diff mbox series

[bpf-next,v3,3/3] bpf: Use 64-bit return value for bpf_prog_run

Message ID 20221108140601.149971-4-toke@redhat.com (mailing list archive)
State Changes Requested
Delegated to: BPF
Headers show
Series A couple of small refactorings of BPF program call sites | expand

Checks

Context Check Description
netdev/tree_selection success Clearly marked for bpf-next, async
netdev/fixes_present success Fixes tag not required for -next series
netdev/subject_prefix success Link
netdev/cover_letter success Series has a cover letter
netdev/patch_count success Link
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 1362 this patch: 1362
netdev/cc_maintainers success CCed 17 of 17 maintainers
netdev/build_clang success Errors and warnings before: 157 this patch: 157
netdev/module_param success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 1352 this patch: 1352
netdev/checkpatch warning CHECK: Lines should not end with a '(' WARNING: line length of 83 exceeds 80 columns WARNING: line length of 85 exceeds 80 columns
netdev/kdoc success Errors and warnings before: 12 this patch: 12
netdev/source_inline success Was 0 now: 0
bpf/vmtest-bpf-next-PR success PR summary
bpf/vmtest-bpf-next-VM_Test-1 success Logs for ShellCheck
bpf/vmtest-bpf-next-VM_Test-3 success Logs for build for aarch64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-5 success Logs for build for x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-6 success Logs for build for x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-7 success Logs for llvm-toolchain
bpf/vmtest-bpf-next-VM_Test-8 success Logs for set-matrix
bpf/vmtest-bpf-next-VM_Test-2 success Logs for build for aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-4 success Logs for build for s390x with gcc
bpf/vmtest-bpf-next-VM_Test-9 success Logs for test_maps on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-10 success Logs for test_maps on aarch64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-12 success Logs for test_maps on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-13 success Logs for test_maps on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-14 success Logs for test_progs on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-15 success Logs for test_progs on aarch64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-17 success Logs for test_progs on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-18 success Logs for test_progs on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-19 fail Logs for test_progs_no_alu32 on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-20 success Logs for test_progs_no_alu32 on aarch64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-22 success Logs for test_progs_no_alu32 on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-23 success Logs for test_progs_no_alu32 on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-24 success Logs for test_progs_no_alu32_parallel on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-25 success Logs for test_progs_no_alu32_parallel on aarch64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-27 success Logs for test_progs_no_alu32_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-28 success Logs for test_progs_no_alu32_parallel on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-29 success Logs for test_progs_parallel on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-30 success Logs for test_progs_parallel on aarch64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-32 success Logs for test_progs_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-33 success Logs for test_progs_parallel on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-34 success Logs for test_verifier on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-35 success Logs for test_verifier on aarch64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-37 success Logs for test_verifier on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-38 success Logs for test_verifier on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-16 success Logs for test_progs on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-21 success Logs for test_progs_no_alu32 on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-26 success Logs for test_progs_no_alu32_parallel on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-36 success Logs for test_verifier on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-31 success Logs for test_progs_parallel on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-11 success Logs for test_maps on s390x with gcc

Commit Message

Toke Høiland-Jørgensen Nov. 8, 2022, 2:06 p.m. UTC 
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>

BPF ABI always uses 64-bit return value, but so far __bpf_prog_run and
higher level wrappers always truncated the return value to 32-bit. We
want to be able to introduce a new BPF program type that returns a
PTR_TO_BTF_ID or NULL from the BPF program to the caller context in the
kernel. To be able to use this returned pointer value, the bpf_prog_run
invocation needs to be able to return a 64-bit value, so update the
definitions to allow this.

To avoid code churn in the whole kernel, we let the compiler handle
truncation normally, and allow new call sites to utilize the 64-bit
return value, by receiving the return value as a u64.

