PCPU_MIN_UNIT_SIZE is an implementation detail of the percpu
allocator. Given we support __GFP_NOWARN now, lets just let
the allocation request fail naturally instead. The two call
sites from BPF mistakenly assumed __GFP_NOWARN would work, so
no changes needed to their actual __alloc_percpu_gfp() calls
which use the flag already.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
It was reported that syzkaller was able to trigger a splat on
devmap percpu allocation due to illegal/unsupported allocation
request size passed to __alloc_percpu():
[ 70.094249] illegal size (32776) or align (8) for percpu allocation
[ 70.094256] ------------[ cut here ]------------
[ 70.094259] WARNING: CPU: 3 PID: 3451 at mm/percpu.c:1365 pcpu_alloc+0x96/0x630
[...]
[ 70.094325] Call Trace:
[ 70.094328] __alloc_percpu_gfp+0x12/0x20
[ 70.094330] dev_map_alloc+0x134/0x1e0
[ 70.094331] SyS_bpf+0x9bc/0x1610
[ 70.094333] ? selinux_task_setrlimit+0x5a/0x60
[ 70.094334] ? security_task_setrlimit+0x43/0x60
[ 70.094336] entry_SYSCALL_64_fastpath+0x1a/0xa5
This was due to too large max_entries for the map such that we
surpassed the upper limit of PCPU_MIN_UNIT_SIZE. It's fine to
fail naturally here, so switch to __alloc_percpu_gfp() and pass
__GFP_NOWARN instead.
Fixes: 11393cc9b9 ("xdp: Add batching support to redirect map")
Reported-by: Mark Rutland <mark.rutland@arm.com>
Reported-by: Shankara Pailoor <sp3485@columbia.edu>
Reported-by: Richard Weinberger <richard@nod.at>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: John Fastabend <john.fastabend@gmail.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use the fact that verifier ops are now separate from program
ops to define a separate set of callbacks for verification of
already translated programs.
Since we expect the analyzer ops to be defined only for
a small subset of all program types initialize their array
by hand (don't use linux/bpf_types.h).
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since the verifier ops don't have to be associated with
the program for its entire lifetime we can move it to
verifier's struct bpf_verifier_env.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
struct bpf_verifier_ops contains both verifier ops and operations
used later during program's lifetime (test_run). Split the runtime
ops into a different structure.
BPF_PROG_TYPE() will now append ## _prog_ops or ## _verifier_ops
to the names.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit f1174f77b5 ("bpf/verifier: rework value tracking")
removed the crafty selection of which pointer types are
allowed to be modified. This is OK for most pointer types
since adjust_ptr_min_max_vals() will catch operations on
immutable pointers. One exception is PTR_TO_CTX which is
now allowed to be offseted freely.
The intent of aforementioned commit was to allow context
access via modified registers. The offset passed to
->is_valid_access() verifier callback has been adjusted
by the value of the variable offset.
What is missing, however, is taking the variable offset
into account when the context register is used. Or in terms
of the code adding the offset to the value passed to the
->convert_ctx_access() callback. This leads to the following
eBPF user code:
r1 += 68
r0 = *(u32 *)(r1 + 8)
exit
being translated to this in kernel space:
0: (07) r1 += 68
1: (61) r0 = *(u32 *)(r1 +180)
2: (95) exit
Offset 8 is corresponding to 180 in the kernel, but offset
76 is valid too. Verifier will "accept" access to offset
68+8=76 but then "convert" access to offset 8 as 180.
Effective access to offset 248 is beyond the kernel context.
(This is a __sk_buff example on a debug-heavy kernel -
packet mark is 8 -> 180, 76 would be data.)
Dereferencing the modified context pointer is not as easy
as dereferencing other types, because we have to translate
the access to reading a field in kernel structures which is
usually at a different offset and often of a different size.
To allow modifying the pointer we would have to make sure
that given eBPF instruction will always access the same
field or the fields accessed are "compatible" in terms of
offset and size...
Disallow dereferencing modified context pointers and add
to selftests the test case described here.
Fixes: f1174f77b5 ("bpf/verifier: rework value tracking")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This adds two tracepoint to the cpumap. One for the enqueue side
trace_xdp_cpumap_enqueue() and one for the kthread dequeue side
trace_xdp_cpumap_kthread().
To mitigate the tracepoint overhead, these are invoked during the
enqueue/dequeue bulking phases, thus amortizing the cost.
The obvious use-cases are for debugging and monitoring. The
non-intuitive use-case is using these as a feedback loop to know the
system load. One can imagine auto-scaling by reducing, adding or
activating more worker CPUs on demand.
V4: tracepoint remove time_limit info, instead add sched info
V8: intro struct bpf_cpu_map_entry members cpu+map_id in this patch
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch makes cpumap functional, by adding SKB allocation and
invoking the network stack on the dequeuing CPU.
For constructing the SKB on the remote CPU, the xdp_buff in converted
into a struct xdp_pkt, and it mapped into the top headroom of the
packet, to avoid allocating separate mem. For now, struct xdp_pkt is
just a cpumap internal data structure, with info carried between
enqueue to dequeue.
