New channels are going to be opened by walking the list sequentially,
so by sorting it we will connect to the fastest interfaces first.
Signed-off-by: Aurelien Aptel <aaptel@suse.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
Even when mounting modern protocol version the server may be
configured without supporting SMB2.1 leases and the client
uses SMB2 oplock to optimize IO performance through local caching.
However there is a problem in oplock break handling that leads
to missing a break notification on the client who has a file
opened. It latter causes big latencies to other clients that
are trying to open the same file.
The problem reproduces when there are multiple shares from the
same server mounted on the client. The processing code tries to
match persistent and volatile file ids from the break notification
with an open file but it skips all share besides the first one.
Fix this by looking up in all shares belonging to the server that
issued the oplock break.
Cc: Stable <stable@vger.kernel.org>
Signed-off-by: Pavel Shilovsky <pshilov@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
It can cause
to fail with
modprobe: FATAL: Module <module> is builtin.
RHBZ: 1767094
Signed-off-by: Ronnie Sahlberg <lsahlber@redhat.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
During reconnecting, the transport may have already been destroyed and is in
the process being reconnected. In this case, return -EAGAIN to not fail and
to retry this I/O.
Signed-off-by: Long Li <longli@microsoft.com>
Cc: stable@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
It's not necessary to queue invalidated memory registration to work queue, as
all we need to do is to unmap the SG and make it usable again. This can save
CPU cycles in normal data paths as memory registration errors are rare and
normally only happens during reconnection.
Signed-off-by: Long Li <longli@microsoft.com>
Cc: stable@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
Helps distinguish between an interrupted close and a truly
unmatched open.
Signed-off-by: Ronnie Sahlberg <lsahlber@redhat.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
When an OPEN command is cancelled we mark a mid as
cancelled and let the demultiplex thread process it
by closing an open handle. The problem is there is
a race between a system call thread and the demultiplex
thread and there may be a situation when the mid has
been already processed before it is set as cancelled.
Fix this by processing cancelled requests when mids
are being destroyed which means that there is only
one thread referencing a particular mid. Also set
mids as cancelled unconditionally on their state.
Cc: Stable <stable@vger.kernel.org>
Tested-by: Frank Sorenson <sorenson@redhat.com>
Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com>
Signed-off-by: Pavel Shilovsky <pshilov@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
There is a race between a system call processing thread
and the demultiplex thread when mid->resp_buf becomes NULL
and later is being accessed to get credits. It happens when
the 1st thread wakes up before a mid callback is called in
the 2nd one but the mid state has already been set to
MID_RESPONSE_RECEIVED. This causes NULL pointer dereference
in mid callback.
Fix this by saving credits from the response before we
update the mid state and then use this value in the mid
callback rather then accessing a response buffer.
Cc: Stable <stable@vger.kernel.org>
Fixes: ee258d7915 ("CIFS: Move credit processing to mid callbacks for SMB3")
Tested-by: Frank Sorenson <sorenson@redhat.com>
Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com>
Signed-off-by: Pavel Shilovsky <pshilov@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
If Close command is interrupted before sending a request
to the server the client ends up leaking an open file
handle. This wastes server resources and can potentially
block applications that try to remove the file or any
directory containing this file.
Fix this by putting the close command into a worker queue,
so another thread retries it later.
Cc: Stable <stable@vger.kernel.org>
Tested-by: Frank Sorenson <sorenson@redhat.com>
Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com>
Signed-off-by: Pavel Shilovsky <pshilov@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
Currently the client translates O_SYNC and O_DIRECT flags
into corresponding SMB create options when openning a file.
The problem is that on reconnect when the file is being
re-opened the client doesn't set those flags and it causes
a server to reject re-open requests because create options
don't match. The latter means that any subsequent system
call against that open file fail until a share is re-mounted.
Fix this by properly setting SMB create options when
re-openning files after reconnects.
