1758feddb0
- Improve stop_machine wait logic: replace cpu_relax_yield call in generic stop_machine function with a weak stop_machine_yield function. This is overridden on s390, which yields the current cpu to the neighbouring cpu after a couple of retries, instead of blindly giving up the cpu to the hipervisor. This significantly improves stop_machine performance on s390 in overcommitted scenarios. This includes common code changes which have been Acked by Peter Zijlstra and Thomas Gleixner. - Improve jump label transformation speed: transform jump labels without using stop_machine. - Refactoring of the vfio-ccw cp handling, simplifying the code and avoiding unneeded allocating/copying. - Various vfio-ccw fixes (ccw translation, state machine). - Add support for vfio-ap queue interrupt control in the guest. This includes s390 kvm changes which have been Acked by Christian Borntraeger. - Add protected virtualization support for virtio-ccw. - Enforce both CONFIG_SMP and CONFIG_HOTPLUG_CPU, which allows to remove some code which most likely isn't working at all, besides that s390 didn't even compile for !CONFIG_SMP. - Support for special flagged EP11 CPRBs for zcrypt. - Handle PCI devices with no support for new MIO instructions. - Avoid KASAN false positives in reworked stack unwinder. - Couple of fixes for the QDIO layer. - Convert s390 specific documentation to ReST format. - Let s390 crypto modules return -ENODEV instead of -EOPNOTSUPP if hardware is missing. This way our modules behave like most other modules and which is also what systemd's systemd-modules-load.service expects. - Replace defconfig with performance_defconfig, so there is one config file less to maintain. - Remove the SCLP call home device driver, which was never useful. - Cleanups all over the place. -----BEGIN PGP SIGNATURE----- iQEzBAABCAAdFiEE3QHqV+H2a8xAv27vjYWKoQLXFBgFAl0iEpcACgkQjYWKoQLX FBgtZwf8DOJ6COUG91jKP0RSDlc2YvIMBxopQ38ql1lIsTj5t6DvJ2z3X5uct1wy 6mMiF01VuyD4V4UXbTJQrihzNx7D4dUh47s2sS+diGHxJyXacVxlmjS5k+6pLIUO AyLvtCcoqDPPiThqnSTZFRm/TcfO/25fCG/IdjrFGj1MD09wHpUCh16tmRPTGFlC BWZeilDT77fVXnh7Ggn3JB0mQay5PAw2ODOxELHTUBaLmYF8RJPPVKBPmXGl9P1W 84ESm2p+iALGGWDiTOUad9eu8wyQci/V/R+hFgs0Bz/HRcjznNH5EVvfQNCD4VNF g/PET10nIQYZv2BNdi0cwRjR9jCFbw== =jp0i -----END PGP SIGNATURE----- Merge tag 's390-5.3-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux Pull s390 updates from Vasily Gorbik: - Improve stop_machine wait logic: replace cpu_relax_yield call in generic stop_machine function with a weak stop_machine_yield function. This is overridden on s390, which yields the current cpu to the neighbouring cpu after a couple of retries, instead of blindly giving up the cpu to the hipervisor. This significantly improves stop_machine performance on s390 in overcommitted scenarios. This includes common code changes which have been Acked by Peter Zijlstra and Thomas Gleixner. - Improve jump label transformation speed: transform jump labels without using stop_machine. - Refactoring of the vfio-ccw cp handling, simplifying the code and avoiding unneeded allocating/copying. - Various vfio-ccw fixes (ccw translation, state machine). - Add support for vfio-ap queue interrupt control in the guest. This includes s390 kvm changes which have been Acked by Christian Borntraeger. - Add protected virtualization support for virtio-ccw. - Enforce both CONFIG_SMP and CONFIG_HOTPLUG_CPU, which allows to remove some code which most likely isn't working at all, besides that s390 didn't even compile for !CONFIG_SMP. - Support for special flagged EP11 CPRBs for zcrypt. - Handle PCI devices with no support for new MIO instructions. - Avoid KASAN false positives in reworked stack unwinder. - Couple of fixes for the QDIO layer. - Convert s390 specific documentation to ReST format. - Let s390 crypto modules return -ENODEV instead of -EOPNOTSUPP if hardware is missing. This way our modules behave like most other modules and which is also what systemd's systemd-modules-load.service expects. - Replace defconfig with performance_defconfig, so there is one config file less to maintain. - Remove the SCLP call home device driver, which was never useful. - Cleanups all over the place. * tag 's390-5.3-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (83 commits) docs: s390: s390dbf: typos and formatting, update crash command docs: s390: unify and update s390dbf kdocs at debug.c docs: s390: restore important non-kdoc parts of s390dbf.rst vfio-ccw: Fix the conversion of Format-0 CCWs to Format-1 s390/pci: correctly handle MIO opt-out s390/pci: deal with devices that have no support for MIO instructions s390: ap: kvm: Enable PQAP/AQIC facility for the guest s390: ap: implement PAPQ AQIC interception in kernel vfio: ap: register IOMMU VFIO notifier s390: ap: kvm: add PQAP interception for AQIC s390/unwind: cleanup unused READ_ONCE_TASK_STACK s390/kasan: avoid false positives during stack unwind s390/qdio: don't touch the dsci in tiqdio_add_input_queues() s390/qdio: (re-)initialize tiqdio list entries s390/dasd: Fix a precision vs width bug in dasd_feature_list() s390/cio: introduce driver_override on the css bus vfio-ccw: make convert_ccw0_to_ccw1 static vfio-ccw: Remove copy_ccw_from_iova() vfio-ccw: Factor out the ccw0-to-ccw1 transition vfio-ccw: Copy CCW data outside length calculation ...
