summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorJoan Bruguera Micó <joanbrugueram@gmail.com>2024-04-01 20:55:30 +0200
committerAlexei Starovoitov <ast@kernel.org>2024-04-02 05:37:56 +0200
commit6a537453000a916392fcac1acb96c1d9d1e05b74 (patch)
tree69ebdb5ddaa504511a9b2f1e327246b1591ba08e
parentx86/bpf: Fix IP after emitting call depth accounting (diff)
downloadlinux-6a537453000a916392fcac1acb96c1d9d1e05b74.tar.xz
linux-6a537453000a916392fcac1acb96c1d9d1e05b74.zip
x86/bpf: Fix IP for relocating call depth accounting
The commit: 59bec00ace28 ("x86/percpu: Introduce %rip-relative addressing to PER_CPU_VAR()") made PER_CPU_VAR() to use rip-relative addressing, hence INCREMENT_CALL_DEPTH macro and skl_call_thunk_template got rip-relative asm code inside of it. A follow up commit: 17bce3b2ae2d ("x86/callthunks: Handle %rip-relative relocations in call thunk template") changed x86_call_depth_emit_accounting() to use apply_relocation(), but mistakenly assumed that the code is being patched in-place (where the destination of the relocation matches the address of the code), using *pprog as the destination ip. This is not true for the call depth accounting, emitted by the BPF JIT, so the calculated address was wrong, JIT-ed BPF progs on kernels with call depth tracking got broken and usually caused a page fault. Pass the destination IP when the BPF JIT emits call depth accounting. Fixes: 17bce3b2ae2d ("x86/callthunks: Handle %rip-relative relocations in call thunk template") Signed-off-by: Joan Bruguera Micó <joanbrugueram@gmail.com> Reviewed-by: Uros Bizjak <ubizjak@gmail.com> Acked-by: Ingo Molnar <mingo@kernel.org> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/r/20240401185821.224068-3-ubizjak@gmail.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
-rw-r--r--arch/x86/include/asm/alternative.h4
-rw-r--r--arch/x86/kernel/callthunks.c4
-rw-r--r--arch/x86/net/bpf_jit_comp.c19
3 files changed, 12 insertions, 15 deletions
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index fcd20c6dc7f9..67b68d0d17d1 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -117,7 +117,7 @@ extern void callthunks_patch_builtin_calls(void);
extern void callthunks_patch_module_calls(struct callthunk_sites *sites,
struct module *mod);
extern void *callthunks_translate_call_dest(void *dest);
-extern int x86_call_depth_emit_accounting(u8 **pprog, void *func);
+extern int x86_call_depth_emit_accounting(u8 **pprog, void *func, void *ip);
#else
static __always_inline void callthunks_patch_builtin_calls(void) {}
static __always_inline void
@@ -128,7 +128,7 @@ static __always_inline void *callthunks_translate_call_dest(void *dest)
return dest;
}
static __always_inline int x86_call_depth_emit_accounting(u8 **pprog,
- void *func)
+ void *func, void *ip)
{
return 0;
}
diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c
index 30335182b6b0..e92ff0c11db8 100644
--- a/arch/x86/kernel/callthunks.c
+++ b/arch/x86/kernel/callthunks.c
@@ -314,7 +314,7 @@ static bool is_callthunk(void *addr)
return !bcmp(pad, insn_buff, tmpl_size);
}
-int x86_call_depth_emit_accounting(u8 **pprog, void *func)
+int x86_call_depth_emit_accounting(u8 **pprog, void *func, void *ip)
{
unsigned int tmpl_size = SKL_TMPL_SIZE;
u8 insn_buff[MAX_PATCH_LEN];
@@ -327,7 +327,7 @@ int x86_call_depth_emit_accounting(u8 **pprog, void *func)
return 0;
memcpy(insn_buff, skl_call_thunk_template, tmpl_size);
- apply_relocation(insn_buff, tmpl_size, *pprog,
+ apply_relocation(insn_buff, tmpl_size, ip,
skl_call_thunk_template, tmpl_size);
memcpy(*pprog, insn_buff, tmpl_size);
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index e55745f512e1..df5fac428408 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -480,7 +480,7 @@ static int emit_call(u8 **pprog, void *func, void *ip)
static int emit_rsb_call(u8 **pprog, void *func, void *ip)
{
OPTIMIZER_HIDE_VAR(func);
- ip += x86_call_depth_emit_accounting(pprog, func);
+ ip += x86_call_depth_emit_accounting(pprog, func, ip);
return emit_patch(pprog, func, ip, 0xE8);
}
@@ -1972,20 +1972,17 @@ populate_extable:
/* call */
case BPF_JMP | BPF_CALL: {
- int offs;
+ u8 *ip = image + addrs[i - 1];
func = (u8 *) __bpf_call_base + imm32;
if (tail_call_reachable) {
RESTORE_TAIL_CALL_CNT(bpf_prog->aux->stack_depth);
- if (!imm32)
- return -EINVAL;
- offs = 7 + x86_call_depth_emit_accounting(&prog, func);
- } else {
- if (!imm32)
- return -EINVAL;
- offs = x86_call_depth_emit_accounting(&prog, func);
+ ip += 7;
}
- if (emit_call(&prog, func, image + addrs[i - 1] + offs))
+ if (!imm32)
+ return -EINVAL;
+ ip += x86_call_depth_emit_accounting(&prog, func, ip);
+ if (emit_call(&prog, func, ip))
return -EINVAL;
break;
}
@@ -2835,7 +2832,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
* Direct-call fentry stub, as such it needs accounting for the
* __fentry__ call.
*/
- x86_call_depth_emit_accounting(&prog, NULL);
+ x86_call_depth_emit_accounting(&prog, NULL, image);
}
EMIT1(0x55); /* push rbp */
EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */