mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-27 03:10:12 +00:00
![Mike Christie](/assets/img/avatar_default.png)
There are several storage drivers like dm-multipath, iscsi, tcmu-runner, amd nbd that have userspace components that can run in the IO path. For example, iscsi and nbd's userspace deamons may need to recreate a socket and/or send IO on it, and dm-multipath's daemon multipathd may need to send SG IO or read/write IO to figure out the state of paths and re-set them up. In the kernel these drivers have access to GFP_NOIO/GFP_NOFS and the memalloc_*_save/restore functions to control the allocation behavior, but for userspace we would end up hitting an allocation that ended up writing data back to the same device we are trying to allocate for. The device is then in a state of deadlock, because to execute IO the device needs to allocate memory, but to allocate memory the memory layers want execute IO to the device. Here is an example with nbd using a local userspace daemon that performs network IO to a remote server. We are using XFS on top of the nbd device, but it can happen with any FS or other modules layered on top of the nbd device that can write out data to free memory. Here a nbd daemon helper thread, msgr-worker-1, is performing a write/sendmsg on a socket to execute a request. This kicks off a reclaim operation which results in a WRITE to the nbd device and the nbd thread calling back into the mm layer. [ 1626.609191] msgr-worker-1 D 0 1026 1 0x00004000 [ 1626.609193] Call Trace: [ 1626.609195] ? __schedule+0x29b/0x630 [ 1626.609197] ? wait_for_completion+0xe0/0x170 [ 1626.609198] schedule+0x30/0xb0 [ 1626.609200] schedule_timeout+0x1f6/0x2f0 [ 1626.609202] ? blk_finish_plug+0x21/0x2e [ 1626.609204] ? _xfs_buf_ioapply+0x2e6/0x410 [ 1626.609206] ? wait_for_completion+0xe0/0x170 [ 1626.609208] wait_for_completion+0x108/0x170 [ 1626.609210] ? wake_up_q+0x70/0x70 [ 1626.609212] ? __xfs_buf_submit+0x12e/0x250 [ 1626.609214] ? xfs_bwrite+0x25/0x60 [ 1626.609215] xfs_buf_iowait+0x22/0xf0 [ 1626.609218] __xfs_buf_submit+0x12e/0x250 [ 1626.609220] xfs_bwrite+0x25/0x60 [ 1626.609222] xfs_reclaim_inode+0x2e8/0x310 [ 1626.609224] xfs_reclaim_inodes_ag+0x1b6/0x300 [ 1626.609227] xfs_reclaim_inodes_nr+0x31/0x40 [ 1626.609228] super_cache_scan+0x152/0x1a0 [ 1626.609231] do_shrink_slab+0x12c/0x2d0 [ 1626.609233] shrink_slab+0x9c/0x2a0 [ 1626.609235] shrink_node+0xd7/0x470 [ 1626.609237] do_try_to_free_pages+0xbf/0x380 [ 1626.609240] try_to_free_pages+0xd9/0x1f0 [ 1626.609245] __alloc_pages_slowpath+0x3a4/0xd30 [ 1626.609251] ? ___slab_alloc+0x238/0x560 [ 1626.609254] __alloc_pages_nodemask+0x30c/0x350 [ 1626.609259] skb_page_frag_refill+0x97/0xd0 [ 1626.609274] sk_page_frag_refill+0x1d/0x80 [ 1626.609279] tcp_sendmsg_locked+0x2bb/0xdd0 [ 1626.609304] tcp_sendmsg+0x27/0x40 [ 1626.609307] sock_sendmsg+0x54/0x60 [ 1626.609308] ___sys_sendmsg+0x29f/0x320 [ 1626.609313] ? sock_poll+0x66/0xb0 [ 1626.609318] ? ep_item_poll.isra.15+0x40/0xc0 [ 1626.609320] ? ep_send_events_proc+0xe6/0x230 [ 1626.609322] ? hrtimer_try_to_cancel+0x54/0xf0 [ 1626.609324] ? ep_read_events_proc+0xc0/0xc0 [ 1626.609326] ? _raw_write_unlock_irq+0xa/0x20 [ 1626.609327] ? ep_scan_ready_list.constprop.19+0x218/0x230 [ 1626.609329] ? __hrtimer_init+0xb0/0xb0 [ 1626.609331] ? _raw_spin_unlock_irq+0xa/0x20 [ 1626.609334] ? ep_poll+0x26c/0x4a0 [ 1626.609337] ? tcp_tsq_write.part.54+0xa0/0xa0 [ 1626.609339] ? release_sock+0x43/0x90 [ 1626.609341] ? _raw_spin_unlock_bh+0xa/0x20 [ 1626.609342] __sys_sendmsg+0x47/0x80 [ 1626.609347] do_syscall_64+0x5f/0x1c0 [ 1626.609349] ? prepare_exit_to_usermode+0x75/0xa0 [ 1626.609351] entry_SYSCALL_64_after_hwframe+0x44/0xa9 This patch adds a new prctl command that daemons can use after they have done their initial