summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--drivers/mmc/host/sdhci.c9
-rw-r--r--drivers/nvme/host/pci.c1
-rw-r--r--include/linux/device.h1
-rw-r--r--include/linux/dma-mapping.h16
-rw-r--r--include/linux/swiotlb.h1
-rw-r--r--kernel/dma/swiotlb.c310
6 files changed, 215 insertions, 123 deletions
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 646823ddd317..2d73407ee52e 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -20,7 +20,6 @@
#include <linux/slab.h>
#include <linux/scatterlist.h>
#include <linux/sizes.h>
-#include <linux/swiotlb.h>
#include <linux/regulator/consumer.h>
#include <linux/pm_runtime.h>
#include <linux/of.h>
@@ -4582,12 +4581,8 @@ int sdhci_setup_host(struct sdhci_host *host)
mmc->max_segs = SDHCI_MAX_SEGS;
} else if (host->flags & SDHCI_USE_SDMA) {
mmc->max_segs = 1;
- if (swiotlb_max_segment()) {
- unsigned int max_req_size = (1 << IO_TLB_SHIFT) *
- IO_TLB_SEGSIZE;
- mmc->max_req_size = min(mmc->max_req_size,
- max_req_size);
- }
+ mmc->max_req_size = min_t(size_t, mmc->max_req_size,
+ dma_max_mapping_size(mmc_dev(mmc)));
} else { /* PIO */
mmc->max_segs = SDHCI_MAX_SEGS;
}
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 7b6632c00ffd..38b0d694dfc9 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2632,6 +2632,7 @@ static void nvme_reset_work(struct work_struct *work)
* Don't limit the IOMMU merged segment size.
*/
dma_set_max_seg_size(dev->dev, 0xffffffff);
+ dma_set_min_align_mask(dev->dev, NVME_CTRL_PAGE_SIZE - 1);
mutex_unlock(&dev->shutdown_lock);
diff --git a/include/linux/device.h b/include/linux/device.h
index 7619a84f8ce4..ba660731bd25 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -291,6 +291,7 @@ struct device_dma_parameters {
* sg limitations.
*/
unsigned int max_segment_size;
+ unsigned int min_align_mask;
unsigned long segment_boundary_mask;
};
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index fbfa3f5abd94..2a984cb4d1e0 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -509,6 +509,22 @@ static inline int dma_set_seg_boundary(struct device *dev, unsigned long mask)
return -EIO;
}
+static inline unsigned int dma_get_min_align_mask(struct device *dev)
+{
+ if (dev->dma_parms)
+ return dev->dma_parms->min_align_mask;
+ return 0;
+}
+
+static inline int dma_set_min_align_mask(struct device *dev,
+ unsigned int min_align_mask)
+{
+ if (WARN_ON_ONCE(!dev->dma_parms))
+ return -EIO;
+ dev->dma_parms->min_align_mask = min_align_mask;
+ return 0;
+}
+
static inline int dma_get_cache_alignment(void)
{
#ifdef ARCH_DMA_MINALIGN
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index d9c9fc9ca5d2..5857a937c637 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -29,6 +29,7 @@ enum swiotlb_force {
* controllable.
*/
#define IO_TLB_SHIFT 11
+#define IO_TLB_SIZE (1 << IO_TLB_SHIFT)
/* default to 64MB */
#define IO_TLB_DEFAULT_SIZE (64UL<<20)
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 7c42df6e6100..c10e855a03bc 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -50,9 +50,6 @@
#define CREATE_TRACE_POINTS
#include <trace/events/swiotlb.h>
-#define OFFSET(val,align) ((unsigned long) \
- ( (val) & ( (align) - 1)))
-
#define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT))
/*
@@ -103,6 +100,11 @@ static unsigned int max_segment;
static phys_addr_t *io_tlb_orig_addr;
/*
+ * The mapped buffer's size should be validated during a sync operation.
+ */
+static size_t *io_tlb_orig_size;
+
+/*
* Protect the above data structures in the map and unmap calls
*/
static DEFINE_SPINLOCK(io_tlb_lock);
@@ -171,7 +173,7 @@ void __init swiotlb_adjust_size(unsigned long new_size)
* adjust/expand SWIOTLB size for their use.
