Re: [PATCH v1 07/26] x86/fault: Add helper for dumping RMP entries

[Tom Lendacky <thomas.lendacky@amd.com>]

On 12/30/23 10:19, Michael Roth wrote:
> From: Brijesh Singh <brijesh.singh@amd.com>
> 
> This information will be useful for debugging things like page faults
> due to RMP access violations and RMPUPDATE failures.
> 
> Signed-off-by: Brijesh Singh <brijesh.singh@amd.com>
> Signed-off-by: Ashish Kalra <ashish.kalra@amd.com>
> [mdr: move helper to standalone patch, rework dump logic to reduce
>        verbosity]
> Signed-off-by: Michael Roth <michael.roth@amd.com>
> ---
>   arch/x86/include/asm/sev.h |  2 +
>   arch/x86/virt/svm/sev.c    | 77 ++++++++++++++++++++++++++++++++++++++
>   2 files changed, 79 insertions(+)
> 
> diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
> index 01ce61b283a3..2c53e3de0b71 100644
> --- a/arch/x86/include/asm/sev.h
> +++ b/arch/x86/include/asm/sev.h
> @@ -247,9 +247,11 @@ static inline u64 sev_get_status(void) { return 0; }
>   #ifdef CONFIG_KVM_AMD_SEV
>   bool snp_probe_rmptable_info(void);
>   int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level);
> +void snp_dump_hva_rmpentry(unsigned long address);
>   #else
>   static inline bool snp_probe_rmptable_info(void) { return false; }
>   static inline int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level) { return -ENODEV; }
> +static inline void snp_dump_hva_rmpentry(unsigned long address) {}
>   #endif
>   
>   #endif
> diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c
> index 49fdfbf4e518..7c9ced8911e9 100644
> --- a/arch/x86/virt/svm/sev.c
> +++ b/arch/x86/virt/svm/sev.c
> @@ -266,3 +266,80 @@ int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level)
>   	return 0;
>   }
>   EXPORT_SYMBOL_GPL(snp_lookup_rmpentry);
> +
> +/*
> + * Dump the raw RMP entry for a particular PFN. These bits are documented in the
> + * PPR for a particular CPU model and provide useful information about how a
> + * particular PFN is being utilized by the kernel/firmware at the time certain
> + * unexpected events occur, such as RMP faults.
> + */
> +static void dump_rmpentry(u64 pfn)
> +{
> +	u64 pfn_current, pfn_end;
> +	struct rmpentry *e;
> +	u64 *e_data;
> +	int level;
> +
> +	e = __snp_lookup_rmpentry(pfn, &level);
> +	if (IS_ERR(e)) {
> +		pr_info("Failed to read RMP entry for PFN 0x%llx, error %ld\n",
> +			pfn, PTR_ERR(e));
> +		return;
> +	}
> +
> +	e_data = (u64 *)e;
> +	if (e->assigned) {
> +		pr_info("RMP entry for PFN 0x%llx: [high=0x%016llx low=0x%016llx]\n",
> +			pfn, e_data[1], e_data[0]);
> +		return;
> +	}
> +
> +	/*
> +	 * If the RMP entry for a particular PFN is not in an assigned state,
> +	 * then it is sometimes useful to get an idea of whether or not any RMP
> +	 * entries for other PFNs within the same 2MB region are assigned, since
> +	 * those too can affect the ability to access a particular PFN in
> +	 * certain situations, such as when the PFN is being accessed via a 2MB
> +	 * mapping in the host page table.
> +	 */
> +	pfn_current = ALIGN(pfn, PTRS_PER_PMD);
> +	pfn_end = pfn_current + PTRS_PER_PMD;
> +
> +	while (pfn_current < pfn_end) {
> +		e = __snp_lookup_rmpentry(pfn_current, &level);
> +		if (IS_ERR(e)) {
> +			pfn_current++;
> +			continue;
> +		}
> +
> +		e_data = (u64 *)e;
> +		if (e_data[0] || e_data[1]) {
> +			pr_info("No assigned RMP entry for PFN 0x%llx, but the 2MB region contains populated RMP entries, e.g.: PFN 0x%llx: [high=0x%016llx low=0x%016llx]\n",
> +				pfn, pfn_current, e_data[1], e_data[0]);
> +			return;
> +		}
> +		pfn_current++;
> +	}
> +
> +	pr_info("No populated RMP entries in the 2MB region containing PFN 0x%llx\n",
> +		pfn);
> +}
> +
> +void snp_dump_hva_rmpentry(unsigned long hva)
> +{
> +	unsigned int level;
> +	pgd_t *pgd;
> +	pte_t *pte;
> +
> +	pgd = __va(read_cr3_pa());
> +	pgd += pgd_index(hva);
> +	pte = lookup_address_in_pgd(pgd, hva, &level);
> +
> +	if (!pte) {
> +		pr_info("Can't dump RMP entry for HVA %lx: no PTE/PFN found\n", hva);
> +		return;
> +	}
> +
> +	dump_rmpentry(pte_pfn(*pte));

Already worked with Mike offline when I was running into issues using this 
function. Net of that conversation is that the PFN needs to be adjusted 
using the address offset if the PTE level indicates a huge page.

Additionally the loop in dump_rmpentry() needs to use ALIGN_DOWN() in 
order to get the PFN of the starting 2MB area.

Thanks,
Tom


> +}
> +EXPORT_SYMBOL_GPL(snp_dump_hva_rmpentry);