[PATCH Part2 v5 09/45] x86/fault: Add support to dump RMP entry on fault

[Brijesh Singh]

When SEV-SNP is enabled globally, a write from the host goes through the
RMP check. If the hardware encounters the check failure, then it raises
the #PF (with RMP set). Dump the RMP entry at the faulting pfn to help
the debug.

Signed-off-by: Brijesh Singh <brijesh.singh@xxxxxxx>
---
 arch/x86/include/asm/sev.h |  7 +++++++
 arch/x86/kernel/sev.c      | 43 ++++++++++++++++++++++++++++++++++++++
 arch/x86/mm/fault.c        | 17 +++++++++++----
 include/linux/sev.h        |  2 ++
 4 files changed, 65 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index 92ced9626e95..569294f687e6 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -106,6 +106,11 @@ struct __packed rmpentry {
 
 #define rmpentry_assigned(x)	((x)->info.assigned)
 #define rmpentry_pagesize(x)	((x)->info.pagesize)
+#define rmpentry_vmsa(x)	((x)->info.vmsa)
+#define rmpentry_asid(x)	((x)->info.asid)
+#define rmpentry_validated(x)	((x)->info.validated)
+#define rmpentry_gpa(x)		((unsigned long)(x)->info.gpa)
+#define rmpentry_immutable(x)	((x)->info.immutable)
 
 #define RMPADJUST_VMSA_PAGE_BIT		BIT(16)
 
@@ -165,6 +170,7 @@ void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op
 void snp_set_memory_shared(unsigned long vaddr, unsigned int npages);
 void snp_set_memory_private(unsigned long vaddr, unsigned int npages);
 void snp_set_wakeup_secondary_cpu(void);
+void dump_rmpentry(u64 pfn);
 #ifdef __BOOT_COMPRESSED
 bool sev_snp_enabled(void);
 #else
@@ -188,6 +194,7 @@ static inline void snp_set_memory_shared(unsigned long vaddr, unsigned int npage
 static inline void snp_set_memory_private(unsigned long vaddr, unsigned int npages) { }
 static inline void snp_set_wakeup_secondary_cpu(void) { }
 static inline void sev_snp_cpuid_init(struct boot_params *bp) { }
+static inline void dump_rmpentry(u64 pfn) {}
 #ifdef __BOOT_COMPRESSED
 static inline bool sev_snp_enabled { return false; }
 #else
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index bad41deb8335..8b3e83e50468 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -2404,6 +2404,49 @@ static struct rmpentry *__snp_lookup_rmpentry(u64 pfn, int *level)
 	return entry;
 }
 
+void dump_rmpentry(u64 pfn)
+{
+	unsigned long pfn_end;
+	struct rmpentry *e;
+	int level;
+
+	e = __snp_lookup_rmpentry(pfn, &level);
+	if (!e) {
+		pr_alert("failed to read RMP entry pfn 0x%llx\n", pfn);
+		return;
+	}
+
+	if (rmpentry_assigned(e)) {
+		pr_alert("RMPEntry paddr 0x%llx [assigned=%d immutable=%d pagesize=%d gpa=0x%lx"
+			" asid=%d vmsa=%d validated=%d]\n", pfn << PAGE_SHIFT,
+			rmpentry_assigned(e), rmpentry_immutable(e), rmpentry_pagesize(e),
+			rmpentry_gpa(e), rmpentry_asid(e), rmpentry_vmsa(e),
+			rmpentry_validated(e));
+		return;
+	}
+
+	/*
+	 * If the RMP entry at the faulting pfn was not assigned, then we do not
+	 * know what caused the RMP violation. To get some useful debug information,
+	 * let iterate through the entire 2MB region, and dump the RMP entries if
+	 * one of the bit in the RMP entry is set.
+	 */
+	pfn = pfn & ~(PTRS_PER_PMD - 1);
+	pfn_end = pfn + PTRS_PER_PMD;
+
+	while (pfn < pfn_end) {
+		e = __snp_lookup_rmpentry(pfn, &level);
+		if (!e)
+			return;
+
+		if (e->low || e->high)
+			pr_alert("RMPEntry paddr 0x%llx: [high=0x%016llx low=0x%016llx]\n",
+				 pfn << PAGE_SHIFT, e->high, e->low);
+		pfn++;
+	}
+}
+EXPORT_SYMBOL_GPL(dump_rmpentry);
+
 /*
  * Return 1 if the RMP entry is assigned, 0 if it exists but is not assigned,
  * and -errno if there is no corresponding RMP entry.
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index f2d543b92f43..9cd33169dfb5 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -33,6 +33,7 @@
 #include <asm/pgtable_areas.h>		/* VMALLOC_START, ...		*/
 #include <asm/kvm_para.h>		/* kvm_handle_async_pf		*/
 #include <asm/vdso.h>			/* fixup_vdso_exception()	*/
+#include <asm/sev.h>			/* dump_rmpentry()		*/
 
