use exact allocation for dma coherent memory

@@ -39,11 +39,11 @@ struct videobuf_dma_contig_memory {
 
 static int __videobuf_dc_alloc(struct device *dev,
 			       struct videobuf_dma_contig_memory *mem,
-			       unsigned long size, gfp_t flags)
+			       unsigned long size)
 {
 	mem->size = size;
-	mem->vaddr = dma_alloc_coherent(dev, mem->size,
-					&mem->dma_handle, flags);
+	mem->vaddr = dma_alloc_coherent(dev, mem->size, &mem->dma_handle,
+			GFP_KERNEL);
 
 	if (!mem->vaddr) {
 		dev_err(dev, "memory alloc size %ld failed\n", mem->size);

@@ -260,8 +260,7 @@ static int __videobuf_iolock(struct videobuf_queue *q,
 			return videobuf_dma_contig_user_get(mem, vb);
 
 		/* allocate memory for the read() method */
-		if (__videobuf_dc_alloc(q->dev, mem, PAGE_ALIGN(vb->size),
-					GFP_KERNEL))
+		if (__videobuf_dc_alloc(q->dev, mem, PAGE_ALIGN(vb->size)))
 			return -ENOMEM;
 		break;
 	case V4L2_MEMORY_OVERLAY:

@@ -280,7 +279,6 @@ static int __videobuf_mmap_mapper(struct videobuf_queue *q,
 	struct videobuf_dma_contig_memory *mem;
 	struct videobuf_mapping *map;
 	int retval;
-	unsigned long size;
 
 	dev_dbg(q->dev, "%s\n", __func__);
 

@@ -298,23 +296,18 @@ static int __videobuf_mmap_mapper(struct videobuf_queue *q,
 	BUG_ON(!mem);
 	MAGIC_CHECK(mem->magic, MAGIC_DC_MEM);
 
-	if (__videobuf_dc_alloc(q->dev, mem, PAGE_ALIGN(buf->bsize),
-				GFP_KERNEL | __GFP_COMP))
+	if (__videobuf_dc_alloc(q->dev, mem, PAGE_ALIGN(buf->bsize)))
 		goto error;
 
-	/* Try to remap memory */
-	size = vma->vm_end - vma->vm_start;
-	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
-
 	/* the "vm_pgoff" is just used in v4l2 to find the
 	 * corresponding buffer data structure which is allocated
 	 * earlier and it does not mean the offset from the physical
 	 * buffer start address as usual. So set it to 0 to pass
-	 * the sanity check in vm_iomap_memory().
+	 * the sanity check in dma_mmap_coherent().
 	 */
 	vma->vm_pgoff = 0;
-
-	retval = vm_iomap_memory(vma, mem->dma_handle, size);
+	retval = dma_mmap_coherent(q->dev, vma, mem->vaddr, mem->dma_handle,
+			vma->vm_end - vma->vm_start);
 	if (retval) {
 		dev_err(q->dev, "mmap: remap failed with error %d. ",
 			retval);

@@ -41,21 +41,14 @@
 static int drm_ati_alloc_pcigart_table(struct drm_device *dev,
 				       struct drm_ati_pcigart_info *gart_info)
 {
-	gart_info->table_handle = drm_pci_alloc(dev, gart_info->table_size,
-						PAGE_SIZE);
-	if (gart_info->table_handle == NULL)
+	gart_info->table_vaddr = dma_alloc_coherent(&dev->pdev->dev,
+			gart_info->table_size, &gart_info->table_handle,
+			GFP_KERNEL);
+	if (!gart_info->table_vaddr)
 		return -ENOMEM;
-
 	return 0;
 }
 
-static void drm_ati_free_pcigart_table(struct drm_device *dev,
-				       struct drm_ati_pcigart_info *gart_info)
-{
-	drm_pci_free(dev, gart_info->table_handle);
-	gart_info->table_handle = NULL;
-}
-
 int drm_ati_pcigart_cleanup(struct drm_device *dev, struct drm_ati_pcigart_info *gart_info)
 {
 	struct drm_sg_mem *entry = dev->sg;

