summaryrefslogtreecommitdiff
path: root/drivers/iommu/dma-iommu.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-08-06 10:56:45 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2022-08-06 10:56:45 -0700
commitc993e07be023acdeec8e84e2e0743c52adb5fc94 (patch)
tree873b039ee47b424a31829ffcda3c316c52bf78e4 /drivers/iommu/dma-iommu.c
parent1d239c1eb873c7d6c6cbc80d68330c939fd86136 (diff)
parent5c850d31880e00f063fa2a3746ba212c4bcc510f (diff)
Merge tag 'dma-mapping-5.20-2022-08-06' of git://git.infradead.org/users/hch/dma-mapping
Pull dma-mapping updates from Christoph Hellwig: - convert arm32 to the common dma-direct code (Arnd Bergmann, Robin Murphy, Christoph Hellwig) - restructure the PCIe peer to peer mapping support (Logan Gunthorpe) - allow the IOMMU code to communicate an optional DMA mapping length and use that in scsi and libata (John Garry) - split the global swiotlb lock (Tianyu Lan) - various fixes and cleanup (Chao Gao, Dan Carpenter, Dongli Zhang, Lukas Bulwahn, Robin Murphy) * tag 'dma-mapping-5.20-2022-08-06' of git://git.infradead.org/users/hch/dma-mapping: (45 commits) swiotlb: fix passing local variable to debugfs_create_ulong() dma-mapping: reformat comment to suppress htmldoc warning PCI/P2PDMA: Remove pci_p2pdma_[un]map_sg() RDMA/rw: drop pci_p2pdma_[un]map_sg() RDMA/core: introduce ib_dma_pci_p2p_dma_supported() nvme-pci: convert to using dma_map_sgtable() nvme-pci: check DMA ops when indicating support for PCI P2PDMA iommu/dma: support PCI P2PDMA pages in dma-iommu map_sg iommu: Explicitly skip bus address marked segments in __iommu_map_sg() dma-mapping: add flags to dma_map_ops to indicate PCI P2PDMA support dma-direct: support PCI P2PDMA pages in dma-direct map_sg dma-mapping: allow EREMOTEIO return code for P2PDMA transfers PCI/P2PDMA: Introduce helpers for dma_map_sg implementations PCI/P2PDMA: Attempt to set map_type if it has not been set lib/scatterlist: add flag for indicating P2PDMA segments in an SGL swiotlb: clean up some coding style and minor issues dma-mapping: update comment after dmabounce removal scsi: sd: Add a comment about limiting max_sectors to shost optimal limit ata: libata-scsi: cap ata_device->max_sectors according to shost->max_sectors scsi: scsi_transport_sas: cap shost opt_sectors according to DMA optimal limit ...
Diffstat (limited to 'drivers/iommu/dma-iommu.c')
-rw-r--r--drivers/iommu/dma-iommu.c105
1 files changed, 91 insertions, 14 deletions
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 458fb6738223..376c4e3ae0e6 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -21,6 +21,7 @@
#include <linux/iova.h>
#include <linux/irq.h>
#include <linux/list_sort.h>
+#include <linux/memremap.h>
#include <linux/mm.h>
#include <linux/mutex.h>
#include <linux/pci.h>
@@ -1062,15 +1063,30 @@ static int __finalise_sg(struct device *dev, struct scatterlist *sg, int nents,
for_each_sg(sg, s, nents, i) {
/* Restore this segment's original unaligned fields first */
+ dma_addr_t s_dma_addr = sg_dma_address(s);
unsigned int s_iova_off = sg_dma_address(s);
unsigned int s_length = sg_dma_len(s);
unsigned int s_iova_len = s->length;
- s->offset += s_iova_off;
- s->length = s_length;
sg_dma_address(s) = DMA_MAPPING_ERROR;
sg_dma_len(s) = 0;
+ if (sg_is_dma_bus_address(s)) {
+ if (i > 0)
+ cur = sg_next(cur);
+
+ sg_dma_unmark_bus_address(s);
+ sg_dma_address(cur) = s_dma_addr;
+ sg_dma_len(cur) = s_length;
+ sg_dma_mark_bus_address(cur);
+ count++;
+ cur_len = 0;
+ continue;
+ }
+
+ s->offset += s_iova_off;
+ s->length = s_length;
+
/*
* Now fill in the real DMA data. If...
