[PATCH v11 1/8] powerpc/bpf: fix alignment of long branch trampoline address

[PATCH v11 1/8] powerpc/bpf: fix alignment of long branch trampoline address

[Saket Kumar Bhaskar]

From: Abhishek Dubey <adubey@linux.ibm.com>

Ensure the dummy trampoline address field present between the OOL stub
and the long branch stub is 8-byte aligned, for memory compatibility
when content loaded to a register.

Reported-by: Hari Bathini <hbathini@linux.ibm.com>
Fixes: d243b62b7bd3 ("powerpc64/bpf: Add support for bpf trampolines")
Cc: stable@vger.kernel.org
Signed-off-by: Abhishek Dubey <adubey@linux.ibm.com>
Signed-off-by: Saket Kumar Bhaskar <skb99@linux.ibm.com>
Tested-by: Yeswanth Krishna Tellakula <yeswanth@linux.ibm.com>
---
 arch/powerpc/net/bpf_jit.h        |  7 +++---
 arch/powerpc/net/bpf_jit_comp.c   | 42 ++++++++++++++++++++++++++-----
 arch/powerpc/net/bpf_jit_comp32.c |  6 +++--
 arch/powerpc/net/bpf_jit_comp64.c |  7 +++---
 4 files changed, 48 insertions(+), 14 deletions(-)

diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index f32de8704d4d..6632de9871dd 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -214,10 +214,11 @@ int bpf_jit_emit_func_call_rel(u32 *image, u32 *fimage, struct codegen_context *
 int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct codegen_context *ctx,
 		       u32 *addrs, int pass, bool extra_pass);
 void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx);
-void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx);
-void bpf_jit_build_fentry_stubs(u32 *image, struct codegen_context *ctx);
+void bpf_jit_build_epilogue(u32 *image, u32 *fimage, struct codegen_context *ctx);
+void bpf_jit_build_fentry_stubs(u32 *image, u32 *fimage, struct codegen_context *ctx);
 void bpf_jit_realloc_regs(struct codegen_context *ctx);
-int bpf_jit_emit_exit_insn(u32 *image, struct codegen_context *ctx, int tmp_reg, long exit_addr);
+int bpf_jit_emit_exit_insn(u32 *image, u32 *fimage, struct codegen_context *ctx, int tmp_reg,
+										long exit_addr);
 void prepare_for_fsession_fentry(u32 *image, struct codegen_context *ctx, int cookie_cnt,
 								int cookie_off, int retval_off);
 void store_func_meta(u32 *image, struct codegen_context *ctx, u64 func_meta, int func_meta_off);
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 7b07b43575f1..f2e0f9755e65 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -49,11 +49,39 @@ asm (
 "	.popsection				;"
 );
 
-void bpf_jit_build_fentry_stubs(u32 *image, struct codegen_context *ctx)
+void bpf_jit_build_fentry_stubs(u32 *image, u32 *fimage, struct codegen_context *ctx)
 {
 	int ool_stub_idx, long_branch_stub_idx;
+	int ool_stub_sz;
 
 	/*
+	 * In the final pass, align the mis-aligned dummy_tramp_addr field
+	 * in the fimage. The alignment NOP must appear before OOL stub,
+	 * to make ool_stub_idx & long_branch_stub_idx constant from end.
+	 *
+	 * dummy_tramp_addr must be 8-byte aligned for load-register
+	 * compatibility. The fimage can be non 8-byte aligned, so final
+	 * alignment depends on start of fimage and the stub's instruction
+	 * count offset. The OOL stub size is 4 instructions (with
+	 * CONFIG_PPC_FTRACE_OUT_OF_LINE) or 3 instructions (without)
+	 * before dummy_tramp_addr.
+	 *
+	 * Emit a NOP here if (ctx->idx + ool_stub_sz) is odd, so that
+	 * dummy_tramp_addr lands at an even instruction offset (== 8-byte
+	 * aligned from an 8-byte aligned base).
+	 *
+	 * In pass=0 when image==NULL, conservatively account for space
+	 * required to accommodate alignment NOP. In case final pass skips
+	 * emitting alignment NOP, the image buffer have 4 spare bytes and
+	 * jited_len signifies correct program size.
+	 */
+
+	ool_stub_sz = IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE) ? 16 : 12;
+	if (!image || !IS_ALIGNED((unsigned long)fimage + ctx->idx*4 + ool_stub_sz, SZL))
+		EMIT(PPC_RAW_NOP());
+
+	/*
+	 *      nop     // optional, for alignment of dummy_tramp_addr
 	 * Out-of-line stub:
 	 *	mflr	r0
 	 *	[b|bl]	tramp
@@ -70,7 +98,7 @@ void bpf_jit_build_fentry_stubs(u32 *image, struct codegen_context *ctx)
 
 	/*
 	 * Long branch stub:
-	 *	.long	<dummy_tramp_addr>
+	 *	.long	<dummy_tramp_addr>  // 8-byte aligned
 	 *	mflr	r11
 	 *	bcl	20,31,$+4
 	 *	mflr	r12
@@ -81,6 +109,7 @@ void bpf_jit_build_fentry_stubs(u32 *image, struct codegen_context *ctx)
 	 */
 	if (image)
 		*((unsigned long *)&image[ctx->idx]) = (unsigned long)dummy_tramp;
+
 	ctx->idx += SZL / 4;
 	long_branch_stub_idx = ctx->idx;
 	EMIT(PPC_RAW_MFLR(_R11));
@@ -97,7 +126,8 @@ void bpf_jit_build_fentry_stubs(u32 *image, struct codegen_context *ctx)
 	}
 }
 
-int bpf_jit_emit_exit_insn(u32 *image, struct codegen_context *ctx, int tmp_reg, long exit_addr)
+int bpf_jit_emit_exit_insn(u32 *image, u32 *fimage, struct codegen_context *ctx,
+							int tmp_reg, long exit_addr)
 {
 	if (!exit_addr || is_offset_in_branch_range(exit_addr - (ctx->idx * 4))) {
 		PPC_JMP(exit_addr);
@@ -107,7 +137,7 @@ int bpf_jit_emit_exit_insn(u32 *image, struct codegen_context *ctx, int tmp_reg,
 		PPC_JMP(ctx->alt_exit_addr);
 	} else {
 		ctx->alt_exit_addr = ctx->idx * 4;
-		bpf_jit_build_epilogue(image, ctx);
+		bpf_jit_build_epilogue(image, fimage, ctx);
 	}
 
 	return 0;
@@ -286,7 +316,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_pr
 	 */
 	bpf_jit_build_prologue(NULL, &cgctx);
 	addrs[fp->len] = cgctx.idx * 4;
-	bpf_jit_build_epilogue(NULL, &cgctx);
+	bpf_jit_build_epilogue(NULL, NULL, &cgctx);
 
 	fixup_len = fp->aux->num_exentries * BPF_FIXUP_LEN * 4;
 	extable_len = fp->aux->num_exentries * sizeof(struct exception_table_entry);
@@ -318,7 +348,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_pr
 			bpf_jit_binary_pack_free(fhdr, hdr);
 			goto out_err;
 		}
-		bpf_jit_build_epilogue(code_base, &cgctx);
+		bpf_jit_build_epilogue(code_base, fcode_base, &cgctx);
 
 		if (bpf_jit_enable > 1)
 			pr_info("Pass %d: shrink = %d, seen = 0x%x\n", pass,
diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c
index bfdc50740da8..1cf12edf0343 100644
--- a/arch/powerpc/net/bpf_jit_comp32.c
+++ b/arch/powerpc/net/bpf_jit_comp32.c
@@ -229,7 +229,7 @@ static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx
 