@@ -87,8 +80,10 @@ int drm_ati_pcigart_cleanup(struct drm_device *dev, struct drm_ati_pcigart_info
 	}
 
 	if (gart_info->gart_table_location == DRM_ATI_GART_MAIN &&
-	    gart_info->table_handle) {
-		drm_ati_free_pcigart_table(dev, gart_info);
+	    gart_info->table_vaddr) {
+		dma_free_coherent(&dev->pdev->dev, gart_info->table_size,
+				gart_info->table_vaddr, gart_info->table_handle);
+		gart_info->table_vaddr = NULL;
 	}
 
 	return 1;

@@ -127,9 +122,9 @@ int drm_ati_pcigart_init(struct drm_device *dev, struct drm_ati_pcigart_info *ga
 			goto done;
 		}
 
-		pci_gart = gart_info->table_handle->vaddr;
-		address = gart_info->table_handle->vaddr;
-		bus_address = gart_info->table_handle->busaddr;
+		pci_gart = gart_info->table_vaddr;
+		address = gart_info->table_vaddr;
+		bus_address = gart_info->table_handle;
 	} else {
 		address = gart_info->addr;
 		bus_address = gart_info->bus_addr;

@@ -18,7 +18,10 @@ struct drm_ati_pcigart_info {
 	void *addr;
 	dma_addr_t bus_addr;
 	dma_addr_t table_mask;
-	struct drm_dma_handle *table_handle;
+
+	dma_addr_t table_handle;
+	void *table_vaddr;
+
 	struct drm_local_map mapping;
 	int table_size;
 };

@@ -38,6 +38,91 @@
 
 #include <linux/nospec.h>
 
+/**
+ * drm_pci_alloc - Allocate a PCI consistent memory block, for DMA.
+ * @dev: DRM device
+ * @size: size of block to allocate
+ * @align: alignment of block
+ *
+ * FIXME: This is a needless abstraction of the Linux dma-api and should be
+ * removed.
+ *
+ * Return: A handle to the allocated memory block on success or NULL on
+ * failure.
+ */
+drm_dma_handle_t *drm_pci_alloc(struct drm_device * dev, size_t size, size_t align)
+{
+	drm_dma_handle_t *dmah;
+	unsigned long addr;
+	size_t sz;
+
+	/* pci_alloc_consistent only guarantees alignment to the smallest
+	 * PAGE_SIZE order which is greater than or equal to the requested size.
+	 * Return NULL here for now to make sure nobody tries for larger alignment
+	 */
+	if (align > size)
+		return NULL;
+
+	dmah = kmalloc(sizeof(drm_dma_handle_t), GFP_KERNEL);
+	if (!dmah)
+		return NULL;
+
+	dmah->size = size;
+	dmah->vaddr = dma_alloc_coherent(&dev->pdev->dev, size,
+					 &dmah->busaddr,
+					 GFP_KERNEL | __GFP_COMP);
+
+	if (dmah->vaddr == NULL) {
+		kfree(dmah);
+		return NULL;
+	}
+
+	/* XXX - Is virt_to_page() legal for consistent mem? */
+	/* Reserve */
+	for (addr = (unsigned long)dmah->vaddr, sz = size;
+	     sz > 0; addr += PAGE_SIZE, sz -= PAGE_SIZE) {
+		SetPageReserved(virt_to_page((void *)addr));
+	}
+
+	return dmah;
+}
+
+/*
+ * Free a PCI consistent memory block without freeing its descriptor.
+ *
+ * This function is for internal use in the Linux-specific DRM core code.
+ */
+void __drm_legacy_pci_free(struct drm_device * dev, drm_dma_handle_t * dmah)
+{
+	unsigned long addr;
+	size_t sz;
+
+	if (dmah->vaddr) {
+		/* XXX - Is virt_to_page() legal for consistent mem? */
+		/* Unreserve */
+		for (addr = (unsigned long)dmah->vaddr, sz = dmah->size;
+		     sz > 0; addr += PAGE_SIZE, sz -= PAGE_SIZE) {
+			ClearPageReserved(virt_to_page((void *)addr));
+		}
+		dma_free_coherent(&dev->pdev->dev, dmah->size, dmah->vaddr,
+				  dmah->busaddr);
+	}
+}
+
+/**
+ * drm_pci_free - Free a PCI consistent memory block
+ * @dev: DRM device
+ * @dmah: handle to memory block
+ *
+ * FIXME: This is a needless abstraction of the Linux dma-api and should be
+ * removed.
+ */
+void drm_pci_free(struct drm_device * dev, drm_dma_handle_t * dmah)
+{
+	__drm_legacy_pci_free(dev, dmah);
+	kfree(dmah);
+}
+
 static struct drm_map_list *drm_find_matching_map(struct drm_device *dev,
 						  struct drm_local_map *map)
 {

