mlx5e_ethtool_set_channels updates the indirection table before
switching to the new channels. If the switch fails, the indirection
table is new, but the channels are old, which is wrong. Fix it by using
the preactivate hook of mlx5e_safe_switch_channels to update the
indirection table at the stage when nothing can fail anymore.
As the code that updates the indirection table is now encapsulated into
a new function, use that function in the attach flow when the driver has
to reduce the number of channels, and prepare the code for the next
commit.
Fixes: 85082dba0a ("net/mlx5e: Correctly handle RSS indirection table when changing number of channels")
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
mlx5e_safe_switch_channels accepts a callback to be called before
activating new channels. It is intended to configure some hardware
parameters in cases where channels are recreated because some
configuration has changed.
Recently, this callback has started being used to update the driver's
internal MLX5E_STATE_XDP_OPEN flag, and the following patches also
intend to use this callback for software preparations. This patch
renames the hw_modify callback to preactivate, so that the name fits
better.
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
As a preparation for one of the following commits, create a function to
encapsulate the code that notifies the kernel about the new amount of
RX and TX queues. The code will be called multiple times in the next
commit.
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
The LRO boolean state in params->lro_en must not be set in case
the NIC is not capable.
Enforce this check and remove the TODO comment.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
We shall always extract channel index out of the txq, regardless
of the relation between txq_ix and num channels. The extraction is
always valid, as if txq is smaller than number of channels,
txq_ix == priv->txq2sq[txq_ix]->ch_ix.
By doing so, we can remove an if clause from the select queue method,
and have one flow for all packets.
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Since commit d8a953ddde ("bootconfig: Set CONFIG_BOOT_CONFIG=n by
default") also changed the CONFIG_BOOTTIME_TRACING to select
CONFIG_BOOT_CONFIG to show the boot-time tracing on the menu,
it introduced wrong dependencies with BLK_DEV_INITRD as below.
WARNING: unmet direct dependencies detected for BOOT_CONFIG
Depends on [n]: BLK_DEV_INITRD [=n]
Selected by [y]:
- BOOTTIME_TRACING [=y] && TRACING_SUPPORT [=y] && FTRACE [=y] && TRACING [=y]
This makes the CONFIG_BOOT_CONFIG selects CONFIG_BLK_DEV_INITRD to
fix this error and make CONFIG_BOOTTIME_TRACING=n by default, so
that both boot-time tracing and boot configuration off but those
appear on the menu list.
Link: http://lkml.kernel.org/r/158264140162.23842.11237423518607465535.stgit@devnote2
Fixes: d8a953ddde ("bootconfig: Set CONFIG_BOOT_CONFIG=n by default")
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Compiled-tested-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Implement support for transferring XDP meta data into skb for
virtio_net driver; before calling into the program, xdp.data_meta points
to xdp.data, where on program return with pass verdict, we call
into skb_metadata_set().
Tested with the script at
https://github.com/higebu/virtio_net-xdp-metadata-test.
Signed-off-by: Yuya Kusakabe <yuya.kusakabe@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Link: https://lore.kernel.org/bpf/20200225033212.437563-2-yuya.kusakabe@gmail.com
We do not want to care about the vnet header in receive_small() if XDP
is loaded, since we can not know whether or not the packet is modified
by XDP.
Fixes: f6b10209b9 ("virtio-net: switch to use build_skb() for small buffer")
Signed-off-by: Yuya Kusakabe <yuya.kusakabe@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Link: https://lore.kernel.org/bpf/20200225033212.437563-1-yuya.kusakabe@gmail.com
Due to various bugs in tests clean up code (usually), if host system is
misconfigured, it happens that test_progs will just crash in the middle of
running a test with little to no indication of where and why the crash
happened. For cases where coredump is not readily available (e.g., inside
a CI), it's very helpful to have a stack trace, which lead to crash, to be
printed out. This change adds a signal handler that will capture and print out
symbolized backtrace:
$ sudo ./test_progs -t mmap
test_mmap:PASS:skel_open_and_load 0 nsec
test_mmap:PASS:bss_mmap 0 nsec
test_mmap:PASS:data_mmap 0 nsec
Caught signal #11!
