linux-stable/fs/tracefs/internal.h

79 lines
2.3 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _TRACEFS_INTERNAL_H
#define _TRACEFS_INTERNAL_H
enum {
tracefs/eventfs: Use dput to free the toplevel events directory Currently when rmdir on an instance is done, eventfs_remove_events_dir() is called and it does a dput on the dentry and then frees the eventfs_inode that represents the events directory. But there's no protection against a reader reading the top level events directory at the same time and we can get a use after free error. Instead, use the dput() associated to the dentry to also free the eventfs_inode associated to the events directory, as that will get called when the last reference to the directory is released. This issue triggered the following KASAN report: ================================================================== BUG: KASAN: slab-use-after-free in eventfs_root_lookup+0x88/0x1b0 Read of size 8 at addr ffff888120130ca0 by task ftracetest/1201 CPU: 4 PID: 1201 Comm: ftracetest Not tainted 6.5.0-test-10737-g469e0a8194e7 #13 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.2-debian-1.16.2-1 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x57/0x90 print_report+0xcf/0x670 ? __pfx_ring_buffer_record_off+0x10/0x10 ? _raw_spin_lock_irqsave+0x2b/0x70 ? __virt_addr_valid+0xd9/0x160 kasan_report+0xd4/0x110 ? eventfs_root_lookup+0x88/0x1b0 ? eventfs_root_lookup+0x88/0x1b0 eventfs_root_lookup+0x88/0x1b0 ? eventfs_root_lookup+0x33/0x1b0 __lookup_slow+0x194/0x2a0 ? __pfx___lookup_slow+0x10/0x10 ? down_read+0x11c/0x330 walk_component+0x166/0x220 link_path_walk.part.0.constprop.0+0x3a3/0x5a0 ? seqcount_lockdep_reader_access+0x82/0x90 ? __pfx_link_path_walk.part.0.constprop.0+0x10/0x10 path_openat+0x143/0x11f0 ? __lock_acquire+0xa1a/0x3220 ? __pfx_path_openat+0x10/0x10 ? __pfx___lock_acquire+0x10/0x10 do_filp_open+0x166/0x290 ? __pfx_do_filp_open+0x10/0x10 ? lock_is_held_type+0xce/0x120 ? preempt_count_sub+0xb7/0x100 ? _raw_spin_unlock+0x29/0x50 ? alloc_fd+0x1a0/0x320 do_sys_openat2+0x126/0x160 ? rcu_is_watching+0x34/0x60 ? __pfx_do_sys_openat2+0x10/0x10 ? __might_resched+0x2cf/0x3b0 ? __fget_light+0xdf/0x100 __x64_sys_openat+0xcd/0x140 ? __pfx___x64_sys_openat+0x10/0x10 ? syscall_enter_from_user_mode+0x22/0x90 ? lockdep_hardirqs_on+0x7d/0x100 do_syscall_64+0x3b/0xc0 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 RIP: 0033:0x7f1dceef5e51 Code: 75 57 89 f0 25 00 00 41 00 3d 00 00 41 00 74 49 80 3d 9a 27 0e 00 00 74 6d 89 da 48 89 ee bf 9c ff ff ff b8 01 01 00 00 0f 05 <48> 3d 00 f0 ff ff 0f 87 93 00 00 00 48 8b 54 24 28 64 48 2b 14 25 RSP: 002b:00007fff2cddf380 EFLAGS: 00000202 ORIG_RAX: 0000000000000101 RAX: ffffffffffffffda RBX: 0000000000000241 RCX: 00007f1dceef5e51 RDX: 0000000000000241 RSI: 000055d7520677d0 RDI: 00000000ffffff9c RBP: 000055d7520677d0 R08: 000000000000001e R09: 0000000000000001 R10: 00000000000001b6 R11: 0000000000000202 R12: 0000000000000000 R13: 0000000000000003 R14: 000055d752035678 R15: 000055d752067788 </TASK> Allocated by task 1200: kasan_save_stack+0x2f/0x50 kasan_set_track+0x21/0x30 __kasan_kmalloc+0x8b/0x90 eventfs_create_events_dir+0x54/0x220 create_event_toplevel_files+0x42/0x130 event_trace_add_tracer+0x33/0x180 trace_array_create_dir+0x52/0xf0 trace_array_create+0x361/0x410 instance_mkdir+0x6b/0xb0 tracefs_syscall_mkdir+0x57/0x80 vfs_mkdir+0x275/0x380 do_mkdirat+0x1da/0x210 __x64_sys_mkdir+0x74/0xa0 do_syscall_64+0x3b/0xc0 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 Freed by task 1251: kasan_save_stack+0x2f/0x50 kasan_set_track+0x21/0x30 kasan_save_free_info+0x27/0x40 __kasan_slab_free+0x106/0x180 __kmem_cache_free+0x149/0x2e0 event_trace_del_tracer+0xcb/0x120 __remove_instance+0x16a/0x340 instance_rmdir+0x77/0xa0 tracefs_syscall_rmdir+0x77/0xc0 vfs_rmdir+0xed/0x2d0 do_rmdir+0x235/0x280 __x64_sys_rmdir+0x5f/0x90 do_syscall_64+0x3b/0xc0 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 The buggy address belongs to the object at ffff888120130ca0 which belongs to the cache kmalloc-16 of size 16 The buggy address is located 0 bytes inside of freed 16-byte region [ffff888120130ca0, ffff888120130cb0) The buggy address belongs to the physical page: page:000000004dbddbb0 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x120130 flags: 0x17ffffc0000800(slab|node=0|zone=2|lastcpupid=0x1fffff) page_type: 0xffffffff() raw: 0017ffffc0000800 ffff8881000423c0 dead000000000122 0000000000000000 raw: 0000000000000000 0000000000800080 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888120130b80: 00 00 fc fc 00 05 fc fc 00 00 fc fc 00 02 fc fc ffff888120130c00: 00 07 fc fc 00 00 fc fc 00 00 fc fc fa fb fc fc >ffff888120130c80: 00 00 fc fc fa fb fc fc 00 00 fc fc 00 00 fc fc ^ ffff888120130d00: 00 00 fc fc 00 00 fc fc 00 00 fc fc fa fb fc fc ffff888120130d80: 00 00 fc fc 00 00 fc fc 00 00 fc fc 00 00 fc fc ================================================================== Link: https://lkml.kernel.org/r/20230907024803.250873643@goodmis.org Link: https://lore.kernel.org/all/1cb3aee2-19af-c472-e265-05176fe9bd84@huawei.com/ Cc: Ajay Kaher <akaher@vmware.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Fixes: 5bdcd5f5331a2 eventfs: ("Implement removal of meta data from eventfs") Tested-by: Linux Kernel Functional Testing <lkft@linaro.org> Tested-by: Naresh Kamboju <naresh.kamboju@linaro.org> Reported-by: Zheng Yejian <zhengyejian1@huawei.com> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2023-09-07 02:47:11 +00:00
TRACEFS_EVENT_INODE = BIT(1),
TRACEFS_EVENT_TOP_INODE = BIT(2),
tracefs/eventfs: Use root and instance inodes as default ownership Instead of walking the dentries on mount/remount to update the gid values of all the dentries if a gid option is specified on mount, just update the root inode. Add .getattr, .setattr, and .permissions on the tracefs inode operations to update the permissions of the files and directories. For all files and directories in the top level instance: /sys/kernel/tracing/* It will use the root inode as the default permissions. The inode that represents: /sys/kernel/tracing (or wherever it is mounted). When an instance is created: mkdir /sys/kernel/tracing/instance/foo The directory "foo" and all its files and directories underneath will use the default of what foo is when it was created. A remount of tracefs will not affect it. If a user were to modify the permissions of any file or directory in tracefs, it will also no longer be modified by a change in ownership of a remount. The events directory, if it is in the top level instance, will use the tracefs root inode as the default ownership for itself and all the files and directories below it. For the events directory in an instance ("foo"), it will keep the ownership of what it was when it was created, and that will be used as the default ownership for the files and directories beneath it. Link: https://lore.kernel.org/linux-trace-kernel/CAHk-=wjVdGkjDXBbvLn2wbZnqP4UsH46E3gqJ9m7UG6DpX2+WA@mail.gmail.com/ Link: https://lore.kernel.org/linux-trace-kernel/20240103215016.1e0c9811@gandalf.local.home Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Al Viro <viro@ZenIV.linux.org.uk> Cc: Christian Brauner <brauner@kernel.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2024-01-04 02:50:16 +00:00
TRACEFS_GID_PERM_SET = BIT(3),
TRACEFS_UID_PERM_SET = BIT(4),
TRACEFS_INSTANCE_INODE = BIT(5),
};
struct tracefs_inode {
struct inode vfs_inode;
/* The below gets initialized with memset_after(ti, 0, vfs_inode) */
unsigned long flags;
void *private;
};
/*
* struct eventfs_attr - cache the mode and ownership of a eventfs entry
* @mode: saved mode plus flags of what is saved
* @uid: saved uid if changed
* @gid: saved gid if changed
*/
struct eventfs_attr {
int mode;
kuid_t uid;
kgid_t gid;
};
eventfs: Remove eventfs_file and just use eventfs_inode Instead of having a descriptor for every file represented in the eventfs directory, only have the directory itself represented. Change the API to send in a list of entries that represent all the files in the directory (but not other directories). The entry list contains a name and a callback function that will be used to create the files when they are accessed. struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry *parent, const struct eventfs_entry *entries, int size, void *data); is used for the top level eventfs directory, and returns an eventfs_inode that will be used by: struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode *parent, const struct eventfs_entry *entries, int size, void *data); where both of the above take an array of struct eventfs_entry entries for every file that is in the directory. The entries are defined by: typedef int (*eventfs_callback)(const char *name, umode_t *mode, void **data, const struct file_operations **fops); struct eventfs_entry { const char *name; eventfs_callback callback; }; Where the name is the name of the file and the callback gets called when the file is being created. The callback passes in the name (in case the same callback is used for multiple files), a pointer to the mode, data and fops. The data will be pointing to the data that was passed in eventfs_create_dir() or eventfs_create_events_dir() but may be overridden to point to something else, as it will be used to point to the inode->i_private that is created. The information passed back from the callback is used to create the dentry/inode. If the callback fills the data and the file should be created, it must return a positive number. On zero or negative, the file is ignored. This logic may also be used as a prototype to convert entire pseudo file systems into just-in-time allocation. The "show_events_dentry" file has been updated to show the directories, and any files they have. With just the eventfs_file allocations: Before after deltas for meminfo (in kB): MemFree: -14360 MemAvailable: -14260 Buffers: 40 Cached: 24 Active: 44 Inactive: 48 Inactive(anon): 28 Active(file): 44 Inactive(file): 20 Dirty: -4 AnonPages: 28 Mapped: 4 KReclaimable: 132 Slab: 1604 SReclaimable: 132 SUnreclaim: 1472 Committed_AS: 12 Before after deltas for slabinfo: <slab>: <objects> [ * <size> = <total>] ext4_inode_cache 27 [* 1184 = 31968 ] extent_status 102 [* 40 = 4080 ] tracefs_inode_cache 144 [* 656 = 94464 ] buffer_head 39 [* 104 = 4056 ] shmem_inode_cache 49 [* 800 = 39200 ] filp -53 [* 256 = -13568 ] dentry 251 [* 192 = 48192 ] lsm_file_cache 277 [* 32 = 8864 ] vm_area_struct -14 [* 184 = -2576 ] trace_event_file 1748 [* 88 = 153824 ] kmalloc-1k 35 [* 1024 = 35840 ] kmalloc-256 49 [* 256 = 12544 ] kmalloc-192 -28 [* 192 = -5376 ] kmalloc-128 -30 [* 128 = -3840 ] kmalloc-96 10581 [* 96 = 1015776 ] kmalloc-64 3056 [* 64 = 195584 ] kmalloc-32 1291 [* 32 = 41312 ] kmalloc-16 2310 [* 16 = 36960 ] kmalloc-8 9216 [* 8 = 73728 ] Free memory dropped by 14,360 kB Available memory dropped by 14,260 kB Total slab additions in size: 1,771,032 bytes With this change: Before after deltas for meminfo (in kB): MemFree: -12084 MemAvailable: -11976 Buffers: 32 Cached: 32 Active: 72 Inactive: 168 Inactive(anon): 176 Active(file): 72 Inactive(file): -8 Dirty: 24 AnonPages: 196 Mapped: 8 KReclaimable: 148 Slab: 836 SReclaimable: 148 SUnreclaim: 688 Committed_AS: 324 Before after deltas for slabinfo: <slab>: <objects> [ * <size> = <total>] tracefs_inode_cache 144 [* 656 = 94464 ] shmem_inode_cache -23 [* 800 = -18400 ] filp -92 [* 256 = -23552 ] dentry 179 [* 192 = 34368 ] lsm_file_cache -3 [* 32 = -96 ] vm_area_struct -13 [* 184 = -2392 ] trace_event_file 1748 [* 88 = 153824 ] kmalloc-1k -49 [* 1024 = -50176 ] kmalloc-256 -27 [* 256 = -6912 ] kmalloc-128 1864 [* 128 = 238592 ] kmalloc-64 4685 [* 64 = 299840 ] kmalloc-32 -72 [* 32 = -2304 ] kmalloc-16 256 [* 16 = 4096 ] total = 721352 Free memory dropped by 12,084 kB Available memory dropped by 11,976 kB Total slab additions in size: 721,352 bytes That's over 2 MB in savings per instance for free and available memory, and over 1 MB in savings per instance of slab memory. Link: https://lore.kernel.org/linux-trace-kernel/20231003184059.4924468e@gandalf.local.home Link: https://lore.kernel.org/linux-trace-kernel/20231004165007.43d79161@gandalf.local.home Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Ajay Kaher <akaher@vmware.com> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2023-10-04 20:50:07 +00:00
/*
* struct eventfs_inode - hold the properties of the eventfs directories.