@@ -31,95 +31,6 @@
 #include "drm_internal.h"
 #include "drm_legacy.h"
 
-/**
- * drm_pci_alloc - Allocate a PCI consistent memory block, for DMA.
- * @dev: DRM device
- * @size: size of block to allocate
- * @align: alignment of block
- *
- * FIXME: This is a needless abstraction of the Linux dma-api and should be
- * removed.
- *
- * Return: A handle to the allocated memory block on success or NULL on
- * failure.
- */
-drm_dma_handle_t *drm_pci_alloc(struct drm_device * dev, size_t size, size_t align)
-{
-	drm_dma_handle_t *dmah;
-	unsigned long addr;
-	size_t sz;
-
-	/* pci_alloc_consistent only guarantees alignment to the smallest
-	 * PAGE_SIZE order which is greater than or equal to the requested size.
-	 * Return NULL here for now to make sure nobody tries for larger alignment
-	 */
-	if (align > size)
-		return NULL;
-
-	dmah = kmalloc(sizeof(drm_dma_handle_t), GFP_KERNEL);
-	if (!dmah)
-		return NULL;
-
-	dmah->size = size;
-	dmah->vaddr = dma_alloc_coherent(&dev->pdev->dev, size,
-					 &dmah->busaddr,
-					 GFP_KERNEL | __GFP_COMP);
-
-	if (dmah->vaddr == NULL) {
-		kfree(dmah);
-		return NULL;
-	}
-
-	/* XXX - Is virt_to_page() legal for consistent mem? */
-	/* Reserve */
-	for (addr = (unsigned long)dmah->vaddr, sz = size;
-	     sz > 0; addr += PAGE_SIZE, sz -= PAGE_SIZE) {
-		SetPageReserved(virt_to_page((void *)addr));
-	}
-
-	return dmah;
-}
-
-EXPORT_SYMBOL(drm_pci_alloc);
-
-/*
- * Free a PCI consistent memory block without freeing its descriptor.
- *
- * This function is for internal use in the Linux-specific DRM core code.
- */
-void __drm_legacy_pci_free(struct drm_device * dev, drm_dma_handle_t * dmah)
-{
-	unsigned long addr;
-	size_t sz;
-
-	if (dmah->vaddr) {
-		/* XXX - Is virt_to_page() legal for consistent mem? */
-		/* Unreserve */
-		for (addr = (unsigned long)dmah->vaddr, sz = dmah->size;
-		     sz > 0; addr += PAGE_SIZE, sz -= PAGE_SIZE) {
-			ClearPageReserved(virt_to_page((void *)addr));
-		}
-		dma_free_coherent(&dev->pdev->dev, dmah->size, dmah->vaddr,
-				  dmah->busaddr);
-	}
-}
-
-/**
- * drm_pci_free - Free a PCI consistent memory block
- * @dev: DRM device
- * @dmah: handle to memory block
- *
- * FIXME: This is a needless abstraction of the Linux dma-api and should be
- * removed.
- */
-void drm_pci_free(struct drm_device * dev, drm_dma_handle_t * dmah)
-{
-	__drm_legacy_pci_free(dev, dmah);
-	kfree(dmah);
-}
-
-EXPORT_SYMBOL(drm_pci_free);
-
 #ifdef CONFIG_PCI
 
 static int drm_get_pci_domain(struct drm_device *dev)