 }
 
-void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
+void bpf_jit_build_epilogue(u32 *image, u32 *fimage, struct codegen_context *ctx)
 {
 	EMIT(PPC_RAW_MR(_R3, bpf_to_ppc(BPF_REG_0)));
 
@@ -237,7 +237,7 @@ void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
 
 	EMIT(PPC_RAW_BLR());
 
-	bpf_jit_build_fentry_stubs(image, ctx);
+	bpf_jit_build_fentry_stubs(image, fimage, ctx);
 }
 
 /* Relative offset needs to be calculated based on final image location */
@@ -1150,6 +1150,8 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
 			 */
 			if (i != flen - 1) {
 				ret = bpf_jit_emit_exit_insn(image, ctx, _R0, exit_addr);
+				ret = bpf_jit_emit_exit_insn(image, fimage,
+								ctx, _R0, exit_addr);
 				if (ret)
 					return ret;
 			}
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index dab106cae22b..951eb10ca1f6 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -398,7 +398,7 @@ static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx
 	}
 }
 
-void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
+void bpf_jit_build_epilogue(u32 *image, u32 *fimage, struct codegen_context *ctx)
 {
 	bpf_jit_emit_common_epilogue(image, ctx);
 
@@ -407,7 +407,7 @@ void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
 
 	EMIT(PPC_RAW_BLR());
 
-	bpf_jit_build_fentry_stubs(image, ctx);
+	bpf_jit_build_fentry_stubs(image, fimage, ctx);
 }
 
 /*
@@ -1737,7 +1737,8 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
 			 * we'll just fall through to the epilogue.
 			 */
 			if (i != flen - 1) {
-				ret = bpf_jit_emit_exit_insn(image, ctx, tmp1_reg, exit_addr);
+				ret = bpf_jit_emit_exit_insn(image, fimage, ctx,
+								tmp1_reg, exit_addr);
 				if (ret)
 					return ret;
 			}
-- 
2.54.0

Re: [PATCH v11 1/8] powerpc/bpf: fix alignment of long branch trampoline address

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:

New issues:
- [High] Dynamic epilogue sizing breaks JIT pass convergence, causing BPF_EXIT branches to skip the first instruction of the epilogue.
- [Low] The patch introduces a compilation error in `arch/powerpc/net/bpf_jit_comp32.c` by failing to remove the old 4-argument call to `bpf_jit_emit_exit_insn()`.

Pre-existing issues:
- [Critical] Out-of-bounds write in BPF JIT due to under-calculated allocation size for large programs.
--

--- Patch [1]: [PATCH v11 1/8] powerpc/bpf: fix alignment of long branch trampoline address ---
commit a15c5c8b15ef787442dd6c60c0e42163a958cb5a
Author: Abhishek Dubey <adubey@linux.ibm.com>

powerpc/bpf: fix alignment of long branch trampoline address

This patch ensures the dummy trampoline address field between the out-of-line
stub and the long branch stub is 8-byte aligned. It modifies the epilogue and
fentry stub building functions to accept the final image pointer and emit a
conditional NOP if needed.

> diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
> index 7b07b43575f11..f2e0f9755e653 100644
> --- a/arch/powerpc/net/bpf_jit_comp.c
> +++ b/arch/powerpc/net/bpf_jit_comp.c
[ ... ]
> @@ -49,11 +49,39 @@ asm (
>  "	.popsection				;"
>  );
>  
> -void bpf_jit_build_fentry_stubs(u32 *image, struct codegen_context *ctx)
> +void bpf_jit_build_fentry_stubs(u32 *image, u32 *fimage, struct codegen_context *ctx)
>  {
>  	int ool_stub_idx, long_branch_stub_idx;
> +	int ool_stub_sz;
>  
>  	/*
> +	 * In the final pass, align the mis-aligned dummy_tramp_addr field
> +	 * in the fimage. The alignment NOP must appear before OOL stub,
> +	 * to make ool_stub_idx & long_branch_stub_idx constant from end.
> +	 *
> +	 * dummy_tramp_addr must be 8-byte aligned for load-register
> +	 * compatibility. The fimage can be non 8-byte aligned, so final
> +	 * alignment depends on start of fimage and the stub's instruction
> +	 * count offset. The OOL stub size is 4 instructions (with
> +	 * CONFIG_PPC_FTRACE_OUT_OF_LINE) or 3 instructions (without)
> +	 * before dummy_tramp_addr.
> +	 *
> +	 * Emit a NOP here if (ctx->idx + ool_stub_sz) is odd, so that
> +	 * dummy_tramp_addr lands at an even instruction offset (== 8-byte
> +	 * aligned from an 8-byte aligned base).
> +	 *
> +	 * In pass=0 when image==NULL, conservatively account for space
> +	 * required to accommodate alignment NOP. In case final pass skips
> +	 * emitting alignment NOP, the image buffer have 4 spare bytes and
> +	 * jited_len signifies correct program size.
> +	 */
> +
> +	ool_stub_sz = IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE) ? 16 : 12;
> +	if (!image || !IS_ALIGNED((unsigned long)fimage + ctx->idx*4 + ool_stub_sz, SZL))
> +		EMIT(PPC_RAW_NOP());
> +

[Severity: High]
Does this conditional NOP break the JIT convergence loop in
bpf_int_jit_compile()?

If the body size shrinks by an odd number of instructions in the final JIT
pass, this could flip the alignment and cause an extra padding NOP to be
emitted.

This would increase the epilogue size by 4 bytes while the total proglen
remains constant. Could this cause the JIT loop to terminate prematurely while
exit_addr still points to the old epilogue start, skipping the first
instruction of the epilogue and potentially leading to register corruption?

>  	/*
> -	 *      nop     // optional, for alignment of dummy_tramp_addr
[ ... ]
> @@ -97,7 +126,8 @@ void bpf_jit_build_fentry_stubs(u32 *image, struct codegen_context *ctx)
>  	}
>  }
>  
> -int bpf_jit_emit_exit_insn(u32 *image, struct codegen_context *ctx, int tmp_reg, long exit_addr)
> +int bpf_jit_emit_exit_insn(u32 *image, u32 *fimage, struct codegen_context *ctx,
> +							int tmp_reg, long exit_addr)
>  {
>  	if (!exit_addr || is_offset_in_branch_range(exit_addr - (ctx->idx * 4))) {

[Severity: Critical]
This is a pre-existing issue, but does the !exit_addr condition falsely
report large branches as in-range during Pass 0?

In bpf_int_jit_compile(), the true epilogue offset is populated after the
second Pass 0 loop, meaning during all Pass 0 execution, exit_addr is
evaluated as 0. This bypasses the branch range evaluation and falsely
predicts only 4 bytes per BPF_EXIT.

When exit_addr is resolved in Pass 1 for large programs (>32MB) that exceed
the branch range, could this cause an under-calculated allocation size,
leading to an out-of-bounds write when the inline epilogue is emitted?

>  		PPC_JMP(exit_addr);
[ ... ]
> diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c
> index bfdc50740da8e..1cf12edf0343f 100644
> --- a/arch/powerpc/net/bpf_jit_comp32.c
> +++ b/arch/powerpc/net/bpf_jit_comp32.c
[ ... ]
> @@ -1150,6 +1150,8 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
>  			 */
>  			if (i != flen - 1) {
>  				ret = bpf_jit_emit_exit_insn(image, ctx, _R0, exit_addr);
> +				ret = bpf_jit_emit_exit_insn(image, fimage,
> +								ctx, _R0, exit_addr);
>  				if (ret)
>  					return ret;
>  			}

[Severity: Low]
Is the old 4-argument call to bpf_jit_emit_exit_insn() accidentally left here?