Fixes: 1013e760d1: ("SMB3: Don't ignore O_SYNC/O_DSYNC and O_DIRECT flags")
Cc: Stable <stable@vger.kernel.org>
Signed-off-by: Pavel Shilovsky <pshilov@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
The smb2/smb3 message checking code was logging to dmesg when mounting
with encryption ("seal") for compounded SMB3 requests. When encrypted
the whole frame (including potentially multiple compounds) is read
so the length field is longer than in the case of non-encrypted
case (where length field will match the the calculated length for
the particular SMB3 request in the compound being validated).
Avoids the warning on mount (with "seal"):
"srv rsp padded more than expected. Length 384 not ..."
Signed-off-by: Steve French <stfrench@microsoft.com>
Return directly after a call of the function "build_path_from_dentry"
failed at the beginning.
Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Steve French <stfrench@microsoft.com>
Move the same error code assignments so that such exception handling
can be better reused at the end of this function.
This issue was detected by using the Coccinelle software.
Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Steve French <stfrench@microsoft.com>
Reuse existing functionality from memdup_user() instead of keeping
duplicate source code.
Generated by: scripts/coccinelle/api/memdup_user.cocci
Fixes: f5b05d622a ("cifs: add IOCTL for QUERY_INFO passthrough to userspace")
Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Steve French <stfrench@microsoft.com>
While it's not friendly to fail user processes that issue more iovs
than we support, at least we should return the correct error code so the
user process gets a chance to retry with smaller number of iovs.
Signed-off-by: Long Li <longli@microsoft.com>
Cc: stable@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
On re-send, there might be a reconnect and all prevoius memory registrations
need to be invalidated and deregistered.
Signed-off-by: Long Li <longli@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
Fixes gcc '-Wunused-but-set-variable' warning:
fs/cifs/file.c: In function 'cifs_flock':
fs/cifs/file.c:1704:8: warning:
variable 'netfid' set but not used [-Wunused-but-set-variable]
fs/cifs/file.c:1702:24: warning:
variable 'cinode' set but not used [-Wunused-but-set-variable]
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
The flock system call locks the whole file rather than a byte
range and so is currently emulated by various other file systems
by simply sending a byte range lock for the whole file.
Add flock handling for cifs.ko in similar way.
xfstest generic/504 passes with this as well
Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Pavel Shilovsky <pshilov@microsoft.com>
Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com>
fs/cifs/cifsacl.c:43:30: warning:
sid_user defined but not used [-Wunused-const-variable=]
It is never used, so remove it.
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
Smatch gets confused because we sometimes refer to "server->srv_mutex" and
sometimes to "sess->server->srv_mutex". They refer to the same lock so
let's just make this consistent.
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
Alexei Starovoitov says:
====================
pull-request: bpf-next 2019-11-24
The following pull-request contains BPF updates for your *net-next* tree.
We've added 27 non-merge commits during the last 4 day(s) which contain
a total of 50 files changed, 2031 insertions(+), 548 deletions(-).
The main changes are:
1) Optimize bpf_tail_call() from retpoline-ed indirect jump to direct jump,
from Daniel.
2) Support global variables in libbpf, from Andrii.
3) Cleanup selftests with BPF_TRACE_x() macro, from Martin.
4) Fix devmap hash, from Toke.
5) Fix register bounds after 32-bit conditional jumps, from Yonghong.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Johan Hedberg says:
====================
pull request: bluetooth-next 2019-11-24
Here's one last bluetooth-next pull request for the 5.5 kernel:
- Fix BDADDR_PROPERTY & INVALID_BDADDR quirk handling
- Added support for BCM4334B0 and BCM4335A0 controllers
- A few other smaller fixes related to locking and memory leaks
====================
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
This enables the use of SW timestamping.
ax88179_178a uses the usbnet transmit function usbnet_start_xmit() which
implements software timestamping. ax88179_178a overrides ethtool_ops but
missed to set .get_ts_info. This caused SOF_TIMESTAMPING_TX_SOFTWARE
capability to be not available.