@@ -70,7 +70,7 @@ drm_dma_handle_t *drm_pci_alloc(struct drm_device * dev, size_t size, size_t ali
 	dmah->size = size;
 	dmah->vaddr = dma_alloc_coherent(&dev->pdev->dev, size,
 					 &dmah->busaddr,
-					 GFP_KERNEL | __GFP_COMP);
+					 GFP_KERNEL);
 
 	if (dmah->vaddr == NULL) {
 		kfree(dmah);

@@ -2076,7 +2076,7 @@ static void alloc_dummy_hdrq(struct qib_devdata *dd)
 	dd->cspec->dummy_hdrq = dma_alloc_coherent(&dd->pcidev->dev,
 					dd->rcd[0]->rcvhdrq_size,
 					&dd->cspec->dummy_hdrq_phys,
-					GFP_ATOMIC | __GFP_COMP);
+					GFP_ATOMIC);
 	if (!dd->cspec->dummy_hdrq) {
 		qib_devinfo(dd->pcidev, "Couldn't allocate dummy hdrq\n");
 		/* fallback to just 0'ing */

@@ -1547,18 +1547,13 @@ int qib_create_rcvhdrq(struct qib_devdata *dd, struct qib_ctxtdata *rcd)
 
 	if (!rcd->rcvhdrq) {
 		dma_addr_t phys_hdrqtail;
-		gfp_t gfp_flags;
-
 		amt = ALIGN(dd->rcvhdrcnt * dd->rcvhdrentsize *
 			    sizeof(u32), PAGE_SIZE);
-		gfp_flags = (rcd->ctxt >= dd->first_user_ctxt) ?
-			GFP_USER : GFP_KERNEL;
 
 		old_node_id = dev_to_node(&dd->pcidev->dev);
 		set_dev_node(&dd->pcidev->dev, rcd->node_id);
 		rcd->rcvhdrq = dma_alloc_coherent(
-			&dd->pcidev->dev, amt, &rcd->rcvhdrq_phys,
-			gfp_flags | __GFP_COMP);
+			&dd->pcidev->dev, amt, &rcd->rcvhdrq_phys, GFP_KERNEL);
 		set_dev_node(&dd->pcidev->dev, old_node_id);
 
 		if (!rcd->rcvhdrq) {

@@ -1578,7 +1573,7 @@ int qib_create_rcvhdrq(struct qib_devdata *dd, struct qib_ctxtdata *rcd)
 			set_dev_node(&dd->pcidev->dev, rcd->node_id);
 			rcd->rcvhdrtail_kvaddr = dma_alloc_coherent(
 				&dd->pcidev->dev, PAGE_SIZE, &phys_hdrqtail,
-				gfp_flags);
+				GFP_KERNEL);
 			set_dev_node(&dd->pcidev->dev, old_node_id);
 			if (!rcd->rcvhdrtail_kvaddr)
 				goto bail_free;

@@ -1622,17 +1617,8 @@ int qib_setup_eagerbufs(struct qib_ctxtdata *rcd)
 	struct qib_devdata *dd = rcd->dd;
 	unsigned e, egrcnt, egrperchunk, chunk, egrsize, egroff;
 	size_t size;
-	gfp_t gfp_flags;
 	int old_node_id;
 
-	/*
-	 * GFP_USER, but without GFP_FS, so buffer cache can be
-	 * coalesced (we hope); otherwise, even at order 4,
-	 * heavy filesystem activity makes these fail, and we can
-	 * use compound pages.
-	 */
-	gfp_flags = __GFP_RECLAIM | __GFP_IO | __GFP_COMP;
-
 	egrcnt = rcd->rcvegrcnt;
 	egroff = rcd->rcvegr_tid_base;
 	egrsize = dd->rcvegrbufsize;

@@ -1664,7 +1650,7 @@ int qib_setup_eagerbufs(struct qib_ctxtdata *rcd)
 		rcd->rcvegrbuf[e] =
 			dma_alloc_coherent(&dd->pcidev->dev, size,
 					   &rcd->rcvegrbuf_phys[e],
-					   gfp_flags);
+					   GFP_KERNEL);
 		set_dev_node(&dd->pcidev->dev, old_node_id);
 		if (!rcd->rcvegrbuf[e])
 			goto bail_rcvegrbuf_phys;

