The guest request synchronous API from SEV-SNP VMs to the host's security
processor consumes a global resource. For this reason, AMD's docs
recommend that the host implements a throttling mechanism. In order for
the guest to know it's been throttled and should try its request again,
we need some good-faith communication from the host that the request
has been throttled.
These patches work with the existing /dev/sev-guest ABI to detect a
throttling code.
Changes from v2:
* Codified the non-firmware-call firmware error code as (u32)-1.
* Changed sev_issue_guest_request unsigned long *fw_err argument to
u64 *exitinfo2 to more accurately and type-safely describe the
value that it outputs.
* Changed sev_issue_guest_request to always set its exitinfo2
argument to either the non-firmware-call error code, the
EXIT_INFO_2 returned from the VMM if the request failed, or 0 on
success. This fixes a bug that returned uninitialized kernel stack
memory to the user when there is no error.
* Changed the throttle behavior to retry in the driver instead of
returning -EAGAIN, due to possible message sequence number reuse
on different message contents.
Changes from v1:
* Changed throttle error code to 2
Cc: Tom Lendacky <[email protected]>
Cc: Paolo Bonzini <[email protected]>
Cc: Joerg Roedel <[email protected]>
Cc: Peter Gonda <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Dave Hansen <[email protected]>
Signed-off-by: Dionna Glaze <[email protected]>
Dionna Glaze (4):
ccp: Name -1 return value as SEV_RET_NO_FW_CALL
x86/sev: Change snp_guest_issue_request's fw_err
virt/coco/sev-guest: Remove err in handle_guest_request
virt/coco/sev-guest: interpret VMM errors from guest request
arch/x86/include/asm/sev.h | 4 +--
arch/x86/kernel/sev.c | 11 +++++--
drivers/crypto/ccp/sev-dev.c | 2 +-
drivers/virt/coco/sev-guest/sev-guest.c | 39 ++++++++++++++++++-------
include/uapi/linux/psp-sev.h | 7 +++++
include/uapi/linux/sev-guest.h | 18 ++++++++++--
6 files changed, 62 insertions(+), 19 deletions(-)
--
2.38.0.135.g90850a2211-goog
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 <[email protected]>
Cc: Paolo Bonzini <[email protected]>
Cc: Joerg Roedel <[email protected]>
Cc: Peter Gonda <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Dave Hansen <[email protected]>
Fixes: d5af44dde546 ("x86/sev: Provide support for SNP guest request NAEs")
Signed-off-by: Dionna Glaze <[email protected]>
---
arch/x86/include/asm/sev.h | 4 ++--
arch/x86/kernel/sev.c | 11 ++++++++---
2 files changed, 10 insertions(+), 5 deletions(-)
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index ebc271bb6d8e..8ebd78b6a57c 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)
+ unsigned long *exitinfo2)
{
return -ENOTTY;
}
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index a428c62330d3..5a402df7549e 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.
@@ -2218,9 +2221,11 @@ int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned
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;
+ *exitinfo2 = ghcb->save.sw_exit_info_2;
ret = -EIO;
+ } else {
+ *exitinfo2 = 0;
}
e_put:
--
2.38.0.135.g90850a2211-goog
The PSP can return a "firmware error" code of -1 in circumstances where
the PSP is not actually called. To make this protocol unambiguous, we
add a constant naming the return value.
From: Peter Gonda <[email protected]>
Cc: Thomas Lendacky <[email protected]>
Cc: Paolo Bonzini <[email protected]>
Cc: Joerg Roedel <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Andy Lutomirsky <[email protected]>
Signed-off-by: Dionna Glaze <[email protected]>
---
drivers/crypto/ccp/sev-dev.c | 2 +-
include/uapi/linux/psp-sev.h | 7 +++++++
2 files changed, 8 insertions(+), 1 deletion(-)
diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c
index 06fc7156c04f..97eb3544ab36 100644
--- a/drivers/crypto/ccp/sev-dev.c
+++ b/drivers/crypto/ccp/sev-dev.c
@@ -444,7 +444,7 @@ static int __sev_platform_init_locked(int *error)
{
struct psp_device *psp = psp_master;
struct sev_device *sev;
- int rc = 0, psp_ret = -1;
+ int rc = 0, psp_ret = SEV_RET_NO_FW_CALL;
int (*init_function)(int *error);
if (!psp || !psp->sev_data)
diff --git a/include/uapi/linux/psp-sev.h b/include/uapi/linux/psp-sev.h
index 91b4c63d5cbf..fb61e083d42e 100644
--- a/include/uapi/linux/psp-sev.h
+++ b/include/uapi/linux/psp-sev.h
@@ -36,6 +36,13 @@ enum {
* SEV Firmware status code
*/
typedef enum {
+ /*
+ * This error code is not in the SEV spec but is added to convey that
+ * there was an error that prevented the SEV Firmware from being called.
+ * This is (u32)-1 since the firmware error code part of EXIT_INFO_2 is
+ * the lower 32 bits.
