From ce9a52e20897955fac0c3586b9ab66e7947c0a70 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Sat, 18 Sep 2021 18:53:08 -0400 Subject: cgroup: Make rebind_subsystems() disable v2 controllers all at once [ Upstream commit 7ee285395b211cad474b2b989db52666e0430daf ] It was found that the following warning was displayed when remounting controllers from cgroup v2 to v1: [ 8042.997778] WARNING: CPU: 88 PID: 80682 at kernel/cgroup/cgroup.c:3130 cgroup_apply_control_disable+0x158/0x190 : [ 8043.091109] RIP: 0010:cgroup_apply_control_disable+0x158/0x190 [ 8043.096946] Code: ff f6 45 54 01 74 39 48 8d 7d 10 48 c7 c6 e0 46 5a a4 e8 7b 67 33 00 e9 41 ff ff ff 49 8b 84 24 e8 01 00 00 0f b7 40 08 eb 95 <0f> 0b e9 5f ff ff ff 48 83 c4 08 5b 5d 41 5c 41 5d 41 5e 41 5f c3 [ 8043.115692] RSP: 0018:ffffba8a47c23d28 EFLAGS: 00010202 [ 8043.120916] RAX: 0000000000000036 RBX: ffffffffa624ce40 RCX: 000000000000181a [ 8043.128047] RDX: ffffffffa63c43e0 RSI: ffffffffa63c43e0 RDI: ffff9d7284ee1000 [ 8043.135180] RBP: ffff9d72874c5800 R08: ffffffffa624b090 R09: 0000000000000004 [ 8043.142314] R10: ffffffffa624b080 R11: 0000000000002000 R12: ffff9d7284ee1000 [ 8043.149447] R13: ffff9d7284ee1000 R14: ffffffffa624ce70 R15: ffffffffa6269e20 [ 8043.156576] FS: 00007f7747cff740(0000) GS:ffff9d7a5fc00000(0000) knlGS:0000000000000000 [ 8043.164663] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 8043.170409] CR2: 00007f7747e96680 CR3: 0000000887d60001 CR4: 00000000007706e0 [ 8043.177539] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 8043.184673] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 8043.191804] PKRU: 55555554 [ 8043.194517] Call Trace: [ 8043.196970] rebind_subsystems+0x18c/0x470 [ 8043.201070] cgroup_setup_root+0x16c/0x2f0 [ 8043.205177] cgroup1_root_to_use+0x204/0x2a0 [ 8043.209456] cgroup1_get_tree+0x3e/0x120 [ 8043.213384] vfs_get_tree+0x22/0xb0 [ 8043.216883] do_new_mount+0x176/0x2d0 [ 8043.220550] __x64_sys_mount+0x103/0x140 [ 8043.224474] do_syscall_64+0x38/0x90 [ 8043.228063] entry_SYSCALL_64_after_hwframe+0x44/0xae It was caused by the fact that rebind_subsystem() disables controllers to be rebound one by one. If more than one disabled controllers are originally from the default hierarchy, it means that cgroup_apply_control_disable() will be called multiple times for the same default hierarchy. A controller may be killed by css_kill() in the first round. In the second round, the killed controller may not be completely dead yet leading to the warning. To avoid this problem, we collect all the ssid's of controllers that needed to be disabled from the default hierarchy and then disable them in one go instead of one by one. Fixes: 334c3679ec4b ("cgroup: reimplement rebind_subsystems() using cgroup_apply_control() and friends") Signed-off-by: Waiman Long Signed-off-by: Tejun Heo Signed-off-by: Sasha Levin Change-Id: I62fb64dec4392451fd649d6bdbb8e409858d9513 --- kernel/cgroup.c | 31 +++++++++++++++++++++++++++---- 1 file changed, 27 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index d36c4f914a1e..c2508ca442b7 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1544,6 +1544,7 @@ static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) struct cgroup *dcgrp = &dst_root->cgrp; struct cgroup_subsys *ss; int ssid, i, ret; + u16 dfl_disable_ss_mask = 0; lockdep_assert_held(&cgroup_mutex); @@ -1560,8 +1561,28 @@ static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) /* can't move between two non-dummy roots either */ if (ss->root != &cgrp_dfl_root && dst_root != &cgrp_dfl_root) return -EBUSY; + + /* + * Collect ssid's that need to be disabled from default + * hierarchy. + */ + if (ss->root == &cgrp_dfl_root) + dfl_disable_ss_mask |= 1 << ssid; + } while_each_subsys_mask(); + if (dfl_disable_ss_mask) { + struct cgroup *scgrp = &cgrp_dfl_root.cgrp; + + /* + * Controllers from default hierarchy that need to be rebound + * are all disabled together in one go. + */ + cgrp_dfl_root.subsys_mask &= ~dfl_disable_ss_mask; + WARN_ON(cgroup_apply_control(scgrp)); + cgroup_finalize_control(scgrp, 0); + } + do_each_subsys_mask(ss, ssid, ss_mask) { struct cgroup_root *src_root = ss->root; struct cgroup *scgrp = &src_root->cgrp; @@ -1570,10 +1591,12 @@ static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) WARN_ON(!css || cgroup_css(dcgrp, ss)); - /* disable from the source */ - src_root->subsys_mask &= ~(1 << ssid); - WARN_ON(cgroup_apply_control(scgrp)); - cgroup_finalize_control(scgrp, 0); + if (src_root != &cgrp_dfl_root) { + /* disable from the source */ + src_root->subsys_mask &= ~(1 << ssid); + WARN_ON(cgroup_apply_control(scgrp)); + cgroup_finalize_control(scgrp, 0); + } /* rebind */ RCU_INIT_POINTER(scgrp->subsys[ssid], NULL); -- cgit v1.2.3 From cbd08255e6f8bd1f43ced8e778e7a34d577772d7 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 1 Feb 2017 06:06:16 +1300 Subject: fs: Better permission checking for submounts commit 93faccbbfa958a9668d3ab4e30f38dd205cee8d8 upstream. To support unprivileged users mounting filesystems two permission checks have to be performed: a test to see if the user allowed to create a mount in the mount namespace, and a test to see if the user is allowed to access the specified filesystem. The automount case is special in that mounting the original filesystem grants permission to mount the sub-filesystems, to any user who happens to stumble across the their mountpoint and satisfies the ordinary filesystem permission checks. Attempting to handle the automount case by using override_creds almost works. It preserves the idea that permission to mount the original filesystem is permission to mount the sub-filesystem. Unfortunately using override_creds messes up the filesystems ordinary permission checks. Solve this by being explicit that a mount is a submount by introducing vfs_submount, and using it where appropriate. vfs_submount uses a new mount internal mount flags MS_SUBMOUNT, to let sget and friends know that a mount is a submount so they can take appropriate action. sget and sget_userns are modified to not perform any permission checks on submounts. follow_automount is modified to stop using override_creds as that has proven problemantic. do_mount is modified to always remove the new MS_SUBMOUNT flag so that we know userspace will never by able to specify it. autofs4 is modified to stop using current_real_cred that was put in there to handle the previous version of submount permission checking. cifs is modified to pass the mountpoint all of the way down to vfs_submount. debugfs is modified to pass the mountpoint all of the way down to trace_automount by adding a new parameter. To make this change easier a new typedef debugfs_automount_t is introduced to capture the type of the debugfs automount function. Fixes: 069d5ac9ae0d ("autofs: Fix automounts by using current_real_cred()->uid") Fixes: aeaa4a79ff6a ("fs: Call d_automount with the filesystems creds") Reviewed-by: Trond Myklebust Reviewed-by: Seth Forshee Signed-off-by: "Eric W. Biederman" Signed-off-by: Greg Kroah-Hartman Change-Id: I09cb1f35368fb8dc4a64b5ac5a35c9d2843ef95b --- kernel/trace/trace.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a67f792fb950..17996354c745 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -7026,7 +7026,7 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer) } -static struct vfsmount *trace_automount(void *ingore) +static struct vfsmount *trace_automount(struct dentry *mntpt, void *ingore) { struct vfsmount *mnt; struct file_system_type *type; @@ -7039,7 +7039,7 @@ static struct vfsmount *trace_automount(void *ingore) type = get_fs_type("tracefs"); if (!type) return NULL; - mnt = vfs_kern_mount(type, 0, "tracefs", NULL); + mnt = vfs_submount(mntpt, type, "tracefs", NULL); put_filesystem(type); if (IS_ERR(mnt)) return NULL; -- cgit v1.2.3 From c46a001439fc6d7016c50ea2514659f9c64bbbc9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 Jul 2022 12:39:00 +0000 Subject: bpf: Make sure mac_header was set before using it commit 0326195f523a549e0a9d7fd44c70b26fd7265090 upstream. Classic BPF has a way to load bytes starting from the mac header. Some skbs do not have a mac header, and skb_mac_header() in this case is returning a pointer that 65535 bytes after skb->head. Existing range check in bpf_internal_load_pointer_neg_helper() was properly kicking and no illegal access was happening. New sanity check in skb_mac_header() is firing, so we need to avoid it. WARNING: CPU: 1 PID: 28990 at include/linux/skbuff.h:2785 skb_mac_header include/linux/skbuff.h:2785 [inline] WARNING: CPU: 1 PID: 28990 at include/linux/skbuff.h:2785 bpf_internal_load_pointer_neg_helper+0x1b1/0x1c0 kernel/bpf/core.c:74 Modules linked in: CPU: 1 PID: 28990 Comm: syz-executor.0 Not tainted 5.19.0-rc4-syzkaller-00865-g4874fb9484be #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 06/29/2022 RIP: 0010:skb_mac_header include/linux/skbuff.h:2785 [inline] RIP: 0010:bpf_internal_load_pointer_neg_helper+0x1b1/0x1c0 kernel/bpf/core.c:74 Code: ff ff 45 31 f6 e9 5a ff ff ff e8 aa 27 40 00 e9 3b ff ff ff e8 90 27 40 00 e9 df fe ff ff e8 86 27 40 00 eb 9e e8 2f 2c f3 ff <0f> 0b eb b1 e8 96 27 40 00 e9 79 fe ff ff 90 41 57 41 56 41 55 41 RSP: 0018:ffffc9000309f668 EFLAGS: 00010216 RAX: 0000000000000118 RBX: ffffffffffeff00c RCX: ffffc9000e417000 RDX: 0000000000040000 RSI: ffffffff81873f21 RDI: 0000000000000003 RBP: ffff8880842878c0 R08: 0000000000000003 R09: 000000000000ffff R10: 000000000000ffff R11: 0000000000000001 R12: 0000000000000004 R13: ffff88803ac56c00 R14: 000000000000ffff R15: dffffc0000000000 FS: 00007f5c88a16700(0000) GS:ffff8880b9b00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fdaa9f6c058 CR3: 000000003a82c000 CR4: 00000000003506e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ____bpf_skb_load_helper_32 net/core/filter.c:276 [inline] bpf_skb_load_helper_32+0x191/0x220 net/core/filter.c:264 Fixes: f9aefd6b2aa3 ("net: warn if mac header was not set") Reported-by: syzbot Signed-off-by: Eric Dumazet Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20220707123900.945305-1-edumazet@google.