From ba00d64643c53a0157b3ad066881e1d4d367154e Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 19 May 2023 12:21:02 +0200
Subject: [PATCH] arm64/arch_timer: Provide noinstr sched_clock_read()
 functions

References: bsc#1214683 (PREEMPT_RT prerequisite backports)
Patch-mainline: v6.5-rc1
Git-commit: 24ee7607b286b44a5112ced38652df14cd80d5e2

With the intent to provide local_clock_noinstr(), a variant of
local_clock() that's safe to be called from noinstr code (with the
assumption that any such code will already be non-preemptible),
prepare for things by providing a noinstr sched_clock_read() function.

Specifically, preempt_enable_*() calls out to schedule(), which upsets
noinstr validation efforts.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Michael Kelley <mikelley@microsoft.com>  # Hyper-V
Link: https://lore.kernel.org/r/20230519102715.435618812@infradead.org
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 arch/arm64/include/asm/arch_timer.h  |  8 +-----
 drivers/clocksource/arm_arch_timer.c | 54 ++++++++++++++++++++++++++----------
 2 files changed, 41 insertions(+), 21 deletions(-)

diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index af1fafbe7e1d..934c658ee947 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -88,13 +88,7 @@ static inline notrace u64 arch_timer_read_cntvct_el0(void)
 
 #define arch_timer_reg_read_stable(reg)					\
 	({								\
-		u64 _val;						\
-									\
-		preempt_disable_notrace();				\
-		_val = erratum_handler(read_ ## reg)();			\
-		preempt_enable_notrace();				\
-									\
-		_val;							\
+		erratum_handler(read_ ## reg)();			\
 	})
 
 /*
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index 6d15ed36cfa1..64491c30417f 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -191,22 +191,40 @@ u32 arch_timer_reg_read(int access, enum arch_timer_reg reg,
 	return val;
 }
 
-static notrace u64 arch_counter_get_cntpct_stable(void)
+static noinstr u64 raw_counter_get_cntpct_stable(void)
 {
 	return __arch_counter_get_cntpct_stable();
 }
 
-static notrace u64 arch_counter_get_cntpct(void)
+static notrace u64 arch_counter_get_cntpct_stable(void)
+{
+	u64 val;
+	preempt_disable_notrace();
+	val = __arch_counter_get_cntpct_stable();
+	preempt_enable_notrace();
+	return val;
+}
+
+static noinstr u64 arch_counter_get_cntpct(void)
 {
 	return __arch_counter_get_cntpct();
 }
 
-static notrace u64 arch_counter_get_cntvct_stable(void)
+static noinstr u64 raw_counter_get_cntvct_stable(void)
 {
 	return __arch_counter_get_cntvct_stable();
 }
 
-static notrace u64 arch_counter_get_cntvct(void)
+static notrace u64 arch_counter_get_cntvct_stable(void)
+{
+	u64 val;
+	preempt_disable_notrace();
+	val = __arch_counter_get_cntvct_stable();
+	preempt_enable_notrace();
+	return val;
+}
+
+static noinstr u64 arch_counter_get_cntvct(void)
 {
 	return __arch_counter_get_cntvct();
 }
@@ -753,14 +771,14 @@ static int arch_timer_set_next_event_phys(unsigned long evt,
 	return 0;
 }
 
-static u64 arch_counter_get_cnt_mem(struct arch_timer *t, int offset_lo)
+static noinstr u64 arch_counter_get_cnt_mem(struct arch_timer *t, int offset_lo)
 {
 	u32 cnt_lo, cnt_hi, tmp_hi;
 
 	do {
-		cnt_hi = readl_relaxed(t->base + offset_lo + 4);
-		cnt_lo = readl_relaxed(t->base + offset_lo);
-		tmp_hi = readl_relaxed(t->base + offset_lo + 4);
+		cnt_hi = __raw_readl(t->base + offset_lo + 4);
+		cnt_lo = __raw_readl(t->base + offset_lo);
+		tmp_hi = __raw_readl(t->base + offset_lo + 4);
 	} while (cnt_hi != tmp_hi);
 
 	return ((u64) cnt_hi << 32) | cnt_lo;
@@ -1068,7 +1086,7 @@ bool arch_timer_evtstrm_available(void)
 	return cpumask_test_cpu(raw_smp_processor_id(), &evtstrm_available);
 }
 
-static u64 arch_counter_get_cntvct_mem(void)
+static noinstr u64 arch_counter_get_cntvct_mem(void)
 {
 	return arch_counter_get_cnt_mem(arch_timer_mem, CNTVCT_LO);
 }
@@ -1082,6 +1100,7 @@ struct arch_timer_kvm_info *arch_timer_get_kvm_info(void)
 
 static void __init arch_counter_register(unsigned type)
 {
+	u64 (*scr)(void);
 	u64 start_count;
 	int width;
 
@@ -1091,21 +1110,28 @@ static void __init arch_counter_register(unsigned type)
 
 		if ((IS_ENABLED(CONFIG_ARM64) && !is_hyp_mode_available()) ||
 		    arch_timer_uses_ppi == ARCH_TIMER_VIRT_PPI) {
-			if (arch_timer_counter_has_wa())
+			if (arch_timer_counter_has_wa()) {
 				rd = arch_counter_get_cntvct_stable;
-			else
+				scr = raw_counter_get_cntvct_stable;
+			} else {
 				rd = arch_counter_get_cntvct;
+				scr = arch_counter_get_cntvct;
+			}
 		} else {
-			if (arch_timer_counter_has_wa())
+			if (arch_timer_counter_has_wa()) {
 				rd = arch_counter_get_cntpct_stable;
-			else
+				scr = raw_counter_get_cntpct_stable;
+			} else {
 				rd = arch_counter_get_cntpct;
+				scr = arch_counter_get_cntpct;
+			}
 		}
 
 		arch_timer_read_counter = rd;
 		clocksource_counter.vdso_clock_mode = vdso_default;
 	} else {
 		arch_timer_read_counter = arch_counter_get_cntvct_mem;
+		scr = arch_counter_get_cntvct_mem;
 	}
 
 	width = arch_counter_get_width();
@@ -1121,7 +1147,7 @@ static void __init arch_counter_register(unsigned type)
 	timecounter_init(&arch_timer_kvm_info.timecounter,
 			 &cyclecounter, start_count);
 
-	sched_clock_register(arch_timer_read_counter, width, arch_timer_rate);
+	sched_clock_register(scr, width, arch_timer_rate);
 }
 
 static void arch_timer_stop(struct clock_event_device *clk)