Stack trace:
./test_progs(crash_handler+0x18)[0x42a888]
/lib64/libpthread.so.0(+0xf5d0)[0x7f2aab5175d0]
./test_progs(test_mmap+0x3c0)[0x41f0a0]
./test_progs(main+0x160)[0x407d10]
/lib64/libc.so.6(__libc_start_main+0xf5)[0x7f2aab15d3d5]
./test_progs[0x407ebc]
[1] 1988412 segmentation fault (core dumped) sudo ./test_progs -t mmap
Unfortunately, glibc's symbolization support is unable to symbolize static
functions, only global ones will be present in stack trace. But it's still a
step forward without adding extra libraries to get a better symbolization.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20200225000847.3965188-1-andriin@fb.com
Jiri Pirko says:
====================
mlxsw: Implement ACL-dropped packets identification
mlxsw hardware allows to insert a ACL-drop action with a value defined
by user that would be later on passed with a dropped packet.
To implement this, use the existing TC action cookie and pass it to the
driver. As the cookie format coming down from TC and the mlxsw HW cookie
format is different, do the mapping of these two using idr and rhashtable.
The cookie is passed up from the HW through devlink_trap_report() to
drop_monitor code. A new metadata type is used for that.
Example:
$ tc qdisc add dev enp0s16np1 clsact
$ tc filter add dev enp0s16np1 ingress protocol ip pref 10 flower skip_sw dst_ip 192.168.1.2 action drop cookie 3b45fa38c8
^^^^^^^^^^
$ devlink trap set pci/0000:00:10.0 trap acl action trap
$ dropwatch
Initializing null lookup method
dropwatch> set hw true
setting hardware drops monitoring to 1
dropwatch> set alertmode packet
Setting alert mode
Alert mode successfully set
dropwatch> start
Enabling monitoring...
Kernel monitoring activated.
Issue Ctrl-C to stop monitoring
drop at: ingress_flow_action_drop (acl_drops)
origin: hardware
input port ifindex: 30
input port name: enp0s16np1
cookie: 3b45fa38c8 <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
timestamp: Fri Jan 24 17:10:53 2020 715387671 nsec
protocol: 0x800
length: 98
original length: 98
This way the user may insert multiple drop rules and monitor the dropped
packets with the information of which action caused the drop.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Extend existing devlink trap test to include metadata type for flow
action cookie.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add new trap ACL which reports flow action cookie in a metadata. Allow
used to setup the cookie using debugfs file.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use the cookie index received along with the packet to lookup original
flow_offload cookie binary and pass it down to devlink_trap_report().
Add "fa_cookie" metadata to the ACL trap.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In case the received packet comes in due to one of ACL discard traps,
take the user_def_val_orig_pkt_len field from CQE and store it
in skb->cb as ACL cookie index.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Track cookies coming down to driver by flow_offload.
Assign a cookie_index to each unique cookie binary. Use previously
defined "Trap with userdef" flex action to ask HW to pass cookie_index
alongside with the dropped packets.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Expose "Trap action with userdef". It is the same as already
defined "Trap action" with a difference that it would ask the policy
engine to pass arbitrary value (userdef) alongside with received packets.
This would be later on used to carry cookie index.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add cookie argument to devlink_trap_report() allowing driver to pass in
the user cookie. Pass on the cookie down to drop monitor code.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
If driver passed along the cookie, push it through Netlink.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Allow driver to indicate cookie metadata for registered traps.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Extend struct flow_action_entry in order to hold TC action cookie
specified by user inserting the action.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The icmpv6_send function has long had a static inline implementation
with an empty body for CONFIG_IPV6=n, so that code calling it doesn't
need to be ifdef'd. The new icmpv6_ndo_send function, which is intended
for drivers as a drop-in replacement with an identical function
signature, should follow the same pattern. Without this patch, drivers
that used to work with CONFIG_IPV6=n now result in a linker error.
Cc: Chen Zhou <chenzhou10@huawei.com>
Reported-by: Hulk Robot <hulkci@huawei.com>
Fixes: 0b41713b60 ("icmp: introduce helper for nat'd source address in network device context")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This tag contains a handful of RISC-V related fixes that I've collected and
would like to target for 5.6-rc4:
* A fix to set up the PMPs on boot, which allows the kernel to access memory on
systems that don't set up permissive PMPs before getting to Linux. This only
effects machine-mode kernels, which currently means only NOMMU kernels.