@@ -1846,17 +1846,10 @@ int hfi1_create_rcvhdrq(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd)
 	u64 reg;
 
 	if (!rcd->rcvhdrq) {
-		gfp_t gfp_flags;
-
 		amt = rcvhdrq_size(rcd);
 
-		if (rcd->ctxt < dd->first_dyn_alloc_ctxt || rcd->is_vnic)
-			gfp_flags = GFP_KERNEL;
-		else
-			gfp_flags = GFP_USER;
 		rcd->rcvhdrq = dma_alloc_coherent(&dd->pcidev->dev, amt,
-						  &rcd->rcvhdrq_dma,
-						  gfp_flags | __GFP_COMP);
+						  &rcd->rcvhdrq_dma, GFP_KERNEL);
 
 		if (!rcd->rcvhdrq) {
 			dd_dev_err(dd,

@@ -1870,7 +1863,7 @@ int hfi1_create_rcvhdrq(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd)
 			rcd->rcvhdrtail_kvaddr = dma_alloc_coherent(&dd->pcidev->dev,
 								    PAGE_SIZE,
 								    &rcd->rcvhdrqtailaddr_dma,
-								    gfp_flags);
+								    GFP_KERNEL);
 			if (!rcd->rcvhdrtail_kvaddr)
 				goto bail_free;
 		}

@@ -1926,19 +1919,10 @@ int hfi1_setup_eagerbufs(struct hfi1_ctxtdata *rcd)
 {
 	struct hfi1_devdata *dd = rcd->dd;
 	u32 max_entries, egrtop, alloced_bytes = 0;
-	gfp_t gfp_flags;
 	u16 order, idx = 0;
 	int ret = 0;
 	u16 round_mtu = roundup_pow_of_two(hfi1_max_mtu);
 
-	/*
-	 * GFP_USER, but without GFP_FS, so buffer cache can be
-	 * coalesced (we hope); otherwise, even at order 4,
-	 * heavy filesystem activity makes these fail, and we can
-	 * use compound pages.
-	 */
-	gfp_flags = __GFP_RECLAIM | __GFP_IO | __GFP_COMP;
-
 	/*
 	 * The minimum size of the eager buffers is a groups of MTU-sized
 	 * buffers.

@@ -1969,7 +1953,7 @@ int hfi1_setup_eagerbufs(struct hfi1_ctxtdata *rcd)
 			dma_alloc_coherent(&dd->pcidev->dev,
 					   rcd->egrbufs.rcvtid_size,
 					   &rcd->egrbufs.buffers[idx].dma,
-					   gfp_flags);
+					   GFP_KERNEL);
 		if (rcd->egrbufs.buffers[idx].addr) {
 			rcd->egrbufs.buffers[idx].len =
 				rcd->egrbufs.rcvtid_size;

@@ -2361,8 +2361,7 @@ iwl_fw_dbg_buffer_allocation(struct iwl_fw_runtime *fwrt, u32 size)
 
 	virtual_addr =
 		dma_alloc_coherent(fwrt->trans->dev, size, &phys_addr,
-				   GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO |
-				   __GFP_COMP);
+				   GFP_KERNEL | __GFP_NOWARN);
 
 	/* TODO: alloc fragments if needed */
 	if (!virtual_addr)

@@ -210,8 +210,7 @@ static void iwl_pcie_alloc_fw_monitor_block(struct iwl_trans *trans,
 	for (power = max_power; power >= min_power; power--) {
 		size = BIT(power);
 		cpu_addr = dma_alloc_coherent(trans->dev, size, &phys,
-					      GFP_KERNEL | __GFP_NOWARN |
-					      __GFP_ZERO | __GFP_COMP);
+					      GFP_KERNEL | __GFP_NOWARN);
 		if (!cpu_addr)
 			continue;
 

@@ -161,15 +161,17 @@ static inline struct page *dma_alloc_contiguous(struct device *dev, size_t size,
 		gfp_t gfp)
 {
 	int node = dev ? dev_to_node(dev) : NUMA_NO_NODE;
-	size_t align = get_order(PAGE_ALIGN(size));
+	void *cpu_addr = alloc_pages_exact_node(node, size, gfp);
 
