Hi all,
This series of backports fixes the SWIOTLB library to maintain the
page offset when mapping a DMA address. The bug that motivated this
patch series manifested when running a 5.4 kernel as a SEV guest with
an NVMe device. However, any device that infers information from the
page offset and is accessed through the SWIOTLB will benefit from this
bug fix.
Jianxiong Gao (7):
driver core: add a min_align_mask field to struct
device_dma_parameters
swiotlb: add a io_tlb_offset helper
swiotlb: factor out a nr_slots helper
swiotlb: clean up swiotlb_tbl_unmap_single
swiotlb: refactor swiotlb_tbl_map_single
swiotlb: don't modify orig_addr in swiotlb_tbl_sync_single
nvme-pci: set min_align_mask
Linus Torvalds (1):
Linux 5.4
Makefile | 2 +-
drivers/nvme/host/pci.c | 1 +
include/linux/device.h | 1 +
include/linux/dma-mapping.h | 16 +++
include/linux/swiotlb.h | 3 +-
kernel/dma/swiotlb.c | 262 ++++++++++++++++++++----------------
6 files changed, 165 insertions(+), 120 deletions(-)
--
2.27.0
Commit 8cdddd182bd7 ("ACPI: processor: Fix CPU0 wakeup in
acpi_idle_play_dead()") tried to fix CPU0 hotplug breakage by copying
wakeup_cpu0() + start_cpu0() logic from hlt_play_dead()//mwait_play_dead()
into acpi_idle_play_dead(). The problem is that these functions are not
exported to modules so when CONFIG_ACPI_PROCESSOR=m build fails.
The issue could've been fixed by exporting both wakeup_cpu0()/start_cpu0()
(the later from assembly) but it seems putting the whole pattern into a
new function and exporting it instead is better.
Reported-by: kernel test robot <lkp(a)intel.com>
Fixes: 8cdddd182bd7 ("CPI: processor: Fix CPU0 wakeup in acpi_idle_play_dead()")
Cc: <stable(a)vger.kernel.org> # 5.10+
Signed-off-by: Vitaly Kuznetsov <vkuznets(a)redhat.com>
---
Changes since v1:
- Rename wakeup_cpu0() to cond_wakeup_cpu0() and fold wakeup_cpu0() in
as it has no other users [Rafael J. Wysocki]
---
arch/x86/include/asm/smp.h | 2 +-
arch/x86/kernel/smpboot.c | 24 ++++++++++--------------
drivers/acpi/processor_idle.c | 4 +---
3 files changed, 12 insertions(+), 18 deletions(-)
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 57ef2094af93..630ff08532be 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -132,7 +132,7 @@ void native_play_dead(void);
void play_dead_common(void);
void wbinvd_on_cpu(int cpu);
int wbinvd_on_all_cpus(void);
-bool wakeup_cpu0(void);
+void cond_wakeup_cpu0(void);
void native_smp_send_reschedule(int cpu);
void native_send_call_func_ipi(const struct cpumask *mask);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index f877150a91da..147f1bba9736 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1659,13 +1659,15 @@ void play_dead_common(void)
local_irq_disable();
}
-bool wakeup_cpu0(void)
+/*
+ * If NMI wants to wake up CPU0, start CPU0.
+ */
+void cond_wakeup_cpu0(void)
{
if (smp_processor_id() == 0 && enable_start_cpu0)
- return true;
-
- return false;
+ start_cpu0();
}
+EXPORT_SYMBOL_GPL(cond_wakeup_cpu0);
/*
* We need to flush the caches before going to sleep, lest we have
@@ -1734,11 +1736,8 @@ static inline void mwait_play_dead(void)
__monitor(mwait_ptr, 0, 0);
mb();
__mwait(eax, 0);
- /*
- * If NMI wants to wake up CPU0, start CPU0.
- */
- if (wakeup_cpu0())
- start_cpu0();
+
+ cond_wakeup_cpu0();
}
}
@@ -1749,11 +1748,8 @@ void hlt_play_dead(void)
while (1) {
native_halt();
- /*
- * If NMI wants to wake up CPU0, start CPU0.