* @list: link list into the parent directory
* @rcu: Union with @list for freeing
* @children: link list into the child eventfs_inode
eventfs: Remove eventfs_file and just use eventfs_inode Instead of having a descriptor for every file represented in the eventfs directory, only have the directory itself represented. Change the API to send in a list of entries that represent all the files in the directory (but not other directories). The entry list contains a name and a callback function that will be used to create the files when they are accessed. struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry *parent, const struct eventfs_entry *entries, int size, void *data); is used for the top level eventfs directory, and returns an eventfs_inode that will be used by: struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode *parent, const struct eventfs_entry *entries, int size, void *data); where both of the above take an array of struct eventfs_entry entries for every file that is in the directory. The entries are defined by: typedef int (*eventfs_callback)(const char *name, umode_t *mode, void **data, const struct file_operations **fops); struct eventfs_entry { const char *name; eventfs_callback callback; }; Where the name is the name of the file and the callback gets called when the file is being created. The callback passes in the name (in case the same callback is used for multiple files), a pointer to the mode, data and fops. The data will be pointing to the data that was passed in eventfs_create_dir() or eventfs_create_events_dir() but may be overridden to point to something else, as it will be used to point to the inode->i_private that is created. The information passed back from the callback is used to create the dentry/inode. If the callback fills the data and the file should be created, it must return a positive number. On zero or negative, the file is ignored. This logic may also be used as a prototype to convert entire pseudo file systems into just-in-time allocation. The "show_events_dentry" file has been updated to show the directories, and any files they have. With just the eventfs_file allocations: Before after deltas for meminfo (in kB): MemFree: -14360 MemAvailable: -14260 Buffers: 40 Cached: 24 Active: 44 Inactive: 48 Inactive(anon): 28 Active(file): 44 Inactive(file): 20 Dirty: -4 AnonPages: 28 Mapped: 4 KReclaimable: 132 Slab: 1604 SReclaimable: 132 SUnreclaim: 1472 Committed_AS: 12 Before after deltas for slabinfo: <slab>: <objects> [ * <size> = <total>] ext4_inode_cache 27 [* 1184 = 31968 ] extent_status 102 [* 40 = 4080 ] tracefs_inode_cache 144 [* 656 = 94464 ] buffer_head 39 [* 104 = 4056 ] shmem_inode_cache 49 [* 800 = 39200 ] filp -53 [* 256 = -13568 ] dentry 251 [* 192 = 48192 ] lsm_file_cache 277 [* 32 = 8864 ] vm_area_struct -14 [* 184 = -2576 ] trace_event_file 1748 [* 88 = 153824 ] kmalloc-1k 35 [* 1024 = 35840 ] kmalloc-256 49 [* 256 = 12544 ] kmalloc-192 -28 [* 192 = -5376 ] kmalloc-128 -30 [* 128 = -3840 ] kmalloc-96 10581 [* 96 = 1015776 ] kmalloc-64 3056 [* 64 = 195584 ] kmalloc-32 1291 [* 32 = 41312 ] kmalloc-16 2310 [* 16 = 36960 ] kmalloc-8 9216 [* 8 = 73728 ] Free memory dropped by 14,360 kB Available memory dropped by 14,260 kB Total slab additions in size: 1,771,032 bytes With this change: Before after deltas for meminfo (in kB): MemFree: -12084 MemAvailable: -11976 Buffers: 32 Cached: 32 Active: 72 Inactive: 168 Inactive(anon): 176 Active(file): 72 Inactive(file): -8 Dirty: 24 AnonPages: 196 Mapped: 8 KReclaimable: 148 Slab: 836 SReclaimable: 148 SUnreclaim: 688 Committed_AS: 324 Before after deltas for slabinfo: <slab>: <objects> [ * <size> = <total>] tracefs_inode_cache 144 [* 656 = 94464 ] shmem_inode_cache -23 [* 800 = -18400 ] filp -92 [* 256 = -23552 ] dentry 179 [* 192 = 34368 ] lsm_file_cache -3 [* 32 = -96 ] vm_area_struct -13 [* 184 = -2392 ] trace_event_file 1748 [* 88 = 153824 ] kmalloc-1k -49 [* 1024 = -50176 ] kmalloc-256 -27 [* 256 = -6912 ] kmalloc-128 1864 [* 128 = 238592 ] kmalloc-64 4685 [* 64 = 299840 ] kmalloc-32 -72 [* 32 = -2304 ] kmalloc-16 256 [* 16 = 4096 ] total = 721352 Free memory dropped by 12,084 kB Available memory dropped by 11,976 kB Total slab additions in size: 721,352 bytes That's over 2 MB in savings per instance for free and available memory, and over 1 MB in savings per instance of slab memory. Link: https://lore.kernel.org/linux-trace-kernel/20231003184059.4924468e@gandalf.local.home Link: https://lore.kernel.org/linux-trace-kernel/20231004165007.43d79161@gandalf.local.home Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Ajay Kaher <akaher@vmware.com> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2023-10-04 20:50:07 +00:00
* @entries: the array of entries representing the files in the directory
* @name: the name of the directory to create
* @entry_attrs: Saved mode and ownership of the @d_children
