1 files changed, 114 insertions, 87 deletions

diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index 651b81cd648e..a6895e440bc3 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -7,12 +7,11 @@
  * Author: Joerg Roedel <jroedel@suse.de>
  */
 
-#define pr_fmt(fmt)	"SEV-ES: " fmt
+#define pr_fmt(fmt)	"SEV: " fmt
 
 #include <linux/sched/debug.h>	/* For show_regs() */
 #include <linux/percpu-defs.h>
 #include <linux/mem_encrypt.h>
-#include <linux/lockdep.h>
 #include <linux/printk.h>
 #include <linux/mm_types.h>
 #include <linux/set_memory.h>
@@ -192,11 +191,19 @@ void noinstr __sev_es_ist_exit(void)
 	this_cpu_write(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC], *(unsigned long *)ist);
 }
 
-static __always_inline struct ghcb *sev_es_get_ghcb(struct ghcb_state *state)
+/*
+ * Nothing shall interrupt this code path while holding the per-CPU
+ * GHCB. The backup GHCB is only for NMIs interrupting this path.
+ *
+ * Callers must disable local interrupts around it.
+ */
+static noinstr struct ghcb *__sev_get_ghcb(struct ghcb_state *state)
 {
 	struct sev_es_runtime_data *data;
 	struct ghcb *ghcb;
 
+	WARN_ON(!irqs_disabled());
+
 	data = this_cpu_read(runtime_data);
 	ghcb = &data->ghcb_page;
 
@@ -213,7 +220,9 @@ static __always_inline struct ghcb *sev_es_get_ghcb(struct ghcb_state *state)
 			data->ghcb_active        = false;
 			data->backup_ghcb_active = false;
 
+			instrumentation_begin();
 			panic("Unable to handle #VC exception! GHCB and Backup GHCB are already in use");
+			instrumentation_end();
 		}
 
 		/* Mark backup_ghcb active before writing to it */
@@ -258,17 +267,24 @@ static int vc_fetch_insn_kernel(struct es_em_ctxt *ctxt,
 static enum es_result __vc_decode_user_insn(struct es_em_ctxt *ctxt)
 {
 	char buffer[MAX_INSN_SIZE];
-	int res;
+	int insn_bytes;
 
-	res = insn_fetch_from_user_inatomic(ctxt->regs, buffer);
-	if (!res) {
+	insn_bytes = insn_fetch_from_user_inatomic(ctxt->regs, buffer);
+	if (insn_bytes == 0) {
+		/* Nothing could be copied */
 		ctxt->fi.vector     = X86_TRAP_PF;
 		ctxt->fi.error_code = X86_PF_INSTR | X86_PF_USER;
 		ctxt->fi.cr2        = ctxt->regs->ip;
 		return ES_EXCEPTION;
+	} else if (insn_bytes == -EINVAL) {
+		/* Effective RIP could not be calculated */
+		ctxt->fi.vector     = X86_TRAP_GP;
+		ctxt->fi.error_code = 0;
+		ctxt->fi.cr2        = 0;
+		return ES_EXCEPTION;
 	}
 
-	if (!insn_decode_from_regs(&ctxt->insn, ctxt->regs, buffer, res))
+	if (!insn_decode_from_regs(&ctxt->insn, ctxt->regs, buffer, insn_bytes))
 		return ES_DECODE_FAILED;
 
 	if (ctxt->insn.immediate.got)
@@ -479,11 +495,13 @@ static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt
 /* Include code shared with pre-decompression boot stage */
 #include "sev-shared.c"
 
-static __always_inline void sev_es_put_ghcb(struct ghcb_state *state)
+static noinstr void __sev_put_ghcb(struct ghcb_state *state)
 {
 	struct sev_es_runtime_data *data;
 	struct ghcb *ghcb;
 
+	WARN_ON(!irqs_disabled());
+
 	data = this_cpu_read(runtime_data);
 	ghcb = &data->ghcb_page;
 
@@ -507,7 +525,7 @@ void noinstr __sev_es_nmi_complete(void)
 	struct ghcb_state state;
 	struct ghcb *ghcb;
 
-	ghcb = sev_es_get_ghcb(&state);
+	ghcb = __sev_get_ghcb(&state);
 
 	vc_ghcb_invalidate(ghcb);
 	ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_NMI_COMPLETE);
@@ -517,7 +535,7 @@ void noinstr __sev_es_nmi_complete(void)
 	sev_es_wr_ghcb_msr(__pa_nodebug(ghcb));
 	VMGEXIT();
 
-	sev_es_put_ghcb(&state);
+	__sev_put_ghcb(&state);
 }
 
 static u64 get_jump_table_addr(void)
@@ -529,7 +547,7 @@ static u64 get_jump_table_addr(void)
 
 	local_irq_save(flags);
 