Leaving this intact right above the newly added 5-argument call appears to
directly break the build on 32-bit PowerPC architectures due to too few
arguments.

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/cover.1786099877.git.skb99@linux.ibm.com?part=1

[PATCH v11 2/8] powerpc/bpf: Move out dummy_tramp_addr after Long branch stub

[Saket Kumar Bhaskar]

From: Abhishek Dubey <adubey@linux.ibm.com>

Move the long branch address field to the bottom of the long
branch stub. This allows uninterrupted disassembly until the
last 4/8 bytes. The last bytes exclusion is logically necessary to
prevent disassembly failure, otherwise the actual program layout
is never altered. Hence no effect on overall program size.
Also, align dummy_tramp_addr field with 8-byte boundary.

Following is disassembler output for test program with moved down
dummy_tramp_addr field:
.....
.....
pc:68    left:44     a6 03 08 7c  :  mtlr 0
pc:72    left:40     bc ff ff 4b  :  b .-68
pc:76    left:36     a6 02 68 7d  :  mflr 11
pc:80    left:32     05 00 9f 42  :  bcl 20, 31, .+4
pc:84    left:28     a6 02 88 7d  :  mflr 12
pc:88    left:24     14 00 8c e9  :  ld 12, 20(12)
pc:92    left:20     a6 03 89 7d  :  mtctr 12
pc:96    left:16     a6 03 68 7d  :  mtlr 11
pc:100   left:12     20 04 80 4e  :  bctr
pc:104   left:8      c0 34 1d 00  :

Failure log:
Can't disasm instruction at offset 104: c0 34 1d 00 00 00 00 c0
Disassembly logic can truncate at 104, ignoring last 8 bytes.

Update the dummy_tramp_addr field offset calculation from the end
of the program to reflect its new location, for bpf_arch_text_poke()
to update the actual trampoline's address in this field.

All BPF trampoline selftests continue to pass with this patch applied.

Fixes: d243b62b7bd3 ("powerpc64/bpf: Add support for bpf trampolines")
Signed-off-by: Abhishek Dubey <adubey@linux.ibm.com>
Signed-off-by: Saket Kumar Bhaskar <skb99@linux.ibm.com>
Tested-by: Yeswanth Krishna Tellakula <yeswanth@linux.ibm.com>
---
 arch/powerpc/net/bpf_jit_comp.c | 46 +++++++++++++++++----------------
 1 file changed, 24 insertions(+), 22 deletions(-)

diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index f2e0f9755e65..bdae835e4b71 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -52,9 +52,10 @@ asm (
 void bpf_jit_build_fentry_stubs(u32 *image, u32 *fimage, struct codegen_context *ctx)
 {
 	int ool_stub_idx, long_branch_stub_idx;
-	int ool_stub_sz;
+	int stub_sz;
 
 	/*
+	 * The dummy_tramp_addr field is placed at bottom of Long branch stub.
 	 * In the final pass, align the mis-aligned dummy_tramp_addr field
 	 * in the fimage. The alignment NOP must appear before OOL stub,
 	 * to make ool_stub_idx & long_branch_stub_idx constant from end.
@@ -62,13 +63,10 @@ void bpf_jit_build_fentry_stubs(u32 *image, u32 *fimage, struct codegen_context
 	 * dummy_tramp_addr must be 8-byte aligned for load-register
 	 * compatibility. The fimage can be non 8-byte aligned, so final
 	 * alignment depends on start of fimage and the stub's instruction
-	 * count offset. The OOL stub size is 4 instructions (with
-	 * CONFIG_PPC_FTRACE_OUT_OF_LINE) or 3 instructions (without)
-	 * before dummy_tramp_addr.
-	 *
-	 * Emit a NOP here if (ctx->idx + ool_stub_sz) is odd, so that
-	 * dummy_tramp_addr lands at an even instruction offset (== 8-byte
-	 * aligned from an 8-byte aligned base).
+	 * count. The stubs block has 11 instructions (with
+	 * CONFIG_PPC_FTRACE_OUT_OF_LINE) or 10 instructions (without)
+	 * before dummy_tramp_addr field. Emit a NOP if the address of
+	 * dummy_tramp_addr is non aligned.
 	 *
 	 * In pass=0 when image==NULL, conservatively account for space
 	 * required to accommodate alignment NOP. In case final pass skips
@@ -76,8 +74,8 @@ void bpf_jit_build_fentry_stubs(u32 *image, u32 *fimage, struct codegen_context
 	 * jited_len signifies correct program size.
 	 */
 
-	ool_stub_sz = IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE) ? 16 : 12;
-	if (!image || !IS_ALIGNED((unsigned long)fimage + ctx->idx*4 + ool_stub_sz, SZL))
+	stub_sz = IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE) ? 44 : 40;
+	if (!image || !IS_ALIGNED((unsigned long)fimage + ctx->idx*4 + stub_sz, SZL))
 		EMIT(PPC_RAW_NOP());
 
 	/*
@@ -98,28 +96,29 @@ void bpf_jit_build_fentry_stubs(u32 *image, u32 *fimage, struct codegen_context
 
 	/*
 	 * Long branch stub:
-	 *	.long	<dummy_tramp_addr>  // 8-byte aligned
 	 *	mflr	r11
 	 *	bcl	20,31,$+4
-	 *	mflr	r12
-	 *	ld	r12, -8-SZL(r12)
+	 *	mflr	r12	// lr/r12 stores pc of current(this) inst.
+	 *	ld	r12, 20(r12) // offset(dummy_tramp_addr) from prev inst. is 20
 	 *	mtctr	r12
-	 *	mtlr	r11 // needed to retain ftrace ABI
+	 *	mtlr	r11	// needed to retain ftrace ABI
 	 *	bctr
+	 *	.long	<dummy_tramp_addr>  // SZL bytes aligned
 	 */
-	if (image)
-		*((unsigned long *)&image[ctx->idx]) = (unsigned long)dummy_tramp;
-
-	ctx->idx += SZL / 4;
 	long_branch_stub_idx = ctx->idx;
 	EMIT(PPC_RAW_MFLR(_R11));
 	EMIT(PPC_RAW_BCL4());
 	EMIT(PPC_RAW_MFLR(_R12));
-	EMIT(PPC_RAW_LL(_R12, _R12, -8-SZL));
+	EMIT(PPC_RAW_LL(_R12, _R12, 20));
 	EMIT(PPC_RAW_MTCTR(_R12));
 	EMIT(PPC_RAW_MTLR(_R11));
 	EMIT(PPC_RAW_BCTR());
 