Signed-off-by: Andreas K. Besslein <besslein.andreas@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Ido Schimmel says:
====================
mlxsw: Two small updates
Patch #1 from Petr handles a corner case in GRE tunnel offload.
Patch #2 from Amit fixes a recent issue where the driver was programming
the device to use an adjacency index (for a nexthop) that was not
properly initialized.
====================
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
When mlxsw_sp_adj_discard_write() is called for the first time, the
value stored in 'mlxsw_sp->router->adj_discard_index' is invalid, as
indicated by 'mlxsw_sp->router->adj_discard_index_valid' being set to
'false'.
In this case, we should not use the value initially stored in
'mlxsw_sp->router->adj_discard_index' (0) and instead use the value
allocated later in the function.
Fixes: 983db6198f ("mlxsw: spectrum_router: Allocate discard adjacency entry when needed")
Signed-off-by: Amit Cohen <amitc@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
When a GRE tunnel is bound to an underlay netdevice and that netdevice is
moved to a different VRF, that could cause two tunnels to have the same
underlay local address in the same VRF. Linux in this situation dispatches
the traffic according to the tunnel key (or lack thereof), but that cannot
be offloaded to Spectrum devices.
Detect this situation and unoffload the two impacted tunnels when it
happens.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Given that we have BPF_MOD_NOP_TO_{CALL,JUMP}, BPF_MOD_{CALL,JUMP}_TO_NOP
and BPF_MOD_{CALL,JUMP}_TO_{CALL,JUMP} poke types and that we also pass in
old_addr as well as new_addr, it's a bit redundant and unnecessarily
complicates __bpf_arch_text_poke() itself since we can derive the same from
the *_addr that were passed in. Hence simplify and use BPF_MOD_{CALL,JUMP}
as types which also allows to clean up call-sites.
In addition to that, __bpf_arch_text_poke() currently verifies that text
matches expected old_insn before we invoke text_poke_bp(). Also add a check
on new_insn and skip rewrite if it already matches. Reason why this is rather
useful is that it avoids making any special casing in prog_array_map_poke_run()
when old and new prog were NULL and has the benefit that also for this case
we perform a check on text whether it really matches our expectations.
Suggested-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/fcb00a2b0b288d6c73de4ef58116a821c8fe8f2f.1574555798.git.daniel@iogearbox.net
For BPF_PROG_TYPE_TRACING, the bpf_prog's ctx is an array of u64.
This patch borrows the idea from BPF_CALL_x in filter.h to
convert a u64 to the arg type of the traced function.
The new BPF_TRACE_x has an arg to specify the return type of a bpf_prog.
It will be used in the future TCP-ops bpf_prog that may return "void".
The new macros are defined in the new header file "bpf_trace_helpers.h".
It is under selftests/bpf/ for now. It could be moved to libbpf later
after seeing more upcoming non-tracing use cases.
The tests are changed to use these new macros also. Hence,
the k[s]u8/16/32/64 are no longer needed and they are removed
from the bpf_helpers.h.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20191123202504.1502696-1-kafai@fb.com
Add a definition of bpf_jit_blinding_enabled() when CONFIG_BPF_JIT is not set
in order to fix a recent build regression:
[...]
CC kernel/bpf/verifier.o
CC kernel/bpf/inode.o
kernel/bpf/verifier.c: In function ‘fixup_bpf_calls’:
kernel/bpf/verifier.c:9132:25: error: implicit declaration of function ‘bpf_jit_blinding_enabled’; did you mean ‘bpf_jit_kallsyms_enabled’? [-Werror=implicit-function-declaration]
9132 | bool expect_blinding = bpf_jit_blinding_enabled(prog);
| ^~~~~~~~~~~~~~~~~~~~~~~~
| bpf_jit_kallsyms_enabled
CC kernel/bpf/helpers.o
CC kernel/bpf/hashtab.o
[...]
