This is a note to let you know that I've just added the patch titled bpf, arm64: fix stack_depth tracking in combination with tail calls to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary The filename of the patch is: bpf-arm64-fix-stack_depth-tracking-in-combination-with-tail-calls.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable@xxxxxxxxxxxxxxx> know about it. >From foo@baz Mon Jan 29 13:14:09 CET 2018 From: Daniel Borkmann <daniel@xxxxxxxxxxxxx> Date: Mon, 29 Jan 2018 00:36:47 +0100 Subject: bpf, arm64: fix stack_depth tracking in combination with tail calls To: gregkh@xxxxxxxxxxxxxxxxxxx Cc: ast@xxxxxxxxxx, stable@xxxxxxxxxxxxxxx, Daniel Borkmann <daniel@xxxxxxxxxxxxx> Message-ID: <20180128233647.21154-7-daniel@xxxxxxxxxxxxx> From: Daniel Borkmann <daniel@xxxxxxxxxxxxx> [ upstream commit a2284d912bfc865cdca4c00488e08a3550f9a405 ] Using dynamic stack_depth tracking in arm64 JIT is currently broken in combination with tail calls. In prologue, we cache ctx->stack_size and adjust SP reg for setting up function call stack, and tearing it down again in epilogue. Problem is that when doing a tail call, the cached ctx->stack_size might not be the same. One way to fix the problem with minimal overhead is to re-adjust SP in emit_bpf_tail_call() and properly adjust it to the current program's ctx->stack_size. Tested on Cavium ThunderX ARMv8. Fixes: f1c9eed7f437 ("bpf, arm64: take advantage of stack_depth tracking") Signed-off-by: Daniel Borkmann <daniel@xxxxxxxxxxxxx> Signed-off-by: Alexei Starovoitov <ast@xxxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- arch/arm64/net/bpf_jit_comp.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -148,7 +148,8 @@ static inline int epilogue_offset(const /* Stack must be multiples of 16B */ #define STACK_ALIGN(sz) (((sz) + 15) & ~15) -#define PROLOGUE_OFFSET 8 +/* Tail call offset to jump into */ +#define PROLOGUE_OFFSET 7 static int build_prologue(struct jit_ctx *ctx) { @@ -200,19 +201,19 @@ static int build_prologue(struct jit_ctx /* Initialize tail_call_cnt */ emit(A64_MOVZ(1, tcc, 0, 0), ctx); - /* 4 byte extra for skb_copy_bits buffer */ - ctx->stack_size = prog->aux->stack_depth + 4; - ctx->stack_size = STACK_ALIGN(ctx->stack_size); - - /* Set up function call stack */ - emit(A64_SUB_I(1, A64_SP, A64_SP, ctx->stack_size), ctx); - cur_offset = ctx->idx - idx0; if (cur_offset != PROLOGUE_OFFSET) { pr_err_once("PROLOGUE_OFFSET = %d, expected %d!\n", cur_offset, PROLOGUE_OFFSET); return -1; } + + /* 4 byte extra for skb_copy_bits buffer */ + ctx->stack_size = prog->aux->stack_depth + 4; + ctx->stack_size = STACK_ALIGN(ctx->stack_size); + + /* Set up function call stack */ + emit(A64_SUB_I(1, A64_SP, A64_SP, ctx->stack_size), ctx); return 0; } @@ -260,11 +261,12 @@ static int emit_bpf_tail_call(struct jit emit(A64_LDR64(prg, tmp, prg), ctx); emit(A64_CBZ(1, prg, jmp_offset), ctx); - /* goto *(prog->bpf_func + prologue_size); */ + /* goto *(prog->bpf_func + prologue_offset); */ off = offsetof(struct bpf_prog, bpf_func); emit_a64_mov_i64(tmp, off, ctx); emit(A64_LDR64(tmp, prg, tmp), ctx); emit(A64_ADD_I(1, tmp, tmp, sizeof(u32) * PROLOGUE_OFFSET), ctx); + emit(A64_ADD_I(1, A64_SP, A64_SP, ctx->stack_size), ctx); emit(A64_BR(tmp), ctx); /* out: */ Patches currently in stable-queue which might be from daniel@xxxxxxxxxxxxx are queue-4.14/bpf-avoid-false-sharing-of-map-refcount-with-max_entries.patch queue-4.14/bpf-reject-stores-into-ctx-via-st-and-xadd.patch queue-4.14/bpf-fix-32-bit-divide-by-zero.patch queue-4.14/bpf-fix-divides-by-zero.patch queue-4.14/bpf-arm64-fix-stack_depth-tracking-in-combination-with-tail-calls.patch queue-4.14/bpf-introduce-bpf_jit_always_on-config.patch