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Kevin F. Haggerty Change-Id: Ied13f2f8e7cb522f451294c28ecdda46994ee37e --- kernel/bpf/core.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 95ffe1fac0bf..3f877a7fde30 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -60,11 +60,13 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns { u8 *ptr = NULL; - if (k >= SKF_NET_OFF) + if (k >= SKF_NET_OFF) { ptr = skb_network_header(skb) + k - SKF_NET_OFF; - else if (k >= SKF_LL_OFF) + } else if (k >= SKF_LL_OFF) { + if (unlikely(!skb_mac_header_was_set(skb))) + return NULL; ptr = skb_mac_header(skb) + k - SKF_LL_OFF; - + } if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb)) return ptr; -- cgit v1.2.3 From c5aa3963b4ae7f2f81f39fdc755e9bec7b3ad974 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 18 Dec 2016 01:52:58 +0100 Subject: bpf: fix overflow in prog accounting commit 5ccb071e97fbd9ffe623a0d3977cc6d013bee93c upstream. Commit aaac3ba95e4c ("bpf: charge user for creation of BPF maps and programs") made a wrong assumption of charging against prog->pages. Unlike map->pages, prog->pages are still subject to change when we need to expand the program through bpf_prog_realloc(). This can for example happen during verification stage when we need to expand and rewrite parts of the program. Should the required space cross a page boundary, then prog->pages is not the same anymore as its original value that we used to bpf_prog_charge_memlock() on. Thus, we'll hit a wrap-around during bpf_prog_uncharge_memlock() when prog is freed eventually. I noticed this that despite having unlimited memlock, programs suddenly refused to load with EPERM error due to insufficient memlock. There are two ways to fix this issue. One would be to add a cached variable to struct bpf_prog that takes a snapshot of prog->pages at the time of charging. The other approach is to also account for resizes. I chose to go with the latter for a couple of reasons: i) We want accounting rather to be more accurate instead of further fooling limits, ii) adding yet another page counter on struct bpf_prog would also be a waste just for this purpose. We also do want to charge as early as possible to avoid going into the verifier just to find out later on that we crossed limits. The only place that needs to be fixed is bpf_prog_realloc(), since only here we expand the program, so we try to account for the needed delta and should we fail, call-sites check for outcome anyway. On cBPF to eBPF migrations, we don't grab a reference to the user as they are charged differently. With that in place, my test case worked fine. Fixes: aaac3ba95e4c ("bpf: charge user for creation of BPF maps and programs") Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller [Quentin: backport to 4.9: Adjust context in bpf.h ] Signed-off-by: Quentin Monnet Signed-off-by: Greg Kroah-Hartman Signed-off-by: Kevin F. Haggerty Change-Id: I4b31ee38eaf8618cf8c89e44aaff02cf70542440 --- kernel/bpf/core.c | 16 +++++++++++++--- kernel/bpf/syscall.c | 36 ++++++++++++++++++++++++++++-------- 2 files changed, 41 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 3f877a7fde30..2b1a925489cf 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -107,19 +107,29 @@ struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO | gfp_extra_flags; struct bpf_prog *fp; + u32 pages, delta; + int ret; BUG_ON(fp_old == NULL); size = round_up(size, PAGE_SIZE); - if (size <= fp_old->pages * PAGE_SIZE) + pages = size / PAGE_SIZE; + if (pages <= fp_old->pages) return fp_old; + delta = pages - fp_old->pages; + ret = __bpf_prog_charge(fp_old->aux->user, delta); + if (ret) + return NULL; + fp = __vmalloc(size, gfp_flags, PAGE_KERNEL); - if (fp != NULL) { + if (fp == NULL) { + __bpf_prog_uncharge(fp_old->aux->user, delta); + } else { kmemcheck_annotate_bitfield(fp, meta); memcpy(fp, fp_old, fp_old->pages * PAGE_SIZE); - fp->pages = size / PAGE_SIZE; + fp->pages = pages; fp->aux->prog = fp; /* We keep fp->aux from fp_old around in the new diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index a73a056ccd88..b573fcb9af39 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -652,19 +652,39 @@ static void free_used_maps(struct bpf_prog_aux *aux) kfree(aux->used_maps); } +int __bpf_prog_charge(struct user_struct *user, u32 pages) +{ + unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + unsigned long user_bufs; + + if (user) { + user_bufs = atomic_long_add_return(pages, &user->locked_vm); + if (user_bufs > memlock_limit) { + atomic_long_sub(pages, &user->locked_vm); + return -EPERM; + } + } + + return 0; +} + +void __bpf_prog_uncharge(struct user_struct *user, u32 pages) +{ + if (user) + atomic_long_sub(pages, &user->locked_vm); +} + static int bpf_prog_charge_memlock(struct bpf_prog *prog) { struct user_struct *user = get_current_user(); - unsigned long memlock_limit; - - memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + int ret; - atomic_long_add(prog->pages, &user->locked_vm); - if (atomic_long_read(&user->locked_vm) > memlock_limit) { - atomic_long_sub(prog->pages, &user->locked_vm); + ret = __bpf_prog_charge(user, prog->pages); + if (ret) { free_uid(user); - return -EPERM; + return ret; } + prog->aux->user = user; return 0; } @@ -673,7 +693,7 @@ static void bpf_prog_uncharge_memlock(struct bpf_prog *prog) { struct user_struct *user = prog->aux->user; - atomic_long_sub(prog->pages, &user->locked_vm); + __bpf_prog_uncharge(user, prog->pages); free_uid(user); } -- cgit v1.2.3 From e7aede4896c0995c3c4312a9e90ff0ae304afc09 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 1 Dec 2016 08:48:04 -0800 Subject: bpf: Add new cgroup attach type to enable sock modifications Add new cgroup based program type, BPF_PROG_TYPE_CGROUP_SOCK. Similar to BPF_PROG_TYPE_CGROUP_SKB programs can be attached to a cgroup and run any time a process in the cgroup opens an AF_INET or AF_INET6 socket. Currently only sk_bound_dev_if is exported to userspace for modification by a bpf program. This allows a cgroup to be configured such that AF_INET{6} sockets opened by processes are automatically bound to a specific device. In turn, this enables the running of programs that do not support SO_BINDTODEVICE in a specific VRF context / L3 domain. Signed-off-by: David Ahern Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller Change-Id: I96a6f6f8f650c494d8c173dbb42580a25698368e --- kernel/bpf/cgroup.c | 33 +++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 21 ++++++++++++++++++++- 2 files changed, 53 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 357ce8355d57..8210c7dd7532 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -424,3 +424,36 @@ int __cgroup_bpf_run_filter(struct sock *sk, return ret == 1 ? 0 : -EPERM; } EXPORT_SYMBOL(__cgroup_bpf_run_filter); + +/** + * __cgroup_bpf_run_filter_sk() - Run a program on a sock + * @sk: sock structure to manipulate + * @type: The type of program to be exectuted + * + * socket is passed is expected to be of type INET or INET6. + * + * The program type passed in via @type must be suitable for sock + * filtering. No further check is performed to assert that. + * + * This function will return %-EPERM if any if an attached program was found + * and if it returned != 1 during execution. In all other cases, 0 is returned. + */ +int __cgroup_bpf_run_filter_sk(struct sock *sk, + enum bpf_attach_type type) +{ + struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); + struct bpf_prog *prog; + int ret = 0; + + + rcu_read_lock(); + + prog = rcu_dereference(cgrp->bpf.effective[type]->progs[0]); + if (prog) + ret = BPF_PROG_RUN(prog, sk) == 1 ? 