From: Yutian Yang <nglaive@gmail.com> To: mhocko@kernel.org, hannes@cmpxchg.org, vdavydov.dev@gmail.com Cc: cgroups@vger.kernel.org, linux-mm@kvack.org, shenwenbo@zju.edu.cn, Yutian Yang <nglaive@gmail.com> Subject: [PATCH] memcg: charge fs_context and legacy_fs_context Date: Sat, 17 Jul 2021 06:20:01 -0400 [thread overview] Message-ID: <1626517201-24086-1-git-send-email-nglaive@gmail.com> (raw) This patch adds accounting flags to fs_context and legacy_fs_context allocation sites so that kernel could correctly charge these objects. We have written a PoC to demonstrate the effect of the missing-charging bugs. The PoC takes around 1,200MB unaccounted memory, while it is charged for only 362MB memory usage. We evaluate the PoC on QEMU x86_64 v5.2.90 + Linux kernel v5.10.19 + Debian buster. All the limitations including ulimits and sysctl variables are set as default. Specifically, the hard NOFILE limit and nr_open in sysctl are both 1,048,576. /*------------------------- POC code ----------------------------*/ #define _GNU_SOURCE #include <sys/types.h> #include <sys/file.h> #include <time.h> #include <sys/wait.h> #include <stdint.h> #include <stdlib.h> #include <unistd.h> #include <stdio.h> #include <signal.h> #include <sched.h> #include <fcntl.h> #include <linux/mount.h> #define errExit(msg) do { perror(msg); exit(EXIT_FAILURE); \ } while (0) #define STACK_SIZE (8 * 1024) #ifndef __NR_fsopen #define __NR_fsopen 430 #endif static inline int fsopen(const char *fs_name, unsigned int flags) { return syscall(__NR_fsopen, fs_name, flags); } static char thread_stack[512][STACK_SIZE]; int thread_fn(void* arg) { for (int i = 0; i< 800000; ++i) { int fsfd = fsopen("nfs", FSOPEN_CLOEXEC); if (fsfd == -1) { errExit("fsopen"); } } while(1); return 0; } int main(int argc, char *argv[]) { int thread_pid; for (int i = 0; i < 1; ++i) { thread_pid = clone(thread_fn, thread_stack[i] + STACK_SIZE, \ SIGCHLD, NULL); } while(1); return 0; } /*-------------------------- end --------------------------------*/ Thanks! Yutian Yang, Zhejiang University Signed-off-by: Yutian Yang <nglaive@gmail.com> --- fs/fs_context.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/fs_context.c b/fs/fs_context.c index 2834d1afa..4858645ca 100644 --- a/fs/fs_context.c +++ b/fs/fs_context.c @@ -231,7 +231,7 @@ static struct fs_context *alloc_fs_context(struct file_system_type *fs_type, struct fs_context *fc; int ret = -ENOMEM; - fc = kzalloc(sizeof(struct fs_context), GFP_KERNEL); + fc = kzalloc(sizeof(struct fs_context), GFP_KERNEL_ACCOUNT); if (!fc) return ERR_PTR(-ENOMEM); @@ -631,7 +631,7 @@ const struct fs_context_operations legacy_fs_context_ops = { */ static int legacy_init_fs_context(struct fs_context *fc) { - fc->fs_private = kzalloc(sizeof(struct legacy_fs_context), GFP_KERNEL); + fc->fs_private = kzalloc(sizeof(struct legacy_fs_context), GFP_KERNEL_ACCOUNT); if (!fc->fs_private) return -ENOMEM; fc->ops = &legacy_fs_context_ops; -- 2.25.1
WARNING: multiple messages have this Message-ID (diff)
