* [PATCH v15 1/7] PCI: Allow per function PCI slots to fix slot reset on s390
2026-05-05 20:05 [PATCH v15 0/7] Error recovery for vfio-pci devices on s390x Farhan Ali
@ 2026-05-05 20:05 ` Farhan Ali
2026-05-05 20:05 ` [PATCH v15 2/7] PCI: Avoid saving config space state if inaccessible Farhan Ali
` (5 subsequent siblings)
6 siblings, 0 replies; 8+ messages in thread
From: Farhan Ali @ 2026-05-05 20:05 UTC (permalink / raw)
To: linux-s390, linux-kernel, linux-pci
Cc: helgaas, alex, alifm, schnelle, mjrosato, stable
On s390 systems, which use a machine level hypervisor, PCI devices are
always accessed through a form of PCI pass-through which fundamentally
operates on a per PCI function granularity. This is also reflected in the
s390 PCI hotplug driver which creates hotplug slots for individual PCI
functions. Its reset_slot() function, which is a wrapper for
zpci_hot_reset_device(), thus also resets individual functions.
Currently, the kernel's PCI_SLOT() macro assigns the same pci_slot object
to multifunction devices. This approach worked fine on s390 systems that
only exposed virtual functions as individual PCI domains to the operating
system. Since commit 44510d6fa0c0 ("s390/pci: Handling multifunctions")
s390 supports exposing the topology of multifunction PCI devices by
grouping them in a shared PCI domain. This creates a problem when resetting
a function through the hotplug driver's slot_reset() interface.
When attempting to reset a function through the hotplug driver, the shared
slot assignment causes the wrong function to be reset instead of the
intended one. It also leaks memory as we do create a pci_slot object for
the function, but don't correctly free it in pci_slot_release().
Add a flag for struct pci_slot to allow per function PCI slots for
functions managed through a hypervisor, which exposes individual PCI
functions while retaining the topology. Since we can use all 8 bits
for slot 'number' (for ARI devices), change slot 'number' u16 to
account for special values -1 and PCI_SLOT_ALL_DEVICES.
Fixes: 44510d6fa0c0 ("s390/pci: Handling multifunctions")
Cc: stable@vger.kernel.org
Suggested-by: Niklas Schnelle <schnelle@linux.ibm.com>
Reviewed-by: Niklas Schnelle <schnelle@linux.ibm.com>
Signed-off-by: Farhan Ali <alifm@linux.ibm.com>
---
drivers/pci/hotplug/rpaphp_slot.c | 2 +-
drivers/pci/pci.c | 5 +++--
drivers/pci/slot.c | 33 +++++++++++++++++++++++--------
include/linux/pci.h | 8 ++++++--
4 files changed, 35 insertions(+), 13 deletions(-)
diff --git a/drivers/pci/hotplug/rpaphp_slot.c b/drivers/pci/hotplug/rpaphp_slot.c
index 67362e5b9971..92eabf5f61b9 100644
--- a/drivers/pci/hotplug/rpaphp_slot.c
+++ b/drivers/pci/hotplug/rpaphp_slot.c
@@ -84,7 +84,7 @@ int rpaphp_register_slot(struct slot *slot)
struct hotplug_slot *php_slot = &slot->hotplug_slot;
u32 my_index;
int retval;
- int slotno = -1;
+ int slotno = PCI_SLOT_PLACEHOLDER;
dbg("%s registering slot:path[%pOF] index[%x], name[%s] pdomain[%x] type[%d]\n",
__func__, slot->dn, slot->index, slot->name,
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 8f7cfcc00090..d0c9f0166af5 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -4865,8 +4865,9 @@ static int pci_reset_hotplug_slot(struct hotplug_slot *hotplug, bool probe)
static int pci_dev_reset_slot_function(struct pci_dev *dev, bool probe)
{
- if (dev->multifunction || dev->subordinate || !dev->slot ||
- dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET)
+ if (dev->subordinate || !dev->slot ||
+ dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET ||
+ (dev->multifunction && !dev->slot->per_func_slot))
return -ENOTTY;
return pci_reset_hotplug_slot(dev->slot->hotplug, probe);
diff --git a/drivers/pci/slot.c b/drivers/pci/slot.c
index 6d5cd37bfb1e..894d6213ed30 100644
--- a/drivers/pci/slot.c
+++ b/drivers/pci/slot.c
@@ -37,7 +37,7 @@ static const struct sysfs_ops pci_slot_sysfs_ops = {
static ssize_t address_read_file(struct pci_slot *slot, char *buf)
{
- if (slot->number == 0xff)
