[PATCH v4 21/22] arm64: Delay enabling hardware DBM feature

[Suzuki K Poulose]

We enable hardware DBM bit in a capable CPU, very early in the
boot via __cpu_setup. This doesn't give us a flexibility of
optionally disable the feature, as the clearing the bit
is a bit costly as the TLB can cache the settings. Instead,
we delay enabling the feature until the CPU is brought up
into the kernel. We use the feature capability mechanism
to handle it.

The hardware DBM is a non-conflicting feature. i.e, the kernel
can safely run with a mix of CPUs with some using the feature
and the others don't. So, it is safe for a late CPU to have
this capability and enable it, even if the active CPUs don't.

To get this handled properly by the infrastructure, we
unconditionally set the capability and only enable it
on CPUs which really have the feature. Also, we print the
feature detection from the "matches" call back to make sure
we don't mislead the user when none of the CPUs could use the
feature.

Cc: Catalin Marinas <catalin.marinas@xxxxxxx>
Cc: Dave Martin <dave.martin@xxxxxxx>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@xxxxxxx>
---
 arch/arm64/include/asm/cpucaps.h |  3 +-
 arch/arm64/kernel/cpufeature.c   | 71 ++++++++++++++++++++++++++++++++++++++++
 arch/arm64/mm/proc.S             | 13 ++++----
 3 files changed, 79 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index ff9fb3aba17b..21bb624e0a7a 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -48,7 +48,8 @@
 #define ARM64_WORKAROUND_843419			27
 #define ARM64_HAS_CACHE_IDC			28
 #define ARM64_HAS_CACHE_DIC			29
+#define ARM64_HW_DBM				30
 
-#define ARM64_NCAPS				30
+#define ARM64_NCAPS				31
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 53273e79f7ce..4e73c610a409 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -954,6 +954,57 @@ static int __init parse_kpti(char *str)
 __setup("kpti=", parse_kpti);
 #endif	/* CONFIG_UNMAP_KERNEL_AT_EL0 */
 
+#ifdef CONFIG_ARM64_HW_AFDBM
+static inline void __cpu_enable_hw_dbm(void)
+{
+	u64 tcr = read_sysreg(tcr_el1) | TCR_HD;
+
+	write_sysreg(tcr, tcr_el1);
+	isb();
+}
+
+static bool cpu_can_use_dbm(const struct arm64_cpu_capabilities *cap)
+{
+	return has_cpuid_feature(cap, SCOPE_LOCAL_CPU);
+}
+
+static void cpu_enable_hw_dbm(struct arm64_cpu_capabilities const *cap)
+{
+	if (cpu_can_use_dbm(cap))
+		__cpu_enable_hw_dbm();
+}
+
+static bool has_hw_dbm(const struct arm64_cpu_capabilities *cap,
+		       int __unused)
+{
+	static bool detected = false;
+	/*
+	 * DBM is a non-conflicting feature. i.e, the kernel can safely
+	 * run a mix of CPUs with and without the feature. So, we
+	 * unconditionally enable the capability to allow any late CPU
+	 * to use the feature. We only enable the control bits on the
+	 * CPU, if it actually supports.
+	 *
+	 * We have to make sure we print the "feature" detection only
+	 * when at least one CPU actually uses it. So check if this CPU
+	 * can actually use it and print the message exactly once.
+	 *
+	 * This is safe as all CPUs (including secondary CPUs - due to the
+	 * LOCAL_CPU scope - and the hotplugged CPUs - via verification)
+	 * goes through the "matches" check exactly once. Also if a CPU
+	 * matches the criteria, it is guaranteed that the CPU will turn
+	 * the DBM on, as the capability is unconditionally enabled.
+	 */
+	if (!detected && cpu_can_use_dbm(cap)) {
+		detected = true;
+		pr_info("detected: Hardware dirty bit management\n");
+	}
+
+	return true;
+}
+
+#endif
+
 static void cpu_copy_el2regs(const struct arm64_cpu_capabilities *__unused)
 {
 	/*
@@ -1130,6 +1181,26 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
 		.matches = has_cache_dic,
 	},
+#ifdef CONFIG_ARM64_HW_AFDBM
+	{
+		/*
+		 * Since we turn this on always, we don't want the user to
+		 * think that the feature is available when it may not be.
+		 * So hide the description.
+		 *
+		 * .desc = "Hardware pagetable Dirty Bit Management",
+		 *
+		 */
+		.type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE,
+		.capability = ARM64_HW_DBM,
+		.sys_reg = SYS_ID_AA64MMFR1_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64MMFR1_HADBS_SHIFT,
+		.min_field_value = 2,
+		.matches = has_hw_dbm,
+		.cpu_enable = cpu_enable_hw_dbm,
+	},
+#endif
 	{},
 };
 
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 8f074d64b760..5f9a73a4452c 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -448,16 +448,15 @@ ENTRY(__cpu_setup)
 	tcr_compute_pa_size x10, #TCR_IPS_SHIFT, x5, x6
 #ifdef CONFIG_ARM64_HW_AFDBM
 	/*
-	 * Hardware update of the Access and Dirty bits.
+	 * Enable hardware update of the Access Flags bit.
+	 * Hardware dirty bit management is enabled later,
+	 * via capabilities.
 	 */
 	mrs	x9, ID_AA64MMFR1_EL1
 	and	x9, x9, #0xf
-	cbz	x9, 2f
-	cmp	x9, #2
-	b.lt	1f
-	orr	x10, x10, #TCR_HD		// hardware Dirty flag update
-1:	orr	x10, x10, #TCR_HA		// hardware Access flag update
-2:
+	cbz	x9, 1f
+	orr	x10, x10, #TCR_HA		// hardware Access flag update
+1:
 #endif	/* CONFIG_ARM64_HW_AFDBM */
 	msr	tcr_el1, x10
 	ret					// return to head.S
-- 
2.14.3