From 5d8de293c224896a4da99763fce4f9794308caf4 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 29 Apr 2022 14:37:59 -0700 Subject: vmcore: convert copy_oldmem_page() to take an iov_iter Patch series "Convert vmcore to use an iov_iter", v5. For some reason several people have been sending bad patches to fix compiler warnings in vmcore recently. Here's how it should be done. Compile-tested only on x86. As noted in the first patch, s390 should take this conversion a bit further, but I'm not inclined to do that work myself. This patch (of 3): Instead of passing in a 'buf' and 'userbuf' argument, pass in an iov_iter. s390 needs more work to pass the iov_iter down further, or refactor, but I'd be more comfortable if someone who can test on s390 did that work. It's more convenient to convert the whole of read_from_oldmem() to take an iov_iter at the same time, so rename it to read_from_oldmem_iter() and add a temporary read_from_oldmem() wrapper that creates an iov_iter. Link: https://lkml.kernel.org/r/20220408090636.560886-1-bhe@redhat.com Link: https://lkml.kernel.org/r/20220408090636.560886-2-bhe@redhat.com Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Baoquan He Reviewed-by: Christoph Hellwig Cc: Heiko Carstens Signed-off-by: Andrew Morton --- include/linux/crash_dump.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 620821549b23..a1cf7d5c03c7 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -24,11 +24,10 @@ extern int remap_oldmem_pfn_range(struct vm_area_struct *vma, unsigned long from, unsigned long pfn, unsigned long size, pgprot_t prot); -extern ssize_t copy_oldmem_page(unsigned long, char *, size_t, - unsigned long, int); -extern ssize_t copy_oldmem_page_encrypted(unsigned long pfn, char *buf, - size_t csize, unsigned long offset, - int userbuf); +ssize_t copy_oldmem_page(struct iov_iter *i, unsigned long pfn, size_t csize, + unsigned long offset); +ssize_t copy_oldmem_page_encrypted(struct iov_iter *iter, unsigned long pfn, + size_t csize, unsigned long offset); void vmcore_cleanup(void); -- cgit v1.2.3 From e0690479917cbce740eef51fa3de92c69647a5ad Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 29 Apr 2022 14:37:59 -0700 Subject: vmcore: convert read_from_oldmem() to take an iov_iter Remove the read_from_oldmem() wrapper introduced earlier and convert all the remaining callers to pass an iov_iter. Link: https://lkml.kernel.org/r/20220408090636.560886-4-bhe@redhat.com Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Baoquan He Reviewed-by: Christoph Hellwig Cc: Tiezhu Yang Cc: Amit Daniel Kachhap Cc: Al Viro Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- arch/x86/kernel/crash_dump_64.c | 7 ++++++- fs/proc/vmcore.c | 40 +++++++++++++++------------------------- include/linux/crash_dump.h | 10 ++++------ 3 files changed, 25 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/arch/x86/kernel/crash_dump_64.c b/arch/x86/kernel/crash_dump_64.c index 94fe4aff9694..e75bc2f217ff 100644 --- a/arch/x86/kernel/crash_dump_64.c +++ b/arch/x86/kernel/crash_dump_64.c @@ -54,6 +54,11 @@ ssize_t copy_oldmem_page_encrypted(struct iov_iter *iter, unsigned long pfn, ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos) { - return read_from_oldmem(buf, count, ppos, 0, + struct kvec kvec = { .iov_base = buf, .iov_len = count }; + struct iov_iter iter; + + iov_iter_kvec(&iter, READ, &kvec, 1, count); + + return read_from_oldmem(&iter, count, ppos, cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)); } diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 4a721865b5cd..4eaeb645e759 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -129,7 +129,7 @@ static int open_vmcore(struct inode *inode, struct file *file) } /* Reads a page from the oldmem device from given offset. */ -static ssize_t read_from_oldmem_iter(struct iov_iter *iter, size_t count, +ssize_t read_from_oldmem(struct iov_iter *iter, size_t count, u64 *ppos, bool encrypted) { unsigned long pfn, offset; @@ -178,27 +178,6 @@ static ssize_t read_from_oldmem_iter(struct iov_iter *iter, size_t count, return read; } -ssize_t read_from_oldmem(char *buf, size_t count, - u64 *ppos, int userbuf, - bool encrypted) -{ - struct iov_iter iter; - struct iovec iov; - struct kvec kvec; - - if (userbuf) { - iov.iov_base = (__force void __user *)buf; - iov.iov_len = count; - iov_iter_init(&iter, READ, &iov, 1, count); - } else { - kvec.iov_base = buf; - kvec.iov_len = count; - iov_iter_kvec(&iter, READ, &kvec, 1, count); - } - - return read_from_oldmem_iter(&iter, count, ppos, encrypted); -} - /* * Architectures may override this function to allocate ELF header in 2nd kernel */ @@ -218,7 +197,12 @@ void __weak elfcorehdr_free(unsigned long long addr) */ ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos) { - return read_from_oldmem(buf, count, ppos, 0, false); + struct kvec kvec = { .iov_base = buf, .iov_len = count }; + struct iov_iter iter; + + iov_iter_kvec(&iter, READ, &kvec, 1, count); + + return read_from_oldmem(&iter, count, ppos, false); } /* @@ -226,7 +210,13 @@ ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos) */ ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos) { - return read_from_oldmem(buf, count, ppos, 0, cc_platform_has(CC_ATTR_MEM_ENCRYPT)); + struct kvec kvec = { .iov_base = buf, .iov_len = count }; + struct iov_iter iter; + + iov_iter_kvec(&iter, READ, &kvec, 1, count); + + return read_from_oldmem(&iter, count, ppos, + cc_platform_has(CC_ATTR_MEM_ENCRYPT)); } /* @@ -402,7 +392,7 @@ static ssize_t __read_vmcore(struct iov_iter *iter, loff_t *fpos) m->offset + m->size - *fpos, iov_iter_count(iter)); start = m->paddr + *fpos - m->offset; - tmp = read_from_oldmem_iter(iter, tsz, &start, + tmp = read_from_oldmem(iter, tsz, &start, cc_platform_has(CC_ATTR_MEM_ENCRYPT)); if (tmp < 0) return tmp; diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index a1cf7d5c03c7..0f3a656293b0 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -134,13 +134,11 @@ static inline int vmcore_add_device_dump(struct vmcoredd_data *data) #endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */ #ifdef CONFIG_PROC_VMCORE -ssize_t read_from_oldmem(char *buf, size_t count, - u64 *ppos, int userbuf, - bool encrypted); +ssize_t read_from_oldmem(struct iov_iter *iter, size_t count, + u64 *ppos, bool encrypted); #else -static inline ssize_t read_from_oldmem(char *buf, size_t count, - u64 *ppos, int userbuf, - bool encrypted) +static inline ssize_t read_from_oldmem(struct iov_iter *iter, size_t count, + u64 *ppos, bool encrypted) { return -EOPNOTSUPP; } -- cgit v1.2.3 From f485922d8fe4e44f6d52a5bb95a603b7c65554bb Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 29 Apr 2022 14:38:01 -0700 Subject: pipe: make poll_usage boolean and annotate its access Patch series "Fix data-races around epoll reported by KCSAN." This series suppresses a false positive KCSAN's message and fixes a real data-race. This patch (of 2): pipe_poll() runs locklessly and assigns 1 to poll_usage. Once poll_usage is set to 1, it never changes in other places. However, concurrent writes of a value trigger KCSAN, so let's make KCSAN happy. BUG: KCSAN: data-race in pipe_poll / pipe_poll write to 0xffff8880042f6678 of 4 bytes by task 174 on cpu 3: pipe_poll (fs/pipe.c:656) ep_item_poll.isra.0 (./include/linux/poll.h:88 fs/eventpoll.c:853) do_epoll_wait (fs/eventpoll.c:1692 fs/eventpoll.c:1806 fs/eventpoll.c:2234) __x64_sys_epoll_wait (fs/eventpoll.c:2246 fs/eventpoll.c:2241 fs/eventpoll.c:2241) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:113) write to 0xffff8880042f6678 of 4 bytes by task 177 on cpu 1: pipe_poll (fs/pipe.c:656) ep_item_poll.isra.0 (./include/linux/poll.h:88 fs/eventpoll.c:853) do_epoll_wait (fs/eventpoll.c:1692 fs/eventpoll.c:1806 fs/eventpoll.c:2234) __x64_sys_epoll_wait (fs/eventpoll.c:2246 fs/eventpoll.c:2241 fs/eventpoll.c:2241) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:113) Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 177 Comm: epoll_race Not tainted 5.17.0-58927-gf443e374ae13 #6 Hardware name: Red Hat KVM, BIOS 1.11.0-2.amzn2 04/01/2014 Link: https://lkml.kernel.org/r/20220322002653.33865-1-kuniyu@amazon.co.jp Link: https://lkml.kernel.org/r/20220322002653.33865-2-kuniyu@amazon.co.jp Fixes: 3b844826b6c6 ("pipe: avoid unnecessary EPOLLET wakeups under normal loads") Signed-off-by: Kuniyuki Iwashima Cc: Alexander Duyck Cc: Al Viro Cc: Davidlohr Bueso Cc: Kuniyuki Iwashima Cc: "Soheil Hassas Yeganeh" Cc: "Sridhar Samudrala" Signed-off-by: Andrew Morton --- fs/pipe.c | 2 +- include/linux/pipe_fs_i.