[bpf-next,v9,2/4] bpf: add bpf_cpu_time_counter_to_ns helper

Commit Message

Vadim Fedorenko Nov. 23, 2024, 12:58 a.m. UTC

The new helper should be used to convert deltas of values
received by bpf_get_cpu_time_counter() into nanoseconds. It is not
designed to do full conversion of time counter values to
CLOCK_MONOTONIC_RAW nanoseconds and cannot guarantee monotonicity of 2
independent values, but rather to convert the difference of 2 close
enough values of CPU timestamp counter into nanoseconds.

This function is also JITted into just several instructions and adds as
low overhead as possible and perfectly suits benchmark use-cases.

Reviewed-by: Eduard Zingerman <[e-mail]>
Acked-by: Andrii Nakryiko <[e-mail]>
Signed-off-by: Vadim Fedorenko <[e-mail]>
---
 arch/x86/net/bpf_jit_comp.c   | 27 +++++++++++++++++++++++++++
 arch/x86/net/bpf_jit_comp32.c | 27 +++++++++++++++++++++++++++
 include/linux/bpf.h           |  1 +
 kernel/bpf/helpers.c          | 14 +++++++++++++-
 4 files changed, 68 insertions(+), 1 deletion(-)

Patch

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 92431ab1a21e..d21e0ab55c94 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -11,10 +11,12 @@ 
 #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>
 #include <asm/nospec-branch.h>
+#include <asm/timer.h>
 #include <asm/text-patching.h>
 #include <asm/unwind.h>
 #include <asm/cfi.h>
@@ -2216,6 +2218,28 @@  st:			if (is_imm8(insn->off))
 				break;
 			}
 
+			if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL &&
+			    imm32 == BPF_CALL_IMM(bpf_cpu_time_counter_to_ns) &&
+			    using_native_sched_clock() && sched_clock_stable()) {
+				struct cyc2ns_data data;
+				u32 mult, shift;
+
+				cyc2ns_read_begin(&data);
+				mult = data.cyc2ns_mul;
+				shift = data.cyc2ns_shift;
+				cyc2ns_read_end();
+				/* 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 +3852,8 @@  bool bpf_jit_inlines_kfunc_call(s32 imm)
 {
 	if (imm == BPF_CALL_IMM(bpf_get_cpu_time_counter))
 		return true;
+	if (imm == BPF_CALL_IMM(bpf_cpu_time_counter_to_ns) &&
+	    using_native_sched_clock() && sched_clock_stable())
+		return true;
 	return false;
 }
diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c
index a549aea25f5f..a2069a3ee4a3 100644
--- a/arch/x86/net/bpf_jit_comp32.c
+++ b/arch/x86/net/bpf_jit_comp32.c
@@ -12,10 +12,12 @@ 
 #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>
 #include <asm/asm-prototypes.h>
+#include <asm/timer.h>
 #include <linux/bpf.h>
 
 /*
@@ -2100,6 +2102,27 @@  static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 					EMIT2(0x0F, 0x31);
 					break;
 				}
+				if (imm32 == BPF_CALL_IMM(bpf_cpu_time_counter_to_ns) &&
+				    cpu_feature_enabled(X86_FEATURE_CONSTANT_TSC)) {
+					struct cyc2ns_data data;
+					u32 mult, shift;
+
+					cyc2ns_read_begin(&data);
+					mult = data.cyc2ns_mul;
+					shift = data.cyc2ns_shift;
+					cyc2ns_read_end();
+
+					/* 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],
@@ -2633,5 +2656,9 @@  bool bpf_jit_inlines_kfunc_call(s32 imm)
 {
 	if (imm == BPF_CALL_IMM(bpf_get_cpu_time_counter))
 		return true;
+	if (imm == BPF_CALL_IMM(bpf_cpu_time_counter_to_ns) &&
+	    using_native_sched_clock() && sched_clock_stable())
+		return true;
+
 	return false;
 }
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 6d540253cfb4..dd3c4ddfd60e 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_time_counter(void);
+u64 bpf_cpu_time_counter_to_ns(u64 cycles);
 #endif
 
 #if defined(CONFIG_NET)
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 23f1a1606f8b..e4d461f2e98f 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -3079,8 +3079,19 @@  __bpf_kfunc u64 bpf_get_cpu_time_counter(void)
 	 */
 	return __arch_get_hw_counter(1, vd);
 }
-#endif
 
+__bpf_kfunc u64 bpf_cpu_time_counter_to_ns(u64 cycles)
+{
+	const struct vdso_data *vd = __arch_get_k_vdso_data();
+
+	vd = &vd[CS_RAW];
+	/* 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)
@@ -3175,6 +3186,7 @@  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_time_counter, KF_FASTCALL)
+BTF_ID_FLAGS(func, bpf_cpu_time_counter_to_ns, KF_FASTCALL)
 #endif
 BTF_KFUNCS_END(common_btf_ids)