+ if (slot->number == (u16)PCI_SLOT_PLACEHOLDER)
return sysfs_emit(buf, "%04x:%02x\n",
pci_domain_nr(slot->bus),
slot->bus->number);
@@ -72,6 +72,23 @@ static ssize_t cur_speed_read_file(struct pci_slot *slot, char *buf)
return bus_speed_read(slot->bus->cur_bus_speed, buf);
}
+static bool pci_dev_matches_slot(struct pci_dev *dev, struct pci_slot *slot)
+{
+ if (slot->per_func_slot)
+ return dev->devfn == slot->number;
+
+ return slot->number == PCI_SLOT_ALL_DEVICES ||
+ PCI_SLOT(dev->devfn) == slot->number;
+}
+
+static bool pci_slot_enabled_per_func(void)
+{
+ if (IS_ENABLED(CONFIG_S390))
+ return true;
+
+ return false;
+}
+
static void pci_slot_release(struct kobject *kobj)
{
struct pci_dev *dev;
@@ -82,8 +99,7 @@ static void pci_slot_release(struct kobject *kobj)
down_read(&pci_bus_sem);
list_for_each_entry(dev, &slot->bus->devices, bus_list)
- if (slot->number == PCI_SLOT_ALL_DEVICES ||
- PCI_SLOT(dev->devfn) == slot->number)
+ if (pci_dev_matches_slot(dev, slot))
dev->slot = NULL;
up_read(&pci_bus_sem);
@@ -187,8 +203,7 @@ void pci_dev_assign_slot(struct pci_dev *dev)
mutex_lock(&pci_slot_mutex);
list_for_each_entry(slot, &dev->bus->slots, list)
- if (slot->number == PCI_SLOT_ALL_DEVICES ||
- PCI_SLOT(dev->devfn) == slot->number)
+ if (pci_dev_matches_slot(dev, slot))
dev->slot = slot;
mutex_unlock(&pci_slot_mutex);
}
@@ -267,7 +282,7 @@ struct pci_slot *pci_create_slot(struct pci_bus *parent, int slot_nr,
mutex_lock(&pci_slot_mutex);
- if (slot_nr == -1)
+ if (slot_nr == PCI_SLOT_PLACEHOLDER)
goto placeholder;
/*
@@ -298,6 +313,9 @@ struct pci_slot *pci_create_slot(struct pci_bus *parent, int slot_nr,
slot->bus = pci_bus_get(parent);
slot->number = slot_nr;
+ if (pci_slot_enabled_per_func())
+ slot->per_func_slot = 1;
+
slot->kobj.kset = pci_slots_kset;
slot_name = make_slot_name(name);
@@ -318,8 +336,7 @@ struct pci_slot *pci_create_slot(struct pci_bus *parent, int slot_nr,
down_read(&pci_bus_sem);
list_for_each_entry(dev, &parent->devices, bus_list)
- if (slot_nr == PCI_SLOT_ALL_DEVICES ||
- PCI_SLOT(dev->devfn) == slot_nr)
+ if (pci_dev_matches_slot(dev, slot))
dev->slot = slot;
up_read(&pci_bus_sem);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 2c4454583c11..d58982aa8730 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -78,14 +78,18 @@
* and, if ARI Forwarding is enabled, functions may appear to be on multiple
* devices.
*/
-#define PCI_SLOT_ALL_DEVICES 0xfe
+#define PCI_SLOT_ALL_DEVICES 0xfeff
+
+/* Used to identify a slot as a placeholder */
+#define PCI_SLOT_PLACEHOLDER -1
/* pci_slot represents a physical slot */
struct pci_slot {
struct pci_bus *bus; /* Bus this slot is on */
struct list_head list; /* Node in list of slots */
struct hotplug_slot *hotplug; /* Hotplug info (move here) */
- unsigned char number; /* Device nr, or PCI_SLOT_ALL_DEVICES */
+ u16 number; /* Device nr, or PCI_SLOT_ALL_DEVICES */
+ unsigned int per_func_slot:1; /* Allow per function slot */
struct kobject kobj;
};
--
2.43.0
^ permalink raw reply related [flat|nested] 8+ messages in thread* [PATCH v15 2/7] PCI: Avoid saving config space state if inaccessible
2026-05-05 20:05 [PATCH v15 0/7] Error recovery for vfio-pci devices on s390x Farhan Ali
2026-05-05 20:05 ` [PATCH v15 1/7] PCI: Allow per function PCI slots to fix slot reset on s390 Farhan Ali
@ 2026-05-05 20:05 ` Farhan Ali
2026-05-05 20:05 ` [PATCH v15 3/7] PCI: Fail FLR when config space is inaccessible Farhan Ali
` (4 subsequent siblings)
6 siblings, 0 replies; 8+ messages in thread
From: Farhan Ali @ 2026-05-05 20:05 UTC (permalink / raw)
To: linux-s390, linux-kernel, linux-pci
Cc: helgaas, alex, alifm, schnelle, mjrosato, Bjorn Helgaas
The current reset process saves the device's config space state before
reset and restores it afterward. However errors may occur unexpectedly and
it may then be impossible to save config space because the device may be
inaccessible (e.g. DPC). This results in saving invalid values that get
written back to the device during state restoration.