316 lines
7.4 KiB
C
316 lines
7.4 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* VFIO based Physical Subchannel device driver
|
|
*
|
|
* Copyright IBM Corp. 2017
|
|
* Copyright Red Hat, Inc. 2019
|
|
*
|
|
* Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
|
|
* Xiao Feng Ren <renxiaof@linux.vnet.ibm.com>
|
|
* Cornelia Huck <cohuck@redhat.com>
|
|
*/
|
|
|
|
#include <linux/module.h>
|
|
#include <linux/init.h>
|
|
#include <linux/device.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/uuid.h>
|
|
#include <linux/mdev.h>
|
|
|
|
#include <asm/isc.h>
|
|
|
|
#include "ioasm.h"
|
|
#include "css.h"
|
|
#include "vfio_ccw_private.h"
|
|
|
|
struct workqueue_struct *vfio_ccw_work_q;
|
|
static struct kmem_cache *vfio_ccw_io_region;
|
|
static struct kmem_cache *vfio_ccw_cmd_region;
|
|
|
|
/*
|
|
* Helpers
|
|
*/
|
|
int vfio_ccw_sch_quiesce(struct subchannel *sch)
|
|
{
|
|
struct vfio_ccw_private *private = dev_get_drvdata(&sch->dev);
|
|
DECLARE_COMPLETION_ONSTACK(completion);
|
|
int iretry, ret = 0;
|
|
|
|
spin_lock_irq(sch->lock);
|
|
if (!sch->schib.pmcw.ena)
|
|
goto out_unlock;
|
|
ret = cio_disable_subchannel(sch);
|
|
if (ret != -EBUSY)
|
|
goto out_unlock;
|
|
|
|
iretry = 255;
|
|
do {
|
|
|
|
ret = cio_cancel_halt_clear(sch, &iretry);
|
|
|
|
if (ret == -EIO) {
|
|
pr_err("vfio_ccw: could not quiesce subchannel 0.%x.%04x!\n",
|
|
sch->schid.ssid, sch->schid.sch_no);
|
|
break;
|
|
}
|
|
|
|
/*
|
|
* Flush all I/O and wait for
|
|
* cancel/halt/clear completion.
|
|
*/
|
|
private->completion = &completion;
|
|
spin_unlock_irq(sch->lock);
|
|
|
|
if (ret == -EBUSY)
|
|
wait_for_completion_timeout(&completion, 3*HZ);
|
|
|
|
private->completion = NULL;
|
|
flush_workqueue(vfio_ccw_work_q);
|
|
spin_lock_irq(sch->lock);
|
|
ret = cio_disable_subchannel(sch);
|
|
} while (ret == -EBUSY);
|
|
out_unlock:
|
|
private->state = VFIO_CCW_STATE_NOT_OPER;
|
|
spin_unlock_irq(sch->lock);
|
|
return ret;
|
|
}
|
|
|
|
static void vfio_ccw_sch_io_todo(struct work_struct *work)
|
|
{
|
|
struct vfio_ccw_private *private;
|
|
struct irb *irb;
|
|
bool is_final;
|
|
|
|
private = container_of(work, struct vfio_ccw_private, io_work);
|
|
irb = &private->irb;
|
|
|
|
is_final = !(scsw_actl(&irb->scsw) &
|
|
(SCSW_ACTL_DEVACT | SCSW_ACTL_SCHACT));
|
|
if (scsw_is_solicited(&irb->scsw)) {
|
|
cp_update_scsw(&private->cp, &irb->scsw);
|
|
if (is_final)
|
|
cp_free(&private->cp);
|
|
}
|
|
mutex_lock(&private->io_mutex);
|
|
memcpy(private->io_region->irb_area, irb, sizeof(*irb));
|
|
mutex_unlock(&private->io_mutex);
|
|
|
|
if (private->mdev && is_final)
|
|
private->state = VFIO_CCW_STATE_IDLE;
|
|
|
|
if (private->io_trigger)
|
|
eventfd_signal(private->io_trigger, 1);
|
|
}
|
|
|
|
/*
|
|
* Css driver callbacks
|
|
*/
|
|
static void vfio_ccw_sch_irq(struct subchannel *sch)
|
|
{
|
|
struct vfio_ccw_private *private = dev_get_drvdata(&sch->dev);
