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
  ...

1 files changed, 183 insertions, 4 deletions

diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c
index aea502922646..e1f2d0eed544 100644
--- a/drivers/s390/cio/css.c
+++ b/drivers/s390/cio/css.c
@@ -20,6 +20,8 @@
 #include <linux/reboot.h>
 #include <linux/suspend.h>
 #include <linux/proc_fs.h>
+#include <linux/genalloc.h>
+#include <linux/dma-mapping.h>
 #include <asm/isc.h>
 #include <asm/crw.h>
 
@@ -165,6 +167,7 @@ static void css_subchannel_release(struct device *dev)
 
 	sch->config.intparm = 0;
 	cio_commit_config(sch);
+	kfree(sch->driver_override);
 	kfree(sch->lock);
 	kfree(sch);
 }
@@ -224,6 +227,12 @@ struct subchannel *css_alloc_subchannel(struct subchannel_id schid,
 	INIT_WORK(&sch->todo_work, css_sch_todo);
 	sch->dev.release = &css_subchannel_release;
 	device_initialize(&sch->dev);
+	/*
+	 * The physical addresses of some the dma structures that can
+	 * belong to a subchannel need to fit 31 bit width (e.g. ccw).
+	 */
+	sch->dev.coherent_dma_mask = DMA_BIT_MASK(31);
+	sch->dev.dma_mask = &sch->dev.coherent_dma_mask;
 	return sch;
 
 err:
@@ -315,9 +324,57 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
 
 static DEVICE_ATTR_RO(modalias);
 
+static ssize_t driver_override_store(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, size_t count)
+{
+	struct subchannel *sch = to_subchannel(dev);
+	char *driver_override, *old, *cp;
+
+	/* We need to keep extra room for a newline */
+	if (count >= (PAGE_SIZE - 1))
+		return -EINVAL;
+
+	driver_override = kstrndup(buf, count, GFP_KERNEL);
+	if (!driver_override)
+		return -ENOMEM;
+
+	cp = strchr(driver_override, '\n');
+	if (cp)
+		*cp = '\0';
+
+	device_lock(dev);
+	old = sch->driver_override;
+	if (strlen(driver_override)) {
+		sch->driver_override = driver_override;
+	} else {
+		kfree(driver_override);
+		sch->driver_override = NULL;
+	}
+	device_unlock(dev);
+
+	kfree(old);
+
+	return count;
+}
+
+static ssize_t driver_override_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	struct subchannel *sch = to_subchannel(dev);
+	ssize_t len;
+
+	device_lock(dev);
+	len = snprintf(buf, PAGE_SIZE, "%s\n", sch->driver_override);
+	device_unlock(dev);
+	return len;
+}
+static DEVICE_ATTR_RW(driver_override);
+
 static struct attribute *subch_attrs[] = {
 	&dev_attr_type.attr,
 	&dev_attr_modalias.attr,
+	&dev_attr_driver_override.attr,
 	NULL,
 };
 
@@ -899,6 +956,13 @@ static int __init setup_css(int nr)
 	dev_set_name(&css->device, "css%x", nr);
 	css->device.groups = cssdev_attr_groups;
 	css->device.release = channel_subsystem_release;
+	/*
+	 * We currently allocate notifier bits with this (using
+	 * css->device as the device argument with the DMA API)
+	 * and are fine with 64 bit addresses.
+	 */
+	css->device.coherent_dma_mask = DMA_BIT_MASK(64);
+	css->device.dma_mask = &css->device.coherent_dma_mask;
 
 	mutex_init(&css->mutex);
 	css->cssid = chsc_get_cssid(nr);
@@ -1018,6 +1082,111 @@ static struct notifier_block css_power_notifier = {
 	.notifier_call = css_power_event,
 };
 
