[PATCH v20 0/3] [VFIO] Error recovery for vfio-pci devices on s390x

[PATCH v20 0/3] [VFIO] Error recovery for vfio-pci devices on s390x

[Farhan Ali]

Hi Alex,

This patch set includes only the VFIO patches of the original series for
error recovery for vfio-pci devices on s390x [1]. Breaking up the patch
series into PCI and VFIO only patches to make merging easier based on our
discussion [2].

Thanks
Farhan

[1] https://lore.kernel.org/all/20260520171113.1111-1-alifm@linux.ibm.com/
[2] https://lore.kernel.org/all/20260602163344.1eda12d2@shazbot.org/

ChangeLog
---------
v19 https://lore.kernel.org/all/20260615183616.2902-1-alifm@linux.ibm.com/
v19 -> v20
 - Change device feature uapi to pass the error data as opaque to
 userspace (patch 2).
 - Rebase on 7.2-rc1 

v18 https://lore.kernel.org/all/20260603182415.2324-1-alifm@linux.ibm.com/
v18 -> v19
 - Fix hole in struct vfio_device_feature_zpci_err.
 - Remove reset_done() callback for vfio-pci driver.
 - Rebase on 7.1-rc7

v17 -> v18
 - Print a warn with dev_warn_ratelimited() for copy_to_user failure.
 - Rebase on 7.1-rc6.
 - Break patch series into VFIO patch set.


Farhan Ali (3):
  s390/pci: Store PCI error information for passthrough devices
  vfio-pci/zdev: Add a device feature for error information
  vfio/pci: Remove the pcie check for VFIO_PCI_ERR_IRQ_INDEX

 arch/s390/include/asm/pci.h       |  32 +++++++
 arch/s390/pci/pci.c               |   1 +
 arch/s390/pci/pci_event.c         | 137 +++++++++++++++++++-----------
 drivers/vfio/pci/vfio_pci_core.c  |  10 +--
 drivers/vfio/pci/vfio_pci_intrs.c |   3 +-
 drivers/vfio/pci/vfio_pci_priv.h  |   9 ++
 drivers/vfio/pci/vfio_pci_zdev.c  |  63 ++++++++++++--
 include/uapi/linux/vfio.h         |  23 +++++
 include/uapi/linux/vfio_zdev.h    |   2 +
 9 files changed, 216 insertions(+), 64 deletions(-)

-- 
2.43.0

[PATCH v20 1/3] s390/pci: Store PCI error information for passthrough devices

[Farhan Ali]

For a passthrough device we need co-operation from user space to recover
the device. This would require to bubble up any error information to user
space.  Let's store this error information for passthrough devices, so it
can be retrieved later.

We can now have userspace drivers (vfio-pci based) on s390x. The userspace
drivers will not have any KVM fd and so no kzdev associated with them. So
we need to update the logic for detecting passthrough devices to not depend
on struct kvm_zdev.

Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Reviewed-by: Niklas Schnelle <schnelle@linux.ibm.com>
Signed-off-by: Farhan Ali <alifm@linux.ibm.com>
---
 arch/s390/include/asm/pci.h      |  30 ++++++++
 arch/s390/pci/pci.c              |   1 +
 arch/s390/pci/pci_event.c        | 118 ++++++++++++++++++-------------
 drivers/vfio/pci/vfio_pci_zdev.c |  18 ++++-
 4 files changed, 113 insertions(+), 54 deletions(-)

diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 5dcf35f0f325..016386f7ef4a 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -118,6 +118,32 @@ struct zpci_bus {
 	enum pci_bus_speed	max_bus_speed;
 };
 
+/* Content Code Description for PCI Function Error */
+struct zpci_ccdf_err {
+	u32 reserved1;
+	u32 fh;                         /* function handle */
+	u32 fid;                        /* function id */
+	u32 ett         :  4;           /* expected table type */
+	u32 mvn         : 12;           /* MSI vector number */
+	u32 dmaas       :  8;           /* DMA address space */
+	u32 reserved2   :  6;
+	u32 q           :  1;           /* event qualifier */
+	u32 rw          :  1;           /* read/write */
+	u64 faddr;                      /* failing address */
+	u32 reserved3;
+	u16 reserved4;
+	u16 pec;                        /* PCI event code */
+} __packed;
+
+#define ZPCI_ERR_PENDING_MAX 4
+struct zpci_ccdf_pending {
+	bool mediated_recovery;
+	u8 count;
+	u8 head;
+	u8 tail;
+	struct zpci_ccdf_err err[ZPCI_ERR_PENDING_MAX];
+};
+
 /* Private data per function */
 struct zpci_dev {
 	struct zpci_bus *zbus;
@@ -192,6 +218,8 @@ struct zpci_dev {
 	struct iommu_domain *s390_domain; /* attached IOMMU domain */
 	struct kvm_zdev *kzdev;
 	struct mutex kzdev_lock;
+	struct zpci_ccdf_pending pending_errs;
+	struct mutex pending_errs_lock;
 	spinlock_t dom_lock;		/* protect s390_domain change */
 };
 
@@ -334,6 +362,8 @@ void zpci_debug_exit_device(struct zpci_dev *);
 int zpci_report_error(struct pci_dev *, struct zpci_report_error_header *);
 int zpci_clear_error_state(struct zpci_dev *zdev);
 int zpci_reset_load_store_blocked(struct zpci_dev *zdev);
+void zpci_start_mediated_recovery(struct zpci_dev *zdev);
+void zpci_stop_mediated_recovery(struct zpci_dev *zdev);
 
 #ifdef CONFIG_NUMA
 
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 39bd2adfc240..2d377c2e194d 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -842,6 +842,7 @@ struct zpci_dev *zpci_create_device(u32 fid, u32 fh, enum zpci_state state)
 	mutex_init(&zdev->state_lock);
 	mutex_init(&zdev->fmb_lock);
 	mutex_init(&zdev->kzdev_lock);
+	mutex_init(&zdev->pending_errs_lock);
 
 	return zdev;
 
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index 839bd91c056e..8934b640a095 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -17,23 +17,6 @@
 #include "pci_bus.h"
 #include "pci_report.h"
 
-/* Content Code Description for PCI Function Error */
-struct zpci_ccdf_err {
-	u32 reserved1;
-	u32 fh;				/* function handle */
-	u32 fid;			/* function id */
-	u32 ett		:  4;		/* expected table type */
-	u32 mvn		: 12;		/* MSI vector number */
-	u32 dmaas	:  8;		/* DMA address space */
-	u32		:  6;
-	u32 q		:  1;		/* event qualifier */
-	u32 rw		:  1;		/* read/write */
-	u64 faddr;			/* failing address */
-	u32 reserved3;
-	u16 reserved4;
-	u16 pec;			/* PCI event code */
-} __packed;
-
 /* Content Code Description for PCI Function Availability */
 struct zpci_ccdf_avail {
 	u32 reserved1;
@@ -60,18 +43,6 @@ static inline bool ers_result_indicates_abort(pci_ers_result_t ers_res)
 	}
 }
 
-static bool is_passed_through(struct pci_dev *pdev)
-{
-	struct zpci_dev *zdev = to_zpci(pdev);
-	bool ret;
-
-	mutex_lock(&zdev->kzdev_lock);
-	ret = !!zdev->kzdev;
-	mutex_unlock(&zdev->kzdev_lock);
-
-	return ret;
-}
-
 static bool is_driver_supported(struct pci_driver *driver)
 {
 	if (!driver || !driver->err_handler)
@@ -81,6 +52,49 @@ static bool is_driver_supported(struct pci_driver *driver)
 	return true;
 }
 