-	return alloc_pages_node(node, gfp, align);
+	if (!cpu_addr)
+		return NULL;
+	return virt_to_page(p);
 }
 
 static inline void dma_free_contiguous(struct device *dev, struct page *page,
 		size_t size)
 {
-	__free_pages(page, get_order(size));
+	free_pages_exact(page_address(page), get_order(size));
 }
 
 #endif

@@ -232,9 +232,8 @@ struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp)
 {
 	int node = dev ? dev_to_node(dev) : NUMA_NO_NODE;
 	size_t count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	size_t align = get_order(PAGE_ALIGN(size));
-	struct page *page = NULL;
 	struct cma *cma = NULL;
+	void *cpu_addr;
 
 	if (dev && dev->cma_area)
 		cma = dev->cma_area;

@@ -243,14 +242,20 @@ struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp)
 
 	/* CMA can be used only in the context which permits sleeping */
 	if (cma && gfpflags_allow_blocking(gfp)) {
+		size_t align = get_order(PAGE_ALIGN(size));
+		struct page *page;
+
 		align = min_t(size_t, align, CONFIG_CMA_ALIGNMENT);
 		page = cma_alloc(cma, count, align, gfp & __GFP_NOWARN);
+		if (page)
+			return page;
 	}
 
 	/* Fallback allocation of normal pages */
-	if (!page)
-		page = alloc_pages_node(node, gfp, align);
-	return page;
+	cpu_addr = alloc_pages_exact_node(node, size, gfp);
+	if (!cpu_addr)
+		return NULL;
+	return virt_to_page(cpu_addr);
 }
 
 /**

@@ -267,7 +272,7 @@ struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp)
 void dma_free_contiguous(struct device *dev, struct page *page, size_t size)
 {
 	if (!cma_release(dev_get_cma_area(dev), page, size >> PAGE_SHIFT))
-		__free_pages(page, get_order(size));
+		free_pages_exact(page_address(page), get_order(size));
 }
 
 /*

@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 config COMEDI
 	tristate "Data acquisition support (comedi)"
+	depends on BROKEN
 	help
 	  Enable support for a wide range of data acquisition devices
 	  for Linux.

@@ -530,9 +530,10 @@ extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order,
 extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order);
 extern unsigned long get_zeroed_page(gfp_t gfp_mask);
 
-void *alloc_pages_exact(size_t size, gfp_t gfp_mask);
 void free_pages_exact(void *virt, size_t size);
-void * __meminit alloc_pages_exact_node(int nid, size_t size, gfp_t gfp_mask);
+void *alloc_pages_exact_node(int nid, size_t size, gfp_t gfp_mask);
+#define alloc_pages_exact(size, gfp_mask) \
+	alloc_pages_exact_node(NUMA_NO_NODE, size, gfp_mask)
 
 #define __get_free_page(gfp_mask) \
 		__get_free_pages((gfp_mask), 0)

@@ -4859,34 +4859,6 @@ static void *make_alloc_exact(unsigned long addr, unsigned int order,
 	return (void *)addr;
 }
 
-/**
- * alloc_pages_exact - allocate an exact number physically-contiguous pages.
- * @size: the number of bytes to allocate
- * @gfp_mask: GFP flags for the allocation, must not contain __GFP_COMP
- *
- * This function is similar to alloc_pages(), except that it allocates the
- * minimum number of pages to satisfy the request.  alloc_pages() can only
- * allocate memory in power-of-two pages.
- *
- * This function is also limited by MAX_ORDER.
- *
- * Memory allocated by this function must be released by free_pages_exact().
- *
- * Return: pointer to the allocated area or %NULL in case of error.
- */
-void *alloc_pages_exact(size_t size, gfp_t gfp_mask)
-{
-	unsigned int order = get_order(size);
-	unsigned long addr;
-
-	if (WARN_ON_ONCE(gfp_mask & __GFP_COMP))
-		gfp_mask &= ~__GFP_COMP;
-
-	addr = __get_free_pages(gfp_mask, order);
-	return make_alloc_exact(addr, order, size);
-}
-EXPORT_SYMBOL(alloc_pages_exact);
-
 /**
  * alloc_pages_exact_node - allocate an exact number of physically-contiguous
  *			   pages on a node.