+	if (image)
+		*((unsigned long *)&image[ctx->idx]) = (unsigned long)dummy_tramp;
+
+	ctx->idx += SZL / 4;
+
 	if (!bpf_jit_ool_stub) {
 		bpf_jit_ool_stub = (ctx->idx - ool_stub_idx) * 4;
 		bpf_jit_long_branch_stub = (ctx->idx - long_branch_stub_idx) * 4;
@@ -1295,6 +1294,7 @@ static void do_isync(void *info __maybe_unused)
  * bpf_func:
  *	[nop|b]	ool_stub
  * 2. Out-of-line stub:
+ * 	nop	// optional nop for alignment
  * ool_stub:
  *	mflr	r0
  *	[b|bl]	<bpf_prog>/<long_branch_stub>
@@ -1302,14 +1302,14 @@ static void do_isync(void *info __maybe_unused)
  *	b	bpf_func + 4
  * 3. Long branch stub:
  * long_branch_stub:
- *	.long	<branch_addr>/<dummy_tramp>
  *	mflr	r11
  *	bcl	20,31,$+4
  *	mflr	r12
- *	ld	r12, -16(r12)
+ *	ld	r12, 20(r12)
  *	mtctr	r12
  *	mtlr	r11 // needed to retain ftrace ABI
  *	bctr
+ *	.long	<branch_addr>/<dummy_tramp>
  *
  * dummy_tramp is used to reduce synchronization requirements.
  *
@@ -1411,10 +1411,12 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type old_t,
 	 * 1. Update the address in the long branch stub:
 	 * If new_addr is out of range, we will have to use the long branch stub, so patch new_addr
 	 * here. Otherwise, revert to dummy_tramp, but only if we had patched old_addr here.
+	 *
+	 * dummy_tramp_addr moved to bottom of long branch stub.
 	 */
 	if ((new_addr && !is_offset_in_branch_range(new_addr - ip)) ||
 	    (old_addr && !is_offset_in_branch_range(old_addr - ip)))
-		ret = patch_ulong((void *)(bpf_func_end - bpf_jit_long_branch_stub - SZL),
+		ret = patch_ulong((void *)(bpf_func_end - SZL), /* SZL: dummy_tramp_addr offset */
 				  (new_addr && !is_offset_in_branch_range(new_addr - ip)) ?
 				  (unsigned long)new_addr : (unsigned long)dummy_tramp);
 	if (ret)
-- 
2.54.0

[PATCH v11 3/8] selftests/bpf: Fixing powerpc JIT disassembly failure

[Saket Kumar Bhaskar]

From: Abhishek Dubey <adubey@linux.ibm.com>

Ensure that the trampoline stubs JITed at the tail of the
epilogue do not expose the dummy trampoline address stored
in the last 8 bytes(64-bit) and last 4 bytes(32-bit)
to the disassembly flow. Prevent the disassembler from
ingesting this memory address, as it may occasionally decode
into a seemingly valid but incorrect instruction. Fix this
issue by truncating the last 8/4 bytes from JITed buffers
before supplying them for disassembly.

Signed-off-by: Abhishek Dubey <adubey@linux.ibm.com>
Signed-off-by: Saket Kumar Bhaskar <skb99@linux.ibm.com>
Tested-by: Yeswanth Krishna Tellakula <yeswanth@linux.ibm.com>
Reviewed-by: Hari Bathini <hbathini@linux.ibm.com>
---
 .../selftests/bpf/jit_disasm_helpers.c        | 25 ++++++++++++++++++-
 1 file changed, 24 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/jit_disasm_helpers.c b/tools/testing/selftests/bpf/jit_disasm_helpers.c
index 3558fe10e28c..c4aa1d69d3bb 100644
--- a/tools/testing/selftests/bpf/jit_disasm_helpers.c
+++ b/tools/testing/selftests/bpf/jit_disasm_helpers.c
@@ -179,9 +179,11 @@ int get_jited_program_text(int fd, char *text, size_t text_sz)
 	struct bpf_prog_info info = {};
 	__u32 info_len = sizeof(info);
 	__u32 jited_funcs, len, pc;
+	__u32 trunc_len = 0, disasm_len;
 	__u32 *func_lens = NULL;
 	FILE *text_out = NULL;
 	uint8_t *image = NULL;
+	char *triple = NULL;
 	int i, err = 0;
 
 	if (!llvm_initialized) {
@@ -225,9 +227,30 @@ int get_jited_program_text(int fd, char *text, size_t text_sz)
 	if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd #2"))
 		goto out;
 
+	/*
+	 * last 8 bytes contains dummy_trampoline address in JIT
+	 * output on 64-bit and last 4 bytes on 32-bit powerpc,
+	 * which can't disassemble to a valid instruction.
+	 */
+	triple = LLVMGetDefaultTargetTriple();
+	if (triple) {
+		if (strstr(triple, "powerpc64") || strstr(triple, "ppc64"))
+			trunc_len = 8;
+		else if (strstr(triple, "powerpc") || strstr(triple, "ppc"))
+			trunc_len = 4;
+		LLVMDisposeMessage(triple);
+	}
+
 	for (pc = 0, i = 0; i < jited_funcs; ++i) {
+
 		fprintf(text_out, "func #%d:\n", i);
-		disasm_one_func(text_out, image + pc, func_lens[i]);
+		/*
+		 * Disabled JIT have zero func_lens, hence underflow
+		 */
+		disasm_len = func_lens[i] > trunc_len ?
+					func_lens[i] - trunc_len : 0;
+		disasm_one_func(text_out, image + pc, disasm_len);
+
 		fprintf(text_out, "\n");
 		pc += func_lens[i];
 	}
-- 
2.54.0

Re: [PATCH v11 3/8] selftests/bpf: Fixing powerpc JIT disassembly failure

[bot+bpf-ci]

[-- Attachment #1: Type: text/plain, Size: 1948 bytes --]

> diff --git a/tools/testing/selftests/bpf/jit_disasm_helpers.c b/tools/testing/selftests/bpf/jit_disasm_helpers.c
> index 3558fe10e28cf..c4aa1d69d3bbf 100644
> --- a/tools/testing/selftests/bpf/jit_disasm_helpers.c
> +++ b/tools/testing/selftests/bpf/jit_disasm_helpers.c

[ ... ]

> @@ -225,9 +227,30 @@ int get_jited_program_text(int fd, char *text, size_t text_sz)
>  	if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd #2"))
>  		goto out;
>
> +	/*
> +	 * last 8 bytes contains dummy_trampoline address in JIT
> +	 * output on 64-bit and last 4 bytes on 32-bit powerpc,
> +	 * which can't disassemble to a valid instruction.
> +	 */
> +	triple = LLVMGetDefaultTargetTriple();
> +	if (triple) {
> +		if (strstr(triple, "powerpc64") || strstr(triple, "ppc64"))
> +			trunc_len = 8;
> +		else if (strstr(triple, "powerpc") || strstr(triple, "ppc"))
> +			trunc_len = 4;
> +		LLVMDisposeMessage(triple);
> +	}
> +
>  	for (pc = 0, i = 0; i < jited_funcs; ++i) {
> +

This isn't a bug, but are the two new blank lines inside this loop
intentional? Dropping them would keep the diff to just the truncation
logic and match how the loops in disasm_one_func() are laid out.

>  		fprintf(text_out, "func #%d:\n", i);
>  		/*
>  		 * Disabled JIT have zero func_lens, hence underflow
>  		 */
>  		disasm_len = func_lens[i] > trunc_len ?
>  					func_lens[i] - trunc_len : 0;
>  		disasm_one_func(text_out, image + pc, disasm_len);
> +
>  		fprintf(text_out, "\n");
>  		pc += func_lens[i];
>  	}

> selftests/bpf: Fixing powerpc JIT disassembly failure

This isn't a bug, but would the subject read better in the imperative
mood, "selftests/bpf: Fix powerpc JIT disassembly failure", to match
the rest of the series?


---
AI reviewed your patch. Please fix the bug or email reply why it's not a bug.
See: https://github.com/kernel-patches/vmtest/blob/master/ci/claude/README.md

CI run summary: https://github.com/kernel-patches/bpf/actions/runs/31176427801

[PATCH v11 4/8] selftests/bpf: Enable verifier selftest for powerpc64

[Saket Kumar Bhaskar]

From: Abhishek Dubey <adubey@linux.ibm.com>

Enable "__arch_powerpc64" specifier in verifier selftest
for ppc64. Power 32-bit would require separate handling.
Changes tested for 64-bit only.