+static int zpci_store_pci_error(struct pci_dev *pdev,
+				 struct zpci_ccdf_err *ccdf)
+{
+	struct zpci_dev *zdev = to_zpci(pdev);
+	int i;
+
+	guard(mutex)(&zdev->pending_errs_lock);
+	if (!zdev->pending_errs.mediated_recovery)
+		return -EINVAL;
+
+	if (zdev->pending_errs.count >= ZPCI_ERR_PENDING_MAX) {
+		dev_warn_ratelimited(&pdev->dev,
+				     "%s: Maximum number (%d) of pending error events queued\n",
+				     pci_name(pdev),
+				     ZPCI_ERR_PENDING_MAX);
+		return -ENOMEM;
+	}
+
+	i = zdev->pending_errs.tail % ZPCI_ERR_PENDING_MAX;
+	memcpy(&zdev->pending_errs.err[i], ccdf, sizeof(struct zpci_ccdf_err));
+	zdev->pending_errs.tail++;
+	zdev->pending_errs.count++;
+	return 0;
+}
+
+void zpci_start_mediated_recovery(struct zpci_dev *zdev)
+{
+	guard(mutex)(&zdev->pending_errs_lock);
+	zdev->pending_errs.mediated_recovery = true;
+}
+EXPORT_SYMBOL_GPL(zpci_start_mediated_recovery);
+
+void zpci_stop_mediated_recovery(struct zpci_dev *zdev)
+{
+	guard(mutex)(&zdev->pending_errs_lock);
+	zdev->pending_errs.mediated_recovery = false;
+	if (zdev->pending_errs.count)
+		pr_info("Unhandled PCI error events count=%d for PCI function 0x%x\n",
+			zdev->pending_errs.count, zdev->fid);
+	memset(&zdev->pending_errs, 0, sizeof(struct zpci_ccdf_pending));
+}
+EXPORT_SYMBOL_GPL(zpci_stop_mediated_recovery);
+
 static pci_ers_result_t zpci_event_notify_error_detected(struct pci_dev *pdev,
 							 struct pci_driver *driver)
 {
@@ -175,12 +189,15 @@ static pci_ers_result_t zpci_event_do_reset(struct pci_dev *pdev,
  * and the platform determines which functions are affected for
  * multi-function devices.
  */
-static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev)
+static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev,
+							  struct zpci_ccdf_err *ccdf)
 {
 	pci_ers_result_t ers_res = PCI_ERS_RESULT_DISCONNECT;
 	struct zpci_dev *zdev = to_zpci(pdev);
+	bool mediated_recovery = false;
 	char *status_str = "success";
 	struct pci_driver *driver;
+	int rc;
 
 	/*
 	 * Ensure that the PCI function is not removed concurrently, no driver
@@ -194,13 +211,6 @@ static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev)
 	}
 	pdev->error_state = pci_channel_io_frozen;
 
-	if (is_passed_through(pdev)) {
-		pr_info("%s: Cannot be recovered in the host because it is a pass-through device\n",
-			pci_name(pdev));
-		status_str = "failed (pass-through)";
-		goto out_unlock;
-	}
-
 	driver = to_pci_driver(pdev->dev.driver);
 	if (!is_driver_supported(driver)) {
 		if (!driver) {
@@ -216,12 +226,24 @@ static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev)
 		goto out_unlock;
 	}
 
+	rc = zpci_store_pci_error(pdev, ccdf);
+	if (!rc || rc == -ENOMEM)
+		mediated_recovery = true;
+
 	ers_res = zpci_event_notify_error_detected(pdev, driver);
 	if (ers_result_indicates_abort(ers_res)) {
 		status_str = "failed (abort on detection)";
 		goto out_unlock;
 	}
 
+	if (mediated_recovery) {
+		pr_info("%s: Leaving recovery of pass-through device to user-space\n",
+			pci_name(pdev));
+		ers_res = PCI_ERS_RESULT_RECOVERED;
+		status_str = "in progress";
+		goto out_unlock;
+	}
+
 	if (ers_res != PCI_ERS_RESULT_NEED_RESET) {
 		ers_res = zpci_event_do_error_state_clear(pdev, driver);
 		if (ers_result_indicates_abort(ers_res)) {
@@ -266,25 +288,19 @@ static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev)
  * @pdev: PCI function for which to report
  * @es: PCI channel failure state to report
  */
-static void zpci_event_io_failure(struct pci_dev *pdev, pci_channel_state_t es)
+static void zpci_event_io_failure(struct pci_dev *pdev, pci_channel_state_t es,
+				  struct zpci_ccdf_err *ccdf)
 {
 	struct pci_driver *driver;
 
 	pci_dev_lock(pdev);
 	pdev->error_state = es;
-	/**
-	 * While vfio-pci's error_detected callback notifies user-space QEMU
-	 * reacts to this by freezing the guest. In an s390 environment PCI
-	 * errors are rarely fatal so this is overkill. Instead in the future
-	 * we will inject the error event and let the guest recover the device
-	 * itself.
-	 */
-	if (is_passed_through(pdev))
-		goto out;
+
+	zpci_store_pci_error(pdev, ccdf);
 	driver = to_pci_driver(pdev->dev.driver);
 	if (driver && driver->err_handler && driver->err_handler->error_detected)
 		driver->err_handler->error_detected(pdev, pdev->error_state);
-out:
+
 	pci_dev_unlock(pdev);
 }
 