@@ -4894,12 +4866,15 @@ EXPORT_SYMBOL(alloc_pages_exact);
  * @size: the number of bytes to allocate
  * @gfp_mask: GFP flags for the allocation, must not contain __GFP_COMP
  *
- * Like alloc_pages_exact(), but try to allocate on node nid first before falling
- * back.
+ * This function is similar to alloc_pages_node(), except that it allocates the
+ * minimum number of pages to satisfy the request while alloc_pages() can only
+ * allocate memory in power-of-two pages.  This function is also limited by
+ * MAX_ORDER.
  *
- * Return: pointer to the allocated area or %NULL in case of error.
+ * Returns a pointer to the allocated area or %NULL in case of error, memory
+ * allocated by this function must be released by free_pages_exact().
  */
-void * __meminit alloc_pages_exact_node(int nid, size_t size, gfp_t gfp_mask)
+void *alloc_pages_exact_node(int nid, size_t size, gfp_t gfp_mask)
 {
 	unsigned int order = get_order(size);
 	struct page *p;

@@ -759,14 +759,6 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 	if (mask < 0xffffffffULL)
 		gfp |= GFP_DMA;
 
-	/*
-	 * Following is a work-around (a.k.a. hack) to prevent pages
-	 * with __GFP_COMP being passed to split_page() which cannot
-	 * handle them.  The real problem is that this flag probably
-	 * should be 0 on ARM as it is not supported on this
-	 * platform; see CONFIG_HUGETLBFS.
-	 */
-	gfp &= ~(__GFP_COMP);
 	args.gfp = gfp;
 
 	*handle = DMA_MAPPING_ERROR;

@@ -1527,15 +1519,6 @@ static void *__arm_iommu_alloc_attrs(struct device *dev, size_t size,
 		return __iommu_alloc_simple(dev, size, gfp, handle,
 					    coherent_flag, attrs);
 
-	/*
-	 * Following is a work-around (a.k.a. hack) to prevent pages
-	 * with __GFP_COMP being passed to split_page() which cannot
-	 * handle them.  The real problem is that this flag probably
-	 * should be 0 on ARM as it is not supported on this
-	 * platform; see CONFIG_HUGETLBFS.
-	 */
-	gfp &= ~(__GFP_COMP);
-
 	pages = __iommu_alloc_buffer(dev, size, gfp, attrs, coherent_flag);
 	if (!pages)
 		return NULL;

@@ -252,6 +252,15 @@ void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	/* let the implementation decide on the zone to allocate from: */
 	flag &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM);
 
+	/*
+	 * __GFP_COMP interacts badly with splitting up a larger order
+	 * allocation.  But as our allocations might not even come from the
+	 * page allocator, the callers can't rely on the fact that they
+	 * even get pages, never mind which kind.
+	 */
+	if (WARN_ON_ONCE(flag & __GFP_COMP))
+		flag &= ~__GFP_COMP;
+
 	if (dma_is_direct(ops))
 		cpu_addr = dma_direct_alloc(dev, size, dma_handle, flag, attrs);
 	else if (ops->alloc)

@@ -532,7 +532,7 @@ extern unsigned long get_zeroed_page(gfp_t gfp_mask);
 
 void *alloc_pages_exact(size_t size, gfp_t gfp_mask);
 void free_pages_exact(void *virt, size_t size);
-void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask);
+void * __meminit alloc_pages_exact_node(int nid, size_t size, gfp_t gfp_mask);
 
 #define __get_free_page(gfp_mask) \
 		__get_free_pages((gfp_mask), 0)

@@ -4888,7 +4888,7 @@ void *alloc_pages_exact(size_t size, gfp_t gfp_mask)
 EXPORT_SYMBOL(alloc_pages_exact);
 
