linux-stable/include/uapi/linux/prctl.h
Mike Christie 8d19f1c8e1
prctl: PR_{G,S}ET_IO_FLUSHER to support controlling memory reclaim
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>
2020-01-28 10:09:51 +01:00

241 lines
8 KiB
C

/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
#ifndef _LINUX_PRCTL_H
#define _LINUX_PRCTL_H
#include <linux/types.h>
/* Values to pass as first argument to prctl() */
#define PR_SET_PDEATHSIG 1 /* Second arg is a signal */
#define PR_GET_PDEATHSIG 2 /* Second arg is a ptr to return the signal */
/* Get/set current->mm->dumpable */
#define PR_GET_DUMPABLE 3
#define PR_SET_DUMPABLE 4
/* Get/set unaligned access control bits (if meaningful) */
#define PR_GET_UNALIGN 5
#define PR_SET_UNALIGN 6
# define PR_UNALIGN_NOPRINT 1 /* silently fix up unaligned user accesses */
# define PR_UNALIGN_SIGBUS 2 /* generate SIGBUS on unaligned user access */
/* Get/set whether or not to drop capabilities on setuid() away from
* uid 0 (as per security/commoncap.c) */
#define PR_GET_KEEPCAPS 7
#define PR_SET_KEEPCAPS 8
/* Get/set floating-point emulation control bits (if meaningful) */
#define PR_GET_FPEMU 9
#define PR_SET_FPEMU 10
# define PR_FPEMU_NOPRINT 1 /* silently emulate fp operations accesses */
# define PR_FPEMU_SIGFPE 2 /* don't emulate fp operations, send SIGFPE instead */
/* Get/set floating-point exception mode (if meaningful) */
#define PR_GET_FPEXC 11
#define PR_SET_FPEXC 12
# define PR_FP_EXC_SW_ENABLE 0x80 /* Use FPEXC for FP exception enables */
# define PR_FP_EXC_DIV 0x010000 /* floating point divide by zero */
# define PR_FP_EXC_OVF 0x020000 /* floating point overflow */
# define PR_FP_EXC_UND 0x040000 /* floating point underflow */
# define PR_FP_EXC_RES 0x080000 /* floating point inexact result */
# define PR_FP_EXC_INV 0x100000 /* floating point invalid operation */
# define PR_FP_EXC_DISABLED 0 /* FP exceptions disabled */
# define PR_FP_EXC_NONRECOV 1 /* async non-recoverable exc. mode */
# define PR_FP_EXC_ASYNC 2 /* async recoverable exception mode */
# define PR_FP_EXC_PRECISE 3 /* precise exception mode */
/* Get/set whether we use statistical process timing or accurate timestamp
* based process timing */
#define PR_GET_TIMING 13
#define PR_SET_TIMING 14
# define PR_TIMING_STATISTICAL 0 /* Normal, traditional,
statistical process timing */
# define PR_TIMING_TIMESTAMP 1 /* Accurate timestamp based
process timing */
#define PR_SET_NAME 15 /* Set process name */
#define PR_GET_NAME 16 /* Get process name */
/* Get/set process endian */
#define PR_GET_ENDIAN 19
#define PR_SET_ENDIAN 20
# define PR_ENDIAN_BIG 0
# define PR_ENDIAN_LITTLE 1 /* True little endian mode */
# define PR_ENDIAN_PPC_LITTLE 2 /* "PowerPC" pseudo little endian */
/* Get/set process seccomp mode */
#define PR_GET_SECCOMP 21
#define PR_SET_SECCOMP 22
/* Get/set the capability bounding set (as per security/commoncap.c) */
#define PR_CAPBSET_READ 23
#define PR_CAPBSET_DROP 24
/* Get/set the process' ability to use the timestamp counter instruction */
#define PR_GET_TSC 25
#define PR_SET_TSC 26
# define PR_TSC_ENABLE 1 /* allow the use of the timestamp counter */
# define PR_TSC_SIGSEGV 2 /* throw a SIGSEGV instead of reading the TSC */
/* Get/set securebits (as per security/commoncap.c) */
#define PR_GET_SECUREBITS 27
#define PR_SET_SECUREBITS 28
/*
* Get/set the timerslack as used by poll/select/nanosleep
* A value of 0 means "use default"
*/
#define PR_SET_TIMERSLACK 29
#define PR_GET_TIMERSLACK 30
#define PR_TASK_PERF_EVENTS_DISABLE 31
#define PR_TASK_PERF_EVENTS_ENABLE 32
/*
* Set early/late kill mode for hwpoison memory corruption.
* This influences when the process gets killed on a memory corruption.
*/
#define PR_MCE_KILL 33
# define PR_MCE_KILL_CLEAR 0
# define PR_MCE_KILL_SET 1
# define PR_MCE_KILL_LATE 0
# define PR_MCE_KILL_EARLY 1
# define PR_MCE_KILL_DEFAULT 2
#define PR_MCE_KILL_GET 34
/*
* Tune up process memory map specifics.
