* Re: [PATCH v3 1/2] powerpc64/bpf: Implement JIT support for private stack
2026-02-26 0:54 [PATCH v3 1/2] powerpc64/bpf: Implement JIT support for private stack adubey
@ 2026-02-25 20:35 ` bot+bpf-ci
2026-02-26 0:54 ` [PATCH v3 2/2] selftests/bpf: Enable private stack tests for powerpc64 adubey
1 sibling, 0 replies; 3+ messages in thread
From: bot+bpf-ci @ 2026-02-25 20:35 UTC (permalink / raw)
To: adubey, linuxppc-dev
Cc: bpf, hbathini, ast, daniel, andrii, maddy, adubey, ast, andrii,
daniel, martin.lau, eddyz87, yonghong.song, clm, ihor.solodrai
[-- Attachment #1: Type: text/plain, Size: 4001 bytes --]
> diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
> --- a/arch/powerpc/net/bpf_jit_comp.c
> +++ b/arch/powerpc/net/bpf_jit_comp.c
[ ... ]
> @@ -209,6 +264,9 @@
> cgctx.is_subprog = bpf_is_subprog(fp);
> cgctx.exception_boundary = fp->aux->exception_boundary;
> cgctx.exception_cb = fp->aux->exception_cb;
> + cgctx.priv_sp = priv_stack_ptr;
> + if (priv_stack_ptr)
> + cgctx.stack_size = 0;
This zeros ctx->stack_size before the JIT passes, which is correct
for the kernel stack frame allocation (skipping BPF stack space on
the kernel stack).
However, emit_fp_priv_stack() also reads ctx->stack_size to compute
the BPF frame pointer offset within the private stack allocation:
> diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
> --- a/arch/powerpc/net/bpf_jit_comp64.c
> +++ b/arch/powerpc/net/bpf_jit_comp64.c
[ ... ]
> +static void emit_fp_priv_stack(u32 *image, struct codegen_context *ctx)
> +{
> + /* Load percpu data offset */
> + EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), _R13,
> + offsetof(struct paca_struct, data_offset)));
> + PPC_LI64(bpf_to_ppc(BPF_REG_FP), (__force long)ctx->priv_sp);
> + /*
> + * Load base percpu pointer of private stack allocation.
> + * Runtime per-cpu address = (base + data_offset) + (guard + stack_size)
> + */
> + EMIT(PPC_RAW_ADD(bpf_to_ppc(BPF_REG_FP),
> + bpf_to_ppc(TMP_REG_1), bpf_to_ppc(BPF_REG_FP)));
> + EMIT(PPC_RAW_ADDI(bpf_to_ppc(BPF_REG_FP), bpf_to_ppc(BPF_REG_FP),
> + PRIV_STACK_GUARD_SZ + round_up(ctx->stack_size, 16)));
> +}
Since ctx->stack_size was set to 0 earlier in bpf_int_jit_compile(),
the ADDI immediate here becomes PRIV_STACK_GUARD_SZ + 0 = 16.
This places BPF_REG_FP at the bottom of the usable stack area
(just past the overflow guard), rather than at the top.
The commit message describes the intended layout:
BPF frame pointer = Priv stack allocation start address +
Overflow guard +
Actual stack size defined by verifier
But the "Actual stack size defined by verifier" term is lost because
ctx->stack_size is already zero at this point.
BPF programs access the stack at FP-8, FP-16, etc. With FP at
offset 16 from the allocation base, FP-8 lands inside the overflow
guard and larger offsets go below the allocation entirely.