Only the cgroup_bpf_lsm functions have been modified apart from the
generic bpf_prog_run wrappers, as their prototype needs to match
bpf_func_t to be called generically, but otherwise none of other cases
have been modified yet. It will be done when a specific call site
requires handling of the 64-bit return value from the BPF program.

Acked-by: Song Liu <song@kernel.org>
Reviewed-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
---
 include/linux/bpf-cgroup.h | 12 ++++++------
 include/linux/bpf.h        | 22 +++++++++++-----------
 include/linux/filter.h     | 30 +++++++++++++++---------------
 kernel/bpf/cgroup.c        | 12 ++++++------
 kernel/bpf/core.c          | 14 +++++++-------
 kernel/bpf/offload.c       |  4 ++--
 net/packet/af_packet.c     |  7 +++++--
 7 files changed, 52 insertions(+), 49 deletions(-)

Comments

Alexei Starovoitov Nov. 15, 2022, 5:09 p.m. UTC | #1 
On Tue, Nov 8, 2022 at 6:07 AM Toke Høiland-Jørgensen <toke@redhat.com> wrote:
>
> From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
>
> BPF ABI always uses 64-bit return value, but so far __bpf_prog_run and
> higher level wrappers always truncated the return value to 32-bit. We
> want to be able to introduce a new BPF program type that returns a
> PTR_TO_BTF_ID or NULL from the BPF program to the caller context in the
> kernel. To be able to use this returned pointer value, the bpf_prog_run
> invocation needs to be able to return a 64-bit value, so update the
> definitions to allow this.

...

> -static __always_inline u32 __bpf_prog_run(const struct bpf_prog *prog,
> +static __always_inline u64 __bpf_prog_run(const struct bpf_prog *prog,
>                                           const void *ctx,
>                                           bpf_dispatcher_fn dfunc)
>  {
> -       u32 ret;
> +       u64 ret;
>
>         cant_migrate();
>         if (static_branch_unlikely(&bpf_stats_enabled_key)) {
> @@ -602,7 +602,7 @@ static __always_inline u32 __bpf_prog_run(const struct bpf_prog *prog,
>         return ret;
>  }
>
> -static __always_inline u32 bpf_prog_run(const struct bpf_prog *prog, const void *ctx)
> +static __always_inline u64 bpf_prog_run(const struct bpf_prog *prog, const void *ctx)
>  {
>         return __bpf_prog_run(prog, ctx, bpf_dispatcher_nop_func);
>  }

I suspect 32-bit archs with JITs are partially broken with this change.
As long as progs want to return pointers it's ok, but actual
64-bit values will be return garbage in upper 32-bit, since 32-bit
JITs won't populate the upper bits.
I don't think changing u32->long retval is a good idea either,
since BPF ISA has to be stable regardless of underlying arch.
The u32->u64 transition is good long term, but let's add
full 64-bit tests to lib/test_bpf and fix JITs.

