shadow(shadow, &memcgid, &pgdat, &token, workingset);
+ eviction_memcg = mem_cgroup_from_id(memcgid);
+
+ lruvec = mem_cgroup_lruvec(eviction_memcg, pgdat);
+ lrugen = &lruvec->lrugen;
+
+ min_seq = READ_ONCE(lrugen->min_seq[file]);
+ return !((token >> LRU_REFS_WIDTH) != (min_seq & (EVICTION_MASK >> LRU_REFS_WIDTH)));
+}
+
static void lru_gen_refault(struct folio *folio, void *shadow)
{
int hist, tier, refs;
@@ -306,6 +333,11 @@ static void *lru_gen_eviction(struct folio *folio)
return NULL;
}
+static bool lru_gen_test_recent(void *shadow, bool file, bool *workingset)
+{
+ return true;
+}
+
static void lru_gen_refault(struct folio *folio, void *shadow)
{
}
@@ -373,40 +405,31 @@ void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg)
folio_test_workingset(folio));
}
-/**
- * workingset_refault - Evaluate the refault of a previously evicted folio.
- * @folio: The freshly allocated replacement folio.
- * @shadow: Shadow entry of the evicted folio.
+/*
+ * Test if the folio is recently evicted by checking if
+ * refault distance of shadow exceeds workingset size.
*
- * Calculates and evaluates the refault distance of the previously
- * evicted folio in the context of the node and the memcg whose memory
- * pressure caused the eviction.
+ * As a side effect, populate workingset with the value
+ * unpacked from shadow.
*/
-void workingset_refault(struct folio *folio, void *shadow)
+bool workingset_test_recent(void *shadow, bool file, bool *workingset)
{
- bool file = folio_is_file_lru(folio);
struct mem_cgroup *eviction_memcg;
struct lruvec *eviction_lruvec;
unsigned long refault_distance;
unsigned long workingset_size;
- struct pglist_data *pgdat;
- struct mem_cgroup *memcg;
- unsigned long eviction;
- struct lruvec *lruvec;
unsigned long refault;
- bool workingset;
+
int memcgid;
- long nr;
+ struct pglist_data *pgdat;
+ unsigned long eviction;
- if (lru_gen_enabled()) {
- lru_gen_refault(folio, shadow);
- return;
- }
+ if (lru_gen_enabled())
+ return lru_gen_test_recent(shadow, file, workingset);
- unpack_shadow(shadow, &memcgid, &pgdat, &eviction, &workingset);
+ unpack_shadow(shadow, &memcgid, &pgdat, &eviction, workingset);
eviction <<= bucket_order;
- rcu_read_lock();
/*
* Look up the memcg associated with the stored ID. It might
* have been deleted since the folio's eviction.
@@ -425,7 +448,8 @@ void workingset_refault(struct folio *folio, void *shadow)
*/
eviction_memcg = mem_cgroup_from_id(memcgid);
if (!mem_cgroup_disabled() && !eviction_memcg)
- goto out;
+ return false;
+
eviction_lruvec = mem_cgroup_lruvec(eviction_memcg, pgdat);
refault = atomic_long_read(&eviction_lruvec->nonresident_age);
@@ -447,21 +471,6 @@ void workingset_refault(struct folio *folio, void *shadow)
*/
refault_distance = (refault - eviction) & EVICTION_MASK;
- /*
- * The activation decision for this folio is made at the level
- * where the eviction occurred, as that is where the LRU order
- * during folio reclaim is being determined.
- *
- * However, the cgroup that will own the folio is the one that
- * is actually experiencing the refault event.
- */
- nr = folio_nr_pages(folio);
- memcg = folio_memcg(folio);
- pgdat = folio_pgdat(folio);
- lruvec = mem_cgroup_lruvec(memcg, pgdat);
-
- mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file, nr);
-
mem_cgroup_flush_stats_delayed();
/*
* Compare the distance to the existing workingset size. We
@@ -483,8 +492,51 @@ void workingset_refault(struct folio *folio, void *shadow)
NR_INACTIVE_ANON);
}
}
- if (refault_distance > workingset_size)
+
+ return refault_distance <= workingset_size;
+}
+
+/**
+ * workingset_refault - Evaluate the refault of a previously evicted folio.
