* [PATCH v5 2/4] x86/sev: Change snp_guest_issue_request's fw_err
2022-11-02 15:18 [PATCH v5 0/4] Add throttling detection to sev-guest Dionna Glaze
2022-11-02 15:18 ` [PATCH v5 1/4] ccp: Name -1 return value as SEV_RET_NO_FW_CALL Dionna Glaze
@ 2022-11-02 15:18 ` Dionna Glaze
2022-11-02 15:18 ` [PATCH v5 3/4] virt/coco/sev-guest: Remove err in handle_guest_request Dionna Glaze
` (2 subsequent siblings)
4 siblings, 0 replies; 9+ messages in thread
From: Dionna Glaze @ 2022-11-02 15:18 UTC (permalink / raw)
To: linux-kernel, x86
Cc: Dionna Glaze, Tom Lendacky, Paolo Bonzini, Joerg Roedel,
Peter Gonda, Thomas Gleixner, Dave Hansen
The GHCB specification declares that the firmware error value for a
guest request will be stored in the lower 32 bits of EXIT_INFO_2.
The upper 32 bits are for the VMM's own error code. The fw_err argument
is thus a misnomer, and callers will need access to all 64 bits.
The type of unsigned long also causes problems, since sw_exit_info2 is
u64 (unsigned long long) vs the argument's previous unsigned long*.
The signature change requires the follow-up change to
drivers/virt/coco/sev-guest to use the new expected type in order to
compile.
The firmware might not even be called, so we bookend the call with the
no firmware call error and clearing the error.
Cc: Tom Lendacky <Thomas.Lendacky@amd.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Joerg Roedel <jroedel@suse.de>
Cc: Peter Gonda <pgonda@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Fixes: d5af44dde546 ("x86/sev: Provide support for SNP guest request NAEs")
Signed-off-by: Dionna Glaze <dionnaglaze@google.com>
---
arch/x86/include/asm/sev.h | 4 ++--
arch/x86/kernel/sev.c | 10 ++++++----
2 files changed, 8 insertions(+), 6 deletions(-)
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index ebc271bb6d8e..05de34d10d89 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -196,7 +196,7 @@ void snp_set_memory_private(unsigned long vaddr, unsigned int npages);
void snp_set_wakeup_secondary_cpu(void);
bool snp_init(struct boot_params *bp);
void __init __noreturn snp_abort(void);
-int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned long *fw_err);
+int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, u64 *exitinfo2);
#else
static inline void sev_es_ist_enter(struct pt_regs *regs) { }
static inline void sev_es_ist_exit(void) { }
@@ -217,7 +217,7 @@ static inline void snp_set_wakeup_secondary_cpu(void) { }
static inline bool snp_init(struct boot_params *bp) { return false; }
static inline void snp_abort(void) { }
static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input,
- unsigned long *fw_err)
+ u64 *exitinfo2)
{
return -ENOTTY;
}
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index a428c62330d3..148f17cb07b5 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -22,6 +22,7 @@
#include <linux/efi.h>
#include <linux/platform_device.h>
#include <linux/io.h>
+#include <linux/psp-sev.h>
#include <asm/cpu_entry_area.h>
#include <asm/stacktrace.h>
@@ -2175,7 +2176,7 @@ static int __init init_sev_config(char *str)
}
__setup("sev=", init_sev_config);
-int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned long *fw_err)
+int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, u64 *exitinfo2)
{
struct ghcb_state state;
struct es_em_ctxt ctxt;
@@ -2186,9 +2187,11 @@ int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned
if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
return -ENODEV;
- if (!fw_err)
+ if (!exitinfo2)
return -EINVAL;
+ *exitinfo2 = SEV_RET_NO_FW_CALL;
+
/*
* __sev_get_ghcb() needs to run with IRQs disabled because it is using
* a per-CPU GHCB.