* A fix to avoid enabling supervisor-mode interrupts when running in
machine-mode, also only for NOMMU kernels.
* A pair of fixes to our KASAN support to avoid corrupting memory.
* A gitignore fix.
This boots on QEMU's virt board for me.
-----BEGIN PGP SIGNATURE-----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=r0RY
-----END PGP SIGNATURE-----
Merge tag 'riscv-for-linux-5.6-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux
Pull RISC-V fixes from Palmer Dabbelt:
"This contains a handful of RISC-V related fixes that I've collected
and would like to target for 5.6-rc4:
- A fix to set up the PMPs on boot, which allows the kernel to access
memory on systems that don't set up permissive PMPs before getting
to Linux. This only effects machine-mode kernels, which currently
means only NOMMU kernels.
- A fix to avoid enabling supervisor-mode interrupts when running in
machine-mode, also only for NOMMU kernels.
- A pair of fixes to our KASAN support to avoid corrupting memory.
- A gitignore fix.
This boots on QEMU's virt board for me"
* tag 'riscv-for-linux-5.6-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux:
riscv: adjust the indent
riscv: allocate a complete page size for each page table
riscv: Fix gitignore
RISC-V: Don't enable all interrupts in trap_init()
riscv: set pmp configuration if kernel is running in M-mode
Pull MIPS fixes from Paul Burton:
"Here are a few MIPS fixes, and a MAINTAINERS update to hand over MIPS
maintenance to Thomas Bogendoerfer - this will be my final pull
request as MIPS maintainer.
Thanks for your helpful comments, useful corrections & responsiveness
during the time I've fulfilled the role, and I'm sure I'll pop up
elsewhere in the tree somewhere down the line"
* 'mips-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/mips/linux:
MAINTAINERS: Hand MIPS over to Thomas
MIPS: ingenic: DTS: Fix watchdog nodes
MIPS: X1000: Fix clock of watchdog node.
MIPS: vdso: Wrap -mexplicit-relocs in cc-option
MIPS: VPE: Fix a double free and a memory leak in 'release_vpe()'
MIPS: cavium_octeon: Fix syncw generation.
mips: vdso: add build time check that no 'jalr t9' calls left
MIPS: Disable VDSO time functionality on microMIPS
mips: vdso: fix 'jalr t9' crash in vdso code
Before nftables commit fb9cea50e8b3 ("main: enforce options before
commands"), 'nft list ruleset -a' happened to work, but it's wrong
and won't work anymore. Replace it by 'nft -a list ruleset'.
Reported-by: Chen Yi <yiche@redhat.com>
Fixes: 611973c1e0 ("selftests: netfilter: Introduce tests for sets with range concatenation")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
When there was no parallelism (no top-level -j arg and a pre-1.7
sphinx-build), the argument passed would be empty ("") instead of just
being missing, which would (understandably) badly confuse sphinx-build.
Fix this by removing the quotes.
Reported-by: Rafael J. Wysocki <rafael@kernel.org>
Fixes: 51e46c7a40 ("docs, parallelism: Rearrange how jobserver reservations are made")
Cc: stable@vger.kernel.org # v5.5 only
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
MPX was removed in commit 45fc24e89b ("x86/mpx: remove MPX from
arch/x86"), this removes the corresponding entry in the x86 toc.
This was suggested by a Sphinx warning.
Signed-off-by: Stephen Kitt <steve@sk2.org>
Fixes: 45fc24e89b ("x86/mpx: remove MPX from arch/x86")
Acked-by: Dave Hansen <dave.hansen@intel.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
My time with MIPS the company has reached its end, and so at best I'll
have little time spend on maintaining arch/mips/.
Ralf last authored a patch over 2 years ago, the last time he committed
one is even further back & activity was sporadic for a while before
that. The reality is that he isn't active.
Having a new maintainer with time to do things properly will be
beneficial all round. Thomas Bogendoerfer has been involved in MIPS
development for a long time & has offered to step up as maintainer, so
add Thomas and remove myself & Ralf from the MIPS entry.
