From 625b8a72f51a30e70ebeb4ab7febd844724c2c9f Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 2 Oct 2019 10:06:12 +0100 Subject: [PATCH] arm64: Relax ICC_PMR_EL1 accesses when ICC_CTLR_EL1.PMHE is clear task #25552995 commit f226650494c6aa87526d12135b7de8b8c074f3de upstream. The GICv3 architecture specification is incredibly misleading when it comes to PMR and the requirement for a DSB. It turns out that this DSB is only required if the CPU interface sends an Upstream Control message to the redistributor in order to update the RD's view of PMR. This message is only sent when ICC_CTLR_EL1.PMHE is set, which isn't the case in Linux. It can still be set from EL3, so some special care is required. But the upshot is that in the (hopefuly large) majority of the cases, we can drop the DSB altogether. This relies on a new static key being set if the boot CPU has PMHE set. The drawback is that this static key has to be exported to modules. Cc: Will Deacon Cc: James Morse Cc: Julien Thierry Cc: Suzuki K Poulose Signed-off-by: Marc Zyngier Signed-off-by: Catalin Marinas Signed-off-by: Zou Cao Reviewed-by: luanshi --- arch/arm64/include/asm/barrier.h | 12 ++++++++++++ arch/arm64/include/asm/daifflags.h | 3 ++- arch/arm64/include/asm/irqflags.h | 19 ++++++++++--------- arch/arm64/include/asm/kvm_host.h | 3 +-- arch/arm64/kernel/entry.S | 6 ++++-- arch/arm64/kvm/hyp/switch.c | 4 ++-- drivers/irqchip/irq-gic-v3.c | 20 ++++++++++++++++++++ include/linux/irqchip/arm-gic-v3.h | 2 ++ 8 files changed, 53 insertions(+), 16 deletions(-) diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index 822a9192c551..909a16c824c5 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -34,6 +34,18 @@ #define psb_csync() asm volatile("hint #17" : : : "memory") #define csdb() asm volatile("hint #20" : : : "memory") +#ifdef CONFIG_ARM64_PSEUDO_NMI +#define pmr_sync() \ + do { \ + extern struct static_key_false gic_pmr_sync; \ + \ + if (static_branch_unlikely(&gic_pmr_sync)) \ + dsb(sy); \ + } while (0) +#else +#define pmr_sync() do {} while (0) +#endif + #define mb() dsb(sy) #define rmb() dsb(ld) #define wmb() dsb(st) diff --git a/arch/arm64/include/asm/daifflags.h b/arch/arm64/include/asm/daifflags.h index eca5bee1d85b..0f9a06eb8e36 100644 --- a/arch/arm64/include/asm/daifflags.h +++ b/arch/arm64/include/asm/daifflags.h @@ -19,6 +19,7 @@ #include #include +#include #include #define DAIF_PROCCTX 0 @@ -74,7 +75,7 @@ static inline void local_daif_restore(unsigned long flags) if (system_uses_irq_prio_masking()) { gic_write_pmr(GIC_PRIO_IRQON); - dsb(sy); + pmr_sync(); } } else if (system_uses_irq_prio_masking()) { u64 pmr; diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h index cac2d2a3c24e..6074bf2ef58d 100644 --- a/arch/arm64/include/asm/irqflags.h +++ b/arch/arm64/include/asm/irqflags.h @@ -19,6 +19,7 @@ #ifdef __KERNEL__ #include +#include #include #include @@ -47,14 +48,14 @@ static inline void arch_local_irq_enable(void) } asm volatile(ALTERNATIVE( - "msr daifclr, #2 // arch_local_irq_enable\n" - "nop", - __msr_s(SYS_ICC_PMR_EL1, "%0") - "dsb sy", + "msr daifclr, #2 // arch_local_irq_enable", + __msr_s(SYS_ICC_PMR_EL1, "%0"), ARM64_HAS_IRQ_PRIO_MASKING) : : "r" ((unsigned long) GIC_PRIO_IRQON) : "memory"); + + pmr_sync(); } static inline void arch_local_irq_disable(void) @@ -129,14 +130,14 @@ static inline unsigned long arch_local_irq_save(void) static inline void arch_local_irq_restore(unsigned long flags) { asm volatile(ALTERNATIVE( - "msr