If a driver doesn't have enough headroom it is simply dropped, with
return code -EOVERFLOW. This will be picked up the xdp tracepoint
infrastructure, to allow users to catch this.
V2: take into account xdp->data_meta
V4:
- Drop busypoll tricks, keeping it more simple.
- Skip RPS and Generic-XDP-recursive-reinjection, suggested by Alexei
V5: correct RCU read protection around __netif_receive_skb_core.
V6: Setting TASK_RUNNING vs TASK_INTERRUPTIBLE based on talk with Rik van Riel
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch connects cpumap to the xdp_do_redirect_map infrastructure.
Still no SKB allocation are done yet. The XDP frames are transferred
to the other CPU, but they are simply refcnt decremented on the remote
CPU. This served as a good benchmark for measuring the overhead of
remote refcnt decrement. If driver page recycle cache is not
efficient then this, exposes a bottleneck in the page allocator.
A shout-out to MST's ptr_ring, which is the secret behind is being so
efficient to transfer memory pointers between CPUs, without constantly
bouncing cache-lines between CPUs.
V3: Handle !CONFIG_BPF_SYSCALL pointed out by kbuild test robot.
V4: Make Generic-XDP aware of cpumap type, but don't allow redirect yet,
as implementation require a separate upstream discussion.
V5:
- Fix a maybe-uninitialized pointed out by kbuild test robot.
- Restrict bpf-prog side access to cpumap, open when use-cases appear
- Implement cpu_map_enqueue() as a more simple void pointer enqueue
V6:
- Allow cpumap type for usage in helper bpf_redirect_map,
general bpf-prog side restriction moved to earlier patch.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The 'cpumap' is primarily used as a backend map for XDP BPF helper
call bpf_redirect_map() and XDP_REDIRECT action, like 'devmap'.
This patch implement the main part of the map. It is not connected to
the XDP redirect system yet, and no SKB allocation are done yet.
The main concern in this patch is to ensure the datapath can run
without any locking. This adds complexity to the setup and tear-down
procedure, which assumptions are extra carefully documented in the
code comments.
V2:
- make sure array isn't larger than NR_CPUS
- make sure CPUs added is a valid possible CPU
V3: fix nitpicks from Jakub Kicinski <kubakici@wp.pl>
V5:
- Restrict map allocation to root / CAP_SYS_ADMIN
- WARN_ON_ONCE if queue is not empty on tear-down
- Return -EPERM on memlock limit instead of -ENOMEM
- Error code in __cpu_map_entry_alloc() also handle ptr_ring_cleanup()
- Moved cpu_map_enqueue() to next patch
V6: all notice by Daniel Borkmann
- Fix err return code in cpu_map_alloc() introduced in V5
- Move cpu_possible() check after max_entries boundary check
- Forbid usage initially in check_map_func_compatibility()
V7:
- Fix alloc error path spotted by Daniel Borkmann
- Did stress test adding+removing CPUs from the map concurrently
- Fixed refcnt issue on cpu_map_entry, kthread started too soon
- Make sure packets are flushed during tear-down, involved use of
rcu_barrier() and kthread_run only exit after queue is empty
- Fix alloc error path in __cpu_map_entry_alloc() for ptr_ring
V8:
- Nitpicking comments and gramma by Edward Cree
- Fix missing semi-colon introduced in V7 due to rebasing
- Move struct bpf_cpu_map_entry members cpu+map_id to tracepoint patch
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
All the trace events defined in include/trace/events/bpf.h are only
used when CONFIG_BPF_SYSCALL is defined. But this file gets included by
include/linux/bpf_trace.h which is included by the networking code with
CREATE_TRACE_POINTS defined.
If a trace event is created but not used it still has data structures
and functions created for its use, even though nothing is using them.
To not waste space, do not define the BPF trace events in bpf.h unless
CONFIG_BPF_SYSCALL is defined.
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull irqchip updates for 4.14-rc5 from Marc Zyngier:
- Fix unfortunate mistake in the GICv3 ITS binding example
- Two fixes for the recently merged GICv4 support
- GICv3 ITS 52bit PA fixes
- Generic irqchip mask-ack fix, and its application to the tango irqchip
Pull perf fixes from Ingo Molnar:
"Some tooling fixes plus three kernel fixes: a memory leak fix, a
statistics fix and a crash fix"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/x86/intel/uncore: Fix memory leaks on allocation failures
perf/core: Fix cgroup time when scheduling descendants
perf/core: Avoid freeing static PMU contexts when PMU is unregistered
tools include uapi bpf.h: Sync kernel ABI header with tooling header
perf pmu: Unbreak perf record for arm/arm64 with events with explicit PMU
perf script: Add missing separator for "-F ip,brstack" (and brstackoff)
perf callchain: Compare dsos (as well) for CCKEY_FUNCTION
Pull locking fixes from Ingo Molnar:
"Two lockdep fixes for bugs introduced by the cross-release dependency
tracking feature - plus a commit that disables it because performance
regressed in an absymal fashion on some systems"
* 'locking-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
locking/lockdep: Disable cross-release features for now
locking/selftest: Avoid false BUG report
locking/lockdep: Fix stacktrace mess
Pull irq fixes from Ingo Molnar:
"A CPU hotplug related fix, plus two related sanity checks"
* 'irq-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
genirq/cpuhotplug: Enforce affinity setting on startup of managed irqs
genirq/cpuhotplug: Add sanity check for effective affinity mask
genirq: Warn when effective affinity is not updated
Use a simplified is_valid_access() callback when verifier
is used for program analysis by non-host JITs. This allows
us to teach the verifier about packet start and packet end
offsets for direct packet access.
