linux.git/kernel/bpf, branch v5.9-rc2

bpf: Avoid visit same object multiple times

2020-08-19T00:36:23+00:00

Currently when traversing all tasks, the next tid
is always increased by one. This may result in
visiting the same task multiple times in a
pid namespace.

This patch fixed the issue by seting the next
tid as pid_nr_ns(pid, ns) + 1, similar to
funciton next_tgid().

Signed-off-by: Yonghong Song 
Signed-off-by: Alexei Starovoitov 
Cc: Rik van Riel 
Link: https://lore.kernel.org/bpf/20200818222310.2181500-1-yhs@fb.com

bpf: Fix a rcu_sched stall issue with bpf task/task_file iterator

2020-08-19T00:36:23+00:00

In our production system, we observed rcu stalls when
'bpftool prog` is running.
  rcu: INFO: rcu_sched self-detected stall on CPU
  rcu: \x097-....: (20999 ticks this GP) idle=302/1/0x4000000000000000 softirq=1508852/1508852 fqs=4913
  \x09(t=21031 jiffies g=2534773 q=179750)
  NMI backtrace for cpu 7
  CPU: 7 PID: 184195 Comm: bpftool Kdump: loaded Tainted: G        W         5.8.0-00004-g68bfc7f8c1b4 #6
  Hardware name: Quanta Twin Lakes MP/Twin Lakes Passive MP, BIOS F09_3A17 05/03/2019
  Call Trace:
  
  dump_stack+0x57/0x70
  nmi_cpu_backtrace.cold+0x14/0x53
  ? lapic_can_unplug_cpu.cold+0x39/0x39
  nmi_trigger_cpumask_backtrace+0xb7/0xc7
  rcu_dump_cpu_stacks+0xa2/0xd0
  rcu_sched_clock_irq.cold+0x1ff/0x3d9
  ? tick_nohz_handler+0x100/0x100
  update_process_times+0x5b/0x90
  tick_sched_timer+0x5e/0xf0
  __hrtimer_run_queues+0x12a/0x2a0
  hrtimer_interrupt+0x10e/0x280
  __sysvec_apic_timer_interrupt+0x51/0xe0
  asm_call_on_stack+0xf/0x20
  
  sysvec_apic_timer_interrupt+0x6f/0x80
  asm_sysvec_apic_timer_interrupt+0x12/0x20
  RIP: 0010:task_file_seq_get_next+0x71/0x220
  Code: 00 00 8b 53 1c 49 8b 7d 00 89 d6 48 8b 47 20 44 8b 18 41 39 d3 76 75 48 8b 4f 20 8b 01 39 d0 76 61 41 89 d1 49 39 c1 48 19 c0 <48> 8b 49 08 21 d0 48 8d 04 c1 4c 8b 08 4d 85 c9 74 46 49 8b 41 38
  RSP: 0018:ffffc90006223e10 EFLAGS: 00000297
  RAX: ffffffffffffffff RBX: ffff888f0d172388 RCX: ffff888c8c07c1c0
  RDX: 00000000000f017b RSI: 00000000000f017b RDI: ffff888c254702c0
  RBP: ffffc90006223e68 R08: ffff888be2a1c140 R09: 00000000000f017b
  R10: 0000000000000002 R11: 0000000000100000 R12: ffff888f23c24118
  R13: ffffc90006223e60 R14: ffffffff828509a0 R15: 00000000ffffffff
  task_file_seq_next+0x52/0xa0
  bpf_seq_read+0xb9/0x320
  vfs_read+0x9d/0x180
  ksys_read+0x5f/0xe0
  do_syscall_64+0x38/0x60
  entry_SYSCALL_64_after_hwframe+0x44/0xa9
  RIP: 0033:0x7f8815f4f76e
  Code: c0 e9 f6 fe ff ff 55 48 8d 3d 76 70 0a 00 48 89 e5 e8 36 06 02 00 66 0f 1f 44 00 00 64 8b 04 25 18 00 00 00 85 c0 75 14 0f 05 <48> 3d 00 f0 ff ff 77 52 c3 66 0f 1f 84 00 00 00 00 00 55 48 89 e5
  RSP: 002b:00007fff8f9df578 EFLAGS: 00000246 ORIG_RAX: 0000000000000000
  RAX: ffffffffffffffda RBX: 000000000170b9c0 RCX: 00007f8815f4f76e
  RDX: 0000000000001000 RSI: 00007fff8f9df5b0 RDI: 0000000000000007
  RBP: 00007fff8f9e05f0 R08: 0000000000000049 R09: 0000000000000010
  R10: 00007f881601fa40 R11: 0000000000000246 R12: 00007fff8f9e05a8
  R13: 00007fff8f9e05a8 R14: 0000000001917f90 R15: 000000000000e22e

Note that `bpftool prog` actually calls a task_file bpf iterator
program to establish an association between prog/map/link/btf anon
files and processes.