0 : -EPERM; + + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index b573fcb9af39..f65bd2dc07f8 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -953,7 +953,24 @@ static int bpf_prog_attach(const union bpf_attr *attr) bpf_prog_put(prog); cgroup_put(cgrp); break; + case BPF_CGROUP_INET_SOCK_CREATE: + prog = bpf_prog_get_type(attr->attach_bpf_fd, + BPF_PROG_TYPE_CGROUP_SOCK); + if (IS_ERR(prog)) + return PTR_ERR(prog); + + cgrp = cgroup_get_from_fd(attr->target_fd); + if (IS_ERR(cgrp)) { + bpf_prog_put(prog); + return PTR_ERR(cgrp); + } + ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type, + attr->attach_flags); + if (ret) + bpf_prog_put(prog); + cgroup_put(cgrp); + break; default: return -EINVAL; } @@ -981,7 +998,9 @@ static int bpf_prog_detach(const union bpf_attr *attr) case BPF_CGROUP_INET_EGRESS: ptype = BPF_PROG_TYPE_CGROUP_SKB; break; - + case BPF_CGROUP_INET_SOCK_CREATE: + ptype = BPF_PROG_TYPE_CGROUP_SOCK; + break; default: return -EINVAL; } -- cgit v1.2.3 From ada02e996b52d9389d76b72213e01ffcdd648e96 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Mon, 19 Nov 2018 00:51:56 +0100 Subject: BACKPORT: signal: add pidfd_send_signal() syscall The kill() syscall operates on process identifiers (pid). After a process has exited its pid can be reused by another process. If a caller sends a signal to a reused pid it will end up signaling the wrong process. This issue has often surfaced and there has been a push to address this problem [1]. This patch uses file descriptors (fd) from proc/ as stable handles on struct pid. Even if a pid is recycled the handle will not change. The fd can be used to send signals to the process it refers to. Thus, the new syscall pidfd_send_signal() is introduced to solve this problem. Instead of pids it operates on process fds (pidfd). /* prototype and argument /* long pidfd_send_signal(int pidfd, int sig, siginfo_t *info, unsigned int flags); /* syscall number 424 */ The syscall number was chosen to be 424 to align with Arnd's rework in his y2038 to minimize merge conflicts (cf. [25]). In addition to the pidfd and signal argument it takes an additional siginfo_t and flags argument. If the siginfo_t argument is NULL then pidfd_send_signal() is equivalent to kill(, ). If it is not NULL pidfd_send_signal() is equivalent to rt_sigqueueinfo(). The flags argument is added to allow for future extensions of this syscall. It currently needs to be passed as 0. Failing to do so will cause EINVAL. /* pidfd_send_signal() replaces multiple pid-based syscalls */ The pidfd_send_signal() syscall currently takes on the job of rt_sigqueueinfo(2) and parts of the functionality of kill(2), Namely, when a positive pid is passed to kill(2). It will however be possible to also replace tgkill(2) and rt_tgsigqueueinfo(2) if this syscall is extended. /* sending signals to threads (tid) and process groups (pgid) */ Specifically, the pidfd_send_signal() syscall does currently not operate on process groups or threads. This is left for future extensions. In order to extend the syscall to allow sending signal to threads and process groups appropriately named flags (e.g. PIDFD_TYPE_PGID, and PIDFD_TYPE_TID) should be added. This implies that the flags argument will determine what is signaled and not the file descriptor itself. Put in other words, grouping in this api is a property of the flags argument not a property of the file descriptor (cf. [13]). Clarification for this has been requested by Eric (cf. [19]). When appropriate extensions through the flags argument are added then pidfd_send_signal() can additionally replace the part of kill(2) which operates on process groups as well as the tgkill(2) and rt_tgsigqueueinfo(2) syscalls. How such an extension could be implemented has been very roughly sketched in [14], [15], and [16]. However, this should not be taken as a commitment to a particular implementation. There might be better ways to do it. Right now this is intentionally left out to keep this patchset as simple as possible (cf. [4]). /* naming */ The syscall had various names throughout iterations of this patchset: - procfd_signal() - procfd_send_signal() - taskfd_send_signal() In the last round of reviews it was pointed out that given that if the flags argument decides the scope of the signal instead of different types of fds it might make sense to either settle for "procfd_" or "pidfd_" as prefix. The community was willing to accept either (cf. [17] and [18]). Given that one developer expressed strong preference for the "pidfd_" prefix (cf. [13]) and with other developers less opinionated about the name we should settle for "pidfd_" to avoid further bikeshedding. The "_send_signal" suffix was chosen to reflect the fact that the syscall takes on the job of multiple syscalls. It is therefore intentional that the name is not reminiscent of neither kill(2) nor rt_sigqueueinfo(2). Not the fomer because it might imply that pidfd_send_signal() is a replacement for kill(2), and not the latter because it is a hassle to remember the correct spelling - especially for non-native speakers - and because it is not descriptive enough of what the syscall actually does. The name "pidfd_send_signal" makes it very clear that its job is to send signals. /* zombies */ Zombies can be signaled just as any other process. No special error will be reported since a zombie state is an unreliable state (cf. [3]). However, this can be added as an extension through the @flags argument if the need ever arises. /* cross-namespace signals */ The patch currently enforces that the signaler and signalee either are in the same pid namespace or that the signaler's pid namespace is an ancestor of the signalee's pid namespace. This is done for the sake of simplicity and because it is unclear to what values certain members of struct siginfo_t would need to be set to (cf. [5], [6]). /* compat syscalls */ It became clear that we would like to avoid adding compat syscalls (cf. [7]). The compat syscall handling is now done in kernel/signal.c itself by adding __copy_siginfo_from_user_generic() which lets us avoid compat syscalls (cf. [8]). It should be noted that the addition of __copy_siginfo_from_user_any() is caused by a bug in the original implementation of rt_sigqueueinfo(2) (cf. 12). With upcoming rework for syscall handling things might improve significantly (cf. [11]) and __copy_siginfo_from_user_any() will not gain any additional callers. /* testing */ This patch was tested on x64 and x86. /* userspace usage */ An asciinema recording for the basic functionality can be found under [9]. With this patch a process can be killed via: #define _GNU_SOURCE #include #include #include #include #include #include #include #include #include #include static inline int do_pidfd_send_signal(int pidfd, int sig, siginfo_t *info, unsigned int flags) { #ifdef __NR_pidfd_send_signal return syscall(__NR_pidfd_send_signal, pidfd, sig, info, flags); #else return -ENOSYS; #endif } int main(int argc, char *argv[]) { int fd, ret, saved_errno, sig; if (argc < 3) exit(EXIT_FAILURE); fd = open(argv[1], O_DIRECTORY | O_CLOEXEC); if (fd < 0) { printf("%s - Failed to open \"%s\"\n", strerror(errno), argv[1]); exit(EXIT_FAILURE); } sig = atoi(argv[2]); printf("Sending signal %d to process %s\n", sig, argv[1]); ret = do_pidfd_send_signal(fd, sig, NULL, 0); saved_errno = errno; close(fd); errno = saved_errno; if (ret < 0) { printf("%s - Failed to send signal %d to process %s\n", strerror(errno), sig, argv[1]); exit(EXIT_FAILURE); } exit(EXIT_SUCCESS); } /* Q&A * Given that it seems the same questions get asked again by people who are * late to the party it makes sense to add a Q&A section to the commit * message so it's hopefully easier to avoid duplicate threads. * * For the sake of progress please consider these arguments settled unless * there is a new point that desperately needs to be addressed. Please make * sure to check the links to the threads in this commit message whether * this has not already been covered. */ Q-01: (Florian Weimer [20], Andrew Morton [21]) What happens when the target process has exited? A-01: Sending the signal will fail with ESRCH (cf. [22]). Q-02: (Andrew Morton [21]) Is the task_struct pinned by the fd? A-02: No. A reference to struct pid is kept. struct pid - as far as I understand - was created exactly for the reason to not require to pin struct task_struct (cf. [22]). Q-03: (Andrew Morton [21]) Does the entire procfs directory remain visible? Just one entry within it? A-03: The same thing that happens right now when you hold a file descriptor to /proc/ open (cf. [22]). Q-04: (Andrew Morton [21]) Does the pid remain reserved? A-04: No. This patchset guarantees a stable handle not that pids are not recycled (cf. [22]). Q-05: (Andrew Morton [21]) Do attempts to signal that fd return errors? A-05: See {Q,A}-01. Q-06: (Andrew Morton [22]) Is there a cleaner way of obtaining the fd? Another syscall perhaps. A-06: Userspace can already trivially retrieve file descriptors from procfs so this is something that we will need to support anyway. Hence, there's no immediate need to add another syscalls just to make pidfd_send_signal() not dependent on the presence of procfs. However, adding a syscalls to get such file descriptors is planned