Ralf already has an entry in CREDITS to honor his contributions, so this
just adds one for me.
Signed-off-by: Paul Burton <paulburton@kernel.org>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Acked-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-kernel@vger.kernel.org
Cc: linux-mips@vger.kernel.org
Currently we run SYN cookies test for all socket types and mark the test as
skipped if socket type is not compatible. This causes confusion because
skipped test might indicate a problem with the testing environment.
Instead, run the test only for the socket type which supports SYN cookies.
Also, switch to using designated initializers when setting up tests, so
that we can tweak only some test parameters, leaving the rest initialized
to default values.
Fixes: eecd618b45 ("selftests/bpf: Mark SYN cookie test skipped for UDP sockets")
Reported-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200224135327.121542-2-jakub@cloudflare.com
SOCKMAP and SOCKHASH map types can be used with reuseport BPF programs but
don't support yet storing UDP sockets. Instead of marking UDP tests with
SOCK{MAP,HASH} as skipped, don't run them at all.
Skipped test might signal that the test environment is not suitable for
running the test, while in reality the functionality is not implemented in
the kernel yet.
Before:
sh# ./test_progs -t select_reuseport
…
#40 select_reuseport:OK
Summary: 1/126 PASSED, 30 SKIPPED, 0 FAILED
After:
sh# ./test_progs -t select_reuseport
…
#40 select_reuseport:OK
Summary: 1/98 PASSED, 2 SKIPPED, 0 FAILED
The remaining two skipped tests are SYN cookies tests, which will be
addressed in the subsequent patch.
Fixes: 11318ba8ca ("selftests/bpf: Extend SK_REUSEPORT tests to cover SOCKMAP/SOCKHASH")
Reported-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200224135327.121542-1-jakub@cloudflare.com
Thomas Gleixner says:
====================
This is the third version of the BPF/RT patch set which makes both coexist
nicely. The long explanation can be found in the cover letter of the V1
submission:
https://lore.kernel.org/r/20200214133917.304937432@linutronix.de
V2 is here:
https://lore.kernel.org/r/20200220204517.863202864@linutronix.de
The following changes vs. V2 have been made:
- Rebased to bpf-next, adjusted to the lock changes in the hashmap code.
- Split the preallocation enforcement patch for instrumentation type BPF
programs into two pieces:
1) Emit a one-time warning on !RT kernels when any instrumentation type
BPF program uses run-time allocation. Emit also a corresponding
warning in the verifier log. But allow the program to run for
backward compatibility sake. After a grace period this should be
enforced.
2) On RT reject such programs because on RT the memory allocator cannot
be called from truly atomic contexts.
- Fixed the fallout from V2 as reported by Alexei and 0-day
- Removed the redundant preempt_disable() from trace_call_bpf()
- Removed the unused export of trace_call_bpf()
====================
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
In a RT kernel down_read_trylock() cannot be used from NMI context and
up_read_non_owner() is another problematic issue.
So in such a configuration, simply elide the annotated stackmap and
just report the raw IPs.
In the longer term, it might be possible to provide a atomic friendly
versions of the page cache traversal which will at least provide the info
if the pages are resident and don't need to be paged in.
[ tglx: Use IS_ENABLED() to avoid the #ifdeffery, fixup the irq work
callback and add a comment ]
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200224145644.708960317@linutronix.de
The LPM trie map cannot be used in contexts like perf, kprobes and tracing
as this map type dynamically allocates memory.
The memory allocation happens with a raw spinlock held which is a truly
spinning lock on a PREEMPT RT enabled kernel which disables preemption and
interrupts.
As RT does not allow memory allocation from such a section for various
reasons, convert the raw spinlock to a regular spinlock.
On a RT enabled kernel these locks are substituted by 'sleeping' spinlocks
which provide the proper protection but keep the code preemptible.