- */
- if (wakeup_cpu0())
- start_cpu0();
+
+ cond_wakeup_cpu0();
}
}
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 768a6b4d2368..4e2d76b8b697 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -544,9 +544,7 @@ static int acpi_idle_play_dead(struct cpuidle_device *dev, int index)
return -ENODEV;
#if defined(CONFIG_X86) && defined(CONFIG_HOTPLUG_CPU)
- /* If NMI wants to wake up CPU0, start CPU0. */
- if (wakeup_cpu0())
- start_cpu0();
+ cond_wakeup_cpu0();
#endif
}
--
2.30.2
This patch fixes a lockdep splat introduced by commit f21916ec4826
("s390/vfio-ap: clean up vfio_ap resources when KVM pointer invalidated").
The lockdep splat only occurs when starting a Secure Execution guest.
Crypto virtualization (vfio_ap) is not yet supported for SE guests;
however, in order to avoid this problem when support becomes available,
this fix is being provided.
The circular locking dependency was introduced when the setting of the
masks in the guest's APCB was executed while holding the matrix_dev->lock.
While the lock is definitely needed to protect the setting/unsetting of the
matrix_mdev->kvm pointer, it is not necessarily critical for setting the
masks; so, the matrix_dev->lock will be released while the masks are being
set or cleared.
Keep in mind, however, that another process that takes the matrix_dev->lock
can get control while the masks in the guest's APCB are being set or
cleared as a result of the driver being notified that the KVM pointer
has been set or unset. This could result in invalid access to the
matrix_mdev->kvm pointer by the intervening process. To avoid this
scenario, two new fields are being added to the ap_matrix_mdev struct:
struct ap_matrix_mdev {
...
bool kvm_busy;
wait_queue_head_t wait_for_kvm;
...
};
The functions that handle notification that the KVM pointer value has
been set or cleared will set the kvm_busy flag to true until they are done
processing at which time they will set it to false and wake up the tasks on
the matrix_mdev->wait_for_kvm wait queue. Functions that require
access to matrix_mdev->kvm will sleep on the wait queue until they are
awakened at which time they can safely access the matrix_mdev->kvm
field.
Fixes: f21916ec4826 ("s390/vfio-ap: clean up vfio_ap resources when KVM pointer invalidated")
Cc: stable(a)vger.kernel.org
Signed-off-by: Tony Krowiak <akrowiak(a)linux.ibm.com>
---
drivers/s390/crypto/vfio_ap_ops.c | 308 ++++++++++++++++++--------
drivers/s390/crypto/vfio_ap_private.h | 2 +
2 files changed, 215 insertions(+), 95 deletions(-)
diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index 1ffdd411201c..6946a7e26eff 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -294,6 +294,19 @@ static int handle_pqap(struct kvm_vcpu *vcpu)
matrix_mdev = container_of(vcpu->kvm->arch.crypto.pqap_hook,
struct ap_matrix_mdev, pqap_hook);
+ /*
+ * If the KVM pointer is in the process of being set, wait until the
+ * process has completed.
+ */
+ wait_event_cmd(matrix_mdev->wait_for_kvm,
+ !matrix_mdev->kvm_busy,
+ mutex_unlock(&matrix_dev->lock),
+ mutex_lock(&matrix_dev->lock));
+
+ /* If the there is no guest using the mdev, there is nothing to do */
+ if (!matrix_mdev->kvm)
+ goto out_unlock;
+
q = vfio_ap_get_queue(matrix_mdev, apqn);
if (!q)
goto out_unlock;
@@ -337,6 +350,7 @@ static int vfio_ap_mdev_create(struct kobject *kobj, struct mdev_device *mdev)
matrix_mdev->mdev = mdev;
vfio_ap_matrix_init(&matrix_dev->info, &matrix_mdev->matrix);
+ init_waitqueue_head(&matrix_mdev->wait_for_kvm);
mdev_set_drvdata(mdev, matrix_mdev);
matrix_mdev->pqap_hook.hook = handle_pqap;
matrix_mdev->pqap_hook.owner = THIS_MODULE;
@@ -351,17 +365,23 @@ static int vfio_ap_mdev_remove(struct mdev_device *mdev)
{
struct ap_matrix_mdev *matrix_mdev = mdev_get_drvdata(mdev);
- if (matrix_mdev->kvm)
+ mutex_lock(&matrix_dev->lock);
+
+ /*
+ * If the KVM pointer is in flux or the guest is running, disallow
+ * un-assignment of control domain.