setup, and before they start to do allocations that are in the IO path. It sets the PF_MEMALLOC_NOIO and PF_LESS_THROTTLE flags so both userspace block and FS threads can use it to avoid the allocation recursion and try to prevent from being throttled while writing out data to free up memory. Signed-off-by: Mike Christie <mchristi@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Tested-by: Masato Suzuki <masato.suzuki@wdc.com> Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Bart Van Assche <bvanassche@acm.org> Reviewed-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Link: https://lore.kernel.org/r/20191112001900.9206-1-mchristi@redhat.com Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
383 lines
12 KiB
C
383 lines
12 KiB
C
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
|
|
/*
|
|
* This is <linux/capability.h>
|
|
*
|
|
* Andrew G. Morgan <morgan@kernel.org>
|
|
* Alexander Kjeldaas <astor@guardian.no>
|
|
* with help from Aleph1, Roland Buresund and Andrew Main.
|
|
*
|
|
* See here for the libcap library ("POSIX draft" compliance):
|
|
*
|
|
* ftp://www.kernel.org/pub/linux/libs/security/linux-privs/kernel-2.6/
|
|
*/
|
|
|
|
#ifndef _UAPI_LINUX_CAPABILITY_H
|
|
#define _UAPI_LINUX_CAPABILITY_H
|
|
|
|
#include <linux/types.h>
|
|
|
|
/* User-level do most of the mapping between kernel and user
|
|
capabilities based on the version tag given by the kernel. The
|
|
kernel might be somewhat backwards compatible, but don't bet on
|
|
it. */
|
|
|
|
/* Note, cap_t, is defined by POSIX (draft) to be an "opaque" pointer to
|
|
a set of three capability sets. The transposition of 3*the
|
|
following structure to such a composite is better handled in a user
|
|
library since the draft standard requires the use of malloc/free
|
|
etc.. */
|
|
|
|
#define _LINUX_CAPABILITY_VERSION_1 0x19980330
|
|
#define _LINUX_CAPABILITY_U32S_1 1
|
|
|
|
#define _LINUX_CAPABILITY_VERSION_2 0x20071026 /* deprecated - use v3 */
|
|
#define _LINUX_CAPABILITY_U32S_2 2
|
|
|
|
#define _LINUX_CAPABILITY_VERSION_3 0x20080522
|
|
#define _LINUX_CAPABILITY_U32S_3 2
|
|
|
|
typedef struct __user_cap_header_struct {
|
|
__u32 version;
|
|
int pid;
|
|
} __user *cap_user_header_t;
|
|
|
|
typedef struct __user_cap_data_struct {
|
|
__u32 effective;
|
|
__u32 permitted;
|
|
__u32 inheritable;
|
|
} __user *cap_user_data_t;
|
|
|
|
|
|
#define VFS_CAP_REVISION_MASK 0xFF000000
|
|
#define VFS_CAP_REVISION_SHIFT 24
|
|
#define VFS_CAP_FLAGS_MASK ~VFS_CAP_REVISION_MASK
|
|
#define VFS_CAP_FLAGS_EFFECTIVE 0x000001
|
|
|
|
#define VFS_CAP_REVISION_1 0x01000000
|
|
#define VFS_CAP_U32_1 1
|
|
#define XATTR_CAPS_SZ_1 (sizeof(__le32)*(1 + 2*VFS_CAP_U32_1))
|
|
|
|
#define VFS_CAP_REVISION_2 0x02000000
|
|
#define VFS_CAP_U32_2 2
|
|
#define XATTR_CAPS_SZ_2 (sizeof(__le32)*(1 + 2*VFS_CAP_U32_2))
|
|
|
|
#define VFS_CAP_REVISION_3 0x03000000
|
|
#define VFS_CAP_U32_3 2
|
|
#define XATTR_CAPS_SZ_3 (sizeof(__le32)*(2 + 2*VFS_CAP_U32_3))
|
|
|
|
#define XATTR_CAPS_SZ XATTR_CAPS_SZ_3
|
|
#define VFS_CAP_U32 VFS_CAP_U32_3
|
|
#define VFS_CAP_REVISION VFS_CAP_REVISION_3
|
|
|
|
struct vfs_cap_data {
|
|
__le32 magic_etc; /* Little endian */
|
|
struct {
|
|
__le32 permitted; /* Little endian */
|
|
__le32 inheritable; /* Little endian */
|
|
} data[VFS_CAP_U32];
|
|
};
|
|
|
|
/*
|
|
* same as vfs_cap_data but with a rootid at the end
|
|
*/
|
|
struct vfs_ns_cap_data {
|
|
__le32 magic_etc;
|
|
struct {
|
|
__le32 permitted; /* Little endian */
|
|
__le32 inheritable; /* Little endian */
|
|
} data[VFS_CAP_U32];
|
|
__le32 rootid;
|
|
};
|
|
|
|
#ifndef __KERNEL__
|
|
|
|
/*
|
|
* Backwardly compatible definition for source code - trapped in a
|
|
* 32-bit world. If you find you need this, please consider using
|
|
* libcap to untrap yourself...