-	ghcb = sev_es_get_ghcb(&state);
+	ghcb = __sev_get_ghcb(&state);
 
 	vc_ghcb_invalidate(ghcb);
 	ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_JUMP_TABLE);
@@ -543,7 +561,7 @@ static u64 get_jump_table_addr(void)
 	    ghcb_sw_exit_info_2_is_valid(ghcb))
 		ret = ghcb->save.sw_exit_info_2;
 
-	sev_es_put_ghcb(&state);
+	__sev_put_ghcb(&state);
 
 	local_irq_restore(flags);
 
@@ -668,7 +686,7 @@ static void sev_es_ap_hlt_loop(void)
 	struct ghcb_state state;
 	struct ghcb *ghcb;
 
-	ghcb = sev_es_get_ghcb(&state);
+	ghcb = __sev_get_ghcb(&state);
 
 	while (true) {
 		vc_ghcb_invalidate(ghcb);
@@ -685,7 +703,7 @@ static void sev_es_ap_hlt_loop(void)
 			break;
 	}
 
-	sev_es_put_ghcb(&state);
+	__sev_put_ghcb(&state);
 }
 
 /*
@@ -775,7 +793,7 @@ void __init sev_es_init_vc_handling(void)
 	sev_es_setup_play_dead();
 
 	/* Secondary CPUs use the runtime #VC handler */
-	initial_vc_handler = (unsigned long)safe_stack_exc_vmm_communication;
+	initial_vc_handler = (unsigned long)kernel_exc_vmm_communication;
 }
 
 static void __init vc_early_forward_exception(struct es_em_ctxt *ctxt)
@@ -1213,14 +1231,6 @@ static enum es_result vc_handle_trap_ac(struct ghcb *ghcb,
 	return ES_EXCEPTION;
 }
 
-static __always_inline void vc_handle_trap_db(struct pt_regs *regs)
-{
-	if (user_mode(regs))
-		noist_exc_debug(regs);
-	else
-		exc_debug(regs);
-}
-
 static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt,
 					 struct ghcb *ghcb,
 					 unsigned long exit_code)
@@ -1316,44 +1326,15 @@ static __always_inline bool on_vc_fallback_stack(struct pt_regs *regs)
 	return (sp >= __this_cpu_ist_bottom_va(VC2) && sp < __this_cpu_ist_top_va(VC2));
 }
 
-/*
- * Main #VC exception handler. It is called when the entry code was able to
- * switch off the IST to a safe kernel stack.
- *
- * With the current implementation it is always possible to switch to a safe
- * stack because #VC exceptions only happen at known places, like intercepted
- * instructions or accesses to MMIO areas/IO ports. They can also happen with
- * code instrumentation when the hypervisor intercepts #DB, but the critical
- * paths are forbidden to be instrumented, so #DB exceptions currently also
- * only happen in safe places.
- */
-DEFINE_IDTENTRY_VC_SAFE_STACK(exc_vmm_communication)
+static bool vc_raw_handle_exception(struct pt_regs *regs, unsigned long error_code)
 {
-	irqentry_state_t irq_state;
 	struct ghcb_state state;
 	struct es_em_ctxt ctxt;
 	enum es_result result;
 	struct ghcb *ghcb;
+	bool ret = true;
 
-	/*
-	 * Handle #DB before calling into !noinstr code to avoid recursive #DB.
-	 */
-	if (error_code == SVM_EXIT_EXCP_BASE + X86_TRAP_DB) {
-		vc_handle_trap_db(regs);
-		return;
-	}
-
-	irq_state = irqentry_nmi_enter(regs);
-	lockdep_assert_irqs_disabled();
-	instrumentation_begin();
-
-	/*
-	 * This is invoked through an interrupt gate, so IRQs are disabled. The
-	 * code below might walk page-tables for user or kernel addresses, so
-	 * keep the IRQs disabled to protect us against concurrent TLB flushes.
-	 */
-
-	ghcb = sev_es_get_ghcb(&state);
+	ghcb = __sev_get_ghcb(&state);
 
 	vc_ghcb_invalidate(ghcb);
 	result = vc_init_em_ctxt(&ctxt, regs, error_code);
@@ -1361,7 +1342,7 @@ DEFINE_IDTENTRY_VC_SAFE_STACK(exc_vmm_communication)
 	if (result == ES_OK)
 		result = vc_handle_exitcode(&ctxt, ghcb, error_code);
 
-	sev_es_put_ghcb(&state);
+	__sev_put_ghcb(&state);
 