I've applied the first two patches of the series.
Kumar Kartikeya Dwivedi Nov. 15, 2022, 7:39 p.m. UTC | #2 
On Tue, Nov 15, 2022 at 10:39:04PM IST, Alexei Starovoitov wrote:
> On Tue, Nov 8, 2022 at 6:07 AM Toke Høiland-Jørgensen <toke@redhat.com> wrote:
> >
> > From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
> >
> > BPF ABI always uses 64-bit return value, but so far __bpf_prog_run and
> > higher level wrappers always truncated the return value to 32-bit. We
> > want to be able to introduce a new BPF program type that returns a
> > PTR_TO_BTF_ID or NULL from the BPF program to the caller context in the
> > kernel. To be able to use this returned pointer value, the bpf_prog_run
> > invocation needs to be able to return a 64-bit value, so update the
> > definitions to allow this.
>
> ...
>
> > -static __always_inline u32 __bpf_prog_run(const struct bpf_prog *prog,
> > +static __always_inline u64 __bpf_prog_run(const struct bpf_prog *prog,
> >                                           const void *ctx,
> >                                           bpf_dispatcher_fn dfunc)
> >  {
> > -       u32 ret;
> > +       u64 ret;
> >
> >         cant_migrate();
> >         if (static_branch_unlikely(&bpf_stats_enabled_key)) {
> > @@ -602,7 +602,7 @@ static __always_inline u32 __bpf_prog_run(const struct bpf_prog *prog,
> >         return ret;
> >  }
> >
> > -static __always_inline u32 bpf_prog_run(const struct bpf_prog *prog, const void *ctx)
> > +static __always_inline u64 bpf_prog_run(const struct bpf_prog *prog, const void *ctx)
> >  {
> >         return __bpf_prog_run(prog, ctx, bpf_dispatcher_nop_func);
> >  }
>
> I suspect 32-bit archs with JITs are partially broken with this change.
> As long as progs want to return pointers it's ok, but actual
> 64-bit values will be return garbage in upper 32-bit, since 32-bit
> JITs won't populate the upper bits.
> I don't think changing u32->long retval is a good idea either,
> since BPF ISA has to be stable regardless of underlying arch.
> The u32->u64 transition is good long term, but let's add
> full 64-bit tests to lib/test_bpf and fix JITs.
>

I will resubmit with these tests and revisiting the 32-bit JITs (but it will
take some time, since my backlog is full).
diff mbox series

Patch

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 57e9e109257e..85ae187e5d41 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -23,12 +23,12 @@  struct ctl_table;
 struct ctl_table_header;
 struct task_struct;
 
-unsigned int __cgroup_bpf_run_lsm_sock(const void *ctx,
-				       const struct bpf_insn *insn);
-unsigned int __cgroup_bpf_run_lsm_socket(const void *ctx,
-					 const struct bpf_insn *insn);
-unsigned int __cgroup_bpf_run_lsm_current(const void *ctx,
-					  const struct bpf_insn *insn);
+u64 __cgroup_bpf_run_lsm_sock(const void *ctx,
+			      const struct bpf_insn *insn);
+u64 __cgroup_bpf_run_lsm_socket(const void *ctx,
+				const struct bpf_insn *insn);
+u64 __cgroup_bpf_run_lsm_current(const void *ctx,
+				 const struct bpf_insn *insn);
 
 #ifdef CONFIG_CGROUP_BPF
 
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 863a5db1e370..8f1190a0fc62 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -59,8 +59,8 @@  typedef u64 (*bpf_callback_t)(u64, u64, u64, u64, u64);
 typedef int (*bpf_iter_init_seq_priv_t)(void *private_data,
 					struct bpf_iter_aux_info *aux);
 typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data);
-typedef unsigned int (*bpf_func_t)(const void *,
-				   const struct bpf_insn *);
+typedef u64 (*bpf_func_t)(const void *,
+			  const struct bpf_insn *);
 struct bpf_iter_seq_info {
 	const struct seq_operations *seq_ops;
 	bpf_iter_init_seq_priv_t init_seq_private;
@@ -1004,7 +1004,7 @@  struct bpf_dispatcher {
 	struct bpf_ksym ksym;
 };
 
-static __always_inline __nocfi unsigned int bpf_dispatcher_nop_func(
+static __always_inline __nocfi u64 bpf_dispatcher_nop_func(
 	const void *ctx,
 	const struct bpf_insn *insnsi,
 	bpf_func_t bpf_func)
@@ -1049,7 +1049,7 @@  int __init bpf_arch_init_dispatcher_early(void *ip);
 
 #define DEFINE_BPF_DISPATCHER(name)					\
 	notrace BPF_DISPATCHER_ATTRIBUTES				\
-	noinline __nocfi unsigned int bpf_dispatcher_##name##_func(	\
+	noinline __nocfi u64 bpf_dispatcher_##name##_func(		\
 		const void *ctx,					\
 		const struct bpf_insn *insnsi,				\
 		bpf_func_t bpf_func)					\
@@ -1062,7 +1062,7 @@  int __init bpf_arch_init_dispatcher_early(void *ip);
 	BPF_DISPATCHER_INIT_CALL(bpf_dispatcher_##name);
 