We can extend the callback as needed but for most packet
processing needs there isn't much more the offloads may
require.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Any usage of the irq_gc_mask_disable_reg_and_ack() function has
been replaced with the desired functionality.
The incorrect and ambiguously named function is removed here to
prevent accidental misuse.
Signed-off-by: Doug Berger <opendmb@gmail.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
The irq_gc_mask_disable_reg_and_ack() function name implies that it
provides the combined functions of irq_gc_mask_disable_reg() and
irq_gc_ack(). However, the implementation does not actually do
that since it writes the mask instead of the disable register. It
also does not maintain the mask cache which makes it inappropriate
to use with other masking functions.
In addition, commit 659fb32d1b ("genirq: replace irq_gc_ack() with
{set,clr}_bit variants (fwd)") effectively renamed irq_gc_ack() to
irq_gc_ack_set_bit() so this function probably should have also been
renamed at that time.
The generic chip code currently provides three functions for use
with the irq_mask member of the irq_chip structure and two functions
for use with the irq_ack member of the irq_chip structure. These
functions could be combined into six functions for use with the
irq_mask_ack member of the irq_chip structure. However, since only
one of the combinations is currently used, only the function
irq_gc_mask_disable_and_ack_set() is added by this commit.
The '_reg' and '_bit' portions of the base function name were left
out of the new combined function name in an attempt to keep the
function name length manageable with the 80 character source code
line length while still allowing the distinct aspects of each
combination to be captured by the name.
If other combinations are desired in the future please add them to
the irq generic chip library at that time.
Signed-off-by: Doug Berger <opendmb@gmail.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Pull livepatching fix from Jiri Kosina:
- bugfix for handling of coming modules (incorrect handling of failure)
from Joe Lawrence
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/livepatching:
livepatch: unpatch all klp_objects if klp_module_coming fails
Merge waitid() fix from Kees Cook.
I'd have hoped that the unsafe_{get|put}_user() naming would have
avoided these kinds of stupid bugs, but no such luck.
* waitid-fix:
waitid(): Add missing access_ok() checks
Variable old_flags is being assigned but is never read; it is redundant
and can be removed.
Cleans up clang warning: Value stored to 'old_flags' is never read
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
When an incoming module is considered for livepatching by
klp_module_coming(), it iterates over multiple patches and multiple
kernel objects in this order:
list_for_each_entry(patch, &klp_patches, list) {
klp_for_each_object(patch, obj) {
which means that if one of the kernel objects fails to patch,
klp_module_coming()'s error path needs to unpatch and cleanup any kernel
objects that were already patched by a previous patch.
Reported-by: Miroslav Benes <mbenes@suse.cz>
Suggested-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Joe Lawrence <joe.lawrence@redhat.com>
Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
This reverts commit fbb1fb4ad4.
This was not the proper fix, lets cleanly revert it, so that
following patch can be carried to stable versions.
sock_cgroup_ptr() callers do not expect a NULL return value.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull seccomp fixlet from Kees Cook:
"Minor seccomp fix for v4.14-rc5. I debated sending this at all for
v4.14, but since it fixes a minor issue in the prior fix, which also
went to -stable, it seemed better to just get all of it cleaned up
right now.
- fix missed "static" to avoid Sparse warning (Colin King)"
* tag 'seccomp-v4.14-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux:
seccomp: make function __get_seccomp_filter static
Verifier log buffer can be quite large (up to 16MB currently).
As Eric Dumazet points out if we allow multiple verification
requests to proceed simultaneously, malicious user may use the
verifier as a way of allocating large amounts of unswappable
memory to OOM the host.
Switch to a strategy of allocating a smaller buffer (1024B)
and writing it out into the user buffer after every print.
While at it remove the old BUG_ON().
This is in preparation of the global verifier lock removal.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
The biggest piece of global state protected by the verifier lock
is the verifier_log. Move that log to struct bpf_verifier_env.
struct bpf_verifier_env has to be passed now to all invocations
of verbose().
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
The function __get_seccomp_filter is local to the source and does
not need to be in global scope, so make it static.
Cleans up sparse warning:
symbol '__get_seccomp_filter' was not declared. Should it be static?