eventfs: Remove eventfs_file and just use eventfs_inode Instead of having a descriptor for every file represented in the eventfs directory, only have the directory itself represented. Change the API to send in a list of entries that represent all the files in the directory (but not other directories). The entry list contains a name and a callback function that will be used to create the files when they are accessed. struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry *parent, const struct eventfs_entry *entries, int size, void *data); is used for the top level eventfs directory, and returns an eventfs_inode that will be used by: struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode *parent, const struct eventfs_entry *entries, int size, void *data); where both of the above take an array of struct eventfs_entry entries for every file that is in the directory. The entries are defined by: typedef int (*eventfs_callback)(const char *name, umode_t *mode, void **data, const struct file_operations **fops); struct eventfs_entry { const char *name; eventfs_callback callback; }; Where the name is the name of the file and the callback gets called when the file is being created. The callback passes in the name (in case the same callback is used for multiple files), a pointer to the mode, data and fops. The data will be pointing to the data that was passed in eventfs_create_dir() or eventfs_create_events_dir() but may be overridden to point to something else, as it will be used to point to the inode->i_private that is created. The information passed back from the callback is used to create the dentry/inode. If the callback fills the data and the file should be created, it must return a positive number. On zero or negative, the file is ignored. This logic may also be used as a prototype to convert entire pseudo file systems into just-in-time allocation. The "show_events_dentry" file has been updated to show the directories, and any files they have. With just the eventfs_file allocations: Before after deltas for meminfo (in kB): MemFree: -14360 MemAvailable: -14260 Buffers: 40 Cached: 24 Active: 44 Inactive: 48 Inactive(anon): 28 Active(file): 44 Inactive(file): 20 Dirty: -4 AnonPages: 28 Mapped: 4 KReclaimable: 132 Slab: 1604 SReclaimable: 132 SUnreclaim: 1472 Committed_AS: 12 Before after deltas for slabinfo: <slab>: <objects> [ * <size> = <total>] ext4_inode_cache 27 [* 1184 = 31968 ] extent_status 102 [* 40 = 4080 ] tracefs_inode_cache 144 [* 656 = 94464 ] buffer_head 39 [* 104 = 4056 ] shmem_inode_cache 49 [* 800 = 39200 ] filp -53 [* 256 = -13568 ] dentry 251 [* 192 = 48192 ] lsm_file_cache 277 [* 32 = 8864 ] vm_area_struct -14 [* 184 = -2576 ] trace_event_file 1748 [* 88 = 153824 ] kmalloc-1k 35 [* 1024 = 35840 ] kmalloc-256 49 [* 256 = 12544 ] kmalloc-192 -28 [* 192 = -5376 ] kmalloc-128 -30 [* 128 = -3840 ] kmalloc-96 10581 [* 96 = 1015776 ] kmalloc-64 3056 [* 64 = 195584 ] kmalloc-32 1291 [* 32 = 41312 ] kmalloc-16 2310 [* 16 = 36960 ] kmalloc-8 9216 [* 8 = 73728 ] Free memory dropped by 14,360 kB Available memory dropped by 14,260 kB Total slab additions in size: 1,771,032 bytes With this change: Before after deltas for meminfo (in kB): MemFree: -12084 MemAvailable: -11976 Buffers: 32 Cached: 32 Active: 72 Inactive: 168 Inactive(anon): 176 Active(file): 72 Inactive(file): -8 Dirty: 24 AnonPages: 196 Mapped: 8 KReclaimable: 148 Slab: 836 SReclaimable: 148 SUnreclaim: 688 Committed_AS: 324 Before after deltas for slabinfo: <slab>: <objects> [ * <size> = <total>] tracefs_inode_cache 144 [* 656 = 94464 ] shmem_inode_cache -23 [* 800 = -18400 ] filp -92 [* 256 = -23552 ] dentry 179 [* 192 = 34368 ] lsm_file_cache -3 [* 32 = -96 ] vm_area_struct -13 [* 184 = -2392 ] trace_event_file 1748 [* 88 = 153824 ] kmalloc-1k -49 [* 1024 = -50176 ] kmalloc-256 -27 [* 256 = -6912 ] kmalloc-128 1864 [* 128 = 238592 ] kmalloc-64 4685 [* 64 = 299840 ] kmalloc-32 -72 [* 32 = -2304 ] kmalloc-16 256 [* 16 = 4096 ] total = 721352 Free memory dropped by 12,084 kB Available memory dropped by 11,976 kB Total slab additions in size: 721,352 bytes That's over 2 MB in savings per instance for free and available memory, and over 1 MB in savings per instance of slab memory. Link: https://lore.kernel.org/linux-trace-kernel/20231003184059.4924468e@gandalf.local.home Link: https://lore.kernel.org/linux-trace-kernel/20231004165007.43d79161@gandalf.local.home Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Ajay Kaher <akaher@vmware.com> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2023-10-04 20:50:07 +00:00
* @data: The private data to pass to the callbacks
* @attr: Saved mode and ownership of eventfs_inode itself
* @is_freed: Flag set if the eventfs is on its way to be freed
eventfs: Test for ei->is_freed when accessing ei->dentry The eventfs_inode (ei) is protected by SRCU, but the ei->dentry is not. It is protected by the eventfs_mutex. Anytime the eventfs_mutex is released, and access to the ei->dentry needs to be done, it should first check if ei->is_freed is set under the eventfs_mutex. If it is, then the ei->dentry is invalid and must not be used. The ei->dentry must only be accessed under the eventfs_mutex and after checking if ei->is_freed is set. When the ei is being freed, it will (under the eventfs_mutex) set is_freed and at the same time move the dentry to a free list to be cleared after the eventfs_mutex is released. This means that any access to the ei->dentry must check first if ei->is_freed is set, because if it is, then the dentry is on its way to be freed. Also add comments to describe this better. Link: https://lore.kernel.org/all/CA+G9fYt6pY+tMZEOg=SoEywQOe19fGP3uR15SGowkdK+_X85Cg@mail.gmail.com/ Link: https://lore.kernel.org/all/CA+G9fYuDP3hVQ3t7FfrBAjd_WFVSurMgCepTxunSJf=MTe=6aA@mail.gmail.com/ Link: https://lkml.kernel.org/r/20231101172649.477608228@goodmis.org Cc: Ajay Kaher <akaher@vmware.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Fixes: 5790b1fb3d672 ("eventfs: Remove eventfs_file and just use eventfs_inode") Reported-by: Linux Kernel Functional Testing <lkft@linaro.org> Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org> Reported-by: Beau Belgrave <beaub@linux.microsoft.com> Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org> Tested-by: Linux Kernel Functional Testing <lkft@linaro.org> Tested-by: Naresh Kamboju <naresh.kamboju@linaro.org> Tested-by: Beau Belgrave <beaub@linux.microsoft.com> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2023-11-01 17:25:44 +00:00
* Note if is_freed is set, then dentry is corrupted.