 #define DECLARE_BPF_DISPATCHER(name)					\
-	unsigned int bpf_dispatcher_##name##_func(			\
+	u64 bpf_dispatcher_##name##_func(				\
 		const void *ctx,					\
 		const struct bpf_insn *insnsi,				\
 		bpf_func_t bpf_func);					\
@@ -1265,7 +1265,7 @@  struct bpf_prog {
 	u8			tag[BPF_TAG_SIZE];
 	struct bpf_prog_stats __percpu *stats;
 	int __percpu		*active;
-	unsigned int		(*bpf_func)(const void *ctx,
+	u64			(*bpf_func)(const void *ctx,
 					    const struct bpf_insn *insn);
 	struct bpf_prog_aux	*aux;		/* Auxiliary fields */
 	struct sock_fprog_kern	*orig_prog;	/* Original BPF program */
@@ -1619,9 +1619,9 @@  static inline void bpf_reset_run_ctx(struct bpf_run_ctx *old_ctx)
 /* BPF program asks to set CN on the packet. */
 #define BPF_RET_SET_CN						(1 << 0)
 
-typedef u32 (*bpf_prog_run_fn)(const struct bpf_prog *prog, const void *ctx);
+typedef u64 (*bpf_prog_run_fn)(const struct bpf_prog *prog, const void *ctx);
 
-static __always_inline u32
+static __always_inline u64
 bpf_prog_run_array(const struct bpf_prog_array *array,
 		   const void *ctx, bpf_prog_run_fn run_prog)
 {
@@ -1629,7 +1629,7 @@  bpf_prog_run_array(const struct bpf_prog_array *array,
 	const struct bpf_prog *prog;
 	struct bpf_run_ctx *old_run_ctx;
 	struct bpf_trace_run_ctx run_ctx;
-	u32 ret = 1;
+	u64 ret = 1;
 
 	RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "no rcu lock held");
 
@@ -1659,7 +1659,7 @@  bpf_prog_run_array(const struct bpf_prog_array *array,
  * section and disable preemption for that program alone, so it can access
  * rcu-protected dynamically sized maps.
  */
-static __always_inline u32
+static __always_inline u64
 bpf_prog_run_array_sleepable(const struct bpf_prog_array __rcu *array_rcu,
 			     const void *ctx, bpf_prog_run_fn run_prog)
 {
@@ -1668,7 +1668,7 @@  bpf_prog_run_array_sleepable(const struct bpf_prog_array __rcu *array_rcu,
 	const struct bpf_prog_array *array;
 	struct bpf_run_ctx *old_run_ctx;
 	struct bpf_trace_run_ctx run_ctx;
-	u32 ret = 1;
+	u64 ret = 1;
 
 	might_fault();
 
diff --git a/include/linux/filter.h b/include/linux/filter.h
index e6c1c277ffdc..d67d3e6a2f58 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -573,16 +573,16 @@  extern int (*nfct_btf_struct_access)(struct bpf_verifier_log *log, const struct
 				     enum bpf_access_type atype, u32 *next_btf_id,
 				     enum bpf_type_flag *flag);
 
-typedef unsigned int (*bpf_dispatcher_fn)(const void *ctx,
-					  const struct bpf_insn *insnsi,
-					  unsigned int (*bpf_func)(const void *,
-								   const struct bpf_insn *));
+typedef u64 (*bpf_dispatcher_fn)(const void *ctx,
+				 const struct bpf_insn *insnsi,
+				 u64 (*bpf_func)(const void *,
+						 const struct bpf_insn *));
 