for a future patchset (cf. [22]). Q-07: (Andrew Morton [21] and others) This fd-for-a-process sounds like a handy thing and people may well think up other uses for it in the future, probably unrelated to signals. Are the code and the interface designed to permit such future applications? A-07: Yes (cf. [22]). Q-08: (Andrew Morton [21] and others) Now I think about it, why a new syscall? This thing is looking rather like an ioctl? A-08: This has been extensively discussed. It was agreed that a syscall is preferred for a variety or reasons. Here are just a few taken from prior threads. Syscalls are safer than ioctl()s especially when signaling to fds. Processes are a core kernel concept so a syscall seems more appropriate. The layout of the syscall with its four arguments would require the addition of a custom struct for the ioctl() thereby causing at least the same amount or even more complexity for userspace than a simple syscall. The new syscall will replace multiple other pid-based syscalls (see description above). The file-descriptors-for-processes concept introduced with this syscall will be extended with other syscalls in the future. See also [22], [23] and various other threads already linked in here. Q-09: (Florian Weimer [24]) What happens if you use the new interface with an O_PATH descriptor? A-09: pidfds opened as O_PATH fds cannot be used to send signals to a process (cf. [2]). Signaling processes through pidfds is the equivalent of writing to a file. Thus, this is not an operation that operates "purely at the file descriptor level" as required by the open(2) manpage. See also [4]. /* References */ [1]: https://lore.kernel.org/lkml/20181029221037.87724-1-dancol@google.com/ [2]: https://lore.kernel.org/lkml/874lbtjvtd.fsf@oldenburg2.str.redhat.com/ [3]: https://lore.kernel.org/lkml/20181204132604.aspfupwjgjx6fhva@brauner.io/ [4]: https://lore.kernel.org/lkml/20181203180224.fkvw4kajtbvru2ku@brauner.io/ [5]: https://lore.kernel.org/lkml/20181121213946.GA10795@mail.hallyn.com/ [6]: https://lore.kernel.org/lkml/20181120103111.etlqp7zop34v6nv4@brauner.io/ [7]: https://lore.kernel.org/lkml/36323361-90BD-41AF-AB5B-EE0D7BA02C21@amacapital.net/ [8]: https://lore.kernel.org/lkml/87tvjxp8pc.fsf@xmission.com/ [9]: https://asciinema.org/a/IQjuCHew6bnq1cr78yuMv16cy [11]: https://lore.kernel.org/lkml/F53D6D38-3521-4C20-9034-5AF447DF62FF@amacapital.net/ [12]: https://lore.kernel.org/lkml/87zhtjn8ck.fsf@xmission.com/ [13]: https://lore.kernel.org/lkml/871s6u9z6u.fsf@xmission.com/ [14]: https://lore.kernel.org/lkml/20181206231742.xxi4ghn24z4h2qki@brauner.io/ [15]: https://lore.kernel.org/lkml/20181207003124.GA11160@mail.hallyn.com/ [16]: https://lore.kernel.org/lkml/20181207015423.4miorx43l3qhppfz@brauner.io/ [17]: https://lore.kernel.org/lkml/CAGXu5jL8PciZAXvOvCeCU3wKUEB_dU-O3q0tDw4uB_ojMvDEew@mail.gmail.com/ [18]: https://lore.kernel.org/lkml/20181206222746.GB9224@mail.hallyn.com/ [19]: https://lore.kernel.org/lkml/20181208054059.19813-1-christian@brauner.io/ [20]: https://lore.kernel.org/lkml/8736rebl9s.fsf@oldenburg.str.redhat.com/ [21]: https://lore.kernel.org/lkml/20181228152012.dbf0508c2508138efc5f2bbe@linux-foundation.org/ [22]: https://lore.kernel.org/lkml/20181228233725.722tdfgijxcssg76@brauner.io/ [23]: https://lwn.net/Articles/773459/ [24]: https://lore.kernel.org/lkml/8736rebl9s.fsf@oldenburg.str.redhat.com/ [25]: https://lore.kernel.org/lkml/CAK8P3a0ej9NcJM8wXNPbcGUyOUZYX+VLoDFdbenW3s3114oQZw@mail.gmail.com/ Cc: "Eric W. Biederman" Cc: Jann Horn Cc: Andy Lutomirsky Cc: Andrew Morton Cc: Oleg Nesterov Cc: Al Viro Cc: Florian Weimer Signed-off-by: Christian Brauner Reviewed-by: Tycho Andersen Reviewed-by: Kees Cook Reviewed-by: David Howells Acked-by: Arnd Bergmann Acked-by: Thomas Gleixner Acked-by: Serge Hallyn Acked-by: Aleksa Sarai (cherry picked from commit 3eb39f47934f9d5a3027fe00d906a45fe3a15fad) Conflicts: arch/x86/entry/syscalls/syscall_32.tbl - trivial manual merge arch/x86/entry/syscalls/syscall_64.tbl - trivial manual merge include/linux/proc_fs.h - trivial manual merge include/linux/syscalls.h - trivial manual merge include/uapi/asm-generic/unistd.h - trivial manual merge kernel/signal.c - struct kernel_siginfo does not exist in 4.14 kernel/sys_ni.c - cond_syscall is used instead of COND_SYSCALL arch/x86/entry/syscalls/syscall_32.tbl arch/x86/entry/syscalls/syscall_64.tbl (1. manual merges because of 4.14 differences 2. change prepare_kill_siginfo() to use struct siginfo instead of kernel_siginfo 3. use copy_from_user() instead of copy_siginfo_from_user() in copy_siginfo_from_user_any() 4. replaced COND_SYSCALL with cond_syscall 5. Removed __ia32_sys_pidfd_send_signal in arch/x86/entry/syscalls/syscall_32.tbl. 6. Replaced __x64_sys_pidfd_send_signal with sys_pidfd_send_signal in arch/x86/entry/syscalls/syscall_64.tbl.) Bug: 135608568 Test: test program using syscall(__NR_pidfd_send_signal,..) to send SIGKILL Change-Id: I34da11c63ac8cafb0353d9af24c820cef519ec27 Signed-off-by: Suren Baghdasaryan Signed-off-by: electimon --- kernel/signal.c | 131 +++++++++++++++++++++++++++++++++++++++++++++++++++++--- kernel/sys_ni.c | 1 + 2 files changed, 127 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/signal.c b/kernel/signal.c index a699055ebfe8..6f97979faec5 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -14,7 +14,9 @@ #include #include #include +#include #include +#include #include #include #include @@ -2922,6 +2924,15 @@ SYSCALL_DEFINE4(rt_sigtimedwait, const sigset_t __user *, uthese, return ret; } +static inline void prepare_kill_siginfo(int sig, struct siginfo *info) +{ + info->si_signo = sig; + info->si_errno = 0; + info->si_code = SI_USER; + info->si_pid = task_tgid_vnr(current); + info->si_uid = from_kuid_munged(current_user_ns(), current_uid()); +} + /** * sys_kill - send a signal to a process * @pid: the PID of the process @@ -2931,15 +2942,125 @@ SYSCALL_DEFINE2(kill, pid_t, pid, int, sig) { struct siginfo info; - info.si_signo = sig; - info.si_errno = 0; - info.si_code = SI_USER; - info.si_pid = task_tgid_vnr(current); - info.si_uid = from_kuid_munged(current_user_ns(), current_uid()); + prepare_kill_siginfo(sig, &info); return kill_something_info(sig, &info, pid); } +#ifdef CONFIG_PROC_FS +/* + * Verify that the signaler and signalee either are in the same pid namespace + * or that the signaler's pid namespace is an ancestor of the signalee's pid + * namespace. + */ +static bool access_pidfd_pidns(struct pid *pid) +{ + struct pid_namespace *active = task_active_pid_ns(current); + struct pid_namespace *p = ns_of_pid(pid); + + for (;;) { + if (!p) + return false; + if (p == active) + break; + p = p->parent; + } + + return true; +} + +static int copy_siginfo_from_user_any(siginfo_t *kinfo, siginfo_t __user *info) +{ +#ifdef CONFIG_COMPAT + /* + * Avoid hooking up compat syscalls and instead handle necessary + * conversions here. Note, this is a stop-gap measure and should not be + * considered a generic solution. + */ + if (in_compat_syscall()) + return copy_siginfo_from_user32( + kinfo, (struct compat_siginfo __user *)info); +#endif + return copy_from_user(kinfo, info, sizeof(siginfo_t)); +} + +/** + * sys_pidfd_send_signal - send a signal to a process through a task file + * descriptor + * @pidfd: the file descriptor of the process + * @sig: signal to be sent + * @info: the signal info + * @flags: future flags to be passed + * + * The syscall currently only signals via PIDTYPE_PID which covers + * kill(, . It does not signal threads or process + * groups. + * In order to extend the syscall to threads and process groups the @flags + * argument should be used. In essence, the @flags argument will determine + * what is signaled and not the file descriptor itself. Put in other words, + * grouping is a property of the flags argument not a property of the file + * descriptor. + * + * Return: 0 on success, negative errno on failure + */ +SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, + siginfo_t __user *, info, unsigned int, flags) +{ + int ret; + struct fd f; + struct pid *pid; + siginfo_t kinfo; + + /* Enforce flags be set to 0 until we add an extension. */ + if (flags) + return -EINVAL; + + f = fdget_raw(pidfd); + if (!f.file) + return -EBADF; + + /* Is this a pidfd? */ + pid = tgid_pidfd_to_pid(f.file); + if (IS_ERR(pid)) { + ret = PTR_ERR(pid); + goto err; + } + + ret = -EINVAL; + if (!access_pidfd_pidns(pid)) + goto err; + + if (info) { + ret = copy_siginfo_from_user_any(&kinfo, info); + if (unlikely(ret)) + goto err; + + ret = -EINVAL; + if (unlikely(sig != kinfo.si_signo)) + goto err; + + if ((task_pid(current) != pid) && + (kinfo.si_code >= 0 || kinfo.si_code == SI_TKILL)) { + /* Only allow sending arbitrary signals to yourself. */ + ret = -EPERM; + if (kinfo.si_code != SI_USER) + goto err; + + /* Turn this into a regular kill signal. */ + prepare_kill_siginfo(sig, &kinfo); + } + } else { + prepare_kill_siginfo(sig, &kinfo); + } + + ret = kill_pid_info(sig, &kinfo, pid); + +err: + fdput(f); + return