+ * @folio: The freshly allocated replacement folio.
+ * @shadow: Shadow entry of the evicted folio.
+ *
+ * Calculates and evaluates the refault distance of the previously
+ * evicted folio in the context of the node and the memcg whose memory
+ * pressure caused the eviction.
+ */
+void workingset_refault(struct folio *folio, void *shadow)
+{
+ bool file = folio_is_file_lru(folio);
+ struct pglist_data *pgdat;
+ struct mem_cgroup *memcg;
+ struct lruvec *lruvec;
+ bool workingset;
+ long nr;
+
+ if (lru_gen_enabled()) {
+ lru_gen_refault(folio, shadow);
+ return;
+ }
+
+ rcu_read_lock();
+
+ nr = folio_nr_pages(folio);
+ memcg = folio_memcg(folio);
+ pgdat = folio_pgdat(folio);
+ lruvec = mem_cgroup_lruvec(memcg, pgdat);
+
+ if (!workingset_test_recent(shadow, file, &workingset)) {
+ /*
+ * The activation decision for this folio is made at the level
+ * where the eviction occurred, as that is where the LRU order
+ * during folio reclaim is being determined.
+ *
+ * However, the cgroup that will own the folio is the one that
+ * is actually experiencing the refault event.
+ */
goto out;
+ }
folio_set_active(folio);
workingset_age_nonresident(lruvec, nr);
@@ -498,6 +550,7 @@ void workingset_refault(struct folio *folio, void *shadow)
mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + file, nr);
}
out:
+ mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file, nr);
rcu_read_unlock();
}
--
2.30.2
^ permalink raw reply [flat|nested] 6+ messages in thread* [PATCH v5 2/3] cachestat: implement cachestat syscall
2023-01-04 23:10 [PATCH v5 0/3] cachestat: a new syscall for page cache state of files Nhat Pham
2023-01-04 23:10 ` [PATCH v5 1/3] workingset: refactor LRU refault to expose refault recency check Nhat Pham
@ 2023-01-04 23:10 ` Nhat Pham
2023-01-04 23:10 ` [PATCH v5 3/3] selftests: Add selftests for cachestat Nhat Pham
2 siblings, 0 replies; 6+ messages in thread
From: Nhat Pham @ 2023-01-04 23:10 UTC (permalink / raw)
To: akpm; +Cc: hannes, linux-mm, linux-kernel, bfoster, willy, kernel-team
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.
Signed-off-by: Nhat Pham <nphamcs@gmail.com>
---
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(-)
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index 8ebacf37a8cf..1f13995d00d7 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -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
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index ac964612d8b0..8ebed8a13874 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -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
diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl
index 72c929d9902b..f8c74ffeeefb 100644
--- a/arch/ia64/kernel/syscalls/syscall.tbl
+++ b/arch/ia64/kernel/syscalls/syscall.tbl
@@ -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
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index b1f3940bc298..4f504783371f 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -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
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index 820145e47350..858d22bf275c 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -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
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index 8a99c998da9b..7c84a72306d1 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -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
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 2bca64f96164..937460f0a8ec 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -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
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 799147658dee..7df0329d46cb 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -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
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index 2de85c977f54..97377e8c5025 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -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
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 4398cc6fb68d..faa835f3c54a 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -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
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 320480a8db4f..bc0a3c941b35 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -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