@@ -2212,14 +2215,13 @@ int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned
if (ret)
goto e_put;
+ *exitinfo2 = ghcb->save.sw_exit_info_2;
if (ghcb->save.sw_exit_info_2) {
/* Number of expected pages are returned in RBX */
if (exit_code == SVM_VMGEXIT_EXT_GUEST_REQUEST &&
ghcb->save.sw_exit_info_2 == SNP_GUEST_REQ_INVALID_LEN)
input->data_npages = ghcb_get_rbx(ghcb);
- *fw_err = ghcb->save.sw_exit_info_2;
-
ret = -EIO;
}
--
2.38.1.273.g43a17bfeac-goog
^ permalink raw reply related [flat|nested] 9+ messages in thread
* [PATCH v5 3/4] virt/coco/sev-guest: Remove err in handle_guest_request
2022-11-02 15:18 [PATCH v5 0/4] Add throttling detection to sev-guest Dionna Glaze
2022-11-02 15:18 ` [PATCH v5 1/4] ccp: Name -1 return value as SEV_RET_NO_FW_CALL Dionna Glaze
2022-11-02 15:18 ` [PATCH v5 2/4] x86/sev: Change snp_guest_issue_request's fw_err Dionna Glaze
@ 2022-11-02 15:18 ` Dionna Glaze
2022-11-02 15:18 ` [PATCH v5 4/4] virt/coco/sev-guest: interpret VMM errors from guest request Dionna Glaze
2022-11-03 15:26 ` [PATCH v5 0/4] Add throttling detection to sev-guest Peter Gonda
4 siblings, 0 replies; 9+ messages in thread
From: Dionna Glaze @ 2022-11-02 15:18 UTC (permalink / raw)
To: linux-kernel, x86
Cc: Dionna Glaze, Tom Lendacky, Paolo Bonzini, Joerg Roedel,
Peter Gonda, Thomas Gleixner, Dave Hansen
The err variable may not be set in the call to snp_issue_guest_request,
yet it is unconditionally written back to fw_err if fw_err is non-null.
This is undefined behavior, and currently returns uninitialized kernel
stack memory to user space.
The fw_err argument is better to just pass through to
snp_issue_guest_request, so we do that. Since the issue_request's
signature has changed fw_err to exitinfo2, we change the argument name
here.
Cc: Tom Lendacky <Thomas.Lendacky@amd.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Joerg Roedel <jroedel@suse.de>
Cc: Peter Gonda <pgonda@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Fixes: fce96cf04430 ("virt: Add SEV-SNP guest driver")
Signed-off-by: Dionna Glaze <dionnaglaze@google.com>
---
drivers/virt/coco/sev-guest/sev-guest.c | 7 ++-----
1 file changed, 2 insertions(+), 5 deletions(-)
diff --git a/drivers/virt/coco/sev-guest/sev-guest.c b/drivers/virt/coco/sev-guest/sev-guest.c
index f422f9c58ba7..0508c2f46f6b 100644
--- a/drivers/virt/coco/sev-guest/sev-guest.c
+++ b/drivers/virt/coco/sev-guest/sev-guest.c
@@ -303,9 +303,8 @@ static int enc_payload(struct snp_guest_dev *snp_dev, u64 seqno, int version, u8
static int handle_guest_request(struct snp_guest_dev *snp_dev, u64 exit_code, int msg_ver,
u8 type, void *req_buf, size_t req_sz, void *resp_buf,
- u32 resp_sz, __u64 *fw_err)
+ u32 resp_sz, __u64 *exitinfo2)
{
- unsigned long err;
u64 seqno;
int rc;
@@ -322,9 +321,7 @@ static int handle_guest_request(struct snp_guest_dev *snp_dev, u64 exit_code, in
return rc;
/* Call firmware to process the request */
- rc = snp_issue_guest_request(exit_code, &snp_dev->input, &err);
- if (fw_err)
- *fw_err = err;
+ rc = snp_issue_guest_request(exit_code, &snp_dev->input, exitinfo2);
if (rc)
return rc;
--
2.38.1.273.g43a17bfeac-goog
^ permalink raw reply related [flat|nested] 9+ messages in thread
* [PATCH v5 4/4] virt/coco/sev-guest: interpret VMM errors from guest request
2022-11-02 15:18 [PATCH v5 0/4] Add throttling detection to sev-guest Dionna Glaze
` (2 preceding siblings ...)
2022-11-02 15:18 ` [PATCH v5 3/4] virt/coco/sev-guest: Remove err in handle_guest_request Dionna Glaze
@ 2022-11-02 15:18 ` Dionna Glaze
2022-11-03 15:26 ` [PATCH v5 0/4] Add throttling detection to sev-guest Peter Gonda
4 siblings, 0 replies; 9+ messages in thread
From: Dionna Glaze @ 2022-11-02 15:18 UTC (permalink / raw)
To: linux-kernel, x86
Cc: Dionna Glaze, Tom Lendacky, Paolo Bonzini, Joerg Roedel,
Peter Gonda, Thomas Gleixner, Dave Hansen
The GHCB specification states that the upper 32 bits of exitinfo2 are
for the VMM's error codes. The sev-guest ABI has already locked in
that the fw_err status of the input will be 64 bits, and that
BIT_ULL(32) means that the extended guest request's data buffer was too
small, so we have to keep that ABI.
