diff mbox series

[v10,50/50] crypto: ccp: Add panic notifier for SEV/SNP firmware shutdown on kdump

Message ID 20231016132819.1002933-51-michael.roth@amd.com (mailing list archive)
State New, archived
Headers show
Series Add AMD Secure Nested Paging (SEV-SNP) Hypervisor Support | expand

Commit Message

Michael Roth Oct. 16, 2023, 1:28 p.m. UTC
From: Ashish Kalra <ashish.kalra@amd.com>

Add a kdump safe version of sev_firmware_shutdown() registered as a
crash_kexec_post_notifier, which is invoked during panic/crash to do
SEV/SNP shutdown. This is required for transitioning all IOMMU pages
to reclaim/hypervisor state, otherwise re-init of IOMMU pages during
crashdump kernel boot fails and panics the crashdump kernel. This
panic notifier runs in atomic context, hence it ensures not to
acquire any locks/mutexes and polls for PSP command completion
instead of depending on PSP command completion interrupt.

Signed-off-by: Ashish Kalra <ashish.kalra@amd.com>
[mdr: remove use of "we" in comments]
Signed-off-by: Michael Roth <michael.roth@amd.com>
---
 arch/x86/kernel/crash.c      |   7 +++
 drivers/crypto/ccp/sev-dev.c | 112 +++++++++++++++++++++++++----------
 2 files changed, 89 insertions(+), 30 deletions(-)
diff mbox series

Patch

diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index c92d88680dbf..23ede774d31b 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -59,6 +59,13 @@  static void kdump_nmi_callback(int cpu, struct pt_regs *regs)
 	 */
 	cpu_emergency_stop_pt();
 
+	/*
+	 * for SNP do wbinvd() on remote CPUs to
+	 * safely do SNP_SHUTDOWN on the local CPU.
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+		wbinvd();
+
 	disable_local_APIC();
 }
 
diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c
index 26218df1371e..21a3064f30c9 100644
--- a/drivers/crypto/ccp/sev-dev.c
+++ b/drivers/crypto/ccp/sev-dev.c
@@ -21,6 +21,7 @@ 
 #include <linux/hw_random.h>
 #include <linux/ccp.h>
 #include <linux/firmware.h>
+#include <linux/panic_notifier.h>
 #include <linux/gfp.h>
 #include <linux/cpufeature.h>
 #include <linux/fs.h>
@@ -137,6 +138,26 @@  static int sev_wait_cmd_ioc(struct sev_device *sev,
 {
 	int ret;
 
+	/*
+	 * If invoked during panic handling, local interrupts are disabled,
+	 * so the PSP command completion interrupt can't be used. Poll for
+	 * PSP command completion instead.
+	 */
+	if (irqs_disabled()) {
+		unsigned long timeout_usecs = (timeout * USEC_PER_SEC) / 10;
+
+		/* Poll for SEV command completion: */
+		while (timeout_usecs--) {
+			*reg = ioread32(sev->io_regs + sev->vdata->cmdresp_reg);
+			if (*reg & PSP_CMDRESP_RESP)
+				return 0;
+
+			udelay(10);
+		}
+
+		return -ETIMEDOUT;
+	}
+
 	ret = wait_event_timeout(sev->int_queue,
 			sev->int_rcvd, timeout * HZ);
 	if (!ret)
@@ -1058,17 +1079,6 @@  static int __sev_platform_shutdown_locked(int *error)
 	return ret;
 }
 
-static int sev_platform_shutdown(int *error)
-{
-	int rc;
-
-	mutex_lock(&sev_cmd_mutex);
-	rc = __sev_platform_shutdown_locked(NULL);
-	mutex_unlock(&sev_cmd_mutex);
-
-	return rc;
-}
-
 static int sev_get_platform_state(int *state, int *error)
 {
 	struct sev_user_data_status data;
@@ -1483,7 +1493,7 @@  static int __sev_snp_init_locked(int *error)
 	return rc;
 }
 
-static int __sev_snp_shutdown_locked(int *error)
+static int __sev_snp_shutdown_locked(int *error, bool in_panic)
 {
 	struct sev_device *sev = psp_master->sev_data;
 	struct sev_data_snp_shutdown_ex data;
@@ -1500,7 +1510,16 @@  static int __sev_snp_shutdown_locked(int *error)
 	sev_snp_certs_put(sev->snp_certs);
 	sev->snp_certs = NULL;
 