In the case where the above rcu stall occured, we had a process
having 1587 tasks and each task having roughly 81305 files.
This implied 129 million bpf prog invocations. Unfortunwtely none of
these files are prog/map/link/btf files so bpf iterator/prog needs
to traverse all these files and not able to return to user space
since there are no seq_file buffer overflow.

This patch fixed the issue in bpf_seq_read() to limit the number
of visited objects. If the maximum number of visited objects is
reached, no more objects will be visited in the current syscall.
If there is nothing written in the seq_file buffer, -EAGAIN will
return to the user so user can try again.

The maximum number of visited objects is set at 1 million.
In our Intel Xeon D-2191 2.3GHZ 18-core server, bpf_seq_read()
visiting 1 million files takes around 0.18 seconds.

We did not use cond_resched() since for some iterators, e.g.,
netlink iterator, where rcu read_lock critical section spans between
consecutive seq_ops->next(), which makes impossible to do cond_resched()
in the key while loop of function bpf_seq_read().

Signed-off-by: Yonghong Song 
Signed-off-by: Alexei Starovoitov 
Cc: Paul E. McKenney 
Link: https://lore.kernel.org/bpf/20200818222309.2181348-1-yhs@fb.com

bpf: Use get_file_rcu() instead of get_file() for task_file iterator

2020-08-17T21:42:58+00:00

With latest `bpftool prog` command, we observed the following kernel
panic.
    BUG: kernel NULL pointer dereference, address: 0000000000000000
    #PF: supervisor instruction fetch in kernel mode
    #PF: error_code(0x0010) - not-present page
    PGD dfe894067 P4D dfe894067 PUD deb663067 PMD 0
    Oops: 0010 [#1] SMP
    CPU: 9 PID: 6023 ...
    RIP: 0010:0x0
    Code: Bad RIP value.
    RSP: 0000:ffffc900002b8f18 EFLAGS: 00010286
    RAX: ffff8883a405f400 RBX: ffff888e46a6bf00 RCX: 000000008020000c
    RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff8883a405f400
    RBP: ffff888e46a6bf50 R08: 0000000000000000 R09: ffffffff81129600
    R10: ffff8883a405f300 R11: 0000160000000000 R12: 0000000000002710
    R13: 000000e9494b690c R14: 0000000000000202 R15: 0000000000000009
    FS:  00007fd9187fe700(0000) GS:ffff888e46a40000(0000) knlGS:0000000000000000
    CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
    CR2: ffffffffffffffd6 CR3: 0000000de5d33002 CR4: 0000000000360ee0
    DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
    DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
    Call Trace:
     
     rcu_core+0x1a4/0x440
     __do_softirq+0xd3/0x2c8
     irq_exit+0x9d/0xa0
     smp_apic_timer_interrupt+0x68/0x120
     apic_timer_interrupt+0xf/0x20
     
    RIP: 0033:0x47ce80
    Code: Bad RIP value.
    RSP: 002b:00007fd9187fba40 EFLAGS: 00000206 ORIG_RAX: ffffffffffffff13
    RAX: 0000000000000002 RBX: 00007fd931789160 RCX: 000000000000010c
    RDX: 00007fd9308cdfb4 RSI: 00007fd9308cdfb4 RDI: 00007ffedd1ea0a8
    RBP: 00007fd9187fbab0 R08: 000000000000000e R09: 000000000000002a
    R10: 0000000000480210 R11: 00007fd9187fc570 R12: 00007fd9316cc400
    R13: 0000000000000118 R14: 00007fd9308cdfb4 R15: 00007fd9317a9380

After further analysis, the bug is triggered by
Commit eaaacd23910f ("bpf: Add task and task/file iterator targets")
which introduced task_file bpf iterator, which traverses all open file
descriptors for all tasks in the current namespace.
The latest `bpftool prog` calls a task_file bpf program to traverse
all files in the system in order to associate processes with progs/maps, etc.
When traversing files for a given task, rcu read_lock is taken to
access all files in a file_struct. But it used get_file() to grab
a file, which is not right. It is possible file->f_count is 0 and
get_file() will unconditionally increase it.
Later put_file() may cause all kind of issues with the above
as one of sympotoms.

