Commit e529d350 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

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
parents 6a24711d ffcb7545

arch/arm/mm/dma-mapping.c

+0 −17
Original line number Diff line number Diff line
@@ -564,14 +564,6 @@ 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;
@@ -1093,15 +1085,6 @@ 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;

drivers/infiniband/hw/hfi1/init.c

+3 −18
Original line number Diff line number Diff line
@@ -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;

		}
@@ -1821,19 +1815,10 @@ 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.
@@ -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;

drivers/infiniband/hw/qib/qib_iba6120.c

+1 −1
Original line number Diff line number Diff line
@@ -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 */

drivers/infiniband/hw/qib/qib_init.c

+4 −17
Original line number Diff line number Diff line
@@ -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;

drivers/iommu/dma-iommu.c

+0 −3
Original line number Diff line number Diff line
@@ -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;