Merge tag 'dma-mapping-6.2-2022-12-13' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - reduce the swiotlb buffer size on allocation failure (Alexey
   Kardashevskiy)

 - clean up passing of bogus GFP flags to the dma-coherent allocator
   (Christoph Hellwig)

* tag 'dma-mapping-6.2-2022-12-13' of git://git.infradead.org/users/hch/dma-mapping:
  dma-mapping: reject __GFP_COMP in dma_alloc_attrs
  ALSA: memalloc: don't pass bogus GFP_ flags to dma_alloc_*
  s390/ism: don't pass bogus GFP_ flags to dma_alloc_coherent
  cnic: don't pass bogus GFP_ flags to dma_alloc_coherent
  RDMA/qib: don't pass bogus GFP_ flags to dma_alloc_coherent
  RDMA/hfi1: don't pass bogus GFP_ flags to dma_alloc_coherent
  media: videobuf-dma-contig: use dma_mmap_coherent
  swiotlb: reduce the swiotlb buffer size on allocation failure

7 files changed, 20 insertions, 58 deletions

diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index 436372b31431..24c0f0d257fc 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -1761,17 +1761,11 @@ int hfi1_create_rcvhdrq(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd)
 	unsigned amt;
 
 	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);
+						  GFP_KERNEL);
 
 		if (!rcd->rcvhdrq) {
 			dd_dev_err(dd,
@@ -1785,7 +1779,7 @@ 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;
 		}
@@ -1821,20 +1815,11 @@ 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.
 	 * The global eager_buffer_size parameter is checked against the
@@ -1864,7 +1849,7 @@ 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;
diff --git a/drivers/infiniband/hw/qib/qib_iba6120.c b/drivers/infiniband/hw/qib/qib_iba6120.c
index aea571943768..07386117f21a 100644
--- a/drivers/infiniband/hw/qib/qib_iba6120.c
+++ b/drivers/infiniband/hw/qib/qib_iba6120.c
@@ -2075,7 +2075,7 @@ 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 */
diff --git a/drivers/infiniband/hw/qib/qib_init.c b/drivers/infiniband/hw/qib/qib_init.c
index 45211008449f..33667becd52b 100644
--- a/drivers/infiniband/hw/qib/qib_init.c
+++ b/drivers/infiniband/hw/qib/qib_init.c
@@ -1546,18 +1546,14 @@ 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);
+		rcd->rcvhdrq = dma_alloc_coherent(&dd->pcidev->dev, amt,
+				&rcd->rcvhdrq_phys, GFP_KERNEL);
 		set_dev_node(&dd->pcidev->dev, old_node_id);
 
 		if (!rcd->rcvhdrq) {
@@ -1577,7 +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;
@@ -1621,17 +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;
@@ -1663,7 +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;
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 9297b741f5e8..f798c44e0903 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -744,9 +744,6 @@ static struct page **__iommu_dma_alloc_pages(struct device *dev,
 	/* IOMMU can map any pages, so himem can also be used here */
 	gfp |= __GFP_NOWARN | __GFP_HIGHMEM;
 
-	/* It makes no sense to muck about with huge pages */
-	gfp &= ~__GFP_COMP;
-
 	while (count) {
 		struct page *page = NULL;
 		unsigned int order_size;
diff --git a/drivers/media/v4l2-core/videobuf-dma-contig.c b/drivers/media/v4l2-core/videobuf-dma-contig.c
index 52312ce2ba05..f2c439359557 100644
--- a/drivers/media/v4l2-core/videobuf-dma-contig.c
+++ b/drivers/media/v4l2-core/videobuf-dma-contig.c
@@ -36,12 +36,11 @@ 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);
 		return -ENOMEM;
@@ -258,8 +257,7 @@ 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:
@@ -295,22 +293,18 @@ 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 */
-	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, mem->size);
+	retval = dma_mmap_coherent(q->dev, vma, mem->vaddr, mem->dma_handle,
+				   mem->size);
 	if (retval) {
 		dev_err(q->dev, "mmap: remap failed with error %d. ",
 			retval);
diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c
index 74bc053a2078..7926aaef8f0c 100644
--- a/drivers/net/ethernet/broadcom/cnic.c
+++ b/drivers/net/ethernet/broadcom/cnic.c
@@ -1027,16 +1027,14 @@ 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);
+					   &udev->l2_ring_map, GFP_KERNEL);
 	if (!udev->l2_ring)
 		return -ENOMEM;
 
 	udev->l2_buf_size = (cp->l2_rx_ring_size + 1) * cp->l2_single_buf_size;
 	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);
+					  &udev->l2_buf_map, GFP_KERNEL);
 	if (!udev->l2_buf) {
 		__cnic_free_uio_rings(udev);
 		return -ENOMEM;
diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c
index d34bb6ec1490..dfd401d9e362 100644
--- a/drivers/s390/net/ism_drv.c
+++ b/drivers/s390/net/ism_drv.c
@@ -243,7 +243,8 @@ 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_NOMEMALLOC | __GFP_NORETRY);
 	if (!dmb->cpu_addr)
 		clear_bit(dmb->sba_idx, ism->sba_bitmap);