On a non-RT kernel regular spinlocks map to raw spinlocks, i.e. this does
not cause any functional change.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200224145644.602129531@linutronix.de
PREEMPT_RT forbids certain operations like memory allocations (even with
GFP_ATOMIC) from atomic contexts. This is required because even with
GFP_ATOMIC the memory allocator calls into code pathes which acquire locks
with long held lock sections. To ensure the deterministic behaviour these
locks are regular spinlocks, which are converted to 'sleepable' spinlocks
on RT. The only true atomic contexts on an RT kernel are the low level
hardware handling, scheduling, low level interrupt handling, NMIs etc. None
of these contexts should ever do memory allocations.
As regular device interrupt handlers and soft interrupts are forced into
thread context, the existing code which does
spin_lock*(); alloc(GPF_ATOMIC); spin_unlock*();
just works.
In theory the BPF locks could be converted to regular spinlocks as well,
but the bucket locks and percpu_freelist locks can be taken from arbitrary
contexts (perf, kprobes, tracepoints) which are required to be atomic
contexts even on RT. These mechanisms require preallocated maps, so there
is no need to invoke memory allocations within the lock held sections.
BPF maps which need dynamic allocation are only used from (forced) thread
context on RT and can therefore use regular spinlocks which in turn allows
to invoke memory allocations from the lock held section.
To achieve this make the hash bucket lock a union of a raw and a regular
spinlock and initialize and lock/unlock either the raw spinlock for
preallocated maps or the regular variant for maps which require memory
allocations.
On a non RT kernel this distinction is neither possible nor required.
spinlock maps to raw_spinlock and the extra code and conditional is
optimized out by the compiler. No functional change.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200224145644.509685912@linutronix.de
As a preparation for making the BPF locking RT friendly, factor out the
hash bucket lock operations into inline functions. This allows to do the
necessary RT modification in one place instead of sprinkling it all over
the place. No functional change.
The now unused htab argument of the lock/unlock functions will be used in
the next step which adds PREEMPT_RT support.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200224145644.420416916@linutronix.de
The required protection is that the caller cannot be migrated to a
different CPU as these functions end up in places which take either a hash
bucket lock or might trigger a kprobe inside the memory allocator. Both
scenarios can lead to deadlocks. The deadlock prevention is per CPU by
incrementing a per CPU variable which temporarily blocks the invocation of
BPF programs from perf and kprobes.
Replace the open coded preempt_[dis|en]able and __this_cpu_[inc|dec] pairs
with the new helper functions. These functions are already prepared to make
BPF work on PREEMPT_RT enabled kernels. No functional change for !RT
kernels.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200224145644.317843926@linutronix.de
The required protection is that the caller cannot be migrated to a
different CPU as these places take either a hash bucket lock or might
trigger a kprobe inside the memory allocator. Both scenarios can lead to
deadlocks. The deadlock prevention is per CPU by incrementing a per CPU
variable which temporarily blocks the invocation of BPF programs from perf
and kprobes.
Replace the open coded preempt_disable/enable() and this_cpu_inc/dec()
pairs with the new recursion prevention helpers to prepare BPF to work on
PREEMPT_RT enabled kernels. On a non-RT kernel the migrate disable/enable
in the helpers map to preempt_disable/enable(), i.e. no functional change.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200224145644.211208533@linutronix.de
The places which need to prevent the execution of trace type BPF programs
to prevent deadlocks on the hash bucket lock do this open coded.
Provide two inline functions, bpf_disable/enable_instrumentation() to
replace these open coded protection constructs.
Use migrate_disable/enable() instead of preempt_disable/enable() right away
so this works on RT enabled kernels. On a !RT kernel migrate_disable /
enable() are mapped to preempt_disable/enable().
These helpers use this_cpu_inc/dec() instead of __this_cpu_inc/dec() on an
RT enabled kernel because migrate disabled regions are preemptible and
preemption might hit in the middle of a RMW operation which can lead to
inconsistent state.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200224145644.103910133@linutronix.de
Replace the preemption disable/enable with migrate_disable/enable() to
reflect the actual requirement and to allow PREEMPT_RT to substitute it
with an actual migration disable mechanism which does not disable
preemption.
Including the code paths that go via __bpf_prog_run_save_cb().
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200224145643.998293311@linutronix.de
Instead of preemption disable/enable to reflect the purpose. This allows
PREEMPT_RT to substitute it with an actual migration disable
implementation. On non RT kernels this is still mapped to
preempt_disable/enable().