+#define  CIO_DMA_GFP (GFP_KERNEL | __GFP_ZERO)
+static struct gen_pool *cio_dma_pool;
+
+/* Currently cio supports only a single css */
+struct device *cio_get_dma_css_dev(void)
+{
+	return &channel_subsystems[0]->device;
+}
+
+struct gen_pool *cio_gp_dma_create(struct device *dma_dev, int nr_pages)
+{
+	struct gen_pool *gp_dma;
+	void *cpu_addr;
+	dma_addr_t dma_addr;
+	int i;
+
+	gp_dma = gen_pool_create(3, -1);
+	if (!gp_dma)
+		return NULL;
+	for (i = 0; i < nr_pages; ++i) {
+		cpu_addr = dma_alloc_coherent(dma_dev, PAGE_SIZE, &dma_addr,
+					      CIO_DMA_GFP);
+		if (!cpu_addr)
+			return gp_dma;
+		gen_pool_add_virt(gp_dma, (unsigned long) cpu_addr,
+				  dma_addr, PAGE_SIZE, -1);
+	}
+	return gp_dma;
+}
+
+static void __gp_dma_free_dma(struct gen_pool *pool,
+			      struct gen_pool_chunk *chunk, void *data)
+{
+	size_t chunk_size = chunk->end_addr - chunk->start_addr + 1;
+
+	dma_free_coherent((struct device *) data, chunk_size,
+			 (void *) chunk->start_addr,
+			 (dma_addr_t) chunk->phys_addr);
+}
+
+void cio_gp_dma_destroy(struct gen_pool *gp_dma, struct device *dma_dev)
+{
+	if (!gp_dma)
+		return;
+	/* this is quite ugly but no better idea */
+	gen_pool_for_each_chunk(gp_dma, __gp_dma_free_dma, dma_dev);
+	gen_pool_destroy(gp_dma);
+}
+
+static int cio_dma_pool_init(void)
+{
+	/* No need to free up the resources: compiled in */
+	cio_dma_pool = cio_gp_dma_create(cio_get_dma_css_dev(), 1);
+	if (!cio_dma_pool)
+		return -ENOMEM;
+	return 0;
+}
+
+void *cio_gp_dma_zalloc(struct gen_pool *gp_dma, struct device *dma_dev,
+			size_t size)
+{
+	dma_addr_t dma_addr;
+	unsigned long addr;
+	size_t chunk_size;
+
+	if (!gp_dma)
+		return NULL;
+	addr = gen_pool_alloc(gp_dma, size);
+	while (!addr) {
+		chunk_size = round_up(size, PAGE_SIZE);
+		addr = (unsigned long) dma_alloc_coherent(dma_dev,
+					 chunk_size, &dma_addr, CIO_DMA_GFP);
+		if (!addr)
+			return NULL;
+		gen_pool_add_virt(gp_dma, addr, dma_addr, chunk_size, -1);
+		addr = gen_pool_alloc(gp_dma, size);
+	}
+	return (void *) addr;
+}
+
+void cio_gp_dma_free(struct gen_pool *gp_dma, void *cpu_addr, size_t size)
+{
+	if (!cpu_addr)
+		return;
+	memset(cpu_addr, 0, size);
+	gen_pool_free(gp_dma, (unsigned long) cpu_addr, size);
+}
+
+/*
+ * Allocate dma memory from the css global pool. Intended for memory not
+ * specific to any single device within the css. The allocated memory
+ * is not guaranteed to be 31-bit addressable.
+ *
+ * Caution: Not suitable for early stuff like console.
+ */
+void *cio_dma_zalloc(size_t size)
+{
+	return cio_gp_dma_zalloc(cio_dma_pool, cio_get_dma_css_dev(), size);
+}
+
+void cio_dma_free(void *cpu_addr, size_t size)
+{
+	cio_gp_dma_free(cio_dma_pool, cpu_addr, size);
+}
+
 /*
  * Now that the driver core is running, we can setup our channel subsystem.
  * The struct subchannel's are created during probing.
@@ -1059,16 +1228,22 @@ static int __init css_bus_init(void)
 	if (ret)
 		goto out_unregister;
 	ret = register_pm_notifier(&css_power_notifier);
-	if (ret) {
-		unregister_reboot_notifier(&css_reboot_notifier);
-		goto out_unregister;
-	}
+	if (ret)
+		goto out_unregister_rn;
+	ret = cio_dma_pool_init();
+	if (ret)
+		goto out_unregister_pmn;
+	airq_init();
 	css_init_done = 1;
 
 	/* Enable default isc for I/O subchannels. */
 	isc_register(IO_SCH_ISC);
 
 	return 0;
+out_unregister_pmn:
+	unregister_pm_notifier(&css_power_notifier);
+out_unregister_rn:
+	unregister_reboot_notifier(&css_reboot_notifier);
 out_unregister:
 	while (i-- > 0) {
 		struct channel_subsystem *css = channel_subsystems[i];
@@ -1222,6 +1397,10 @@ static int css_bus_match(struct device *dev, struct device_driver *drv)
 	struct css_driver *driver = to_cssdriver(drv);
 	struct css_device_id *id;
 
+	/* When driver_override is set, only bind to the matching driver */
+	if (sch->driver_override && strcmp(sch->driver_override, drv->name))
+		return 0;
+
 	for (id = driver->subchannel_type; id->match_flags; id++) {
 		if (sch->st == id->type)
 			return 1;