For comparison, x86 in do_jit() pre-computes the offset before
zeroing:
priv_frame_ptr = priv_stack_ptr + PRIV_STACK_GUARD_SZ +
round_up(stack_depth, 8);
stack_depth = 0;
And arm64 in build_prologue() does not zero ctx->stack_size at all,
instead using it directly:
priv_stack_ptr = prog->aux->priv_stack_ptr + PRIV_STACK_GUARD_SZ;
emit_percpu_ptr(priv_sp, priv_stack_ptr, ctx);
emit(A64_ADD_I(1, fp, priv_sp, ctx->stack_size), ctx);
The v1 of this patch also had it correct, pre-computing in
bpf_jit_build_prologue():
priv_frame_ptr = (void*) ctx->priv_sp + PRIV_STACK_GUARD_SZ +
round_up(ctx->stack_size, 16);
It appears the "Minor refactoring" in v1->v2 moved the
cgctx.stack_size = 0 earlier in the pipeline and removed the
pre-computation step, but did not account for emit_fp_priv_stack()
needing the original stack depth.
---
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/22413899411
AI-authorship-score: low
AI-authorship-explanation: Code follows established powerpc JIT patterns with architecture-specific constructs; commit history references specific CI-bot fixes consistent with human iterative development.
issues-found: 1
issue-severity-score: high
issue-severity-explanation: BPF frame pointer is miscalculated due to using zeroed ctx->stack_size in emit_fp_priv_stack(), causing all BPF stack accesses to write outside the allocated private stack region, resulting in memory corruption.
^ permalink raw reply [flat|nested] 3+ messages in thread
* [PATCH v3 1/2] powerpc64/bpf: Implement JIT support for private stack
@ 2026-02-26 0:54 adubey
2026-02-25 20:35 ` bot+bpf-ci
2026-02-26 0:54 ` [PATCH v3 2/2] selftests/bpf: Enable private stack tests for powerpc64 adubey
0 siblings, 2 replies; 3+ messages in thread
From: adubey @ 2026-02-26 0:54 UTC (permalink / raw)
To: linuxppc-dev; +Cc: bpf, hbathini, ast, daniel, andrii, maddy, Abhishek Dubey
From: Abhishek Dubey <adubey@linux.ibm.com>
Provision the private stack as a per-CPU allocation during
bpf_int_jit_compile(). Align the stack to 16 bytes and place guard
regions at both ends to detect runtime stack overflow and underflow.
Round the private stack size up to the nearest 16-byte boundary.
Make each guard region 16 bytes to preserve the required overall
16-byte alignment. When private stack is set, skip bpf stack size
accounting in kernel stack.
There is no stack pointer in powerpc. Stack referencing during JIT
is done using frame pointer. Frame pointer calculation goes like:
BPF frame pointer = Priv stack allocation start address +
Overflow guard +
Actual stack size defined by verifier
Memory layout:
High Addr +--------------------------------------------------+
| |
| 16 bytes Underflow guard (0xEB9F12345678eb9fULL) |
| |
BPF FP -> +--------------------------------------------------+
| |
| Private stack - determined by verifier |
| 16-bytes aligned |
| |
+--------------------------------------------------+
| |
Lower Addr | 16 byte Overflow guard (0xEB9F12345678eb9fULL) |
| |
Priv stack alloc ->+--------------------------------------------------+
start
Update BPF_REG_FP to point to the calculated offset within the
allocated private stack buffer. Now, BPF stack usage reference
in the allocated private stack.