|
|
*/
|
|
#define _LINUX_CAPABILITY_VERSION _LINUX_CAPABILITY_VERSION_1
|
|
#define _LINUX_CAPABILITY_U32S _LINUX_CAPABILITY_U32S_1
|
|
|
|
#endif
|
|
|
|
|
|
/**
|
|
** POSIX-draft defined capabilities.
|
|
**/
|
|
|
|
/* In a system with the [_POSIX_CHOWN_RESTRICTED] option defined, this
|
|
overrides the restriction of changing file ownership and group
|
|
ownership. */
|
|
|
|
#define CAP_CHOWN 0
|
|
|
|
/* Override all DAC access, including ACL execute access if
|
|
[_POSIX_ACL] is defined. Excluding DAC access covered by
|
|
CAP_LINUX_IMMUTABLE. */
|
|
|
|
#define CAP_DAC_OVERRIDE 1
|
|
|
|
/* Overrides all DAC restrictions regarding read and search on files
|
|
and directories, including ACL restrictions if [_POSIX_ACL] is
|
|
defined. Excluding DAC access covered by CAP_LINUX_IMMUTABLE. */
|
|
|
|
#define CAP_DAC_READ_SEARCH 2
|
|
|
|
/* Overrides all restrictions about allowed operations on files, where
|
|
file owner ID must be equal to the user ID, except where CAP_FSETID
|
|
is applicable. It doesn't override MAC and DAC restrictions. */
|
|
|
|
#define CAP_FOWNER 3
|
|
|
|
/* Overrides the following restrictions that the effective user ID
|
|
shall match the file owner ID when setting the S_ISUID and S_ISGID
|
|
bits on that file; that the effective group ID (or one of the
|
|
supplementary group IDs) shall match the file owner ID when setting
|
|
the S_ISGID bit on that file; that the S_ISUID and S_ISGID bits are
|
|
cleared on successful return from chown(2) (not implemented). */
|
|
|
|
#define CAP_FSETID 4
|
|
|
|
/* Overrides the restriction that the real or effective user ID of a
|
|
process sending a signal must match the real or effective user ID
|
|
of the process receiving the signal. */
|
|
|
|
#define CAP_KILL 5
|
|
|
|
/* Allows setgid(2) manipulation */
|
|
/* Allows setgroups(2) */
|
|
/* Allows forged gids on socket credentials passing. */
|
|
|
|
#define CAP_SETGID 6
|
|
|
|
/* Allows set*uid(2) manipulation (including fsuid). */
|
|
/* Allows forged pids on socket credentials passing. */
|
|
|
|
#define CAP_SETUID 7
|
|
|
|
|
|
/**
|
|
** Linux-specific capabilities
|
|
**/
|
|
|
|
/* Without VFS support for capabilities:
|
|
* Transfer any capability in your permitted set to any pid,
|
|
* remove any capability in your permitted set from any pid
|
|
* With VFS support for capabilities (neither of above, but)
|
|
* Add any capability from current's capability bounding set
|
|
* to the current process' inheritable set
|
|
* Allow taking bits out of capability bounding set
|
|
* Allow modification of the securebits for a process
|
|
*/
|
|
|
|
#define CAP_SETPCAP 8
|
|
|
|
/* Allow modification of S_IMMUTABLE and S_APPEND file attributes */
|
|
|
|
#define CAP_LINUX_IMMUTABLE 9
|
|
|
|
/* Allows binding to TCP/UDP sockets below 1024 */
|
|
/* Allows binding to ATM VCIs below 32 */
|
|
|
|
#define CAP_NET_BIND_SERVICE 10
|
|
|
|
/* Allow broadcasting, listen to multicast */
|
|
|
|
#define CAP_NET_BROADCAST 11
|
|
|
|
/* Allow interface configuration */
|
|
/* Allow administration of IP firewall, masquerading and accounting */
|
|
/* Allow setting debug option on sockets */
|
|
/* Allow modification of routing tables */
|
|
