fs: use current->mm for io_uring
Subsystems (14)
PATCH 1/2 fs: use current->mm for io_uring
per-request by Jens,
https://lore.kernel.org/io-uring/[email protected]/
Andrew, please fold this into "mm/madvise: pass task and mm to do_madvise"
--- fs/io_uring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
fs/io_uring.c +1 -1
@@ -3267,7 +3267,7 @@ static int io_madvise(struct io_kiocb *req, bool force_nonblock)if (force_nonblock)return -EAGAIN ; - ret =do_madvise (NULL , req->work.mm, ma->addr, ma->len, ma->advice); + ret =do_madvise (NULL , current->mm, ma->addr, ma->len, ma->advice);if (ret <0 )req_set_fail_links (req);io_cqring_add_event (req, ret);
Signature · 1 line
2.26.1.301.g55bc3eb7cb9-goog
PATCH 2/2 mm: support vector address ranges for process_madvise
This patch extends a) process_madvise(2) support vector address ranges in a system call and then b) support the vector address ranges to local process as well as external process.
Android app has thousands of vmas due to zygote so it's totally waste of CPU and power if we should call the syscall one by one for each vma. (With testing 2000-vma syscall vs 1-vector syscall, it showed 15% performance improvement. I think it would be bigger in real practice because the testing ran very cache friendly environment).
Another potential use case for the vector range is to amortize the cost of TLB shootdowns for multiple ranges when using MADV_DONTNEED; this could benefit users like TCP receive zerocopy and malloc implementations. In future, we could find more usecases for other advises so let's make it happens as API since we introduce a new syscall at this moment. With that, existing madvise(2) user could replace it with process_madvise(2) with their own pid if they want to have batch address ranges support feature.
So finally, the API is as follows,
ssize_t process_madvise(idtype_t idtype, id_t id,
const struct iovec *iovec, unsigned long vlen,
int advice, unsigned long flags);DESCRIPTION
The process_madvise() system call is used to give advice or directions to the kernel about the address ranges from external process as well as local process. It provides the advice to address ranges of process described by iovec and vlen. The goal of such advice is to improve system or application performance.
The idtype and id arguments select the target process to be advised as follows:
idtype == P_PID
select the process whose process ID matches id
idtype == P_PIDFD
select the process referred to by the PID file descriptor specified in id. (See pidofd_open(2) for further information)
The pointer iovec points to an array of iovec structures, defined in <sys/uio.h> as:
struct iovec {
void *iov_base; /* starting address */
size_t iov_len; /* number of bytes to be advised */
};
The iovec describes address ranges beginning at address(iov_base) and with size length of bytes(iov_len).
The vlen represents the number of elements in iovec.
The advice is indicated in the advice argument, which is one of the following at this moment if the target process specified by idtype and id is external.
MADV_COLD
MADV_PAGEOUT
MADV_MERGEABLE
MADV_UNMERGEABLE
Permission to provide a hint to external process is governed by a ptrace access mode PTRACE_MODE_ATTACH_FSCREDS check; see ptrace(2).
The process_madvise supports every advice madvise(2) has if target process is in same thread group with calling process so user could use process_madvise(2) to extend existing madvise(2) to support vector address ranges.
RETURN VALUE
On success, process_madvise() returns the number of bytes advised. This return value may be less than the total number of requested bytes, if an error occurred. The caller should check return value to determine whether a partial advice occurred.