Fixes: d2e4c1e6c2 ("bpf: Constant map key tracking for prog array pokes")
Reported-by: Jakub Sitnicki <jakub@cloudflare.com>
Reported-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/40baf8f3507cac4851a310578edfb98ce73b5605.1574541375.git.daniel@iogearbox.net
Daniel Borkmann says:
====================
This gets rid of indirect jumps for BPF tail calls whenever possible.
The series adds emission for *direct* jumps for tail call maps in order
to avoid the retpoline overhead from a493a87f38 ("bpf, x64: implement
retpoline for tail call") for situations that allow for it, meaning,
for known constant keys at verification time which are used as index
into the tail call map. See patch 7/8 for more general details.
Thanks!
v1 -> v2:
- added more test cases
- u8 ip_stable -> bool (Andrii)
- removed bpf_map_poke_{un,}lock and simplified the code (Andrii)
- added break into prog_array_map_poke_untrack since there's just
one prog (Andrii)
- fixed typo: for for in commit msg (Andrii)
- reworked __bpf_arch_text_poke (Andrii)
- added subtests, and comment on tests themselves, NULL-NULL
transistion (Andrii)
- in constant map key tracking I've moved the map_poke_track callback
to once we've finished creating the poke tab as otherwise concurrent
access from tail call map would blow up (since we realloc the table)
rfc -> v1:
- Applied Alexei's and Andrii's feeback from
https://lore.kernel.org/bpf/cover.1573779287.git.daniel@iogearbox.net/T/#t
====================
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Add several BPF kselftest cases for tail calls which test the various
patch directions, and that multiple locations are patched in same and
different programs.
# ./test_progs -n 45
#45/1 tailcall_1:OK
#45/2 tailcall_2:OK
#45/3 tailcall_3:OK
#45/4 tailcall_4:OK
#45/5 tailcall_5:OK
#45 tailcalls:OK
Summary: 1/5 PASSED, 0 SKIPPED, 0 FAILED
I've also verified the JITed dump after each of the rewrite cases that
it matches expectations.
Also regular test_verifier suite passes fine which contains further tail
call tests:
# ./test_verifier
[...]
Summary: 1563 PASSED, 0 SKIPPED, 0 FAILED
Checked under JIT, interpreter and JIT + hardening.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/3d6cbecbeb171117dccfe153306e479798fb608d.1574452833.git.daniel@iogearbox.net
Add initial code emission for *direct* jumps for tail call maps in
order to avoid the retpoline overhead from a493a87f38 ("bpf, x64:
implement retpoline for tail call") for situations that allow for
it, meaning, for known constant keys at verification time which are
used as index into the tail call map. In case of Cilium which makes
heavy use of tail calls, constant keys are used in the vast majority,
only for a single occurrence we use a dynamic key.
High level outline is that if the target prog is NULL in the map, we
emit a 5-byte nop for the fall-through case and if not, we emit a
5-byte direct relative jmp to the target bpf_func + skipped prologue
offset. Later during runtime, we patch these 5-byte nop/jmps upon
tail call map update or deletions dynamically. Note that on x86-64
the direct jmp works as we reuse the same stack frame and skip
prologue (as opposed to some other JIT implementations).
One of the issues is that the tail call map slots can change at any
given time even during JITing. Therefore, we have two passes: i) emit
nops for all patchable locations during main JITing phase until we
declare prog->jited = 1 eventually. At this point the image is stable,
not public yet and with all jmps disabled. While JITing, we collect
additional info like poke->ip in order to remember the patch location
for later modifications. In ii) bpf_tail_call_direct_fixup() walks
over the progs poke_tab, locks the tail call maps poke_mutex to
prevent from parallel updates and patches in the right locations via
__bpf_arch_text_poke(). Note, the main bpf_arch_text_poke() cannot
be used at this point since we're not yet exposed to kallsyms. For
the update we use plain memcpy() since the image is not public and
still in read-write mode. After patching, we activate that poke entry
through poke->ip_stable. Meaning, at this point any tail call map
updates/deletions are not going to ignore that poke entry anymore.
Then, bpf_arch_text_poke() might still occur on the read-write image
until we finally locked it as read-only. Both modifications on the
given image are under text_mutex to avoid interference with each
other when update requests come in in parallel for different tail
call maps (current one we have locked in JIT and different one where
poke->ip_stable was already set).
Example prog:
# ./bpftool p d x i 1655
0: (b7) r3 = 0
1: (18) r2 = map[id:526]
3: (85) call bpf_tail_call#12
4: (b7) r0 = 1
5: (95) exit
Before:
# ./bpftool p d j i 1655
0xffffffffc076e55c:
0: nopl 0x0(%rax,%rax,1)
5: push %rbp
6: mov %rsp,%rbp
9: sub $0x200,%rsp
10: push %rbx
11: push %r13
13: push %r14
15: push %r15
17: pushq $0x0 _
19: xor %edx,%edx |_ index (arg 3)
1b: movabs $0xffff88d95cc82600,%rsi |_ map (arg 2)
25: mov %edx,%edx | index >= array->map.max_entries
27: cmp %edx,0x24(%rsi) |
2a: jbe 0x0000000000000066 |_
2c: mov -0x224(%rbp),%eax | tail call limit check
32: cmp $0x20,%eax |
35: ja 0x0000000000000066 |
37: add $0x1,%eax |
3a: mov %eax,-0x224(%rbp) |_
40: mov 0xd0(%rsi,%rdx,8),%rax |_ prog = array->ptrs[index]
48: test %rax,%rax | prog == NULL check
4b: je 0x0000000000000066 |_
4d: mov 0x30(%rax),%rax | goto *(prog->bpf_func + prologue_size)
51: add $0x19,%rax |
55: callq 0x0000000000000061 | retpoline for indirect jump
5a: pause |
5c: lfence |
5f: jmp 0x000000000000005a |
61: mov %rax,(%rsp) |
65: retq |_
66: mov $0x1,%eax
6b: pop %rbx
6c: pop %r15
6e: pop %r14
70: pop %r13
72: pop %rbx
73: leaveq
74: retq
After; state after JIT:
# ./bpftool p d j i 1655
0xffffffffc08e8930:
0: nopl 0x0(%rax,%rax,1)
5: push %rbp
6: mov %rsp,%rbp
9: sub $0x200,%rsp
10: push %rbx
11: push %r13
13: push %r14
15: push %r15
17: pushq $0x0 _
19: xor %edx,%edx |_ index (arg 3)
1b: movabs $0xffff9d8afd74c000,%rsi |_ map (arg 2)
25: mov -0x224(%rbp),%eax | tail call limit check
2b: cmp $0x20,%eax |
2e: ja 0x000000000000003e |
30: add $0x1,%eax |
33: mov %eax,-0x224(%rbp) |_
39: jmpq 0xfffffffffffd1785 |_ [direct] goto *(prog->bpf_func + prologue_size)
3e: mov $0x1,%eax
43: pop %rbx
44: pop %r15
46: pop %r14
48: pop %r13
4a: pop %rbx
4b: leaveq
4c: retq
After; state after map update (target prog):
# ./bpftool p d j i 1655
0xffffffffc08e8930:
0: nopl 0x0(%rax,%rax,1)
5: push %rbp
6: mov %rsp,%rbp
9: sub $0x200,%rsp
10: push %rbx
11: push %r13
13: push %r14
15: push %r15
17: pushq $0x0
19: xor %edx,%edx
1b: movabs $0xffff9d8afd74c000,%rsi
25: mov -0x224(%rbp),%eax
2b: cmp $0x20,%eax .
2e: ja 0x000000000000003e .
30: add $0x1,%eax .