+ */
+ if (matrix_mdev->kvm_busy || matrix_mdev->kvm) {
+ mutex_unlock(&matrix_dev->lock);
return -EBUSY;
+ }
- mutex_lock(&matrix_dev->lock);
vfio_ap_mdev_reset_queues(mdev);
list_del(&matrix_mdev->node);
- mutex_unlock(&matrix_dev->lock);
-
kfree(matrix_mdev);
mdev_set_drvdata(mdev, NULL);
atomic_inc(&matrix_dev->available_instances);
+ mutex_unlock(&matrix_dev->lock);
return 0;
}
@@ -606,24 +626,31 @@ static ssize_t assign_adapter_store(struct device *dev,
struct mdev_device *mdev = mdev_from_dev(dev);
struct ap_matrix_mdev *matrix_mdev = mdev_get_drvdata(mdev);
- /* If the guest is running, disallow assignment of adapter */
- if (matrix_mdev->kvm)
- return -EBUSY;
+ mutex_lock(&matrix_dev->lock);
+
+ /*
+ * If the KVM pointer is in flux or the guest is running, disallow
+ * un-assignment of adapter
+ */
+ if (matrix_mdev->kvm_busy || matrix_mdev->kvm) {
+ ret = -EBUSY;
+ goto done;
+ }
ret = kstrtoul(buf, 0, &apid);
if (ret)
- return ret;
+ goto done;
- if (apid > matrix_mdev->matrix.apm_max)
- return -ENODEV;
+ if (apid > matrix_mdev->matrix.apm_max) {
+ ret = -ENODEV;
+ goto done;
+ }
/*
* Set the bit in the AP mask (APM) corresponding to the AP adapter
* number (APID). The bits in the mask, from most significant to least
* significant bit, correspond to APIDs 0-255.
*/
- mutex_lock(&matrix_dev->lock);
-
ret = vfio_ap_mdev_verify_queues_reserved_for_apid(matrix_mdev, apid);
if (ret)
goto done;
@@ -672,22 +699,31 @@ static ssize_t unassign_adapter_store(struct device *dev,
struct mdev_device *mdev = mdev_from_dev(dev);
struct ap_matrix_mdev *matrix_mdev = mdev_get_drvdata(mdev);
- /* If the guest is running, disallow un-assignment of adapter */
- if (matrix_mdev->kvm)
- return -EBUSY;
+ mutex_lock(&matrix_dev->lock);
+
+ /*
+ * If the KVM pointer is in flux or the guest is running, disallow
+ * un-assignment of adapter
+ */
+ if (matrix_mdev->kvm_busy || matrix_mdev->kvm) {
+ ret = -EBUSY;
+ goto done;
+ }
ret = kstrtoul(buf, 0, &apid);
if (ret)
- return ret;
+ goto done;
- if (apid > matrix_mdev->matrix.apm_max)
- return -ENODEV;
+ if (apid > matrix_mdev->matrix.apm_max) {
+ ret = -ENODEV;
+ goto done;
+ }
- mutex_lock(&matrix_dev->lock);
clear_bit_inv((unsigned long)apid, matrix_mdev->matrix.apm);
+ ret = count;
+done:
mutex_unlock(&matrix_dev->lock);
-
- return count;
+ return ret;
}
static DEVICE_ATTR_WO(unassign_adapter);
@@ -753,17 +789,24 @@ static ssize_t assign_domain_store(struct device *dev,
struct ap_matrix_mdev *matrix_mdev = mdev_get_drvdata(mdev);
unsigned long max_apqi = matrix_mdev->matrix.aqm_max;
- /* If the guest is running, disallow assignment of domain */
- if (matrix_mdev->kvm)
- return -EBUSY;
+ mutex_lock(&matrix_dev->lock);
+
+ /*
+ * If the KVM pointer is in flux or the guest is running, disallow
+ * assignment of domain
+ */
+ if (matrix_mdev->kvm_busy || matrix_mdev->kvm) {
+ ret = -EBUSY;
+ goto done;
+ }
ret = kstrtoul(buf, 0, &apqi);