ret; +} +#endif /* CONFIG_PROC_FS */ + static int do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info) { diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 0623787ec67a..109267bfa321 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -152,6 +152,7 @@ cond_syscall(sys_io_cancel); cond_syscall(sys_io_getevents); cond_syscall(sys_sysfs); cond_syscall(sys_syslog); +cond_syscall(sys_pidfd_send_signal); cond_syscall(sys_process_vm_readv); cond_syscall(sys_process_vm_writev); cond_syscall(compat_sys_process_vm_readv); -- cgit v1.2.3 From 229e1bdd624eb6e2a4b946ae938485a05b37438a Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Sat, 30 Mar 2019 03:12:32 +0100 Subject: UPSTREAM: signal: don't silently convert SI_USER signals to non-current pidfd The current sys_pidfd_send_signal() silently turns signals with explicit SI_USER context that are sent to non-current tasks into signals with kernel-generated siginfo. This is unlike do_rt_sigqueueinfo(), which returns -EPERM in this case. If a user actually wants to send a signal with kernel-provided siginfo, they can do that with pidfd_send_signal(pidfd, sig, NULL, 0); so allowing this case is unnecessary. Instead of silently replacing the siginfo, just bail out with an error; this is consistent with other interfaces and avoids special-casing behavior based on security checks. Fixes: 3eb39f47934f ("signal: add pidfd_send_signal() syscall") Signed-off-by: Jann Horn Signed-off-by: Christian Brauner (cherry picked from commit 556a888a14afe27164191955618990fb3ccc9aad) Bug: 135608568 Test: test program using syscall(__NR_pidfd_send_signal,..) to send SIGKILL Change-Id: I493af671b82c43bff1425ee24550d2fb9aa6d961 Signed-off-by: Suren Baghdasaryan --- kernel/signal.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/kernel/signal.c b/kernel/signal.c index 6f97979faec5..3c06e9a2a117 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -3039,16 +3039,11 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, if (unlikely(sig != kinfo.si_signo)) goto err; + /* Only allow sending arbitrary signals to yourself. */ + ret = -EPERM; if ((task_pid(current) != pid) && - (kinfo.si_code >= 0 || kinfo.si_code == SI_TKILL)) { - /* Only allow sending arbitrary signals to yourself. */ - ret = -EPERM; - if (kinfo.si_code != SI_USER) - goto err; - - /* Turn this into a regular kill signal. */ - prepare_kill_siginfo(sig, &kinfo); - } + (kinfo.si_code >= 0 || kinfo.si_code == SI_TKILL)) + goto err; } else { prepare_kill_siginfo(sig, &kinfo); } -- cgit v1.2.3 From de80525cd462f5a87a8997ecbaba2ffd3bd1bc68 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 18 Apr 2019 12:18:39 +0200 Subject: UPSTREAM: signal: use fdget() since we don't allow O_PATH As stated in the original commit for pidfd_send_signal() we don't allow to signal processes through O_PATH file descriptors since it is semantically equivalent to a write on the pidfd. We already correctly error out right now and return EBADF if an O_PATH fd is passed. This is because we use file->f_op to detect whether a pidfd is passed and O_PATH fds have their file->f_op set to empty_fops in do_dentry_open() and thus fail the test. Thus, there is no regression. It's just semantically correct to use fdget() and return an error right from there instead of taking a reference and returning an error later. Signed-off-by: Christian Brauner Acked-by: Oleg Nesterov Cc: Arnd Bergmann Cc: "Eric W. Biederman" Cc: Kees Cook Cc: Thomas Gleixner Cc: Jann Horn Cc: David Howells Cc: "Michael Kerrisk (man-pages)" Cc: Andy Lutomirsky Cc: Andrew Morton Cc: Oleg Nesterov Cc: Aleksa Sarai Cc: Al Viro Signed-off-by: Linus Torvalds (cherry picked from commit 738a7832d21e3d911fcddab98ce260b79010b461) Bug: 135608568 Test: test program using syscall(__NR_pidfd_send_signal,..) to send SIGKILL Change-Id: Id52eaadf9da371fb2d9caae4df49627760de7229 Signed-off-by: Suren Baghdasaryan --- kernel/signal.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/signal.c b/kernel/signal.c index 3c06e9a2a117..bc8e3223161c 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -3015,7 +3015,7 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, if (flags) return -EINVAL; - f = fdget_raw(pidfd); + f = fdget(pidfd); if (!f.file) return -EBADF; -- cgit v1.2.3 From f044fa00d72a7b947e77c479fa3114076cbcb4f8 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 27 Mar 2019 13:04:15 +0100 Subject: BACKPORT: clone: add CLONE_PIDFD This patchset makes it possible to retrieve pid file descriptors at process creation time by introducing the new flag CLONE_PIDFD to the clone() system call. Linus originally suggested to implement this as a new flag to clone() instead of making it a separate system call. As spotted by Linus, there is exactly one bit for clone() left. CLONE_PIDFD creates file descriptors based on the anonymous inode implementation in the kernel that will also be used to implement the new mount api. They serve as a simple opaque handle on pids. Logically, this makes it possible to interpret a pidfd differently, narrowing or widening the scope of various operations (e.g. signal sending). Thus, a pidfd cannot just refer to a tgid, but also a tid, or in theory - given appropriate flag arguments in relevant syscalls - a process group or session. A pidfd does not represent a privilege. This does not imply it cannot ever be that way but for now this is not the case. A pidfd comes with additional information in fdinfo if the kernel supports procfs. The fdinfo file contains the pid of the process in the callers pid namespace in the same format as the procfs status file, i.e. "Pid:\t%d". As suggested by Oleg, with CLONE_PIDFD the pidfd is returned in the parent_tidptr argument of clone. This has the advantage that we can give back the associated pid and the pidfd at the same time. To remove worries about missing metadata access this patchset comes with a sample program that illustrates how a combination of CLONE_PIDFD, and pidfd_send_signal() can be used to gain race-free access to process metadata through /proc/. The sample program can easily be translated into a helper that would be suitable for inclusion in libc so that users don't have to worry about writing it themselves. Suggested-by: Linus Torvalds Signed-off-by: Christian Brauner Co-developed-by: Jann Horn Signed-off-by: Jann Horn Reviewed-by: Oleg Nesterov Cc: Arnd Bergmann Cc: "Eric W. Biederman" Cc: Kees Cook Cc: Thomas Gleixner Cc: David Howells Cc: "Michael Kerrisk (man-pages)" Cc: Andy Lutomirsky Cc: Andrew Morton Cc: Aleksa Sarai Cc: Linus Torvalds Cc: Al Viro (cherry picked from commit b3e5838252665ee4cfa76b82bdf1198dca81e5be) Conflicts: kernel/fork.c (1. Replaced proc_pid_ns() with its direct implementation.) Bug: 135608568 Test: test program using syscall(__NR_sys_pidfd_open,..) and poll() Change-Id: I3c804a92faea686e5bf7f99df893fe3a5d87ddf7 Signed-off-by: Suren Baghdasaryan Signed-off-by: electimon --- kernel/fork.c | 107 +++++++++++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 103 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index 92a0df862115..50897504f31c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -11,6 +11,7 @@ * management can be a bitch. See 'mm/memory.c': 'copy_page_range()' */ +#include #include #include #include @@ -38,6 +39,7 @@ #include #include #include +#include #include #include #include @@ -1294,6 +1296,58 @@ init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid) task->pids[type].pid = pid; } +static int pidfd_release(struct inode *inode, struct file *file) +{ + struct pid *pid = file->private_data; + + file->private_data = NULL; + put_pid(pid); + return 0; +} + +#ifdef CONFIG_PROC_FS +static void pidfd_show_fdinfo(struct seq_file *m, struct file *f) +{ + struct pid_namespace *ns = file_inode(m->file)->i_sb->s_fs_info; + struct pid *pid = f->private_data; + + seq_put_decimal_ull(m, "Pid:\t", pid_nr_ns(pid, ns)); + seq_putc(m, '\n'); +} +#endif + +const struct file_operations pidfd_fops = { + .release = pidfd_release, +#ifdef CONFIG_PROC_FS + .show_fdinfo = pidfd_show_fdinfo, +#endif +}; + +/** + * pidfd_create() - Create a new pid file descriptor. + * + * @pid: struct pid that the pidfd will reference + * + * This creates a new pid file descriptor with the O_CLOEXEC flag set. + * + * Note, that this function can only be called after the fd table has + * been unshared to avoid leaking the pidfd to the new process. + * + * Return: On success, a cloexec pidfd is returned. + * On error, a negative errno number will be returned. + */ +static int pidfd_create(struct pid *pid) +{ + int fd; + + fd = anon_inode_getfd("[pidfd]", &pidfd_fops, get_pid(pid), + O_RDWR | O_CLOEXEC); + if (fd < 0) + put_pid(pid); + + return fd; +} + /* * This creates a new process as a copy of the old one, * but does not actually start it yet. @@ -1305,13 +1359,14 @@ init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid) static struct task_struct *copy_process(unsigned long clone_flags, unsigned long stack_start, unsigned