Signed-off-by: Abhishek Dubey <adubey@linux.ibm.com>
Signed-off-by: Saket Kumar Bhaskar <skb99@linux.ibm.com>
Reviewed-by: Hari Bathini <hbathini@linux.ibm.com>
Tested-by: Yeswanth Krishna Tellakula <yeswanth@linux.ibm.com>
---
 tools/testing/selftests/bpf/progs/bpf_misc.h | 1 +
 tools/testing/selftests/bpf/test_loader.c    | 5 +++++
 2 files changed, 6 insertions(+)

diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h
index b0c441384f20..365008d1ed40 100644
--- a/tools/testing/selftests/bpf/progs/bpf_misc.h
+++ b/tools/testing/selftests/bpf/progs/bpf_misc.h
@@ -159,6 +159,7 @@
 #define __arch_riscv64		__arch("RISCV64")
 #define __arch_s390x		__arch("s390x")
 #define __arch_loongarch	__arch("LOONGARCH")
+#define __arch_powerpc64	__arch("POWERPC64")
 #define __caps_unpriv(caps)	__test_tag("test_caps_unpriv=" EXPAND_QUOTE(caps))
 #define __load_if_JITed()	__test_tag("load_mode=jited")
 #define __load_if_no_JITed()	__test_tag("load_mode=no_jited")
diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c
index 3ce32d134e2c..01b1420097d2 100644
--- a/tools/testing/selftests/bpf/test_loader.c
+++ b/tools/testing/selftests/bpf/test_loader.c
@@ -378,6 +378,7 @@ enum arch {
 	ARCH_RISCV64	= 0x8,
 	ARCH_S390X	= 0x10,
 	ARCH_LOONGARCH	= 0x20,
+	ARCH_POWERPC64	= 0x40,
 };
 
 static int get_current_arch(void)
@@ -392,6 +393,8 @@ static int get_current_arch(void)
 	return ARCH_S390X;
 #elif defined(__loongarch__)
 	return ARCH_LOONGARCH;
+#elif defined(__powerpc64__)
+	return ARCH_POWERPC64;
 #endif
 	return ARCH_UNKNOWN;
 }
@@ -585,6 +588,8 @@ static int parse_test_spec(struct test_loader *tester,
 				arch = ARCH_S390X;
 			} else if (strcmp(val, "LOONGARCH") == 0) {
 				arch = ARCH_LOONGARCH;
+			} else if (strcmp(val, "POWERPC64") == 0) {
+				arch = ARCH_POWERPC64;
 			} else {
 				PRINT_FAIL("bad arch spec: '%s'\n", val);
 				err = -EINVAL;
-- 
2.54.0

[PATCH v11 5/8] powerpc64/bpf: fix compare instruction emitted for tailcall

[Saket Kumar Bhaskar]

From: Abhishek Dubey <adubey@linux.ibm.com>

The tail_call_info field can contain either a scalar counter
value or a 64-bit pointer to the counter, using a 32-bit
compare (cmplwi) only checks the lower 32 bits, which can lead
to incorrect comparisions when location of counter is near 4GB
boundary. Use instruction cmpldi/cmplwi for accurate comparision
in corresponding cases.

Reported-by: sashiko-bot@kernel.org
Closes: https://lore.kernel.org/bpf/20260517191450.85AE6C2BCB8@smtp.kernel.org/
Fixes: 2ed2d8f6fb38 ("powerpc64/bpf: Support tailcalls with subprogs")
Signed-off-by: Abhishek Dubey <adubey@linux.ibm.com>
Signed-off-by: Saket Kumar Bhaskar <skb99@linux.ibm.com>
Tested-by: Yeswanth Krishna Tellakula <yeswanth@linux.ibm.com>
Acked-by: Hari Bathini <hbathini@linux.ibm.com>
---
 arch/powerpc/net/bpf_jit.h        | 6 ++++++
 arch/powerpc/net/bpf_jit_comp.c   | 2 +-
 arch/powerpc/net/bpf_jit_comp64.c | 8 ++++----
 3 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index 6632de9871dd..af510da12d8e 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -188,6 +188,12 @@ struct codegen_context {
 
 #define bpf_to_ppc(r)	(ctx->b2p[r])
 
+#ifdef CONFIG_PPC64
+#define PPC_RAW_CMPLLI(a, i)    PPC_RAW_CMPLDI(a, i)
+#else
+#define PPC_RAW_CMPLLI(a, i)    PPC_RAW_CMPLWI(a, i)
+#endif
+
 #ifdef CONFIG_PPC32
 #define BPF_FIXUP_LEN	3 /* Three instructions => 12 bytes */
 #else
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index bdae835e4b71..757b36bfbac3 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -768,7 +768,7 @@ static void bpf_trampoline_setup_tail_call_info(u32 *image, struct codegen_conte
 		 * Setting the tail_call_info in trampoline's frame
 		 * depending on if previous frame had value or reference.
 		 */
-		EMIT(PPC_RAW_CMPLWI(_R3, MAX_TAIL_CALL_CNT));
+		EMIT(PPC_RAW_CMPLLI(_R3, MAX_TAIL_CALL_CNT));
 		PPC_BCC_CONST_SHORT(COND_GT, 8);
 		EMIT(PPC_RAW_ADDI(_R3, _R4, -BPF_PPC_TAILCALL));
 
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 951eb10ca1f6..e80312171aa7 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -276,7 +276,7 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
 		 */
 		EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_2), _R1, 0));
 		EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_2), -(BPF_PPC_TAILCALL)));
-		EMIT(PPC_RAW_CMPLWI(bpf_to_ppc(TMP_REG_1), MAX_TAIL_CALL_CNT));
+		EMIT(PPC_RAW_CMPLDI(bpf_to_ppc(TMP_REG_1), MAX_TAIL_CALL_CNT));
 		PPC_BCC_CONST_SHORT(COND_GT, 8);
 		EMIT(PPC_RAW_ADDI(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_2),
 								-(BPF_PPC_TAILCALL)));
@@ -662,7 +662,7 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
 	PPC_BCC_SHORT(COND_GE, out);
 
 	EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), _R1, bpf_jit_stack_tailcallinfo_offset(ctx)));
-	EMIT(PPC_RAW_CMPLWI(bpf_to_ppc(TMP_REG_1), MAX_TAIL_CALL_CNT));
+	EMIT(PPC_RAW_CMPLDI(bpf_to_ppc(TMP_REG_1), MAX_TAIL_CALL_CNT));
 	PPC_BCC_CONST_SHORT(COND_LE, 8);
 
 	/* dereference TMP_REG_1 */
@@ -672,7 +672,7 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
 	 * if (tail_call_info == MAX_TAIL_CALL_CNT)
 	 *   goto out;
 	 */
-	EMIT(PPC_RAW_CMPLWI(bpf_to_ppc(TMP_REG_1), MAX_TAIL_CALL_CNT));
+	EMIT(PPC_RAW_CMPLDI(bpf_to_ppc(TMP_REG_1), MAX_TAIL_CALL_CNT));
 	PPC_BCC_SHORT(COND_EQ, out);
 
 	/*
@@ -707,7 +707,7 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
 	 * tail_call_info.
 	 */
 	EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_2), _R1, bpf_jit_stack_tailcallinfo_offset(ctx)));
-	EMIT(PPC_RAW_CMPLWI(bpf_to_ppc(TMP_REG_2), MAX_TAIL_CALL_CNT));
+	EMIT(PPC_RAW_CMPLDI(bpf_to_ppc(TMP_REG_2), MAX_TAIL_CALL_CNT));
 	PPC_BCC_CONST_SHORT(COND_GT, 8);
 
 	/* First get address of tail_call_info */
-- 
2.54.0

[PATCH v11 6/8] selftests/bpf: Add tailcall verifier selftest for powerpc64

[Saket Kumar Bhaskar]