@@ -330,12 +346,12 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf)
 		break;
 	case 0x0040: /* Service Action or Error Recovery Failed */
 	case 0x003b:
-		zpci_event_io_failure(pdev, pci_channel_io_perm_failure);
+		zpci_event_io_failure(pdev, pci_channel_io_perm_failure, ccdf);
 		break;
 	default: /* PCI function left in the error state attempt to recover */
-		ers_res = zpci_event_attempt_error_recovery(pdev);
+		ers_res = zpci_event_attempt_error_recovery(pdev, ccdf);
 		if (ers_res != PCI_ERS_RESULT_RECOVERED)
-			zpci_event_io_failure(pdev, pci_channel_io_perm_failure);
+			zpci_event_io_failure(pdev, pci_channel_io_perm_failure, ccdf);
 		break;
 	}
 	pci_dev_put(pdev);
diff --git a/drivers/vfio/pci/vfio_pci_zdev.c b/drivers/vfio/pci/vfio_pci_zdev.c
index 0990fdb146b7..78a28db00c6d 100644
--- a/drivers/vfio/pci/vfio_pci_zdev.c
+++ b/drivers/vfio/pci/vfio_pci_zdev.c
@@ -144,24 +144,36 @@ int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev,
 int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev)
 {
 	struct zpci_dev *zdev = to_zpci(vdev->pdev);
+	int ret;
 
 	if (!zdev)
 		return -ENODEV;
 
+	zpci_start_mediated_recovery(zdev);
+
 	if (!vdev->vdev.kvm)
 		return 0;
 
+	ret = -ENOENT;
 	if (zpci_kvm_hook.kvm_register)
-		return zpci_kvm_hook.kvm_register(zdev, vdev->vdev.kvm);
+		ret = zpci_kvm_hook.kvm_register(zdev, vdev->vdev.kvm);
 
-	return -ENOENT;
+	if (ret)
+		zpci_stop_mediated_recovery(zdev);
+
+	return ret;
 }
 
 void vfio_pci_zdev_close_device(struct vfio_pci_core_device *vdev)
 {
 	struct zpci_dev *zdev = to_zpci(vdev->pdev);
 
-	if (!zdev || !vdev->vdev.kvm)
+	if (!zdev)
+		return;
+
+	zpci_stop_mediated_recovery(zdev);
+
+	if (!vdev->vdev.kvm)
 		return;
 
 	if (zpci_kvm_hook.kvm_unregister)
-- 
2.43.0

[PATCH v20 2/3] vfio-pci/zdev: Add a device feature for error information

[Farhan Ali]

For zPCI devices, we have platform specific error information. The platform
firmware provides this error information to the operating system in an
architecture specific mechanism. To enable recovery from userspace for
these devices, we want to expose this error information to userspace. Add a
new device feature to expose this information.

Userspace needs to be provide a buffer of fixed size. This size is provided
to userspace via the VFIO_DEVICE_INFO_CAP_ZPCI_BASE capability.

Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Reviewed-by: Niklas Schnelle <schnelle@linux.ibm.com>
Signed-off-by: Farhan Ali <alifm@linux.ibm.com>
---
 arch/s390/include/asm/pci.h      |  2 ++
 arch/s390/pci/pci_event.c        | 19 ++++++++++++++
 drivers/vfio/pci/vfio_pci_core.c |  2 ++
 drivers/vfio/pci/vfio_pci_priv.h |  9 +++++++
 drivers/vfio/pci/vfio_pci_zdev.c | 45 ++++++++++++++++++++++++++++++--
 include/uapi/linux/vfio.h        | 23 ++++++++++++++++
 include/uapi/linux/vfio_zdev.h   |  2 ++
 7 files changed, 100 insertions(+), 2 deletions(-)

diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 016386f7ef4a..88a125b92bdd 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -364,6 +364,8 @@ int zpci_clear_error_state(struct zpci_dev *zdev);
 int zpci_reset_load_store_blocked(struct zpci_dev *zdev);
 void zpci_start_mediated_recovery(struct zpci_dev *zdev);
 void zpci_stop_mediated_recovery(struct zpci_dev *zdev);
+int zpci_get_pending_error(struct zpci_dev *zdev,
+			   struct zpci_ccdf_err *ccdf);
 