 	/* Done - now check the result */
 	switch (result) {
@@ -1369,17 +1350,20 @@ DEFINE_IDTENTRY_VC_SAFE_STACK(exc_vmm_communication)
 		vc_finish_insn(&ctxt);
 		break;
 	case ES_UNSUPPORTED:
-		pr_err_ratelimited("Unsupported exit-code 0x%02lx in early #VC exception (IP: 0x%lx)\n",
+		pr_err_ratelimited("Unsupported exit-code 0x%02lx in #VC exception (IP: 0x%lx)\n",
 				   error_code, regs->ip);
-		goto fail;
+		ret = false;
+		break;
 	case ES_VMM_ERROR:
 		pr_err_ratelimited("Failure in communication with VMM (exit-code 0x%02lx IP: 0x%lx)\n",
 				   error_code, regs->ip);
-		goto fail;
+		ret = false;
+		break;
 	case ES_DECODE_FAILED:
 		pr_err_ratelimited("Failed to decode instruction (exit-code 0x%02lx IP: 0x%lx)\n",
 				   error_code, regs->ip);
-		goto fail;
+		ret = false;
+		break;
 	case ES_EXCEPTION:
 		vc_forward_exception(&ctxt);
 		break;
@@ -1395,24 +1379,52 @@ DEFINE_IDTENTRY_VC_SAFE_STACK(exc_vmm_communication)
 		BUG();
 	}
 
-out:
-	instrumentation_end();
-	irqentry_nmi_exit(regs, irq_state);
+	return ret;
+}
 
-	return;
+static __always_inline bool vc_is_db(unsigned long error_code)
+{
+	return error_code == SVM_EXIT_EXCP_BASE + X86_TRAP_DB;
+}
 
-fail:
-	if (user_mode(regs)) {
-		/*
-		 * Do not kill the machine if user-space triggered the
-		 * exception. Send SIGBUS instead and let user-space deal with
-		 * it.
-		 */
-		force_sig_fault(SIGBUS, BUS_OBJERR, (void __user *)0);
-	} else {
-		pr_emerg("PANIC: Unhandled #VC exception in kernel space (result=%d)\n",
-			 result);
+/*
+ * Runtime #VC exception handler when raised from kernel mode. Runs in NMI mode
+ * and will panic when an error happens.
+ */
+DEFINE_IDTENTRY_VC_KERNEL(exc_vmm_communication)
+{
+	irqentry_state_t irq_state;
+
+	/*
+	 * With the current implementation it is always possible to switch to a
+	 * safe stack because #VC exceptions only happen at known places, like
+	 * intercepted instructions or accesses to MMIO areas/IO ports. They can
+	 * also happen with code instrumentation when the hypervisor intercepts
+	 * #DB, but the critical paths are forbidden to be instrumented, so #DB
+	 * exceptions currently also only happen in safe places.
+	 *
+	 * But keep this here in case the noinstr annotations are violated due
+	 * to bug elsewhere.
+	 */
+	if (unlikely(on_vc_fallback_stack(regs))) {
+		instrumentation_begin();
+		panic("Can't handle #VC exception from unsupported context\n");
+		instrumentation_end();
+	}
 
+	/*
+	 * Handle #DB before calling into !noinstr code to avoid recursive #DB.
+	 */
+	if (vc_is_db(error_code)) {
+		exc_debug(regs);
+		return;
+	}
+
+	irq_state = irqentry_nmi_enter(regs);
+
+	instrumentation_begin();
+
+	if (!vc_raw_handle_exception(regs, error_code)) {
 		/* Show some debug info */
 		show_regs(regs);
 
@@ -1423,23 +1435,38 @@ fail:
 		panic("Returned from Terminate-Request to Hypervisor\n");
 	}
 
-	goto out;
+	instrumentation_end();
+	irqentry_nmi_exit(regs, irq_state);
 }
 
-/* This handler runs on the #VC fall-back stack. It can cause further #VC exceptions */
-DEFINE_IDTENTRY_VC_IST(exc_vmm_communication)
+/*
+ * Runtime #VC exception handler when raised from user mode. Runs in IRQ mode
+ * and will kill the current task with SIGBUS when an error happens.
+ */
+DEFINE_IDTENTRY_VC_USER(exc_vmm_communication)
 {
+	/*
+	 * Handle #DB before calling into !noinstr code to avoid recursive #DB.
+	 */
+	if (vc_is_db(error_code)) {
+		noist_exc_debug(regs);
+		return;
+	}
+
+	irqentry_enter_from_user_mode(regs);
 	instrumentation_begin();
-	panic("Can't handle #VC exception from unsupported context\n");
-	instrumentation_end();
-}
 
-DEFINE_IDTENTRY_VC(exc_vmm_communication)
-{
-	if (likely(!on_vc_fallback_stack(regs)))
-		safe_stack_exc_vmm_communication(regs, error_code);
-	else
-		ist_exc_vmm_communication(regs, error_code);
+	if (!vc_raw_handle_exception(regs, error_code)) {
+		/*
+		 * Do not kill the machine if user-space triggered the
+		 * exception. Send SIGBUS instead and let user-space deal with
+		 * it.
+		 */
+		force_sig_fault(SIGBUS, BUS_OBJERR, (void __user *)0);
+	}
+
+	instrumentation_end();
+	irqentry_exit_to_user_mode(regs);
 }
 
 bool __init handle_vc_boot_ghcb(struct pt_regs *regs)