-static __always_inline u32 __bpf_prog_run(const struct bpf_prog *prog,
+static __always_inline u64 __bpf_prog_run(const struct bpf_prog *prog,
 					  const void *ctx,
 					  bpf_dispatcher_fn dfunc)
 {
-	u32 ret;
+	u64 ret;
 
 	cant_migrate();
 	if (static_branch_unlikely(&bpf_stats_enabled_key)) {
@@ -602,7 +602,7 @@  static __always_inline u32 __bpf_prog_run(const struct bpf_prog *prog,
 	return ret;
 }
 
-static __always_inline u32 bpf_prog_run(const struct bpf_prog *prog, const void *ctx)
+static __always_inline u64 bpf_prog_run(const struct bpf_prog *prog, const void *ctx)
 {
 	return __bpf_prog_run(prog, ctx, bpf_dispatcher_nop_func);
 }
@@ -615,10 +615,10 @@  static __always_inline u32 bpf_prog_run(const struct bpf_prog *prog, const void
  * invocation of a BPF program does not require reentrancy protection
  * against a BPF program which is invoked from a preempting task.
  */
-static inline u32 bpf_prog_run_pin_on_cpu(const struct bpf_prog *prog,
+static inline u64 bpf_prog_run_pin_on_cpu(const struct bpf_prog *prog,
 					  const void *ctx)
 {
-	u32 ret;
+	u64 ret;
 
 	migrate_disable();
 	ret = bpf_prog_run(prog, ctx);
@@ -714,13 +714,13 @@  static inline u8 *bpf_skb_cb(const struct sk_buff *skb)
 }
 
 /* Must be invoked with migration disabled */
-static inline u32 __bpf_prog_run_save_cb(const struct bpf_prog *prog,
+static inline u64 __bpf_prog_run_save_cb(const struct bpf_prog *prog,
 					 const void *ctx)
 {
 	const struct sk_buff *skb = ctx;
 	u8 *cb_data = bpf_skb_cb(skb);
 	u8 cb_saved[BPF_SKB_CB_LEN];
-	u32 res;
+	u64 res;
 
 	if (unlikely(prog->cb_access)) {
 		memcpy(cb_saved, cb_data, sizeof(cb_saved));
@@ -735,10 +735,10 @@  static inline u32 __bpf_prog_run_save_cb(const struct bpf_prog *prog,
 	return res;
 }
 
-static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog,
+static inline u64 bpf_prog_run_save_cb(const struct bpf_prog *prog,
 				       struct sk_buff *skb)
 {
-	u32 res;
+	u64 res;
 
 	migrate_disable();
 	res = __bpf_prog_run_save_cb(prog, skb);
@@ -746,11 +746,11 @@  static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog,
 	return res;
 }
 
-static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog,
+static inline u64 bpf_prog_run_clear_cb(const struct bpf_prog *prog,
 					struct sk_buff *skb)
 {
 	u8 *cb_data = bpf_skb_cb(skb);
-	u32 res;
+	u64 res;
 
 	if (unlikely(prog->cb_access))
 		memset(cb_data, 0, BPF_SKB_CB_LEN);
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index bf2fdb33fb31..b78a51513431 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -63,8 +63,8 @@  bpf_prog_run_array_cg(const struct cgroup_bpf *cgrp,
 	return run_ctx.retval;
 }
 
-unsigned int __cgroup_bpf_run_lsm_sock(const void *ctx,
-				       const struct bpf_insn *insn)
+u64 __cgroup_bpf_run_lsm_sock(const void *ctx,
+			      const struct bpf_insn *insn)
 {
 	const struct bpf_prog *shim_prog;
 	struct sock *sk;
@@ -85,8 +85,8 @@  unsigned int __cgroup_bpf_run_lsm_sock(const void *ctx,
 	return ret;
 }
 