*/
if (!io_tlb_nslabs) {
- size = ALIGN(new_size, 1 << IO_TLB_SHIFT);
+ size = ALIGN(new_size, IO_TLB_SIZE);
io_tlb_nslabs = size >> IO_TLB_SHIFT;
io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
@@ -192,6 +194,16 @@ void swiotlb_print_info(void)
bytes >> 20);
}
+static inline unsigned long io_tlb_offset(unsigned long val)
+{
+ return val & (IO_TLB_SEGSIZE - 1);
+}
+
+static inline unsigned long nr_slots(u64 val)
+{
+ return DIV_ROUND_UP(val, IO_TLB_SIZE);
+}
+
/*
* Early SWIOTLB allocation may be too early to allow an architecture to
* perform the desired operations. This function allows the architecture to
@@ -240,9 +252,16 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
panic("%s: Failed to allocate %zu bytes align=0x%lx\n",
__func__, alloc_size, PAGE_SIZE);
+ alloc_size = PAGE_ALIGN(io_tlb_nslabs * sizeof(size_t));
+ io_tlb_orig_size = memblock_alloc(alloc_size, PAGE_SIZE);
+ if (!io_tlb_orig_size)
+ panic("%s: Failed to allocate %zu bytes align=0x%lx\n",
+ __func__, alloc_size, PAGE_SIZE);
+
for (i = 0; i < io_tlb_nslabs; i++) {
- io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
+ io_tlb_list[i] = IO_TLB_SEGSIZE - io_tlb_offset(i);
io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
+ io_tlb_orig_size[i] = 0;
}
io_tlb_index = 0;
no_iotlb_memory = false;
@@ -363,7 +382,7 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
* between io_tlb_start and io_tlb_end.
*/
io_tlb_list = (unsigned int *)__get_free_pages(GFP_KERNEL,
- get_order(io_tlb_nslabs * sizeof(int)));
+ get_order(io_tlb_nslabs * sizeof(int)));
if (!io_tlb_list)
goto cleanup3;
@@ -374,9 +393,18 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
if (!io_tlb_orig_addr)
goto cleanup4;
+ io_tlb_orig_size = (size_t *)
+ __get_free_pages(GFP_KERNEL,
+ get_order(io_tlb_nslabs *
+ sizeof(size_t)));
+ if (!io_tlb_orig_size)
+ goto cleanup5;
+
+
for (i = 0; i < io_tlb_nslabs; i++) {
- io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
+ io_tlb_list[i] = IO_TLB_SEGSIZE - io_tlb_offset(i);
io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
+ io_tlb_orig_size[i] = 0;
}
io_tlb_index = 0;
no_iotlb_memory = false;
@@ -389,6 +417,10 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
return 0;
+cleanup5:
+ free_pages((unsigned long)io_tlb_orig_addr, get_order(io_tlb_nslabs *
+ sizeof(phys_addr_t)));
+
cleanup4:
free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs *
sizeof(int)));
@@ -404,6 +436,8 @@ void __init swiotlb_exit(void)
return;
if (late_alloc) {
+ free_pages((unsigned long)io_tlb_orig_size,
+ get_order(io_tlb_nslabs * sizeof(size_t)));
free_pages((unsigned long)io_tlb_orig_addr,
get_order(io_tlb_nslabs * sizeof(phys_addr_t)));
free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs *
@@ -413,6 +447,8 @@ void __init swiotlb_exit(void)
} else {
memblock_free_late(__pa(io_tlb_orig_addr),
PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)));
+ memblock_free_late(__pa(io_tlb_orig_size),
+ PAGE_ALIGN(io_tlb_nslabs * sizeof(size_t)));
memblock_free_late(__pa(io_tlb_list),
PAGE_ALIGN(io_tlb_nslabs * sizeof(int)));
memblock_free_late(io_tlb_start,
@@ -461,79 +497,71 @@ static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr,
}
}
-phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t orig_addr,
- size_t mapping_size, size_t alloc_size,
- enum dma_data_direction dir, unsigned long attrs)
-{
- dma_addr_t tbl_dma_addr = phys_to_dma_unencrypted(hwdev, io_tlb_start);
- unsigned long flags;
- phys_addr_t tlb_addr;
- unsigned int nslots, stride, index, wrap;
- int i;
- unsigned long mask;
- unsigned long offset_slots;
- unsigned long max_slots;
- unsigned long tmp_io_tlb_used;
-
- if (no_iotlb_memory)
- panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer");
-
- if (mem_encrypt_active())
- pr_warn_once("Memory encryption is active and system is using DMA bounce buffers\n");
+#define slot_addr(start, idx) ((start) + ((idx) << IO_TLB_SHIFT))
- if (mapping_size > alloc_size) {
- dev_warn_once(hwdev, "Invalid sizes (mapping: %zd bytes, alloc: %zd bytes)",
- mapping_size, alloc_size);
- return (phys_addr_t)DMA_MAPPING_ERROR;
- }
+/*
+ * Return the offset into a iotlb slot required to keep the device happy.