|
|
|
|
inc_irq_stat(IRQIO_CIO);
|
|
vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_INTERRUPT);
|
|
}
|
|
|
|
static int vfio_ccw_sch_probe(struct subchannel *sch)
|
|
{
|
|
struct pmcw *pmcw = &sch->schib.pmcw;
|
|
struct vfio_ccw_private *private;
|
|
int ret = -ENOMEM;
|
|
|
|
if (pmcw->qf) {
|
|
dev_warn(&sch->dev, "vfio: ccw: does not support QDIO: %s\n",
|
|
dev_name(&sch->dev));
|
|
return -ENODEV;
|
|
}
|
|
|
|
private = kzalloc(sizeof(*private), GFP_KERNEL | GFP_DMA);
|
|
if (!private)
|
|
return -ENOMEM;
|
|
|
|
private->cp.guest_cp = kcalloc(CCWCHAIN_LEN_MAX, sizeof(struct ccw1),
|
|
GFP_KERNEL);
|
|
if (!private->cp.guest_cp)
|
|
goto out_free;
|
|
|
|
private->io_region = kmem_cache_zalloc(vfio_ccw_io_region,
|
|
GFP_KERNEL | GFP_DMA);
|
|
if (!private->io_region)
|
|
goto out_free;
|
|
|
|
private->cmd_region = kmem_cache_zalloc(vfio_ccw_cmd_region,
|
|
GFP_KERNEL | GFP_DMA);
|
|
if (!private->cmd_region)
|
|
goto out_free;
|
|
|
|
private->sch = sch;
|
|
dev_set_drvdata(&sch->dev, private);
|
|
mutex_init(&private->io_mutex);
|
|
|
|
spin_lock_irq(sch->lock);
|
|
private->state = VFIO_CCW_STATE_NOT_OPER;
|
|
sch->isc = VFIO_CCW_ISC;
|
|
ret = cio_enable_subchannel(sch, (u32)(unsigned long)sch);
|
|
spin_unlock_irq(sch->lock);
|
|
if (ret)
|
|
goto out_free;
|
|
|
|
INIT_WORK(&private->io_work, vfio_ccw_sch_io_todo);
|
|
atomic_set(&private->avail, 1);
|
|
private->state = VFIO_CCW_STATE_STANDBY;
|
|
|
|
ret = vfio_ccw_mdev_reg(sch);
|
|
if (ret)
|
|
goto out_disable;
|
|
|
|
return 0;
|
|
|
|
out_disable:
|
|
cio_disable_subchannel(sch);
|
|
out_free:
|
|
dev_set_drvdata(&sch->dev, NULL);
|
|
if (private->cmd_region)
|
|
kmem_cache_free(vfio_ccw_cmd_region, private->cmd_region);
|
|
if (private->io_region)
|
|
kmem_cache_free(vfio_ccw_io_region, private->io_region);
|
|
kfree(private->cp.guest_cp);
|
|
kfree(private);
|
|
return ret;
|
|
}
|
|
|
|
static int vfio_ccw_sch_remove(struct subchannel *sch)
|
|
{
|
|
struct vfio_ccw_private *private = dev_get_drvdata(&sch->dev);
|
|
|
|
vfio_ccw_sch_quiesce(sch);
|
|
|
|
vfio_ccw_mdev_unreg(sch);
|
|
|
|
dev_set_drvdata(&sch->dev, NULL);
|
|
|
|
kmem_cache_free(vfio_ccw_cmd_region, private->cmd_region);
|
|
kmem_cache_free(vfio_ccw_io_region, private->io_region);
|
|
kfree(private->cp.guest_cp);
|
|
kfree(private);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void vfio_ccw_sch_shutdown(struct subchannel *sch)
|
|
{
|
|
vfio_ccw_sch_quiesce(sch);
|
|
}
|
|
|
|
/**
|
|
* vfio_ccw_sch_event - process subchannel event
|
|
* @sch: subchannel
|
|
* @process: non-zero if function is called in process context
|
|
*
|
|
* An unspecified event occurred for this subchannel. Adjust data according
|
|
* to the current operational state of the subchannel. Return zero when the
|
|
* event has been handled sufficiently or -EAGAIN when this function should
|
|
* be called again in process context.