 /**
- * alloc_pages_exact_nid - allocate an exact number of physically-contiguous
+ * alloc_pages_exact_node - allocate an exact number of physically-contiguous
  *			   pages on a node.
  * @nid: the preferred node ID where memory should be allocated
  * @size: the number of bytes to allocate

@@ -4899,7 +4899,7 @@ EXPORT_SYMBOL(alloc_pages_exact);
  *
  * Return: pointer to the allocated area or %NULL in case of error.
  */
-void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask)
+void * __meminit alloc_pages_exact_node(int nid, size_t size, gfp_t gfp_mask)
 {
 	unsigned int order = get_order(size);
 	struct page *p;

@@ -215,7 +215,7 @@ static void *__meminit alloc_page_ext(size_t size, int nid)
 	gfp_t flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN;
 	void *addr = NULL;
 
-	addr = alloc_pages_exact_nid(nid, size, flags);
+	addr = alloc_pages_exact_node(nid, size, flags);
 	if (addr) {
 		kmemleak_alloc(addr, size, 1, flags);
 		return addr;

@@ -241,7 +241,8 @@ static int ism_alloc_dmb(struct ism_dev *ism, struct smcd_dmb *dmb)
 
 	dmb->cpu_addr = dma_alloc_coherent(&ism->pdev->dev, dmb->dmb_len,
 					   &dmb->dma_addr,
-					   GFP_KERNEL | __GFP_NOWARN | __GFP_NOMEMALLOC | __GFP_COMP | __GFP_NORETRY);
+					   GFP_KERNEL | __GFP_NOWARN |
+					   __GFP_NORETRY);
 	if (!dmb->cpu_addr)
 		clear_bit(dmb->sba_idx, ism->sba_bitmap);
 

@@ -1028,7 +1028,7 @@ static int __cnic_alloc_uio_rings(struct cnic_uio_dev *udev, int pages)
 	udev->l2_ring_size = pages * CNIC_PAGE_SIZE;
 	udev->l2_ring = dma_alloc_coherent(&udev->pdev->dev, udev->l2_ring_size,
 					   &udev->l2_ring_map,
-					   GFP_KERNEL | __GFP_COMP);
+					   GFP_KERNEL);
 	if (!udev->l2_ring)
 		return -ENOMEM;
 

@@ -1036,7 +1036,7 @@ static int __cnic_alloc_uio_rings(struct cnic_uio_dev *udev, int pages)
 	udev->l2_buf_size = CNIC_PAGE_ALIGN(udev->l2_buf_size);
 	udev->l2_buf = dma_alloc_coherent(&udev->pdev->dev, udev->l2_buf_size,
 					  &udev->l2_buf_map,
-					  GFP_KERNEL | __GFP_COMP);
+					  GFP_KERNEL);
 	if (!udev->l2_buf) {
 		__cnic_free_uio_rings(udev);
 		return -ENOMEM;

@@ -77,13 +77,6 @@ drm_dma_handle_t *drm_pci_alloc(struct drm_device * dev, size_t size, size_t ali
 		return NULL;
 	}
 
-	/* XXX - Is virt_to_page() legal for consistent mem? */
-	/* Reserve */
-	for (addr = (unsigned long)dmah->vaddr, sz = size;
-	     sz > 0; addr += PAGE_SIZE, sz -= PAGE_SIZE) {
-		SetPageReserved(virt_to_page((void *)addr));
-	}
-
 	return dmah;
 }
 

@@ -97,16 +90,9 @@ void __drm_legacy_pci_free(struct drm_device * dev, drm_dma_handle_t * dmah)
 	unsigned long addr;
 	size_t sz;
 
-	if (dmah->vaddr) {
-		/* XXX - Is virt_to_page() legal for consistent mem? */
-		/* Unreserve */
-		for (addr = (unsigned long)dmah->vaddr, sz = dmah->size;
-		     sz > 0; addr += PAGE_SIZE, sz -= PAGE_SIZE) {
-			ClearPageReserved(virt_to_page((void *)addr));
-		}
+	if (dmah->vaddr)
 		dma_free_coherent(&dev->pdev->dev, dmah->size, dmah->vaddr,
 				  dmah->busaddr);
-	}
 }
 
 /**