* - there is a valid output segment to append to
@@ -1111,10 +1127,14 @@ static void __invalidate_sg(struct scatterlist *sg, int nents)
int i;
for_each_sg(sg, s, nents, i) {
- if (sg_dma_address(s) != DMA_MAPPING_ERROR)
- s->offset += sg_dma_address(s);
- if (sg_dma_len(s))
- s->length = sg_dma_len(s);
+ if (sg_is_dma_bus_address(s)) {
+ sg_dma_unmark_bus_address(s);
+ } else {
+ if (sg_dma_address(s) != DMA_MAPPING_ERROR)
+ s->offset += sg_dma_address(s);
+ if (sg_dma_len(s))
+ s->length = sg_dma_len(s);
+ }
sg_dma_address(s) = DMA_MAPPING_ERROR;
sg_dma_len(s) = 0;
}
@@ -1167,6 +1187,8 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
struct iova_domain *iovad = &cookie->iovad;
struct scatterlist *s, *prev = NULL;
int prot = dma_info_to_prot(dir, dev_is_dma_coherent(dev), attrs);
+ struct pci_p2pdma_map_state p2pdma_state = {};
+ enum pci_p2pdma_map_type map;
dma_addr_t iova;
size_t iova_len = 0;
unsigned long mask = dma_get_seg_boundary(dev);
@@ -1196,6 +1218,30 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
size_t s_length = s->length;
size_t pad_len = (mask - iova_len + 1) & mask;
+ if (is_pci_p2pdma_page(sg_page(s))) {
+ map = pci_p2pdma_map_segment(&p2pdma_state, dev, s);
+ switch (map) {
+ case PCI_P2PDMA_MAP_BUS_ADDR:
+ /*
+ * iommu_map_sg() will skip this segment as
+ * it is marked as a bus address,
+ * __finalise_sg() will copy the dma address
+ * into the output segment.
+ */
+ continue;
+ case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE:
+ /*
+ * Mapping through host bridge should be
+ * mapped with regular IOVAs, thus we
+ * do nothing here and continue below.
+ */
+ break;
+ default:
+ ret = -EREMOTEIO;
+ goto out_restore_sg;
+ }
+ }
+
sg_dma_address(s) = s_iova_off;
sg_dma_len(s) = s_length;
s->offset -= s_iova_off;
@@ -1224,6 +1270,9 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
prev = s;
}
+ if (!iova_len)
+ return __finalise_sg(dev, sg, nents, 0);
+
iova = iommu_dma_alloc_iova(domain, iova_len, dma_get_mask(dev), dev);
if (!iova) {
ret = -ENOMEM;
@@ -1245,7 +1294,7 @@ out_free_iova:
out_restore_sg:
__invalidate_sg(sg, nents);
out:
- if (ret != -ENOMEM)
+ if (ret != -ENOMEM && ret != -EREMOTEIO)
return -EINVAL;
return ret;
}
@@ -1253,7 +1302,7 @@ out:
static void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
int nents, enum dma_data_direction dir, unsigned long attrs)
{
- dma_addr_t start, end;
+ dma_addr_t end = 0, start;
struct scatterlist *tmp;
int i;
@@ -1267,16 +1316,37 @@ static void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
/*
* The scatterlist segments are mapped into a single
- * contiguous IOVA allocation, so this is incredibly easy.
+ * contiguous IOVA allocation, the start and end points
+ * just have to be determined.
*/
- start = sg_dma_address(sg);
- for_each_sg(sg_next(sg), tmp, nents - 1, i) {
+ for_each_sg(sg, tmp, nents, i) {
+ if (sg_is_dma_bus_address(tmp)) {
+ sg_dma_unmark_bus_address(tmp);
+ continue;
+ }
+
if (sg_dma_len(tmp) == 0)
break;
- sg = tmp;
+
+ start = sg_dma_address(tmp);
+ break;
}
- end = sg_dma_address(sg) + sg_dma_len(sg);
- __iommu_dma_unmap(dev, start, end - start);
+
+ nents -= i;
+ for_each_sg(tmp, tmp, nents, i) {
+ if (sg_is_dma_bus_address(tmp)) {
+ sg_dma_unmark_bus_address(tmp);
+ continue;
+ }
+
+ if (sg_dma_len(tmp) == 0)
+ break;
+
+ end = sg_dma_address(tmp) + sg_dma_len(tmp);
+ }
+
+ if (end)
+ __iommu_dma_unmap(dev, start, end - start);
}
static dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
@@ -1468,7 +1538,13 @@ static unsigned long iommu_dma_get_merge_boundary(struct device *dev)
return (1UL << __ffs(domain->pgsize_bitmap)) - 1;
}
+static size_t iommu_dma_opt_mapping_size(void)
+{
+ return iova_rcache_range();
+}
+
static const struct dma_map_ops iommu_dma_ops = {
+ .flags = DMA_F_PCI_P2PDMA_SUPPORTED,
.alloc = iommu_dma_alloc,
.free = iommu_dma_free,
.alloc_pages = dma_common_alloc_pages,
@@ -1488,6 +1564,7 @@ static const struct dma_map_ops iommu_dma_ops = {
.map_resource = iommu_dma_map_resource,
.unmap_resource = iommu_dma_unmap_resource,
.get_merge_boundary = iommu_dma_get_merge_boundary,
+ .opt_mapping_size = iommu_dma_opt_mapping_size,
};
/*