With a reset we want to recover/restore the device into a functional state.
So avoid saving the state of the config space when the device config space
is inaccessible.
Reviewed-by: Niklas Schnelle <schnelle@linux.ibm.com>
Reviewed-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Farhan Ali <alifm@linux.ibm.com>
---
drivers/pci/pci.c | 24 ++++++++++++++++++++++++
1 file changed, 24 insertions(+)
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index d0c9f0166af5..e71b81415392 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -722,6 +722,27 @@ u16 pci_find_dvsec_capability(struct pci_dev *dev, u16 vendor, u16 dvsec)
}
EXPORT_SYMBOL_GPL(pci_find_dvsec_capability);
+static bool pci_dev_config_accessible(struct pci_dev *dev, char *msg)
+{
+ u32 val;
+
+ /*
+ * If device's config space is inaccessible it can return ~0 for
+ * any reads. Since VFs can also return ~0 for Device and Vendor ID
+ * check Command and Status registers. Note that this is racy
+ * because the device may become inaccessible partway through
+ * next access.
+ */
+ pci_read_config_dword(dev, PCI_COMMAND, &val);
+ if (PCI_POSSIBLE_ERROR(val)) {
+ pci_warn(dev, "Device config space inaccessible; unable to %s\n",
+ msg);
+ return false;
+ }
+
+ return true;
+}
+
/**
* pci_find_parent_resource - return resource region of parent bus of given
* region
@@ -5027,6 +5048,9 @@ static void pci_dev_save_and_disable(struct pci_dev *dev)
*/
pci_set_power_state(dev, PCI_D0);
+ if (!pci_dev_config_accessible(dev, "save state"))
+ return;
+
pci_save_state(dev);
/*
* Disable the device by clearing the Command register, except for
--
2.43.0
^ permalink raw reply related [flat|nested] 8+ messages in thread* [PATCH v15 3/7] PCI: Fail FLR when config space is inaccessible
2026-05-05 20:05 [PATCH v15 0/7] Error recovery for vfio-pci devices on s390x Farhan Ali
2026-05-05 20:05 ` [PATCH v15 1/7] PCI: Allow per function PCI slots to fix slot reset on s390 Farhan Ali
2026-05-05 20:05 ` [PATCH v15 2/7] PCI: Avoid saving config space state if inaccessible Farhan Ali
@ 2026-05-05 20:05 ` Farhan Ali
2026-05-05 20:05 ` [PATCH v15 4/7] s390/pci: Store PCI error information for passthrough devices Farhan Ali
` (3 subsequent siblings)
6 siblings, 0 replies; 8+ messages in thread
From: Farhan Ali @ 2026-05-05 20:05 UTC (permalink / raw)
To: linux-s390, linux-kernel, linux-pci
Cc: helgaas, alex, alifm, schnelle, mjrosato, Benjamin Block
If a device is in an error state, then it's config space may not be
accssible. Add additional check to validate if a device's config space is
accessible before doing an FLR reset.
Reviewed-by: Benjamin Block <bblock@linux.ibm.com>
Reviewed-by: Niklas Schnelle <schnelle@linux.ibm.com>
Signed-off-by: Farhan Ali <alifm@linux.ibm.com>
---
drivers/pci/pci.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index e71b81415392..c50418f5e318 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -4396,6 +4396,9 @@ int pcie_reset_flr(struct pci_dev *dev, bool probe)
if (!(dev->devcap & PCI_EXP_DEVCAP_FLR))
return -ENOTTY;
+ if (!pci_dev_config_accessible(dev, "FLR"))
+ return -ENOTTY;
+
if (probe)
return 0;
--
2.43.0
^ permalink raw reply related [flat|nested] 8+ messages in thread* [PATCH v15 4/7] s390/pci: Store PCI error information for passthrough devices
2026-05-05 20:05 [PATCH v15 0/7] Error recovery for vfio-pci devices on s390x Farhan Ali
` (2 preceding siblings ...)