From: Abhishek Dubey <adubey@linux.ibm.com>

Verifier testcase result for tailcalls:

Summary: 2/3 PASSED, 0 SKIPPED, 0 FAILED

Signed-off-by: Abhishek Dubey <adubey@linux.ibm.com>
Signed-off-by: Saket Kumar Bhaskar <skb99@linux.ibm.com>
Tested-by: Yeswanth Krishna Tellakula <yeswanth@linux.ibm.com>
---
 .../bpf/progs/verifier_tailcall_jit.c         | 75 +++++++++++++++++++
 1 file changed, 75 insertions(+)

diff --git a/tools/testing/selftests/bpf/progs/verifier_tailcall_jit.c b/tools/testing/selftests/bpf/progs/verifier_tailcall_jit.c
index 48fa34d2959f..182302ff1db0 100644
--- a/tools/testing/selftests/bpf/progs/verifier_tailcall_jit.c
+++ b/tools/testing/selftests/bpf/progs/verifier_tailcall_jit.c
@@ -91,6 +91,81 @@ __jited("	popq	%rax")
 __jited("	jmp	{{.*}}")		/* jump to tail call tgt   */
 __jited("L0:	leave")
 __jited("	{{(retq|jmp	0x)}}")		/* return or jump to rethunk */
+__arch_powerpc64
+/* program entry for main(), regular function prologue */
+__jited("	nop")
+__jited("...")                          /* ld 2, 16(13) absent with CONFIG_PPC_KERNEL_PCREL */
+__jited("	li 9, 0")
+__jited("	std 9, -8(1)")
+__jited("	mflr 0")
+__jited("	std 0, 16(1)")
+__jited("	stdu 1, {{.*}}(1)")
+/* load address and call sub() via count register
+ *
+ * Address materialization differs between PCREL and non-PCREL kernels.
+ * Skip the address generation sequence and verify only that the call
+ * target is loaded into CTR before branching.
+ */
+__jited("...")
+__jited("...")
+__jited("...")
+__jited("...")
+__jited("...")
+__jited("	mtctr 12")
+__jited("	bctrl")
+__jited("	mr	8, 3")
+__jited("	li 8, 0")
+__jited("	addi 1, 1, {{.*}}")
+__jited("	ld 0, 16(1)")
+__jited("	mtlr 0")
+__jited("	mr	3, 8")
+__jited("	blr")
+__jited("...")
+__jited("func #1")
+/* subprogram entry for sub() */
+__jited("	nop")
+__jited("...")                          /* ld 2, 16(13) absent with CONFIG_PPC_KERNEL_PCREL */
+/* tail call prologue for subprogram */
+__jited("	ld 10, 0(1)")
+__jited("	ld 9, -8(10)")
+__jited("	cmpldi	9, 33")
+__jited("	bt	{{.*}}, {{.*}}")
+__jited("	addi 9, 10, -8")
+__jited("	std 9, -8(1)")
+__jited("	lis {{.*}}, {{.*}}")
+__jited("	sldi {{.*}}, {{.*}}, 32")
+__jited("	oris {{.*}}, {{.*}}, {{.*}}")
+__jited("	ori {{.*}}, {{.*}}, {{.*}}")
+__jited("	li {{.*}}, 0")
+__jited("	lwz 9, {{.*}}({{.*}})")
+__jited("	slwi {{.*}}, {{.*}}, 0")
+__jited("	cmplw	{{.*}}, 9")
+__jited("	bf	0, {{.*}}")
+/* bpf_tail_call implementation */
+__jited("	ld 9, -8(1)")
+__jited("	cmpldi	9, 33")
+__jited("	bf	{{.*}}, {{.*}}")
+__jited("	ld 9, 0(9)")
+__jited("	cmpldi	9, 33")
+__jited("	bt	{{.*}}, {{.*}}")
+__jited("	addi 9, 9, 1")
+__jited("	mulli 10, {{.*}}, 8")
+__jited("	add 10, 10, {{.*}}")
+__jited("	ld 10, {{.*}}(10)")
+__jited("	cmpldi	10, 0")
+__jited("	bt	{{.*}}, {{.*}}")
+__jited("	ld 10, {{.*}}(10)")
+__jited("	addi 10, 10, {{.*}}")    /* offset depends on CONFIG_PPC_KERNEL_PCREL */
+__jited("	mtctr 10")
+__jited("	ld 10, -8(1)")
+__jited("	cmpldi	10, 33")
+__jited("	bt	{{.*}}, {{.*}}")
+__jited("	addi 10, 1, -8")
+__jited("	std 9, 0(10)")
+__jited("	bctr")
+__jited("	mr	3, 8")
+__jited("	blr")
+
 SEC("tc")
 __naked int main(void)
 {
-- 
2.54.0

Re: [PATCH v11 6/8] selftests/bpf: Add tailcall verifier selftest for powerpc64

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Low] Multi-line comment in the BPF subsystem does not follow the required style.
--

--- Patch [6]: [PATCH v11 6/8] selftests/bpf: Add tailcall verifier selftest for powerpc64 ---
commit db11673742dde393ab8f7429a8221e1b2ec5a904
Author: Abhishek Dubey <adubey@linux.ibm.com>

selftests/bpf: Add tailcall verifier selftest for powerpc64

This commit adds a BPF verifier tailcall JIT testcase for powerpc64 to
the selftests suite. It introduces the expected JIT instruction sequences
for tail calls on the architecture.

> diff --git a/tools/testing/selftests/bpf/progs/verifier_tailcall_jit.c b/tools/testing/selftests/bpf/progs/verifier_tailcall_jit.c
> index 48fa34d2959f4..182302ff1db07 100644
> --- a/tools/testing/selftests/bpf/progs/verifier_tailcall_jit.c
> +++ b/tools/testing/selftests/bpf/progs/verifier_tailcall_jit.c
> @@ -91,6 +91,81 @@ __jited("	popq	%rax")
[ ... ]
> +__jited("	std 9, -8(1)")
> +__jited("	mflr 0")
> +__jited("	std 0, 16(1)")
> +__jited("	stdu 1, {{.*}}(1)")
> +/* load address and call sub() via count register
> + *
> + * Address materialization differs between PCREL and non-PCREL kernels.
> + * Skip the address generation sequence and verify only that the call
> + * target is loaded into CTR before branching.
> + */

[Severity: Low]
Does this multi-line comment follow the modern BPF subsystem style rules?

The BPF subsystem style requires the opening /* of a multi-line comment
to be on its own line, rather than having text on the same line. Should
the comment start with a standalone /* to match the expected format?

[ ... ]

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/cover.1786099877.git.skb99@linux.ibm.com?part=6

[PATCH v11 7/8] powerpc/bpf: fix buffer overflow in JIT for large BPF programs

[Saket Kumar Bhaskar]

From: Abhishek Dubey <adubey@linux.ibm.com>

During size calculation in pass-0, exit_addr is 0 since addrs[fp->len]
is not yet populated. bpf_jit_emit_exit_insn() treats a zero exit_addr
as in-range and skips bpf_jit_build_epilogue(), so the alternate inline
epilogue instructions are not counted in alloclen.

In later passes, if the real exit_addr falls outside the 32MB branch
range, the full inline epilogue is emitted into the already-allocated
buffer, writing past its end and corrupting adjacent memory.

Fix by ensuring exit_addr is non-zero before treating it as in-range,
so pass-0 always falls through to bpf_jit_build_epilogue() and
conservatively accounts for all epilogue instructions in alloclen.
Also range check alt_exit_addr directly in the else-if condition.