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/fs/pipe.c b/fs/pipe.c index e140ea150bbb..d04c3fce28a6 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -653,7 +653,7 @@ pipe_poll(struct file *filp, poll_table *wait) unsigned int head, tail; /* Epoll has some historical nasty semantics, this enables them */ - pipe->poll_usage = 1; + WRITE_ONCE(pipe->poll_usage, true); /* * Reading pipe state only -- no need for acquiring the semaphore. diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index c00c618ef290..cb0fd633a610 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -71,7 +71,7 @@ struct pipe_inode_info { unsigned int files; unsigned int r_counter; unsigned int w_counter; - unsigned int poll_usage; + bool poll_usage; struct page *tmp_page; struct fasync_struct *fasync_readers; struct fasync_struct *fasync_writers; -- cgit v1.2.3 From d679ae94fdd5d3ab00c35078f5af5f37e068b03d Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 29 Apr 2022 14:38:01 -0700 Subject: list: fix a data-race around ep->rdllist ep_poll() first calls ep_events_available() with no lock held and checks if ep->rdllist is empty by list_empty_careful(), which reads rdllist->prev. Thus all accesses to it need some protection to avoid store/load-tearing. Note INIT_LIST_HEAD_RCU() already has the annotation for both prev and next. Commit bf3b9f6372c4 ("epoll: Add busy poll support to epoll with socket fds.") added the first lockless ep_events_available(), and commit c5a282e9635e ("fs/epoll: reduce the scope of wq lock in epoll_wait()") made some ep_events_available() calls lockless and added single call under a lock, finally commit e59d3c64cba6 ("epoll: eliminate unnecessary lock for zero timeout") made the last ep_events_available() lockless. BUG: KCSAN: data-race in do_epoll_wait / do_epoll_wait write to 0xffff88810480c7d8 of 8 bytes by task 1802 on cpu 0: INIT_LIST_HEAD include/linux/list.h:38 [inline] list_splice_init include/linux/list.h:492 [inline] ep_start_scan fs/eventpoll.c:622 [inline] ep_send_events fs/eventpoll.c:1656 [inline] ep_poll fs/eventpoll.c:1806 [inline] do_epoll_wait+0x4eb/0xf40 fs/eventpoll.c:2234 do_epoll_pwait fs/eventpoll.c:2268 [inline] __do_sys_epoll_pwait fs/eventpoll.c:2281 [inline] __se_sys_epoll_pwait+0x12b/0x240 fs/eventpoll.c:2275 __x64_sys_epoll_pwait+0x74/0x80 fs/eventpoll.c:2275 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff88810480c7d8 of 8 bytes by task 1799 on cpu 1: list_empty_careful include/linux/list.h:329 [inline] ep_events_available fs/eventpoll.c:381 [inline] ep_poll fs/eventpoll.c:1797 [inline] do_epoll_wait+0x279/0xf40 fs/eventpoll.c:2234 do_epoll_pwait fs/eventpoll.c:2268 [inline] __do_sys_epoll_pwait fs/eventpoll.c:2281 [inline] __se_sys_epoll_pwait+0x12b/0x240 fs/eventpoll.c:2275 __x64_sys_epoll_pwait+0x74/0x80 fs/eventpoll.c:2275 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0xffff88810480c7d0 -> 0xffff888103c15098 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 1799 Comm: syz-fuzzer Tainted: G W 5.17.0-rc7-syzkaller-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Link: https://lkml.kernel.org/r/20220322002653.33865-3-kuniyu@amazon.co.jp Fixes: e59d3c64cba6 ("epoll: eliminate unnecessary lock for zero timeout") Fixes: c5a282e9635e ("fs/epoll: reduce the scope of wq lock in epoll_wait()") Fixes: bf3b9f6372c4 ("epoll: Add busy poll support to epoll with socket fds.") Signed-off-by: Kuniyuki Iwashima Reported-by: syzbot+bdd6e38a1ed5ee58d8bd@syzkaller.appspotmail.com Cc: Al Viro , Andrew Morton Cc: Kuniyuki Iwashima Cc: Kuniyuki Iwashima Cc: "Soheil Hassas Yeganeh" Cc: Davidlohr Bueso Cc: "Sridhar Samudrala" Cc: Alexander Duyck Signed-off-by: Andrew Morton --- include/linux/list.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/list.h b/include/linux/list.h index dd6c2041d09c..d7d2bfa1a365 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -35,7 +35,7 @@ static inline void INIT_LIST_HEAD(struct list_head *list) { WRITE_ONCE(list->next, list); - list->prev = list; + WRITE_ONCE(list->prev, list); } #ifdef CONFIG_DEBUG_LIST @@ -306,7 +306,7 @@ static inline int list_empty(const struct list_head *head) static inline void list_del_init_careful(struct list_head *entry) { __list_del_entry(entry); - entry->prev = entry; + WRITE_ONCE(entry->prev, entry); smp_store_release(&entry->next, entry); } @@ -326,7 +326,7 @@ static inline void