/* Allow setting arbitrary process / process group ownership on
|
|
sockets */
|
|
/* Allow binding to any address for transparent proxying (also via NET_RAW) */
|
|
/* Allow setting TOS (type of service) */
|
|
/* Allow setting promiscuous mode */
|
|
/* Allow clearing driver statistics */
|
|
/* Allow multicasting */
|
|
/* Allow read/write of device-specific registers */
|
|
/* Allow activation of ATM control sockets */
|
|
|
|
#define CAP_NET_ADMIN 12
|
|
|
|
/* Allow use of RAW sockets */
|
|
/* Allow use of PACKET sockets */
|
|
/* Allow binding to any address for transparent proxying (also via NET_ADMIN) */
|
|
|
|
#define CAP_NET_RAW 13
|
|
|
|
/* Allow locking of shared memory segments */
|
|
/* Allow mlock and mlockall (which doesn't really have anything to do
|
|
with IPC) */
|
|
|
|
#define CAP_IPC_LOCK 14
|
|
|
|
/* Override IPC ownership checks */
|
|
|
|
#define CAP_IPC_OWNER 15
|
|
|
|
/* Insert and remove kernel modules - modify kernel without limit */
|
|
#define CAP_SYS_MODULE 16
|
|
|
|
/* Allow ioperm/iopl access */
|
|
/* Allow sending USB messages to any device via /dev/bus/usb */
|
|
|
|
#define CAP_SYS_RAWIO 17
|
|
|
|
/* Allow use of chroot() */
|
|
|
|
#define CAP_SYS_CHROOT 18
|
|
|
|
/* Allow ptrace() of any process */
|
|
|
|
#define CAP_SYS_PTRACE 19
|
|
|
|
/* Allow configuration of process accounting */
|
|
|
|
#define CAP_SYS_PACCT 20
|
|
|
|
/* Allow configuration of the secure attention key */
|
|
/* Allow administration of the random device */
|
|
/* Allow examination and configuration of disk quotas */
|
|
/* Allow setting the domainname */
|
|
/* Allow setting the hostname */
|
|
/* Allow calling bdflush() */
|
|
/* Allow mount() and umount(), setting up new smb connection */
|
|
/* Allow some autofs root ioctls */
|
|
/* Allow nfsservctl */
|
|
/* Allow VM86_REQUEST_IRQ */
|
|
/* Allow to read/write pci config on alpha */
|
|
/* Allow irix_prctl on mips (setstacksize) */
|
|
/* Allow flushing all cache on m68k (sys_cacheflush) */
|
|
/* Allow removing semaphores */
|
|
/* Used instead of CAP_CHOWN to "chown" IPC message queues, semaphores
|
|
and shared memory */
|
|
/* Allow locking/unlocking of shared memory segment */
|
|
/* Allow turning swap on/off */
|
|
/* Allow forged pids on socket credentials passing */
|
|
/* Allow setting readahead and flushing buffers on block devices */
|
|
/* Allow setting geometry in floppy driver */
|
|
/* Allow turning DMA on/off in xd driver */
|
|
/* Allow administration of md devices (mostly the above, but some
|
|
extra ioctls) */
|
|
/* Allow tuning the ide driver */
|
|
/* Allow access to the nvram device */
|
|
/* Allow administration of apm_bios, serial and bttv (TV) device */
|
|
/* Allow manufacturer commands in isdn CAPI support driver */
|
|
/* Allow reading non-standardized portions of pci configuration space */
|
|
/* Allow DDI debug ioctl on sbpcd driver */
|
|
/* Allow setting up serial ports */
|
|
/* Allow sending raw qic-117 commands */
|
|
/* Allow enabling/disabling tagged queuing on SCSI controllers and sending
|
|
arbitrary SCSI commands */
|
|
/* Allow setting encryption key on loopback filesystem */
|
|
/* Allow setting zone reclaim policy */
|
|
|
|
#define CAP_SYS_ADMIN 21