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Fixes: 66a733ea6b ("seccomp: fix the usage of get/put_seccomp_filter() in seccomp_get_filter()")
Cc: stable@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Josef reported a HARDIRQ-safe -> HARDIRQ-unsafe lock order detected by
lockdep:
[ 1270.472259] WARNING: HARDIRQ-safe -> HARDIRQ-unsafe lock order detected
[ 1270.472783] 4.14.0-rc1-xfstests-12888-g76833e8 #110 Not tainted
[ 1270.473240] -----------------------------------------------------
[ 1270.473710] kworker/u5:2/5157 [HC0[0]:SC0[0]:HE0:SE1] is trying to acquire:
[ 1270.474239] (&(&lock->wait_lock)->rlock){+.+.}, at: [<ffffffff8da253d2>] __mutex_unlock_slowpath+0xa2/0x280
[ 1270.474994]
[ 1270.474994] and this task is already holding:
[ 1270.475440] (&pool->lock/1){-.-.}, at: [<ffffffff8d2992f6>] worker_thread+0x366/0x3c0
[ 1270.476046] which would create a new lock dependency:
[ 1270.476436] (&pool->lock/1){-.-.} -> (&(&lock->wait_lock)->rlock){+.+.}
[ 1270.476949]
[ 1270.476949] but this new dependency connects a HARDIRQ-irq-safe lock:
[ 1270.477553] (&pool->lock/1){-.-.}
...
[ 1270.488900] to a HARDIRQ-irq-unsafe lock:
[ 1270.489327] (&(&lock->wait_lock)->rlock){+.+.}
...
[ 1270.494735] Possible interrupt unsafe locking scenario:
[ 1270.494735]
[ 1270.495250] CPU0 CPU1
[ 1270.495600] ---- ----
[ 1270.495947] lock(&(&lock->wait_lock)->rlock);
[ 1270.496295] local_irq_disable();
[ 1270.496753] lock(&pool->lock/1);
[ 1270.497205] lock(&(&lock->wait_lock)->rlock);
[ 1270.497744] <Interrupt>
[ 1270.497948] lock(&pool->lock/1);
, which will cause a irq inversion deadlock if the above lock scenario
happens.
The root cause of this safe -> unsafe lock order is the
mutex_unlock(pool->manager_arb) in manage_workers() with pool->lock
held.
Unlocking mutex while holding an irq spinlock was never safe and this
problem has been around forever but it never got noticed because the
only time the mutex is usually trylocked while holding irqlock making
actual failures very unlikely and lockdep annotation missed the
condition until the recent b9c16a0e1f ("locking/mutex: Fix
lockdep_assert_held() fail").
Using mutex for pool->manager_arb has always been a bit of stretch.
It primarily is an mechanism to arbitrate managership between workers
which can easily be done with a pool flag. The only reason it became
a mutex is that pool destruction path wants to exclude parallel
managing operations.
This patch replaces the mutex with a new pool flag POOL_MANAGER_ACTIVE
and make the destruction path wait for the current manager on a wait
queue.
v2: Drop unnecessary flag clearing before pool destruction as
suggested by Boqun.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: stable@vger.kernel.org
While load_balance() masks the source CPUs against active_mask, it had
a hole against the destination CPU. Ensure the destination CPU is also
part of the 'domain-mask & active-mask' set.
Reported-by: Levin, Alexander (Sasha Levin) <alexander.levin@verizon.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 77d1dfda0e ("sched/topology, cpuset: Avoid spurious/wrong domain rebuilds")
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The trivial wake_affine_idle() implementation is very good for a
number of workloads, but it comes apart at the moment there are no
idle CPUs left, IOW. the overloaded case.
hackbench:
NO_WA_WEIGHT WA_WEIGHT
hackbench-20 : 7.362717561 seconds 6.450509391 seconds
(win)
netperf:
NO_WA_WEIGHT WA_WEIGHT
TCP_SENDFILE-1 : Avg: 54524.6 Avg: 52224.3
TCP_SENDFILE-10 : Avg: 48185.2 Avg: 46504.3
TCP_SENDFILE-20 : Avg: 29031.2 Avg: 28610.3
TCP_SENDFILE-40 : Avg: 9819.72 Avg: 9253.12
TCP_SENDFILE-80 : Avg: 5355.3 Avg: 4687.4
TCP_STREAM-1 : Avg: 41448.3 Avg: 42254
TCP_STREAM-10 : Avg: 24123.2 Avg: 25847.9
TCP_STREAM-20 : Avg: 15834.5 Avg: 18374.4
TCP_STREAM-40 : Avg: 5583.91 Avg: 5599.57
TCP_STREAM-80 : Avg: 2329.66 Avg: 2726.41
TCP_RR-1 : Avg: 80473.5 Avg: 82638.8
TCP_RR-10 : Avg: 72660.5 Avg: 73265.1
TCP_RR-20 : Avg: 52607.1 Avg: 52634.5
TCP_RR-40 : Avg: 57199.2 Avg: 56302.3
TCP_RR-80 : Avg: 25330.3 Avg: 26867.9
UDP_RR-1 : Avg: 108266 Avg: 107844
UDP_RR-10 : Avg: 95480 Avg: 95245.2
UDP_RR-20 : Avg: 68770.8 Avg: 68673.7
UDP_RR-40 : Avg: 76231 Avg: 75419.1
UDP_RR-80 : Avg: 34578.3 Avg: 35639.1
UDP_STREAM-1 : Avg: 64684.3 Avg: 66606
UDP_STREAM-10 : Avg: 52701.2 Avg: 52959.5
UDP_STREAM-20 : Avg: 30376.4 Avg: 29704
UDP_STREAM-40 : Avg: 15685.8 Avg: 15266.5
UDP_STREAM-80 : Avg: 8415.13 Avg: 7388.97
(wins and losses)
sysbench:
NO_WA_WEIGHT WA_WEIGHT
sysbench-mysql-2 : 2135.17 per sec. 2142.51 per sec.