if (ret)
- return ret;
- if (apqi > max_apqi)
- return -ENODEV;
-
- mutex_lock(&matrix_dev->lock);
+ goto done;
+ if (apqi > max_apqi) {
+ ret = -ENODEV;
+ goto done;
+ }
ret = vfio_ap_mdev_verify_queues_reserved_for_apqi(matrix_mdev, apqi);
if (ret)
@@ -814,22 +857,32 @@ static ssize_t unassign_domain_store(struct device *dev,
struct mdev_device *mdev = mdev_from_dev(dev);
struct ap_matrix_mdev *matrix_mdev = mdev_get_drvdata(mdev);
- /* If the guest is running, disallow un-assignment of domain */
- if (matrix_mdev->kvm)
- return -EBUSY;
+ mutex_lock(&matrix_dev->lock);
+
+ /*
+ * If the KVM pointer is in flux or the guest is running, disallow
+ * un-assignment of domain
+ */
+ if (matrix_mdev->kvm_busy || matrix_mdev->kvm) {
+ ret = -EBUSY;
+ goto done;
+ }
ret = kstrtoul(buf, 0, &apqi);
if (ret)
- return ret;
+ goto done;
- if (apqi > matrix_mdev->matrix.aqm_max)
- return -ENODEV;
+ if (apqi > matrix_mdev->matrix.aqm_max) {
+ ret = -ENODEV;
+ goto done;
+ }
- mutex_lock(&matrix_dev->lock);
clear_bit_inv((unsigned long)apqi, matrix_mdev->matrix.aqm);
- mutex_unlock(&matrix_dev->lock);
+ ret = count;
- return count;
+done:
+ mutex_unlock(&matrix_dev->lock);
+ return ret;
}
static DEVICE_ATTR_WO(unassign_domain);
@@ -858,27 +911,36 @@ static ssize_t assign_control_domain_store(struct device *dev,
struct mdev_device *mdev = mdev_from_dev(dev);
struct ap_matrix_mdev *matrix_mdev = mdev_get_drvdata(mdev);
- /* If the guest is running, disallow assignment of control domain */
- if (matrix_mdev->kvm)
- return -EBUSY;
+ mutex_lock(&matrix_dev->lock);
+
+ /*
+ * If the KVM pointer is in flux or the guest is running, disallow
+ * assignment of control domain.
+ */
+ if (matrix_mdev->kvm_busy || matrix_mdev->kvm) {
+ ret = -EBUSY;
+ goto done;
+ }
ret = kstrtoul(buf, 0, &id);
if (ret)
- return ret;
+ goto done;
- if (id > matrix_mdev->matrix.adm_max)
- return -ENODEV;
+ if (id > matrix_mdev->matrix.adm_max) {
+ ret = -ENODEV;
+ goto done;
+ }
/* Set the bit in the ADM (bitmask) corresponding to the AP control
* domain number (id). The bits in the mask, from most significant to
* least significant, correspond to IDs 0 up to the one less than the
* number of control domains that can be assigned.
*/
- mutex_lock(&matrix_dev->lock);
set_bit_inv(id, matrix_mdev->matrix.adm);
+ ret = count;
+done:
mutex_unlock(&matrix_dev->lock);
-
- return count;
+ return ret;
}
static DEVICE_ATTR_WO(assign_control_domain);
@@ -908,21 +970,30 @@ static ssize_t unassign_control_domain_store(struct device *dev,
struct ap_matrix_mdev *matrix_mdev = mdev_get_drvdata(mdev);
unsigned long max_domid = matrix_mdev->matrix.adm_max;
- /* If the guest is running, disallow un-assignment of control domain */
- if (matrix_mdev->kvm)
- return -EBUSY;
+ mutex_lock(&matrix_dev->lock);
+
+ /*
+ * If the KVM pointer is in flux or the guest is running, disallow
+ * un-assignment of control domain.
