[bpf-next,v6,2/4] bpf: add bpf_cpu_cycles_to_ns helper

Commit Message

Vadim Fedorenko Nov. 15, 2024, 7:48 p.m. UTC

The new helper should be used to convert cycles received by
bpf_get_cpu_cycle() into nanoseconds.

Reviewed-by: Eduard Zingerman <[e-mail]>
Signed-off-by: Vadim Fedorenko <[e-mail]>
---
v4 -> v6:
* add comment about simplified implementation (Eduard)
v4:
* change helper name to bpf_cpu_cycles_to_ns.
* hide it behind CONFIG_GENERIC_GETTIMEOFDAY to avoid exposing on
  unsupported architectures.
---
 arch/x86/net/bpf_jit_comp.c   | 22 ++++++++++++++++++++++
 arch/x86/net/bpf_jit_comp32.c | 19 +++++++++++++++++++
 include/linux/bpf.h           |  1 +
 kernel/bpf/helpers.c          | 13 ++++++++++++-
 4 files changed, 54 insertions(+), 1 deletion(-)

Patch

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 107bd921f104..b87233d41a75 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -11,6 +11,7 @@ 
 #include <linux/bpf.h>
 #include <linux/memory.h>
 #include <linux/sort.h>
+#include <linux/clocksource.h>
 #include <asm/extable.h>
 #include <asm/ftrace.h>
 #include <asm/set_memory.h>
@@ -2216,6 +2217,24 @@  st:			if (is_imm8(insn->off))
 				break;
 			}
 
+			if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL &&
+			    imm32 == BPF_CALL_IMM(bpf_cpu_cycles_to_ns) &&
+			    boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
+				u32 mult, shift;
+
+				clocks_calc_mult_shift(&mult, &shift, tsc_khz, USEC_PER_SEC, 0);
+				/* imul RAX, RDI, mult */
+				maybe_emit_mod(&prog, BPF_REG_1, BPF_REG_0, true);
+				EMIT2_off32(0x69, add_2reg(0xC0, BPF_REG_1, BPF_REG_0),
+					    mult);
+
+				/* shr RAX, shift (which is less than 64) */
+				maybe_emit_1mod(&prog, BPF_REG_0, true);
+				EMIT3(0xC1, add_1reg(0xE8, BPF_REG_0), shift);
+
+				break;
+			}
+
 			func = (u8 *) __bpf_call_base + imm32;
 			if (src_reg == BPF_PSEUDO_CALL && tail_call_reachable) {
 				LOAD_TAIL_CALL_CNT_PTR(stack_depth);
@@ -3828,5 +3847,8 @@  bool bpf_jit_inlines_kfunc_call(s32 imm)
 {
 	if (imm == BPF_CALL_IMM(bpf_get_cpu_cycles))
 		return true;
+	if (imm == BPF_CALL_IMM(bpf_cpu_cycles_to_ns) &&
+	    boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
+		return true;
 	return false;
 }
diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c
index e6097a371b69..34f762f28c82 100644
--- a/arch/x86/net/bpf_jit_comp32.c
+++ b/arch/x86/net/bpf_jit_comp32.c
@@ -12,6 +12,7 @@ 
 #include <linux/netdevice.h>
 #include <linux/filter.h>
 #include <linux/if_vlan.h>
+#include <linux/clocksource.h>
 #include <asm/cacheflush.h>
 #include <asm/set_memory.h>
 #include <asm/nospec-branch.h>
@@ -2100,6 +2101,24 @@  static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 					EMIT2(0x0F, 0x31);
 					break;
 				}
+				if (imm32 == BPF_CALL_IMM(bpf_cpu_cycles_to_ns) &&
+				    boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
+					u32 mult, shift;
+
+					clocks_calc_mult_shift(&mult, &shift, tsc_khz,
+							       USEC_PER_SEC, 0);
+
+					/* move parameter to BPF_REG_0 */
+					emit_ia32_mov_r64(true, bpf2ia32[BPF_REG_0],
+							  bpf2ia32[BPF_REG_1], true, true,
+							  &prog, bpf_prog->aux);
+					/* multiply parameter by mut */
+					emit_ia32_mul_i64(bpf2ia32[BPF_REG_0],
+							  mult, true, &prog);
+					/* shift parameter by shift which is less than 64 */
+					emit_ia32_rsh_i64(bpf2ia32[BPF_REG_0],
+							  shift, true, &prog);
+				}
 
 				err = emit_kfunc_call(bpf_prog,
 						      image + addrs[i],
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 43a5207a1591..af47704afeaa 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -3336,6 +3336,7 @@  u64 bpf_get_raw_cpu_id(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 /* Inlined kfuncs */
 #if IS_ENABLED(CONFIG_GENERIC_GETTIMEOFDAY)
 u64 bpf_get_cpu_cycles(void);
+u64 bpf_cpu_cycles_to_ns(u64 cycles);
 #endif
 
 #if defined(CONFIG_NET)
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 12d40537e57b..e89eff53c340 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -3073,8 +3073,18 @@  __bpf_kfunc u64 bpf_get_cpu_cycles(void)
 	 */
 	return __arch_get_hw_counter(vd->clock_mode, vd);
 }
-#endif
 
+__bpf_kfunc u64 bpf_cpu_cycles_to_ns(u64 cycles)
+{
+	const struct vdso_data *vd = __arch_get_k_vdso_data();
+
+	/* kfunc implementation does less manipulations than vDSO
+	 * implementation. BPF use-case assumes two measurements are close
+	 * in time and can simplify the logic.
+	 */
+	return mul_u64_u32_shr(cycles, vd->mult, vd->shift);
+}
+#endif
 __bpf_kfunc_end_defs();
 
 BTF_KFUNCS_START(generic_btf_ids)
@@ -3169,6 +3179,7 @@  BTF_ID_FLAGS(func, bpf_iter_kmem_cache_next, KF_ITER_NEXT | KF_RET_NULL | KF_SLE
 BTF_ID_FLAGS(func, bpf_iter_kmem_cache_destroy, KF_ITER_DESTROY | KF_SLEEPABLE)
 #if IS_ENABLED(CONFIG_GENERIC_GETTIMEOFDAY)
 BTF_ID_FLAGS(func, bpf_get_cpu_cycles, KF_FASTCALL)
+BTF_ID_FLAGS(func, bpf_cpu_cycles_to_ns, KF_FASTCALL)
 #endif
 BTF_KFUNCS_END(common_btf_ids)