list_del_init_careful(struct list_head *entry) static inline int list_empty_careful(const struct list_head *head) { struct list_head *next = smp_load_acquire(&head->next); - return list_is_head(next, head) && (next == head->prev); + return list_is_head(next, head) && (next == READ_ONCE(head->prev)); } /** -- cgit v1.2.3 From a9866bef5171c859cfabc1155c594d28f194aa23 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Fri, 29 Apr 2022 14:38:02 -0700 Subject: ptrace: fix wrong comment of PT_DTRACE PT_DTRACE is only used on um now, fix the wrong comment. Link: https://lkml.kernel.org/r/1649240981-11024-3-git-send-email-yangtiezhu@loongson.cn Signed-off-by: Tiezhu Yang Cc: Oleg Nesterov Signed-off-by: Andrew Morton --- include/linux/ptrace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 15b3d176b6b4..db4509587d2c 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -30,7 +30,7 @@ extern int ptrace_access_vm(struct task_struct *tsk, unsigned long addr, #define PT_SEIZED 0x00010000 /* SEIZE used, enable new behavior */ #define PT_PTRACED 0x00000001 -#define PT_DTRACE 0x00000002 /* delayed trace (used on m68k, i386) */ +#define PT_DTRACE 0x00000002 /* delayed trace (used on um) */ #define PT_OPT_FLAG_SHIFT 3 /* PT_TRACE_* event enable flags */ -- cgit v1.2.3 From 0e0af57e0e91b304f36b7d1dba859e3c04094273 Mon Sep 17 00:00:00 2001 From: "Dr. Thomas Orgis" Date: Fri, 29 Apr 2022 14:38:03 -0700 Subject: taskstats: version 12 with thread group and exe info The task exit struct needs some crucial information to be able to provide an enhanced version of process and thread accounting. This change provides: 1. ac_tgid in additon to ac_pid 2. thread group execution walltime in ac_tgetime 3. flag AGROUP in ac_flag to indicate the last task in a thread group / process 4. device ID and inode of task's /proc/self/exe in ac_exe_dev and ac_exe_inode 5. tools/accounting/procacct as demonstrator When a task exits, taskstats are reported to userspace including the task's pid and ppid, but without the id of the thread group this task is part of. Without the tgid, the stats of single tasks cannot be correlated to each other as a thread group (process). The taskstats documentation suggests that on process exit a data set consisting of accumulated stats for the whole group is produced. But such an additional set of stats is only produced for actually multithreaded processes, not groups that had only one thread, and also those stats only contain data about delay accounting and not the more basic information about CPU and memory resource usage. Adding the AGROUP flag to be set when the last task of a group exited enables determination of process end also for single-threaded processes. My applicaton basically does enhanced process accounting with summed cputime, biggest maxrss, tasks per process. The data is not available with the traditional BSD process accounting (which is not designed to be extensible) and the taskstats interface allows more efficient on-the-fly grouping and summing of the stats, anyway, without intermediate disk writes. Furthermore, I do carry statistics on which exact program binary is used how often with associated resources, getting a picture on how important which parts of a collection of installed scientific software in different versions are, and how well they put load on the machine. This is enabled by providing information on /proc/self/exe for each task. I assume the two 64-bit fields for device ID and inode are more appropriate than the possibly large resolved path to keep the data volume down. Add the tgid to the stats to complete task identification, the flag AGROUP to mark the last task of a group, the group wallclock time, and inode-based identification of the associated executable file. Add tools/accounting/procacct.c as a simplified fork of getdelays.c to demonstrate process and thread accounting. [thomas.orgis@uni-hamburg.de: fix version number in comment] Link: https://lkml.kernel.org/r/20220405003601.7a5f6008@plasteblaster Link: https://lkml.kernel.org/r/20220331004106.64e5616b@plasteblaster Signed-off-by: Dr. Thomas Orgis Reviewed-by: Ismael Luceno Cc: Balbir Singh Cc: Eric W. Biederman Cc: xu xin Cc: Yang Yang Signed-off-by: Andrew Morton --- include/uapi/linux/acct.h | 3 +- include/uapi/linux/taskstats.h | 24 ++- kernel/taskstats.c | 23 +++ kernel/tsacct.c | 10 +- tools/accounting/.gitignore | 1 + tools/accounting/Makefile | 2 +- tools/accounting/procacct.c | 417 +++++++++++++++++++++++++++++++++++++++++ 7 files changed, 473 insertions(+), 7 deletions(-) create mode 100644 tools/accounting/procacct.c (limited to 'include') diff --git a/include/uapi/linux/acct.h b/include/uapi/linux/acct.h index 985b89068591..0e591152aa8a 100644 --- a/include/uapi/linux/acct.h +++ b/include/uapi/linux/acct.h @@ -103,12 +103,13 @@ struct acct_v3 /* * accounting flags */ - /* bit set when the process ... */ + /* bit set when the process/task ... */ #define AFORK 0x01 /* ... executed fork, but did not exec */ #define ASU 0x02 /* ... used super-user privileges */ #define ACOMPAT 0x04 /* ... used compatibility mode (VAX only not used) */ #define ACORE 0x08 /* ... dumped core */ #define AXSIG 0x10 /* ... was killed by a signal */ +#define AGROUP 0x20 /* ... was the last task of the process (task group) */ #if defined(__BYTE_ORDER) ? __BYTE_ORDER == __BIG_ENDIAN : defined(__BIG_ENDIAN) #define ACCT_BYTEORDER 0x80 /* accounting file is big endian */ diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h index 12327d32378f..736154171489 100644 --- a/include/uapi/linux/taskstats.h +++ b/include/uapi/linux/taskstats.h @@ -34,7 +34,7 @@ */ -#define TASKSTATS_VERSION 11 +#define TASKSTATS_VERSION 12 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -48,7 +48,8 @@ struct taskstats { __u32 ac_exitcode; /* Exit status */ /* The accounting flags of a task as defined in - * Defined values are AFORK, ASU, ACOMPAT, ACORE, and AXSIG. + * Defined values are AFORK, ASU, ACOMPAT, ACORE, AXSIG, and AGROUP. + * (AGROUP since version 12). */ __u8 ac_flag; /* Record flags */ __u8 ac_nice; /* task_nice */ @@ -173,9 +174,26 @@ struct taskstats { /* v10: 64-bit btime to avoid overflow */ __u64 ac_btime64; /* 64-bit begin time */ - /* Delay waiting for memory compact */ + /* v11: Delay waiting for memory compact */ __u64 compact_count; __u64 compact_delay_total; + + /* v12 begin */ + __u32 ac_tgid; /* thread group ID */ + /* Thread group walltime up to now. This is total process walltime if + * AGROUP flag is set. + */ + __u64 ac_tgetime __attribute__((aligned(8))); + /* Lightweight information to identify process binary files. + * This leaves userspace to match this to a file system path, using + * MAJOR() and MINOR() macros to identify a device and mount point, + * the inode to identify the executable file. This is /proc/self/exe + * at the end, so matching the most recent exec(). Values are zero + * for kernel threads. + */ + __u64 ac_exe_dev; /* program binary device ID */ + __u64 ac_exe_inode; /* program binary inode number */ + /* v12 end */ }; diff --git a/kernel/taskstats.c b/kernel/taskstats.c index bcac5a9043aa..72415e22342b 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -153,6 +154,23 @@ static void send_cpu_listeners(struct sk_buff *skb, up_write(&listeners->sem); } +static void exe_add_tsk(struct taskstats *stats, struct task_struct *tsk) +{ + /* No idea if I'm allowed to access that here, now. */ + struct file *exe_file = get_task_exe_file(tsk); + + if (exe_file) { + /* Following cp_new_stat64() in stat.c . */ + stats->ac_exe_dev = + huge_encode_dev(exe_file->f_inode->i_sb->s_dev); + stats->ac_exe_inode = exe_file->f_inode->i_ino; + fput(exe_file); + } else { + stats->ac_exe_dev = 0; + stats->ac_exe_inode = 0; + } +} + static void fill_stats(struct user_namespace *user_ns, struct pid_namespace *pid_ns, struct task_struct *tsk, struct taskstats *stats) @@ -175,6 +193,9 @@ static void fill_stats(struct user_namespace *user_ns, /* fill in extended acct fields */ xacct_add_tsk(stats, tsk); + + /* add executable info */ + exe_add_tsk(stats, tsk); } static int fill_stats_for_pid(pid_t pid, struct taskstats *stats) @@ -620,6 +641,8 @@ void taskstats_exit(struct task_struct *tsk, int group_dead) goto err; fill_stats(&init_user_ns, &init_pid_ns, tsk, stats); + if (group_dead) + stats->ac_flag |= AGROUP; /* * Doesn't matter if tsk is the leader or the last group member leaving diff --git a/kernel/tsacct.c b/kernel/tsacct.c index 1d261fbe367b..4252f0645b9e 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -23,15 +23,20 @@ void bacct_add_tsk(struct user_namespace *user_ns, { const struct