sysbench-mysql-5 : 4809.68 per sec. 4800.19 per sec.
sysbench-mysql-10 : 9158.59 per sec. 9157.05 per sec.
sysbench-mysql-20 : 14570.70 per sec. 14543.55 per sec.
sysbench-mysql-40 : 22130.56 per sec. 22184.82 per sec.
sysbench-mysql-80 : 20995.56 per sec. 21904.18 per sec.
sysbench-psql-2 : 1679.58 per sec. 1705.06 per sec.
sysbench-psql-5 : 3797.69 per sec. 3879.93 per sec.
sysbench-psql-10 : 7253.22 per sec. 7258.06 per sec.
sysbench-psql-20 : 11166.75 per sec. 11220.00 per sec.
sysbench-psql-40 : 17277.28 per sec. 17359.78 per sec.
sysbench-psql-80 : 17112.44 per sec. 17221.16 per sec.
(increase on the top end)
tbench:
NO_WA_WEIGHT
Throughput 685.211 MB/sec 2 clients 2 procs max_latency=0.123 ms
Throughput 1596.64 MB/sec 5 clients 5 procs max_latency=0.119 ms
Throughput 2985.47 MB/sec 10 clients 10 procs max_latency=0.262 ms
Throughput 4521.15 MB/sec 20 clients 20 procs max_latency=0.506 ms
Throughput 9438.1 MB/sec 40 clients 40 procs max_latency=2.052 ms
Throughput 8210.5 MB/sec 80 clients 80 procs max_latency=8.310 ms
WA_WEIGHT
Throughput 697.292 MB/sec 2 clients 2 procs max_latency=0.127 ms
Throughput 1596.48 MB/sec 5 clients 5 procs max_latency=0.080 ms
Throughput 2975.22 MB/sec 10 clients 10 procs max_latency=0.254 ms
Throughput 4575.14 MB/sec 20 clients 20 procs max_latency=0.502 ms
Throughput 9468.65 MB/sec 40 clients 40 procs max_latency=2.069 ms
Throughput 8631.73 MB/sec 80 clients 80 procs max_latency=8.605 ms
(increase on the top end)
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Eric reported a sysbench regression against commit:
3fed382b46 ("sched/numa: Implement NUMA node level wake_affine()")
Similarly, Rik was looking at the NAS-lu.C benchmark, which regressed
against his v3.10 enterprise kernel.
PRE (current tip/master):
ivb-ep sysbench:
2: [30 secs] transactions: 64110 (2136.94 per sec.)
5: [30 secs] transactions: 143644 (4787.99 per sec.)
10: [30 secs] transactions: 274298 (9142.93 per sec.)
20: [30 secs] transactions: 418683 (13955.45 per sec.)
40: [30 secs] transactions: 320731 (10690.15 per sec.)
80: [30 secs] transactions: 355096 (11834.28 per sec.)
hsw-ex NAS:
OMP_PROC_BIND/lu.C.x_threads_144_run_1.log: Time in seconds = 18.01
OMP_PROC_BIND/lu.C.x_threads_144_run_2.log: Time in seconds = 17.89
OMP_PROC_BIND/lu.C.x_threads_144_run_3.log: Time in seconds = 17.93
lu.C.x_threads_144_run_1.log: Time in seconds = 434.68
lu.C.x_threads_144_run_2.log: Time in seconds = 405.36
lu.C.x_threads_144_run_3.log: Time in seconds = 433.83
POST (+patch):
ivb-ep sysbench:
2: [30 secs] transactions: 64494 (2149.75 per sec.)
5: [30 secs] transactions: 145114 (4836.99 per sec.)
10: [30 secs] transactions: 278311 (9276.69 per sec.)
20: [30 secs] transactions: 437169 (14571.60 per sec.)
40: [30 secs] transactions: 669837 (22326.73 per sec.)
80: [30 secs] transactions: 631739 (21055.88 per sec.)
hsw-ex NAS:
lu.C.x_threads_144_run_1.log: Time in seconds = 23.36
lu.C.x_threads_144_run_2.log: Time in seconds = 22.96
lu.C.x_threads_144_run_3.log: Time in seconds = 22.52
This patch takes out all the shiny wake_affine() stuff and goes back to
utter basics. Between the two CPUs involved with the wakeup (the CPU
doing the wakeup and the CPU we ran on previously) pick the CPU we can
run on _now_.
This restores much of the regressions against the older kernels,
but leaves some ground in the overloaded case. The default-enabled
WA_WEIGHT (which will be introduced in the next patch) is an attempt
to address the overloaded situation.