Since exit_addr handling now falls through to the epilogue, two
related issues in bpf_int_jit_compile() must also be addressed:

1. Reset cgctx.alt_exit_addr before the second size-calculation pass.
   Without this, a stale alt_exit_addr from the first pass causes the
   second pass to emit a single jump instead of the full epilogue,
   undercounting alloclen and reintroducing the overflow.

2. Recompute addrs[fp->len] at the end of each code-generation pass.
   The larger pass-0 body can shrink in later passes as out-of-range
   exits settle into in-range jumps; a stale addrs[fp->len] would
   leave exit branches targeting past the real (shrunken) epilogue.

Because shrinkage in a later pass can move the epilogue offset, the
fixed two-pass loop is no longer sufficient: an exit that was out of
range in an earlier pass may fall in range once the epilogue offset
shrinks, shrinking the body further and overwriting the start of the
epilogue. Convert the code-generation loop to iterate until the
program size converges, bounded by CODEGEN_MAX_PASSES, and fail the
JIT if it does not converge.

Reported-by: sashiko-bot@kernel.org
Closes: https://lore.kernel.org/bpf/20260529015855.364704-2-adubey@linux.ibm.com/T/#mfcb23909d977b949727cca4f59ee56a13fd69b92
Fixes: d243b62b7bd3 ("powerpc64/bpf: Add support for bpf trampolines")
Cc: stable@vger.kernel.org
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Signed-off-by: Abhishek Dubey <adubey@linux.ibm.com>
Signed-off-by: Saket Kumar Bhaskar <skb99@linux.ibm.com>
Link: https://lore.kernel.org/bpf/20260529015855.364704-2-adubey@linux.ibm.com/T/#mfcb23909d977b949727cca4f59ee56a13fd69b92
Tested-by: Yeswanth Krishna Tellakula <yeswanth@linux.ibm.com>
---
 arch/powerpc/net/bpf_jit.h      |  7 +++++++
 arch/powerpc/net/bpf_jit_comp.c | 34 +++++++++++++++++++++++++--------
 2 files changed, 33 insertions(+), 8 deletions(-)

diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index af510da12d8e..4da8bde92e1e 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -14,6 +14,13 @@
 #include <asm/ppc-opcode.h>
 #include <linux/build_bug.h>
 
+/*
+ * We need at least 2 passes for proper code generation, and may need
+ * additional passes if code size changes between passes.
+ */
+#define CODEGEN_MIN_PASSES    2
+#define CODEGEN_MAX_PASSES    3
+
 #ifdef CONFIG_PPC64_ELF_ABI_V1
 #define FUNCTION_DESCR_SIZE	24
 #else
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 757b36bfbac3..2cc1124ed530 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -128,11 +128,10 @@ void bpf_jit_build_fentry_stubs(u32 *image, u32 *fimage, struct codegen_context
 int bpf_jit_emit_exit_insn(u32 *image, u32 *fimage, struct codegen_context *ctx,
 							int tmp_reg, long exit_addr)
 {
-	if (!exit_addr || is_offset_in_branch_range(exit_addr - (ctx->idx * 4))) {
+	if (exit_addr && is_offset_in_branch_range(exit_addr - (long)(ctx->idx * 4))) {
 		PPC_JMP(exit_addr);
-	} else if (ctx->alt_exit_addr) {
-		if (WARN_ON(!is_offset_in_branch_range((long)ctx->alt_exit_addr - (ctx->idx * 4))))
-			return -1;
+	} else if (ctx->alt_exit_addr && is_offset_in_branch_range(
+			(long)(ctx->alt_exit_addr) - (long)(ctx->idx * 4))) {
 		PPC_JMP(ctx->alt_exit_addr);
 	} else {
 		ctx->alt_exit_addr = ctx->idx * 4;
@@ -303,6 +302,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_pr
 	 */
 	if (cgctx.seen & SEEN_TAILCALL || !is_offset_in_branch_range((long)cgctx.idx * 4)) {
 		cgctx.idx = 0;
+		cgctx.alt_exit_addr = 0;
 		if (bpf_jit_build_body(fp, NULL, NULL, &cgctx, addrs, 0, false))
 			goto out_err;
 	}
@@ -335,10 +335,13 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_pr
 	code_base = (u32 *)(image + FUNCTION_DESCR_SIZE);
 	fcode_base = (u32 *)(fimage + FUNCTION_DESCR_SIZE);
 
-	/* Code generation passes 1-2 */
-	for (pass = 1; pass < 3; pass++) {
+	/* Code generation passes 1-2+, loop until program size converges. */
+	for (pass = 1; pass <= CODEGEN_MAX_PASSES; pass++) {
+		u32 prev_proglen = proglen;
+
 		/* Now build the prologue, body code & epilogue for real. */
 		cgctx.idx = 0;
+		cgctx.exentry_idx = 0;
 		cgctx.alt_exit_addr = 0;
 		bpf_jit_build_prologue(code_base, &cgctx);
 		if (bpf_jit_build_body(fp, code_base, fcode_base, &cgctx, addrs, pass,
@@ -347,11 +350,26 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_pr
 			bpf_jit_binary_pack_free(fhdr, hdr);
 			goto out_err;
 		}
+		addrs[fp->len] = cgctx.idx * 4;
 		bpf_jit_build_epilogue(code_base, fcode_base, &cgctx);
 
+		proglen = cgctx.idx * 4;
+
 		if (bpf_jit_enable > 1)
 			pr_info("Pass %d: shrink = %d, seen = 0x%x\n", pass,
-				proglen - (cgctx.idx * 4), cgctx.seen);
+				prev_proglen - proglen, cgctx.seen);
+
+		/* Check if program size has converged, but ensure minimum passes */
+		if (pass >= CODEGEN_MIN_PASSES && proglen == prev_proglen)
+			break;
+
+		if (pass == CODEGEN_MAX_PASSES && proglen != prev_proglen) {
+			pr_err("BPF JIT: Program did not converge after %d passes\n",
+								CODEGEN_MAX_PASSES);
+			bpf_arch_text_copy(&fhdr->size, &hdr->size, sizeof(hdr->size));
+			bpf_jit_binary_pack_free(fhdr, hdr);
+			goto out_err;
+		}
 	}
 
 	if (bpf_jit_enable > 1)
@@ -428,7 +446,7 @@ int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, u32 *fimage, int pass
 	u32 *fixup;
 
 	/* Populate extable entries only in the last pass */
-	if (pass != 2)
+	if (pass < CODEGEN_MIN_PASSES)
 		return 0;
 
 	if (!fp->aux->extable ||
-- 
2.54.0

Re: [PATCH v11 7/8] powerpc/bpf: fix buffer overflow in JIT for large BPF programs

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:

Pre-existing issues:
- [High] Silent branch offset truncation in exception table fixup generation.
--

--- Patch [7]: [PATCH v11 7/8] powerpc/bpf: fix buffer overflow in JIT for large BPF programs ---
commit 575dc92c1d10e63b9fc1ecf052e4cace5279974f
Author: Abhishek Dubey <adubey@linux.ibm.com>
Subject: powerpc/bpf: fix buffer overflow in JIT for large BPF programs

This commit fixes a buffer overflow during JIT compilation of large BPF
programs on PowerPC. It addresses an issue where the exit address was
unpopulated in the first pass, skipping the epilogue size calculation and
causing a buffer overflow in subsequent passes when the real exit address
required a full inline epilogue. The patch updates the multi-pass logic to
loop until the program size converges.