+ */
+ SEV_RET_NO_FW_CALL = 0xffffffff,
SEV_RET_SUCCESS = 0,
SEV_RET_INVALID_PLATFORM_STATE,
SEV_RET_INVALID_GUEST_STATE,
--
2.38.0.135.g90850a2211-goog
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 <[email protected]>
Cc: Paolo Bonzini <[email protected]>
Cc: Joerg Roedel <[email protected]>
Cc: Peter Gonda <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Dave Hansen <[email protected]>
Fixes: fce96cf04430 ("virt: Add SEV-SNP guest driver")
Signed-off-by: Dionna Glaze <[email protected]>
---
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;
--
2.38.0.135.g90850a2211-goog
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. The ioctl may block indefinitely, but that has always been the
case when deferring these requests to the host.
Cc: Tom Lendacky <[email protected]>
Cc: Paolo Bonzini <[email protected]>
Cc: Joerg Roedel <[email protected]>
Cc: Peter Gonda <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Dave Hansen <[email protected]>
Signed-off-by: Dionna Glaze <[email protected]>
---
drivers/virt/coco/sev-guest/sev-guest.c | 32 ++++++++++++++++++++-----
include/uapi/linux/sev-guest.h | 18 ++++++++++++--
2 files changed, 42 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..7abf4c3daa6d 100644
--- a/drivers/virt/coco/sev-guest/sev-guest.c
+++ b/drivers/virt/coco/sev-guest/sev-guest.c
@@ -305,9 +305,12 @@ 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;
+ might_resched();
+
/* Get message sequence and verify that its a non-zero */
seqno = snp_get_msg_seqno(snp_dev);
if (!seqno)
@@ -320,9 +323,26 @@ static int handle_guest_request(struct snp_guest_dev *snp_dev, u64 exit_code, in
if (rc)
return rc;
+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) {
+ cond_resched();
+ 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 +395,7 @@ 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 +435,7 @@ 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 +497,10 @@ 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 +535,7 @@ 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 +566,7 @@ 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;
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_ */
--
2.38.0.135.g90850a2211-goog
On 10/21/22 11:59, Dionna Glaze wrote:
> 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 <[email protected]>
> Cc: Paolo Bonzini <[email protected]>
> Cc: Joerg Roedel <[email protected]>
> Cc: Peter Gonda <[email protected]>
> Cc: Thomas Gleixner <[email protected]>
> Cc: Dave Hansen <[email protected]>
>
> Fixes: d5af44dde546 ("x86/sev: Provide support for SNP guest request NAEs")
> Signed-off-by: Dionna Glaze <[email protected]>
> ---
> arch/x86/include/asm/sev.h | 4 ++--
> arch/x86/kernel/sev.c | 11 ++++++++---
> 2 files changed, 10 insertions(+), 5 deletions(-)
>
> diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
> index ebc271bb6d8e..8ebd78b6a57c 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)
> + unsigned long *exitinfo2)
s/unsigned long/u64/
> {
> return -ENOTTY;
> }
> diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
> index a428c62330d3..5a402df7549e 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.
> @@ -2218,9 +2221,11 @@ int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned
> 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;
> + *exitinfo2 = ghcb->save.sw_exit_info_2;
Looks like you can do "*exitinfo2 = ghcb->save.sw_exit_info_2;" just
before the "if (ghcb->save.sw_exit_info_2) {". That would eliminate the
need to assign it in each branch of the if.
Thanks,
Tom
>
> ret = -EIO;
> + } else {
> + *exitinfo2 = 0;
> }
>
> e_put:
On 10/21/22 11:59, Dionna Glaze wrote:
> 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. The ioctl may block indefinitely, but that has always been the
> case when deferring these requests to the host.
>
> Cc: Tom Lendacky <[email protected]>
> Cc: Paolo Bonzini <[email protected]>
> Cc: Joerg Roedel <[email protected]>
> Cc: Peter Gonda <[email protected]>
> Cc: Thomas Gleixner <[email protected]>
> Cc: Dave Hansen <[email protected]>
>
> Signed-off-by: Dionna Glaze <[email protected]>
> ---
> drivers/virt/coco/sev-guest/sev-guest.c | 32 ++++++++++++++++++++-----
> include/uapi/linux/sev-guest.h | 18 ++++++++++++--
> 2 files changed, 42 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..7abf4c3daa6d 100644
> --- a/drivers/virt/coco/sev-guest/sev-guest.c
> +++ b/drivers/virt/coco/sev-guest/sev-guest.c
> @@ -305,9 +305,12 @@ 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;
>
> + might_resched();
> +
> /* Get message sequence and verify that its a non-zero */
> seqno = snp_get_msg_seqno(snp_dev);
> if (!seqno)
> @@ -320,9 +323,26 @@ static int handle_guest_request(struct snp_guest_dev *snp_dev, u64 exit_code, in
> if (rc)
> return rc;
>
> +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) {
> + cond_resched();
I would think there should be some form of delay here. Otherwise, it is
likely that the request could be re-issued almost immediately, which may
make the hypervisor think even more requests are being issued and try to
rate limit the guest even more.
Thanks,
Tom
> + 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 +395,7 @@ 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 +435,7 @@ 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 +497,10 @@ 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 +535,7 @@ 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 +566,7 @@ 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;
> 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_ */