[PATCH 1/2] arm64: Support inlined clocksource reads for the arch counter

[David Woodhouse]

From: David Woodhouse <dwmw@xxxxxxxxxxxx>

Commit 2e27beeb66e43 ("timekeeping: Allow inlining clocksource::read()")
allows an architecture's clocksource::read() to be inlined, and was only
wired up for x86_64 thus far in commit b27801189f7fc ("x86: Inline TSC
reads in timekeeping").

Add the corresponding ARCH_WANTS_CLOCKSOURCE_READ_INLINE support for the
arm64 arch counter, allowing the indirect clock->read() call in the fast
paths to be replaced with a direct sysreg read. A static key selects
CNTPCT vs CNTVCT as appropriate, and the inline support is only
advertised for the plain (no erratum workaround) read paths.

Measured on a Cortex-A53 at 1.35GHz (12.5MHz arch counter): the
interval from a raw counter read in the caller to the counter read
inside ktime_get_real_ts64() drops from 30.2ns to 23.4ns, mean of 1M
iterations. Every ktime_get*() user of tk_clock_read() benefits
similarly. Except ktime_get_snapshot_id(), which I shall get to shortly.

Signed-off-by: David Woodhouse <dwmw@xxxxxxxxxxxx>
Assisted-by: LLM
---
 arch/arm64/Kconfig                     |  1 +
 arch/arm64/include/asm/clock_inlined.h | 26 ++++++++++++++++++++++++++
 drivers/clocksource/arm_arch_timer.c   | 21 +++++++++++++++++++++
 3 files changed, 48 insertions(+)
 create mode 100644 arch/arm64/include/asm/clock_inlined.h

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index b5a51b0ef944..25795b87cd41 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -94,6 +94,7 @@ config ARM64
 	select ARCH_WANT_FRAME_POINTERS
 	select ARCH_WANT_HUGE_PMD_SHARE if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36)
 	select ARCH_WANT_LD_ORPHAN_WARN
+	select ARCH_WANTS_CLOCKSOURCE_READ_INLINE
 	select ARCH_WANTS_EXECMEM_LATE
 	select ARCH_WANTS_NO_INSTR
 	select ARCH_WANTS_THP_SWAP if ARM64_4K_PAGES
diff --git a/arch/arm64/include/asm/clock_inlined.h b/arch/arm64/include/asm/clock_inlined.h
new file mode 100644
index 000000000000..fe997412bc7d
--- /dev/null
+++ b/arch/arm64/include/asm/clock_inlined.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_ARM64_CLOCK_INLINED_H
+#define _ASM_ARM64_CLOCK_INLINED_H
+
+#include <linux/jump_label.h>
+#include <asm/arch_timer.h>
+
+struct clocksource;
+
+/*
+ * Set by the arch timer driver when it selects the physical counter
+ * (kernel booted at EL2); otherwise the virtual counter is used. The
+ * driver only advertises CLOCK_SOURCE_CAN_INLINE_READ when it selected
+ * a plain (no erratum workaround) sysreg read matching this function.
+ */
+DECLARE_STATIC_KEY_FALSE(arch_timer_inline_read_pct);
+
+static __always_inline u64 arch_inlined_clocksource_read(struct clocksource *cs)
+{
+	if (static_branch_likely(&arch_timer_inline_read_pct))
+		return __arch_counter_get_cntpct();
+
+	return __arch_counter_get_cntvct();
+}
+
+#endif
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index cc9a8b399004..1c3d503d881a 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -133,6 +133,13 @@ static noinstr u64 arch_counter_get_cntvct(void)
 u64 (*arch_timer_read_counter)(void) __ro_after_init = arch_counter_get_cntvct;
 EXPORT_SYMBOL_GPL(arch_timer_read_counter);
 
+#ifdef CONFIG_ARM64
+#include <asm/clock_inlined.h>
+
+/* Selects CNTPCT in arch_inlined_clocksource_read() */
+DEFINE_STATIC_KEY_FALSE(arch_timer_inline_read_pct);
+#endif
+
 static u64 arch_counter_read(struct clocksource *cs)
 {
 	return arch_timer_read_counter();
@@ -917,6 +924,15 @@ static void __init arch_counter_register(void)
 		} else {
 			rd = arch_counter_get_cntvct;
 			scr = arch_counter_get_cntvct;
+			/*
+			 * A plain sysreg read with no erratum workaround
+			 * matches arch_inlined_clocksource_read(); allow the
+			 * core timekeeping code to bypass the indirect call.
+			 */
+#ifdef CONFIG_ARM64
+			clocksource_counter.flags |=
+				CLOCK_SOURCE_CAN_INLINE_READ;
+#endif
 		}
 	} else {
 		if (arch_timer_counter_has_wa()) {
@@ -925,6 +941,11 @@ static void __init arch_counter_register(void)
 		} else {
 			rd = arch_counter_get_cntpct;
 			scr = arch_counter_get_cntpct;
+#ifdef CONFIG_ARM64
+			static_branch_enable(&arch_timer_inline_read_pct);
+			clocksource_counter.flags |=
+				CLOCK_SOURCE_CAN_INLINE_READ;
+#endif
 		}
 	}
 
-- 
2.43.0