+ */
+ if (matrix_mdev->kvm_busy || matrix_mdev->kvm) {
+ ret = -EBUSY;
+ goto done;
+ }
ret = kstrtoul(buf, 0, &domid);
if (ret)
- return ret;
- if (domid > max_domid)
- return -ENODEV;
+ goto done;
+ if (domid > max_domid) {
+ ret = -ENODEV;
+ goto done;
+ }
- mutex_lock(&matrix_dev->lock);
clear_bit_inv(domid, matrix_mdev->matrix.adm);
+ ret = count;
+done:
mutex_unlock(&matrix_dev->lock);
-
- return count;
+ return ret;
}
static DEVICE_ATTR_WO(unassign_control_domain);
@@ -1027,8 +1098,15 @@ static const struct attribute_group *vfio_ap_mdev_attr_groups[] = {
* @matrix_mdev: a mediated matrix device
* @kvm: reference to KVM instance
*
- * Verifies no other mediated matrix device has @kvm and sets a reference to
- * it in @matrix_mdev->kvm.
+ * Sets all data for @matrix_mdev that are needed to manage AP resources
+ * for the guest whose state is represented by @kvm.
+ *
+ * Note: The matrix_dev->lock must be taken prior to calling
+ * this function; however, the lock will be temporarily released while the
+ * guest's AP configuration is set to avoid a potential lockdep splat.
+ * The kvm->lock is taken to set the guest's AP configuration which, under
+ * certain circumstances, will result in a circular lock dependency if this is
+ * done under the @matrix_mdev->lock.
*
* Return 0 if no other mediated matrix device has a reference to @kvm;
* otherwise, returns an -EPERM.
@@ -1038,14 +1116,25 @@ static int vfio_ap_mdev_set_kvm(struct ap_matrix_mdev *matrix_mdev,
{
struct ap_matrix_mdev *m;
- list_for_each_entry(m, &matrix_dev->mdev_list, node) {
- if ((m != matrix_mdev) && (m->kvm == kvm))
- return -EPERM;
- }
+ if (kvm->arch.crypto.crycbd) {
+ list_for_each_entry(m, &matrix_dev->mdev_list, node) {
+ if (m != matrix_mdev && m->kvm == kvm)
+ return -EPERM;
+ }
- matrix_mdev->kvm = kvm;
- kvm_get_kvm(kvm);
- kvm->arch.crypto.pqap_hook = &matrix_mdev->pqap_hook;
+ kvm_get_kvm(kvm);
+ matrix_mdev->kvm_busy = true;
+ mutex_unlock(&matrix_dev->lock);
+ kvm_arch_crypto_set_masks(kvm,
+ matrix_mdev->matrix.apm,
+ matrix_mdev->matrix.aqm,
+ matrix_mdev->matrix.adm);
+ mutex_lock(&matrix_dev->lock);
+ kvm->arch.crypto.pqap_hook = &matrix_mdev->pqap_hook;
+ matrix_mdev->kvm = kvm;
+ matrix_mdev->kvm_busy = false;
+ wake_up_all(&matrix_mdev->wait_for_kvm);
+ }
return 0;
}
@@ -1079,51 +1168,65 @@ static int vfio_ap_mdev_iommu_notifier(struct notifier_block *nb,
return NOTIFY_DONE;
}
+/**
+ * vfio_ap_mdev_unset_kvm
+ *
+ * @matrix_mdev: a matrix mediated device
+ *
+ * Performs clean-up of resources no longer needed by @matrix_mdev.
+ *
+ * Note: The matrix_dev->lock must be taken prior to calling
+ * this function; however, the lock will be temporarily released while the
+ * guest's AP configuration is cleared to avoid a potential lockdep splat.
+ * The kvm->lock is taken to clear the guest's AP configuration which, under
+ * certain circumstances, will result in a circular lock dependency if this is
+ * done under the @matrix_mdev->lock.
+ *
+ */
static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev)
{
- kvm_arch_crypto_clear_masks(matrix_mdev->kvm);
- matrix_mdev->kvm->arch.crypto.pqap_hook = NULL;
- vfio_ap_mdev_reset_queues(matrix_mdev->mdev);
- kvm_put_kvm(matrix_mdev->kvm);
- matrix_mdev->kvm = NULL;
+ /*
+ * If the KVM pointer is in the process of being set, wait until the
+ * process has completed.
