We used bpf_prog_pack to aggregate bpf programs into huge page to
relieve the iTLB pressure on the system. This was merged for ARM64[1]
We can apply it to bpf trampoline as well. This would increase the
preformance of fentry and struct_ops programs.
[1] https://lore.kernel.org/bpf/20240228141824.119877-1-puranjay12@gmail.com/
Signed-off-by: Puranjay Mohan <puranjay12@gmail.com>
Reviewed-by: Pu Lehui <pulehui@huawei.com>
Message-ID: <20240304202803.31400-1-puranjay12@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Use bpf_jit_binary_pack_alloc for memory management of JIT binaries in
ARM64 BPF JIT. The bpf_jit_binary_pack_alloc creates a pair of RW and RX
buffers. The JIT writes the program into the RW buffer. When the JIT is
done, the program is copied to the final RX buffer
with bpf_jit_binary_pack_finalize.
Implement bpf_arch_text_copy() and bpf_arch_text_invalidate() for ARM64
JIT as these functions are required by bpf_jit_binary_pack allocator.
Signed-off-by: Puranjay Mohan <puranjay12@gmail.com>
Acked-by: Song Liu <song@kernel.org>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/20240228141824.119877-3-puranjay12@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
The prologue generation code has been modified to make the callback
program use the stack of the program marked as exception boundary where
callee-saved registers are already pushed.
As the bpf_throw function never returns, if it clobbers any callee-saved
registers, they would remain clobbered. So, the prologue of the
exception-boundary program is modified to push R23 and R24 as well,
which the callback will then recover in its epilogue.
The Procedure Call Standard for the Arm 64-bit Architecture[1] states
that registers r19 to r28 should be saved by the callee. BPF programs on
ARM64 already save all callee-saved registers except r23 and r24. This
patch adds an instruction in prologue of the program to save these
two registers and another instruction in the epilogue to recover them.
These extra instructions are only added if bpf_throw() is used. Otherwise
the emitted prologue/epilogue remains unchanged.
[1] https://github.com/ARM-software/abi-aa/blob/main/aapcs64/aapcs64.rst
Signed-off-by: Puranjay Mohan <puranjay12@gmail.com>
Link: https://lore.kernel.org/r/20240201125225.72796-3-puranjay12@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
ARM64 bpf jit satisfies the following two conditions:
1) support BPF_XCHG() on pointer-sized word.
2) the implementation of xchg is the same as atomic_xchg() on
pointer-sized words. Both of these two functions use arch_xchg() to
implement the exchange.
So enable the inline of bpf_kptr_xchg() for arm64 bpf jit.
Signed-off-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/r/20240119102529.99581-2-houtao@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Instead of blindly allocating PAGE_SIZE for each trampoline, check the size
of the trampoline with arch_bpf_trampoline_size(). This size is saved in
bpf_tramp_image->size, and used for modmem charge/uncharge. The fallback
arch_alloc_bpf_trampoline() still allocates a whole page because we need to
use set_memory_* to protect the memory.
struct_ops trampoline still uses a whole page for multiple trampolines.
With this size check at caller (regular trampoline and struct_ops
trampoline), remove arch_bpf_trampoline_size() from
arch_prepare_bpf_trampoline() in archs.
Also, update bpf_image_ksym_add() to handle symbol of different sizes.
Signed-off-by: Song Liu <song@kernel.org>
Acked-by: Ilya Leoshkevich <iii@linux.ibm.com>
Tested-by: Ilya Leoshkevich <iii@linux.ibm.com> # on s390x
Acked-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Björn Töpel <bjorn@rivosinc.com>
Tested-by: Björn Töpel <bjorn@rivosinc.com> # on riscv
Link: https://lore.kernel.org/r/20231206224054.492250-7-song@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This helper will be used to calculate the size of the trampoline before
allocating the memory.
arch_prepare_bpf_trampoline() for arm64 and riscv64 can use
arch_bpf_trampoline_size() to check the trampoline fits in the image.
OTOH, arch_prepare_bpf_trampoline() for s390 has to call the JIT process
twice, so it cannot use arch_bpf_trampoline_size().
Signed-off-by: Song Liu <song@kernel.org>
Acked-by: Ilya Leoshkevich <iii@linux.ibm.com>
Tested-by: Ilya Leoshkevich <iii@linux.ibm.com> # on s390x
Acked-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Björn Töpel <bjorn@rivosinc.com>
Tested-by: Björn Töpel <bjorn@rivosinc.com> # on riscv
Link: https://lore.kernel.org/r/20231206224054.492250-6-song@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
We are using "im" for "struct bpf_tramp_image" and "tr" for "struct
bpf_trampoline" in most of the code base. The only exception is the
prototype and fallback version of arch_prepare_bpf_trampoline(). Update
them to match the rest of the code base.
We mix "orig_call" and "func_addr" for the argument in different versions
of arch_prepare_bpf_trampoline(). s/orig_call/func_addr/g so they match.
Signed-off-by: Song Liu <song@kernel.org>
Acked-by: Ilya Leoshkevich <iii@linux.ibm.com>
Tested-by: Ilya Leoshkevich <iii@linux.ibm.com> # on s390x
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20231206224054.492250-3-song@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
We would like to know whether a bpf_prog corresponds to the main prog or
one of the subprogs. The current JIT implementations simply check this
using the func_idx in bpf_prog->aux->func_idx. When the index is 0, it
belongs to the main program, otherwise it corresponds to some
subprogram.
This will also be necessary to halt exception propagation while walking
the stack when an exception is thrown, so we add a simple helper
function to check this, named bpf_is_subprog, and convert existing JIT
implementations to also make use of it.
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20230912233214.1518551-2-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Add support for 32-bit offset jmp instructions. Given the arm64 direct jump
range is +-128MB, which is large enough for BPF prog, jumps beyond this range
are not supported.
Signed-off-by: Xu Kuohai <xukuohai@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Florent Revest <revest@chromium.org>
Acked-by: Florent Revest <revest@chromium.org>
Link: https://lore.kernel.org/bpf/20230815154158.717901-6-xukuohai@huaweicloud.com
When running an freplace attached bpf program on an arm64 system w were
seeing the following issue:
Unhandled 64-bit el1h sync exception on CPU47, ESR 0x0000000036000003 -- BTI
After a bit of work to track it down I determined that what appeared to be
happening is that the 'bti c' at the start of the program was somehow being
reached after a 'br' instruction. Further digging pointed me toward the
fact that the function was attached via freplace. This in turn led me to
build_plt which I believe is invoking the long jump which is triggering
this error.
To resolve it we can replace the 'bti c' with 'bti jc' and add a comment
explaining why this has to be modified as such.
Fixes: b2ad54e153 ("bpf, arm64: Implement bpf_arch_text_poke() for arm64")
Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Acked-by: Xu Kuohai <xukuohai@huawei.com>
Link: https://lore.kernel.org/r/168926677665.316237.9953845318337455525.stgit@ahduyck-xeon-server.home.arpa
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This extends the BPF trampoline JIT to support attachment to functions
that take small structures (up to 128bit) as argument. This is trivially
achieved by saving/restoring a number of "argument registers" rather
than a number of arguments.
The AAPCS64 section 6.8.2 describes the parameter passing ABI.
"Composite types" (like C structs) below 16 bytes (as enforced by the
BPF verifier) are provided as part of the 8 argument registers as
explained in the section C.12.
