[bpf-next,v6,1/4] riscv, bpf: add internal-only MOV instruction to resolve per-CPU addrs

Commit Message

Puranjay Mohan May 2, 2024, 3:18 p.m. UTC

Support an instruction for resolving absolute addresses of per-CPU
data from their per-CPU offsets. This instruction is internal-only and
users are not allowed to use them directly. They will only be used for
internal inlining optimizations for now between BPF verifier and BPF
JITs.

RISC-V uses generic per-cpu implementation where the offsets for CPUs
are kept in an array called __per_cpu_offset[cpu_number]. RISCV stores
the address of the task_struct in TP register. The first element in
task_struct is struct thread_info, and we can get the cpu number by
reading from the TP register + offsetof(struct thread_info, cpu).

Once we have the cpu number in a register we read the offset for that
cpu from address: &__per_cpu_offset + cpu_number << 3. Then we add this
offset to the destination register.

To measure the improvement from this change, the benchmark in [1] was
used on Qemu:

Before:
glob-arr-inc   :    1.127 ± 0.013M/s
arr-inc        :    1.121 ± 0.004M/s
hash-inc       :    0.681 ± 0.052M/s

After:
glob-arr-inc   :    1.138 ± 0.011M/s
arr-inc        :    1.366 ± 0.006M/s
hash-inc       :    0.676 ± 0.001M/s

[1] https://github.com/anakryiko/linux/commit/8dec900975ef

Signed-off-by: Puranjay Mohan <[e-mail]>
---
 arch/riscv/net/bpf_jit_comp64.c | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

Comments

Andrii Nakryiko May 7, 2024, 9:07 p.m. UTC | #1

On Thu, May 2, 2024 at 8:19 AM Puranjay Mohan <[e-mail]> wrote:
>
> Support an instruction for resolving absolute addresses of per-CPU
> data from their per-CPU offsets. This instruction is internal-only and
> users are not allowed to use them directly. They will only be used for
> internal inlining optimizations for now between BPF verifier and BPF
> JITs.
>
> RISC-V uses generic per-cpu implementation where the offsets for CPUs
> are kept in an array called __per_cpu_offset[cpu_number]. RISCV stores
> the address of the task_struct in TP register. The first element in
> task_struct is struct thread_info, and we can get the cpu number by
> reading from the TP register + offsetof(struct thread_info, cpu).
>
> Once we have the cpu number in a register we read the offset for that
> cpu from address: &__per_cpu_offset + cpu_number << 3. Then we add this
> offset to the destination register.
>
> To measure the improvement from this change, the benchmark in [1] was
> used on Qemu:
>
> Before:
> glob-arr-inc   :    1.127 ± 0.013M/s
> arr-inc        :    1.121 ± 0.004M/s
> hash-inc       :    0.681 ± 0.052M/s
>
> After:
> glob-arr-inc   :    1.138 ± 0.011M/s
> arr-inc        :    1.366 ± 0.006M/s
> hash-inc       :    0.676 ± 0.001M/s
>
> [1] https://github.com/anakryiko/linux/commit/8dec900975ef
>
> Signed-off-by: Puranjay Mohan <[e-mail]>
> ---
>  arch/riscv/net/bpf_jit_comp64.c | 24 ++++++++++++++++++++++++
>  1 file changed, 24 insertions(+)
>

Please carry over acks you got on previous revisions, unless you
significantly change something about the patch, invalidating previous
acks. You had Bjorn's ack on this one, I believe:

Acked-by: Björn Töpel <[e-mail]>


> diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
> index 15e482f2c657..1f0159963b3e 100644
> --- a/arch/riscv/net/bpf_jit_comp64.c
> +++ b/arch/riscv/net/bpf_jit_comp64.c
> @@ -12,6 +12,7 @@
>  #include <linux/stop_machine.h>
>  #include <asm/patch.h>
>  #include <asm/cfi.h>
> +#include <asm/percpu.h>
>  #include "bpf_jit.h"
>
>  #define RV_FENTRY_NINSNS 2
> @@ -1089,6 +1090,24 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
>                         emit_or(RV_REG_T1, rd, RV_REG_T1, ctx);
>                         emit_mv(rd, RV_REG_T1, ctx);
>                         break;
> +               } else if (insn_is_mov_percpu_addr(insn)) {
> +                       if (rd != rs)
> +                               emit_mv(rd, rs, ctx);
> +#ifdef CONFIG_SMP
> +                       /* Load current CPU number in T1 */
> +                       emit_ld(RV_REG_T1, offsetof(struct thread_info, cpu),
> +                               RV_REG_TP, ctx);
> +                       /* << 3 because offsets are 8 bytes */
> +                       emit_slli(RV_REG_T1, RV_REG_T1, 3, ctx);
> +                       /* Load address of __per_cpu_offset array in T2 */
> +                       emit_addr(RV_REG_T2, (u64)&__per_cpu_offset, extra_pass, ctx);
> +                       /* Add offset of current CPU to  __per_cpu_offset */
> +                       emit_add(RV_REG_T1, RV_REG_T2, RV_REG_T1, ctx);
> +                       /* Load __per_cpu_offset[cpu] in T1 */
> +                       emit_ld(RV_REG_T1, 0, RV_REG_T1, ctx);
> +                       /* Add the offset to Rd */
> +                       emit_add(rd, rd, RV_REG_T1, ctx);
> +#endif
>                 }
>                 if (imm == 1) {
>                         /* Special mov32 for zext */
> @@ -2038,3 +2057,8 @@ bool bpf_jit_supports_arena(void)
>  {
>         return true;
>  }
> +
> +bool bpf_jit_supports_percpu_insn(void)
> +{
> +       return true;
> +}
> --
> 2.40.1
>

Patch

diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 15e482f2c657..1f0159963b3e 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -12,6 +12,7 @@ 
 #include <linux/stop_machine.h>
 #include <asm/patch.h>
 #include <asm/cfi.h>
+#include <asm/percpu.h>
 #include "bpf_jit.h"
 
 #define RV_FENTRY_NINSNS 2
@@ -1089,6 +1090,24 @@  int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 			emit_or(RV_REG_T1, rd, RV_REG_T1, ctx);
 			emit_mv(rd, RV_REG_T1, ctx);
 			break;
+		} else if (insn_is_mov_percpu_addr(insn)) {
+			if (rd != rs)
+				emit_mv(rd, rs, ctx);
+#ifdef CONFIG_SMP
+			/* Load current CPU number in T1 */
+			emit_ld(RV_REG_T1, offsetof(struct thread_info, cpu),
+				RV_REG_TP, ctx);
+			/* << 3 because offsets are 8 bytes */
+			emit_slli(RV_REG_T1, RV_REG_T1, 3, ctx);
+			/* Load address of __per_cpu_offset array in T2 */
+			emit_addr(RV_REG_T2, (u64)&__per_cpu_offset, extra_pass, ctx);
+			/* Add offset of current CPU to  __per_cpu_offset */
+			emit_add(RV_REG_T1, RV_REG_T2, RV_REG_T1, ctx);
+			/* Load __per_cpu_offset[cpu] in T1 */
+			emit_ld(RV_REG_T1, 0, RV_REG_T1, ctx);
+			/* Add the offset to Rd */
+			emit_add(rd, rd, RV_REG_T1, ctx);
+#endif
 		}
 		if (imm == 1) {
 			/* Special mov32 for zext */
@@ -2038,3 +2057,8 @@  bool bpf_jit_supports_arena(void)
 {
 	return true;
 }
+
+bool bpf_jit_supports_percpu_insn(void)
+{
+	return true;
+}