* @is_events: Flag set for only the top level "events" directory
eventfs: Remove eventfs_file and just use eventfs_inode Instead of having a descriptor for every file represented in the eventfs directory, only have the directory itself represented. Change the API to send in a list of entries that represent all the files in the directory (but not other directories). The entry list contains a name and a callback function that will be used to create the files when they are accessed. struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry *parent, const struct eventfs_entry *entries, int size, void *data); is used for the top level eventfs directory, and returns an eventfs_inode that will be used by: struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode *parent, const struct eventfs_entry *entries, int size, void *data); where both of the above take an array of struct eventfs_entry entries for every file that is in the directory. The entries are defined by: typedef int (*eventfs_callback)(const char *name, umode_t *mode, void **data, const struct file_operations **fops); struct eventfs_entry { const char *name; eventfs_callback callback; }; Where the name is the name of the file and the callback gets called when the file is being created. The callback passes in the name (in case the same callback is used for multiple files), a pointer to the mode, data and fops. The data will be pointing to the data that was passed in eventfs_create_dir() or eventfs_create_events_dir() but may be overridden to point to something else, as it will be used to point to the inode->i_private that is created. The information passed back from the callback is used to create the dentry/inode. If the callback fills the data and the file should be created, it must return a positive number. On zero or negative, the file is ignored. This logic may also be used as a prototype to convert entire pseudo file systems into just-in-time allocation. The "show_events_dentry" file has been updated to show the directories, and any files they have. With just the eventfs_file allocations: Before after deltas for meminfo (in kB): MemFree: -14360 MemAvailable: -14260 Buffers: 40 Cached: 24 Active: 44 Inactive: 48 Inactive(anon): 28 Active(file): 44 Inactive(file): 20 Dirty: -4 AnonPages: 28 Mapped: 4 KReclaimable: 132 Slab: 1604 SReclaimable: 132 SUnreclaim: 1472 Committed_AS: 12 Before after deltas for slabinfo: <slab>: <objects> [ * <size> = <total>] ext4_inode_cache 27 [* 1184 = 31968 ] extent_status 102 [* 40 = 4080 ] tracefs_inode_cache 144 [* 656 = 94464 ] buffer_head 39 [* 104 = 4056 ] shmem_inode_cache 49 [* 800 = 39200 ] filp -53 [* 256 = -13568 ] dentry 251 [* 192 = 48192 ] lsm_file_cache 277 [* 32 = 8864 ] vm_area_struct -14 [* 184 = -2576 ] trace_event_file 1748 [* 88 = 153824 ] kmalloc-1k 35 [* 1024 = 35840 ] kmalloc-256 49 [* 256 = 12544 ] kmalloc-192 -28 [* 192 = -5376 ] kmalloc-128 -30 [* 128 = -3840 ] kmalloc-96 10581 [* 96 = 1015776 ] kmalloc-64 3056 [* 64 = 195584 ] kmalloc-32 1291 [* 32 = 41312 ] kmalloc-16 2310 [* 16 = 36960 ] kmalloc-8 9216 [* 8 = 73728 ] Free memory dropped by 14,360 kB Available memory dropped by 14,260 kB Total slab additions in size: 1,771,032 bytes With this change: Before after deltas for meminfo (in kB): MemFree: -12084 MemAvailable: -11976 Buffers: 32 Cached: 32 Active: 72 Inactive: 168 Inactive(anon): 176 Active(file): 72 Inactive(file): -8 Dirty: 24 AnonPages: 196 Mapped: 8 KReclaimable: 148 Slab: 836 SReclaimable: 148 SUnreclaim: 688 Committed_AS: 324 Before after deltas for slabinfo: <slab>: <objects> [ * <size> = <total>] tracefs_inode_cache 144 [* 656 = 94464 ] shmem_inode_cache -23 [* 800 = -18400 ] filp -92 [* 256 = -23552 ] dentry 179 [* 192 = 34368 ] lsm_file_cache -3 [* 32 = -96 ] vm_area_struct -13 [* 184 = -2392 ] trace_event_file 1748 [* 88 = 153824 ] kmalloc-1k -49 [* 1024 = -50176 ] kmalloc-256 -27 [* 256 = -6912 ] kmalloc-128 1864 [* 128 = 238592 ] kmalloc-64 4685 [* 64 = 299840 ] kmalloc-32 -72 [* 32 = -2304 ] kmalloc-16 256 [* 16 = 4096 ] total = 721352 Free memory dropped by 12,084 kB Available memory dropped by 11,976 kB Total slab additions in size: 721,352 bytes That's over 2 MB in savings per instance for free and available memory, and over 1 MB in savings per instance of slab memory. Link: https://lore.kernel.org/linux-trace-kernel/20231003184059.4924468e@gandalf.local.home Link: https://lore.kernel.org/linux-trace-kernel/20231004165007.43d79161@gandalf.local.home Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Ajay Kaher <akaher@vmware.com> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2023-10-04 20:50:07 +00:00
* @nr_entries: The number of items in @entries
* @ino: The saved inode number
eventfs: Remove eventfs_file and just use eventfs_inode Instead of having a descriptor for every file represented in the eventfs directory, only have the directory itself represented. Change the API to send in a list of entries that represent all the files in the directory (but not other directories). The entry list contains a name and a callback function that will be used to create the files when they are accessed. struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry *parent, const struct eventfs_entry *entries, int size, void *data); is used for the top level eventfs directory, and returns an eventfs_inode that will be used by: struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode *parent, const struct eventfs_entry *entries, int size, void *data); where both of the above take an array of struct eventfs_entry entries for every file that is in the directory. The entries are defined by: typedef int (*eventfs_callback)(const char *name, umode_t *mode, void **data, const struct file_operations **fops); struct eventfs_entry { const char *name; eventfs_callback callback; }; Where the name is the name of the file and the callback gets called when the file is being created. The callback passes in the name (in case the same callback is used for multiple files), a pointer to the mode, data and fops. The data will be pointing to the data that was passed in eventfs_create_dir() or eventfs_create_events_dir() but may be overridden to point to something else, as it will be used to point to the inode->i_private that is created. The information passed back from the callback is used to create the dentry/inode. If the callback fills the data and the file should be created, it must return a positive number. On zero or negative, the file is ignored. This logic may also be used as a prototype to convert entire pseudo file systems into just-in-time allocation. The "show_events_dentry" file has been updated to show the directories, and any files they have. With just the eventfs_file allocations: Before after deltas for meminfo (in kB): MemFree: -14360 MemAvailable: -14260 Buffers: 40 Cached: 24 Active: 44 Inactive: 48 Inactive(anon): 28 Active(file): 