Reported-by: Eric Farman <farman@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Matthew Rosato <mjrosato@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: jinpuwang@gmail.com
Cc: vcaputo@pengaru.com
Fixes: 3fed382b46 ("sched/numa: Implement NUMA node level wake_affine()")
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Since commit:
1fd7e41699 ("perf/core: Remove perf_cpu_context::unique_pmu")
... when a PMU is unregistered then its associated ->pmu_cpu_context is
unconditionally freed. Whilst this is fine for dynamically allocated
context types (i.e. those registered using perf_invalid_context), this
causes a problem for sharing of static contexts such as
perf_{sw,hw}_context, which are used by multiple built-in PMUs and
effectively have a global lifetime.
Whilst testing the ARM SPE driver, which must use perf_sw_context to
support per-task AUX tracing, unregistering the driver as a result of a
module unload resulted in:
Unable to handle kernel NULL pointer dereference at virtual address 00000038
Internal error: Oops: 96000004 [#1] PREEMPT SMP
Modules linked in: [last unloaded: arm_spe_pmu]
PC is at ctx_resched+0x38/0xe8
LR is at perf_event_exec+0x20c/0x278
[...]
ctx_resched+0x38/0xe8
perf_event_exec+0x20c/0x278
setup_new_exec+0x88/0x118
load_elf_binary+0x26c/0x109c
search_binary_handler+0x90/0x298
do_execveat_common.isra.14+0x540/0x618
SyS_execve+0x38/0x48
since the software context has been freed and the ctx.pmu->pmu_disable_count
field has been set to NULL.
This patch fixes the problem by avoiding the freeing of static PMU contexts
altogether. Whilst the sharing of dynamic contexts is questionable, this
actually requires the caller to share their context pointer explicitly
and so the burden is on them to manage the object lifetime.
Reported-by: Kim Phillips <kim.phillips@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 1fd7e41699 ("perf/core: Remove perf_cpu_context::unique_pmu")
Link: http://lkml.kernel.org/r/1507040450-7730-1-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
There is some complication between check_prevs_add() and
check_prev_add() wrt. saving stack traces. The problem is that we want
to be frugal with saving stack traces, since it consumes static
resources.
We'll only know in check_prev_add() if we need the trace, but we can
call into it multiple times. So we want to do on-demand and re-use.
A further complication is that check_prev_add() can drop graph_lock
and mess with our static resources.
In any case, the current state; after commit:
ce07a9415f ("locking/lockdep: Make check_prev_add() able to handle external stack_trace")
is that we'll assume the trace contains valid data once
check_prev_add() returns '2'. However, as noted by Josh, this is
false, check_prev_add() can return '2' before having saved a trace,
this then result in the possibility of using uninitialized data.
Testing, as reported by Wu, shows a NULL deref.
So simplify.
Since the graph_lock() thing is a debug path that hasn't
really been used in a long while, take it out back and avoid the
head-ache.
Further initialize the stack_trace to a known 'empty' state; as long
as nr_entries == 0, nothing should deref entries. We can then use the
'entries == NULL' test for a valid trace / on-demand saving.
Analyzed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Byungchul Park <byungchul.park@lge.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: ce07a9415f ("locking/lockdep: Make check_prev_add() able to handle external stack_trace")
Signed-off-by: Ingo Molnar <mingo@kernel.org>
sk_clone_lock() might run while TCP/DCCP listener already vanished.
In order to prevent use after free, it is better to defer cgroup_sk_alloc()
to the point we know both parent and child exist, and from process context.
Fixes: e994b2f0fb ("tcp: do not lock listener to process SYN packets")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull networking fixes from David Miller:
1) Fix object leak on IPSEC offload failure, from Steffen Klassert.
2) Fix range checks in ipset address range addition operations, from
Jozsef Kadlecsik.
3) Fix pernet ops unregistration order in ipset, from Florian Westphal.
4) Add missing netlink attribute policy for nl80211 packet pattern
attrs, from Peng Xu.
5) Fix PPP device destruction race, from Guillaume Nault.
6) Write marks get lost when BPF verifier processes R1=R2 register
assignments, causing incorrect liveness information and less state
pruning. Fix from Alexei Starovoitov.
7) Fix blockhole routes so that they are marked dead and therefore not
cached in sockets, otherwise IPSEC stops working. From Steffen
Klassert.
8) Fix broadcast handling of UDP socket early demux, from Paolo Abeni.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (37 commits)
cdc_ether: flag the u-blox TOBY-L2 and SARA-U2 as wwan
net: thunderx: mark expected switch fall-throughs in nicvf_main()
udp: fix bcast packet reception
netlink: do not set cb_running if dump's start() errs
ipv4: Fix traffic triggered IPsec connections.
ipv6: Fix traffic triggered IPsec connections.
ixgbe: incorrect XDP ring accounting in ethtool tx_frame param
net: ixgbe: Use new PCI_DEV_FLAGS_NO_RELAXED_ORDERING flag
Revert commit 1a8b6d76dc ("net:add one common config...")
ixgbe: fix masking of bits read from IXGBE_VXLANCTRL register
ixgbe: Return error when getting PHY address if PHY access is not supported
netfilter: xt_bpf: Fix XT_BPF_MODE_FD_PINNED mode of 'xt_bpf_info_v1'
netfilter: SYNPROXY: skip non-tcp packet in {ipv4, ipv6}_synproxy_hook
tipc: Unclone message at secondary destination lookup
tipc: correct initialization of skb list
gso: fix payload length when gso_size is zero
mlxsw: spectrum_router: Avoid expensive lookup during route removal
bpf: fix liveness marking
doc: Fix typo "8023.ad" in bonding documentation
ipv6: fix net.ipv6.conf.all.accept_dad behaviour for real
...