--- mm/madvise.c | 47 ++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 40 insertions(+), 7 deletions(-)
mm/madvise.c +40 -7
@@ -1195,20 +1195,39 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)return do_madvise (current, current->mm, start, len_in, behavior); } -SYSCALL_DEFINE6(process_madvise, int, which, pid_t, upid, unsigned long, start, - size_t, len_in, int, behavior, unsigned long, flags) +static int do_process_madvise (struct task_struct *target_task, +struct mm_struct *mm,struct iov_iter *iter,int behavior) { -int ret; +struct iovec iovec; +int ret =0 ; + +while (iov_iter_count (iter)) { + iovec =iov_iter_iovec (iter); + ret =do_madvise (target_task, mm, (unsigned long )iovec.iov_base, + iovec.iov_len, behavior); +if (ret <0 ) +break ; +iov_iter_advance (iter, iovec.iov_len); + } + +return ret; +} + +SYSCALL_DEFINE6 (process_madvise, int, which, pid_t, upid, + const struct iovec __user *, vec, unsigned long, vlen, + int, behavior, unsigned long, flags) +{ +ssize_t ret;struct pid *pid;struct task_struct *task;struct mm_struct *mm; +struct iovec iovstack[UIO_FASTIOV ]; +struct iovec *iov = iovstack; +struct iov_iter iter;if (flags !=0 )return -EINVAL ; -if (!process_madvise_behavior_valid (behavior)) -return -EINVAL ; -switch (which) {case P_PID :if (upid <=0 )
@@ -1236,13 +1255,27 @@ SYSCALL_DEFINE6(process_madvise, int, which, pid_t, upid, unsigned long, start, goto put_pid; } +if (task->mm != current->mm && + !process_madvise_behavior_valid (behavior)) { + ret = -EINVAL ; + goto release_task; + } + mm =mm_access (task,PTRACE_MODE_ATTACH_FSCREDS );if (IS_ERR_OR_NULL (mm)) { ret =IS_ERR (mm) ?PTR_ERR (mm) : -ESRCH ; goto release_task; } - ret =do_madvise (task, mm, start, len_in, behavior); + ret =import_iovec (READ , vec, vlen,ARRAY_SIZE (iovstack), &iov, &iter); +if (ret >=0 ) { +size_t total_len =iov_iter_count (&iter); + + ret =do_process_madvise (task, mm, &iter, behavior); +if (ret >=0 ) + ret = total_len -iov_iter_count (&iter); +kfree (iov); + }mmput (mm); release_task:put_task_struct (task);
Signature · 1 line
2.26.1.301.g55bc3eb7cb9-goog
Re: [PATCH 2/2] mm: support vector address ranges for process_madvise
mm/madvise.c SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) · line 1219
Quoted 4 lines · Minchan Kim
mm/madvise.c +4
-0+SYSCALL_DEFINE6 (process_madvise, int, which, pid_t, upid, + const struct iovec __user *, vec, unsigned long, vlen, + int, behavior, unsigned long, flags) +{
Don't we now need a compat version of this that calls compat_import_iovec()?
Re: [PATCH 2/2] mm: support vector address ranges for process_madvise
Quoted 7 lines · Matthew Wilcox
Review
Quoted 4 lines · Minchan Kim
(quoted diff) +4
-0+SYSCALL_DEFINE6(process_madvise, int, which, pid_t, upid, + const struct iovec __user *, vec, unsigned long, vlen, + int, behavior, unsigned long, flags) +{Don't we now need a compat version of this that calls
compat_import_iovec()?
Yub, Thanks.
From 72fd6dbbab734803110817ef180ac2c6e3c2ca2a Mon Sep 17 00:00:00 2001
From: Minchan Kim <[email protected]>
Date: Thu, 23 Apr 2020 12:53:53 -0700
Subject: [PATCH] mm: support compat_sys_proess_madvise
This patch supports compat syscall for process_madvise
--- arch/arm64/include/asm/unistd32.h | 2 +- arch/mips/kernel/syscalls/syscall_n32.tbl | 2 +- arch/parisc/kernel/syscalls/syscall.tbl | 2 +- arch/powerpc/kernel/syscalls/syscall.tbl | 2 +- arch/s390/kernel/syscalls/syscall.tbl | 2 +- arch/sparc/kernel/syscalls/syscall.tbl | 2 +- arch/x86/entry/syscalls/syscall_32.tbl | 2 +- arch/x86/entry/syscalls/syscall_64.tbl | 3 +- include/linux/compat.h | 3 ++ include/uapi/asm-generic/unistd.h | 3 +- kernel/sys_ni.c | 1 + mm/madvise.c | 60 +++++++++++++++++------ 12 files changed, 60 insertions(+), 24 deletions(-)
arch/arm64/include/asm/unistd32.h +1 -1