The failure can be reproduced with the following steps in a few seconds:
    $ cat t.c
    #include 
    #include 
    #include 
    #include 
    #include 

    #define N 10000
    int fd[N];
    int main() {
      int i;

      for (i = 0; i < N; i++) {
        fd[i] = open("./note.txt", 'r');
        if (fd[i] < 0) {
           fprintf(stderr, "failed\n");
           return -1;
        }
      }
      for (i = 0; i < N; i++)
        close(fd[i]);

      return 0;
    }
    $ gcc -O2 t.c
    $ cat run.sh
    #/bin/bash
    for i in {1..100}
    do
      while true; do ./a.out; done &
    done
    $ ./run.sh
    $ while true; do bpftool prog >& /dev/null; done

This patch used get_file_rcu() which only grabs a file if the
file->f_count is not zero. This is to ensure the file pointer
is always valid. The above reproducer did not fail for more
than 30 minutes.

Fixes: eaaacd23910f ("bpf: Add task and task/file iterator targets")
Suggested-by: Josef Bacik 
Signed-off-by: Yonghong Song 
Signed-off-by: Alexei Starovoitov 
Reviewed-by: Josef Bacik 
Link: https://lore.kernel.org/bpf/20200817174214.252601-1-yhs@fb.com

bpf: Iterate through all PT_NOTE sections when looking for build id

2020-08-13T01:14:49+00:00

Currently when we look for build id within bpf_get_stackid helper
call, we check the first NOTE section and we fail if build id is
not there.

However on some system (Fedora) there can be multiple NOTE sections
in binaries and build id data is not always the first one, like:

  $ readelf -a /usr/bin/ls
  ...
  [ 2] .note.gnu.propert NOTE             0000000000000338  00000338
       0000000000000020  0000000000000000   A       0     0     8358
  [ 3] .note.gnu.build-i NOTE             0000000000000358  00000358
       0000000000000024  0000000000000000   A       0     0     437c
  [ 4] .note.ABI-tag     NOTE             000000000000037c  0000037c
  ...

So the stack_map_get_build_id function will fail on build id retrieval
and fallback to BPF_STACK_BUILD_ID_IP.

This patch is changing the stack_map_get_build_id code to iterate
through all the NOTE sections and try to get build id data from
each of them.

When tracing on sched_switch tracepoint that does bpf_get_stackid
helper call kernel build, I can see about 60% increase of successful
build id retrieval. The rest seems fails on -EFAULT.

Signed-off-by: Jiri Olsa 
Signed-off-by: Alexei Starovoitov 
Acked-by: Song Liu 
Link: https://lore.kernel.org/bpf/20200812123102.20032-1-jolsa@kernel.org

bpf: Delete repeated words in comments

2020-08-07T16:57:24+00:00

Drop repeated words in kernel/bpf/: {has, the}

Signed-off-by: Randy Dunlap 
Signed-off-by: Daniel Borkmann 
Link: https://lore.kernel.org/bpf/20200807033141.10437-1-rdunlap@infradead.org

bpf: Change uapi for bpf iterator map elements

2020-08-06T23:39:14+00:00

Commit a5cbe05a6673 ("bpf: Implement bpf iterator for
map elements") added bpf iterator support for
map elements. The map element bpf iterator requires
info to identify a particular map. In the above
commit, the attr->link_create.target_fd is used
to carry map_fd and an enum bpf_iter_link_info
is added to uapi to specify the target_fd actually
representing a map_fd:
    enum bpf_iter_link_info {
	BPF_ITER_LINK_UNSPEC = 0,
	BPF_ITER_LINK_MAP_FD = 1,

	MAX_BPF_ITER_LINK_INFO,
    };

This is an extensible approach as we can grow
enumerator for pid, cgroup_id, etc. and we can
unionize target_fd for pid, cgroup_id, etc.
But in the future, there are chances that
more complex customization may happen, e.g.,
for tasks, it could be filtered based on
both cgroup_id and user_id.

This patch changed the uapi to have fields
	__aligned_u64	iter_info;
	__u32		iter_info_len;
for additional iter_info for link_create.
The iter_info is defined as
	union bpf_iter_link_info {
		struct {
			__u32   map_fd;
		} map;
	};

So future extension for additional customization
will be easier. The bpf_iter_link_info will be
passed to target callback to validate and generic
bpf_iter framework does not need to deal it any
more.

Note that map_fd = 0 will be considered invalid
and -EBADF will be returned to user space.

Fixes: a5cbe05a6673 ("bpf: Implement bpf iterator for map elements")
Signed-off-by: Yonghong Song 
Signed-off-by: Alexei Starovoitov 
Acked-by: Andrii Nakryiko 
Acked-by: John Fastabend 
Link: https://lore.kernel.org/bpf/20200805055056.1457463-1-yhs@fb.com

Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

2020-08-04T01:27:40+00:00

Daniel Borkmann says:

====================
pull-request: bpf-next 2020-08-04

The following pull-request contains BPF updates for your *net-next* tree.

We've added 73 non-merge commits during the last 9 day(s) which contain
a total of 135 files changed, 4603 insertions(+), 1013 deletions(-).