Signed-off-by: Florent Revest <revest@chromium.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yhs@fb.com>
Acked-by: Xu Kuohai <xukuohai@huawei.com>
Link: https://lore.kernel.org/bpf/20230511140507.514888-1-revest@chromium.org
When BPF_TRAMP_F_CALL_ORIG is set, BPF trampoline uses BLR to jump
back to the instruction next to call site to call the patched function.
For BTI-enabled kernel, the instruction next to call site is usually
PACIASP, in this case, it's safe to jump back with BLR. But when
the call site is not followed by a PACIASP or bti, a BTI exception
is triggered.
Here is a fault log:
Unhandled 64-bit el1h sync exception on CPU0, ESR 0x0000000034000002 -- BTI
CPU: 0 PID: 263 Comm: test_progs Tainted: GF
Hardware name: linux,dummy-virt (DT)
pstate: 40400805 (nZcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=-c)
pc : bpf_fentry_test1+0xc/0x30
lr : bpf_trampoline_6442573892_0+0x48/0x1000
sp : ffff80000c0c3a50
x29: ffff80000c0c3a90 x28: ffff0000c2e6c080 x27: 0000000000000000
x26: 0000000000000000 x25: 0000000000000000 x24: 0000000000000050
x23: 0000000000000000 x22: 0000ffffcfd2a7f0 x21: 000000000000000a
x20: 0000ffffcfd2a7f0 x19: 0000000000000000 x18: 0000000000000000
x17: 0000000000000000 x16: 0000000000000000 x15: 0000ffffcfd2a7f0
x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000000
x11: 0000000000000000 x10: ffff80000914f5e4 x9 : ffff8000082a1528
x8 : 0000000000000000 x7 : 0000000000000000 x6 : 0101010101010101
x5 : 0000000000000000 x4 : 00000000fffffff2 x3 : 0000000000000001
x2 : ffff8001f4b82000 x1 : 0000000000000000 x0 : 0000000000000001
Kernel panic - not syncing: Unhandled exception
CPU: 0 PID: 263 Comm: test_progs Tainted: GF
Hardware name: linux,dummy-virt (DT)
Call trace:
dump_backtrace+0xec/0x144
show_stack+0x24/0x7c
dump_stack_lvl+0x8c/0xb8
dump_stack+0x18/0x34
panic+0x1cc/0x3ec
__el0_error_handler_common+0x0/0x130
el1h_64_sync_handler+0x60/0xd0
el1h_64_sync+0x78/0x7c
bpf_fentry_test1+0xc/0x30
bpf_fentry_test1+0xc/0x30
bpf_prog_test_run_tracing+0xdc/0x2a0
__sys_bpf+0x438/0x22a0
__arm64_sys_bpf+0x30/0x54
invoke_syscall+0x78/0x110
el0_svc_common.constprop.0+0x6c/0x1d0
do_el0_svc+0x38/0xe0
el0_svc+0x30/0xd0
el0t_64_sync_handler+0x1ac/0x1b0
el0t_64_sync+0x1a0/0x1a4
Kernel Offset: disabled
CPU features: 0x0000,00034c24,f994fdab
Memory Limit: none
And the instruction next to call site of bpf_fentry_test1 is ADD,
not PACIASP:
<bpf_fentry_test1>:
bti c
nop
nop
add w0, w0, #0x1
paciasp
For BPF prog, JIT always puts a PACIASP after call site for BTI-enabled
kernel, so there is no problem. To fix it, replace BLR with RET to bypass
the branch target check.
Fixes: efc9909fdc ("bpf, arm64: Add bpf trampoline for arm64")
Reported-by: Florent Revest <revest@chromium.org>
Signed-off-by: Xu Kuohai <xukuohai@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Florent Revest <revest@chromium.org>
Acked-by: Florent Revest <revest@chromium.org>
Link: https://lore.kernel.org/bpf/20230401234144.3719742-1-xukuohai@huaweicloud.com
The commit 64696c40d0 ("bpf: Add __bpf_prog_{enter,exit}_struct_ops for struct_ops trampoline")
removed prog->active check for struct_ops prog. The bpf_lsm
and bpf_iter is also using trampoline. Like struct_ops, the bpf_lsm
and bpf_iter have fixed hooks for the prog to attach. The
kernel does not call the same hook in a recursive way.
This patch also removes the prog->active check for
bpf_lsm and bpf_iter.
A later patch has a test to reproduce the recursion issue
for a sleepable bpf_lsm program.
This patch appends the '_recur' naming to the existing
enter and exit functions that track the prog->active counter.
New __bpf_prog_{enter,exit}[_sleepable] function are
added to skip the prog->active tracking. The '_struct_ops'
version is also removed.
It also moves the decision on picking the enter and exit function to
the new bpf_trampoline_{enter,exit}(). It returns the '_recur' ones
for all tracing progs to use. For bpf_lsm, bpf_iter,
struct_ops (no prog->active tracking after 64696c40d0), and
bpf_lsm_cgroup (no prog->active tracking after 69fd337a97),
it will return the functions that don't track the prog->active.
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20221025184524.3526117-2-martin.lau@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
The sparse tool complains as follows:
arch/arm64/net/bpf_jit_comp.c:1684:16:
warning: incorrect type in assignment (different base types)
arch/arm64/net/bpf_jit_comp.c:1684:16:
expected unsigned int [usertype] *branch
arch/arm64/net/bpf_jit_comp.c:1684:16:
got restricted __le32 [usertype] *
arch/arm64/net/bpf_jit_comp.c:1700:52:
error: subtraction of different types can't work (different base
types)
arch/arm64/net/bpf_jit_comp.c:1734:29:
warning: incorrect type in assignment (different base types)
arch/arm64/net/bpf_jit_comp.c:1734:29:
expected unsigned int [usertype] *
arch/arm64/net/bpf_jit_comp.c:1734:29:
got restricted __le32 [usertype] *
arch/arm64/net/bpf_jit_comp.c:1918:52:
error: subtraction of different types can't work (different base
types)
This is because the variable branch in function invoke_bpf_prog and the
variable branches in function prepare_trampoline are defined as type
u32 *, which conflicts with ctx->image's type __le32 *, so sparse complains
when assignment or arithmetic operation are performed on these two
variables and ctx->image.
Since arm64 instructions are always little-endian, change the type of
these two variables to __le32 * and call cpu_to_le32() to convert
instruction to little-endian before writing it to memory. This is also
in line with emit() which internally does cpu_to_le32(), too.
Fixes: efc9909fdc ("bpf, arm64: Add bpf trampoline for arm64")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Xu Kuohai <xukuohai@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Link: https://lore.kernel.org/bpf/20220808040735.1232002-1-xukuohai@huawei.com
It is not necessary to allocate contiguous physical memory for BPF
program buffer using kcalloc. When the BPF program is large more than
memory page size, kcalloc allocates multiple memory pages from buddy
system. If the device can not provide sufficient memory, for example
in low-end android devices [0], memory allocation for BPF program is
likely to fail.
Test cases in lib/test_bpf.c all pass on ARM64 QEMU.