The patch is rebase over fixes by Hari:
https://lore.kernel.org/bpf/20260220063933.196141-1-hbathini@linux.ibm.com/
v1->v2:
Fix ci-bot warning for percpu pointer casting
Minor refactoring
v2->v3:
Fix ci-bot bug targeting clobbered NVRs on stack rollback
[v2]: https://lore.kernel.org/bpf/20260225153950.15331-1-adubey@linux.ibm.com
[v1]: https://lore.kernel.org/bpf/20260216152234.36632-1-adubey@linux.ibm.com
Signed-off-by: Abhishek Dubey <adubey@linux.ibm.com>
---
arch/powerpc/net/bpf_jit.h | 5 ++
arch/powerpc/net/bpf_jit_comp.c | 87 +++++++++++++++++++++++++++++--
arch/powerpc/net/bpf_jit_comp64.c | 29 +++++++++--
3 files changed, 113 insertions(+), 8 deletions(-)
diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index 7354e1d72f79..eb0a400b5a98 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -178,8 +178,13 @@ struct codegen_context {
bool is_subprog;
bool exception_boundary;
bool exception_cb;
+ void __percpu *priv_sp;
};
+/* Memory size & magic-value to detect private stack overflow/underflow */
+#define PRIV_STACK_GUARD_SZ 16
+#define PRIV_STACK_GUARD_VAL 0xEB9F12345678eb9fULL
+
#define bpf_to_ppc(r) (ctx->b2p[r])
#ifdef CONFIG_PPC32
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 278e09b57560..adb2838bc653 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -129,25 +129,60 @@ bool bpf_jit_needs_zext(void)
return true;
}
+static void priv_stack_init_guard(void __percpu *priv_stack_ptr, int alloc_size)
+{
+ int cpu, underflow_idx = (alloc_size - PRIV_STACK_GUARD_SZ) >> 3;
+ u64 *stack_ptr;
+
+ for_each_possible_cpu(cpu) {
+ stack_ptr = per_cpu_ptr(priv_stack_ptr, cpu);
+ stack_ptr[0] = PRIV_STACK_GUARD_VAL;
+ stack_ptr[1] = PRIV_STACK_GUARD_VAL;
+ stack_ptr[underflow_idx] = PRIV_STACK_GUARD_VAL;
+ stack_ptr[underflow_idx + 1] = PRIV_STACK_GUARD_VAL;
+ }
+}
+
+static void priv_stack_check_guard(void __percpu *priv_stack_ptr, int alloc_size,
+ struct bpf_prog *fp)
+{
+ int cpu, underflow_idx = (alloc_size - PRIV_STACK_GUARD_SZ) >> 3;
+ u64 *stack_ptr;
+
+ for_each_possible_cpu(cpu) {
+ stack_ptr = per_cpu_ptr(priv_stack_ptr, cpu);
+ if (stack_ptr[0] != PRIV_STACK_GUARD_VAL ||
+ stack_ptr[1] != PRIV_STACK_GUARD_VAL ||
+ stack_ptr[underflow_idx] != PRIV_STACK_GUARD_VAL ||
+ stack_ptr[underflow_idx + 1] != PRIV_STACK_GUARD_VAL) {
+ pr_err("BPF private stack overflow/underflow detected for prog %s\n",
+ bpf_jit_get_prog_name(fp));
+ break;
+ }
+ }
+}
+
struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
{
u32 proglen;
u32 alloclen;
u8 *image = NULL;
- u32 *code_base;
- u32 *addrs;
- struct powerpc_jit_data *jit_data;
+ u32 *code_base = NULL;
+ u32 *addrs = NULL;
+ struct powerpc_jit_data *jit_data = NULL;
struct codegen_context cgctx;
int pass;
int flen;
+ int priv_stack_alloc_size;
+ void __percpu *priv_stack_ptr = NULL;
struct bpf_binary_header *fhdr = NULL;
struct bpf_binary_header *hdr = NULL;
struct bpf_prog *org_fp = fp;
- struct bpf_prog *tmp_fp;
+ struct bpf_prog *tmp_fp = NULL;
bool bpf_blinded = false;
bool extra_pass = false;
u8 *fimage = NULL;
- u32 *fcode_base;
+ u32 *fcode_base = NULL;
u32 extable_len;
u32 fixup_len;
@@ -173,6 +208,26 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
fp->aux->jit_data = jit_data;
}
+ priv_stack_ptr = fp->aux->priv_stack_ptr;
+ if (!priv_stack_ptr && fp->aux->jits_use_priv_stack) {
+ /*
+ * Allocate private stack of size equivalent to
+ * verifier-calculated stack size plus two memory
+ * guard regions to detect private stack overflow
+ * and underflow.