+ */
+static unsigned int swiotlb_align_offset(struct device *dev, u64 addr)
+{
+ return addr & dma_get_min_align_mask(dev) & (IO_TLB_SIZE - 1);
+}
- mask = dma_get_seg_boundary(hwdev);
+/*
+ * Carefully handle integer overflow which can occur when boundary_mask == ~0UL.
+ */
+static inline unsigned long get_max_slots(unsigned long boundary_mask)
+{
+ if (boundary_mask == ~0UL)
+ return 1UL << (BITS_PER_LONG - IO_TLB_SHIFT);
+ return nr_slots(boundary_mask + 1);
+}
- tbl_dma_addr &= mask;
+static unsigned int wrap_index(unsigned int index)
+{
+ if (index >= io_tlb_nslabs)
+ return 0;
+ return index;
+}
- offset_slots = ALIGN(tbl_dma_addr, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
+/*
+ * Find a suitable number of IO TLB entries size that will fit this request and
+ * allocate a buffer from that IO TLB pool.
+ */
+static int find_slots(struct device *dev, phys_addr_t orig_addr,
+ size_t alloc_size)
+{
+ unsigned long boundary_mask = dma_get_seg_boundary(dev);
+ dma_addr_t tbl_dma_addr =
+ phys_to_dma_unencrypted(dev, io_tlb_start) & boundary_mask;
+ unsigned long max_slots = get_max_slots(boundary_mask);
+ unsigned int iotlb_align_mask =
+ dma_get_min_align_mask(dev) & ~(IO_TLB_SIZE - 1);
+ unsigned int nslots = nr_slots(alloc_size), stride;
+ unsigned int index, wrap, count = 0, i;
+ unsigned long flags;
- /*
- * Carefully handle integer overflow which can occur when mask == ~0UL.
- */
- max_slots = mask + 1
- ? ALIGN(mask + 1, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT
- : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT);
+ BUG_ON(!nslots);
/*
- * For mappings greater than or equal to a page, we limit the stride
- * (and hence alignment) to a page size.
+ * For mappings with an alignment requirement don't bother looping to
+ * unaligned slots once we found an aligned one. For allocations of
+ * PAGE_SIZE or larger only look for page aligned allocations.
*/
- nslots = ALIGN(alloc_size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
+ stride = (iotlb_align_mask >> IO_TLB_SHIFT) + 1;
if (alloc_size >= PAGE_SIZE)
- stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT));
- else
- stride = 1;
-
- BUG_ON(!nslots);
+ stride = max(stride, stride << (PAGE_SHIFT - IO_TLB_SHIFT));
- /*
- * Find suitable number of IO TLB entries size that will fit this
- * request and allocate a buffer from that IO TLB pool.