[0]
AndroidTestSuit: page allocation failure: order:4,
mode:0x40dc0(GFP_KERNEL|__GFP_COMP|__GFP_ZERO), nodemask=(null),cpuset=foreground,mems_allowed=0
Call trace:
dump_stack+0xa4/0x114
warn_alloc+0xf8/0x14c
__alloc_pages_slowpath+0xac8/0xb14
__alloc_pages_nodemask+0x194/0x3d0
kmalloc_order_trace+0x44/0x1e8
__kmalloc+0x29c/0x66c
bpf_int_jit_compile+0x17c/0x568
bpf_prog_select_runtime+0x4c/0x1b0
bpf_prepare_filter+0x5fc/0x6bc
bpf_prog_create_from_user+0x118/0x1c0
seccomp_set_mode_filter+0x1c4/0x7cc
__do_sys_prctl+0x380/0x1424
__arm64_sys_prctl+0x20/0x2c
el0_svc_common+0xc8/0x22c
el0_svc_handler+0x1c/0x28
el0_svc+0x8/0x100
Signed-off-by: Aijun Sun <aijun.sun@unisoc.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20220804025442.22524-1-aijun.sun@unisoc.com
dummy_tramp() uses "lr" to refer to the x30 register, but some assembler
does not recognize "lr" and reports a build failure:
/tmp/cc52xO0c.s: Assembler messages:
/tmp/cc52xO0c.s:8: Error: operand 1 should be an integer register -- `mov lr,x9'
/tmp/cc52xO0c.s:7: Error: undefined symbol lr used as an immediate value
make[2]: *** [scripts/Makefile.build:250: arch/arm64/net/bpf_jit_comp.o] Error 1
make[1]: *** [scripts/Makefile.build:525: arch/arm64/net] Error 2
So replace "lr" with "x30" to fix it.
Fixes: b2ad54e153 ("bpf, arm64: Implement bpf_arch_text_poke() for arm64")
Reported-by: Jon Hunter <jonathanh@nvidia.com>
Signed-off-by: Xu Kuohai <xukuohai@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Jon Hunter <jonathanh@nvidia.com>
Reviewed-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Link: https://lore.kernel.org/bpf/20220721121319.2999259-1-xukuohai@huaweicloud.com
When building with clang + CONFIG_CFI_CLANG=y, the following error
occurs at link time:
ld.lld: error: undefined symbol: dummy_tramp
dummy_tramp is declared globally in C but its definition in inline
assembly does not use .global, which prevents clang from properly
resolving the references to it when creating the CFI jump tables.
Mark dummy_tramp as global so that the reference can be properly
resolved.
Fixes: b2ad54e153 ("bpf, arm64: Implement bpf_arch_text_poke() for arm64")
Suggested-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Stanislav Fomichev <sdf@google.com>
Link: https://github.com/ClangBuiltLinux/linux/issues/1661
Link: https://lore.kernel.org/bpf/20220713173503.3889486-1-nathan@kernel.org
Implement bpf_arch_text_poke() for arm64, so bpf prog or bpf trampoline
can be patched with it.
When the target address is NULL, the original instruction is patched to
a NOP.
When the target address and the source address are within the branch
range, the original instruction is patched to a bl instruction to the
target address directly.
To support attaching bpf trampoline to both regular kernel function and
bpf prog, we follow the ftrace patchsite way for bpf prog. That is, two
instructions are inserted at the beginning of bpf prog, the first one
saves the return address to x9, and the second is a nop which will be
patched to a bl instruction when a bpf trampoline is attached.
However, when a bpf trampoline is attached to bpf prog, the distance
between target address and source address may exceed 128MB, the maximum
branch range, because bpf trampoline and bpf prog are allocated
separately with vmalloc. So long jump should be handled.
When a bpf prog is constructed, a plt pointing to empty trampoline
dummy_tramp is placed at the end:
bpf_prog:
mov x9, lr
nop // patchsite
...
ret
plt:
ldr x10, target
br x10
target:
.quad dummy_tramp // plt target
This is also the state when no trampoline is attached.
When a short-jump bpf trampoline is attached, the patchsite is patched to
a bl instruction to the trampoline directly:
bpf_prog:
mov x9, lr
bl <short-jump bpf trampoline address> // patchsite
...
ret
plt:
ldr x10, target
br x10
target:
.quad dummy_tramp // plt target
When a long-jump bpf trampoline is attached, the plt target is filled with
the trampoline address and the patchsite is patched to a bl instruction to
the plt:
bpf_prog:
mov x9, lr
bl plt // patchsite
...
ret
plt:
ldr x10, target
br x10
target:
.quad <long-jump bpf trampoline address>
dummy_tramp is used to prevent another CPU from jumping to an unknown
location during the patching process, making the patching process easier.
The patching process is as follows:
1. when neither the old address or the new address is a long jump, the
patchsite is replaced with a bl to the new address, or nop if the new
address is NULL;
2. when the old address is not long jump but the new one is, the
branch target address is written to plt first, then the patchsite
is replaced with a bl instruction to the plt;
3. when the old address is long jump but the new one is not, the address
of dummy_tramp is written to plt first, then the patchsite is replaced
with a bl to the new address, or a nop if the new address is NULL;
4. when both the old address and the new address are long jump, the
new address is written to plt and the patchsite is not changed.
Signed-off-by: Xu Kuohai <xukuohai@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Reviewed-by: KP Singh <kpsingh@kernel.org>
Reviewed-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20220711150823.2128542-4-xukuohai@huawei.com
syzbot reported an illegal copy_to_user() attempt
from bpf_prog_get_info_by_fd() [1]
There was no repro yet on this bug, but I think
that commit 0aef499f31 ("mm/usercopy: Detect vmalloc overruns")
is exposing a prior bug in bpf arm64.
bpf_prog_get_info_by_fd() looks at prog->jited_len
to determine if the JIT image can be copied out to user space.
My theory is that syzbot managed to get a prog where prog->jited_len
has been set to 43, while prog->bpf_func has ben cleared.
It is not clear why copy_to_user(uinsns, NULL, ulen) is triggering
this particular warning.
I thought find_vma_area(NULL) would not find a vm_struct.
As we do not hold vmap_area_lock spinlock, it might be possible
that the found vm_struct was garbage.
[1]
usercopy: Kernel memory exposure attempt detected from vmalloc (offset 792633534417210172, size 43)!
kernel BUG at mm/usercopy.c:101!