 #ifdef CONFIG_NUMA
 
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index 8934b640a095..3ad16038e005 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -77,6 +77,25 @@ static int zpci_store_pci_error(struct pci_dev *pdev,
 	return 0;
 }
 
+int zpci_get_pending_error(struct zpci_dev *zdev,
+			   struct zpci_ccdf_err *ccdf)
+{
+	int head = 0;
+
+	guard(mutex)(&zdev->pending_errs_lock);
+
+	if (!zdev->pending_errs.count)
+		return -ENOMSG;
+
+	head = zdev->pending_errs.head % ZPCI_ERR_PENDING_MAX;
+	memcpy(ccdf, &zdev->pending_errs.err[head],
+	       sizeof(struct zpci_ccdf_err));
+	zdev->pending_errs.head++;
+	zdev->pending_errs.count--;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(zpci_get_pending_error);
+
 void zpci_start_mediated_recovery(struct zpci_dev *zdev)
 {
 	guard(mutex)(&zdev->pending_errs_lock);
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index a28f1e99362c..5a6786feadd7 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -1572,6 +1572,8 @@ int vfio_pci_core_ioctl_feature(struct vfio_device *device, u32 flags,
 		return vfio_pci_core_feature_token(vdev, flags, arg, argsz);
 	case VFIO_DEVICE_FEATURE_DMA_BUF:
 		return vfio_pci_core_feature_dma_buf(vdev, flags, arg, argsz);
+	case VFIO_DEVICE_FEATURE_ZPCI_ERROR:
+		return vfio_pci_zdev_feature_err(device, flags, arg, argsz);
 	default:
 		return -ENOTTY;
 	}
diff --git a/drivers/vfio/pci/vfio_pci_priv.h b/drivers/vfio/pci/vfio_pci_priv.h
index fca9d0dfac90..4e7162234a2e 100644
--- a/drivers/vfio/pci/vfio_pci_priv.h
+++ b/drivers/vfio/pci/vfio_pci_priv.h
@@ -93,6 +93,8 @@ int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev,
 				struct vfio_info_cap *caps);
 int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev);
 void vfio_pci_zdev_close_device(struct vfio_pci_core_device *vdev);
+int vfio_pci_zdev_feature_err(struct vfio_device *device, u32 flags,
+			      void __user *arg, size_t argsz);
 #else
 static inline int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev,
 					      struct vfio_info_cap *caps)
@@ -107,6 +109,13 @@ static inline int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev)
 
 static inline void vfio_pci_zdev_close_device(struct vfio_pci_core_device *vdev)
 {}
+
+static inline int vfio_pci_zdev_feature_err(struct vfio_device *device,
+					    u32 flags, void __user *arg,
+					    size_t argsz)
+{
+	return -ENOTTY;
+}
 #endif
 
 static inline bool vfio_pci_is_vga(struct pci_dev *pdev)
diff --git a/drivers/vfio/pci/vfio_pci_zdev.c b/drivers/vfio/pci/vfio_pci_zdev.c
index 78a28db00c6d..49aa800fe153 100644
--- a/drivers/vfio/pci/vfio_pci_zdev.c
+++ b/drivers/vfio/pci/vfio_pci_zdev.c
@@ -24,7 +24,7 @@ static int zpci_base_cap(struct zpci_dev *zdev, struct vfio_info_cap *caps)
 {
 	struct vfio_device_info_cap_zpci_base cap = {
 		.header.id = VFIO_DEVICE_INFO_CAP_ZPCI_BASE,
-		.header.version = 2,
+		.header.version = 3,
 		.start_dma = zdev->start_dma,
 		.end_dma = zdev->end_dma,
 		.pchid = zdev->pchid,
@@ -32,7 +32,8 @@ static int zpci_base_cap(struct zpci_dev *zdev, struct vfio_info_cap *caps)
 		.fmb_length = zdev->fmb_length,
 		.pft = zdev->pft,
 		.gid = zdev->pfgid,
-		.fh = zdev->fh
+		.fh = zdev->fh,
+		.ccdf_err_length = sizeof(struct zpci_ccdf_err)
 	};
 
 	return vfio_info_add_capability(caps, &cap.header, sizeof(cap));
@@ -141,6 +142,46 @@ int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev,
 	return ret;
 }
 