long stack_size, + int __user *parent_tidptr, int __user *child_tidptr, struct pid *pid, int trace, unsigned long tls, int node) { - int retval; + int pidfd = -1, retval; struct task_struct *p; if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS)) @@ -1356,6 +1411,31 @@ static struct task_struct *copy_process(unsigned long clone_flags, return ERR_PTR(-EINVAL); } + if (clone_flags & CLONE_PIDFD) { + int reserved; + + /* + * - CLONE_PARENT_SETTID is useless for pidfds and also + * parent_tidptr is used to return pidfds. + * - CLONE_DETACHED is blocked so that we can potentially + * reuse it later for CLONE_PIDFD. + * - CLONE_THREAD is blocked until someone really needs it. + */ + if (clone_flags & + (CLONE_DETACHED | CLONE_PARENT_SETTID | CLONE_THREAD)) + return ERR_PTR(-EINVAL); + + /* + * Verify that parent_tidptr is sane so we can potentially + * reuse it later. + */ + if (get_user(reserved, parent_tidptr)) + return ERR_PTR(-EFAULT); + + if (reserved != 0) + return ERR_PTR(-EINVAL); + } + retval = security_task_create(clone_flags); if (retval) goto fork_out; @@ -1538,6 +1618,22 @@ static struct task_struct *copy_process(unsigned long clone_flags, } } + /* + * This has to happen after we've potentially unshared the file + * descriptor table (so that the pidfd doesn't leak into the child + * if the fd table isn't shared). + */ + if (clone_flags & CLONE_PIDFD) { + retval = pidfd_create(pid); + if (retval < 0) + goto bad_fork_free_pid; + + pidfd = retval; + retval = put_user(pidfd, parent_tidptr); + if (retval) + goto bad_fork_put_pidfd; + } + #ifdef CONFIG_BLOCK p->plug = NULL; #endif @@ -1587,7 +1683,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, */ retval = cgroup_can_fork(p); if (retval) - goto bad_fork_free_pid; + goto bad_fork_put_pidfd; /* * From this point on we must avoid any synchronous user-space @@ -1698,6 +1794,9 @@ bad_fork_cancel_cgroup: spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); cgroup_cancel_fork(p); +bad_fork_put_pidfd: + if (clone_flags & CLONE_PIDFD) + sys_close(pidfd); bad_fork_free_pid: threadgroup_change_end(current); if (pid != &init_struct_pid) @@ -1754,7 +1853,7 @@ static inline void init_idle_pids(struct pid_link *links) struct task_struct *fork_idle(int cpu) { struct task_struct *task; - task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0, + task = copy_process(CLONE_VM, 0, 0, NULL, NULL, &init_struct_pid, 0, 0, cpu_to_node(cpu)); if (!IS_ERR(task)) { init_idle_pids(task->pids); @@ -1799,7 +1898,7 @@ long _do_fork(unsigned long clone_flags, trace = 0; } - p = copy_process(clone_flags, stack_start, stack_size, + p = copy_process(clone_flags, stack_start, stack_size, parent_tidptr, child_tidptr, NULL, trace, tls, NUMA_NO_NODE); /* * Do this prior waking up the new thread - the thread pointer -- cgit v1.2.3 From fc7d707593e38a5b62aaa6026e4805bbd0113ac9 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 17 Apr 2019 22:50:25 +0200 Subject: BACKPORT: signal: support CLONE_PIDFD with pidfd_send_signal Let pidfd_send_signal() use pidfds retrieved via CLONE_PIDFD. With this patch pidfd_send_signal() becomes independent of procfs. This fullfils the request made when we merged the pidfd_send_signal() patchset. The pidfd_send_signal() syscall is now always available allowing for it to be used by users without procfs mounted or even users without procfs support compiled into the kernel. Signed-off-by: Christian Brauner Co-developed-by: Jann Horn Signed-off-by: Jann Horn Acked-by: Oleg Nesterov Cc: Arnd Bergmann Cc: "Eric W. Biederman" Cc: Kees Cook Cc: Thomas Gleixner Cc: David Howells Cc: "Michael Kerrisk (man-pages)" Cc: Andy Lutomirsky Cc: Andrew Morton Cc: Aleksa Sarai Cc: Linus Torvalds Cc: Al Viro (cherry picked from commit 2151ad1b067275730de1b38c7257478cae47d29e) Conflicts: kernel/sys_ni.c (1. Replaced COND_SYSCALL with cond_syscall.) Bug: 135608568 Test: test program using syscall(__NR_sys_pidfd_open,..) and poll() Change-Id: I621fe6547397e0e68c560d7da60ef7715deb290c Signed-off-by: Suren Baghdasaryan --- kernel/signal.c | 12 +++++++++--- kernel/sys_ni.c | 1 - 2 files changed, 9 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/signal.c b/kernel/signal.c index bc8e3223161c..437778f62bfb 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2947,7 +2947,6 @@ SYSCALL_DEFINE2(kill, pid_t, pid, int, sig) return kill_something_info(sig, &info, pid); } -#ifdef CONFIG_PROC_FS /* * Verify that the signaler and signalee either are in the same pid namespace * or that the signaler's pid namespace is an ancestor of the signalee's pid @@ -2969,6 +2968,14 @@ static bool access_pidfd_pidns(struct pid *pid) return true; } +static struct pid *pidfd_to_pid(const struct file *file) +{ + if (file->f_op == &pidfd_fops) + return file->private_data; + + return tgid_pidfd_to_pid(file); +} + static int copy_siginfo_from_user_any(siginfo_t *kinfo, siginfo_t __user *info) { #ifdef CONFIG_COMPAT @@ -3020,7 +3027,7 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, return -EBADF; /* Is this a pidfd? */ - pid = tgid_pidfd_to_pid(f.file); + pid = pidfd_to_pid(f.file); if (IS_ERR(pid)) { ret = PTR_ERR(pid); goto err; @@ -3054,7 +3061,6 @@ err: fdput(f); return ret; } -#endif /* CONFIG_PROC_FS */ static int do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info) diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 109267bfa321..0623787ec67a 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -152,7 +152,6 @@ cond_syscall(sys_io_cancel); cond_syscall(sys_io_getevents); cond_syscall(sys_sysfs); cond_syscall(sys_syslog); -cond_syscall(sys_pidfd_send_signal); cond_syscall(sys_process_vm_readv); cond_syscall(sys_process_vm_writev); cond_syscall(compat_sys_process_vm_readv); -- cgit v1.2.3 From 5500316dc8d87d8786c1389ddb2cbbeca24a4b07 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 10 May 2019 11:53:46 +0200 Subject: UPSTREAM: fork: do not release lock that wasn't taken Avoid calling cgroup_threadgroup_change_end() without having called cgroup_threadgroup_change_begin() first. During process creation we need to check whether the cgroup we are in allows us to fork. To perform this check the cgroup needs to guard itself against threadgroup changes and takes a lock. Prior to CLONE_PIDFD the cleanup target "bad_fork_free_pid" would also need to call cgroup_threadgroup_change_end() because said lock had already been taken. However, this is not the case anymore with the addition of CLONE_PIDFD. We are now allocating a pidfd before we check whether the cgroup we're in can fork and thus prior to taking the lock. So when copy_process() fails at the right step it would release a lock we haven't taken. This bug is not even very subtle to be honest. It's just not very clear from the naming of cgroup_threadgroup_change_{begin,end}() that a lock is taken. Here's the relevant splat: entry_SYSENTER_compat+0x70/0x7f arch/x86/entry/entry_64_compat.S:139 RIP: 0023:0xf7fec849 Code: 85 d2 74 02 89 0a 5b 5d c3 8b 04 24 c3 8b 14 24 c3 8b 3c 24 c3 90 90 90 90 90 90 90 90 90 90 90 90 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 eb 0d 90 90 90 90 90 90 90 90 90 90 90 90 RSP: 002b:00000000ffed5a8c EFLAGS: 00000246 ORIG_RAX: 0000000000000078 RAX: ffffffffffffffda RBX: 0000000000003ffc RCX: 0000000000000000 RDX: 00000000200005c0 RSI: 0000000000000000 RDI: 0000000000000000 RBP: 0000000000000012 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ------------[ cut here ]------------ DEBUG_LOCKS_WARN_ON(depth <= 0) WARNING: CPU: 1 PID: 7744 at kernel/locking/lockdep.c:4052 __lock_release kernel/locking/lockdep.c:4052 [inline] WARNING: CPU: 1 PID: 7744 at kernel/locking/lockdep.c:4052 lock_release+0x667/0xa00 kernel/locking/lockdep.c:4321 Kernel panic - not syncing: panic_on_warn set ... CPU: 1 PID: 7744 Comm: syz-executor007 Not tainted 5.1.0+ #4 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x172/0x1f0 lib/dump_stack.c:113 panic+0x2cb/0x65c kernel/panic.c:214 __warn.cold+0x20/0x45 kernel/panic.c:566 report_bug+0x263/0x2b0 lib/bug.c:186 fixup_bug arch/x86/kernel/traps.c:179 [inline] fixup_bug arch/x86/kernel/traps.c:174 [inline] do_error_trap+0x11b/0x200 arch/x86/kernel/traps.c:272 do_invalid_op+0x37/0x50 arch/x86/kernel/traps.c:291 invalid_op+0x14/0x20 arch/x86/entry/entry_64.S:972 RIP: 0010:__lock_release kernel/locking/lockdep.c:4052 [inline] RIP: 0010:lock_release+0x667/0xa00 kernel/locking/lockdep.c:4321 Code: 0f 85 a0 03 00 00 8b 35 77 66 08 08 85 f6 75 23 48 c7 c6 a0 55 6b 87 48 c7 c7 40 25 6b 87 4c 89 85 70 ff ff ff e8 b7 a9 eb ff <0f> 0b 4c 8b 85 70 ff ff ff 4c 89 ea 4c 89 e6 4c 89 c7 e8 52 63 ff RSP: 0018:ffff888094117b48 EFLAGS: 00010086 RAX: 0000000000000000 RBX: 1ffff11012822f6f RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffffffff815af236 RDI: ffffed1012822f5b RBP: ffff888094117c00 R08: ffff888092bfc400 R09: fffffbfff113301d R10: fffffbfff113301c R11: ffffffff889980e3 R12: ffffffff8a451df8 R13: ffffffff8142e71f R14: ffffffff8a44cc80 R15: ffff888094117bd8 percpu_up_read.constprop.0+0xcb/0x110 include/linux/percpu-rwsem.h:92 cgroup_threadgroup_change_end include/linux/cgroup-defs.h:712 [inline] copy_process.part.0+0x47ff/0x6710 kernel/fork.c:2222 copy_process kernel/fork.c:1772 [inline] _do_fork+0x25d/0xfd0 kernel/fork.c:2338 __do_compat_sys_x86_clone arch/x86/ia32/sys_ia32.c:240 [inline] __se_compat_sys_x86_clone arch/x86/ia32/sys_ia32.c:236 [inline] __ia32_compat_sys_x86_clone+0xbc/0x140 arch/x86/ia32/sys_ia32.c:236 do_syscall_32_irqs_on arch/x86/entry/common.c:334 [inline] do_fast_syscall_32+0x281/0xd54 arch/x86/entry/common.c:405 entry_SYSENTER_compat+0x70/0x7f arch/x86/entry/entry_64_compat.S:139 RIP: 0023:0xf7fec849 Code: 85 d2 74 02 89 0a 5b 5d c3 8b 04 24 c3 8b 14 24 c3 8b 3c 24 c3 90 90 90 90 90 90 90 90 90 90 90 90 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 eb 0d 90 90 90 90 90 90 90 90 90 90 90 90 RSP: 002b:00000000ffed5a8c EFLAGS: 00000246 ORIG_RAX: 0000000000000078 RAX: ffffffffffffffda RBX: 0000000000003ffc RCX: 0000000000000000 RDX: 00000000200005c0 RSI: 0000000000000000 RDI: 0000000000000000 RBP: 0000000000000012 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 Kernel Offset: disabled Rebooting in 86400 seconds.. Reported-and-tested-by: syzbot+3286e58549edc479faae@syzkaller.appspotmail.com Fixes: b3e583825266 ("clone: add CLONE_PIDFD") Signed-off-by: Christian Brauner (cherry picked from commit c3b7112df86b769927a60a6d7175988ca3d60f09) Bug: 135608568 Test: test program using syscall(__NR_sys_pidfd_open,..) and poll() Change-Id: Ib9ecb1e5c0c6e2d062b89c25109ec571570eb497 Signed-off-by: Suren Baghdasaryan --- kernel/fork.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index 50897504f31c..062001a8f932 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1683,7 +1683,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, */ retval = cgroup_can_fork(p); if (retval) - goto bad_fork_put_pidfd; + goto bad_fork_cgroup_threadgroup_change_end; /* * From this point on we must avoid any synchronous user-space @@ -1794,11 +1794,12 @@ bad_fork_cancel_cgroup: spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); cgroup_cancel_fork(p); +bad_fork_cgroup_threadgroup_change_end: + cgroup_threadgroup_change_end(current); bad_fork_put_pidfd: if (clone_flags & CLONE_PIDFD) sys_close(pidfd); bad_fork_free_pid: - threadgroup_change_end(current); if (pid != &init_struct_pid) free_pid(pid); bad_fork_cleanup_io: -- cgit v1.2.3 From f4c358582254bffd827449d7ba45b90142844179 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Tue, 4 Jun 2019 15:18:43 +0200 Subject: UPSTREAM: signal: improve comments Improve the comments for pidfd_send_signal(). First, the comment still referred to a file descriptor for a process as a "task file descriptor" which stems from way back at the beginning of the discussion. Replace this with "pidfd" for consistency. Second, the wording for the explanation of the arguments to the syscall was a bit inconsistent, e.g. some used the past tense some used present tense. Make the wording more consistent. Signed-off-by: Christian Brauner (cherry picked from commit c732327f04a3818f35fa97d07b1d64d31b691d78) Bug: 135608568 Test: test program using syscall(__NR_sys_pidfd_open,..) and poll() Change-Id: I06c6bdd1dddaeb8ac75a78dd21f9cdd0dc139a4c Signed-off-by: Suren Baghdasaryan --- kernel/signal.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/signal.c b/kernel/signal.c index 437778f62bfb..63f3aafdd0af 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2992,12 +2992,11 @@ static int copy_siginfo_from_user_any(siginfo_t *kinfo, siginfo_t __user *info) } /** - * sys_pidfd_send_signal - send a signal to a process through a task file - * descriptor - * @pidfd: the file descriptor of the process - * @sig: signal to be sent - * @info: the signal info - * @flags: future flags to be passed + * sys_pidfd_send_signal - Signal a process through a pidfd + * @pidfd: file descriptor of the process + * @sig: signal to send + * @info: signal info + * @flags: future flags * * The syscall currently only signals via PIDTYPE_PID which covers * kill(, . It does not signal threads or process -- cgit v1.2.3 From f8396a127dafd6c77ffdf37654b7e0a96b362e69 Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Tue, 30 Apr 2019 12:21:53 -0400 Subject: UPSTREAM: pidfd: add polling support This patch adds polling support to pidfd. Android low memory killer (LMK) needs to know when a process dies once it is sent the kill signal. It does so by checking for the existence of /proc/pid which is both racy and slow. For example, if a PID is reused between when LMK sends a kill signal and checks for existence of the PID, since the wrong PID is now possibly checked for existence. Using the polling support, LMK will be able to get notified when a process exists in race-free and fast way, and allows the LMK to do other things (such as by polling on other fds) while awaiting the process being killed to die. For notification to polling processes, we follow the same existing mechanism in the kernel used when the parent of the task group is to be notified of a child's death (do_notify_parent). This is precisely when the tasks waiting on a poll of pidfd are also awakened in this patch. We have decided to include the waitqueue in struct pid for the following reasons: 1. The wait queue has to survive for the lifetime of the poll. Including it in task_struct would not be option in this case because the task can be reaped and destroyed before the poll returns. 2. By including the struct pid for the waitqueue means that during de_thread(), the new thread group leader automatically gets the new waitqueue/pid even though its task_struct is different. Appropriate test cases are added in the second patch to provide coverage of all the cases the patch is handling. Cc: Andy Lutomirski Cc: Steven Rostedt Cc: Daniel Colascione Cc: Jann Horn Cc: Tim Murray Cc: Jonathan Kowalski Cc: Linus Torvalds Cc: Al Viro Cc: Kees Cook Cc: David Howells Cc: Oleg Nesterov Cc: kernel-team@android.com Reviewed-by: Oleg Nesterov Co-developed-by: Daniel Colascione Signed-off-by: Daniel Colascione Signed-off-by: Joel Fernandes (Google) Signed-off-by: Christian Brauner (cherry picked from commit b53b0b9d9a613c418057f6cb921c2f40a6f78c24) Bug: 135608568 Test: test program using syscall(__NR_sys_pidfd_open,..) and poll() Change-Id: I02f259d2875bec46b198d580edfbb067f077084e Signed-off-by: Suren Baghdasaryan --- kernel/fork.c | 26 ++++++++++++++++++++++++++ kernel/pid.c | 2 ++ kernel/signal.c | 11 +++++++++++ 3 files changed, 39 insertions(+) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index 062001a8f932..a21adc0155b9 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1316,8 +1316,34 @@ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f) } #endif +/* + * Poll support for process exit notification. + */ +static unsigned int pidfd_poll(struct file *file, struct poll_table_struct *pts) +{ + struct task_struct *task; + struct pid *pid = file->private_data; + int poll_flags = 0; + + poll_wait(file, &pid->wait_pidfd, pts); + + rcu_read_lock(); + task = pid_task(pid, PIDTYPE_PID); + /* + * Inform pollers only when the whole thread group exits. + * If the thread group leader exits before all other threads in the + * group, then poll(2) should block, similar to the wait(2) family. + */ + if (!task || (task->exit_state && thread_group_empty(task))) + poll_flags = POLLIN | POLLRDNORM; + rcu_read_unlock(); + + return poll_flags; +} + const struct file_operations pidfd_fops = { .release = pidfd_release, + .poll = pidfd_poll, #ifdef CONFIG_PROC_FS .show_fdinfo = pidfd_show_fdinfo, #endif diff --git a/kernel/pid.c b/kernel/pid.c index ccfdb56321c6..3c66f42ade66 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -331,6 +331,8 @@ struct pid *alloc_pid(struct pid_namespace *ns) for (type = 0; type < PIDTYPE_MAX; ++type) INIT_HLIST_HEAD(&pid->tasks[type]); + init_waitqueue_head(&pid->wait_pidfd); + upid = pid->numbers + ns->level; spin_lock_irq(&pidmap_lock); if (!