|
|
*/
|
|
static int vfio_ccw_sch_event(struct subchannel *sch, int process)
|
|
{
|
|
struct vfio_ccw_private *private = dev_get_drvdata(&sch->dev);
|
|
unsigned long flags;
|
|
int rc = -EAGAIN;
|
|
|
|
spin_lock_irqsave(sch->lock, flags);
|
|
if (!device_is_registered(&sch->dev))
|
|
goto out_unlock;
|
|
|
|
if (work_pending(&sch->todo_work))
|
|
goto out_unlock;
|
|
|
|
if (cio_update_schib(sch)) {
|
|
vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_NOT_OPER);
|
|
rc = 0;
|
|
goto out_unlock;
|
|
}
|
|
|
|
private = dev_get_drvdata(&sch->dev);
|
|
if (private->state == VFIO_CCW_STATE_NOT_OPER) {
|
|
private->state = private->mdev ? VFIO_CCW_STATE_IDLE :
|
|
VFIO_CCW_STATE_STANDBY;
|
|
}
|
|
rc = 0;
|
|
|
|
out_unlock:
|
|
spin_unlock_irqrestore(sch->lock, flags);
|
|
|
|
return rc;
|
|
}
|
|
|
|
static struct css_device_id vfio_ccw_sch_ids[] = {
|
|
{ .match_flags = 0x1, .type = SUBCHANNEL_TYPE_IO, },
|
|
{ /* end of list */ },
|
|
};
|
|
MODULE_DEVICE_TABLE(css, vfio_ccw_sch_ids);
|
|
|
|
static struct css_driver vfio_ccw_sch_driver = {
|
|
.drv = {
|
|
.name = "vfio_ccw",
|
|
.owner = THIS_MODULE,
|
|
},
|
|
.subchannel_type = vfio_ccw_sch_ids,
|
|
.irq = vfio_ccw_sch_irq,
|
|
.probe = vfio_ccw_sch_probe,
|
|
.remove = vfio_ccw_sch_remove,
|
|
.shutdown = vfio_ccw_sch_shutdown,
|
|
.sch_event = vfio_ccw_sch_event,
|
|
};
|
|
|
|
static int __init vfio_ccw_sch_init(void)
|
|
{
|
|
int ret = -ENOMEM;
|
|
|
|
vfio_ccw_work_q = create_singlethread_workqueue("vfio-ccw");
|
|
if (!vfio_ccw_work_q)
|
|
return -ENOMEM;
|
|
|
|
vfio_ccw_io_region = kmem_cache_create_usercopy("vfio_ccw_io_region",
|
|
sizeof(struct ccw_io_region), 0,
|
|
SLAB_ACCOUNT, 0,
|
|
sizeof(struct ccw_io_region), NULL);
|
|
if (!vfio_ccw_io_region)
|
|
goto out_err;
|
|
|
|
vfio_ccw_cmd_region = kmem_cache_create_usercopy("vfio_ccw_cmd_region",
|
|
sizeof(struct ccw_cmd_region), 0,
|
|
SLAB_ACCOUNT, 0,
|
|
sizeof(struct ccw_cmd_region), NULL);
|
|
if (!vfio_ccw_cmd_region)
|
|
goto out_err;
|
|
|
|
isc_register(VFIO_CCW_ISC);
|
|
ret = css_driver_register(&vfio_ccw_sch_driver);
|
|
if (ret) {
|
|
isc_unregister(VFIO_CCW_ISC);
|
|
goto out_err;
|
|
}
|
|
|
|
return ret;
|
|
|
|
out_err:
|
|
kmem_cache_destroy(vfio_ccw_cmd_region);
|
|
kmem_cache_destroy(vfio_ccw_io_region);
|
|
destroy_workqueue(vfio_ccw_work_q);
|
|
return ret;
|
|
}
|
|
|
|
static void __exit vfio_ccw_sch_exit(void)
|
|
{
|
|
css_driver_unregister(&vfio_ccw_sch_driver);
|
|
isc_unregister(VFIO_CCW_ISC);
|
|
kmem_cache_destroy(vfio_ccw_io_region);
|
|
kmem_cache_destroy(vfio_ccw_cmd_region);
|
|
destroy_workqueue(vfio_ccw_work_q);
|
|
}
|
|
module_init(vfio_ccw_sch_init);
|
|
module_exit(vfio_ccw_sch_exit);
|
|
|
|
MODULE_LICENSE("GPL v2");
|