lkml.org 
[lkml]   [2021]   [Jul]   [28]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
SubjectRe: [BUG] crypto: ccp: random crashes after kexec on AMD with PSP since commit 97f9ac3d
Date
Hi Lucas,

>On several AMD systems, we see random crashes after kexec, during the
>boot of the new system (typically 1 out of 5 boots ends up with a
>crash).

>According to git bisect, the regression was introduced by commit
>97f9ac3d ("crypto: ccp - Add support for SEV-ES to the PSP driver"),
>included since 5.8-rc1. 5.14-rc3 is still affected.

Can you try the below patch and confirm whether it fixes the random
crashes seen during the kexec.

From: Brijesh Singh <brijesh.singh@amd.com>
Date: Tue, 27 Jul 2021 21:48:25 -0500
Subject: [PATCH] crypto: ccp: shutdown SEV firmware on kexec

The commit 97f9ac3db6612 ("crypto: ccp - Add support for SEV-ES to the
PSP driver") added support to allocate Trusted Memory Region (TMR) that
is used during the SEV-ES firmware initialization. The TMR memory region
is locked by the firmware and access to it is disallowed by the x86
software. The firmware SHUTDOWN command can be used to unlock the TMR.

Fixes: 97f9ac3db6612 ("crypto: ccp - Add support for SEV-ES to the PSP driver")
Signed-off-by: Brijesh Singh <brijesh.singh@amd.com>
---
drivers/crypto/ccp/sev-dev.c | 49 +++++++++++++++++-------------------
drivers/crypto/ccp/sp-pci.c | 12 +++++++++
2 files changed, 35 insertions(+), 26 deletions(-)

diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c
index 91808402e0bf..2ecb0e1f65d8 100644
--- a/drivers/crypto/ccp/sev-dev.c
+++ b/drivers/crypto/ccp/sev-dev.c
@@ -300,6 +300,9 @@ static int __sev_platform_shutdown_locked(int *error)
struct sev_device *sev = psp_master->sev_data;
int ret;

+ if (sev->state == SEV_STATE_UNINIT)
+ return 0;
+
ret = __sev_do_cmd_locked(SEV_CMD_SHUTDOWN, NULL, error);
if (ret)
return ret;
@@ -1019,6 +1022,20 @@ int sev_dev_init(struct psp_device *psp)
return ret;
}

+static void sev_firmware_shutdown(struct sev_device *sev)
+{
+ sev_platform_shutdown(NULL);
+
+ if (sev_es_tmr) {
+ /* The TMR area was encrypted, flush it from the cache */
+ wbinvd_on_all_cpus();
+
+ free_pages((unsigned long)sev_es_tmr,
+ get_order(SEV_ES_TMR_SIZE));
+ sev_es_tmr = NULL;
+ }
+}
+
void sev_dev_destroy(struct psp_device *psp)
{
struct sev_device *sev = psp->sev_data;
@@ -1026,6 +1043,8 @@ void sev_dev_destroy(struct psp_device *psp)
if (!sev)
return;

+ sev_firmware_shutdown(sev);
+
if (sev->misc)
kref_put(&misc_dev->refcount, sev_exit);

@@ -1056,21 +1075,6 @@ void sev_pci_init(void)
if (sev_get_api_version())
goto err;

- /*
- * If platform is not in UNINIT state then firmware upgrade and/or
- * platform INIT command will fail. These command require UNINIT state.
- *
- * In a normal boot we should never run into case where the firmware
- * is not in UNINIT state on boot. But in case of kexec boot, a reboot
- * may not go through a typical shutdown sequence and may leave the
- * firmware in INIT or WORKING state.
- */
-
- if (sev->state != SEV_STATE_UNINIT) {
- sev_platform_shutdown(NULL);
- sev->state = SEV_STATE_UNINIT;
- }
-
if (sev_version_greater_or_equal(0, 15) &&
sev_update_firmware(sev->dev) == 0)
sev_get_api_version();
@@ -1115,17 +1119,10 @@ void sev_pci_init(void)

void sev_pci_exit(void)
{
- if (!psp_master->sev_data)
- return;
-
- sev_platform_shutdown(NULL);
+ struct sev_device *sev = psp_master->sev_data;

- if (sev_es_tmr) {
- /* The TMR area was encrypted, flush it from the cache */
- wbinvd_on_all_cpus();
+ if (!sev)
+ return;

- free_pages((unsigned long)sev_es_tmr,
- get_order(SEV_ES_TMR_SIZE));
- sev_es_tmr = NULL;
- }
+ sev_firmware_shutdown(sev);
}
diff --git a/drivers/crypto/ccp/sp-pci.c b/drivers/crypto/ccp/sp-pci.c
index 6fb6ba35f89d..9bcc1884c06a 100644
--- a/drivers/crypto/ccp/sp-pci.c
+++ b/drivers/crypto/ccp/sp-pci.c
@@ -241,6 +241,17 @@ static int sp_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
return ret;
}

+static void sp_pci_shutdown(struct pci_dev *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct sp_device *sp = dev_get_drvdata(dev);
+
+ if (!sp)
+ return;
+
+ sp_destroy(sp);
+}
+
static void sp_pci_remove(struct pci_dev *pdev)
{
struct device *dev = &pdev->dev;
@@ -371,6 +382,7 @@ static struct pci_driver sp_pci_driver = {
.id_table = sp_pci_table,
.probe = sp_pci_probe,
.remove = sp_pci_remove,
+ .shutdown = sp_pci_shutdown,
.driver.pm = &sp_pci_pm_ops,
};

--
2.17.1
\
 
 \ /
  Last update: 2021-07-28 15:36    [W:0.044 / U:0.076 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site