-unsigned int __cgroup_bpf_run_lsm_socket(const void *ctx,
-					 const struct bpf_insn *insn)
+u64 __cgroup_bpf_run_lsm_socket(const void *ctx,
+				const struct bpf_insn *insn)
 {
 	const struct bpf_prog *shim_prog;
 	struct socket *sock;
@@ -107,8 +107,8 @@  unsigned int __cgroup_bpf_run_lsm_socket(const void *ctx,
 	return ret;
 }
 
-unsigned int __cgroup_bpf_run_lsm_current(const void *ctx,
-					  const struct bpf_insn *insn)
+u64 __cgroup_bpf_run_lsm_current(const void *ctx,
+				 const struct bpf_insn *insn)
 {
 	const struct bpf_prog *shim_prog;
 	struct cgroup *cgrp;
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 9c16338bcbe8..bc4ca1e6a990 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2004,7 +2004,7 @@  static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn)
 
 #define PROG_NAME(stack_size) __bpf_prog_run##stack_size
 #define DEFINE_BPF_PROG_RUN(stack_size) \
-static unsigned int PROG_NAME(stack_size)(const void *ctx, const struct bpf_insn *insn) \
+static u64 PROG_NAME(stack_size)(const void *ctx, const struct bpf_insn *insn) \
 { \
 	u64 stack[stack_size / sizeof(u64)]; \
 	u64 regs[MAX_BPF_EXT_REG] = {}; \
@@ -2048,8 +2048,8 @@  EVAL4(DEFINE_BPF_PROG_RUN_ARGS, 416, 448, 480, 512);
 
 #define PROG_NAME_LIST(stack_size) PROG_NAME(stack_size),
 
-static unsigned int (*interpreters[])(const void *ctx,
-				      const struct bpf_insn *insn) = {
+static u64 (*interpreters[])(const void *ctx,
+			     const struct bpf_insn *insn) = {
 EVAL6(PROG_NAME_LIST, 32, 64, 96, 128, 160, 192)
 EVAL6(PROG_NAME_LIST, 224, 256, 288, 320, 352, 384)
 EVAL4(PROG_NAME_LIST, 416, 448, 480, 512)
@@ -2074,8 +2074,8 @@  void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth)
 }
 
 #else
-static unsigned int __bpf_prog_ret0_warn(const void *ctx,
-					 const struct bpf_insn *insn)
+static u64 __bpf_prog_ret0_warn(const void *ctx,
+				const struct bpf_insn *insn)
 {
 	/* If this handler ever gets executed, then BPF_JIT_ALWAYS_ON
 	 * is not working properly, so warn about it!
@@ -2210,8 +2210,8 @@  struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 }
 EXPORT_SYMBOL_GPL(bpf_prog_select_runtime);
 
-static unsigned int __bpf_prog_ret1(const void *ctx,
-				    const struct bpf_insn *insn)
+static u64 __bpf_prog_ret1(const void *ctx,
+			   const struct bpf_insn *insn)
 {
 	return 1;
 }
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 13e4efc971e6..d6a37ab87511 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -246,8 +246,8 @@  static int bpf_prog_offload_translate(struct bpf_prog *prog)
 	return ret;
 }
 
-static unsigned int bpf_prog_warn_on_exec(const void *ctx,
-					  const struct bpf_insn *insn)
+static u64 bpf_prog_warn_on_exec(const void *ctx,
+				 const struct bpf_insn *insn)
 {
 	WARN(1, "attempt to execute device eBPF program on the host!");
 	return 0;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 44f20cf8a0c0..2f61f2889e52 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1444,8 +1444,11 @@  static unsigned int fanout_demux_bpf(struct packet_fanout *f,
 
 	rcu_read_lock();
 	prog = rcu_dereference(f->bpf_prog);
-	if (prog)
-		ret = bpf_prog_run_clear_cb(prog, skb) % num;
+	if (prog) {
+		ret = bpf_prog_run_clear_cb(prog, skb);
+		/* For some architectures, we need to do modulus in 32-bit width */
+		ret %= num;
+	}
 	rcu_read_unlock();
 
 	return ret;