33: mov %eax,-0x224(%rbp) |_
39: jmpq 0xffffffffffb09f55 |_ goto *(prog->bpf_func + prologue_size)
3e: mov $0x1,%eax
43: pop %rbx
44: pop %r15
46: pop %r14
48: pop %r13
4a: pop %rbx
4b: leaveq
4c: retq
After; state after map update (no prog):
# ./bpftool p d j i 1655
0xffffffffc08e8930:
0: nopl 0x0(%rax,%rax,1)
5: push %rbp
6: mov %rsp,%rbp
9: sub $0x200,%rsp
10: push %rbx
11: push %r13
13: push %r14
15: push %r15
17: pushq $0x0
19: xor %edx,%edx
1b: movabs $0xffff9d8afd74c000,%rsi
25: mov -0x224(%rbp),%eax
2b: cmp $0x20,%eax .
2e: ja 0x000000000000003e .
30: add $0x1,%eax .
33: mov %eax,-0x224(%rbp) |_
39: nopl 0x0(%rax,%rax,1) |_ fall-through nop
3e: mov $0x1,%eax
43: pop %rbx
44: pop %r15
46: pop %r14
48: pop %r13
4a: pop %rbx
4b: leaveq
4c: retq
Nice bonus is that this also shrinks the code emission quite a bit
for every tail call invocation.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/6ada4c1c9d35eeb5f4ecfab94593dafa6b5c4b09.1574452833.git.daniel@iogearbox.net
Add tracking of constant keys into tail call maps. The signature of
bpf_tail_call_proto is that arg1 is ctx, arg2 map pointer and arg3
is a index key. The direct call approach for tail calls can be enabled
if the verifier asserted that for all branches leading to the tail call
helper invocation, the map pointer and index key were both constant
and the same.
Tracking of map pointers we already do from prior work via c93552c443
("bpf: properly enforce index mask to prevent out-of-bounds speculation")
and 09772d92cd ("bpf: avoid retpoline for lookup/update/ delete calls
on maps").
Given the tail call map index key is not on stack but directly in the
register, we can add similar tracking approach and later in fixup_bpf_calls()
add a poke descriptor to the progs poke_tab with the relevant information
for the JITing phase.
We internally reuse insn->imm for the rewritten BPF_JMP | BPF_TAIL_CALL
instruction in order to point into the prog's poke_tab, and keep insn->imm
as 0 as indicator that current indirect tail call emission must be used.
Note that publishing to the tracker must happen at the end of fixup_bpf_calls()
since adding elements to the poke_tab reallocates its memory, so we need
to wait until its in final state.
Future work can generalize and add similar approach to optimize plain
array map lookups. Difference there is that we need to look into the key
value that sits on stack. For clarity in bpf_insn_aux_data, map_state
has been renamed into map_ptr_state, so we get map_{ptr,key}_state as
trackers.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/e8db37f6b2ae60402fa40216c96738ee9b316c32.1574452833.git.daniel@iogearbox.net
This work adds program tracking to prog array maps. This is needed such
that upon prog array updates/deletions we can fix up all programs which
make use of this tail call map. We add ops->map_poke_{un,}track()
helpers to maps to maintain the list of programs and ops->map_poke_run()
for triggering the actual update.
bpf_array_aux is extended to contain the list head and poke_mutex in
order to serialize program patching during updates/deletions.
bpf_free_used_maps() will untrack the program shortly before dropping
the reference to the map. For clearing out the prog array once all urefs
are dropped we need to use schedule_work() to have a sleepable context.
The prog_array_map_poke_run() is triggered during updates/deletions and
walks the maintained prog list. It checks in their poke_tabs whether the
map and key is matching and runs the actual bpf_arch_text_poke() for
patching in the nop or new jmp location. Depending on the type of update,
we use one of BPF_MOD_{NOP_TO_JUMP,JUMP_TO_NOP,JUMP_TO_JUMP}.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/1fb364bb3c565b3e415d5ea348f036ff379e779d.1574452833.git.daniel@iogearbox.net
Add a test that benchmarks different ways of attaching BPF program to a kernel function.
