From 306d0c3e29cad7c8e41e1bdfc53a3ceac5d2ad66 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Fri, 22 May 2020 14:28:20 +1000 Subject: [PATCH] mm/madvise: support both pid and pidfd for process_madvise There is a demand[1] to support pid as well pidfd for process_madvise to reduce unnecessary syscall to get pidfd if the user has control of the target process (ie, they could guarantee the process is not gone or pid is not reused). This patch aims for supporting both options like waitid(2). So, the syscall is currently, int process_madvise(idtype_t idtype, id_t id, void *addr, size_t length, int advice, unsigned long flags); @which is actually idtype_t for userspace library and currently, it supports P_PID and P_PIDFD. [1] https://lore.kernel.org/linux-mm/9d849087-3359-c4ab-fbec-859e8186c509@virtuozzo.com/. Change-Id: I06249a7621685e120e548a94098e6cce8d32d38d Link: http://lkml.kernel.org/r/20200302193630.68771-6-minchan@kernel.org Signed-off-by: Minchan Kim Suggested-by: Kirill Tkhai Reviewed-by: Suren Baghdasaryan Reviewed-by: Vlastimil Babka Cc: Christian Brauner Cc: Alexander Duyck Cc: Brian Geffon Cc: Daniel Colascione Cc: Jann Horn Cc: Jens Axboe Cc: Joel Fernandes Cc: Johannes Weiner Cc: John Dias Cc: Michal Hocko Cc: Oleksandr Natalenko Cc: Sandeep Patil Cc: SeongJae Park Cc: SeongJae Park Cc: Shakeel Butt Cc: Sonny Rao Cc: Tim Murray Cc: Christian Brauner Cc: Signed-off-by: Andrew Morton Signed-off-by: Stephen Rothwell Git-Commit: 6c7663468de1b093e8ef5c0ef1df42c890f612bf Git-Repo: git://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git Signed-off-by: Charan Teja Reddy --- include/linux/syscalls.h | 3 ++- mm/madvise.c | 34 ++++++++++++++++++++++------------ 2 files changed, 24 insertions(+), 13 deletions(-) diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index e099fcb9cf0a..e3ecc5fc32cd 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -874,7 +874,8 @@ asmlinkage long sys_munlockall(void); asmlinkage long sys_mincore(unsigned long start, size_t len, unsigned char __user * vec); asmlinkage long sys_madvise(unsigned long start, size_t len, int behavior); -asmlinkage long sys_process_madvise(int pidfd, unsigned long start, + +asmlinkage long sys_process_madvise(int which, pid_t pid, unsigned long start, size_t len, int behavior, unsigned long flags); asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size, unsigned long prot, unsigned long pgoff, diff --git a/mm/madvise.c b/mm/madvise.c index b4ba5b08aff2..f09d4f8559a7 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -1208,11 +1208,10 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) return do_madvise(current, current->mm, start, len_in, behavior); } -SYSCALL_DEFINE5(process_madvise, int, pidfd, unsigned long, start, +SYSCALL_DEFINE6(process_madvise, int, which, pid_t, upid, unsigned long, start, size_t, len_in, int, behavior, unsigned long, flags) { int ret; - struct fd f; struct pid *pid; struct task_struct *task; struct mm_struct *mm; @@ -1223,20 +1222,31 @@ SYSCALL_DEFINE5(process_madvise, int, pidfd, unsigned long, start, if (!process_madvise_behavior_valid(behavior)) return -EINVAL; - f = fdget(pidfd); - if (!f.file) - return -EBADF; + switch (which) { + case P_PID: + if (upid <= 0) + return -EINVAL; - pid = pidfd_pid(f.file); - if (IS_ERR(pid)) { - ret = PTR_ERR(pid); - goto fdput; + pid = find_get_pid(upid); + if (!pid) + return -ESRCH; + break; + case P_PIDFD: + if (upid < 0) + return -EINVAL; + + pid = pidfd_get_pid(upid); + if (IS_ERR(pid)) + return PTR_ERR(pid); + break; + default: + return -EINVAL; } task = get_pid_task(pid, PIDTYPE_PID); if (!task) { ret = -ESRCH; - goto fdput; + goto put_pid; } mm = mm_access(task, PTRACE_MODE_ATTACH_FSCREDS); @@ -1249,7 +1259,7 @@ SYSCALL_DEFINE5(process_madvise, int, pidfd, unsigned long, start, mmput(mm); release_task: put_task_struct(task); -fdput: - fdput(f); +put_pid: + put_pid(pid); return ret; }