Internal error: Oops - BUG: 0 [#1] PREEMPT SMP
Modules linked in:
CPU: 0 PID: 25002 Comm: syz-executor.1 Not tainted 5.18.0-syzkaller-10139-g8291eaafed36 #0
Hardware name: linux,dummy-virt (DT)
pstate: 60400009 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : usercopy_abort+0x90/0x94 mm/usercopy.c:101
lr : usercopy_abort+0x90/0x94 mm/usercopy.c:89
sp : ffff80000b773a20
x29: ffff80000b773a30 x28: faff80000b745000 x27: ffff80000b773b48
x26: 0000000000000000 x25: 000000000000002b x24: 0000000000000000
x23: 00000000000000e0 x22: ffff80000b75db67 x21: 0000000000000001
x20: 000000000000002b x19: ffff80000b75db3c x18: 00000000fffffffd
x17: 2820636f6c6c616d x16: 76206d6f72662064 x15: 6574636574656420
x14: 74706d6574746120 x13: 2129333420657a69 x12: 73202c3237313031
x11: 3237313434333533 x10: 3336323937207465 x9 : 657275736f707865
x8 : ffff80000a30c550 x7 : ffff80000b773830 x6 : ffff80000b773830
x5 : 0000000000000000 x4 : ffff00007fbbaa10 x3 : 0000000000000000
x2 : 0000000000000000 x1 : f7ff000028fc0000 x0 : 0000000000000064
Call trace:
usercopy_abort+0x90/0x94 mm/usercopy.c:89
check_heap_object mm/usercopy.c:186 [inline]
__check_object_size mm/usercopy.c:252 [inline]
__check_object_size+0x198/0x36c mm/usercopy.c:214
check_object_size include/linux/thread_info.h:199 [inline]
check_copy_size include/linux/thread_info.h:235 [inline]
copy_to_user include/linux/uaccess.h:159 [inline]
bpf_prog_get_info_by_fd.isra.0+0xf14/0xfdc kernel/bpf/syscall.c:3993
bpf_obj_get_info_by_fd+0x12c/0x510 kernel/bpf/syscall.c:4253
__sys_bpf+0x900/0x2150 kernel/bpf/syscall.c:4956
__do_sys_bpf kernel/bpf/syscall.c:5021 [inline]
__se_sys_bpf kernel/bpf/syscall.c:5019 [inline]
__arm64_sys_bpf+0x28/0x40 kernel/bpf/syscall.c:5019
__invoke_syscall arch/arm64/kernel/syscall.c:38 [inline]
invoke_syscall+0x48/0x114 arch/arm64/kernel/syscall.c:52
el0_svc_common.constprop.0+0x44/0xec arch/arm64/kernel/syscall.c:142
do_el0_svc+0xa0/0xc0 arch/arm64/kernel/syscall.c:206
el0_svc+0x44/0xb0 arch/arm64/kernel/entry-common.c:624
el0t_64_sync_handler+0x1ac/0x1b0 arch/arm64/kernel/entry-common.c:642
el0t_64_sync+0x198/0x19c arch/arm64/kernel/entry.S:581
Code: aa0003e3 d00038c0 91248000 97fff65f (d4210000)
Fixes: db496944fd ("bpf: arm64: add JIT support for multi-function programs")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20220531215113.1100754-1-eric.dumazet@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Sign return address for JITed code when the kernel is built with pointer
authentication enabled:
1. Sign LR with paciasp instruction before LR is pushed to stack. Since
paciasp acts like landing pads for function entry, no need to insert
bti instruction before paciasp.
2. Authenticate LR with autiasp instruction after LR is popped from stack.
For BPF tail call, the stack frame constructed by the caller is reused by
the callee. That is, the stack frame is constructed by the caller and
destructed by the callee. Thus LR is signed and pushed to the stack in the
caller's prologue, and poped from the stack and authenticated in the
callee's epilogue.
For BPF2BPF call, the caller and callee construct their own stack frames,
and sign and authenticate their own LRs.
Signed-off-by: Xu Kuohai <xukuohai@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://events.static.linuxfound.org/sites/events/files/slides/slides_23.pdf
Link: https://lore.kernel.org/bpf/20220402073942.3782529-1-xukuohai@huawei.com
The current BPF store/load instruction is translated by the JIT into two
instructions. The first instruction moves the immediate offset into a
temporary register. The second instruction uses this temporary register
to do the real store/load.
In fact, arm64 supports addressing with immediate offsets. So This patch
introduces optimization that uses arm64 str/ldr instruction with immediate
offset when the offset fits.
Example of generated instuction for r2 = *(u64 *)(r1 + 0):
without optimization:
mov x10, 0
ldr x1, [x0, x10]
with optimization:
ldr x1, [x0, 0]
If the offset is negative, or is not aligned correctly, or exceeds max
value, rollback to the use of temporary register.
Signed-off-by: Xu Kuohai <xukuohai@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20220321152852.2334294-3-xukuohai@huawei.com
Besides asking vmalloc memory to be executable via the prot argument of
__vmalloc_node_range() (see the previous patch), the kernel can skip that
bit and instead mark memory as executable via set_memory_x().
Once tag-based KASAN modes start tagging vmalloc allocations, executing
code from such allocations will lead to the PC register getting a tag,
which is not tolerated by the kernel.
Generic kernel code typically allocates memory via module_alloc() if it
intends to mark memory as executable. (On arm64 module_alloc() uses
__vmalloc_node_range() without setting the executable bit).
Thus, reset pointer tags of pointers returned from module_alloc().
However, on arm64 there's an exception: the eBPF subsystem. Instead of
using module_alloc(), it uses vmalloc() (via bpf_jit_alloc_exec()) to
allocate its JIT region.
Thus, reset pointer tags of pointers returned from bpf_jit_alloc_exec().
Resetting tags for these pointers results in untagged pointers being
passed to set_memory_x(). This causes conflicts in arithmetic checks in
change_memory_common(), as vm_struct->addr pointer returned by
find_vm_area() is tagged.
Reset pointer tag of find_vm_area(addr)->addr in change_memory_common().
Link: https://lkml.kernel.org/r/b7b2595423340cd7d76b770e5d519acf3b72f0ab.1643047180.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Marco Elver <elver@google.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Collingbourne <pcc@google.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Atomics for eBPF patch series adds support for atomic[64]_fetch_add,
atomic[64]_[fetch_]{and,or,xor} and atomic[64]_{xchg|cmpxchg}, but it
only adds support for x86-64, so support these atomic operations for
arm64 as well.
Basically the implementation procedure is almost mechanical translation
of code snippets in atomic_ll_sc.h & atomic_lse.h & cmpxchg.h located
under arch/arm64/include/asm.
When LSE atomic is unavailable, an extra temporary register is needed for
(BPF_ADD | BPF_FETCH) to save the value of src register, instead of adding
TMP_REG_4 just use BPF_REG_AX instead. Also make emit_lse_atomic() as an
empty inline function when CONFIG_ARM64_LSE_ATOMICS is disabled.
For cpus_have_cap(ARM64_HAS_LSE_ATOMICS) case and no-LSE-ATOMICS case, the
following three tests: "./test_verifier", "./test_progs -t atomic" and
"insmod ./test_bpf.ko" are exercised and passed.
Signed-off-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20220217072232.1186625-4-houtao1@huawei.com
insn_to_jit_off passed to bpf_prog_fill_jited_linfo() is calculated in
instruction granularity instead of bytes granularity, but BPF line info
requires byte offset.
bpf_prog_fill_jited_linfo() will be the last user of ctx.offset before
it is freed, so convert the offset into byte-offset before calling into
bpf_prog_fill_jited_linfo() in order to fix the line info dump on arm64.
Fixes: 37ab566c17 ("bpf: arm64: Enable arm64 jit to provide bpf_line_info")
Suggested-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20220226121906.5709-3-houtao1@huawei.com
BPF line info needs ctx->offset to be the instruction offset in the whole JITed
image instead of the body itself, so also call build_prologue() first in first
JIT pass.
Fixes: 37ab566c17 ("bpf: arm64: Enable arm64 jit to provide bpf_line_info")
Signed-off-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20220226121906.5709-2-houtao1@huawei.com
Since commit b2eed9b588 ("arm64/kernel: kaslr: reduce module
randomization range to 2 GB"), for arm64 whether KASLR is enabled
or not, the module is placed within 2GB of the kernel region, so
s32 in bpf_kfunc_desc is sufficient to represente the offset of
module function relative to __bpf_call_base. The only thing needed
is to override bpf_jit_supports_kfunc_call().
Signed-off-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20220130092917.14544-2-hotforest@gmail.com
The following error is reported when running "./test_progs -t for_each"
under arm64:
bpf_jit: multi-func JIT bug 58 != 56
[...]
JIT doesn't support bpf-to-bpf calls
The root cause is the size of BPF_PSEUDO_FUNC instruction increases
from 2 to 3 after the address of called bpf-function is settled and
there are two bpf-to-bpf calls in test_pkt_access. The generated
instructions are shown below:
0x48: 21 00 C0 D2 movz x1, #0x1, lsl #32
0x4c: 21 00 80 F2 movk x1, #0x1
0x48: E1 3F C0 92 movn x1, #0x1ff, lsl #32
0x4c: 41 FE A2 F2 movk x1, #0x17f2, lsl #16
0x50: 81 70 9F F2 movk x1, #0xfb84
Fixing it by using emit_addr_mov_i64() for BPF_PSEUDO_FUNC, so
the size of jited image will not change.