+ */
+ priv_stack_alloc_size = round_up(fp->aux->stack_depth, 16) +
+ 2 * PRIV_STACK_GUARD_SZ;
+ priv_stack_ptr = __alloc_percpu_gfp(priv_stack_alloc_size, 16, GFP_KERNEL);
+ if (!priv_stack_ptr) {
+ fp = org_fp;
+ goto out_priv_stack;
+ }
+
+ priv_stack_init_guard(priv_stack_ptr, priv_stack_alloc_size);
+ fp->aux->priv_stack_ptr = priv_stack_ptr;
+ }
+
flen = fp->len;
addrs = jit_data->addrs;
if (addrs) {
@@ -209,6 +264,9 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
cgctx.is_subprog = bpf_is_subprog(fp);
cgctx.exception_boundary = fp->aux->exception_boundary;
cgctx.exception_cb = fp->aux->exception_cb;
+ cgctx.priv_sp = priv_stack_ptr;
+ if (priv_stack_ptr)
+ cgctx.stack_size = 0;
/* Scouting faux-generate pass 0 */
if (bpf_jit_build_body(fp, NULL, NULL, &cgctx, addrs, 0, false)) {
@@ -306,6 +364,11 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
}
bpf_prog_fill_jited_linfo(fp, addrs);
out_addrs:
+ if (!image && priv_stack_ptr) {
+ fp->aux->priv_stack_ptr = NULL;
+ free_percpu(priv_stack_ptr);
+ }
+out_priv_stack:
kfree(addrs);
kfree(jit_data);
fp->aux->jit_data = NULL;
@@ -419,6 +482,8 @@ void bpf_jit_free(struct bpf_prog *fp)
if (fp->jited) {
struct powerpc_jit_data *jit_data = fp->aux->jit_data;
struct bpf_binary_header *hdr;
+ void __percpu *priv_stack_ptr;
+ int priv_stack_alloc_size;
/*
* If we fail the final pass of JIT (from jit_subprogs),
@@ -432,6 +497,13 @@ void bpf_jit_free(struct bpf_prog *fp)
}
hdr = bpf_jit_binary_pack_hdr(fp);
bpf_jit_binary_pack_free(hdr, NULL);
+ priv_stack_ptr = fp->aux->priv_stack_ptr;
+ if (priv_stack_ptr) {
+ priv_stack_alloc_size = round_up(fp->aux->stack_depth, 16) +
+ 2 * PRIV_STACK_GUARD_SZ;
+ priv_stack_check_guard(priv_stack_ptr, priv_stack_alloc_size, fp);
+ free_percpu(priv_stack_ptr);
+ }
WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(fp));
}
@@ -453,6 +525,11 @@ bool bpf_jit_supports_kfunc_call(void)
return true;
}
+bool bpf_jit_supports_private_stack(void)
+{
+ return IS_ENABLED(CONFIG_PPC64);
+}
+
bool bpf_jit_supports_arena(void)
{
return IS_ENABLED(CONFIG_PPC64);
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 640b84409687..65ab8b7a7f82 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -183,6 +183,22 @@ void bpf_jit_realloc_regs(struct codegen_context *ctx)
{
}
+static void emit_fp_priv_stack(u32 *image, struct codegen_context *ctx)
+{
+ /* Load percpu data offset */
+ EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), _R13,
+ offsetof(struct paca_struct, data_offset)));
+ PPC_LI64(bpf_to_ppc(BPF_REG_FP), (__force long)ctx->priv_sp);
+ /*
+ * Load base percpu pointer of private stack allocation.
+ * Runtime per-cpu address = (base + data_offset) + (guard + stack_size)
+ */
+ EMIT(PPC_RAW_ADD(bpf_to_ppc(BPF_REG_FP),
+ bpf_to_ppc(TMP_REG_1), bpf_to_ppc(BPF_REG_FP)));
+ EMIT(PPC_RAW_ADDI(bpf_to_ppc(BPF_REG_FP), bpf_to_ppc(BPF_REG_FP),
+ PRIV_STACK_GUARD_SZ + round_up(ctx->stack_size, 16)));
+}
+
/*
* For exception boundary & exception_cb progs:
* return increased size to accommodate additional NVRs.
@@ -307,9 +323,16 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
* Exception_cb not restricted from using stack area or arena.