+int vfio_pci_zdev_feature_err(struct vfio_device *device, u32 flags,
+			      void __user *arg, size_t argsz)
+{
+	struct vfio_device_feature_zpci_err err;
+	struct vfio_pci_core_device *vdev;
+	struct zpci_ccdf_err ccdf = {};
+	struct zpci_dev *zdev;
+	int ret;
+
+	vdev = container_of(device, struct vfio_pci_core_device, vdev);
+	zdev = to_zpci(vdev->pdev);
+	if (!zdev)
+		return -ENODEV;
+
+	ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_GET,
+				 sizeof(err));
+	if (ret != 1)
+		return ret;
+
+	if (copy_from_user(&err, arg, sizeof(err)))
+		return -EFAULT;
+
+	if (!err.data)
+		return -EINVAL;
+
+	ret = zpci_get_pending_error(zdev, &ccdf);
+	if (ret)
+		return ret;
+
+
+	if (copy_to_user(u64_to_user_ptr(err.data), &ccdf, sizeof(ccdf))) {
+		dev_warn_ratelimited(device->dev,
+				     "Failed to handle PCI error event for PCI function 0x%x",
+				     zdev->fid);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
 int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev)
 {
 	struct zpci_dev *zdev = to_zpci(vdev->pdev);
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 5de618a3a5ee..6d224e7e9fa2 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -1534,6 +1534,29 @@ struct vfio_device_feature_dma_buf {
  */
 #define VFIO_DEVICE_FEATURE_MIG_PRECOPY_INFOv2  12
 
+/**
+ * VFIO_DEVICE_FEATURE_ZPCI_ERROR feature provides PCI error information to
+ * userspace for vfio-pci devices on s390. On s390, PCI error recovery
+ * involves platform firmware and notification to operating systems is done
+ * by architecture specific mechanism. Exposing this information to
+ * userspace allows it to take appropriate actions to handle an
+ * error on the device.
+ *
+ * Userspace provides an opaque buffer of fixed length, and the kernel
+ * fills it with the zpci_ccdf_err data structure. The length of
+ * zpci_ccdf_err is provided to userspace via the
+ * VFIO_DEVICE_INFO_CAP_ZPCI_BASE capability.
+ *
+ * The ioctl returns -ENOMSG if there are no pending PCI errors.
+ */
+
+
+struct vfio_device_feature_zpci_err {
+	__aligned_u64 data;
+};
+
+#define VFIO_DEVICE_FEATURE_ZPCI_ERROR 13
+
 /* -------- API for Type1 VFIO IOMMU -------- */
 
 /**
diff --git a/include/uapi/linux/vfio_zdev.h b/include/uapi/linux/vfio_zdev.h
index 77f2aff1f27e..d6c1175c884e 100644
--- a/include/uapi/linux/vfio_zdev.h
+++ b/include/uapi/linux/vfio_zdev.h
@@ -32,6 +32,8 @@ struct vfio_device_info_cap_zpci_base {
 	/* End of version 1 */
 	__u32 fh;		/* PCI function handle */
 	/* End of version 2 */
+	__u32 ccdf_err_length;	/* PCI CCDF length */
+	/* End of version 3 */
 };
 
 /**
-- 
2.43.0

[PATCH v20 3/3] vfio/pci: Remove the pcie check for VFIO_PCI_ERR_IRQ_INDEX

[Farhan Ali]

The error signaling is configured for the vast majority of devices and it's
extremely rare that it fires anyway. Removing the pcie check will allow
userspace to be notified on errors for legacy PCI devices. The Internal
Shared Memory (ISM) device on s390 is one such device. For PCI devices on
IBM s390 error recovery involves platform firmware and notification to
operating system is done by architecture specific way. So the ISM device
can still be recovered when notified of an error.