The main changes are:

1) Implement bpf_link support for XDP. Also add LINK_DETACH operation for the BPF
   syscall allowing processes with BPF link FD to force-detach, from Andrii Nakryiko.

2) Add BPF iterator for map elements and to iterate all BPF programs for efficient
   in-kernel inspection, from Yonghong Song and Alexei Starovoitov.

3) Separate bpf_get_{stack,stackid}() helpers for perf events in BPF to avoid
   unwinder errors, from Song Liu.

4) Allow cgroup local storage map to be shared between programs on the same
   cgroup. Also extend BPF selftests with coverage, from YiFei Zhu.

5) Add BPF exception tables to ARM64 JIT in order to be able to JIT BPF_PROBE_MEM
   load instructions, from Jean-Philippe Brucker.

6) Follow-up fixes on BPF socket lookup in combination with reuseport group
   handling. Also add related BPF selftests, from Jakub Sitnicki.

7) Allow to use socket storage in BPF_PROG_TYPE_CGROUP_SOCK-typed programs for
   socket create/release as well as bind functions, from Stanislav Fomichev.

8) Fix an info leak in xsk_getsockopt() when retrieving XDP stats via old struct
   xdp_statistics, from Peilin Ye.

9) Fix PT_REGS_RC{,_CORE}() macros in libbpf for MIPS arch, from Jerry Crunchtime.

10) Extend BPF kernel test infra with skb->family and skb->{local,remote}_ip{4,6}
    fields and allow user space to specify skb->dev via ifindex, from Dmitry Yakunin.

11) Fix a bpftool segfault due to missing program type name and make it more robust
    to prevent them in future gaps, from Quentin Monnet.

12) Consolidate cgroup helper functions across selftests and fix a v6 localhost
    resolver issue, from John Fastabend.
====================

Signed-off-by: David S. Miller

Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

2020-08-02T08:02:12+00:00

Resolved kernel/bpf/btf.c using instructions from merge commit
69138b34a7248d2396ab85c8652e20c0c39beaba

Signed-off-by: David S. Miller

bpf: Add support for forced LINK_DETACH command

2020-08-02T03:38:28+00:00

Add LINK_DETACH command to force-detach bpf_link without destroying it. It has
the same behavior as auto-detaching of bpf_link due to cgroup dying for
bpf_cgroup_link or net_device being destroyed for bpf_xdp_link. In such case,
bpf_link is still a valid kernel object, but is defuncts and doesn't hold BPF
program attached to corresponding BPF hook. This functionality allows users
with enough access rights to manually force-detach attached bpf_link without
killing respective owner process.

This patch implements LINK_DETACH for cgroup, xdp, and netns links, mostly
re-using existing link release handling code.

Signed-off-by: Andrii Nakryiko 
Signed-off-by: Alexei Starovoitov 
Acked-by: Song Liu 
Acked-by: John Fastabend 
Link: https://lore.kernel.org/bpf/20200731182830.286260-2-andriin@fb.com

Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

2020-08-01T00:19:47+00:00

Daniel Borkmann says:

====================
pull-request: bpf 2020-07-31

The following pull-request contains BPF updates for your *net* tree.

We've added 5 non-merge commits during the last 21 day(s) which contain
a total of 5 files changed, 126 insertions(+), 18 deletions(-).

The main changes are:

1) Fix a map element leak in HASH_OF_MAPS map type, from Andrii Nakryiko.

2) Fix a NULL pointer dereference in __btf_resolve_helper_id() when no
   btf_vmlinux is available, from Peilin Ye.

3) Init pos variable in __bpfilter_process_sockopt(), from Christoph Hellwig.

4) Fix a cgroup sockopt verifier test by specifying expected attach type,
   from Jean-Philippe Brucker.

Note that when net gets merged into net-next later on, there is a small
merge conflict in kernel/bpf/btf.c between commit 5b801dfb7feb ("bpf: Fix
NULL pointer dereference in __btf_resolve_helper_id()") from the bpf tree
and commit 138b9a0511c7 ("bpf: Remove btf_id helpers resolving") from the
net-next tree.

Resolve as follows: remove the old hunk with the __btf_resolve_helper_id()
function. Change the btf_resolve_helper_id() so it actually tests for a
NULL btf_vmlinux and bails out:

int btf_resolve_helper_id(struct bpf_verifier_log *log,
                          const struct bpf_func_proto *fn, int arg)
{
        int id;

        if (fn->arg_type[arg] != ARG_PTR_TO_BTF_ID || !btf_vmlinux)
                return -EINVAL;
        id = fn->btf_id[arg];
        if (!id || id > btf_vmlinux->nr_types)
                return -EINVAL;
        return id;
}

Let me know if you run into any others issues (CC'ing Jiri Olsa so he's in
the loop with regards to merge conflict resolution).
====================

Signed-off-by: David S. Miller