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index c84d12608cd2..227538b0ce80 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -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
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index 52c94ab5c205..2b69c3c035b6 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -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
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e654435f1651..83300f1491e7 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -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);
/*
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index a34b0f9a9972..50f8c6999d99 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -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
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 45fa180cc56a..cd639fae9086 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -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
diff --git a/include/uapi/linux/mman.h b/include/uapi/linux/mman.h
index f55bc680b5b0..fe03ed0b7587 100644
--- a/include/uapi/linux/mman.h
+++ b/include/uapi/linux/mman.h
@@ -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 */
diff --git a/init/Kconfig b/init/Kconfig
index 694f7c160c9c..da96ac29af1d 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -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
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 860b2dcf3ac4..04bfb1e4d377 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -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);
diff --git a/mm/filemap.c b/mm/filemap.c
index 08341616ae7a..d70d47b20700 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -22,6 +22,7 @@
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/swapops.h>
+#include <linux/syscalls.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/file.h>
@@ -55,6 +56,9 @@
#include <linux/buffer_head.h> /* for try_to_free_buffers */
#include <asm/mman.h>
+#include <uapi/linux/mman.h>
+
+#include "swap.h"
/*
* Shared mappings implemented 30.11.1994. It's not fully working yet,
@@ -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);
+
+/**
+ * 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
+ * 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) {
+ unsigned long nr_pages;
+ pgoff_t folio_first_index, folio_last_index;
+
+ if (xas_retry(&xas, folio))
+ continue;
+
+ nr_pages = folio_nr_pages(folio);
+ folio_first_index = folio_pgoff(folio);
+ folio_last_index = folio_first_index + nr_pages - 1;
+
+ /* Folios might straddle the range boundaries, only count covered subpages */
+ if (folio_first_index < first_index)
+ nr_pages -= first_index - folio_first_index;
+
+ if (folio_last_index > last_index)
+ nr_pages -= folio_last_index - last_index;
+
+ if (xa_is_value(folio)) {
+ /* page is evicted */
+ void *shadow = (void *)folio;
+ bool workingset; /* not used */
+
+ cs->nr_evicted += nr_pages;
+
+#ifdef CONFIG_SWAP /* implies CONFIG_MMU */
+ if (shmem_mapping(mapping)) {
+ /* shmem file - in swap cache */
+ swp_entry_t swp = radix_to_swp_entry(folio);
+
+ shadow = get_shadow_from_swap_cache(swp);
+ }
+#endif
+ if (workingset_test_recent(shadow, true, &workingset))
+ cs->nr_recently_evicted += nr_pages;
+
+ continue;
+ }
+
+ /* page is in cache */
+ cs->nr_cache += nr_pages;
+
+ if (folio_test_dirty(folio))
+ cs->nr_dirty += nr_pages;
+
+ if (folio_test_writeback(folio))
+ cs->nr_writeback += nr_pages;
+ }
+ rcu_read_unlock();
+}
+EXPORT_SYMBOL(filemap_cachestat);
+
+#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)
+ return -EINVAL;
+
+ if (!f.file)
+ return -EBADF;
+
+ 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
^ permalink raw reply [flat|nested] 6+ messages in thread* [PATCH v5 3/3] selftests: Add selftests for cachestat
2023-01-04 23:10 [PATCH v5 0/3] cachestat: a new syscall for page cache state of files Nhat Pham
2023-01-04 23:10 ` [PATCH v5 1/3] workingset: refactor LRU refault to expose refault recency check Nhat Pham
2023-01-04 23:10 ` [PATCH v5 2/3] cachestat: implement cachestat syscall Nhat Pham
@ 2023-01-04 23:10 ` Nhat Pham
2 siblings, 0 replies; 6+ messages in thread
From: Nhat Pham @ 2023-01-04 23:10 UTC (permalink / raw)
To: akpm; +Cc: hannes, linux-mm, linux-kernel, bfoster, willy, kernel-team
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).