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200224145643.891428873@linutronix.de
Replace the preemption disable/enable with migrate_disable/enable() to
reflect the actual requirement and to allow PREEMPT_RT to substitute it
with an actual migration disable mechanism which does not disable
preemption.
[ tglx: Switched it over to migrate disable ]
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200224145643.785306549@linutronix.de
All of these cases are strictly of the form:
preempt_disable();
BPF_PROG_RUN(...);
preempt_enable();
Replace this with bpf_prog_run_pin_on_cpu() which wraps BPF_PROG_RUN()
with:
migrate_disable();
BPF_PROG_RUN(...);
migrate_enable();
On non RT enabled kernels this maps to preempt_disable/enable() and on RT
enabled kernels this solely prevents migration, which is sufficient as
there is no requirement to prevent reentrancy to any BPF program from a
preempting task. The only requirement is that the program stays on the same
CPU.
Therefore, this is a trivially correct transformation.
The seccomp loop does not need protection over the loop. It only needs
protection per BPF filter program
[ tglx: Converted to bpf_prog_run_pin_on_cpu() ]
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200224145643.691493094@linutronix.de
As already discussed in the previous change which introduced
BPF_RUN_PROG_PIN_ON_CPU() BPF only requires to disable migration to
guarantee per CPUness.
If RT substitutes the preempt disable based migration protection then the
cant_sleep() check will obviously trigger as preemption is not disabled.
Replace it by cant_migrate() which maps to cant_sleep() on a non RT kernel
and will verify that migration is disabled on a full RT kernel.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200224145643.583038889@linutronix.de
BPF programs require to run on one CPU to completion as they use per CPU
storage, but according to Alexei they don't need reentrancy protection as
obviously BPF programs running in thread context can always be 'preempted'
by hard and soft interrupts and instrumentation and the same program can
run concurrently on a different CPU.
The currently used mechanism to ensure CPUness is to wrap the invocation
into a preempt_disable/enable() pair. Disabling preemption is also
disabling migration for a task.
preempt_disable/enable() is used because there is no explicit way to
reliably disable only migration.
Provide a separate macro to invoke a BPF program which can be used in
migrateable task context.
It wraps BPF_PROG_RUN() in a migrate_disable/enable() pair which maps on
non RT enabled kernels to preempt_disable/enable(). On RT enabled kernels
this merely disables migration. Both methods ensure that the invoked BPF
program runs on one CPU to completion.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200224145643.474592620@linutronix.de
pcpu_freelist_populate() is disabling interrupts and then iterates over the
possible CPUs. The reason why this disables interrupts is to silence
lockdep because the invoked ___pcpu_freelist_push() takes spin locks.
Neither the interrupt disabling nor the locking are required in this
function because it's called during initialization and the resulting map is
not yet visible to anything.
Split out the actual push assignement into an inline, call it from the loop
and remove the interrupt disable.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200224145643.365930116@linutronix.de
If an element is freed via RCU then recursion into BPF instrumentation
functions is not a concern. The element is already detached from the map
and the RCU callback does not hold any locks on which a kprobe, perf event
or tracepoint attached BPF program could deadlock.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200224145643.259118710@linutronix.de
The BPF invocation from the perf event overflow handler does not require to
disable preemption because this is called from NMI or at least hard
interrupt context which is already non-preemptible.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200224145643.151953573@linutronix.de
Similar to __bpf_trace_run this is redundant because __bpf_trace_run() is
invoked from a trace point via __DO_TRACE() which already disables
preemption _before_ invoking any of the functions which are attached to a
trace point.
Remove it and add a cant_sleep() check.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200224145643.059995527@linutronix.de
trace_call_bpf() no longer disables preemption on its own.
All callers of this function has to do it explicitly.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
All callers are built in. No point to export this.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
__bpf_trace_run() disables preemption around the BPF_PROG_RUN() invocation.
This is redundant because __bpf_trace_run() is invoked from a trace point
via __DO_TRACE() which already disables preemption _before_ invoking any of
the functions which are attached to a trace point.
Remove it and add a cant_sleep() check.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200224145642.847220186@linutronix.de
Maxim Mikityanskiy