|
|
|
|
/* Allow use of reboot() */
|
|
|
|
#define CAP_SYS_BOOT 22
|
|
|
|
/* Allow raising priority and setting priority on other (different
|
|
UID) processes */
|
|
/* Allow use of FIFO and round-robin (realtime) scheduling on own
|
|
processes and setting the scheduling algorithm used by another
|
|
process. */
|
|
/* Allow setting cpu affinity on other processes */
|
|
|
|
#define CAP_SYS_NICE 23
|
|
|
|
/* Override resource limits. Set resource limits. */
|
|
/* Override quota limits. */
|
|
/* Override reserved space on ext2 filesystem */
|
|
/* Modify data journaling mode on ext3 filesystem (uses journaling
|
|
resources) */
|
|
/* NOTE: ext2 honors fsuid when checking for resource overrides, so
|
|
you can override using fsuid too */
|
|
/* Override size restrictions on IPC message queues */
|
|
/* Allow more than 64hz interrupts from the real-time clock */
|
|
/* Override max number of consoles on console allocation */
|
|
/* Override max number of keymaps */
|
|
/* Control memory reclaim behavior */
|
|
|
|
#define CAP_SYS_RESOURCE 24
|
|
|
|
/* Allow manipulation of system clock */
|
|
/* Allow irix_stime on mips */
|
|
/* Allow setting the real-time clock */
|
|
|
|
#define CAP_SYS_TIME 25
|
|
|
|
/* Allow configuration of tty devices */
|
|
/* Allow vhangup() of tty */
|
|
|
|
#define CAP_SYS_TTY_CONFIG 26
|
|
|
|
/* Allow the privileged aspects of mknod() */
|
|
|
|
#define CAP_MKNOD 27
|
|
|
|
/* Allow taking of leases on files */
|
|
|
|
#define CAP_LEASE 28
|
|
|
|
/* Allow writing the audit log via unicast netlink socket */
|
|
|
|
#define CAP_AUDIT_WRITE 29
|
|
|
|
/* Allow configuration of audit via unicast netlink socket */
|
|
|
|
#define CAP_AUDIT_CONTROL 30
|
|
|
|
#define CAP_SETFCAP 31
|
|
|
|
/* Override MAC access.
|
|
The base kernel enforces no MAC policy.
|
|
An LSM may enforce a MAC policy, and if it does and it chooses
|
|
to implement capability based overrides of that policy, this is
|
|
the capability it should use to do so. */
|
|
|
|
#define CAP_MAC_OVERRIDE 32
|
|
|
|
/* Allow MAC configuration or state changes.
|
|
The base kernel requires no MAC configuration.
|
|
An LSM may enforce a MAC policy, and if it does and it chooses
|
|
to implement capability based checks on modifications to that
|
|
policy or the data required to maintain it, this is the
|
|
capability it should use to do so. */
|
|
|
|
#define CAP_MAC_ADMIN 33
|
|
|
|
/* Allow configuring the kernel's syslog (printk behaviour) */
|
|
|
|
#define CAP_SYSLOG 34
|
|
|
|
/* Allow triggering something that will wake the system */
|
|
|
|
#define CAP_WAKE_ALARM 35
|
|
|
|
/* Allow preventing system suspends */
|
|
|
|
#define CAP_BLOCK_SUSPEND 36
|
|
|
|
/* Allow reading the audit log via multicast netlink socket */
|
|
|
|
#define CAP_AUDIT_READ 37
|
|
|
|
|
|
#define CAP_LAST_CAP CAP_AUDIT_READ
|
|
|
|
#define cap_valid(x) ((x) >= 0 && (x) <= CAP_LAST_CAP)
|
|
|
|
/*
|
|
* Bit location of each capability (used by user-space library and kernel)
|
|
*/
|
|
|
|
#define CAP_TO_INDEX(x) ((x) >> 5) /* 1 << 5 == bits in __u32 */
|
|
#define CAP_TO_MASK(x) (1 << ((x) & 31)) /* mask for indexed __u32 */
|
|
|
|
|
|
#endif /* _UAPI_LINUX_CAPABILITY_H */
|