Fixes: 69c087ba62 ("bpf: Add bpf_for_each_map_elem() helper")
Signed-off-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20211231151018.3781550-1-houtao1@huawei.com
The eBPF name has completely taken over from eBPF in general usage for
the actual eBPF representation, or BPF for any general in-kernel use.
Prune all remaining references to "internal BPF".
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20211119163215.971383-4-hch@lst.de
In the current code, the actual max tail call count is 33 which is greater
than MAX_TAIL_CALL_CNT (defined as 32). The actual limit is not consistent
with the meaning of MAX_TAIL_CALL_CNT and thus confusing at first glance.
We can see the historical evolution from commit 04fd61ab36 ("bpf: allow
bpf programs to tail-call other bpf programs") and commit f9dabe016b
("bpf: Undo off-by-one in interpreter tail call count limit"). In order
to avoid changing existing behavior, the actual limit is 33 now, this is
reasonable.
After commit 874be05f52 ("bpf, tests: Add tail call test suite"), we can
see there exists failed testcase.
On all archs when CONFIG_BPF_JIT_ALWAYS_ON is not set:
# echo 0 > /proc/sys/net/core/bpf_jit_enable
# modprobe test_bpf
# dmesg | grep -w FAIL
Tail call error path, max count reached jited:0 ret 34 != 33 FAIL
On some archs:
# echo 1 > /proc/sys/net/core/bpf_jit_enable
# modprobe test_bpf
# dmesg | grep -w FAIL
Tail call error path, max count reached jited:1 ret 34 != 33 FAIL
Although the above failed testcase has been fixed in commit 18935a72eb
("bpf/tests: Fix error in tail call limit tests"), it would still be good
to change the value of MAX_TAIL_CALL_CNT from 32 to 33 to make the code
more readable.
The 32-bit x86 JIT was using a limit of 32, just fix the wrong comments and
limit to 33 tail calls as the constant MAX_TAIL_CALL_CNT updated. For the
mips64 JIT, use "ori" instead of "addiu" as suggested by Johan Almbladh.
For the riscv JIT, use RV_REG_TCC directly to save one register move as
suggested by Björn Töpel. For the other implementations, no function changes,
it does not change the current limit 33, the new value of MAX_TAIL_CALL_CNT
can reflect the actual max tail call count, the related tail call testcases
in test_bpf module and selftests can work well for the interpreter and the
JIT.
Here are the test results on x86_64:
# uname -m
x86_64
# echo 0 > /proc/sys/net/core/bpf_jit_enable
# modprobe test_bpf test_suite=test_tail_calls
# dmesg | tail -1
test_bpf: test_tail_calls: Summary: 8 PASSED, 0 FAILED, [0/8 JIT'ed]
# rmmod test_bpf
# echo 1 > /proc/sys/net/core/bpf_jit_enable
# modprobe test_bpf test_suite=test_tail_calls
# dmesg | tail -1
test_bpf: test_tail_calls: Summary: 8 PASSED, 0 FAILED, [8/8 JIT'ed]
# rmmod test_bpf
# ./test_progs -t tailcalls
#142 tailcalls:OK
Summary: 1/11 PASSED, 0 SKIPPED, 0 FAILED
Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Johan Almbladh <johan.almbladh@anyfinetworks.com>
Tested-by: Ilya Leoshkevich <iii@linux.ibm.com>
Acked-by: Björn Töpel <bjorn@kernel.org>
Acked-by: Johan Almbladh <johan.almbladh@anyfinetworks.com>
Acked-by: Ilya Leoshkevich <iii@linux.ibm.com>
Link: https://lore.kernel.org/bpf/1636075800-3264-1-git-send-email-yangtiezhu@loongson.cn
Commit 91fc957c9b ("arm64/bpf: don't allocate BPF JIT programs in module
memory") restricts BPF JIT program allocation to a 128MB region to ensure
BPF programs are still in branching range of each other. However this
restriction should not apply to the aarch64 JIT, since BPF_JMP | BPF_CALL
are implemented as a 64-bit move into a register and then a BLR instruction -
which has the effect of being able to call anything without proximity
limitation.
The practical reason to relax this restriction on JIT memory is that 128MB of
JIT memory can be quickly exhausted, especially where PAGE_SIZE is 64KB - one
page is needed per program. In cases where seccomp filters are applied to
multiple VMs on VM launch - such filters are classic BPF but converted to
BPF - this can severely limit the number of VMs that can be launched. In a
world where we support BPF JIT always on, turning off the JIT isn't always an
option either.
Fixes: 91fc957c9b ("arm64/bpf: don't allocate BPF JIT programs in module memory")
Suggested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Russell King <russell.king@oracle.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Alan Maguire <alan.maguire@oracle.com>
Link: https://lore.kernel.org/bpf/1636131046-5982-2-git-send-email-alan.maguire@oracle.com
- Support for the Arm8.6 timer extensions, including a self-synchronising
view of the system registers to elide some expensive ISB instructions.
- Exception table cleanup and rework so that the fixup handlers appear
correctly in backtraces.
- A handful of miscellaneous changes, the main one being selection of
CONFIG_HAVE_POSIX_CPU_TIMERS_TASK_WORK.
- More mm and pgtable cleanups.
- KASAN support for "asymmetric" MTE, where tag faults are reported
synchronously for loads (via an exception) and asynchronously for
stores (via a register).
- Support for leaving the MMU enabled during kexec relocation, which
significantly speeds up the operation.
- Minor improvements to our perf PMU drivers.
- Improvements to the compat vDSO build system, particularly when
building with LLVM=1.
- Preparatory work for handling some Coresight TRBE tracing errata.
- Cleanup and refactoring of the SVE code to pave the way for SME
support in future.
- Ensure SCS pages are unpoisoned immediately prior to freeing them
when KASAN is enabled for the vmalloc area.
- Try moving to the generic pfn_valid() implementation again now that
the DMA mapping issue from last time has been resolved.
- Numerous improvements and additions to our FPSIMD and SVE selftests.
-----BEGIN PGP SIGNATURE-----
iQFDBAABCgAuFiEEPxTL6PPUbjXGY88ct6xw3ITBYzQFAmF74ZYQHHdpbGxAa2Vy
bmVsLm9yZwAKCRC3rHDchMFjNI/eB/UZYAtmNi6xC5StPaETyMLeZph9BV/IqIFq
N71ds7MFzlX/agR6MwLbH2tBHezBtlQ90O732Jjz8zAec2cHd+7sx/w82JesX7PB
IuOfqP78rvtU4ZkKe1Rcd96QtYvbtNAqcRhIo95OzfV9xwuzkvdXI+ZTYhtCfCuZ
GozCqQoJtnNDayMtfzbDSXyJLNJc/qnIcUQhrt3vg12zbF3BcHxnmp0nBcHCqZEo
lDJYufju7p87kCzaFYda2WhlI3t+NThqKOiZ332wQfqzNcr+rw1Y4jWbnCfrdLtI
JfHT9yiuHDmFSYaJrk7NU8kftW31NV70bbhD7rZ+DQCVndl0lRc=
=3R3j
-----END PGP SIGNATURE-----
Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux
Pull arm64 updates from Will Deacon:
"There's the usual summary below, but the highlights are support for
the Armv8.6 timer extensions, KASAN support for asymmetric MTE, the
ability to kexec() with the MMU enabled and a second attempt at
switching to the generic pfn_valid() implementation.