-	wbinvd_on_all_cpus();
+	/*
+	 * If invoked during panic handling, local interrupts are disabled
+	 * and all CPUs are stopped, so wbinvd_on_all_cpus() can't be called.
+	 * In that case, a wbinvd() is done on remote CPUs via the NMI
+	 * callback, so only a local wbinvd() is needed here.
+	 */
+	if (!in_panic)
+		wbinvd_on_all_cpus();
+	else
+		wbinvd();
 
 retry:
 	ret = __sev_do_cmd_locked(SEV_CMD_SNP_SHUTDOWN_EX, &data, error);
@@ -1543,17 +1562,6 @@  static int __sev_snp_shutdown_locked(int *error)
 	return ret;
 }
 
-static int sev_snp_shutdown(int *error)
-{
-	int rc;
-
-	mutex_lock(&sev_cmd_mutex);
-	rc = __sev_snp_shutdown_locked(error);
-	mutex_unlock(&sev_cmd_mutex);
-
-	return rc;
-}
-
 static int sev_ioctl_do_pek_import(struct sev_issue_cmd *argp, bool writable)
 {
 	struct sev_device *sev = psp_master->sev_data;
@@ -2262,19 +2270,29 @@  int sev_dev_init(struct psp_device *psp)
 	return ret;
 }
 
-static void sev_firmware_shutdown(struct sev_device *sev)
+static void __sev_firmware_shutdown(struct sev_device *sev, bool in_panic)
 {
 	int error;
 
-	sev_platform_shutdown(NULL);
+	__sev_platform_shutdown_locked(NULL);
 
 	if (sev_es_tmr) {
-		/* The TMR area was encrypted, flush it from the cache */
-		wbinvd_on_all_cpus();
+		/*
+		 * The TMR area was encrypted, flush it from the cache
+		 *
+		 * If invoked during panic handling, local interrupts are
+		 * disabled and all CPUs are stopped, so wbinvd_on_all_cpus()
+		 * can't be used. In that case, wbinvd() is done on remote CPUs
+		 * via the NMI callback, so a local wbinvd() is sufficient here.
+		 */
+		if (!in_panic)
+			wbinvd_on_all_cpus();
+		else
+			wbinvd();
 
 		__snp_free_firmware_pages(virt_to_page(sev_es_tmr),
 					  get_order(sev_es_tmr_size),
-					  false);
+					  true);
 		sev_es_tmr = NULL;
 	}
 
@@ -2295,7 +2313,14 @@  static void sev_firmware_shutdown(struct sev_device *sev)
 	 */
 	free_snp_host_map(sev);
 
-	sev_snp_shutdown(&error);
+	__sev_snp_shutdown_locked(&error, in_panic);
+}
+
+static void sev_firmware_shutdown(struct sev_device *sev)
+{
+	mutex_lock(&sev_cmd_mutex);
+	__sev_firmware_shutdown(sev, false);
+	mutex_unlock(&sev_cmd_mutex);
 }
 
 void sev_dev_destroy(struct psp_device *psp)
@@ -2313,6 +2338,28 @@  void sev_dev_destroy(struct psp_device *psp)
 	psp_clear_sev_irq_handler(psp);
 }
 
+static int sev_snp_shutdown_on_panic(struct notifier_block *nb,
+				     unsigned long reason, void *arg)
+{
+	struct sev_device *sev = psp_master->sev_data;
+
+	/*
+	 * Panic callbacks are executed with all other CPUs stopped,
+	 * so don't wait for sev_cmd_mutex to be released since it
+	 * would block here forever.
+	 */
+	if (mutex_is_locked(&sev_cmd_mutex))
+		return NOTIFY_DONE;
+
+	__sev_firmware_shutdown(sev, true);
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block sev_snp_panic_notifier = {
+	.notifier_call = sev_snp_shutdown_on_panic,
+};
+
 int sev_issue_cmd_external_user(struct file *filep, unsigned int cmd,
 				void *data, int *error)
 {
@@ -2360,6 +2407,8 @@  void sev_pci_init(void)
 	dev_info(sev->dev, "SEV%s API:%d.%d build:%d\n", sev->snp_initialized ?
 		"-SNP" : "", sev->api_major, sev->api_minor, sev->build);
 
+	atomic_notifier_chain_register(&panic_notifier_list,
+				       &sev_snp_panic_notifier);
 	return;
 
 err:
@@ -2375,4 +2424,7 @@  void sev_pci_exit(void)
 		return;
 
 	sev_firmware_shutdown(sev);
+
+	atomic_notifier_chain_unregister(&panic_notifier_list,
+					 &sev_snp_panic_notifier);
 }