Skip to contentSkip to conversation

x86/bpf: Fixes for the BPF JIT with retbleed=stuff

PATCH RESEND Applied Uros Bizjak 4 participants 8 messages Apr 1, 2024 – Apr 3, 2024

Subsystems (5)
Networking Network drivers x86 BPF +1 more subsystems
lore
Share & tools
lore
#0 lore raw

v2 cover x86/bpf: Fixes for the BPF JIT with retbleed=stuff

From: Joan Bruguera Micó <[email protected]>

Fixes two issues that cause kernels panic when using the BPF JIT with the call depth tracking / stuffing mitigation for Skylake processors (retbleed=stuff). Both issues can be triggered by running simple BPF programs (e.g. running the test suite should trigger both).

The first (resubmit) fixes a trivial issue related to calculating the destination IP for call instructions with call depth tracking.

The second is related to using the correct IP for relocations, related to the recently introduced %rip-relative addressing for PER_CPU_VAR.

Cc Alexei Starovoitov <[email protected]>
Cc Daniel Borkmann <[email protected]>

---
v2:
Simplify calculation of "ip".
Add more details to the commit message.

Joan Bruguera Micó (1):
x86/bpf: Fix IP for relocating call depth accounting

Uros Bizjak (1):
x86/bpf: Fix IP after emitting call depth accounting

 arch/x86/include/asm/alternative.h |  4 ++--
 arch/x86/kernel/callthunks.c       |  4 ++--
 arch/x86/net/bpf_jit_comp.c        | 19 ++++++++-----------
 3 files changed, 12 insertions(+), 15 deletions(-)
Signature · 1 line
2.42.0
#1 lore raw

PATCH RESEND v2 1/2 x86/bpf: Fix IP after emitting call depth accounting

Adjust the IP passed to emit_patch so it calculates the correct offset for the CALL instruction if x86_call_depth_emit_accounting emits code. Otherwise we will skip some instructions and most likely crash.

Fixes b2e9dfe54be4 ("x86/bpf: Emit call depth accounting if required")
Cc Alexei Starovoitov <[email protected]>
Cc Daniel Borkmann <[email protected]>

---
v2: Simplify calculation of "ip".

---
 arch/x86/net/bpf_jit_comp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/x86/net/bpf_jit_comp.c +1 -1
index a7ba8e178645..e55745f512e1 100644
@@ -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);
-	x86_call_depth_emit_accounting(pprog, func);
+	ip += x86_call_depth_emit_accounting(pprog, func);
 	return emit_patch(pprog, func, ip, 0xE8);
 }
 
Signature · 1 line
2.42.0
#2 lore raw

PATCH RESEND v2 2/2 x86/bpf: Fix IP for relocating call depth accounting

In reply to Uros Bizjak

From: Joan Bruguera Micó <[email protected]>

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")
Cc Alexei Starovoitov <[email protected]>
Cc Daniel Borkmann <[email protected]>

---
v2: Add more details to the commit message.

---
 arch/x86/include/asm/alternative.h |  4 ++--
 arch/x86/kernel/callthunks.c       |  4 ++--
 arch/x86/net/bpf_jit_comp.c        | 19 ++++++++-----------
 3 files changed, 12 insertions(+), 15 deletions(-)
arch/x86/include/asm/alternative.h +2 -2
index fcd20c6dc7f9..67b68d0d17d1 100644
@@ -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;
 }
arch/x86/kernel/callthunks.c +2 -2
index 30335182b6b0..e92ff0c11db8 100644
@@ -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);
arch/x86/net/bpf_jit_comp.c +8 -11
index e55745f512e1..df5fac428408 100644
@@ -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 @@ st:			if (is_imm8(insn->off))
 
 			/* 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 */
Signature · 1 line
2.42.0
#3 lore raw
In reply to Uros Bizjak
This series was applied to bpf/bpf.git (master) by Alexei Starovoitov <[email protected]>:

Hello:

This series was applied to bpf/bpf.git (master)
by Alexei Starovoitov <[email protected]>:

Quoted 8 lines · On Mon, 1 Apr 2024 20:55:28 +0200 you wrote:

From: Joan Bruguera Micó <[email protected]>

Fixes two issues that cause kernels panic when using the BPF JIT with the call depth tracking / stuffing mitigation for Skylake processors (retbleed=stuff). Both issues can be triggered by running simple BPF programs (e.g. running the test suite should trigger both).

[...]

Here is the summary with links:
- [RESEND,bpf,v2,1/2] x86/bpf: Fix IP after emitting call depth accounting

    https://git.kernel.org/bpf/bpf/c/9d98aa088386
  - [RESEND,bpf,v2,2/2] x86/bpf: Fix IP for relocating call depth accounting
    https://git.kernel.org/bpf/bpf/c/6a537453000a

You are awesome, thank you!