Summary:
- Support for the Arm8.6 timer extensions, including a
self-synchronising view of the system registers to elide some
expensive ISB instructions.
- Exception table cleanup and rework so that the fixup handlers
appear correctly in backtraces.
- A handful of miscellaneous changes, the main one being selection of
CONFIG_HAVE_POSIX_CPU_TIMERS_TASK_WORK.
- More mm and pgtable cleanups.
- KASAN support for "asymmetric" MTE, where tag faults are reported
synchronously for loads (via an exception) and asynchronously for
stores (via a register).
- Support for leaving the MMU enabled during kexec relocation, which
significantly speeds up the operation.
- Minor improvements to our perf PMU drivers.
- Improvements to the compat vDSO build system, particularly when
building with LLVM=1.
- Preparatory work for handling some Coresight TRBE tracing errata.
- Cleanup and refactoring of the SVE code to pave the way for SME
support in future.
- Ensure SCS pages are unpoisoned immediately prior to freeing them
when KASAN is enabled for the vmalloc area.
- Try moving to the generic pfn_valid() implementation again now that
the DMA mapping issue from last time has been resolved.
- Numerous improvements and additions to our FPSIMD and SVE
selftests"
[ armv8.6 timer updates were in a shared branch and already came in
through -tip in the timer pull - Linus ]
* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (85 commits)
arm64: Select POSIX_CPU_TIMERS_TASK_WORK
arm64: Document boot requirements for FEAT_SME_FA64
arm64/sve: Fix warnings when SVE is disabled
arm64/sve: Add stub for sve_max_virtualisable_vl()
arm64: errata: Add detection for TRBE write to out-of-range
arm64: errata: Add workaround for TSB flush failures
arm64: errata: Add detection for TRBE overwrite in FILL mode
arm64: Add Neoverse-N2, Cortex-A710 CPU part definition
selftests: arm64: Factor out utility functions for assembly FP tests
arm64: vmlinux.lds.S: remove `.fixup` section
arm64: extable: add load_unaligned_zeropad() handler
arm64: extable: add a dedicated uaccess handler
arm64: extable: add `type` and `data` fields
arm64: extable: use `ex` for `exception_table_entry`
arm64: extable: make fixup_exception() return bool
arm64: extable: consolidate definitions
arm64: gpr-num: support W registers
arm64: factor out GPR numbering helpers
arm64: kvm: use kvm_exception_table_entry
arm64: lib: __arch_copy_to_user(): fold fixups into body
...
Subsequent patches will add specialized handlers for fixups, in addition
to the simple PC fixup and BPF handlers we have today. In preparation,
this patch adds a new `type` field to struct exception_table_entry, and
uses this to distinguish the fixup and BPF cases. A `data` field is also
added so that subsequent patches can associate data specific to each
exception site (e.g. register numbers).
Handlers are named ex_handler_*() for consistency, following the exmaple
of x86. At the same time, get_ex_fixup() is split out into a helper so
that it can be used by other ex_handler_*() functions ins subsequent
patches.
This patch will increase the size of the exception tables, which will be
remedied by subsequent patches removing redundant fixup code. There
should be no functional change as a result of this patch.
Since each entry is now 12 bytes in size, we must reduce the alignment
of each entry from `.align 3` (i.e. 8 bytes) to `.align 2` (i.e. 4
bytes), which is the natrual alignment of the `insn` and `fixup` fields.
The current 8-byte alignment is a holdover from when the `insn` and
`fixup` fields was 8 bytes, and while not harmful has not been necessary
since commit:
6c94f27ac8 ("arm64: switch to relative exception tables")
Similarly, RO_EXCEPTION_TABLE_ALIGN is dropped to 4 bytes.
Concurrently with this patch, x86's exception table entry format is
being updated (similarly to a 12-byte format, with 32-bytes of absolute
data). Once both have been merged it should be possible to unify the
sorttable logic for the two.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: James Morse <james.morse@arm.com>
Cc: Jean-Philippe Brucker <jean-philippe@linaro.org>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20211019160219.5202-11-mark.rutland@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
The return values of fixup_exception() and arm64_bpf_fixup_exception()
represent a boolean condition rather than an error code, so for clarity
it would be better to return `bool` rather than `int`.
This patch adjusts the code accordingly. While we're modifying the
prototype, we also remove the unnecessary `extern` keyword, so that this
won't look out of place when we make subsequent additions to the header.
There should be no functional change as a result of this patch.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: James Morse <james.morse@arm.com>
Cc: Jean-Philippe Brucker <jean-philippe@linaro.org>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20211019160219.5202-9-mark.rutland@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
In case of JITs, each of the JIT backends compiles the BPF nospec instruction
/either/ to a machine instruction which emits a speculation barrier /or/ to
/no/ machine instruction in case the underlying architecture is not affected
by Speculative Store Bypass or has different mitigations in place already.
This covers both x86 and (implicitly) arm64: In case of x86, we use 'lfence'
instruction for mitigation. In case of arm64, we rely on the firmware mitigation
as controlled via the ssbd kernel parameter. Whenever the mitigation is enabled,
it works for all of the kernel code with no need to provide any additional
instructions here (hence only comment in arm64 JIT). Other archs can follow
as needed. The BPF nospec instruction is specifically targeting Spectre v4
since i) we don't use a serialization barrier for the Spectre v1 case, and
ii) mitigation instructions for v1 and v4 might be different on some archs.
The BPF nospec is required for a future commit, where the BPF verifier does
annotate intermediate BPF programs with speculation barriers.
Co-developed-by: Piotr Krysiuk <piotras@gmail.com>
Co-developed-by: Benedict Schlueter <benedict.schlueter@rub.de>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Piotr Krysiuk <piotras@gmail.com>
Signed-off-by: Benedict Schlueter <benedict.schlueter@rub.de>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Core:
- BPF:
- add syscall program type and libbpf support for generating
instructions and bindings for in-kernel BPF loaders (BPF loaders
for BPF), this is a stepping stone for signed BPF programs
- infrastructure to migrate TCP child sockets from one listener
to another in the same reuseport group/map to improve flexibility
of service hand-off/restart
- add broadcast support to XDP redirect
- allow bypass of the lockless qdisc to improving performance
(for pktgen: +23% with one thread, +44% with 2 threads)
- add a simpler version of "DO_ONCE()" which does not require
jump labels, intended for slow-path usage
- virtio/vsock: introduce SOCK_SEQPACKET support
- add getsocketopt to retrieve netns cookie
- ip: treat lowest address of a IPv4 subnet as ordinary unicast address
allowing reclaiming of precious IPv4 addresses
- ipv6: use prandom_u32() for ID generation
- ip: add support for more flexible field selection for hashing
across multi-path routes (w/ offload to mlxsw)
- icmp: add support for extended RFC 8335 PROBE (ping)
- seg6: add support for SRv6 End.DT46 behavior
- mptcp:
- DSS checksum support (RFC 8684) to detect middlebox meddling
- support Connection-time 'C' flag
- time stamping support
- sctp: packetization Layer Path MTU Discovery (RFC 8899)
- xfrm: speed up state addition with seq set
- WiFi:
- hidden AP discovery on 6 GHz and other HE 6 GHz improvements
- aggregation handling improvements for some drivers
- minstrel improvements for no-ack frames
- deferred rate control for TXQs to improve reaction times
- switch from round robin to virtual time-based airtime scheduler
- add trace points:
- tcp checksum errors
- openvswitch - action execution, upcalls
- socket errors via sk_error_report
Device APIs:
- devlink: add rate API for hierarchical control of max egress rate
of virtual devices (VFs, SFs etc.)
