Re: [PATCH 3/6] x86/sev: add support for RMPOPT instruction

[Uros Bizjak <ubizjak@gmail.com>]

On 2/17/26 21:10, Ashish Kalra wrote:
> From: Ashish Kalra <ashish.kalra@amd.com>
> 
> As SEV-SNP is enabled by default on boot when an RMP table is
> allocated by BIOS, the hypervisor and non-SNP guests are subject to
> RMP write checks to provide integrity of SNP guest memory.
> 
> RMPOPT is a new instruction that minimizes the performance overhead of
> RMP checks on the hypervisor and on non-SNP guests by allowing RMP
> checks to be skipped for 1GB regions of memory that are known not to
> contain any SEV-SNP guest memory.
> 
> Enable RMPOPT optimizations globally for all system RAM at RMP
> initialization time. RMP checks can initially be skipped for 1GB memory
> ranges that do not contain SEV-SNP guest memory (excluding preassigned
> pages such as the RMP table and firmware pages). As SNP guests are
> launched, RMPUPDATE will disable the corresponding RMPOPT optimizations.
> 
> Suggested-by: Thomas Lendacky <thomas.lendacky@amd.com>
> Signed-off-by: Ashish Kalra <ashish.kalra@amd.com>
> ---
>   arch/x86/virt/svm/sev.c | 84 +++++++++++++++++++++++++++++++++++++++++
>   1 file changed, 84 insertions(+)
> 
> diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c
> index e6b784d26c33..a0d38fc50698 100644
> --- a/arch/x86/virt/svm/sev.c
> +++ b/arch/x86/virt/svm/sev.c
> @@ -19,6 +19,7 @@
>   #include <linux/iommu.h>
>   #include <linux/amd-iommu.h>
>   #include <linux/nospec.h>
> +#include <linux/kthread.h>
>   
>   #include <asm/sev.h>
>   #include <asm/processor.h>
> @@ -127,10 +128,17 @@ static DEFINE_SPINLOCK(snp_leaked_pages_list_lock);
>   
>   static unsigned long snp_nr_leaked_pages;
>   
> +enum rmpopt_function {
> +	RMPOPT_FUNC_VERIFY_AND_REPORT_STATUS,
> +	RMPOPT_FUNC_REPORT_STATUS
> +};
> +
>   #define RMPOPT_TABLE_MAX_LIMIT_IN_TB	2
>   #define NUM_TB(pfn_min, pfn_max)	\
>   	(((pfn_max) - (pfn_min)) / (1 << (40 - PAGE_SHIFT)))
>   
> +static struct task_struct *rmpopt_task;
> +
>   struct rmpopt_socket_config {
>   	unsigned long start_pfn, end_pfn;
>   	cpumask_var_t cpulist;
> @@ -527,6 +535,66 @@ static void get_cpumask_of_primary_threads(cpumask_var_t cpulist)
>   	}
>   }
>   
> +/*
> + * 'val' is a system physical address aligned to 1GB OR'ed with
> + * a function selection. Currently supported functions are 0
> + * (verify and report status) and 1 (report status).
> + */
> +static void rmpopt(void *val)
> +{
> +	asm volatile(".byte 0xf2, 0x0f, 0x01, 0xfc\n\t"

There is no need for \n\t instruction delimiter with single instruction 
in the asm template, it will just confuse compiler's insn count estimator.

Uros.

> +		     : : "a" ((u64)val & PUD_MASK), "c" ((u64)val & 0x1)
> +		     : "memory", "cc");
> +}
> +
> +static int rmpopt_kthread(void *__unused)
> +{
> +	phys_addr_t pa_start, pa_end;
> +	cpumask_var_t cpus;
> +
> +	if (!zalloc_cpumask_var(&cpus, GFP_KERNEL))
> +		return -ENOMEM;
> +
> +	pa_start = ALIGN_DOWN(PFN_PHYS(min_low_pfn), PUD_SIZE);
> +	pa_end = ALIGN(PFN_PHYS(max_pfn), PUD_SIZE);
> +
> +	while (!kthread_should_stop()) {
> +		phys_addr_t pa;
> +
> +		pr_info("RMP optimizations enabled on physical address range @1GB alignment [0x%016llx - 0x%016llx]\n",
> +			pa_start, pa_end);
> +
> +		/* Only one thread per core needs to issue RMPOPT instruction */
> +		get_cpumask_of_primary_threads(cpus);
> +
> +		/*
> +		 * RMPOPT optimizations skip RMP checks at 1GB granularity if this range of
> +		 * memory does not contain any SNP guest memory.
> +		 */
> +		for (pa = pa_start; pa < pa_end; pa += PUD_SIZE) {
> +			/* Bit zero passes the function to the RMPOPT instruction. */
> +			on_each_cpu_mask(cpus, rmpopt,
> +					 (void *)(pa | RMPOPT_FUNC_VERIFY_AND_REPORT_STATUS),
> +					 true);
> +
> +			 /* Give a chance for other threads to run */
> +			cond_resched();
> +		}
> +
> +		set_current_state(TASK_INTERRUPTIBLE);
> +		schedule();
> +	}
> +
> +	free_cpumask_var(cpus);
> +	return 0;
> +}
> +
> +static void rmpopt_all_physmem(void)
> +{
> +	if (rmpopt_task)
> +		wake_up_process(rmpopt_task);
> +}
> +
>   static void __configure_rmpopt(void *val)
>   {
>   	u64 rmpopt_base = ((u64)val & PUD_MASK) | MSR_AMD64_RMPOPT_ENABLE;
> @@ -687,6 +755,22 @@ static __init void configure_and_enable_rmpopt(void)
>   	else
>   		configure_rmpopt_large_physmem(primary_threads_cpulist);
>   
> +	rmpopt_task = kthread_create(rmpopt_kthread, NULL, "rmpopt_kthread");
> +	if (IS_ERR(rmpopt_task)) {
> +		pr_warn("Unable to start RMPOPT kernel thread\n");
> +		rmpopt_task = NULL;
> +		goto free_cpumask;
> +	}
> +
> +	pr_info("RMPOPT worker thread created with PID %d\n", task_pid_nr(rmpopt_task));
> +
> +	/*
> +	 * Once all per-CPU RMPOPT tables have been configured, enable RMPOPT
> +	 * optimizations on all physical memory.
> +	 */
> +	rmpopt_all_physmem();
> +
> +free_cpumask:
>   	free_cpumask_var(primary_threads_cpulist);
>   }
>