cred *tcred; u64 utime, stime, utimescaled, stimescaled; - u64 delta; + u64 now_ns, delta; time64_t btime; BUILD_BUG_ON(TS_COMM_LEN < TASK_COMM_LEN); /* calculate task elapsed time in nsec */ - delta = ktime_get_ns() - tsk->start_time; + now_ns = ktime_get_ns(); + /* store whole group time first */ + delta = now_ns - tsk->group_leader->start_time; /* Convert to micro seconds */ do_div(delta, NSEC_PER_USEC); + stats->ac_tgetime = delta; + delta = now_ns - tsk->start_time; + do_div(delta, NSEC_PER_USEC); stats->ac_etime = delta; /* Convert to seconds for btime (note y2106 limit) */ btime = ktime_get_real_seconds() - div_u64(delta, USEC_PER_SEC); @@ -51,6 +56,7 @@ void bacct_add_tsk(struct user_namespace *user_ns, stats->ac_nice = task_nice(tsk); stats->ac_sched = tsk->policy; stats->ac_pid = task_pid_nr_ns(tsk, pid_ns); + stats->ac_tgid = task_tgid_nr_ns(tsk, pid_ns); rcu_read_lock(); tcred = __task_cred(tsk); stats->ac_uid = from_kuid_munged(user_ns, tcred->uid); diff --git a/tools/accounting/.gitignore b/tools/accounting/.gitignore index c45fb4ed4309..522a690aaf3d 100644 --- a/tools/accounting/.gitignore +++ b/tools/accounting/.gitignore @@ -1,2 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only getdelays +procacct diff --git a/tools/accounting/Makefile b/tools/accounting/Makefile index 03687f19cbb1..11def1ad046c 100644 --- a/tools/accounting/Makefile +++ b/tools/accounting/Makefile @@ -2,7 +2,7 @@ CC := $(CROSS_COMPILE)gcc CFLAGS := -I../../usr/include -PROGS := getdelays +PROGS := getdelays procacct all: $(PROGS) diff --git a/tools/accounting/procacct.c b/tools/accounting/procacct.c new file mode 100644 index 000000000000..8353d3237e50 --- /dev/null +++ b/tools/accounting/procacct.c @@ -0,0 +1,417 @@ +// SPDX-License-Identifier: GPL-2.0 +/* procacct.c + * + * Demonstrator of fetching resource data on task exit, as a way + * to accumulate accurate program resource usage statistics, without + * prior identification of the programs. For that, the fields for + * device and inode of the program executable binary file are also + * extracted in addition to the command string. + * + * The TGID together with the PID and the AGROUP flag allow + * identification of threads in a process and single-threaded processes. + * The ac_tgetime field gives proper whole-process walltime. + * + * Written (changed) by Thomas Orgis, University of Hamburg in 2022 + * + * This is a cheap derivation (inheriting the style) of getdelays.c: + * + * Utility to get per-pid and per-tgid delay accounting statistics + * Also illustrates usage of the taskstats interface + * + * Copyright (C) Shailabh Nagar, IBM Corp. 2005 + * Copyright (C) Balbir Singh, IBM Corp. 2006 + * Copyright (c) Jay Lan, SGI. 2006 + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +/* + * Generic macros for dealing with netlink sockets. Might be duplicated + * elsewhere. It is recommended that commercial grade applications use + * libnl or libnetlink and use the interfaces provided by the library + */ +#define GENLMSG_DATA(glh) ((void *)(NLMSG_DATA(glh) + GENL_HDRLEN)) +#define GENLMSG_PAYLOAD(glh) (NLMSG_PAYLOAD(glh, 0) - GENL_HDRLEN) +#define NLA_DATA(na) ((void *)((char *)(na) + NLA_HDRLEN)) +#define NLA_PAYLOAD(len) (len - NLA_HDRLEN) + +#define err(code, fmt, arg...) \ + do { \ + fprintf(stderr, fmt, ##arg); \ + exit(code); \ + } while (0) + +int rcvbufsz; +char name[100]; +int dbg; +int print_delays; +int print_io_accounting; +int print_task_context_switch_counts; + +#define PRINTF(fmt, arg...) { \ + if (dbg) { \ + printf(fmt, ##arg); \ + } \ + } + +/* Maximum size of response requested or message sent */ +#define MAX_MSG_SIZE 1024 +/* Maximum number of cpus expected to be specified in a cpumask */ +#define MAX_CPUS 32 + +struct msgtemplate { + struct nlmsghdr n; + struct genlmsghdr g; + char buf[MAX_MSG_SIZE]; +}; + +char cpumask[100+6*MAX_CPUS]; + +static void usage(void) +{ + fprintf(stderr, "procacct [-v] [-w logfile] [-r bufsize] [-m cpumask]\n"); + fprintf(stderr, " -v: debug on\n"); +} + +/* + * Create a raw netlink socket and bind + */ +static int create_nl_socket(int protocol) +{ + int fd; + struct sockaddr_nl local; + + fd = socket(AF_NETLINK, SOCK_RAW, protocol); + if (fd < 0) + return -1; + + if (rcvbufsz) + if (setsockopt(fd, SOL_SOCKET, SO_RCVBUF, + &rcvbufsz, sizeof(rcvbufsz)) < 0) { + fprintf(stderr, "Unable to set socket rcv buf size to %d\n", + rcvbufsz); + goto error; + } + + memset(&local, 0, sizeof(local)); + local.nl_family = AF_NETLINK; + + if (bind(fd, (struct sockaddr *) &local, sizeof(local)) < 0) + goto error; + + return fd; +error: + close(fd); + return -1; +} + + +static int send_cmd(int sd, __u16 nlmsg_type, __u32 nlmsg_pid, + __u8 genl_cmd, __u16 nla_type, + void *nla_data, int nla_len) +{ + struct nlattr *na; + struct sockaddr_nl nladdr; + int r, buflen; + char *buf; + + struct msgtemplate msg; + + msg.n.