s390/cio: introduce DMA pools to cio

To support protected virtualization cio will need to make sure the
memory used for communication with the hypervisor is DMA memory.

Let us introduce one global pool for cio.

Our DMA pools are implemented as a gen_pool backed with DMA pages. The
idea is to avoid each allocation effectively wasting a page, as we
typically allocate much less than PAGE_SIZE.

Signed-off-by: Halil Pasic <[e-mail]>
Reviewed-by: Sebastian Ott <[e-mail]>
Reviewed-by: Cornelia Huck <[e-mail]>
Reviewed-by: Michael Mueller <[e-mail]>
Tested-by: Michael Mueller <[e-mail]>
Signed-off-by: Heiko Carstens <[e-mail]>

arch/s390/Kconfig

···
 	select ARCH_HAS_SCALED_CPUTIME
 	select HAVE_NMI
 	select SWIOTLB
+	select GENERIC_ALLOCATOR
 
 
 config SCHED_OMIT_FRAME_POINTER

arch/s390/include/asm/cio.h

···
 
 #include <linux/spinlock.h>
 #include <linux/bitops.h>
+#include <linux/genalloc.h>
 #include <asm/types.h>
 
 #define LPM_ANYPATH 0xff
···
 
 void channel_subsystem_reinit(void);
 extern void css_schedule_reprobe(void);
+
+extern void *cio_dma_zalloc(size_t size);
+extern void cio_dma_free(void *cpu_addr, size_t size);
+extern struct device *cio_get_dma_css_dev(void);
+
+void *cio_gp_dma_zalloc(struct gen_pool *gp_dma, struct device *dma_dev,
+			size_t size);
+void cio_gp_dma_free(struct gen_pool *gp_dma, void *cpu_addr, size_t size);
+void cio_gp_dma_destroy(struct gen_pool *gp_dma, struct device *dma_dev);
+struct gen_pool *cio_gp_dma_create(struct device *dma_dev, int nr_pages);
 
 /* Function from drivers/s390/cio/chsc.c */
 int chsc_sstpc(void *page, unsigned int op, u16 ctrl, u64 *clock_delta);

drivers/s390/cio/css.c

···
 #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>
 
···
 	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:
···
 	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);
···
 	.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.
···
 	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;
 	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];