Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Julien Thierry <julien.thierry@arm.com>
To:     linux-arm-kernel@lists.infradead.org
Cc:     linux-kernel@vger.kernel.org, daniel.thompson@linaro.org,
        joel@joelfernandes.org, marc.zyngier@arm.com,
        christoffer.dall@arm.com, james.morse@arm.com,
        catalin.marinas@arm.com, will.deacon@arm.com, mark.rutland@arm.com,
        Julien Thierry <julien.thierry@arm.com>,
        Arnd Bergmann <arnd@arndb.de>, linux-arch@vger.kernel.org,
        stable@vger.kernel.org
Subject: [PATCH v10 01/25] arm64: Fix HCR.TGE status for NMI contexts
Date:   Thu, 31 Jan 2019 14:58:39 +0000
Message-Id: <1548946743-38979-2-git-send-email-julien.thierry@arm.com>
In-Reply-To: <1548946743-38979-1-git-send-email-julien.thierry@arm.com>
References: <1548946743-38979-1-git-send-email-julien.thierry@arm.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

When using VHE, the host needs to clear HCR_EL2.TGE bit in order
to interact with guest TLBs, switching from EL2&0 translation regime
to EL1&0.

However, some non-maskable asynchronous event could happen while TGE is
cleared like SDEI. Because of this address translation operations
relying on EL2&0 translation regime could fail (tlb invalidation,
userspace access, ...).

Fix this by properly setting HCR_EL2.TGE when entering NMI context and
clear it if necessary when returning to the interrupted context.

Signed-off-by: Julien Thierry <julien.thierry@arm.com>
Suggested-by: Marc Zyngier <marc.zyngier@arm.com>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Reviewed-by: James Morse <james.morse@arm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: James Morse <james.morse@arm.com>
Cc: linux-arch@vger.kernel.org
Cc: stable@vger.kernel.org
---
 arch/arm64/include/asm/hardirq.h | 31 +++++++++++++++++++++++++++++++
 arch/arm64/kernel/irq.c          |  3 +++
 include/linux/hardirq.h          |  7 +++++++
 3 files changed, 41 insertions(+)

diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h
index 1473fc2..89691c8 100644
--- a/arch/arm64/include/asm/hardirq.h
+++ b/arch/arm64/include/asm/hardirq.h
@@ -17,8 +17,12 @@
 #define __ASM_HARDIRQ_H
 
 #include <linux/cache.h>
+#include <linux/percpu.h>
 #include <linux/threads.h>
+#include <asm/barrier.h>
 #include <asm/irq.h>
+#include <asm/kvm_arm.h>
+#include <asm/sysreg.h>
 
 #define NR_IPI	7
 
@@ -37,6 +41,33 @@
 
 #define __ARCH_IRQ_EXIT_IRQS_DISABLED	1
 
+struct nmi_ctx {
+	u64 hcr;
+};
+
+DECLARE_PER_CPU(struct nmi_ctx, nmi_contexts);
+
+#define arch_nmi_enter()							\
+	do {									\
+		if (is_kernel_in_hyp_mode()) {					\
+			struct nmi_ctx *nmi_ctx = this_cpu_ptr(&nmi_contexts);	\
+			nmi_ctx->hcr = read_sysreg(hcr_el2);			\
+			if (!(nmi_ctx->hcr & HCR_TGE)) {			\
+				write_sysreg(nmi_ctx->hcr | HCR_TGE, hcr_el2);	\
+				isb();						\
+			}							\
+		}								\
+	} while (0)
+
+#define arch_nmi_exit()								\
+	do {									\
+		if (is_kernel_in_hyp_mode()) {					\
+			struct nmi_ctx *nmi_ctx = this_cpu_ptr(&nmi_contexts);	\
+			if (!(nmi_ctx->hcr & HCR_TGE))				\
+				write_sysreg(nmi_ctx->hcr, hcr_el2);		\
+		}								\
+	} while (0)
+
 static inline void ack_bad_irq(unsigned int irq)
 {
 	extern unsigned long irq_err_count;
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 780a12f..92fa817 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -33,6 +33,9 @@
 
 unsigned long irq_err_count;
 
+/* Only access this in an NMI enter/exit */
+DEFINE_PER_CPU(struct nmi_ctx, nmi_contexts);
+
 DEFINE_PER_CPU(unsigned long *, irq_stack_ptr);
 
 int arch_show_interrupts(struct seq_file *p, int prec)
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index 0fbbcdf..da0af63 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -60,8 +60,14 @@ static inline void rcu_nmi_exit(void)
  */
 extern void irq_exit(void);
 
+#ifndef arch_nmi_enter
+#define arch_nmi_enter()	do { } while (0)
+#define arch_nmi_exit()		do { } while (0)
+#endif
+
 #define nmi_enter()						\
 	do {							\
+		arch_nmi_enter();				\
 		printk_nmi_enter();				\
 		lockdep_off();					\
 		ftrace_nmi_enter();				\
@@ -80,6 +86,7 @@ static inline void rcu_nmi_exit(void)
 		ftrace_nmi_exit();				\
 		lockdep_on();					\
 		printk_nmi_exit();				\
+		arch_nmi_exit();				\
 	} while (0)
 
 #endif /* LINUX_HARDIRQ_H */
-- 
1.9.1