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN); + msg.n.nlmsg_type = nlmsg_type; + msg.n.nlmsg_flags = NLM_F_REQUEST; + msg.n.nlmsg_seq = 0; + msg.n.nlmsg_pid = nlmsg_pid; + msg.g.cmd = genl_cmd; + msg.g.version = 0x1; + na = (struct nlattr *) GENLMSG_DATA(&msg); + na->nla_type = nla_type; + na->nla_len = nla_len + 1 + NLA_HDRLEN; + memcpy(NLA_DATA(na), nla_data, nla_len); + msg.n.nlmsg_len += NLMSG_ALIGN(na->nla_len); + + buf = (char *) &msg; + buflen = msg.n.nlmsg_len; + memset(&nladdr, 0, sizeof(nladdr)); + nladdr.nl_family = AF_NETLINK; + while ((r = sendto(sd, buf, buflen, 0, (struct sockaddr *) &nladdr, + sizeof(nladdr))) < buflen) { + if (r > 0) { + buf += r; + buflen -= r; + } else if (errno != EAGAIN) + return -1; + } + return 0; +} + + +/* + * Probe the controller in genetlink to find the family id + * for the TASKSTATS family + */ +static int get_family_id(int sd) +{ + struct { + struct nlmsghdr n; + struct genlmsghdr g; + char buf[256]; + } ans; + + int id = 0, rc; + struct nlattr *na; + int rep_len; + + strcpy(name, TASKSTATS_GENL_NAME); + rc = send_cmd(sd, GENL_ID_CTRL, getpid(), CTRL_CMD_GETFAMILY, + CTRL_ATTR_FAMILY_NAME, (void *)name, + strlen(TASKSTATS_GENL_NAME)+1); + if (rc < 0) + return 0; /* sendto() failure? */ + + rep_len = recv(sd, &ans, sizeof(ans), 0); + if (ans.n.nlmsg_type == NLMSG_ERROR || + (rep_len < 0) || !NLMSG_OK((&ans.n), rep_len)) + return 0; + + na = (struct nlattr *) GENLMSG_DATA(&ans); + na = (struct nlattr *) ((char *) na + NLA_ALIGN(na->nla_len)); + if (na->nla_type == CTRL_ATTR_FAMILY_ID) + id = *(__u16 *) NLA_DATA(na); + + return id; +} + +#define average_ms(t, c) (t / 1000000ULL / (c ? c : 1)) + +static void print_procacct(struct taskstats *t) +{ + /* First letter: T is a mere thread, G the last in a group, U unknown. */ + printf( + "%c pid=%lu tgid=%lu uid=%lu wall=%llu gwall=%llu cpu=%llu vmpeak=%llu rsspeak=%llu dev=%lu:%lu inode=%llu comm=%s\n" + , t->version >= 12 ? (t->ac_flag & AGROUP ? 'P' : 'T') : '?' + , (unsigned long)t->ac_pid + , (unsigned long)(t->version >= 12 ? t->ac_tgid : 0) + , (unsigned long)t->ac_uid + , (unsigned long long)t->ac_etime + , (unsigned long long)(t->version >= 12 ? t->ac_tgetime : 0) + , (unsigned long long)(t->ac_utime+t->ac_stime) + , (unsigned long long)t->hiwater_vm + , (unsigned long long)t->hiwater_rss + , (unsigned long)(t->version >= 12 ? MAJOR(t->ac_exe_dev) : 0) + , (unsigned long)(t->version >= 12 ? MINOR(t->ac_exe_dev) : 0) + , (unsigned long long)(t->version >= 12 ? t->ac_exe_inode : 0) + , t->ac_comm + ); +} + +void handle_aggr(int mother, struct nlattr *na, int fd) +{ + int aggr_len = NLA_PAYLOAD(na->nla_len); + int len2 = 0; + pid_t rtid = 0; + + na = (struct nlattr *) NLA_DATA(na); + while (len2 < aggr_len) { + switch (na->nla_type) { + case TASKSTATS_TYPE_PID: + rtid = *(int *) NLA_DATA(na); + PRINTF("PID\t%d\n", rtid); + break; + case TASKSTATS_TYPE_TGID: + rtid = *(int *) NLA_DATA(na); + PRINTF("TGID\t%d\n", rtid); + break; + case TASKSTATS_TYPE_STATS: + if (mother == TASKSTATS_TYPE_AGGR_PID) + print_procacct((struct taskstats *) NLA_DATA(na)); + if (fd) { + if (write(fd, NLA_DATA(na), na->nla_len) < 0) + err(1, "write error\n"); + } + break; + case TASKSTATS_TYPE_NULL: + break; + default: + fprintf(stderr, "Unknown nested nla_type %d\n", + na->nla_type); + break; + } + len2 += NLA_ALIGN(na->nla_len); + na = (struct nlattr *)((char *)na + + NLA_ALIGN(na->nla_len)); + } +} + +int main(int argc, char *argv[]) +{ + int c, rc, rep_len, aggr_len, len2; + int cmd_type = TASKSTATS_CMD_ATTR_UNSPEC; + __u16 id; + __u32 mypid; + + struct nlattr *na; + int nl_sd = -1; + int len = 0; + pid_t tid = 0; + + int fd = 0; + int write_file = 0; + int maskset = 0; + char *logfile = NULL; + int containerset = 0; + char *containerpath = NULL; + int cfd = 0; + int forking = 0; + sigset_t sigset; + + struct msgtemplate msg; + + while (!forking) { + c = getopt(argc, argv, "m:vr:"); + if (c < 0) + break; + + switch (c) { + case 'w': + logfile = strdup(optarg); + printf("write to file %s\n", logfile); + write_file = 1; + break; + case 'r': + rcvbufsz = atoi(optarg); + printf("receive buf size %d\n", rcvbufsz); + if (rcvbufsz < 0) + err(1, "Invalid rcv buf size\n"); + break; + case 'm': + strncpy(cpumask, optarg, sizeof(cpumask)); + cpumask[sizeof(cpumask) - 1] = '\0'; + maskset = 1; + break; + case 'v': + printf("debug on\n"); + dbg = 1; + break; + default: + usage(); + exit(-1); + } + } + if (!maskset) { + maskset = 1; + strncpy(cpumask, "1", sizeof(cpumask)); + cpumask[sizeof(cpumask) - 1] = '\0'; + } + printf("cpumask %s maskset %d\n", cpumask, maskset); + + if (write_file) { + fd = open(logfile, O_WRONLY | O_CREAT | O_TRUNC, 0644); + if (fd == -1) { + perror("Cannot open output file\n"); + exit(1); + } + } + + nl_sd = create_nl_socket(NETLINK_GENERIC); + if (nl_sd < 0) + err(1, "error creating Netlink socket\n"); + + mypid = getpid(); + id = get_family_id(nl_sd); + if (!id) { + fprintf(stderr, "Error getting family id, errno %d\n", errno); + goto err; + } + PRINTF("family id %d\n", id); + + if (maskset) { + rc = send_cmd(nl_sd, id, mypid, TASKSTATS_CMD_GET, + TASKSTATS_CMD_ATTR_REGISTER_CPUMASK, + &cpumask, strlen(cpumask) + 1); + PRINTF("Sent register cpumask, retval %d\n", rc); + if (rc < 0) { + fprintf(stderr, "error sending register cpumask\n"); + goto err; + } + } + + do { + rep_len = recv(nl_sd, &msg, sizeof(msg), 0); + PRINTF("received %d bytes\n", rep_len); + + if (rep_len < 0) { + fprintf(stderr, "nonfatal reply error: errno %d\n", + errno); + continue; + } + if (msg.n.nlmsg_type == NLMSG_ERROR || + !NLMSG_OK((&msg.n), rep_len)) { + struct nlmsgerr *err = NLMSG_DATA(&msg); + + fprintf(stderr, "fatal reply error, errno %d\n", + err->error); + goto done; + } + + PRINTF("nlmsghdr size=%zu, nlmsg_len=%d, rep_len=%d\n", + sizeof(struct nlmsghdr), msg.n.nlmsg_len, rep_len); + + + rep_len = GENLMSG_PAYLOAD(&msg.n); + + na = (struct nlattr *) GENLMSG_DATA(&msg); + len = 0; + while (len < rep_len) { + len += NLA_ALIGN(na->nla_len); + int mother = na->nla_type; + + PRINTF("mother=%i\n", mother); + switch (na->nla_type) { + case TASKSTATS_TYPE_AGGR_PID: + case TASKSTATS_TYPE_AGGR_TGID: + /* For nested attributes, na follows */ + handle_aggr(mother, na, fd); + break; + default: + fprintf(stderr, "Unexpected nla_type %d\n", + na->nla_type); + case TASKSTATS_TYPE_NULL: + break; + } + na = (struct nlattr *) (GENLMSG_DATA(&msg) + len); + } + } while (1); +done: + if (maskset) { + rc = send_cmd(nl_sd, id, mypid, TASKSTATS_CMD_GET, + TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK, + &cpumask, strlen(cpumask) + 1); + printf("Sent deregister mask, retval %d\n", rc); + if (rc < 0) + err(rc, "error sending deregister cpumask\n"); + } +err: + close(nl_sd); + if (fd) + close(fd); + if (cfd) + close(cfd); + return 0; +} -- cgit v1.2.3 From c9b516f16be5896a3d798f8efb03acbd2ceec715 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 12 May 2022 20:38:36 -0700 Subject: ELF, uapi: fixup ELF_ST_TYPE definition This is very theoretical compile failure: ELF_ST_TYPE(st_info = A) Cast will bind first and st_info will stop being lvalue: error: lvalue required as left operand of assignment Given that the only use of this macro is ELF_ST_TYPE(sym->st_info) where st_info is "unsigned char" I've decided to remove cast especially given that companion macro ELF_ST_BIND doesn't use cast. Link: https://lkml.kernel.org/r/Ymv7G1BeX4kt3obz@localhost.localdomain Signed-off-by: Alexey Dobriyan Acked-by: Kees Cook Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton --- include/uapi/linux/elf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 787c657bfae8..237f21a5e0f6 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -134,7 +134,7 @@ typedef __s64 Elf64_Sxword; #define STT_TLS 6 #define ELF_ST_BIND(x) ((x) >> 4) -#define ELF_ST_TYPE(x) (((unsigned int) x) & 0xf) +#define ELF_ST_TYPE(x) ((x) & 0xf) #define ELF32_ST_BIND(x) ELF_ST_BIND(x) #define ELF32_ST_TYPE(x) ELF_ST_TYPE(x) #define ELF64_ST_BIND(x) ELF_ST_BIND(x) -- cgit v1.2.3