Signature · 2 lines
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html
#4 lore raw
Quoted 13 lines · * [email protected] <[email protected]> wrote:

Hello:

This series was applied to bpf/bpf.git (master)
by Alexei Starovoitov <[email protected]>:

Quoted 7 lines · On Mon, 1 Apr 2024 20:55:28 +0200 you wrote:

From: Joan Bruguera Micó <[email protected]>

Fixes two issues that cause kernels panic when using the BPF JIT with the call depth tracking / stuffing mitigation for Skylake processors (retbleed=stuff). Both issues can be triggered by running simple BPF programs (e.g. running the test suite should trigger both).

Quoted 7 lines
Quoted 1 line

[...]

Here is the summary with links:
- [RESEND,bpf,v2,1/2] x86/bpf: Fix IP after emitting call depth accounting

    https://git.kernel.org/bpf/bpf/c/9d98aa088386
  - [RESEND,bpf,v2,2/2] x86/bpf: Fix IP for relocating call depth accounting
    https://git.kernel.org/bpf/bpf/c/6a537453000a

Just wondering, which kernel version is this targeted for?

The bug is upstream as well, so a fix needs to be sent to Linus.

I can pick all of this up into tip:x86/urgent, if that accelerates things.

Thanks,

Ingo

#5 lore raw
Quoted 19 lines · Ingo Molnar
Quoted 15 lines · * [email protected] <[email protected]> wrote:

Hello:

This series was applied to bpf/bpf.git (master)
by Alexei Starovoitov <[email protected]>:

Quoted 8 lines · On Mon, 1 Apr 2024 20:55:28 +0200 you wrote:

From: Joan Bruguera Micó <[email protected]>

Fixes two issues that cause kernels panic when using the BPF JIT with the call depth tracking / stuffing mitigation for Skylake processors (retbleed=stuff). Both issues can be triggered by running simple BPF programs (e.g. running the test suite should trigger both).

[...]

Quoted 7 lines
Quoted 5 lines

Here is the summary with links:
- [RESEND,bpf,v2,1/2] x86/bpf: Fix IP after emitting call depth accounting

    https://git.kernel.org/bpf/bpf/c/9d98aa088386
  - [RESEND,bpf,v2,2/2] x86/bpf: Fix IP for relocating call depth accounting
    https://git.kernel.org/bpf/bpf/c/6a537453000a

Just wondering, which kernel version is this targeted for?

The whole series is intended for the current mainline (v6.9), this is why it is developed against the bpf (*not* bpf-next) branch. Please note that the kernel panics with retbleed=stuff even without %rip-relative changes (patch 1/2 above) [1], so patch 1/2 should be backported to stable branches.

[1] https://lore.kernel.org/lkml/[email protected]/

Uros.

Quoted 8 lines

The bug is upstream as well, so a fix needs to be sent to Linus.

I can pick all of this up into tip:x86/urgent, if that accelerates things.

Thanks,

Ingo

#6 lore raw
Quoted 10 lines · Uros Bizjak
Quoted 7 lines
Quoted 5 lines

Here is the summary with links:
- [RESEND,bpf,v2,1/2] x86/bpf: Fix IP after emitting call depth accounting

    https://git.kernel.org/bpf/bpf/c/9d98aa088386
  - [RESEND,bpf,v2,2/2] x86/bpf: Fix IP for relocating call depth accounting
    https://git.kernel.org/bpf/bpf/c/6a537453000a

Just wondering, which kernel version is this targeted for?

The whole series is intended for the current mainline (v6.9), this is why it is developed against the bpf (*not* bpf-next) branch.

I see - so bpf.git:master are current-mainline BPF fixes - that's perfect.

BTW., bpf-next is not a branch, but a separate Git tree. (Which is what confused me.)

Thanks,

Ingo

maintainer
#7 lore raw
Quoted 8 lines · Ingo Molnar
Quoted 6 lines · Uros Bizjak
Quoted 6 lines
Quoted 5 lines

Here is the summary with links:
- [RESEND,bpf,v2,1/2] x86/bpf: Fix IP after emitting call depth accounting

     https://git.kernel.org/bpf/bpf/c/9d98aa088386
   - [RESEND,bpf,v2,2/2] x86/bpf: Fix IP for relocating call depth accounting
     https://git.kernel.org/bpf/bpf/c/6a537453000a
Quoted 6 lines
Quoted 4 lines
Quoted 1 line

Just wondering, which kernel version is this targeted for?

The whole series is intended for the current mainline (v6.9), this is why it is developed against the bpf (*not* bpf-next) branch.

I see - so bpf.git:master are current-mainline BPF fixes - that's perfect.

Yes, correct, that is for mainline (v6.9).

Thanks,
Daniel