Reviewed-by: Julian Ruess <julianr@linux.ibm.com>
Reviewed-by: Niklas Schnelle <schnelle@linux.ibm.com>
Reviewed-by: Alex Williamson <alex@shazbot.org>
Signed-off-by: Farhan Ali <alifm@linux.ibm.com>
---
 drivers/vfio/pci/vfio_pci_core.c  | 8 ++------
 drivers/vfio/pci/vfio_pci_intrs.c | 3 +--
 2 files changed, 3 insertions(+), 8 deletions(-)

diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 5a6786feadd7..077a122fb602 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -824,8 +824,7 @@ static int vfio_pci_get_irq_count(struct vfio_pci_core_device *vdev, int irq_typ
 			return (flags & PCI_MSIX_FLAGS_QSIZE) + 1;
 		}
 	} else if (irq_type == VFIO_PCI_ERR_IRQ_INDEX) {
-		if (pci_is_pcie(vdev->pdev))
-			return 1;
+		return 1;
 	} else if (irq_type == VFIO_PCI_REQ_IRQ_INDEX) {
 		return 1;
 	}
@@ -1201,11 +1200,8 @@ static int vfio_pci_ioctl_get_irq_info(struct vfio_pci_core_device *vdev,
 	switch (info.index) {
 	case VFIO_PCI_INTX_IRQ_INDEX ... VFIO_PCI_MSIX_IRQ_INDEX:
 	case VFIO_PCI_REQ_IRQ_INDEX:
-		break;
 	case VFIO_PCI_ERR_IRQ_INDEX:
-		if (pci_is_pcie(vdev->pdev))
-			break;
-		fallthrough;
+		break;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index 33944d4d9dc4..64f80f64ff57 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -859,8 +859,7 @@ int vfio_pci_set_irqs_ioctl(struct vfio_pci_core_device *vdev, uint32_t flags,
 	case VFIO_PCI_ERR_IRQ_INDEX:
 		switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) {
 		case VFIO_IRQ_SET_ACTION_TRIGGER:
-			if (pci_is_pcie(vdev->pdev))
-				func = vfio_pci_set_err_trigger;
+			func = vfio_pci_set_err_trigger;
 			break;
 		}
 		break;
-- 
2.43.0

Re: [PATCH v20 1/3] s390/pci: Store PCI error information for passthrough devices

[sashiko-bot]

> For a passthrough device we need co-operation from user space to recover
> the device. This would require to bubble up any error information to user
> space.  Let's store this error information for passthrough devices, so it
> can be retrieved later.
> 
> We can now have userspace drivers (vfio-pci based) on s390x. The userspace
> drivers will not have any KVM fd and so no kzdev associated with them. So
> we need to update the logic for detecting passthrough devices to not depend
> on struct kvm_zdev.
> 
> Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
> Reviewed-by: Niklas Schnelle <schnelle@linux.ibm.com>
> Signed-off-by: Farhan Ali <alifm@linux.ibm.com>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260630165553.725-1-alifm@linux.ibm.com?part=1

Re: [PATCH v20 2/3] vfio-pci/zdev: Add a device feature for error information

[sashiko-bot]

> For zPCI devices, we have platform specific error information. The platform
> firmware provides this error information to the operating system in an
> architecture specific mechanism. To enable recovery from userspace for
> these devices, we want to expose this error information to userspace. Add a
> new device feature to expose this information.
> 
> Userspace needs to be provide a buffer of fixed size. This size is provided
> to userspace via the VFIO_DEVICE_INFO_CAP_ZPCI_BASE capability.
> 
> Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
> Reviewed-by: Niklas Schnelle <schnelle@linux.ibm.com>
> Signed-off-by: Farhan Ali <alifm@linux.ibm.com>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260630165553.725-1-alifm@linux.ibm.com?part=2

Re: [PATCH v20 3/3] vfio/pci: Remove the pcie check for VFIO_PCI_ERR_IRQ_INDEX

[sashiko-bot]

> The error signaling is configured for the vast majority of devices and it's
> extremely rare that it fires anyway. Removing the pcie check will allow
> userspace to be notified on errors for legacy PCI devices. The Internal
> Shared Memory (ISM) device on s390 is one such device. For PCI devices on
> IBM s390 error recovery involves platform firmware and notification to
> operating system is done by architecture specific way. So the ISM device
> can still be recovered when notified of an error.
> 
> Reviewed-by: Julian Ruess <julianr@linux.ibm.com>
> Reviewed-by: Niklas Schnelle <schnelle@linux.ibm.com>
> Reviewed-by: Alex Williamson <alex@shazbot.org>
> Signed-off-by: Farhan Ali <alifm@linux.ibm.com>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260630165553.725-1-alifm@linux.ibm.com?part=3