 #define CREATE_TRACE_POINTS
 #include <asm/trace/exceptions.h>
@@ -289,7 +290,7 @@ static bool low_pfn(unsigned long pfn)
 	return pfn < max_low_pfn;
 }
 
-static void dump_pagetable(unsigned long address)
+static void dump_pagetable(unsigned long address, bool show_rmpentry)
 {
 	pgd_t *base = __va(read_cr3_pa());
 	pgd_t *pgd = &base[pgd_index(address)];
@@ -345,10 +346,11 @@ static int bad_address(void *p)
 	return get_kernel_nofault(dummy, (unsigned long *)p);
 }
 
-static void dump_pagetable(unsigned long address)
+static void dump_pagetable(unsigned long address, bool show_rmpentry)
 {
 	pgd_t *base = __va(read_cr3_pa());
 	pgd_t *pgd = base + pgd_index(address);
+	unsigned long pfn;
 	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
@@ -366,6 +368,7 @@ static void dump_pagetable(unsigned long address)
 	if (bad_address(p4d))
 		goto bad;
 
+	pfn = p4d_pfn(*p4d);
 	pr_cont("P4D %lx ", p4d_val(*p4d));
 	if (!p4d_present(*p4d) || p4d_large(*p4d))
 		goto out;
@@ -374,6 +377,7 @@ static void dump_pagetable(unsigned long address)
 	if (bad_address(pud))
 		goto bad;
 
+	pfn = pud_pfn(*pud);
 	pr_cont("PUD %lx ", pud_val(*pud));
 	if (!pud_present(*pud) || pud_large(*pud))
 		goto out;
@@ -382,6 +386,7 @@ static void dump_pagetable(unsigned long address)
 	if (bad_address(pmd))
 		goto bad;
 
+	pfn = pmd_pfn(*pmd);
 	pr_cont("PMD %lx ", pmd_val(*pmd));
 	if (!pmd_present(*pmd) || pmd_large(*pmd))
 		goto out;
@@ -390,9 +395,13 @@ static void dump_pagetable(unsigned long address)
 	if (bad_address(pte))
 		goto bad;
 
+	pfn = pte_pfn(*pte);
 	pr_cont("PTE %lx", pte_val(*pte));
 out:
 	pr_cont("\n");
+
+	if (show_rmpentry)
+		dump_rmpentry(pfn);
 	return;
 bad:
 	pr_info("BAD\n");
@@ -578,7 +587,7 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long ad
 		show_ldttss(&gdt, "TR", tr);
 	}
 
-	dump_pagetable(address);
+	dump_pagetable(address, error_code & X86_PF_RMP);
 }
 
 static noinline void
@@ -595,7 +604,7 @@ pgtable_bad(struct pt_regs *regs, unsigned long error_code,
 
 	printk(KERN_ALERT "%s: Corrupted page table at address %lx\n",
 	       tsk->comm, address);
-	dump_pagetable(address);
+	dump_pagetable(address, false);
 
 	if (__die("Bad pagetable", regs, error_code))
 		sig = 0;
diff --git a/include/linux/sev.h b/include/linux/sev.h
index 1a68842789e1..734b13a69c54 100644
--- a/include/linux/sev.h
+++ b/include/linux/sev.h
@@ -16,6 +16,7 @@ int snp_lookup_rmpentry(u64 pfn, int *level);
 int psmash(u64 pfn);
 int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, int asid, bool immutable);
 int rmp_make_shared(u64 pfn, enum pg_level level);
+void dump_rmpentry(u64 pfn);
 #else
 static inline int snp_lookup_rmpentry(u64 pfn, int *level) { return 0; }
 static inline int psmash(u64 pfn) { return -ENXIO; }
@@ -25,6 +26,7 @@ static inline int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, int as
 	return -ENODEV;
 }
 static inline int rmp_make_shared(u64 pfn, enum pg_level level) { return -ENODEV; }
+static inline void dump_rmpentry(u64 pfn) { }
 
 #endif /* CONFIG_AMD_MEM_ENCRYPT */
 #endif /* __LINUX_SEV_H */
-- 
2.17.1