- */
spin_lock_irqsave(&io_tlb_lock, flags);
-
if (unlikely(nslots > io_tlb_nslabs - io_tlb_used))
goto not_found;
- index = ALIGN(io_tlb_index, stride);
- if (index >= io_tlb_nslabs)
- index = 0;
- wrap = index;
-
+ index = wrap = wrap_index(ALIGN(io_tlb_index, stride));
do {
- while (iommu_is_span_boundary(index, nslots, offset_slots,
- max_slots)) {
- index += stride;
- if (index >= io_tlb_nslabs)
- index = 0;
- if (index == wrap)
- goto not_found;
+ if ((slot_addr(tbl_dma_addr, index) & iotlb_align_mask) !=
+ (orig_addr & iotlb_align_mask)) {
+ index = wrap_index(index + 1);
+ continue;
}
/*
@@ -541,55 +569,96 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t orig_addr,
* contiguous buffers, we allocate the buffers from that slot
* and mark the entries as '0' indicating unavailable.
*/
- if (io_tlb_list[index] >= nslots) {
- int count = 0;
-
- for (i = index; i < (int) (index + nslots); i++)
- io_tlb_list[i] = 0;
- for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE - 1) && io_tlb_list[i]; i--)
- io_tlb_list[i] = ++count;
- tlb_addr = io_tlb_start + (index << IO_TLB_SHIFT);
-
- /*
- * Update the indices to avoid searching in the next
- * round.
- */
- io_tlb_index = ((index + nslots) < io_tlb_nslabs
- ? (index + nslots) : 0);
-
- goto found;
+ if (!iommu_is_span_boundary(index, nslots,
+ nr_slots(tbl_dma_addr),
+ max_slots)) {
+ if (io_tlb_list[index] >= nslots)
+ goto found;
}
- index += stride;
- if (index >= io_tlb_nslabs)
- index = 0;
+ index = wrap_index(index + stride);
} while (index != wrap);
not_found:
- tmp_io_tlb_used = io_tlb_used;
-
spin_unlock_irqrestore(&io_tlb_lock, flags);
- if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit())
- dev_warn(hwdev, "swiotlb buffer is full (sz: %zd bytes), total %lu (slots), used %lu (slots)\n",
- alloc_size, io_tlb_nslabs, tmp_io_tlb_used);
- return (phys_addr_t)DMA_MAPPING_ERROR;
+ return -1;
+
found:
+ for (i = index; i < index + nslots; i++)
+ io_tlb_list[i] = 0;
+ for (i = index - 1;
+ io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 &&
+ io_tlb_list[i]; i--)
+ io_tlb_list[i] = ++count;
+
+ /*
+ * Update the indices to avoid searching in the next round.
+ */
+ if (index + nslots < io_tlb_nslabs)
+ io_tlb_index = index + nslots;
+ else
+ io_tlb_index = 0;
io_tlb_used += nslots;
+
spin_unlock_irqrestore(&io_tlb_lock, flags);
+ return index;
+}
+
+phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
+ size_t mapping_size, size_t alloc_size,
+ enum dma_data_direction dir, unsigned long attrs)
+{
+ unsigned int offset = swiotlb_align_offset(dev, orig_addr);
+ unsigned int index, i;
+ phys_addr_t tlb_addr;
+
+ if (no_iotlb_memory)
+ panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer");
+
+ if (mem_encrypt_active())
+ pr_warn_once("Memory encryption is active and system is using DMA bounce buffers\n");
+
+ if (mapping_size > alloc_size) {
+ dev_warn_once(dev, "Invalid sizes (mapping: %zd bytes, alloc: %zd bytes)",
+ mapping_size, alloc_size);
+ return (phys_addr_t)DMA_MAPPING_ERROR;
+ }
+
+ index = find_slots(dev, orig_addr, alloc_size + offset);
+ if (index == -1) {
+ if (!(attrs & DMA_ATTR_NO_WARN))
+ dev_warn_ratelimited(dev,
+ "swiotlb buffer is full (sz: %zd bytes), total %lu (slots), used %lu (slots)\n",
+ alloc_size, io_tlb_nslabs, io_tlb_used);
+ return (phys_addr_t)DMA_MAPPING_ERROR;
+ }
/*
* Save away the mapping from the original address to the DMA address.
* This is needed when we sync the memory. Then we sync the buffer if
* needed.