2026-05-05 20:05 ` [PATCH v15 3/7] PCI: Fail FLR when config space is inaccessible Farhan Ali
@ 2026-05-05 20:05 ` Farhan Ali
2026-05-05 20:05 ` [PATCH v15 5/7] vfio-pci/zdev: Add a device feature for error information Farhan Ali
` (2 subsequent siblings)
6 siblings, 0 replies; 8+ messages in thread
From: Farhan Ali @ 2026-05-05 20:05 UTC (permalink / raw)
To: linux-s390, linux-kernel, linux-pci
Cc: helgaas, alex, alifm, schnelle, mjrosato
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>
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 | 114 +++++++++++++++++--------------
drivers/vfio/pci/vfio_pci_zdev.c | 18 ++++-
4 files changed, 109 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..41547c54076f 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 +52,46 @@ static bool is_driver_supported(struct pci_driver *driver)
return true;
}
+static void 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;
+
+ if (zdev->pending_errs.count >= ZPCI_ERR_PENDING_MAX) {
+ pr_err("%s: Maximum number (%d) of pending error events queued",
+ pci_name(pdev), ZPCI_ERR_PENDING_MAX);
+ return;
+ }
+
+ 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++;
+}
+
+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",
+ 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)
{
@@ -175,7 +186,8 @@ 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);
@@ -194,13 +206,6 @@ 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 +221,25 @@ static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev)
goto out_unlock;
}
+ zpci_store_pci_error(pdev, ccdf);
+
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;
}
+ mutex_lock(&zdev->pending_errs_lock);
+ if (zdev->pending_errs.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";
+ mutex_unlock(&zdev->pending_errs_lock);
+ goto out_unlock;
+ }
+ mutex_unlock(&zdev->pending_errs_lock);
+
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 +284,19 @@ 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 +342,12 @@ 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
^ permalink raw reply related [flat|nested] 8+ messages in thread* [PATCH v15 5/7] vfio-pci/zdev: Add a device feature for error information
2026-05-05 20:05 [PATCH v15 0/7] Error recovery for vfio-pci devices on s390x Farhan Ali
` (3 preceding siblings ...)
2026-05-05 20:05 ` [PATCH v15 4/7] s390/pci: Store PCI error information for passthrough devices Farhan Ali
@ 2026-05-05 20:05 ` Farhan Ali
2026-05-05 20:05 ` [PATCH v15 6/7] vfio/pci: Add a reset_done callback for vfio-pci driver Farhan Ali
2026-05-05 20:05 ` [PATCH v15 7/7] vfio/pci: Remove the pcie check for VFIO_PCI_ERR_IRQ_INDEX Farhan Ali
6 siblings, 0 replies; 8+ messages in thread
From: Farhan Ali @ 2026-05-05 20:05 UTC (permalink / raw)
To: linux-s390, linux-kernel, linux-pci
Cc: helgaas, alex, alifm, schnelle, mjrosato
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.
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 | 39 ++++++++++++++++++++++++++++++++
include/uapi/linux/vfio.h | 30 ++++++++++++++++++++++++
6 files changed, 101 insertions(+)
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 41547c54076f..fc4b51bc4c3c 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -74,6 +74,25 @@ static void zpci_store_pci_error(struct pci_dev *pdev,
zdev->pending_errs.count++;
}
+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 3f8d093aacf8..f47a49ca67fa 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -1534,6 +1534,8 @@ 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..cc148123a97b 100644
--- a/drivers/vfio/pci/vfio_pci_zdev.c
+++ b/drivers/vfio/pci/vfio_pci_zdev.c
@@ -141,6 +141,45 @@ 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;
+
+ ret = zpci_get_pending_error(zdev, &ccdf);
+ if (ret)
+ return ret;
+
+ err.fh = ccdf.fh;
+ err.fid = ccdf.fid;
+ err.ett = ccdf.ett;
+ err.mvn = ccdf.mvn;
+ err.dmaas = ccdf.dmaas;
+ err.q = ccdf.q;
+ err.rw = ccdf.rw;
+ err.faddr = ccdf.faddr;
+ err.pec = ccdf.pec;
+
+ if (copy_to_user(arg, &err, sizeof(err)))
+ 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..3eead86a00ab 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -1534,6 +1534,36 @@ 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. The ioctl returns -ENOMSG if there are no pending
+ * PCI errors.
