[PATCH v2 2/2] x86/sev: Add callback to apply RMP table fixups for kexec.

[Ashish Kalra]

From: Ashish Kalra <ashish.kalra@xxxxxxx>

Handle cases where the RMP table placement in the BIOS is
not 2M aligned and then the kexec kernel could try to allocate
from within that chunk and that causes a fatal RMP fault.
Check if RMP table start & end physical range in e820_table
is not aligned to 2MB and in that case use e820__range_update()
to map this range to reserved.

The callback to apply these RMP table fixups needs to be called
after the e820 tables are setup/populated and before the e820 map
has been converted to the standard Linux memory resources and e820 map
is no longer used and modifying it has no effect.

Fixes: c3b86e61b756 ("x86/cpufeatures: Enable/unmask SEV-SNP CPU feature")
Signed-off-by: Ashish Kalra <ashish.kalra@xxxxxxx>
---
 arch/x86/include/asm/sev.h |  2 ++
 arch/x86/mm/mem_encrypt.c  |  3 +++
 arch/x86/virt/svm/sev.c    | 44 ++++++++++++++++++++++++++++++++++++++
 3 files changed, 49 insertions(+)

diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index 7f57382afee4..6600ac467cf9 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -269,6 +269,7 @@ int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 asid, bool immut
 int rmp_make_shared(u64 pfn, enum pg_level level);
 void snp_leak_pages(u64 pfn, unsigned int npages);
 void kdump_sev_callback(void);
+void snp_rmptable_e820_fixup(void);
 #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; }
@@ -282,6 +283,7 @@ static inline int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 as
 static inline int rmp_make_shared(u64 pfn, enum pg_level level) { return -ENODEV; }
 static inline void snp_leak_pages(u64 pfn, unsigned int npages) {}
 static inline void kdump_sev_callback(void) { }
+static inline void snp_rmptable_e820_fixup(void) {}
 #endif
 
 #endif
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 6f3b3e028718..765ce94e4b89 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -102,6 +102,9 @@ void __init mem_encrypt_setup_arch(void)
 	phys_addr_t total_mem = memblock_phys_mem_size();
 	unsigned long size;
 
+	if (cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+		snp_rmptable_e820_fixup();
+
 	if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
 		return;
 
diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c
index ab0e8448bb6e..d999ff7f1671 100644
--- a/arch/x86/virt/svm/sev.c
+++ b/arch/x86/virt/svm/sev.c
@@ -163,6 +163,50 @@ bool snp_probe_rmptable_info(void)
 	return true;
 }
 
+/*
+ * Callback to do any RMP table fixups, needs to be called
+ * after e820__memory_setup(), after the e820 tables are
+ * setup/populated and before e820__reserve_resources(), before
+ * the e820 map has been converted to the standard Linux memory
+ * resources and e820 map is no longer used and modifying it
+ * has no effect.
+ */
+void __init snp_rmptable_e820_fixup(void)
+{
+	u64 pa;
+
+	/*
+	 * Handle cases where the RMP table placement in the BIOS is not 2M aligned
+	 * and then the kexec kernel could try to allocate from within that chunk
+	 * and that causes a fatal RMP fault. Check if RMP table start & end
+	 * physical range in e820_table is not aligned to 2MB and in that case use
+	 * e820__range_update() to map this range to reserved, e820__range_update()
+	 * nicely handles partial range update and also merges any consecutive
+	 * ranges of the same type.
+	 */
+	pa = probed_rmp_base;
+	if (!IS_ALIGNED(pa, PMD_SIZE)) {
+		pa = ALIGN_DOWN(pa, PMD_SIZE);
+		if (e820__mapped_any(pa, pa + PMD_SIZE, E820_TYPE_RAM)) {
+			pr_info("Reserving start of RMP table on a 2MB boundary [0x%016llx]\n", pa);
+			e820__range_update(pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
+			e820__range_update_kexec(pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
+			e820__range_update_firmware(pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
+		}
+	}
+
+	pa = probed_rmp_base + probed_rmp_size;
+	if (!IS_ALIGNED(pa, PMD_SIZE)) {
+		pa = ALIGN_DOWN(pa, PMD_SIZE);
+		if (e820__mapped_any(pa, pa + PMD_SIZE, E820_TYPE_RAM)) {
+			pr_info("Reserving end of RMP table on a 2MB boundary [0x%016llx]\n", pa);
+			e820__range_update(pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
+			e820__range_update_kexec(pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
+			e820__range_update_firmware(pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
+		}
+	}
+}
+
 /*
  * Do the necessary preparations which are verified by the firmware as
  * described in the SNP_INIT_EX firmware command description in the SNP
-- 
2.34.1