Hi Julien,
On 21/01/2019 15:33, Julien Thierry wrote:
> When using VHE, the host needs to clear HCR_EL2.TGE bit in order
> to interract with guest TLBs, switching from EL2&0 translation regime
(interact)
> 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.
Yes please. This would not have been fun to debug!
Reviewed-by: James Morse <james.morse@xxxxxxx>
I was looking for why we need core code to do this, instead of updating the
arch's call sites. Your 'irqdesc: Add domain handlers for NMIs' patch (pointed
to from the cover letter) is the reason: core-code calls nmi_enter()/nmi_exit()
itself.
Thanks,
James
> diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h
> index 1473fc2..94b7481 100644
> --- a/arch/arm64/include/asm/hardirq.h
> +++ b/arch/arm64/include/asm/hardirq.h
> @@ -19,6 +19,7 @@
> #include <linux/cache.h>
> #include <linux/threads.h>
> #include <asm/irq.h>
> +#include <asm/kvm_arm.h>
percpu.h?
sysreg.h?
barrier.h?
> @@ -37,6 +38,33 @@
>
> #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/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 */
>