Signed-off-by: Nhat Pham <nphamcs@gmail.com>
---
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
diff --git a/MAINTAINERS b/MAINTAINERS
index a198da986146..792a866353ec 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -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 <nphamcs@gmail.com>
+M: Johannes Weiner <hannes@cmpxchg.org>
+L: linux-mm@kvack.org
+S: Maintained
+F: tools/testing/selftests/cachestat/test_cachestat.c
+
CADENCE MIPI-CSI2 BRIDGES
M: Maxime Ripard <mripard@kernel.org>
L: linux-media@vger.kernel.org
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 0464b2c6c1e4..3cad0b38c5c2 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -4,6 +4,7 @@ TARGETS += amd-pstate
TARGETS += arm64
TARGETS += bpf
TARGETS += breakpoints
+TARGETS += cachestat
TARGETS += capabilities
TARGETS += cgroup
TARGETS += clone3
diff --git a/tools/testing/selftests/cachestat/.gitignore b/tools/testing/selftests/cachestat/.gitignore
new file mode 100644
index 000000000000..d6c30b43a4bb
--- /dev/null
+++ b/tools/testing/selftests/cachestat/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+test_cachestat
diff --git a/tools/testing/selftests/cachestat/Makefile b/tools/testing/selftests/cachestat/Makefile
new file mode 100644
index 000000000000..fca73aaa7d14
--- /dev/null
+++ b/tools/testing/selftests/cachestat/Makefile
@@ -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
diff --git a/tools/testing/selftests/cachestat/test_cachestat.c b/tools/testing/selftests/cachestat/test_cachestat.c
new file mode 100644
index 000000000000..3f5cd5695c51
--- /dev/null
+++ b/tools/testing/selftests/cachestat/test_cachestat.c
@@ -0,0 +1,259 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <stdbool.h>
+#include <linux/kernel.h>
+#include <linux/mman.h>
+#include <sys/mman.h>
+#include <sys/shm.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+#include <string.h>
+#include <fcntl.h>
+#include <errno.h>
+
+#include "../kselftest.h"
+
+static const char * const dev_files[] = {
+ "/dev/zero", "/dev/null", "/dev/urandom",
+ "/proc/version", "/proc"
+};
+static const int cachestat_nr = 451;
+
+void print_cachestat(struct cachestat *cs)
+{
+ ksft_print_msg(
+ "Using cachestat: Cached: %lu, Dirty: %lu, Writeback: %lu, Evicted: %lu, Recently Evicted: %lu\n",
+ cs->nr_cache, cs->nr_dirty, cs->nr_writeback,
+ cs->nr_evicted, cs->nr_recently_evicted);
+}
+
+bool write_exactly(int fd, size_t filesize)
+{
+ char data[filesize];
+ bool ret = true;
+ int random_fd = open("/dev/urandom", O_RDONLY);
+
+ if (random_fd < 0) {
+ ksft_print_msg("Unable to access urandom.\n");
+ ret = false;
+ goto out;
+ } else {
+ int remained = filesize;
+ char *cursor = data;
+
+ while (remained) {
+ ssize_t read_len = read(random_fd, cursor, remained);
+
+ if (read_len <= 0) {
+ ksft_print_msg("Unable to read from urandom.\n");
+ ret = false;
+ goto close_random_fd;
+ }
+
+ remained -= read_len;
+ cursor += read_len;
+ }
+
+ /* write random data to fd */
+ remained = filesize;
+ cursor = data;
+ while (remained) {
+ ssize_t write_len = write(fd, cursor, remained);
+
+ if (write_len <= 0) {
+ ksft_print_msg("Unable write random data to file.\n");
+ ret = false;
+ goto close_random_fd;
+ }
+
+ remained -= write_len;
+ cursor += write_len;
+ }
+ }
+
+close_random_fd:
+ close(random_fd);
+out:
+ return ret;
+}
+
+/*
+ * Open/create the file at filename, (optionally) write random data to it
+ * (exactly num_pages), then test the cachestat syscall on this file.
+ *
+ * If test_fsync == true, fsync the file, then check the number of dirty
+ * pages.