- don't require RCU read lock to be held around BPF hooks
in NAPI context
- page_pool: generic buffer recycling
New hardware/drivers:
- mobile:
- iosm: PCIe Driver for Intel M.2 Modem
- support for Qualcomm MSM8998 (ipa)
- WiFi: Qualcomm QCN9074 and WCN6855 PCI devices
- sparx5: Microchip SparX-5 family of Enterprise Ethernet switches
- Mellanox BlueField Gigabit Ethernet (control NIC of the DPU)
- NXP SJA1110 Automotive Ethernet 10-port switch
- Qualcomm QCA8327 switch support (qca8k)
- Mikrotik 10/25G NIC (atl1c)
Driver changes:
- ACPI support for some MDIO, MAC and PHY devices from Marvell and NXP
(our first foray into MAC/PHY description via ACPI)
- HW timestamping (PTP) support: bnxt_en, ice, sja1105, hns3, tja11xx
- Mellanox/Nvidia NIC (mlx5)
- NIC VF offload of L2 bridging
- support IRQ distribution to Sub-functions
- Marvell (prestera):
- add flower and match all
- devlink trap
- link aggregation
- Netronome (nfp): connection tracking offload
- Intel 1GE (igc): add AF_XDP support
- Marvell DPU (octeontx2): ingress ratelimit offload
- Google vNIC (gve): new ring/descriptor format support
- Qualcomm mobile (rmnet & ipa): inline checksum offload support
- MediaTek WiFi (mt76)
- mt7915 MSI support
- mt7915 Tx status reporting
- mt7915 thermal sensors support
- mt7921 decapsulation offload
- mt7921 enable runtime pm and deep sleep
- Realtek WiFi (rtw88)
- beacon filter support
- Tx antenna path diversity support
- firmware crash information via devcoredump
- Qualcomm 60GHz WiFi (wcn36xx)
- Wake-on-WLAN support with magic packets and GTK rekeying
- Micrel PHY (ksz886x/ksz8081): add cable test support
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
-----BEGIN PGP SIGNATURE-----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=LvtX
-----END PGP SIGNATURE-----
Merge tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski:
"Core:
- BPF:
- add syscall program type and libbpf support for generating
instructions and bindings for in-kernel BPF loaders (BPF loaders
for BPF), this is a stepping stone for signed BPF programs
- infrastructure to migrate TCP child sockets from one listener to
another in the same reuseport group/map to improve flexibility
of service hand-off/restart
- add broadcast support to XDP redirect
- allow bypass of the lockless qdisc to improving performance (for
pktgen: +23% with one thread, +44% with 2 threads)
- add a simpler version of "DO_ONCE()" which does not require jump
labels, intended for slow-path usage
- virtio/vsock: introduce SOCK_SEQPACKET support
- add getsocketopt to retrieve netns cookie
- ip: treat lowest address of a IPv4 subnet as ordinary unicast
address allowing reclaiming of precious IPv4 addresses
- ipv6: use prandom_u32() for ID generation
- ip: add support for more flexible field selection for hashing
across multi-path routes (w/ offload to mlxsw)
- icmp: add support for extended RFC 8335 PROBE (ping)
- seg6: add support for SRv6 End.DT46 behavior
- mptcp:
- DSS checksum support (RFC 8684) to detect middlebox meddling
- support Connection-time 'C' flag
- time stamping support
- sctp: packetization Layer Path MTU Discovery (RFC 8899)
- xfrm: speed up state addition with seq set
- WiFi:
- hidden AP discovery on 6 GHz and other HE 6 GHz improvements
- aggregation handling improvements for some drivers
- minstrel improvements for no-ack frames
- deferred rate control for TXQs to improve reaction times
- switch from round robin to virtual time-based airtime scheduler
- add trace points:
- tcp checksum errors
- openvswitch - action execution, upcalls
- socket errors via sk_error_report
Device APIs:
- devlink: add rate API for hierarchical control of max egress rate
of virtual devices (VFs, SFs etc.)
- don't require RCU read lock to be held around BPF hooks in NAPI
context
- page_pool: generic buffer recycling
New hardware/drivers:
- mobile:
- iosm: PCIe Driver for Intel M.2 Modem
- support for Qualcomm MSM8998 (ipa)
- WiFi: Qualcomm QCN9074 and WCN6855 PCI devices
- sparx5: Microchip SparX-5 family of Enterprise Ethernet switches
- Mellanox BlueField Gigabit Ethernet (control NIC of the DPU)
- NXP SJA1110 Automotive Ethernet 10-port switch
- Qualcomm QCA8327 switch support (qca8k)
- Mikrotik 10/25G NIC (atl1c)
Driver changes:
- ACPI support for some MDIO, MAC and PHY devices from Marvell and
NXP (our first foray into MAC/PHY description via ACPI)
- HW timestamping (PTP) support: bnxt_en, ice, sja1105, hns3, tja11xx
- Mellanox/Nvidia NIC (mlx5)
- NIC VF offload of L2 bridging
- support IRQ distribution to Sub-functions
- Marvell (prestera):
- add flower and match all
- devlink trap
- link aggregation
- Netronome (nfp): connection tracking offload
- Intel 1GE (igc): add AF_XDP support
- Marvell DPU (octeontx2): ingress ratelimit offload
- Google vNIC (gve): new ring/descriptor format support
- Qualcomm mobile (rmnet & ipa): inline checksum offload support
- MediaTek WiFi (mt76)
- mt7915 MSI support
- mt7915 Tx status reporting
- mt7915 thermal sensors support
- mt7921 decapsulation offload
- mt7921 enable runtime pm and deep sleep
- Realtek WiFi (rtw88)
- beacon filter support
- Tx antenna path diversity support
- firmware crash information via devcoredump
- Qualcomm WiFi (wcn36xx)
- Wake-on-WLAN support with magic packets and GTK rekeying
- Micrel PHY (ksz886x/ksz8081): add cable test support"
* tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2168 commits)
tcp: change ICSK_CA_PRIV_SIZE definition
tcp_yeah: check struct yeah size at compile time
gve: DQO: Fix off by one in gve_rx_dqo()
stmmac: intel: set PCI_D3hot in suspend
stmmac: intel: Enable PHY WOL option in EHL
net: stmmac: option to enable PHY WOL with PMT enabled
net: say "local" instead of "static" addresses in ndo_dflt_fdb_{add,del}
net: use netdev_info in ndo_dflt_fdb_{add,del}
ptp: Set lookup cookie when creating a PTP PPS source.
net: sock: add trace for socket errors
net: sock: introduce sk_error_report
net: dsa: replay the local bridge FDB entries pointing to the bridge dev too
net: dsa: ensure during dsa_fdb_offload_notify that dev_hold and dev_put are on the same dev
net: dsa: include fdb entries pointing to bridge in the host fdb list
net: dsa: include bridge addresses which are local in the host fdb list
net: dsa: sync static FDB entries on foreign interfaces to hardware
net: dsa: install the host MDB and FDB entries in the master's RX filter
net: dsa: reference count the FDB addresses at the cross-chip notifier level
net: dsa: introduce a separate cross-chip notifier type for host FDBs
net: dsa: reference count the MDB entries at the cross-chip notifier level
...