Link: https://lore.kernel.org/bpf/20260529015855.364704-2-adubey@linux.ibm.com/T/#mfcb23909d977b949727cca4f59ee56a13fd69b92

> diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
> index 757b36bfbac35..2cc1124ed5303 100644
> --- a/arch/powerpc/net/bpf_jit_comp.c
> +++ b/arch/powerpc/net/bpf_jit_comp.c

[ ... ]

> @@ -428,7 +446,7 @@ int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, u32 *fimage, int pass
>  	u32 *fixup;
>  
>  	/* Populate extable entries only in the last pass */
> -	if (pass != 2)
> +	if (pass < CODEGEN_MIN_PASSES)
>  		return 0;
>  
>  	if (!fp->aux->extable ||

[Severity: High]
This is a pre-existing issue, but since this patch explicitly targets
support for large BPF programs (exceeding the 32MB branch range), does the
exception table fixup generation also need an out-of-range branch check?

Looking at bpf_add_extable_entry() just below this hunk:

    fixup[BPF_FIXUP_LEN - 1] =
        PPC_RAW_BRANCH((long)(pc + jmp_off) - (long)&fixup[BPF_FIXUP_LEN - 1]);

Since PPC_RAW_BRANCH silently masks out-of-range offsets without returning
an error (unlike PPC_JMP which uses is_offset_in_branch_range()), could a
large BPF program with exception handlers result in a truncated branch
offset?

If a program has PROBE_MEM accesses and the offset between the fixup
routine and the main program exceeds 32MB, it seems the CPU might jump to
a corrupted address after handling the exception. Is it worth validating
the branch offset here as well?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/cover.1786099877.git.skb99@linux.ibm.com?part=7

[PATCH v11 8/8] powerpc64/bpf: fix percpu private stack leak on JIT failure

[Saket Kumar Bhaskar]

From: Abhishek Dubey <adubey@linux.ibm.com>

The existing conditional statement in bpf_int_jit_compile() frees the
percpu private stack at out_addrs only when the image buffer was never
allocated.

If bpf_jit_build_body() fails during a code-generation pass, the
image buffer has already been allocated, so !image is false and the
percpu stack is not freed.

Because JIT compilation failed, fp->jited remains at 0. The subsequent
bpf_jit_free() path only frees priv_stack_ptr when fp->jited is set, so
freeing is skipped here too, leaking the percpu allocation.

Fix implements freeing the private stack whenever fp->jited was not set,
i.e. compilation did not succeed, instead of keying off !image. !fp->jited
already covers the !image case, since image is only NULL on early-failure
paths where fp->jited is likewise 0.

Reported-by: sashiko-bot@kernel.org
Closes: https://lore.kernel.org/bpf/20260616135426.A06B71F000E9@smtp.kernel.org
Fixes: 156d985123b6 ("powerpc64/bpf: Implement JIT support for private stack")
Cc: stable@vger.kernel.org
Signed-off-by: Abhishek Dubey <adubey@linux.ibm.com>
Signed-off-by: Saket Kumar Bhaskar <skb99@linux.ibm.com>
Tested-by: Yeswanth Krishna Tellakula <yeswanth@linux.ibm.com>
Acked-by: Hari Bathini <hbathini@linux.ibm.com>
---
 arch/powerpc/net/bpf_jit_comp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 2cc1124ed530..395f1458db2e 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -404,7 +404,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_pr
 				(void *)fimage + FUNCTION_DESCR_SIZE);
 
 out_addrs:
-		if (!image && priv_stack_ptr) {
+		if (!fp->jited && priv_stack_ptr) {
 			fp->aux->priv_stack_ptr = NULL;
 			free_percpu(priv_stack_ptr);
 		}
-- 
2.54.0

Re: [PATCH v11 8/8] powerpc64/bpf: fix percpu private stack leak on JIT failure

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:

Pre-existing issues:
- [Critical] In `bpf_jit_binary_pack_finalize()`, if `bpf_arch_text_copy()` fails, it uses uninitialized `ro_header->size` to free the pack (causing bitmap corruption) and fails to uncharge modmem.
- [Critical] If `bpf_jit_binary_pack_finalize()` fails during `bpf_jit_free()`, the JIT memory pack is double-freed.
- [High] The ARM64 BPF JIT compiler has the exact same percpu private stack memory leak on failure paths that this patch fixes for PowerPC.
--

--- Patch [8]: [PATCH  v11 8/8] powerpc64/bpf: fix percpu private stack leak on JIT failure ---
commit e1be4be6e638db0714dd1f4ef6a5f98e6f888db6
Author: Abhishek Dubey <adubey@linux.ibm.com>

powerpc64/bpf: fix percpu private stack leak on JIT failure

The existing conditional statement in bpf_int_jit_compile() frees the
percpu private stack at out_addrs only when the image buffer was never
allocated.

Closes: https://lore.kernel.org/bpf/20260616135426.A06B71F000E9@smtp.kernel.org

> diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
> index 2cc1124ed5303..395f1458db2e6 100644
> --- a/arch/powerpc/net/bpf_jit_comp.c
> +++ b/arch/powerpc/net/bpf_jit_comp.c
> @@ -404,7 +404,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_pr
>  				(void *)fimage + FUNCTION_DESCR_SIZE);
>  
>  out_addrs:
> -		if (!image && priv_stack_ptr) {
> +		if (!fp->jited && priv_stack_ptr) {
>  			fp->aux->priv_stack_ptr = NULL;
>  			free_percpu(priv_stack_ptr);
>  		}

[Severity: High]
This isn't a bug introduced by this patch, but the ARM64 BPF JIT compiler
has the exact same percpu private stack memory leak on failure paths that
this patch addresses for PowerPC.

In arch/arm64/net/bpf_jit_comp.c:bpf_int_jit_compile():

    out_off:
		if (!ro_header && priv_stack_ptr) {
			free_percpu(priv_stack_ptr);
			prog->aux->priv_stack_ptr = NULL;
		}

On failure paths jumping from out_free_hdr, ro_header is not NULL, causing
the percpu stack free to be skipped. Could this also exhaust percpu memory
on ARM64?

[Severity: Critical]
This is a pre-existing issue, but if bpf_jit_binary_pack_finalize() fails
during bpf_jit_free(), does this double-free the JIT memory pack?

In arch/powerpc/net/bpf_jit_comp.c:bpf_jit_free():

		if (jit_data) {
			bpf_jit_binary_pack_finalize(jit_data->fhdr,
                                                     jit_data->hdr);
			kvfree(jit_data->addrs);
			kfree(jit_data);
		}
		hdr = bpf_jit_binary_pack_hdr(fp);
		bpf_jit_binary_pack_free(hdr, NULL);

If jit_subprogs() aborts early and calls bpf_jit_free() on subprograms,
bpf_jit_binary_pack_finalize() is called. If its internal text copy fails,
it internally frees ro_header. However, the return value of
bpf_jit_binary_pack_finalize() is ignored here, and bpf_jit_binary_pack_free()
is called again, which seems to double-free the same pack structure.

The same pattern appears to exist in arch/x86/net/bpf_jit_comp.c:bpf_jit_free()
as well.

[Severity: Critical]
This is a pre-existing issue, but does bpf_jit_binary_pack_finalize() use
uninitialized memory if bpf_arch_text_copy() fails?

In kernel/bpf/core.c:bpf_jit_binary_pack_finalize():

	if (IS_ERR(ptr)) {
		bpf_prog_pack_free(ro_header, ro_header->size);
		return PTR_ERR(ptr);
	}

If bpf_arch_text_copy() fails, ro_header->size has not been initialized.
Could this clear arbitrary memory regions in the shared pack allocator bitmap
and permanently leak the module memory charge since bpf_jit_uncharge_modmem()
is missing on this error path?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/cover.1786099877.git.skb99@linux.ibm.com?part=8