(ns->nr_hashed & PIDNS_HASH_ADDING)) diff --git a/kernel/signal.c b/kernel/signal.c index 63f3aafdd0af..a9697e189a58 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1634,6 +1634,14 @@ ret: return ret; } +static void do_notify_pidfd(struct task_struct *task) +{ + struct pid *pid; + + pid = task_pid(task); + wake_up_all(&pid->wait_pidfd); +} + /* * Let a parent know about the death of a child. * For a stopped/continued status change, use do_notify_parent_cldstop instead. @@ -1657,6 +1665,9 @@ bool do_notify_parent(struct task_struct *tsk, int sig) BUG_ON(!tsk->ptrace && (tsk->group_leader != tsk || !thread_group_empty(tsk))); + /* Wake up all pidfd waiters */ + do_notify_pidfd(tsk); + if (sig != SIGCHLD) { /* * This is only possible if parent == real_parent. -- cgit v1.2.3 From 5d2e9e4f8630b4dbf04f6721d34ce93b5278144a Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 24 May 2019 12:43:51 +0200 Subject: BACKPORT: pid: add pidfd_open() This adds the pidfd_open() syscall. It allows a caller to retrieve pollable pidfds for a process which did not get created via CLONE_PIDFD, i.e. for a process that is created via traditional fork()/clone() calls that is only referenced by a PID: int pidfd = pidfd_open(1234, 0); ret = pidfd_send_signal(pidfd, SIGSTOP, NULL, 0); With the introduction of pidfds through CLONE_PIDFD it is possible to created pidfds at process creation time. However, a lot of processes get created with traditional PID-based calls such as fork() or clone() (without CLONE_PIDFD). For these processes a caller can currently not create a pollable pidfd. This is a problem for Android's low memory killer (LMK) and service managers such as systemd. Both are examples of tools that want to make use of pidfds to get reliable notification of process exit for non-parents (pidfd polling) and race-free signal sending (pidfd_send_signal()). They intend to switch to this API for process supervision/management as soon as possible. Having no way to get pollable pidfds from PID-only processes is one of the biggest blockers for them in adopting this api. With pidfd_open() making it possible to retrieve pidfds for PID-based processes we enable them to adopt this api. In line with Arnd's recent changes to consolidate syscall numbers across architectures, I have added the pidfd_open() syscall to all architectures at the same time. Signed-off-by: Christian Brauner Reviewed-by: David Howells Reviewed-by: Oleg Nesterov Acked-by: Arnd Bergmann Cc: "Eric W. Biederman" Cc: Kees Cook Cc: Joel Fernandes (Google) Cc: Thomas Gleixner Cc: Jann Horn Cc: Andy Lutomirsky Cc: Andrew Morton Cc: Aleksa Sarai Cc: Linus Torvalds Cc: Al Viro Cc: linux-api@vger.kernel.org (cherry picked from commit 32fcb426ec001cb6d5a4a195091a8486ea77e2df) Conflicts: kernel/pid.c (1. Replaced PIDTYPE_TGID with PIDTYPE_PID and thread_group_leader() check in pidfd_open() call) Bug: 135608568 Test: test program using syscall(__NR_sys_pidfd_open,..) and poll() Change-Id: I52a93a73722d7f7754dae05f63b94b4ca4a71a75 Signed-off-by: Suren Baghdasaryan Signed-off-by: electimon --- kernel/pid.c | 72 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 72 insertions(+) (limited to 'kernel') diff --git a/kernel/pid.c b/kernel/pid.c index 3c66f42ade66..9bc06f3a2b54 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -38,6 +38,8 @@ #include #include #include +#include +//#include #define pid_hashfn(nr, ns) \ hash_long((unsigned long)nr + (unsigned long)ns, pidhash_shift) @@ -566,6 +568,76 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns) return pid; } +/** + * pidfd_create() - Create a new pid file descriptor. + * + * @pid: struct pid that the pidfd will reference + * + * This creates a new pid file descriptor with the O_CLOEXEC flag set. + * + * Note, that this function can only be called after the fd table has + * been unshared to avoid leaking the pidfd to the new process. + * + * Return: On success, a cloexec pidfd is returned. + * On error, a negative errno number will be returned. + */ +static int pidfd_create(struct pid *pid) +{ + int fd; + + fd = anon_inode_getfd("[pidfd]", &pidfd_fops, get_pid(pid), + O_RDWR | O_CLOEXEC); + if (fd < 0) + put_pid(pid); + + return fd; +} + +/** + * pidfd_open() - Open new pid file descriptor. + * + * @pid: pid for which to retrieve a pidfd + * @flags: flags to pass + * + * This creates a new pid file descriptor with the O_CLOEXEC flag set for + * the process identified by @pid. Currently, the process identified by + * @pid must be a thread-group leader. This restriction currently exists + * for all aspects of pidfds including pidfd creation (CLONE_PIDFD cannot + * be used with CLONE_THREAD) and pidfd polling (only supports thread group + * leaders). + * + * Return: On success, a cloexec pidfd is returned. + * On error, a negative errno number will be returned. + */ +SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags) +{ + int fd, ret; + struct pid *p; + struct task_struct *tsk; + + if (flags) + return -EINVAL; + + if (pid <= 0) + return -EINVAL; + + p = find_get_pid(pid); + if (!p) + return -ESRCH; + + ret = 0; + rcu_read_lock(); + tsk = pid_task(p, PIDTYPE_PID); + /* Check that pid belongs to a group leader task */ + if (!tsk || !thread_group_leader(tsk)) + ret = -EINVAL; + rcu_read_unlock(); + + fd = ret ?: pidfd_create(p); + put_pid(p); + return fd; +} + /* * The pid hash table is scaled according to the amount of memory in the * machine. From a minimum of 16 slots up to 4096 slots at one gigabyte or -- cgit v1.2.3 From dba4259216a0f1152a1cffea0f1afb40b74a4fe0 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Wed, 17 Jul 2019 13:21:00 -0400 Subject: UPSTREAM: pidfd: fix a poll race when setting exit_state There is a race between reading task->exit_state in pidfd_poll and writing it after do_notify_parent calls do_notify_pidfd. Expected sequence of events is: CPU 0 CPU 1 ------------------------------------------------ exit_notify do_notify_parent do_notify_pidfd tsk->exit_state = EXIT_DEAD pidfd_poll if (tsk->exit_state) However nothing prevents the following sequence: CPU 0 CPU 1 ------------------------------------------------ exit_notify do_notify_parent do_notify_pidfd pidfd_poll if (tsk->exit_state) tsk->exit_state = EXIT_DEAD This causes a polling task to wait forever, since poll blocks because exit_state is 0 and the waiting task is not notified again. A stress test continuously doing pidfd poll and process exits uncovered this bug. To fix it, we make sure that the task's exit_state is always set before calling do_notify_pidfd. Fixes: b53b0b9d9a6 ("pidfd: add polling support") Cc: kernel-team@android.com Cc: Oleg Nesterov Signed-off-by: Suren Baghdasaryan Signed-off-by: Joel Fernandes (Google) Link: https://lore.kernel.org/r/20190717172100.261204-1-joel@joelfernandes.org [christian@brauner.io: adapt commit message and drop unneeded changes from wait_task_zombie] Signed-off-by: Christian Brauner (cherry picked from commit b191d6491be67cef2b3fa83015561caca1394ab9) Bug: 135608568 Test: test program using syscall(__NR_sys_pidfd_open,..) and poll() Change-Id: I043e54c9b69f25de88f6f19ae167920af8532de2 Signed-off-by: Suren Baghdasaryan --- kernel/exit.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/exit.c b/kernel/exit.c index babbc3c0a181..052aa52de331 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -616,6 +616,7 @@ static void exit_notify(struct task_struct *tsk, int group_dead) if (group_dead) kill_orphaned_pgrp(tsk->group_leader, NULL); + tsk->exit_state = EXIT_ZOMBIE; if (unlikely(tsk->ptrace)) { int sig = thread_group_leader(tsk) && thread_group_empty(tsk) && -- cgit v1.2.3 From 95b0a5e52f2aa815d377664fed4dce64825f80b6 Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Thu, 10 May 2018 14:56:41 -0700 Subject: BACKPORT: ANDROID: ftrace: fix function type mismatches This change fixes indirect call mismatches with function and function graph tracing, which trip Control-Flow Integrity (CFI) checking. Bug: 79510107 Bug: 67506682 Change-Id: I5de08c113fb970ffefedce93c58e0161f22c7ca2 Signed-off-by: Sami Tolvanen (cherry picked from commit c2f9bce9fee8e31e0500c501076f73db7791d8e9) Signed-off-by: Dan Aloni Signed-off-by: Davide Garberi --- kernel/trace/ftrace.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index c5484723abda..74fa302d9a68 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -128,8 +128,9 @@ static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct pt_regs *regs); #else /* See comment below, where ftrace_ops_list_func is defined */ -static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip); -#define ftrace_ops_list_func ((ftrace_func_t)ftrace_ops_no_ops) +static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs); +#define ftrace_ops_list_func ftrace_ops_no_ops #endif /* @@ -5229,7 +5230,8 @@ static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, } NOKPROBE_SYMBOL(ftrace_ops_list_func); #else -static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip) +static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs) { __ftrace_ops_list_func(ip, parent_ip, NULL, NULL); } @@ -5677,14 +5679,17 @@ void ftrace_graph_graph_time_control(bool enable) fgraph_graph_time = enable; } +void ftrace_graph_return_stub(struct ftrace_graph_ret *trace) +{ +} + int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace) { return 0; } /* The callbacks that hook a function */ -trace_func_graph_ret_t ftrace_graph_return = - (trace_func_graph_ret_t)ftrace_stub; +trace_func_graph_ret_t ftrace_graph_return = ftrace_graph_return_stub; trace_func_graph_ent_t ftrace_graph_entry = ftrace_graph_entry_stub; static trace_func_graph_ent_t __ftrace_graph_entry = ftrace_graph_entry_stub; @@ -5912,7 +5917,7 @@ void unregister_ftrace_graph(void) goto out; ftrace_graph_active--; - ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub; + ftrace_graph_return = ftrace_graph_return_stub; ftrace_graph_entry = ftrace_graph_entry_stub; __ftrace_graph_entry = ftrace_graph_entry_stub; ftrace_shutdown(&graph_ops, FTRACE_STOP_FUNC_RET); -- cgit v1.2.3