44 Inactive(file): 20 Dirty: -4 AnonPages: 28 Mapped: 4 KReclaimable: 132 Slab: 1604 SReclaimable: 132 SUnreclaim: 1472 Committed_AS: 12 Before after deltas for slabinfo: <slab>: <objects> [ * <size> = <total>] ext4_inode_cache 27 [* 1184 = 31968 ] extent_status 102 [* 40 = 4080 ] tracefs_inode_cache 144 [* 656 = 94464 ] buffer_head 39 [* 104 = 4056 ] shmem_inode_cache 49 [* 800 = 39200 ] filp -53 [* 256 = -13568 ] dentry 251 [* 192 = 48192 ] lsm_file_cache 277 [* 32 = 8864 ] vm_area_struct -14 [* 184 = -2576 ] trace_event_file 1748 [* 88 = 153824 ] kmalloc-1k 35 [* 1024 = 35840 ] kmalloc-256 49 [* 256 = 12544 ] kmalloc-192 -28 [* 192 = -5376 ] kmalloc-128 -30 [* 128 = -3840 ] kmalloc-96 10581 [* 96 = 1015776 ] kmalloc-64 3056 [* 64 = 195584 ] kmalloc-32 1291 [* 32 = 41312 ] kmalloc-16 2310 [* 16 = 36960 ] kmalloc-8 9216 [* 8 = 73728 ] Free memory dropped by 14,360 kB Available memory dropped by 14,260 kB Total slab additions in size: 1,771,032 bytes With this change: Before after deltas for meminfo (in kB): MemFree: -12084 MemAvailable: -11976 Buffers: 32 Cached: 32 Active: 72 Inactive: 168 Inactive(anon): 176 Active(file): 72 Inactive(file): -8 Dirty: 24 AnonPages: 196 Mapped: 8 KReclaimable: 148 Slab: 836 SReclaimable: 148 SUnreclaim: 688 Committed_AS: 324 Before after deltas for slabinfo: <slab>: <objects> [ * <size> = <total>] tracefs_inode_cache 144 [* 656 = 94464 ] shmem_inode_cache -23 [* 800 = -18400 ] filp -92 [* 256 = -23552 ] dentry 179 [* 192 = 34368 ] lsm_file_cache -3 [* 32 = -96 ] vm_area_struct -13 [* 184 = -2392 ] trace_event_file 1748 [* 88 = 153824 ] kmalloc-1k -49 [* 1024 = -50176 ] kmalloc-256 -27 [* 256 = -6912 ] kmalloc-128 1864 [* 128 = 238592 ] kmalloc-64 4685 [* 64 = 299840 ] kmalloc-32 -72 [* 32 = -2304 ] kmalloc-16 256 [* 16 = 4096 ] total = 721352 Free memory dropped by 12,084 kB Available memory dropped by 11,976 kB Total slab additions in size: 721,352 bytes That's over 2 MB in savings per instance for free and available memory, and over 1 MB in savings per instance of slab memory. Link: https://lore.kernel.org/linux-trace-kernel/20231003184059.4924468e@gandalf.local.home Link: https://lore.kernel.org/linux-trace-kernel/20231004165007.43d79161@gandalf.local.home Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Ajay Kaher <akaher@vmware.com> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2023-10-04 20:50:07 +00:00
*/
struct eventfs_inode {
union {
struct list_head list;
struct rcu_head rcu;
};
struct list_head children;
eventfs: Remove eventfs_file and just use eventfs_inode Instead of having a descriptor for every file represented in the eventfs directory, only have the directory itself represented. Change the API to send in a list of entries that represent all the files in the directory (but not other directories). The entry list contains a name and a callback function that will be used to create the files when they are accessed. struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry *parent, const struct eventfs_entry *entries, int size, void *data); is used for the top level eventfs directory, and returns an eventfs_inode that will be used by: struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode *parent, const struct eventfs_entry *entries, int size, void *data); where both of the above take an array of struct eventfs_entry entries for every file that is in the directory. The entries are defined by: typedef int (*eventfs_callback)(const char *name, umode_t *mode, void **data, const struct file_operations **fops); struct eventfs_entry { const char *name; eventfs_callback callback; }; Where the name is the name of the file and the callback gets called when the file is being created. The callback passes in the name (in case the same callback is used for multiple files), a pointer to the mode, data and fops. The data will be pointing to the data that was passed in eventfs_create_dir() or eventfs_create_events_dir() but may be overridden to point to something else, as it will be used to point to the inode->i_private that is created. The information passed back from the callback is used to create the dentry/inode. If the callback fills the data and the file should be created, it must return a positive number. On zero or negative, the file is ignored. This logic may also be used as a prototype to convert entire pseudo file systems into just-in-time allocation. The "show_events_dentry" file has been updated to show the directories, and any files they have. With just the eventfs_file allocations: Before after deltas for meminfo (in kB): MemFree: -14360 MemAvailable: -14260 Buffers: 40 Cached: 24 Active: 44 Inactive: 48 Inactive(anon): 28 Active(file): 44 Inactive(file): 20 Dirty: -4 AnonPages: 28 Mapped: 4 KReclaimable: 132 Slab: 1604 SReclaimable: 132 SUnreclaim: 1472 Committed_AS: 12 Before after deltas for slabinfo: <slab>: <objects> [ * <size> = <total>] ext4_inode_cache 27 [* 1184 = 31968 ] extent_status 102 [* 40 = 4080 ] tracefs_inode_cache 144 [* 656 = 94464 ] buffer_head 39 [* 104 = 4056 ] shmem_inode_cache 49 [* 800 = 39200 ] filp -53 [* 256 = -13568 ] dentry 251 [* 192 = 48192 ] lsm_file_cache 277 [* 32 = 8864 ] vm_area_struct -14 [* 184 = -2576 ] trace_event_file 1748 [* 88 = 153824 ] kmalloc-1k 35 [* 1024 = 35840 ] kmalloc-256 49 [* 256 = 12544 ] kmalloc-192 -28 [* 192 = -5376 ] kmalloc-128 -30 [* 128 = -3840 ] kmalloc-96 10581 [* 96 = 1015776 ] kmalloc-64 3056 [* 64 = 195584 ] kmalloc-32 1291 [* 32 = 41312 ] kmalloc-16 2310 [* 16 = 36960 ] kmalloc-8 9216 [* 8 = 73728 ] Free memory dropped by 14,360 kB Available memory dropped by 14,260 kB Total slab additions in size: 1,771,032 bytes With this change: Before after deltas for meminfo (in kB): MemFree: -12084 MemAvailable: -11976 Buffers: 32 Cached: 32 Active: 72 Inactive: 168 Inactive(anon): 176 Active(file): 72 Inactive(file): -8 Dirty: 24 AnonPages: 196 Mapped: 8 KReclaimable: 148 Slab: 836 SReclaimable: 148 SUnreclaim: 688 Committed_AS: 324 Before after deltas for slabinfo: <slab>: <objects> [ * <size> = <total>] tracefs_inode_cache 144 [* 656 = 94464 ] shmem_inode_cache -23 [* 800 = -18400 ] filp -92 [* 256 = -23552 ] dentry 179 [* 192 = 34368 ] lsm_file_cache -3 [* 32 = -96 ] vm_area_struct -13 [* 184 = -2392 ] trace_event_file 1748 [* 88 = 153824 ] kmalloc-1k -49 [* 1024 = -50176 ] kmalloc-256 -27 [* 256 = -6912 ] kmalloc-128 1864 [* 128 = 238592 ] kmalloc-64 4685 [* 64 = 299840 ] kmalloc-32 -72 [* 32 = -2304 ] kmalloc-16 256 [* 16 = 4096 ] total = 721352 Free memory dropped by 12,084 kB Available memory dropped by 11,976 kB Total slab additions in size: 721,352 bytes That's over 2 MB in savings per instance for free and available memory, and over 1 MB in savings per instance of slab memory. Link: https://lore.kernel.org/linux-trace-kernel/20231003184059.4924468e@gandalf.local.home Link: https://lore.kernel.org/linux-trace-kernel/20231004165007.43d79161@gandalf.local.home Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Ajay Kaher <akaher@vmware.com> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2023-10-04 20:50:07 +00:00
