arm64: Add hypervisor safe helper for checking constant capabilities

commit a4023f68 upstream.

The hypervisor may not have full access to the kernel data structures
and hence cannot safely use cpus_have_cap() helper for checking the
system capability. Add a safe helper for hypervisors to check a constant
system capability, which *doesn't* fall back to checking the bitmap
maintained by the kernel. With this, make the cpus_have_cap() only
check the bitmask and force constant cap checks to use the new API
for quicker checks.

Cc: Robert Ritcher <rritcher@cavium.com>
Cc: Tirumalesh Chalamarla <tchalamarla@cavium.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Will Deacon <will.deacon@arm.com>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
[4.9: restore cpus_have_const_cap() to previously-backported code]
Signed-off-by: Mark Rutland <mark.rutland@arm.com> [v4.9 backport]
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

arch/arm64/include/asm/cpufeature.h

@@ -9,8 +9,6 @@
 #ifndef __ASM_CPUFEATURE_H
 #define __ASM_CPUFEATURE_H
 
-#include <linux/jump_label.h>
-
 #include <asm/cpucaps.h>
 #include <asm/hwcap.h>
 #include <asm/sysreg.h>
@@ -27,6 +25,8 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/bug.h>
+#include <linux/jump_label.h>
 #include <linux/kernel.h>
 
 /* CPU feature register tracking */
@@ -104,14 +104,19 @@ static inline bool cpu_have_feature(unsigned int num)
 	return elf_hwcap & (1UL << num);
 }
 
+/* System capability check for constant caps */
+static inline bool cpus_have_const_cap(int num)
+{
+	if (num >= ARM64_NCAPS)
+		return false;
+	return static_branch_unlikely(&cpu_hwcap_keys[num]);
+}
+
 static inline bool cpus_have_cap(unsigned int num)
 {
 	if (num >= ARM64_NCAPS)
 		return false;
-	if (__builtin_constant_p(num))
-		return static_branch_unlikely(&cpu_hwcap_keys[num]);
-	else
-		return test_bit(num, cpu_hwcaps);
+	return test_bit(num, cpu_hwcaps);
 }
 
 static inline void cpus_set_cap(unsigned int num)
@@ -200,7 +205,7 @@ static inline bool cpu_supports_mixed_endian_el0(void)
 
 static inline bool system_supports_32bit_el0(void)
 {
-	return cpus_have_cap(ARM64_HAS_32BIT_EL0);
+	return cpus_have_const_cap(ARM64_HAS_32BIT_EL0);
 }
 
 static inline bool system_supports_mixed_endian_el0(void)

arch/arm64/include/asm/kvm_host.h

@@ -398,7 +398,7 @@ static inline void __cpu_init_stage2(void)
 
 static inline bool kvm_arm_harden_branch_predictor(void)
 {
-	return cpus_have_cap(ARM64_HARDEN_BRANCH_PREDICTOR);
+	return cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR);
 }
 
 #endif /* __ARM64_KVM_HOST_H__ */

arch/arm64/include/asm/kvm_mmu.h

@@ -341,7 +341,7 @@ static inline void *kvm_get_hyp_vector(void)
 		vect = __bp_harden_hyp_vecs_start +
 		       data->hyp_vectors_slot * SZ_2K;
 
-		if (!cpus_have_cap(ARM64_HAS_VIRT_HOST_EXTN))
+		if (!cpus_have_const_cap(ARM64_HAS_VIRT_HOST_EXTN))
 			vect = lm_alias(vect);
 	}
 

arch/arm64/include/asm/mmu.h

@@ -37,7 +37,7 @@ typedef struct {
 static inline bool arm64_kernel_unmapped_at_el0(void)
 {
 	return IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0) &&
-	       cpus_have_cap(ARM64_UNMAP_KERNEL_AT_EL0);
+	       cpus_have_const_cap(ARM64_UNMAP_KERNEL_AT_EL0);
 }
 
 typedef void (*bp_hardening_cb_t)(void);

arch/arm64/kernel/cpufeature.c

@@ -47,6 +47,7 @@ unsigned int compat_elf_hwcap2 __read_mostly;
 #endif
 
 DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
+EXPORT_SYMBOL(cpu_hwcaps);
 
 DEFINE_STATIC_KEY_ARRAY_FALSE(cpu_hwcap_keys, ARM64_NCAPS);
 EXPORT_SYMBOL(cpu_hwcap_keys);
@@ -762,7 +763,7 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
 	 * ThunderX leads to apparent I-cache corruption of kernel text, which
 	 * ends as well as you might imagine. Don't even try.
 	 */
-	if (cpus_have_cap(ARM64_WORKAROUND_CAVIUM_27456)) {
+	if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_27456)) {
 		str = "ARM64_WORKAROUND_CAVIUM_27456";
 		__kpti_forced = -1;
 	}
@@ -1203,5 +1204,5 @@ void __init setup_cpu_features(void)
 static bool __maybe_unused
 cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused)
 {
-	return (cpus_have_cap(ARM64_HAS_PAN) && !cpus_have_cap(ARM64_HAS_UAO));
+	return (cpus_have_const_cap(ARM64_HAS_PAN) && !cpus_have_const_cap(ARM64_HAS_UAO));
 }

arch/arm64/kernel/process.c

@@ -291,7 +291,7 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 		memset(childregs, 0, sizeof(struct pt_regs));
 		childregs->pstate = PSR_MODE_EL1h;
 		if (IS_ENABLED(CONFIG_ARM64_UAO) &&
-		    cpus_have_cap(ARM64_HAS_UAO))
+		    cpus_have_const_cap(ARM64_HAS_UAO))
 			childregs->pstate |= PSR_UAO_BIT;
 		p->thread.cpu_context.x19 = stack_start;
 		p->thread.cpu_context.x20 = stk_sz;

drivers/irqchip/irq-gic-v3.c

@@ -120,11 +120,10 @@ static void gic_redist_wait_for_rwp(void)
 }
 
 #ifdef CONFIG_ARM64
-static DEFINE_STATIC_KEY_FALSE(is_cavium_thunderx);
 
 static u64 __maybe_unused gic_read_iar(void)
 {
-	if (static_branch_unlikely(&is_cavium_thunderx))
+	if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_23154))
 		return gic_read_iar_cavium_thunderx();
 	else
 		return gic_read_iar_common();
@@ -908,14 +907,6 @@ static const struct irq_domain_ops partition_domain_ops = {
 	.select = gic_irq_domain_select,
 };
 
-static void gicv3_enable_quirks(void)
-{
-#ifdef CONFIG_ARM64
-	if (cpus_have_cap(ARM64_WORKAROUND_CAVIUM_23154))
-		static_branch_enable(&is_cavium_thunderx);
-#endif
-}
-
 static int __init gic_init_bases(void __iomem *dist_base,
 				 struct redist_region *rdist_regs,
 				 u32 nr_redist_regions,
@@ -938,8 +929,6 @@ static int __init gic_init_bases(void __iomem *dist_base,
 	gic_data.nr_redist_regions = nr_redist_regions;
 	gic_data.redist_stride = redist_stride;
 
-	gicv3_enable_quirks();
-
 	/*
 	 * Find out how many interrupts are supported.
 	 * The GIC only supports up to 1020 interrupt sources (SGI+PPI+SPI)