@@ -884,7 +884,7 @@ __SYSCALL(__NR_openat2, sys_openat2)#define __NR_pidfd_getfd 438 __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)#define __NR_process_madvise 439 -__SYSCALL (__NR_process_madvise, sys_process_madvise) +__SYSCALL (__NR_process_madvise, compat_sys_process_madvise)/* * Please add new compat syscalls above this comment and update
arch/mips/kernel/syscalls/syscall_n32.tbl +1 -1
@@ -376,4 +376,4 @@ 435 n32 clone3 __sys_clone3 437 n32 openat2 sys_openat2 438 n32 pidfd_getfd sys_pidfd_getfd -439 n32 process_madvise sys_process_madvise +439 n32 process_madvise compat_sys_process_madvise
arch/parisc/kernel/syscalls/syscall.tbl +1 -1
@@ -435,4 +435,4 @@ 435 common clone3 sys_clone3_wrapper 437 common openat2 sys_openat2 438 common pidfd_getfd sys_pidfd_getfd -439 common process_madvise sys_process_madvise +439 common process_madvise sys_process_madvise compat_sys_process_madvise
arch/powerpc/kernel/syscalls/syscall.tbl +1 -1
@@ -527,4 +527,4 @@ 435 spu clone3 sys_ni_syscall 437 common openat2 sys_openat2 438 common pidfd_getfd sys_pidfd_getfd -439 common process_madvise sys_process_madvise +439 common process_madvise sys_process_madvise compat_sys_process_madvise
arch/s390/kernel/syscalls/syscall.tbl +1 -1
@@ -440,4 +440,4 @@ 435 common clone3 sys_clone3 sys_clone3 437 common openat2 sys_openat2 sys_openat2 438 common pidfd_getfd sys_pidfd_getfd sys_pidfd_getfd -439 common process_madvise sys_process_madvise sys_process_madvise +439 common process_madvise sys_process_madvise compat_sys_process_madvise
arch/sparc/kernel/syscalls/syscall.tbl +1 -1
@@ -483,4 +483,4 @@ # 435 reserved for clone3 437 common openat2 sys_openat2 438 common pidfd_getfd sys_pidfd_getfd -439 common process_madvise sys_process_madvise +439 common process_madvise sys_process_madvise compat_sys_process_madvise
arch/x86/entry/syscalls/syscall_32.tbl +1 -1
@@ -442,4 +442,4 @@ 435 i386 clone3 sys_clone3 437 i386 openat2 sys_openat2 438 i386 pidfd_getfd sys_pidfd_getfd -439 i386 process_madvise sys_process_madvise +439 i386 process_madvise sys_process_madvise compat_sys_process_madvise
arch/x86/entry/syscalls/syscall_64.tbl +2 -1
@@ -359,7 +359,7 @@ 435 common clone3 sys_clone3 437 common openat2 sys_openat2 438 common pidfd_getfd sys_pidfd_getfd -439 common process_madvise sys_process_madvise +439 64 process_madvise sys_process_madvise # # x32-specific system call numbers start at 512 to avoid cache impact
@@ -403,3 +403,4 @@ 545 x32 execveat compat_sys_execveat 546 x32 preadv2 compat_sys_preadv64v2 547 x32 pwritev2 compat_sys_pwritev64v2 +548 x32 process_madvise compat_sys_process_madvise
include/linux/compat.h +3 -0
@@ -820,6 +820,9 @@ asmlinkage long compat_sys_pwritev64v2(unsigned long fd, unsigned long vlen, loff_t pos, rwf_t flags);#endif +asmlinkage ssize_t compat_sys_process_madvise(int which, +compat_pid_t upid,const struct compat_iovec __user *vec, +unsigned long vlen,int behavior,unsigned long flags);/* * Deprecated system calls which are still defined in
include/uapi/asm-generic/unistd.h +2 -1
@@ -856,7 +856,8 @@ __SYSCALL(__NR_openat2, sys_openat2)#define __NR_pidfd_getfd 438 __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)#define __NR_process_madvise 439 -__SYSCALL(__NR_process_madvise, sys_process_madvise) +__SC_COMP (__NR_process_madvise, sys_process_madvise, \ + compat_sys_process_madvise)#undef __NR_syscalls#define __NR_syscalls 440
kernel/sys_ni.c +1 -0
@@ -281,6 +281,7 @@ COND_SYSCALL(munlockall);COND_SYSCALL (mincore);COND_SYSCALL (madvise);COND_SYSCALL (process_madvise); +COND_SYSCALL_COMPAT (process_madvise);COND_SYSCALL (remap_file_pages);COND_SYSCALL (mbind);COND_SYSCALL_COMPAT (mbind);
mm/madvise.c +45 -15
87 lines not on this page · raw message
Signature · 1 line
2.26.1.301.g55bc3eb7cb9-goog