For histroical reasons, we define AARCH64_INSN_SIZE in
<asm/alternative-macros.h>, but it would make more sense to do so in
<asm/insn.h>. Let's move it into <asm/insn.h>, and add the necessary
include directives for this.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20210609102301.17332-3-mark.rutland@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
After commit 96a71005bd ("bpf, arm64: remove obsolete exception handling
from div/mod"), there is no need to check twice about BPF_DIV and BPF_MOD,
remove the redundant switch case.
Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/1621328170-17583-1-git-send-email-yangtiezhu@loongson.cn
Use the common function round_up() directly to show the align size
explicitly, the function STACK_ALIGN() is needless, remove it. Other
JITs also just rely on round_up().
Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/1620651119-5663-1-git-send-email-yangtiezhu@loongson.cn
A subsequent patch will add additional atomic operations. These new
operations will use the same opcode field as the existing XADD, with
the immediate discriminating different operations.
In preparation, rename the instruction mode BPF_ATOMIC and start
calling the zero immediate BPF_ADD.
This is possible (doesn't break existing valid BPF progs) because the
immediate field is currently reserved MBZ and BPF_ADD is zero.
All uses are removed from the tree but the BPF_XADD definition is
kept around to avoid breaking builds for people including kernel
headers.
Signed-off-by: Brendan Jackman <jackmanb@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Björn Töpel <bjorn.topel@gmail.com>
Link: https://lore.kernel.org/bpf/20210114181751.768687-5-jackmanb@google.com
Running the eBPF test_verifier leads to random errors looking like this:
[ 6525.735488] Unexpected kernel BRK exception at EL1
[ 6525.735502] Internal error: ptrace BRK handler: f2000100 [#1] SMP
[ 6525.741609] Modules linked in: nls_utf8 cifs libdes libarc4 dns_resolver fscache binfmt_misc nls_ascii nls_cp437 vfat fat aes_ce_blk crypto_simd cryptd aes_ce_cipher ghash_ce gf128mul efi_pstore sha2_ce sha256_arm64 sha1_ce evdev efivars efivarfs ip_tables x_tables autofs4 btrfs blake2b_generic xor xor_neon zstd_compress raid6_pq libcrc32c crc32c_generic ahci xhci_pci libahci xhci_hcd igb libata i2c_algo_bit nvme realtek usbcore nvme_core scsi_mod t10_pi netsec mdio_devres of_mdio gpio_keys fixed_phy libphy gpio_mb86s7x
[ 6525.787760] CPU: 3 PID: 7881 Comm: test_verifier Tainted: G W 5.9.0-rc1+ #47
[ 6525.796111] Hardware name: Socionext SynQuacer E-series DeveloperBox, BIOS build #1 Jun 6 2020
[ 6525.804812] pstate: 20000005 (nzCv daif -PAN -UAO BTYPE=--)
[ 6525.810390] pc : bpf_prog_c3d01833289b6311_F+0xc8/0x9f4
[ 6525.815613] lr : bpf_prog_d53bb52e3f4483f9_F+0x38/0xc8c
[ 6525.820832] sp : ffff8000130cbb80
[ 6525.824141] x29: ffff8000130cbbb0 x28: 0000000000000000
[ 6525.829451] x27: 000005ef6fcbf39b x26: 0000000000000000
[ 6525.834759] x25: ffff8000130cbb80 x24: ffff800011dc7038
[ 6525.840067] x23: ffff8000130cbd00 x22: ffff0008f624d080
[ 6525.845375] x21: 0000000000000001 x20: ffff800011dc7000
[ 6525.850682] x19: 0000000000000000 x18: 0000000000000000
[ 6525.855990] x17: 0000000000000000 x16: 0000000000000000
[ 6525.861298] x15: 0000000000000000 x14: 0000000000000000
[ 6525.866606] x13: 0000000000000000 x12: 0000000000000000
[ 6525.871913] x11: 0000000000000001 x10: ffff8000000a660c
[ 6525.877220] x9 : ffff800010951810 x8 : ffff8000130cbc38
[ 6525.882528] x7 : 0000000000000000 x6 : 0000009864cfa881
[ 6525.887836] x5 : 00ffffffffffffff x4 : 002880ba1a0b3e9f
[ 6525.893144] x3 : 0000000000000018 x2 : ffff8000000a4374
[ 6525.898452] x1 : 000000000000000a x0 : 0000000000000009
[ 6525.903760] Call trace:
[ 6525.906202] bpf_prog_c3d01833289b6311_F+0xc8/0x9f4
[ 6525.911076] bpf_prog_d53bb52e3f4483f9_F+0x38/0xc8c
[ 6525.915957] bpf_dispatcher_xdp_func+0x14/0x20
[ 6525.920398] bpf_test_run+0x70/0x1b0
[ 6525.923969] bpf_prog_test_run_xdp+0xec/0x190
[ 6525.928326] __do_sys_bpf+0xc88/0x1b28
[ 6525.932072] __arm64_sys_bpf+0x24/0x30
[ 6525.935820] el0_svc_common.constprop.0+0x70/0x168
[ 6525.940607] do_el0_svc+0x28/0x88
[ 6525.943920] el0_sync_handler+0x88/0x190
[ 6525.947838] el0_sync+0x140/0x180
[ 6525.951154] Code: d4202000 d4202000 d4202000 d4202000 (d4202000)
[ 6525.957249] ---[ end trace cecc3f93b14927e2 ]---
The reason is the offset[] creation and later usage, while building
the eBPF body. The code currently omits the first instruction, since
build_insn() will increase our ctx->idx before saving it.
That was fine up until bounded eBPF loops were introduced. After that
introduction, offset[0] must be the offset of the end of prologue which
is the start of the 1st insn while, offset[n] holds the
offset of the end of n-th insn.
When "taken loop with back jump to 1st insn" test runs, it will
eventually call bpf2a64_offset(-1, 2, ctx). Since negative indexing is
permitted, the current outcome depends on the value stored in
ctx->offset[-1], which has nothing to do with our array.
If the value happens to be 0 the tests will work. If not this error
triggers.
commit 7c2e988f40 ("bpf: fix x64 JIT code generation for jmp to 1st insn")
fixed an indentical bug on x86 when eBPF bounded loops were introduced.
So let's fix it by creating the ctx->offset[] differently. Track the
beginning of instruction and account for the extra instruction while
calculating the arm instruction offsets.
Fixes: 2589726d12 ("bpf: introduce bounded loops")
Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Reported-by: Jiri Olsa <jolsa@kernel.org>
Co-developed-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Co-developed-by: Yauheni Kaliuta <yauheni.kaliuta@redhat.com>
Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Signed-off-by: Yauheni Kaliuta <yauheni.kaliuta@redhat.com>
Signed-off-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Acked-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20200917084925.177348-1-ilias.apalodimas@linaro.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
When a tracing BPF program attempts to read memory without using the
bpf_probe_read() helper, the verifier marks the load instruction with
the BPF_PROBE_MEM flag. Since the arm64 JIT does not currently recognize
this flag it falls back to the interpreter.
Add support for BPF_PROBE_MEM, by appending an exception table to the
BPF program. If the load instruction causes a data abort, the fixup
infrastructure finds the exception table and fixes up the fault, by
clearing the destination register and jumping over the faulting
instruction.
To keep the compact exception table entry format, inspect the pc in
fixup_exception(). A more generic solution would add a "handler" field
to the table entry, like on x86 and s390.
Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20200728152122.1292756-2-jean-philippe@linaro.org
Puranjay Mohan