riscv, bpf: add internal-only MOV instruction to resolve per-CPU addrs

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/8dec900975efSigned-off-by: Puranjay Mohan <puranjay@kernel.org>
Acked-by: Björn Töpel <bjorn@kernel.org>
Link: https://lore.kernel.org/r/20240502151854.9810-2-puranjay@kernel.orgSigned-off-by: Alexei Starovoitov <ast@kernel.org>

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;
+}