+ */
+ wait_event_cmd(matrix_mdev->wait_for_kvm,
+ !matrix_mdev->kvm_busy,
+ mutex_unlock(&matrix_dev->lock),
+ mutex_lock(&matrix_dev->lock));
+
+ if (matrix_mdev->kvm) {
+ matrix_mdev->kvm_busy = true;
+ mutex_unlock(&matrix_dev->lock);
+ kvm_arch_crypto_clear_masks(matrix_mdev->kvm);
+ mutex_lock(&matrix_dev->lock);
+ vfio_ap_mdev_reset_queues(matrix_mdev->mdev);
+ matrix_mdev->kvm->arch.crypto.pqap_hook = NULL;
+ kvm_put_kvm(matrix_mdev->kvm);
+ matrix_mdev->kvm = NULL;
+ matrix_mdev->kvm_busy = false;
+ wake_up_all(&matrix_mdev->wait_for_kvm);
+ }
}
static int vfio_ap_mdev_group_notifier(struct notifier_block *nb,
unsigned long action, void *data)
{
- int ret, notify_rc = NOTIFY_OK;
+ int notify_rc = NOTIFY_OK;
struct ap_matrix_mdev *matrix_mdev;
if (action != VFIO_GROUP_NOTIFY_SET_KVM)
return NOTIFY_OK;
- matrix_mdev = container_of(nb, struct ap_matrix_mdev, group_notifier);
mutex_lock(&matrix_dev->lock);
+ matrix_mdev = container_of(nb, struct ap_matrix_mdev, group_notifier);
- if (!data) {
- if (matrix_mdev->kvm)
- vfio_ap_mdev_unset_kvm(matrix_mdev);
- goto notify_done;
- }
-
- ret = vfio_ap_mdev_set_kvm(matrix_mdev, data);
- if (ret) {
- notify_rc = NOTIFY_DONE;
- goto notify_done;
- }
-
- /* If there is no CRYCB pointer, then we can't copy the masks */
- if (!matrix_mdev->kvm->arch.crypto.crycbd) {
+ if (!data)
+ vfio_ap_mdev_unset_kvm(matrix_mdev);
+ else if (vfio_ap_mdev_set_kvm(matrix_mdev, data))
notify_rc = NOTIFY_DONE;
- goto notify_done;
- }
-
- kvm_arch_crypto_set_masks(matrix_mdev->kvm, matrix_mdev->matrix.apm,
- matrix_mdev->matrix.aqm,
- matrix_mdev->matrix.adm);
-notify_done:
mutex_unlock(&matrix_dev->lock);
+
return notify_rc;
}
@@ -1258,8 +1361,7 @@ static void vfio_ap_mdev_release(struct mdev_device *mdev)
struct ap_matrix_mdev *matrix_mdev = mdev_get_drvdata(mdev);
mutex_lock(&matrix_dev->lock);
- if (matrix_mdev->kvm)
- vfio_ap_mdev_unset_kvm(matrix_mdev);
+ vfio_ap_mdev_unset_kvm(matrix_mdev);
mutex_unlock(&matrix_dev->lock);
vfio_unregister_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY,
@@ -1293,6 +1395,7 @@ static ssize_t vfio_ap_mdev_ioctl(struct mdev_device *mdev,
unsigned int cmd, unsigned long arg)
{
int ret;
+ struct ap_matrix_mdev *matrix_mdev;
mutex_lock(&matrix_dev->lock);
switch (cmd) {
@@ -1300,6 +1403,21 @@ static ssize_t vfio_ap_mdev_ioctl(struct mdev_device *mdev,
ret = vfio_ap_mdev_get_device_info(arg);
break;
case VFIO_DEVICE_RESET:
+ matrix_mdev = mdev_get_drvdata(mdev);
+ if (WARN(!matrix_mdev, "Driver data missing from mdev!!")) {
+ ret = -EINVAL;
+ break;
+ }
+
+ /*
+ * If the KVM pointer is in the process of being set, wait until
+ * the process has completed.
