Re: [PATCH v4 02/27] hardirq/nmi: Allow nested nmi_enter()

[Peter Zijlstra]

On Tue, Feb 25, 2020 at 04:09:06AM +0100, Frederic Weisbecker wrote:
> On Mon, Feb 24, 2020 at 05:13:18PM +0100, Peter Zijlstra wrote:

> > +#define arch_nmi_enter()						\
> > +do {									\
> > +	struct nmi_ctx *___ctx;						\
> > +	unsigned int ___cnt;						\
> > +									\
> > +	if (!is_kernel_in_hyp_mode() || in_nmi())			\
> > +		break;							\
> > +									\
> > +	___ctx = this_cpu_ptr(&nmi_contexts);				\
> > +	___cnt = ___ctx->cnt;						\
> > +	if (!(___cnt & 1) && __cnt) {					\
> > +		___ctx->cnt += 2;					\
> > +		break;							\
> > +	}								\
> > +									\
> > +	___ctx->cnt |= 1;						\
> > +	barrier();							\
> > +	nmi_ctx->hcr = read_sysreg(hcr_el2);				\
> > +	if (!(nmi_ctx->hcr & HCR_TGE)) {				\
> > +		write_sysreg(nmi_ctx->hcr | HCR_TGE, hcr_el2);		\
> > +		isb();							\
> > +	}								\
> > +	barrier();							\
> 
> Suppose the first NMI is interrupted here. nmi_ctx->hcr has HCR_TGE unset.
> The new NMI is going to overwrite nmi_ctx->hcr with HCR_TGE set. Then the
> first NMI will not restore the correct value upon arch_nmi_exit().
> 
> So perhaps the below, but I bet I overlooked something obvious.

Well, none of this is obvious :/

The basic idea was that the LSB signifies 'pending/in-progress' and when
that is set, nobody else touches no nothing. Enter will unconditionally
(re) write_sysreg(), exit will nothing.

Obviously I messed that up.

How's this? 

#define arch_nmi_enter()						\
do {									\
	struct nmi_ctx *___ctx;						\
	unsigned int ___cnt;						\
									\
	if (!is_kernel_in_hyp_mode() || in_nmi())			\
		break;							\
									\
	___ctx = this_cpu_ptr(&nmi_contexts);				\
	___cnt = ___ctx->cnt;						\
	if (!(___cnt & 1)) { /* !IN-PROGRESS */				\
		if (___cnt) {						\
			___ctx->cnt += 2;				\
			break;						\
		}							\
									\
		___ctx->hcr = read_sysreg(hcr_el2);			\
		barrier();						\
		___ctx->cnt |= 1; /* IN-PROGRESS */			\
		barrier();						\
	}								\
									\
	if (!(___ctx->hcr & HCR_TGE)) {					\
		write_sysreg(___ctx->hcr | HCR_TGE, hcr_el2);		\
		isb();							\
	}								\
	barrier();							\
	if (!(___cnt & 1))						\
		___ctx->cnt++; /* COMPLETE */				\
} while (0)

#define arch_nmi_exit()							\
do {									\
	struct nmi_ctx *___ctx;						\
									\
	if (!is_kernel_in_hyp_mode() || in_nmi())			\
		break;							\
									\
	___ctx = this_cpu_ptr(&nmi_contexts);				\
	if ((___ctx->cnt & 1) || (___ctx->cnt -= 2))			\
		break;							\
									\
	if (!(___ctx->hcr & HCR_TGE))					\
		write_sysreg(___ctx->hcr, hcr_el2);			\
} while (0)