daif, %0\n" - "nop", - __msr_s(SYS_ICC_PMR_EL1, "%0") - "dsb sy", - ARM64_HAS_IRQ_PRIO_MASKING) + "msr daif, %0", + __msr_s(SYS_ICC_PMR_EL1, "%0"), + ARM64_HAS_IRQ_PRIO_MASKING) : : "r" (flags) : "memory"); + + pmr_sync(); } #endif diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index b21f471d68e0..8e9a582c3d2d 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -496,8 +496,7 @@ static inline void kvm_arm_vhe_guest_enter(void) * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU. */ - if (system_uses_irq_prio_masking()) - dsb(sy); + pmr_sync(); } static inline void kvm_arm_vhe_guest_exit(void) diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 5b46a34512ff..8e3c2413f29b 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -280,8 +280,10 @@ alternative_else_nop_endif alternative_if ARM64_HAS_IRQ_PRIO_MASKING ldr x20, [sp, #S_PMR_SAVE] msr_s SYS_ICC_PMR_EL1, x20 - /* Ensure priority change is seen by redistributor */ - dsb sy + mrs_s x21, SYS_ICC_CTLR_EL1 + tbz x21, #6, .L__skip_pmr_sync\@ // Check for ICC_CTLR_EL1.PMHE + dsb sy // Ensure priority change is seen by redistributor +.L__skip_pmr_sync\@: alternative_else_nop_endif ldp x21, x22, [sp, #S_PC] // load ELR, SPSR diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index b3e3c1e6299a..47cccd268c65 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -22,7 +22,7 @@ #include -#include +#include #include #include #include @@ -515,7 +515,7 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) */ if (system_uses_irq_prio_masking()) { gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); - dsb(sy); + pmr_sync(); } vcpu = kern_hyp_va(vcpu); diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 10a3c8f868a6..2e583d9c2a06 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -91,6 +91,15 @@ static DEFINE_STATIC_KEY_TRUE(supports_deactivate_key); */ static DEFINE_STATIC_KEY_FALSE(supports_pseudo_nmis); +/* + * Global static key controlling whether an update to PMR allowing more + * interrupts requires to be propagated to the redistributor (DSB SY). + * And this needs to be exported for modules to be able to enable + * interrupts... + */ +DEFINE_STATIC_KEY_FALSE(gic_pmr_sync); +EXPORT_SYMBOL(gic_pmr_sync); + /* ppi_nmi_refs[n] == number of cpus having ppi[n + 16] set as NMI */ static refcount_t ppi_nmi_refs[16]; @@ -1260,6 +1269,17 @@ static void gic_enable_nmi_support(void) for (i = 0; i < 16; i++) refcount_set(&ppi_nmi_refs[i], 0); + /* + * Linux itself doesn't use 1:N distribution, so has no need to + * set PMHE. The only reason to have it set is if EL3 requires it + * (and we can't change it). + */ + if (gic_read_ctlr() & ICC_CTLR_EL1_PMHE_MASK) + static_branch_enable(&gic_pmr_sync); + + pr_info("%s ICC_PMR_EL1 synchronisation\n", + static_branch_unlikely(&gic_pmr_sync) ? "Forcing" : "Relaxing"); + static_branch_enable(&supports_pseudo_nmis); if (static_branch_likely(&supports_deactivate_key)) diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 95b69d3006ee..bc2eefc626e9 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -467,6 +467,8 @@ #define ICC_CTLR_EL1_EOImode_MASK (1 << ICC_CTLR_EL1_EOImode_SHIFT) #define ICC_CTLR_EL1_CBPR_SHIFT 0 #define ICC_CTLR_EL1_CBPR_MASK (1 << ICC_CTLR_EL1_CBPR_SHIFT) +#define ICC_CTLR_EL1_PMHE_SHIFT 6 +#define ICC_CTLR_EL1_PMHE_MASK (1 << ICC_CTLR_EL1_PMHE_SHIFT) #define ICC_CTLR_EL1_PRI_BITS_SHIFT 8 #define ICC_CTLR_EL1_PRI_BITS_MASK (0x7 << ICC_CTLR_EL1_PRI_BITS_SHIFT) #define ICC_CTLR_EL1_ID_BITS_SHIFT 11 -- GitLab