+ */
+ wait_event_cmd(matrix_mdev->wait_for_kvm,
+ !matrix_mdev->kvm_busy,
+ mutex_unlock(&matrix_dev->lock),
+ mutex_lock(&matrix_dev->lock));
+
ret = vfio_ap_mdev_reset_queues(mdev);
break;
default:
diff --git a/drivers/s390/crypto/vfio_ap_private.h b/drivers/s390/crypto/vfio_ap_private.h
index 28e9d9989768..f82a6396acae 100644
--- a/drivers/s390/crypto/vfio_ap_private.h
+++ b/drivers/s390/crypto/vfio_ap_private.h
@@ -83,6 +83,8 @@ struct ap_matrix_mdev {
struct ap_matrix matrix;
struct notifier_block group_notifier;
struct notifier_block iommu_notifier;
+ bool kvm_busy;
+ wait_queue_head_t wait_for_kvm;
struct kvm *kvm;
struct kvm_s390_module_hook pqap_hook;
struct mdev_device *mdev;
--
2.21.3
Commit 8cdddd182bd7 ("ACPI: processor: Fix CPU0 wakeup in
acpi_idle_play_dead()") tried to fix CPU0 hotplug breakage by copying
wakeup_cpu0() + start_cpu0() logic from hlt_play_dead()//mwait_play_dead()
into acpi_idle_play_dead(). The problem is that these functions are not
exported to modules so when CONFIG_ACPI_PROCESSOR=m build fails.
The issue could've been fixed by exporting both wakeup_cpu0()/start_cpu0()
(the later from assembly) but it seems putting the whole pattern into a
new function and exporting it instead is better.
Reported-by: kernel test robot <lkp(a)intel.com>
Fixes: 8cdddd182bd7 ("CPI: processor: Fix CPU0 wakeup in acpi_idle_play_dead()")
Cc: <stable(a)vger.kernel.org> # 5.10+
Signed-off-by: Vitaly Kuznetsov <vkuznets(a)redhat.com>
---
arch/x86/include/asm/smp.h | 2 +-
arch/x86/kernel/smpboot.c | 15 ++++++++++-----
drivers/acpi/processor_idle.c | 3 +--
3 files changed, 12 insertions(+), 8 deletions(-)
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 57ef2094af93..6f79deb1f970 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -132,7 +132,7 @@ void native_play_dead(void);
void play_dead_common(void);
void wbinvd_on_cpu(int cpu);
int wbinvd_on_all_cpus(void);
-bool wakeup_cpu0(void);
+void wakeup_cpu0_if_needed(void);
void native_smp_send_reschedule(int cpu);
void native_send_call_func_ipi(const struct cpumask *mask);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index f877150a91da..9547d870ee27 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1659,7 +1659,7 @@ void play_dead_common(void)
local_irq_disable();
}
-bool wakeup_cpu0(void)
+static bool wakeup_cpu0(void)
{
if (smp_processor_id() == 0 && enable_start_cpu0)
return true;
@@ -1667,6 +1667,13 @@ bool wakeup_cpu0(void)
return false;
}
+void wakeup_cpu0_if_needed(void)
+{
+ if (wakeup_cpu0())
+ start_cpu0();
+}
+EXPORT_SYMBOL_GPL(wakeup_cpu0_if_needed);
+
/*
* We need to flush the caches before going to sleep, lest we have
* dirty data in our caches when we come back up.
@@ -1737,8 +1744,7 @@ static inline void mwait_play_dead(void)
/*
* If NMI wants to wake up CPU0, start CPU0.
*/
- if (wakeup_cpu0())
- start_cpu0();
+ wakeup_cpu0_if_needed();
}
}
@@ -1752,8 +1758,7 @@ void hlt_play_dead(void)
/*
* If NMI wants to wake up CPU0, start CPU0.
*/
- if (wakeup_cpu0())
- start_cpu0();
+ wakeup_cpu0_if_needed();
}
}
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 768a6b4d2368..de15116b754a 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -545,8 +545,7 @@ static int acpi_idle_play_dead(struct cpuidle_device *dev, int index)
#if defined(CONFIG_X86) && defined(CONFIG_HOTPLUG_CPU)
/* If NMI wants to wake up CPU0, start CPU0. */
- if (wakeup_cpu0())
- start_cpu0();
+ wakeup_cpu0_if_needed();
#endif
}
--
2.30.2