From: Yutian Yang <nglaive-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org> To: mhocko-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org, hannes-druUgvl0LCNAfugRpC6u6w@public.gmane.org, vdavydov.dev-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org Cc: cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org, shenwenbo-Y5EWUtBUdg4nDS1+zs4M5A@public.gmane.org, Yutian Yang <nglaive-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org> Subject: [PATCH] memcg: charge fs_context and legacy_fs_context Date: Sat, 17 Jul 2021 06:20:01 -0400 [thread overview] Message-ID: <1626517201-24086-1-git-send-email-nglaive@gmail.com> (raw) This patch adds accounting flags to fs_context and legacy_fs_context allocation sites so that kernel could correctly charge these objects. We have written a PoC to demonstrate the effect of the missing-charging bugs. The PoC takes around 1,200MB unaccounted memory, while it is charged for only 362MB memory usage. We evaluate the PoC on QEMU x86_64 v5.2.90 + Linux kernel v5.10.19 + Debian buster. All the limitations including ulimits and sysctl variables are set as default. Specifically, the hard NOFILE limit and nr_open in sysctl are both 1,048,576. /*------------------------- POC code ----------------------------*/ #define _GNU_SOURCE #include <sys/types.h> #include <sys/file.h> #include <time.h> #include <sys/wait.h> #include <stdint.h> #include <stdlib.h> #include <unistd.h> #include <stdio.h> #include <signal.h> #include <sched.h> #include <fcntl.h> #include <linux/mount.h> #define errExit(msg) do { perror(msg); exit(EXIT_FAILURE); \ } while (0) #define STACK_SIZE (8 * 1024) #ifndef __NR_fsopen #define __NR_fsopen 430 #endif static inline int fsopen(const char *fs_name, unsigned int flags) { return syscall(__NR_fsopen, fs_name, flags); } static char thread_stack[512][STACK_SIZE]; int thread_fn(void* arg) { for (int i = 0; i< 800000; ++i) { int fsfd = fsopen("nfs", FSOPEN_CLOEXEC); if (fsfd == -1) { errExit("fsopen"); } } while(1); return 0; } int main(int argc, char *argv[]) { int thread_pid; for (int i = 0; i < 1; ++i) { thread_pid = clone(thread_fn, thread_stack[i] + STACK_SIZE, \ SIGCHLD, NULL); } while(1); return 0; } /*-------------------------- end --------------------------------*/ Thanks! Yutian Yang, Zhejiang University Signed-off-by: Yutian Yang <nglaive-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org> --- fs/fs_context.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/fs_context.c b/fs/fs_context.c index 2834d1afa..4858645ca 100644 --- a/fs/fs_context.c +++ b/fs/fs_context.c @@ -231,7 +231,7 @@ static struct fs_context *alloc_fs_context(struct file_system_type *fs_type, struct fs_context *fc; int ret = -ENOMEM; - fc = kzalloc(sizeof(struct fs_context), GFP_KERNEL); + fc = kzalloc(sizeof(struct fs_context), GFP_KERNEL_ACCOUNT); if (!fc) return ERR_PTR(-ENOMEM); @@ -631,7 +631,7 @@ const struct fs_context_operations legacy_fs_context_ops = { */ static int legacy_init_fs_context(struct fs_context *fc) { - fc->fs_private = kzalloc(sizeof(struct legacy_fs_context), GFP_KERNEL); + fc->fs_private = kzalloc(sizeof(struct legacy_fs_context), GFP_KERNEL_ACCOUNT); if (!fc->fs_private) return -ENOMEM; fc->ops = &legacy_fs_context_ops; -- 2.25.1
next reply other threads:[~2021-07-17 10:20 UTC|newest] Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top 2021-07-17 10:20 Yutian Yang [this message] 2021-07-17 10:20 ` [PATCH] memcg: charge fs_context and legacy_fs_context Yutian Yang 2021-07-17 16:52 ` Shakeel Butt 2021-07-17 16:52 ` Shakeel Butt
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=1626517201-24086-1-git-send-email-nglaive@gmail.com \ --to=nglaive@gmail.com \ --cc=cgroups@vger.kernel.org \ --cc=hannes@cmpxchg.org \ --cc=linux-mm@kvack.org \ --cc=mhocko@kernel.org \ --cc=shenwenbo@zju.edu.cn \ --cc=vdavydov.dev@gmail.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.