* Setup frame pointer to point to the bpf stack area
*/
- if (bpf_is_seen_register(ctx, bpf_to_ppc(BPF_REG_FP)))
- EMIT(PPC_RAW_ADDI(bpf_to_ppc(BPF_REG_FP), _R1,
- STACK_FRAME_MIN_SIZE + ctx->stack_size));
+ if (bpf_is_seen_register(ctx, bpf_to_ppc(BPF_REG_FP))) {
+ if (ctx->priv_sp) {
+ /* Set up fp in private stack */
+ emit_fp_priv_stack(image, ctx);
+ } else {
+ /* Setup frame pointer to point to the bpf stack area */
+ EMIT(PPC_RAW_ADDI(bpf_to_ppc(BPF_REG_FP), _R1,
+ STACK_FRAME_MIN_SIZE + ctx->stack_size));
+ }
+ }
if (ctx->arena_vm_start)
PPC_LI64(bpf_to_ppc(ARENA_VM_START), ctx->arena_vm_start);
--
2.52.0
^ permalink raw reply related [flat|nested] 3+ messages in thread
* [PATCH v3 2/2] selftests/bpf: Enable private stack tests for powerpc64
2026-02-26 0:54 [PATCH v3 1/2] powerpc64/bpf: Implement JIT support for private stack adubey
2026-02-25 20:35 ` bot+bpf-ci
@ 2026-02-26 0:54 ` adubey
1 sibling, 0 replies; 3+ messages in thread
From: adubey @ 2026-02-26 0:54 UTC (permalink / raw)
To: linuxppc-dev; +Cc: bpf, hbathini, ast, daniel, andrii, maddy, Abhishek Dubey
From: Abhishek Dubey <adubey@linux.ibm.com>
With support of private stack, relevant tests must pass
on powerpc64.
#./test_progs -t struct_ops_private_stack
#434/1 struct_ops_private_stack/private_stack:OK
#434/2 struct_ops_private_stack/private_stack_fail:OK
#434/3 struct_ops_private_stack/private_stack_recur:OK
#434 struct_ops_private_stack:OK
Summary: 1/3 PASSED, 0 SKIPPED, 0 FAILED
v2->v3:
Enable testcase using __powerpc64__ instead of __TARGET_ARCH_powerpc,
to prevent it getting invoked on powerpc32
[v2]: https://lore.kernel.org/bpf/20260225153950.15331-1-adubey@linux.ibm.com
Signed-off-by: Abhishek Dubey <adubey@linux.ibm.com>
---
.../bpf/prog_tests/struct_ops_private_stack.c | 29 +++++++++----------
.../bpf/progs/struct_ops_private_stack.c | 6 ----
.../bpf/progs/struct_ops_private_stack_fail.c | 6 ----
.../progs/struct_ops_private_stack_recur.c | 6 ----
4 files changed, 13 insertions(+), 34 deletions(-)
diff --git a/tools/testing/selftests/bpf/prog_tests/struct_ops_private_stack.c b/tools/testing/selftests/bpf/prog_tests/struct_ops_private_stack.c
index 4006879ca3fe..afad3522b772 100644
--- a/tools/testing/selftests/bpf/prog_tests/struct_ops_private_stack.c
+++ b/tools/testing/selftests/bpf/prog_tests/struct_ops_private_stack.c
@@ -5,6 +5,7 @@
#include "struct_ops_private_stack_fail.skel.h"
#include "struct_ops_private_stack_recur.skel.h"
+#if defined(__x86_64__) || defined(__aarch64__) || defined(__powerpc64__)
static void test_private_stack(void)
{
struct struct_ops_private_stack *skel;
@@ -15,11 +16,6 @@ static void test_private_stack(void)
if (!ASSERT_OK_PTR(skel, "struct_ops_private_stack__open"))
return;
- if (skel->data->skip) {
- test__skip();
- goto cleanup;
- }
-
err = struct_ops_private_stack__load(skel);
if (!ASSERT_OK(err, "struct_ops_private_stack__load"))
goto cleanup;
@@ -48,11 +44,6 @@ static void test_private_stack_fail(void)
if (!ASSERT_OK_PTR(skel, "struct_ops_private_stack_fail__open"))
return;
- if (skel->data->skip) {
- test__skip();
- goto cleanup;
- }
-
err = struct_ops_private_stack_fail__load(skel);
if (!ASSERT_ERR(err, "struct_ops_private_stack_fail__load"))