Here are the results for 2.4Ghz x86 cpu on a kernel without mitigations:
$ ./test_progs -n 49 -v|grep events
task_rename base 2743K events per sec
task_rename kprobe 2419K events per sec
task_rename kretprobe 1876K events per sec
task_rename raw_tp 2578K events per sec
task_rename fentry 2710K events per sec
task_rename fexit 2685K events per sec
On a kernel with retpoline:
$ ./test_progs -n 49 -v|grep events
task_rename base 2401K events per sec
task_rename kprobe 1930K events per sec
task_rename kretprobe 1485K events per sec
task_rename raw_tp 2053K events per sec
task_rename fentry 2351K events per sec
task_rename fexit 2185K events per sec
All 5 approaches:
- kprobe/kretprobe in __set_task_comm()
- raw tracepoint in trace_task_rename()
- fentry/fexit in __set_task_comm()
are roughly equivalent.
__set_task_comm() by itself is quite fast, so any extra instructions add up.
Until BPF trampoline was introduced the fastest mechanism was raw tracepoint.
kprobe via ftrace was second best. kretprobe is slow due to trap. New
fentry/fexit methods via BPF trampoline are clearly the fastest and the
difference is more pronounced with retpoline on, since BPF trampoline doesn't
use indirect jumps.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20191122011515.255371-1-ast@kernel.org
Yonghong Song says:
====================
With latest llvm, bpf selftest test_progs, which has +alu32 enabled, failed for
strobemeta.o and a few other subtests. The reason is due to that
verifier did not provide better var_off.mask after jmp32 instructions.
This patch set addressed this issue and after the fix, test_progs passed
with alu32.
Patch #1 provided detailed explanation of the problem and the fix.
Patch #2 added three tests in test_verifier.
Changelog:
v1 -> v2:
- do not directly manipulate tnum.{value,mask} in __reg_bound_offset32(),
using tnum_lshift/tnum_rshift functions instead
- do __reg_bound_offset32() after regular 64bit __reg_bound_offset()
since the latter may give a better upper 32bit var_off, which can
be inherited by __reg_bound_offset32().
====================
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Three test cases are added.
Test 1: jmp32 'reg op imm'.
Test 2: jmp32 'reg op reg' where dst 'reg' has unknown constant
and src 'reg' has known constant
Test 3: jmp32 'reg op reg' where dst 'reg' has known constant
and src 'reg' has unknown constant
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20191121170651.449096-1-yhs@fb.com
If bpf_object__open_file() gets path like "some/dir/obj.o", it should derive
BPF object's name as "obj" (unless overriden through opts->object_name).
Instead, due to using `path` as a fallback value for opts->obj_name, path is
used as is for object name, so for above example BPF object's name will be
verbatim "some/dir/obj", which leads to all sorts of troubles, especially when
internal maps are concern (they are using up to 8 characters of object name).
Fix that by ensuring object_name stays NULL, unless overriden.
Fixes: 291ee02b5e ("libbpf: Refactor bpf_object__open APIs to use common opts")
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20191122003527.551556-1-andriin@fb.com
With latest llvm (trunk https://github.com/llvm/llvm-project),
test_progs, which has +alu32 enabled, failed for strobemeta.o.
The verifier output looks like below with edit to replace large
decimal numbers with hex ones.
193: (85) call bpf_probe_read_user_str#114
R0=inv(id=0)
194: (26) if w0 > 0x1 goto pc+4
R0_w=inv(id=0,umax_value=0xffffffff00000001)
195: (6b) *(u16 *)(r7 +80) = r0
196: (bc) w6 = w0
R6_w=inv(id=0,umax_value=0xffffffff,var_off=(0x0; 0xffffffff))
197: (67) r6 <<= 32
R6_w=inv(id=0,smax_value=0x7fffffff00000000,umax_value=0xffffffff00000000,
var_off=(0x0; 0xffffffff00000000))
198: (77) r6 >>= 32
R6=inv(id=0,umax_value=0xffffffff,var_off=(0x0; 0xffffffff))
...