We can still interpret the upper 32 bits of exitinfo2 for the user
anyway in case the request gets throttled. For safety, since the
encryption algorithm in GHCBv2 is AES_GCM, we cannot return to user
space without having completed the request with the current sequence
number. If we were to return and the guest were to make another request
but with different message contents, then that would be IV reuse.
When throttled, the driver will reschedule itself and then try
again after sleeping half its ratelimit time to avoid a big wait queue.
The ioctl may block indefinitely, but that has always been the case
when deferring these requests to the host.
Cc: Tom Lendacky <Thomas.Lendacky@amd.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Joerg Roedel <jroedel@suse.de>
Cc: Peter Gonda <pgonda@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Dionna Glaze <dionnaglaze@google.com>
---
drivers/virt/coco/sev-guest/sev-guest.c | 50 ++++++++++++++++++++++---
include/uapi/linux/sev-guest.h | 18 ++++++++-
2 files changed, 60 insertions(+), 8 deletions(-)
diff --git a/drivers/virt/coco/sev-guest/sev-guest.c b/drivers/virt/coco/sev-guest/sev-guest.c
index 0508c2f46f6b..43e110ad4aa9 100644
--- a/drivers/virt/coco/sev-guest/sev-guest.c
+++ b/drivers/virt/coco/sev-guest/sev-guest.c
@@ -14,6 +14,7 @@
#include <linux/io.h>
#include <linux/platform_device.h>
#include <linux/miscdevice.h>
+#include <linux/ratelimit.h>
#include <linux/set_memory.h>
#include <linux/fs.h>
#include <crypto/aead.h>
@@ -48,12 +49,22 @@ struct snp_guest_dev {
struct snp_req_data input;
u32 *os_area_msg_seqno;
u8 *vmpck;
+
+ struct ratelimit_state rs;
};
static u32 vmpck_id;
module_param(vmpck_id, uint, 0444);
MODULE_PARM_DESC(vmpck_id, "The VMPCK ID to use when communicating with the PSP.");
+static int rate_hz = 2;
+module_param(rate_hz, int, 0444);
+MODULE_PARM_DESC(vmpck_id, "The rate limit frequency to limit requests to.");
+
+static int rate_burst = 1;
+module_param(rate_burst, int, 0444);
+MODULE_PARM_DESC(rate_burst, "The rate limit burst amount to limit requests to.");
+
/* Mutex to serialize the shared buffer access and command handling. */
static DEFINE_MUTEX(snp_cmd_mutex);
@@ -305,6 +316,7 @@ static int handle_guest_request(struct snp_guest_dev *snp_dev, u64 exit_code, in
u8 type, void *req_buf, size_t req_sz, void *resp_buf,
u32 resp_sz, __u64 *exitinfo2)
{
+ unsigned int vmm_err;
u64 seqno;
int rc;
@@ -320,9 +332,33 @@ static int handle_guest_request(struct snp_guest_dev *snp_dev, u64 exit_code, in
if (rc)
return rc;
+retry:
+ /*
+ * Rate limit commands internally since the host can also throttle, and
+ * we don't want to create a tight request spin that could end up
+ * getting this VM throttled more heavily.
+ */
+ if (!__ratelimit(&snp_dev->rs)) {
+ sleep_timeout_interruptible((rate_hz * HZ) / 2);
+ goto retry;
+ }
/* Call firmware to process the request */
rc = snp_issue_guest_request(exit_code, &snp_dev->input, exitinfo2);
+ vmm_err = *exitinfo2 >> SNP_GUEST_VMM_ERR_SHIFT;
+ /*
+ * The host may return EBUSY if the request has been throttled.
+ * We retry in the driver to avoid returning and reusing the message
+ * sequence number on a different message.