Pablo Neira Ayuso says:
====================
Netfilter/IPVS fixes for net
The following patchset contains Netfilter/IPVS fixes for your net tree,
they are:
1) Fix packet drops due to incorrect ECN handling in IPVS, from Vadim
Fedorenko.
2) Fix splat with mark restoration in xt_socket with non-full-sock,
patch from Subash Abhinov Kasiviswanathan.
3) ipset bogusly bails out when adding IPv4 range containing more than
2^31 addresses, from Jozsef Kadlecsik.
4) Incorrect pernet unregistration order in ipset, from Florian Westphal.
5) Races between dump and swap in ipset results in BUG_ON splats, from
Ross Lagerwall.
6) Fix chain renames in nf_tables, from JingPiao Chen.
7) Fix race in pernet codepath with ebtables table registration, from
Artem Savkov.
8) Memory leak in error path in set name allocation in nf_tables, patch
from Arvind Yadav.
9) Don't dump chain counters if they are not available, this fixes a
crash when listing the ruleset.
10) Fix out of bound memory read in strlcpy() in x_tables compat code,
from Eric Dumazet.
11) Make sure we only process TCP packets in SYNPROXY hooks, patch from
Lin Zhang.
12) Cannot load rules incrementally anymore after xt_bpf with pinned
objects, added in revision 1. From Shmulik Ladkani.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 2c16d60332 ("netfilter: xt_bpf: support ebpf") introduced
support for attaching an eBPF object by an fd, with the
'bpf_mt_check_v1' ABI expecting the '.fd' to be specified upon each
IPT_SO_SET_REPLACE call.
However this breaks subsequent iptables calls:
# iptables -A INPUT -m bpf --object-pinned /sys/fs/bpf/xxx -j ACCEPT
# iptables -A INPUT -s 5.6.7.8 -j ACCEPT
iptables: Invalid argument. Run `dmesg' for more information.
That's because iptables works by loading existing rules using
IPT_SO_GET_ENTRIES to userspace, then issuing IPT_SO_SET_REPLACE with
the replacement set.
However, the loaded 'xt_bpf_info_v1' has an arbitrary '.fd' number
(from the initial "iptables -m bpf" invocation) - so when 2nd invocation
occurs, userspace passes a bogus fd number, which leads to
'bpf_mt_check_v1' to fail.
One suggested solution [1] was to hack iptables userspace, to perform a
"entries fixup" immediatley after IPT_SO_GET_ENTRIES, by opening a new,
process-local fd per every 'xt_bpf_info_v1' entry seen.
However, in [2] both Pablo Neira Ayuso and Willem de Bruijn suggested to
depricate the xt_bpf_info_v1 ABI dealing with pinned ebpf objects.
This fix changes the XT_BPF_MODE_FD_PINNED behavior to ignore the given
'.fd' and instead perform an in-kernel lookup for the bpf object given
the provided '.path'.
It also defines an alias for the XT_BPF_MODE_FD_PINNED mode, named
XT_BPF_MODE_PATH_PINNED, to better reflect the fact that the user is
expected to provide the path of the pinned object.
Existing XT_BPF_MODE_FD_ELF behavior (non-pinned fd mode) is preserved.
References: [1] https://marc.info/?l=netfilter-devel&m=150564724607440&w=2
[2] https://marc.info/?l=netfilter-devel&m=150575727129880&w=2
Reported-by: Rafael Buchbinder <rafi@rbk.ms>
Signed-off-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Managed interrupts can end up in a stale state on CPU hotplug. If the
interrupt is not targeting a single CPU, i.e. the affinity mask spawns
multiple CPUs then the following can happen:
After boot:
dstate: 0x01601200
IRQD_ACTIVATED
IRQD_IRQ_STARTED
IRQD_SINGLE_TARGET
IRQD_AFFINITY_SET
IRQD_AFFINITY_MANAGED
node: 0
affinity: 24-31
effectiv: 24
pending: 0
After offlining CPU 31 - 24
dstate: 0x01a31000
IRQD_IRQ_DISABLED
IRQD_IRQ_MASKED
IRQD_SINGLE_TARGET
IRQD_AFFINITY_SET
IRQD_AFFINITY_MANAGED
IRQD_MANAGED_SHUTDOWN
node: 0
affinity: 24-31
effectiv: 24
pending: 0
Now CPU 25 gets onlined again, so it should get the effective interrupt
affinity for this interruopt, but due to the x86 interrupt affinity setter
restrictions this ends up after restarting the interrupt with:
dstate: 0x01601300
IRQD_ACTIVATED
IRQD_IRQ_STARTED
IRQD_SINGLE_TARGET
IRQD_AFFINITY_SET
IRQD_SETAFFINITY_PENDING
IRQD_AFFINITY_MANAGED
node: 0
affinity: 24-31
effectiv: 24
pending: 24-31
So the interrupt is still affine to CPU 24, which was the last CPU to go
offline of that affinity set and the move to an online CPU within 24-31,
in this case 25, is pending. This mechanism is x86/ia64 specific as those
architectures cannot move interrupts from thread context and do this when
an interrupt is actually handled. So the move is set to pending.
