cachestat: implement cachestat syscall

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.

Some use cases where this information could come in handy:
* Allowing database to decide whether to perform an index scan or
direct table queries based on the in-memory cache state of the
index.
* Visibility into the writeback algorithm, for performance issues
diagnostic.
* Workload-aware writeback pacing: estimating IO fulfilled by page
cache (and IO to be done) within a range of a file, allowing for
more frequent syncing when and where there is IO capacity, and
batching when there is not.
* Computing memory usage of large files/directory trees, analogous to
the du tool for disk usage.

More information about these use cases could be found in the following
thread:

https://lore.kernel.org/lkml/[e-mail]/

This patch implements 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. Currently, the syscall is only wired in for x86
architecture.

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

SYNOPSIS
#include <sys/mman.h>

struct cachestat_range {
__u64 off;
__u64 len;
};

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

int cachestat(unsigned int fd, struct cachestat_range *cstat_range,
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.

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

Currently, hugetlbfs is not supported.

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

ERRORS
EFAULT cstat or cstat_args points to an invalid address.

EINVAL invalid flags.

EBADF invalid file descriptor.

EOPNOTSUPP file descriptor is of a hugetlbfs file

[[e-mail]: replace rounddown logic with the existing helper]
Link: https://lkml.kernel.org/r/[e-mail]
Link: https://lkml.kernel.org/r/[e-mail]
Signed-off-by: Nhat Pham <[e-mail]>
Acked-by: Johannes Weiner <[e-mail]>
Cc: Brian Foster <[e-mail]>
Cc: Matthew Wilcox (Oracle) <[e-mail]>
Cc: Michael Kerrisk <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>

arch/x86/entry/syscalls/syscall_32.tbl

···
 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

···
 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

include/linux/syscalls.h

···
 struct mount_attr;
 struct landlock_ruleset_attr;
 enum landlock_rule_type;
+struct cachestat_range;
+struct cachestat;
 
 #include <linux/types.h>
 #include <linux/aio_abi.h>
···
 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,
+		struct cachestat_range __user *cstat_range,
+		struct cachestat __user *cstat, unsigned int flags);
 
 /*
  * Architecture-specific system calls

include/uapi/asm-generic/unistd.h

···
 #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

···
 
 #include <asm/mman.h>
 #include <asm-generic/hugetlb_encode.h>
+#include <linux/types.h>
 
 #define MREMAP_MAYMOVE		1
 #define MREMAP_FIXED		2
···
 #define MAP_HUGE_1GB	HUGETLB_FLAG_ENCODE_1GB
 #define MAP_HUGE_2GB	HUGETLB_FLAG_ENCODE_2GB
 #define MAP_HUGE_16GB	HUGETLB_FLAG_ENCODE_16GB
+
+struct cachestat_range {
+	__u64 off;
+	__u64 len;
+};
+
+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

···
 
 	  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

···
 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

···
 #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>
···
 #include <linux/buffer_head.h> /* for try_to_free_buffers */
 
 #include <asm/mman.h>
+
+#include "swap.h"
 
 /*
  * Shared mappings implemented 30.11.1994. It's not fully working yet,
···
 	return try_to_free_buffers(folio);
 }
 EXPORT_SYMBOL(filemap_release_folio);
+
+#ifdef CONFIG_CACHESTAT_SYSCALL
+/**
+ * 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.
+ */
+static 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;
+
+		if (xa_is_value(folio)) {
+			/* page is evicted */
+			void *shadow = (void *)folio;
+			bool workingset; /* not used */
+			int order = xa_get_order(xas.xa, xas.xa_index);
+
+			nr_pages = 1 << order;
+			folio_first_index = round_down(xas.xa_index, 1 << order);
+			folio_last_index = folio_first_index + nr_pages - 1;
+
+			/* Folios might straddle the range boundaries, only count covered pages */
+			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;
+
+			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;
+
+			goto resched;
+		}
+
+		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 pages */
+		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;
+
+		/* 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;
+
+resched:
+		if (need_resched()) {
+			xas_pause(&xas);
+			cond_resched_rcu();
+		}
+	}
+	rcu_read_unlock();
+}
+
+/*
+ * The cachestat(2) 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.
+ *
+ * The `flags` argument is unused for now, but is included for future
+ * extensibility. User should pass 0 (i.e no flag specified).
+ *
+ * Currently, hugetlbfs is not supported.
+ *
+ * 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 or cstat_range points to an illegal address
+ *  -EINVAL     - invalid flags
+ *  -EBADF      - invalid file descriptor
+ *  -EOPNOTSUPP - file descriptor is of a hugetlbfs file
+ */
+SYSCALL_DEFINE4(cachestat, unsigned int, fd,
+		struct cachestat_range __user *, cstat_range,
+		struct cachestat __user *, cstat, unsigned int, flags)
+{
+	struct fd f = fdget(fd);
+	struct address_space *mapping;
+	struct cachestat_range csr;
+	struct cachestat cs;
+	pgoff_t first_index, last_index;
+
+	if (!f.file)
+		return -EBADF;
+
+	if (copy_from_user(&csr, cstat_range,
+			sizeof(struct cachestat_range))) {
+		fdput(f);
+		return -EFAULT;
+	}
+
+	/* hugetlbfs is not supported */
+	if (is_file_hugepages(f.file)) {
+		fdput(f);
+		return -EOPNOTSUPP;
+	}
+
+	if (flags != 0) {
+		fdput(f);
+		return -EINVAL;
+	}
+
+	first_index = csr.off >> PAGE_SHIFT;
+	last_index =
+		csr.len == 0 ? ULONG_MAX : (csr.off + csr.len - 1) >> PAGE_SHIFT;
+	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, sizeof(struct cachestat)))
+		return -EFAULT;
+
+	return 0;
+}
+#endif /* CONFIG_CACHESTAT_SYSCALL */