*/
#define PR_SET_MM 35
# define PR_SET_MM_START_CODE 1
# define PR_SET_MM_END_CODE 2
# define PR_SET_MM_START_DATA 3
# define PR_SET_MM_END_DATA 4
# define PR_SET_MM_START_STACK 5
# define PR_SET_MM_START_BRK 6
# define PR_SET_MM_BRK 7
# define PR_SET_MM_ARG_START 8
# define PR_SET_MM_ARG_END 9
# define PR_SET_MM_ENV_START 10
# define PR_SET_MM_ENV_END 11
# define PR_SET_MM_AUXV 12
# define PR_SET_MM_EXE_FILE 13
# define PR_SET_MM_MAP 14
# define PR_SET_MM_MAP_SIZE 15
/*
* This structure provides new memory descriptor
* map which mostly modifies /proc/pid/stat[m]
* output for a task. This mostly done in a
* sake of checkpoint/restore functionality.
*/
struct prctl_mm_map {
__u64 start_code; /* code section bounds */
__u64 end_code;
__u64 start_data; /* data section bounds */
__u64 end_data;
__u64 start_brk; /* heap for brk() syscall */
__u64 brk;
__u64 start_stack; /* stack starts at */
__u64 arg_start; /* command line arguments bounds */
__u64 arg_end;
__u64 env_start; /* environment variables bounds */
__u64 env_end;
__u64 *auxv; /* auxiliary vector */
__u32 auxv_size; /* vector size */
__u32 exe_fd; /* /proc/$pid/exe link file */
};
/*
* Set specific pid that is allowed to ptrace the current task.
* A value of 0 mean "no process".
*/
#define PR_SET_PTRACER 0x59616d61
# define PR_SET_PTRACER_ANY ((unsigned long)-1)
#define PR_SET_CHILD_SUBREAPER 36
#define PR_GET_CHILD_SUBREAPER 37
/*
* If no_new_privs is set, then operations that grant new privileges (i.e.
* execve) will either fail or not grant them. This affects suid/sgid,
* file capabilities, and LSMs.
*
* Operations that merely manipulate or drop existing privileges (setresuid,
* capset, etc.) will still work. Drop those privileges if you want them gone.
*
* Changing LSM security domain is considered a new privilege. So, for example,
* asking selinux for a specific new context (e.g. with runcon) will result
* in execve returning -EPERM.
*
* See Documentation/userspace-api/no_new_privs.rst for more details.
*/
#define PR_SET_NO_NEW_PRIVS 38
#define PR_GET_NO_NEW_PRIVS 39
#define PR_GET_TID_ADDRESS 40
#define PR_SET_THP_DISABLE 41
#define PR_GET_THP_DISABLE 42
/*
* No longer implemented, but left here to ensure the numbers stay reserved:
*/
#define PR_MPX_ENABLE_MANAGEMENT 43
#define PR_MPX_DISABLE_MANAGEMENT 44
#define PR_SET_FP_MODE 45
#define PR_GET_FP_MODE 46
# define PR_FP_MODE_FR (1 << 0) /* 64b FP registers */
# define PR_FP_MODE_FRE (1 << 1) /* 32b compatibility */
/* Control the ambient capability set */
#define PR_CAP_AMBIENT 47
# define PR_CAP_AMBIENT_IS_SET 1
# define PR_CAP_AMBIENT_RAISE 2
# define PR_CAP_AMBIENT_LOWER 3
# define PR_CAP_AMBIENT_CLEAR_ALL 4
/* arm64 Scalable Vector Extension controls */
/* Flag values must be kept in sync with ptrace NT_ARM_SVE interface */
#define PR_SVE_SET_VL 50 /* set task vector length */
# define PR_SVE_SET_VL_ONEXEC (1 << 18) /* defer effect until exec */
#define PR_SVE_GET_VL 51 /* get task vector length */
/* Bits common to PR_SVE_SET_VL and PR_SVE_GET_VL */
# define PR_SVE_VL_LEN_MASK 0xffff
# define PR_SVE_VL_INHERIT (1 << 17) /* inherit across exec */
/* Per task speculation control */
#define PR_GET_SPECULATION_CTRL 52
#define PR_SET_SPECULATION_CTRL 53
/* Speculation control variants */
# define PR_SPEC_STORE_BYPASS 0
# define PR_SPEC_INDIRECT_BRANCH 1
/* Return and control values for PR_SET/GET_SPECULATION_CTRL */
# define PR_SPEC_NOT_AFFECTED 0
# define PR_SPEC_PRCTL (1UL << 0)
# define PR_SPEC_ENABLE (1UL << 1)
# define PR_SPEC_DISABLE (1UL << 2)
# define PR_SPEC_FORCE_DISABLE (1UL << 3)
# define PR_SPEC_DISABLE_NOEXEC (1UL << 4)
/* Reset arm64 pointer authentication keys */
#define PR_PAC_RESET_KEYS 54
# define PR_PAC_APIAKEY (1UL << 0)
# define PR_PAC_APIBKEY (1UL << 1)
# define PR_PAC_APDAKEY (1UL << 2)
# define PR_PAC_APDBKEY (1UL << 3)
# define PR_PAC_APGAKEY (1UL << 4)
/* Tagged user address controls for arm64 */
#define PR_SET_TAGGED_ADDR_CTRL 55
#define PR_GET_TAGGED_ADDR_CTRL 56
# define PR_TAGGED_ADDR_ENABLE (1UL << 0)
/* Control reclaim behavior when allocating memory */
#define PR_SET_IO_FLUSHER 57
#define PR_GET_IO_FLUSHER 58
#endif /* _LINUX_PRCTL_H */