201: (79) r8 = *(u64 *)(r10 -416)
R8_w=map_value(id=0,off=40,ks=4,vs=13872,imm=0)
202: (0f) r8 += r6
R8_w=map_value(id=0,off=40,ks=4,vs=13872,umax_value=0xffffffff,var_off=(0x0; 0xffffffff))
203: (07) r8 += 9696
R8_w=map_value(id=0,off=9736,ks=4,vs=13872,umax_value=0xffffffff,var_off=(0x0; 0xffffffff))
...
255: (bf) r1 = r8
R1_w=map_value(id=0,off=9736,ks=4,vs=13872,umax_value=0xffffffff,var_off=(0x0; 0xffffffff))
...
257: (85) call bpf_probe_read_user_str#114
R1 unbounded memory access, make sure to bounds check any array access into a map
The value range for register r6 at insn 198 should be really just 0/1.
The umax_value=0xffffffff caused later verification failure.
After jmp instructions, the current verifier already tried to use just
obtained information to get better register range. The current mechanism is
for 64bit register only. This patch implemented to tighten the range
for 32bit sub-registers after jmp32 instructions.
With the patch, we have the below range ranges for the
above code sequence:
193: (85) call bpf_probe_read_user_str#114
R0=inv(id=0)
194: (26) if w0 > 0x1 goto pc+4
R0_w=inv(id=0,smax_value=0x7fffffff00000001,umax_value=0xffffffff00000001,
var_off=(0x0; 0xffffffff00000001))
195: (6b) *(u16 *)(r7 +80) = r0
196: (bc) w6 = w0
R6_w=inv(id=0,umax_value=0xffffffff,var_off=(0x0; 0x1))
197: (67) r6 <<= 32
R6_w=inv(id=0,umax_value=0x100000000,var_off=(0x0; 0x100000000))
198: (77) r6 >>= 32
R6=inv(id=0,umax_value=1,var_off=(0x0; 0x1))
...
201: (79) r8 = *(u64 *)(r10 -416)
R8_w=map_value(id=0,off=40,ks=4,vs=13872,imm=0)
202: (0f) r8 += r6
R8_w=map_value(id=0,off=40,ks=4,vs=13872,umax_value=1,var_off=(0x0; 0x1))
203: (07) r8 += 9696
R8_w=map_value(id=0,off=9736,ks=4,vs=13872,umax_value=1,var_off=(0x0; 0x1))
...
255: (bf) r1 = r8
R1_w=map_value(id=0,off=9736,ks=4,vs=13872,umax_value=1,var_off=(0x0; 0x1))
...
257: (85) call bpf_probe_read_user_str#114
...
At insn 194, the register R0 has better var_off.mask and smax_value.
Especially, the var_off.mask ensures later lshift and rshift
maintains proper value range.
Suggested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20191121170650.449030-1-yhs@fb.com
Tetsuo pointed out that it was not only the device unregister hook that was
broken for devmap_hash types, it was also cleanup on map free. So better
fix this as well.
While we're at it, there's no reason to allocate the netdev_map array for
DEVMAP_HASH, so skip that and adjust the cost accordingly.
Fixes: 6f9d451ab1 ("xdp: Add devmap_hash map type for looking up devices by hashed index")
Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20191121133612.430414-1-toke@redhat.com
Andrii Nakryiko says:
====================
This patch set salvages all the non-extern-specific changes out of blocked
externs patch set ([0]). In addition to small clean ups, it also refactors
libbpf's handling of relocations and allows support for global (non-static)
variables.
[0] https://patchwork.ozlabs.org/project/netdev/list/?series=143358&state=*
====================
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