+ */
+bool test_cachestat(const char *filename, bool write_random, bool create,
+ bool test_fsync, unsigned long num_pages, int open_flags,
+ mode_t open_mode)
+{
+ size_t PS = sysconf(_SC_PAGESIZE);
+ int filesize = num_pages * PS;
+ bool ret = true;
+ long syscall_ret;
+ struct cachestat cs;
+
+ int fd = open(filename, open_flags, open_mode);
+
+ if (fd == -1) {
+ ksft_print_msg("Unable to create/open file.\n");
+ goto out;
+ } else {
+ ksft_print_msg("Create/open %s\n", filename);
+ }
+
+ if (write_random) {
+ if (!write_exactly(fd, filesize)) {
+ ksft_print_msg("Unable to access urandom.\n");
+ ret = false;
+ goto out1;
+ }
+ }
+
+ syscall_ret = syscall(cachestat_nr, fd, 0, filesize,
+ sizeof(struct cachestat), &cs, 0);
+
+ ksft_print_msg("Cachestat call returned %ld\n", syscall_ret);
+
+ if (syscall_ret) {
+ ksft_print_msg("Cachestat returned non-zero.\n");
+ ret = false;
+ goto out1;
+
+ } else {
+ print_cachestat(&cs);
+
+ if (write_random) {
+ if (cs.nr_cache + cs.nr_evicted != num_pages) {
+ ksft_print_msg(
+ "Total number of cached and evicted pages is off.\n");
+ ret = false;
+ }
+ }
+ }
+
+ if (test_fsync) {
+ if (fsync(fd)) {
+ ksft_print_msg("fsync fails.\n");
+ ret = false;
+ } else {
+ syscall_ret = syscall(cachestat_nr, fd, 0, filesize,
+ sizeof(struct cachestat), &cs, 0);
+
+ ksft_print_msg("Cachestat call (after fsync) returned %ld\n",
+ syscall_ret);
+
+ if (!syscall_ret) {
+ print_cachestat(&cs);
+
+ if (cs.nr_dirty) {
+ ret = false;
+ ksft_print_msg(
+ "Number of dirty should be zero after fsync.\n");
+ }
+ } else {
+ ksft_print_msg("Cachestat (after fsync) returned non-zero.\n");
+ ret = false;
+ goto out1;
+ }
+ }
+ }
+
+out1:
+ close(fd);
+
+ if (create)
+ remove(filename);
+out:
+ return ret;
+}
+
+bool test_cachestat_shmem(void)
+{
+ size_t PS = sysconf(_SC_PAGESIZE);
+ size_t filesize = PS * 512 * 2; /* 2 2MB huge pages */
+ int syscall_ret;
+ off_t off = PS;
+ size_t compute_len = PS * 512;
+ char *filename = "tmpshmcstat";
+ struct cachestat cs;
+ bool ret = true;
+ unsigned long num_pages = compute_len / PS;
+ int fd = shm_open(filename, O_CREAT | O_RDWR, 0600);
+
+ if (fd < 0) {
+ ksft_print_msg("Unable to create shmem file.\n");
+ ret = false;
+ goto out;
+ }
+
+ if (ftruncate(fd, filesize)) {
+ ksft_print_msg("Unable to trucate shmem file.\n");
+ ret = false;
+ goto close_fd;
+ }
+
+ if (!write_exactly(fd, filesize)) {
+ ksft_print_msg("Unable to write to shmem file.\n");
+ ret = false;
+ goto close_fd;
+ }
+
+ syscall_ret = syscall(cachestat_nr, fd, off, compute_len,
+ sizeof(struct cachestat), &cs, 0);
+
+ if (syscall_ret) {
+ ksft_print_msg("Cachestat returned non-zero.\n");
+ ret = false;
+ goto close_fd;
+ } else {
+ print_cachestat(&cs);
+ if (cs.nr_cache + cs.nr_evicted != num_pages) {
+ ksft_print_msg(
+ "Total number of cached and evicted pages is off.\n");
+ ret = false;
+ }
+ }
+
+close_fd:
+ shm_unlink(filename);
+out:
+ return ret;
+}
+
+int main(void)
+{
+ int ret = 0;
+
+ for (int i = 0; i < 5; i++) {
+ const char *dev_filename = dev_files[i];
+
+ if (test_cachestat(dev_filename, false, false, false,
+ 4, O_RDONLY, 0400))
+ ksft_test_result_pass("cachestat works with %s\n", dev_filename);
+ else {
+ ksft_test_result_fail("cachestat fails with %s\n", dev_filename);
+ ret = 1;
+ }
+ }
+
+ if (test_cachestat("tmpfilecachestat", true, true,
+ true, 4, O_CREAT | O_RDWR, 0400 | 0600))
+ ksft_test_result_pass("cachestat works with a normal file\n");
+ else {
+ ksft_test_result_fail("cachestat fails with normal file\n");
+ ret = 1;
+ }
+
+ if (test_cachestat_shmem())
+ ksft_test_result_pass("cachestat works with a shmem file\n");
+ else {
+ ksft_test_result_fail("cachestat fails with a shmem file\n");
+ ret = 1;
+ }
+
+ return ret;
+}
--
2.30.2
^ permalink raw reply [flat|nested] 6+ messages in thread