const struct eventfs_entry *entries;
const char *name;
struct eventfs_attr *entry_attrs;
eventfs: Remove eventfs_file and just use eventfs_inode Instead of having a descriptor for every file represented in the eventfs directory, only have the directory itself represented. Change the API to send in a list of entries that represent all the files in the directory (but not other directories). The entry list contains a name and a callback function that will be used to create the files when they are accessed. struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry *parent, const struct eventfs_entry *entries, int size, void *data); is used for the top level eventfs directory, and returns an eventfs_inode that will be used by: struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode *parent, const struct eventfs_entry *entries, int size, void *data); where both of the above take an array of struct eventfs_entry entries for every file that is in the directory. The entries are defined by: typedef int (*eventfs_callback)(const char *name, umode_t *mode, void **data, const struct file_operations **fops); struct eventfs_entry { const char *name; eventfs_callback callback; }; Where the name is the name of the file and the callback gets called when the file is being created. The callback passes in the name (in case the same callback is used for multiple files), a pointer to the mode, data and fops. The data will be pointing to the data that was passed in eventfs_create_dir() or eventfs_create_events_dir() but may be overridden to point to something else, as it will be used to point to the inode->i_private that is created. The information passed back from the callback is used to create the dentry/inode. If the callback fills the data and the file should be created, it must return a positive number. On zero or negative, the file is ignored. This logic may also be used as a prototype to convert entire pseudo file systems into just-in-time allocation. The "show_events_dentry" file has been updated to show the directories, and any files they have. With just the eventfs_file allocations: Before after deltas for meminfo (in kB): MemFree: -14360 MemAvailable: -14260 Buffers: 40 Cached: 24 Active: 44 Inactive: 48 Inactive(anon): 28 Active(file): 44 Inactive(file): 20 Dirty: -4 AnonPages: 28 Mapped: 4 KReclaimable: 132 Slab: 1604 SReclaimable: 132 SUnreclaim: 1472 Committed_AS: 12 Before after deltas for slabinfo: <slab>: <objects> [ * <size> = <total>] ext4_inode_cache 27 [* 1184 = 31968 ] extent_status 102 [* 40 = 4080 ] tracefs_inode_cache 144 [* 656 = 94464 ] buffer_head 39 [* 104 = 4056 ] shmem_inode_cache 49 [* 800 = 39200 ] filp -53 [* 256 = -13568 ] dentry 251 [* 192 = 48192 ] lsm_file_cache 277 [* 32 = 8864 ] vm_area_struct -14 [* 184 = -2576 ] trace_event_file 1748 [* 88 = 153824 ] kmalloc-1k 35 [* 1024 = 35840 ] kmalloc-256 49 [* 256 = 12544 ] kmalloc-192 -28 [* 192 = -5376 ] kmalloc-128 -30 [* 128 = -3840 ] kmalloc-96 10581 [* 96 = 1015776 ] kmalloc-64 3056 [* 64 = 195584 ] kmalloc-32 1291 [* 32 = 41312 ] kmalloc-16 2310 [* 16 = 36960 ] kmalloc-8 9216 [* 8 = 73728 ] Free memory dropped by 14,360 kB Available memory dropped by 14,260 kB Total slab additions in size: 1,771,032 bytes With this change: Before after deltas for meminfo (in kB): MemFree: -12084 MemAvailable: -11976 Buffers: 32 Cached: 32 Active: 72 Inactive: 168 Inactive(anon): 176 Active(file): 72 Inactive(file): -8 Dirty: 24 AnonPages: 196 Mapped: 8 KReclaimable: 148 Slab: 836 SReclaimable: 148 SUnreclaim: 688 Committed_AS: 324 Before after deltas for slabinfo: <slab>: <objects> [ * <size> = <total>] tracefs_inode_cache 144 [* 656 = 94464 ] shmem_inode_cache -23 [* 800 = -18400 ] filp -92 [* 256 = -23552 ] dentry 179 [* 192 = 34368 ] lsm_file_cache -3 [* 32 = -96 ] vm_area_struct -13 [* 184 = -2392 ] trace_event_file 1748 [* 88 = 153824 ] kmalloc-1k -49 [* 1024 = -50176 ] kmalloc-256 -27 [* 256 = -6912 ] kmalloc-128 1864 [* 128 = 238592 ] kmalloc-64 4685 [* 64 = 299840 ] kmalloc-32 -72 [* 32 = -2304 ] kmalloc-16 256 [* 16 = 4096 ] total = 721352 Free memory dropped by 12,084 kB Available memory dropped by 11,976 kB Total slab additions in size: 721,352 bytes That's over 2 MB in savings per instance for free and available memory, and over 1 MB in savings per instance of slab memory. Link: https://lore.kernel.org/linux-trace-kernel/20231003184059.4924468e@gandalf.local.home Link: https://lore.kernel.org/linux-trace-kernel/20231004165007.43d79161@gandalf.local.home Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Ajay Kaher <akaher@vmware.com> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2023-10-04 20:50:07 +00:00
void *data;
struct eventfs_attr attr;
struct kref kref;
eventfs: Save directory inodes in the eventfs_inode structure The eventfs inodes and directories are allocated when referenced. But this leaves the issue of keeping consistent inode numbers and the number is only saved in the inode structure itself. When the inode is no longer referenced, it can be freed. When the file that the inode was representing is referenced again, the inode is once again created, but the inode number needs to be the same as it was before. Just making the inode numbers the same for all files is fine, but that does not work with directories. The find command will check for loops via the inode number and having the same inode number for directories triggers: # find /sys/kernel/tracing find: File system loop detected; '/sys/kernel/debug/tracing/events/initcall/initcall_finish' is part of the same file system loop as '/sys/kernel/debug/tracing/events/initcall'. [..] Linus pointed out that the eventfs_inode structure ends with a single 32bit int, and on 64 bit machines, there's likely a 4 byte hole due to alignment. We can use this hole to store the inode number for the eventfs_inode. All directories in eventfs are represented by an eventfs_inode and that data structure can hold its inode number. That last int was also purposely placed at the end of the structure to prevent holes from within. Now that there's a 4 byte number to hold the inode, both the inode number and the last integer can be moved up in the structure for better cache locality, where the llist and rcu fields can be moved to the end as they are only used when the eventfs_inode is being deleted. Link: https://lore.kernel.org/all/CAMuHMdXKiorg-jiuKoZpfZyDJ3Ynrfb8=X+c7x0Eewxn-YRdCA@mail.gmail.com/ Link: https://lore.kernel.org/linux-trace-kernel/20240122152748.46897388@gandalf.local.home Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Reported-by: Geert Uytterhoeven <geert@linux-m68k.org> Tested-by: Geert Uytterhoeven <geert+renesas@glider.be> Fixes: 53c41052ba31 ("eventfs: Have the inodes all for files and directories all be the same") Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org> Reviewed-by: Kees Cook <keescook@chromium.org>