*/
- for (i = 0; i < nslots; i++)
- io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT);
+ for (i = 0; i < nr_slots(alloc_size + offset); i++) {
+ io_tlb_orig_addr[index + i] = slot_addr(orig_addr, i);
+ io_tlb_orig_size[index+i] = alloc_size - (i << IO_TLB_SHIFT);
+ }
+ tlb_addr = slot_addr(io_tlb_start, index) + offset;
if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
swiotlb_bounce(orig_addr, tlb_addr, mapping_size, DMA_TO_DEVICE);
-
return tlb_addr;
}
+static void validate_sync_size_and_truncate(struct device *hwdev, size_t orig_size, size_t *size)
+{
+ if (*size > orig_size) {
+ /* Warn and truncate mapping_size */
+ dev_WARN_ONCE(hwdev, 1,
+ "Attempt for buffer overflow. Original size: %zu. Mapping size: %zu.\n",
+ orig_size, *size);
+ *size = orig_size;
+ }
+}
+
/*
* tlb_addr is the physical address of the bounce buffer to unmap.
*/
@@ -598,10 +667,13 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
enum dma_data_direction dir, unsigned long attrs)
{
unsigned long flags;
- int i, count, nslots = ALIGN(alloc_size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
- int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT;
+ unsigned int offset = swiotlb_align_offset(hwdev, tlb_addr);
+ int i, count, nslots = nr_slots(alloc_size + offset);
+ int index = (tlb_addr - offset - io_tlb_start) >> IO_TLB_SHIFT;
phys_addr_t orig_addr = io_tlb_orig_addr[index];
+ validate_sync_size_and_truncate(hwdev, io_tlb_orig_size[index], &mapping_size);
+
/*
* First, sync the memory before unmapping the entry
*/
@@ -617,26 +689,30 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
* with slots below and above the pool being returned.
*/
spin_lock_irqsave(&io_tlb_lock, flags);
- {
- count = ((index + nslots) < ALIGN(index + 1, IO_TLB_SEGSIZE) ?
- io_tlb_list[index + nslots] : 0);
- /*
- * Step 1: return the slots to the free list, merging the
- * slots with superceeding slots
- */
- for (i = index + nslots - 1; i >= index; i--) {
- io_tlb_list[i] = ++count;
- io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
- }
- /*
- * Step 2: merge the returned slots with the preceding slots,
- * if available (non zero)
- */
- for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE -1) && io_tlb_list[i]; i--)
- io_tlb_list[i] = ++count;
+ if (index + nslots < ALIGN(index + 1, IO_TLB_SEGSIZE))
+ count = io_tlb_list[index + nslots];
+ else
+ count = 0;
- io_tlb_used -= nslots;
+ /*
+ * Step 1: return the slots to the free list, merging the slots with
+ * superceeding slots
+ */
+ for (i = index + nslots - 1; i >= index; i--) {
+ io_tlb_list[i] = ++count;
+ io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
+ io_tlb_orig_size[i] = 0;
}
+
+ /*
+ * Step 2: merge the returned slots with the preceding slots, if
+ * available (non zero)
+ */
+ for (i = index - 1;
+ io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 && io_tlb_list[i];
+ i--)
+ io_tlb_list[i] = ++count;
+ io_tlb_used -= nslots;
spin_unlock_irqrestore(&io_tlb_lock, flags);
}
@@ -645,11 +721,13 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr,
enum dma_sync_target target)
{
int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT;
+ size_t orig_size = io_tlb_orig_size[index];
phys_addr_t orig_addr = io_tlb_orig_addr[index];
if (orig_addr == INVALID_PHYS_ADDR)
return;
- orig_addr += (unsigned long)tlb_addr & ((1 << IO_TLB_SHIFT) - 1);
+
+ validate_sync_size_and_truncate(hwdev, orig_size, &size);
switch (target) {
case SYNC_FOR_CPU:
@@ -707,7 +785,7 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size,
size_t swiotlb_max_mapping_size(struct device *dev)
{
- return ((size_t)1 << IO_TLB_SHIFT) * IO_TLB_SEGSIZE;
+ return ((size_t)IO_TLB_SIZE) * IO_TLB_SEGSIZE;
}
bool is_swiotlb_active(void)