+ */
+
+struct vfio_device_feature_zpci_err {
+ __u32 feature_flags; /* Indicate future features */
+ __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 */
+ __u8 reserved5[28]; /* Allow for future expansion */
+};
+
+#define VFIO_DEVICE_FEATURE_ZPCI_ERROR 13
+
/* -------- API for Type1 VFIO IOMMU -------- */
/**
--
2.43.0
^ permalink raw reply related [flat|nested] 8+ messages in thread* [PATCH v15 6/7] vfio/pci: Add a reset_done callback for vfio-pci driver
2026-05-05 20:05 [PATCH v15 0/7] Error recovery for vfio-pci devices on s390x Farhan Ali
` (4 preceding siblings ...)
2026-05-05 20:05 ` [PATCH v15 5/7] vfio-pci/zdev: Add a device feature for error information Farhan Ali
@ 2026-05-05 20:05 ` Farhan Ali
2026-05-05 20:05 ` [PATCH v15 7/7] vfio/pci: Remove the pcie check for VFIO_PCI_ERR_IRQ_INDEX Farhan Ali
6 siblings, 0 replies; 8+ messages in thread
From: Farhan Ali @ 2026-05-05 20:05 UTC (permalink / raw)
To: linux-s390, linux-kernel, linux-pci
Cc: helgaas, alex, alifm, schnelle, mjrosato, Julian Ruess
On error recovery for a PCI device bound to vfio-pci driver, we want to
recover the state of the device to its last known saved state. The callback
restores the state of the device to its initial saved state.
Reviewed-by: Julian Ruess <julianr@linux.ibm.com>
Reviewed-by: Niklas Schnelle <schnelle@linux.ibm.com>
Acked-by: Alex Williamson <alex@shazbot.org>
Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Signed-off-by: Farhan Ali <alifm@linux.ibm.com>
---
drivers/vfio/pci/vfio_pci_core.c | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index f47a49ca67fa..6358b59fab2b 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -2255,6 +2255,17 @@ pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev,
}
EXPORT_SYMBOL_GPL(vfio_pci_core_aer_err_detected);
+static void vfio_pci_core_aer_reset_done(struct pci_dev *pdev)
+{
+ struct vfio_pci_core_device *vdev = dev_get_drvdata(&pdev->dev);
+
+ if (!vdev->pci_saved_state)
+ return;
+
+ pci_load_saved_state(pdev, vdev->pci_saved_state);
+ pci_restore_state(pdev);
+}
+
int vfio_pci_core_sriov_configure(struct vfio_pci_core_device *vdev,
int nr_virtfn)
{
@@ -2319,6 +2330,7 @@ EXPORT_SYMBOL_GPL(vfio_pci_core_sriov_configure);
const struct pci_error_handlers vfio_pci_core_err_handlers = {
.error_detected = vfio_pci_core_aer_err_detected,
+ .reset_done = vfio_pci_core_aer_reset_done,
};
EXPORT_SYMBOL_GPL(vfio_pci_core_err_handlers);
--
2.43.0
^ permalink raw reply related [flat|nested] 8+ messages in thread* [PATCH v15 7/7] vfio/pci: Remove the pcie check for VFIO_PCI_ERR_IRQ_INDEX
2026-05-05 20:05 [PATCH v15 0/7] Error recovery for vfio-pci devices on s390x Farhan Ali
` (5 preceding siblings ...)
2026-05-05 20:05 ` [PATCH v15 6/7] vfio/pci: Add a reset_done callback for vfio-pci driver Farhan Ali
@ 2026-05-05 20:05 ` Farhan Ali
6 siblings, 0 replies; 8+ messages in thread
From: Farhan Ali @ 2026-05-05 20:05 UTC (permalink / raw)
To: linux-s390, linux-kernel, linux-pci
Cc: helgaas, alex, alifm, schnelle, mjrosato, Julian Ruess
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 6358b59fab2b..cd9f31b28160 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -786,8 +786,7 @@ 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;
}
@@ -1163,11 +1162,8 @@ 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
^ permalink raw reply related [flat|nested] 8+ messages in thread