2024-01-22 20:27:48 +00:00
unsigned int is_freed:1;
unsigned int is_events:1;
unsigned int nr_entries:30;
unsigned int ino;
eventfs: Remove eventfs_file and just use eventfs_inode Instead of having a descriptor for every file represented in the eventfs directory, only have the directory itself represented. Change the API to send in a list of entries that represent all the files in the directory (but not other directories). The entry list contains a name and a callback function that will be used to create the files when they are accessed. struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry *parent, const struct eventfs_entry *entries, int size, void *data); is used for the top level eventfs directory, and returns an eventfs_inode that will be used by: struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode *parent, const struct eventfs_entry *entries, int size, void *data); where both of the above take an array of struct eventfs_entry entries for every file that is in the directory. The entries are defined by: typedef int (*eventfs_callback)(const char *name, umode_t *mode, void **data, const struct file_operations **fops); struct eventfs_entry { const char *name; eventfs_callback callback; }; Where the name is the name of the file and the callback gets called when the file is being created. The callback passes in the name (in case the same callback is used for multiple files), a pointer to the mode, data and fops. The data will be pointing to the data that was passed in eventfs_create_dir() or eventfs_create_events_dir() but may be overridden to point to something else, as it will be used to point to the inode->i_private that is created. The information passed back from the callback is used to create the dentry/inode. If the callback fills the data and the file should be created, it must return a positive number. On zero or negative, the file is ignored. This logic may also be used as a prototype to convert entire pseudo file systems into just-in-time allocation. The "show_events_dentry" file has been updated to show the directories, and any files they have. With just the eventfs_file allocations: Before after deltas for meminfo (in kB): MemFree: -14360 MemAvailable: -14260 Buffers: 40 Cached: 24 Active: 44 Inactive: 48 Inactive(anon): 28 Active(file): 44 Inactive(file): 20 Dirty: -4 AnonPages: 28 Mapped: 4 KReclaimable: 132 Slab: 1604 SReclaimable: 132 SUnreclaim: 1472 Committed_AS: 12 Before after deltas for slabinfo: <slab>: <objects> [ * <size> = <total>] ext4_inode_cache 27 [* 1184 = 31968 ] extent_status 102 [* 40 = 4080 ] tracefs_inode_cache 144 [* 656 = 94464 ] buffer_head 39 [* 104 = 4056 ] shmem_inode_cache 49 [* 800 = 39200 ] filp -53 [* 256 = -13568 ] dentry 251 [* 192 = 48192 ] lsm_file_cache 277 [* 32 = 8864 ] vm_area_struct -14 [* 184 = -2576 ] trace_event_file 1748 [* 88 = 153824 ] kmalloc-1k 35 [* 1024 = 35840 ] kmalloc-256 49 [* 256 = 12544 ] kmalloc-192 -28 [* 192 = -5376 ] kmalloc-128 -30 [* 128 = -3840 ] kmalloc-96 10581 [* 96 = 1015776 ] kmalloc-64 3056 [* 64 = 195584 ] kmalloc-32 1291 [* 32 = 41312 ] kmalloc-16 2310 [* 16 = 36960 ] kmalloc-8 9216 [* 8 = 73728 ] Free memory dropped by 14,360 kB Available memory dropped by 14,260 kB Total slab additions in size: 1,771,032 bytes With this change: Before after deltas for meminfo (in kB): MemFree: -12084 MemAvailable: -11976 Buffers: 32 Cached: 32 Active: 72 Inactive: 168 Inactive(anon): 176 Active(file): 72 Inactive(file): -8 Dirty: 24 AnonPages: 196 Mapped: 8 KReclaimable: 148 Slab: 836 SReclaimable: 148 SUnreclaim: 688 Committed_AS: 324 Before after deltas for slabinfo: <slab>: <objects> [ * <size> = <total>] tracefs_inode_cache 144 [* 656 = 94464 ] shmem_inode_cache -23 [* 800 = -18400 ] filp -92 [* 256 = -23552 ] dentry 179 [* 192 = 34368 ] lsm_file_cache -3 [* 32 = -96 ] vm_area_struct -13 [* 184 = -2392 ] trace_event_file 1748 [* 88 = 153824 ] kmalloc-1k -49 [* 1024 = -50176 ] kmalloc-256 -27 [* 256 = -6912 ] kmalloc-128 1864 [* 128 = 238592 ] kmalloc-64 4685 [* 64 = 299840 ] kmalloc-32 -72 [* 32 = -2304 ] kmalloc-16 256 [* 16 = 4096 ] total = 721352 Free memory dropped by 12,084 kB Available memory dropped by 11,976 kB Total slab additions in size: 721,352 bytes That's over 2 MB in savings per instance for free and available memory, and over 1 MB in savings per instance of slab memory. Link: https://lore.kernel.org/linux-trace-kernel/20231003184059.4924468e@gandalf.local.home Link: https://lore.kernel.org/linux-trace-kernel/20231004165007.43d79161@gandalf.local.home Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Ajay Kaher <akaher@vmware.com> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2023-10-04 20:50:07 +00:00
};
static inline struct tracefs_inode *get_tracefs(const struct inode *inode)
{
return container_of(inode, struct tracefs_inode, vfs_inode);
}
struct dentry *tracefs_start_creating(const char *name, struct dentry *parent);
struct dentry *tracefs_end_creating(struct dentry *dentry);
struct dentry *tracefs_failed_creating(struct dentry *dentry);
struct inode *tracefs_get_inode(struct super_block *sb);
eventfs: Clean up dentry ops and add revalidate function In order for the dentries to stay up-to-date with the eventfs changes, just add a 'd_revalidate' function that checks the 'is_freed' bit. Also, clean up the dentry release to actually use d_release() rather than the slightly odd d_iput() function. We don't care about the inode, all we want to do is to get rid of the refcount to the eventfs data added by dentry->d_fsdata. It would probably be cleaner to make eventfs its own filesystem, or at least set its own dentry ops when looking up eventfs files. But as it is, only eventfs dentries use d_fsdata, so we don't really need to split these things up by use. Another thing that might be worth doing is to make all eventfs lookups mark their dentries as not worth caching. We could do that with d_delete(), but the DCACHE_DONTCACHE flag would likely be even better. As it is, the dentries are all freeable, but they only tend to get freed at memory pressure rather than more proactively. But that's a separate issue. Link: https://lore.kernel.org/linux-trace-kernel/202401291043.e62e89dc-oliver.sang@intel.com/ Link: https://lore.kernel.org/linux-trace-kernel/20240131185513.124644253@goodmis.org Cc: stable@vger.kernel.org Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Al Viro <viro@ZenIV.linux.org.uk> Cc: Ajay Kaher <ajay.kaher@broadcom.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Fixes: c1504e510238 ("eventfs: Implement eventfs dir creation functions") Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2024-01-31 18:49:24 +00:00
void eventfs_d_release(struct dentry *dentry);
#endif /* _TRACEFS_INTERNAL_H */