+ */
+ if (vmm_err == SNP_GUEST_VMM_ERR_BUSY)
+ goto retry;
+
+ if (vmm_err && vmm_err != SNP_GUEST_VMM_ERR_INVALID_LEN) {
+ pr_err("sev-guest: host returned unknown error code: %d\n",
+ vmm_err);
+ return -EINVAL;
+ }
if (rc)
return rc;
@@ -375,7 +411,7 @@ static int get_report(struct snp_guest_dev *snp_dev, struct snp_guest_request_io
rc = handle_guest_request(snp_dev, SVM_VMGEXIT_GUEST_REQUEST, arg->msg_version,
SNP_MSG_REPORT_REQ, &req, sizeof(req), resp->data,
- resp_len, &arg->fw_err);
+ resp_len, &arg->exitinfo2);
if (rc)
goto e_free;
@@ -415,7 +451,7 @@ static int get_derived_key(struct snp_guest_dev *snp_dev, struct snp_guest_reque
rc = handle_guest_request(snp_dev, SVM_VMGEXIT_GUEST_REQUEST, arg->msg_version,
SNP_MSG_KEY_REQ, &req, sizeof(req), buf, resp_len,
- &arg->fw_err);
+ &arg->exitinfo2);
if (rc)
return rc;
@@ -477,10 +513,10 @@ static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_reques
snp_dev->input.data_npages = npages;
ret = handle_guest_request(snp_dev, SVM_VMGEXIT_EXT_GUEST_REQUEST, arg->msg_version,
SNP_MSG_REPORT_REQ, &req.data,
- sizeof(req.data), resp->data, resp_len, &arg->fw_err);
+ sizeof(req.data), resp->data, resp_len, &arg->exitinfo2);
/* If certs length is invalid then copy the returned length */
- if (arg->fw_err == SNP_GUEST_REQ_INVALID_LEN) {
+ if (arg->vmm_error == SNP_GUEST_VMM_ERR_INVALID_LEN) {
req.certs_len = snp_dev->input.data_npages << PAGE_SHIFT;
if (copy_to_user((void __user *)arg->req_data, &req, sizeof(req)))
@@ -515,7 +551,7 @@ static long snp_guest_ioctl(struct file *file, unsigned int ioctl, unsigned long
if (copy_from_user(&input, argp, sizeof(input)))
return -EFAULT;
- input.fw_err = 0xff;
+ input.exitinfo2 = SEV_RET_NO_FW_CALL;
/* Message version must be non-zero */
if (!input.msg_version)
@@ -546,7 +582,7 @@ static long snp_guest_ioctl(struct file *file, unsigned int ioctl, unsigned long
mutex_unlock(&snp_cmd_mutex);
- if (input.fw_err && copy_to_user(argp, &input, sizeof(input)))
+ if (input.exitinfo2 && copy_to_user(argp, &input, sizeof(input)))
return -EFAULT;
return ret;
@@ -696,6 +732,8 @@ static int __init sev_guest_probe(struct platform_device *pdev)
if (ret)
goto e_free_cert_data;
+ ratelimit_state_init(&snp_dev->rs, rate_hz * HZ, rate_burst);
+
dev_info(dev, "Initialized SEV guest driver (using vmpck_id %d)\n", vmpck_id);
return 0;
diff --git a/include/uapi/linux/sev-guest.h b/include/uapi/linux/sev-guest.h
index 256aaeff7e65..8e4144aa78c9 100644
--- a/include/uapi/linux/sev-guest.h
+++ b/include/uapi/linux/sev-guest.h
@@ -52,8 +52,15 @@ struct snp_guest_request_ioctl {
__u64 req_data;
__u64 resp_data;
- /* firmware error code on failure (see psp-sev.h) */
- __u64 fw_err;
+ /* bits[63:32]: VMM error code, bits[31:0] firmware error code (see psp-sev.h) */
+ union {
+ __u64 exitinfo2;
+ __u64 fw_err; /* Name deprecated in favor of others */
+ struct {
+ __u32 fw_error;
+ __u32 vmm_error;
+ };
+ };
};
struct snp_ext_report_req {
@@ -77,4 +84,11 @@ struct snp_ext_report_req {
/* Get SNP extended report as defined in the GHCB specification version 2. */
#define SNP_GET_EXT_REPORT _IOWR(SNP_GUEST_REQ_IOC_TYPE, 0x2, struct snp_guest_request_ioctl)
+/* Guest message request EXIT_INFO_2 constants */
+#define SNP_GUEST_FW_ERR_MASK GENMASK_ULL(31, 0)
+#define SNP_GUEST_VMM_ERR_SHIFT 32
+
+#define SNP_GUEST_VMM_ERR_INVALID_LEN 1
+#define SNP_GUEST_VMM_ERR_BUSY 2
+
#endif /* __UAPI_LINUX_SEV_GUEST_H_ */
--
2.38.1.273.g43a17bfeac-goog
^ permalink raw reply related [flat|nested] 9+ messages in thread