Whats worse is that offlining CPU 25 again results in:
dstate: 0x01601300
IRQD_ACTIVATED
IRQD_IRQ_STARTED
IRQD_SINGLE_TARGET
IRQD_AFFINITY_SET
IRQD_SETAFFINITY_PENDING
IRQD_AFFINITY_MANAGED
node: 0
affinity: 24-31
effectiv: 24
pending: 24-31
This means the interrupt has not been shut down, because the outgoing CPU
is not in the effective affinity mask, but of course nothing notices that
the effective affinity mask is pointing at an offline CPU.
In the case of restarting a managed interrupt the move restriction does not
apply, so the affinity setting can be made unconditional. This needs to be
done _before_ the interrupt is started up as otherwise the condition for
moving it from thread context would not longer be fulfilled.
With that change applied onlining CPU 25 after offlining 31-24 results in:
dstate: 0x01600200
IRQD_ACTIVATED
IRQD_IRQ_STARTED
IRQD_SINGLE_TARGET
IRQD_AFFINITY_MANAGED
node: 0
affinity: 24-31
effectiv: 25
pending:
And after offlining CPU 25:
dstate: 0x01a30000
IRQD_IRQ_DISABLED
IRQD_IRQ_MASKED
IRQD_SINGLE_TARGET
IRQD_AFFINITY_MANAGED
IRQD_MANAGED_SHUTDOWN
node: 0
affinity: 24-31
effectiv: 25
pending:
which is the correct and expected result.
Fixes: 761ea388e8 ("genirq: Handle managed irqs gracefully in irq_startup()")
Reported-by: YASUAKI ISHIMATSU <yasu.isimatu@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: axboe@kernel.dk
Cc: linux-scsi@vger.kernel.org
Cc: Sumit Saxena <sumit.saxena@broadcom.com>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: mpe@ellerman.id.au
Cc: Shivasharan Srikanteshwara <shivasharan.srikanteshwara@broadcom.com>
Cc: Kashyap Desai <kashyap.desai@broadcom.com>
Cc: keith.busch@intel.com
Cc: peterz@infradead.org
Cc: Hannes Reinecke <hare@suse.de>
Cc: Christoph Hellwig <hch@lst.de>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/alpine.DEB.2.20.1710042208400.2406@nanos
This patch makes the bpf_prog's name available
in kallsyms.
The new format is bpf_prog_tag[_name].
Sample kallsyms from running selftests/bpf/test_progs:
[root@arch-fb-vm1 ~]# egrep ' bpf_prog_[0-9a-fA-F]{16}' /proc/kallsyms
ffffffffa0048000 t bpf_prog_dabf0207d1992486_test_obj_id
ffffffffa0038000 t bpf_prog_a04f5eef06a7f555__123456789ABCDE
ffffffffa0050000 t bpf_prog_a04f5eef06a7f555
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
During get_info_by_fd, the prog/map name is memcpy-ed. It depends
on the prog->aux->name and map->name to be zero initialized.
bpf_prog_aux is easy to guarantee that aux->name is zero init.
The name in bpf_map may be harder to be guaranteed in the future when
new map type is added.
Hence, this patch makes bpf_obj_name_cpy() to always zero init
the prog/map name.
Suggested-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
while processing Rx = Ry instruction the verifier does
regs[insn->dst_reg] = regs[insn->src_reg]
which often clears write mark (when Ry doesn't have it)
that was just set by check_reg_arg(Rx) prior to the assignment.
That causes mark_reg_read() to keep marking Rx in this block as
REG_LIVE_READ (since the logic incorrectly misses that it's
screened by the write) and in many of its parents (until lucky
write into the same Rx or beginning of the program).
That causes is_state_visited() logic to miss many pruning opportunities.
Furthermore mark_reg_read() logic propagates the read mark
for BPF_REG_FP as well (though it's readonly) which causes
harmless but unnecssary work during is_state_visited().
Note that do_propagate_liveness() skips FP correctly,
so do the same in mark_reg_read() as well.
It saves 0.2 seconds for the test below
program before after
bpf_lb-DLB_L3.o 2604 2304
bpf_lb-DLB_L4.o 11159 3723
bpf_lb-DUNKNOWN.o 1116 1110
bpf_lxc-DDROP_ALL.o 34566 28004
bpf_lxc-DUNKNOWN.o 53267 39026
bpf_netdev.o 17843 16943
bpf_overlay.o 8672 7929
time ~11 sec ~4 sec
Fixes: dc503a8ad9 ("bpf/verifier: track liveness for pruning")
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Edward Cree <ecree@solarflare.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