goto cleanup;
@@ -72,11 +63,6 @@ static void test_private_stack_recur(void)
if (!ASSERT_OK_PTR(skel, "struct_ops_private_stack_recur__open"))
return;
- if (skel->data->skip) {
- test__skip();
- goto cleanup;
- }
-
err = struct_ops_private_stack_recur__load(skel);
if (!ASSERT_OK(err, "struct_ops_private_stack_recur__load"))
goto cleanup;
@@ -95,7 +81,7 @@ static void test_private_stack_recur(void)
struct_ops_private_stack_recur__destroy(skel);
}
-void test_struct_ops_private_stack(void)
+static void __test_struct_ops_private_stack(void)
{
if (test__start_subtest("private_stack"))
test_private_stack();
@@ -104,3 +90,14 @@ void test_struct_ops_private_stack(void)
if (test__start_subtest("private_stack_recur"))
test_private_stack_recur();
}
+#else
+static void __test_struct_ops_private_stack(void)
+{
+ test__skip();
+}
+#endif
+
+void test_struct_ops_private_stack(void)
+{
+ __test_struct_ops_private_stack();
+}
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_private_stack.c b/tools/testing/selftests/bpf/progs/struct_ops_private_stack.c
index dbe646013811..3cd0c1a55cbd 100644
--- a/tools/testing/selftests/bpf/progs/struct_ops_private_stack.c
+++ b/tools/testing/selftests/bpf/progs/struct_ops_private_stack.c
@@ -7,12 +7,6 @@
char _license[] SEC("license") = "GPL";
-#if defined(__TARGET_ARCH_x86) || defined(__TARGET_ARCH_arm64)
-bool skip __attribute((__section__(".data"))) = false;
-#else
-bool skip = true;
-#endif
-
void bpf_testmod_ops3_call_test_2(void) __ksym;
int val_i, val_j;
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_private_stack_fail.c b/tools/testing/selftests/bpf/progs/struct_ops_private_stack_fail.c
index 3d89ad7cbe2a..1442728f5604 100644
--- a/tools/testing/selftests/bpf/progs/struct_ops_private_stack_fail.c
+++ b/tools/testing/selftests/bpf/progs/struct_ops_private_stack_fail.c
@@ -7,12 +7,6 @@
char _license[] SEC("license") = "GPL";
-#if defined(__TARGET_ARCH_x86) || defined(__TARGET_ARCH_arm64)
-bool skip __attribute((__section__(".data"))) = false;
-#else
-bool skip = true;
-#endif
-
void bpf_testmod_ops3_call_test_2(void) __ksym;
int val_i, val_j;
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_private_stack_recur.c b/tools/testing/selftests/bpf/progs/struct_ops_private_stack_recur.c
index b1f6d7e5a8e5..faaa0f8d65a4 100644
--- a/tools/testing/selftests/bpf/progs/struct_ops_private_stack_recur.c
+++ b/tools/testing/selftests/bpf/progs/struct_ops_private_stack_recur.c
@@ -7,12 +7,6 @@
char _license[] SEC("license") = "GPL";
-#if defined(__TARGET_ARCH_x86) || defined(__TARGET_ARCH_arm64)
-bool skip __attribute((__section__(".data"))) = false;
-#else
-bool skip = true;
-#endif
-
void bpf_testmod_ops3_call_test_1(void) __ksym;
int val_i, val_j;
--
2.52.0
^ permalink raw reply related [flat|nested] 3+ messages in thread
end of thread, other threads:[~2026-02-25 20:35 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-02-26 0:54 [PATCH v3 1/2] powerpc64/bpf: Implement JIT support for private stack adubey
2026-02-25 20:35 ` bot+bpf-ci
2026-02-26 0:54 ` [PATCH v3 2/2] selftests/bpf: Enable private stack tests for powerpc64 adubey
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox