From: Brijesh Singh <[email protected]>
The RMPUPDATE instruction writes a new RMP entry in the RMP Table. The
hypervisor will use the instruction to add pages to the RMP table. See
APM3 for details on the instruction operations.
The PSMASH instruction expands a 2MB RMP entry into a corresponding set
of contiguous 4KB RMP entries. The hypervisor will use this instruction
to adjust the RMP entry without invalidating it.
Add helpers to make use of these instructions.
Signed-off-by: Brijesh Singh <[email protected]>
Signed-off-by: Ashish Kalra <[email protected]>
[mdr: add RMPUPDATE retry logic for transient FAIL_OVERLAP errors]
Signed-off-by: Michael Roth <[email protected]>
---
arch/x86/include/asm/sev.h | 23 +++++++++++
arch/x86/virt/svm/sev.c | 79 ++++++++++++++++++++++++++++++++++++++
2 files changed, 102 insertions(+)
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index 2c53e3de0b71..d3ccb7a0c7e9 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -87,10 +87,23 @@ extern bool handle_vc_boot_ghcb(struct pt_regs *regs);
/* Software defined (when rFlags.CF = 1) */
#define PVALIDATE_FAIL_NOUPDATE 255
+/* RMUPDATE detected 4K page and 2MB page overlap. */
+#define RMPUPDATE_FAIL_OVERLAP 4
+
/* RMP page size */
#define RMP_PG_SIZE_4K 0
#define RMP_PG_SIZE_2M 1
#define RMP_TO_PG_LEVEL(level) (((level) == RMP_PG_SIZE_4K) ? PG_LEVEL_4K : PG_LEVEL_2M)
+#define PG_LEVEL_TO_RMP(level) (((level) == PG_LEVEL_4K) ? RMP_PG_SIZE_4K : RMP_PG_SIZE_2M)
+
+struct rmp_state {
+ u64 gpa;
+ u8 assigned;
+ u8 pagesize;
+ u8 immutable;
+ u8 rsvd;
+ u32 asid;
+} __packed;
#define RMPADJUST_VMSA_PAGE_BIT BIT(16)
@@ -248,10 +261,20 @@ static inline u64 sev_get_status(void) { return 0; }
bool snp_probe_rmptable_info(void);
int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level);
void snp_dump_hva_rmpentry(unsigned long address);
+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);
#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) {}
+static inline int psmash(u64 pfn) { return -ENODEV; }
+static inline int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, int asid,
+ bool immutable)
+{
+ return -ENODEV;
+}
+static inline int rmp_make_shared(u64 pfn, enum pg_level level) { return -ENODEV; }
#endif
#endif
diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c
index 7c9ced8911e9..ff9fa0a85a7f 100644
--- a/arch/x86/virt/svm/sev.c
+++ b/arch/x86/virt/svm/sev.c
@@ -343,3 +343,82 @@ void snp_dump_hva_rmpentry(unsigned long hva)
dump_rmpentry(pte_pfn(*pte));
}
EXPORT_SYMBOL_GPL(snp_dump_hva_rmpentry);
+
+/*
+ * PSMASH a 2MB aligned page into 4K pages in the RMP table while preserving the
+ * Validated bit.
+ */
+int psmash(u64 pfn)
+{
+ unsigned long paddr = pfn << PAGE_SHIFT;
+ int ret;
+
+ if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+ return -ENODEV;
+
+ if (!pfn_valid(pfn))
+ return -EINVAL;
+
+ /* Binutils version 2.36 supports the PSMASH mnemonic. */
+ asm volatile(".byte 0xF3, 0x0F, 0x01, 0xFF"
+ : "=a" (ret)
+ : "a" (paddr)
+ : "memory", "cc");
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(psmash);
+
+static int rmpupdate(u64 pfn, struct rmp_state *state)
+{
+ unsigned long paddr = pfn << PAGE_SHIFT;
+ int ret;
+
+ if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+ return -ENODEV;
+
+ do {
+ /* Binutils version 2.36 supports the RMPUPDATE mnemonic. */
+ asm volatile(".byte 0xF2, 0x0F, 0x01, 0xFE"
+ : "=a" (ret)
+ : "a" (paddr), "c" ((unsigned long)state)
+ : "memory", "cc");
+ } while (ret == RMPUPDATE_FAIL_OVERLAP);
+
+ if (ret) {
+ pr_err("RMPUPDATE failed for PFN %llx, ret: %d\n", pfn, ret);
+ dump_rmpentry(pfn);
+ dump_stack();
+ return -EFAULT;
+ }
+
+ return 0;
+}
+
+/* Transition a page to guest-owned/private state in the RMP table. */
+int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, int asid, bool immutable)
+{
+ struct rmp_state state;
+
+ memset(&state, 0, sizeof(state));
+ state.assigned = 1;
+ state.asid = asid;
+ state.immutable = immutable;
+ state.gpa = gpa;
+ state.pagesize = PG_LEVEL_TO_RMP(level);
+
+ return rmpupdate(pfn, &state);
+}
+EXPORT_SYMBOL_GPL(rmp_make_private);
+
+/* Transition a page to hypervisor-owned/shared state in the RMP table. */
+int rmp_make_shared(u64 pfn, enum pg_level level)
+{
+ struct rmp_state state;
+
+ memset(&state, 0, sizeof(state));
+ state.pagesize = PG_LEVEL_TO_RMP(level);
+
+ return rmpupdate(pfn, &state);
+}
+EXPORT_SYMBOL_GPL(rmp_make_shared);
--
2.25.1
On Sat, Dec 30, 2023 at 10:19:38AM -0600, Michael Roth wrote:
> +static int rmpupdate(u64 pfn, struct rmp_state *state)
> +{
> + unsigned long paddr = pfn << PAGE_SHIFT;
> + int ret;
> +
> + if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
> + return -ENODEV;
> +
Let's document this deal here and leave the door open for potential
future improvements:
---
diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c
index c9156ce47c77..1fbf9843c163 100644
--- a/arch/x86/virt/svm/sev.c
+++ b/arch/x86/virt/svm/sev.c
@@ -374,6 +374,21 @@ static int rmpupdate(u64 pfn, struct rmp_state *state)
if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
return -ENODEV;
+ /*
+ * It is expected that those operations are seldom enough so
+ * that no mutual exclusion of updaters is needed and thus the
+ * overlap error condition below should happen very seldomly and
+ * would get resolved relatively quickly by the firmware.
+ *
+ * If not, one could consider introducing a mutex or so here to
+ * sync concurrent RMP updates and thus diminish the amount of
+ * cases where firmware needs to lock 2M ranges to protect
+ * against concurrent updates.
+ *
+ * The optimal solution would be range locking to avoid locking
+ * disjoint regions unnecessarily but there's no support for
+ * that yet.
+ */
do {
/* Binutils version 2.36 supports the RMPUPDATE mnemonic. */
asm volatile(".byte 0xF2, 0x0F, 0x01, 0xFE"
> + do {
> + /* Binutils version 2.36 supports the RMPUPDATE mnemonic. */
> + asm volatile(".byte 0xF2, 0x0F, 0x01, 0xFE"
> + : "=a" (ret)
> + : "a" (paddr), "c" ((unsigned long)state)
> + : "memory", "cc");
> + } while (ret == RMPUPDATE_FAIL_OVERLAP);
> +
> + if (ret) {
> + pr_err("RMPUPDATE failed for PFN %llx, ret: %d\n", pfn, ret);
> + dump_rmpentry(pfn);
> + dump_stack();
> + return -EFAULT;
> + }
> +
> + return 0;
> +}
--
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquette