From b22da3d8526a935aa31e086e63f60ff3246cb61c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Sat, 09 Dec 2023 07:24:11 +0000
Subject: [PATCH] add stmac read mac form eeprom
---
kernel/kernel/dma/swiotlb.c | 807 ++++++++++++++++++---------------------------------------
1 files changed, 261 insertions(+), 546 deletions(-)
diff --git a/kernel/kernel/dma/swiotlb.c b/kernel/kernel/dma/swiotlb.c
index 6f7d4e9..d897d16 100644
--- a/kernel/kernel/dma/swiotlb.c
+++ b/kernel/kernel/dma/swiotlb.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Dynamic DMA mapping support.
*
@@ -21,6 +22,7 @@
#include <linux/cache.h>
#include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
#include <linux/mm.h>
#include <linux/export.h>
#include <linux/spinlock.h>
@@ -34,19 +36,19 @@
#include <linux/scatterlist.h>
#include <linux/mem_encrypt.h>
#include <linux/set_memory.h>
+#ifdef CONFIG_DEBUG_FS
+#include <linux/debugfs.h>
+#endif
#include <asm/io.h>
#include <asm/dma.h>
#include <linux/init.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/iommu-helper.h>
#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))
@@ -64,7 +66,7 @@
* swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this
* API.
*/
-static phys_addr_t io_tlb_start, io_tlb_end;
+phys_addr_t io_tlb_start, io_tlb_end;
/*
* The number of IO TLB blocks (in groups of 64) between io_tlb_start and
@@ -73,11 +75,9 @@
static unsigned long io_tlb_nslabs;
/*
- * When the IOMMU overflows we return a fallback buffer. This sets the size.
+ * The number of used IO TLB block
*/
-static unsigned long io_tlb_overflow = 32*1024;
-
-static phys_addr_t io_tlb_overflow_buffer;
+static unsigned long io_tlb_used;
/*
* This is a free list describing the number of free entries available from
@@ -90,7 +90,7 @@
* Max segment that we can provide which (if pages are contingous) will
* not be bounced (unless SWIOTLB_FORCE is set).
*/
-unsigned int max_segment;
+static unsigned int max_segment;
/*
* We need to save away the original address corresponding to a mapped entry
@@ -126,17 +126,18 @@
return 0;
}
early_param("swiotlb", setup_io_tlb_npages);
-/* make io_tlb_overflow tunable too? */
+
+static bool no_iotlb_memory;
unsigned long swiotlb_nr_tbl(void)
{
- return io_tlb_nslabs;
+ return unlikely(no_iotlb_memory) ? 0 : io_tlb_nslabs;
}
EXPORT_SYMBOL_GPL(swiotlb_nr_tbl);
unsigned int swiotlb_max_segment(void)
{
- return max_segment;
+ return unlikely(no_iotlb_memory) ? 0 : max_segment;
}
EXPORT_SYMBOL_GPL(swiotlb_max_segment);
@@ -159,8 +160,6 @@
return size ? size : (IO_TLB_DEFAULT_SIZE);
}
-static bool no_iotlb_memory;
-
void swiotlb_print_info(void)
{
unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT;
@@ -170,10 +169,18 @@
return;
}
- pr_info("mapped [mem %#010llx-%#010llx] (%luMB)\n",
- (unsigned long long)io_tlb_start,
- (unsigned long long)io_tlb_end,
+ pr_info("mapped [mem %pa-%pa] (%luMB)\n", &io_tlb_start, &io_tlb_end,
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);
}
/*
@@ -194,17 +201,12 @@
bytes = PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT);
set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT);
memset(vaddr, 0, bytes);
-
- vaddr = phys_to_virt(io_tlb_overflow_buffer);
- bytes = PAGE_ALIGN(io_tlb_overflow);
- set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT);
- memset(vaddr, 0, bytes);
}
int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
{
- void *v_overflow_buffer;
unsigned long i, bytes;
+ size_t alloc_size;
bytes = nslabs << IO_TLB_SHIFT;
@@ -213,29 +215,24 @@
io_tlb_end = io_tlb_start + bytes;
/*
- * Get the overflow emergency buffer
- */
- v_overflow_buffer = memblock_virt_alloc_low_nopanic(
- PAGE_ALIGN(io_tlb_overflow),
- PAGE_SIZE);
- if (!v_overflow_buffer)
- return -ENOMEM;
-
- io_tlb_overflow_buffer = __pa(v_overflow_buffer);
-
- /*
* Allocate and initialize the free list array. This array is used
* to find contiguous free memory regions of size up to IO_TLB_SEGSIZE
* between io_tlb_start and io_tlb_end.
*/
- io_tlb_list = memblock_virt_alloc(
- PAGE_ALIGN(io_tlb_nslabs * sizeof(int)),
- PAGE_SIZE);
- io_tlb_orig_addr = memblock_virt_alloc(
- PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)),
- PAGE_SIZE);
+ alloc_size = PAGE_ALIGN(io_tlb_nslabs * sizeof(int));
+ io_tlb_list = memblock_alloc(alloc_size, PAGE_SIZE);
+ if (!io_tlb_list)
+ panic("%s: Failed to allocate %zu bytes align=0x%lx\n",
+ __func__, alloc_size, PAGE_SIZE);
+
+ alloc_size = PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t));
+ io_tlb_orig_addr = memblock_alloc(alloc_size, PAGE_SIZE);
+ if (!io_tlb_orig_addr)
+ 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_index = 0;
@@ -267,7 +264,7 @@
bytes = io_tlb_nslabs << IO_TLB_SHIFT;
/* Get IO TLB memory from the low pages */
- vstart = memblock_virt_alloc_low_nopanic(PAGE_ALIGN(bytes), PAGE_SIZE);
+ vstart = memblock_alloc_low(PAGE_ALIGN(bytes), PAGE_SIZE);
if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose))
return;
@@ -329,11 +326,18 @@
return rc;
}
+static void swiotlb_cleanup(void)
+{
+ io_tlb_end = 0;
+ io_tlb_start = 0;
+ io_tlb_nslabs = 0;
+ max_segment = 0;
+}
+
int
swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
{
unsigned long i, bytes;
- unsigned char *v_overflow_buffer;
bytes = nslabs << IO_TLB_SHIFT;
@@ -343,19 +347,6 @@
set_memory_decrypted((unsigned long)tlb, bytes >> PAGE_SHIFT);
memset(tlb, 0, bytes);
-
- /*
- * Get the overflow emergency buffer
- */
- v_overflow_buffer = (void *)__get_free_pages(GFP_DMA,
- get_order(io_tlb_overflow));
- if (!v_overflow_buffer)
- goto cleanup2;
-
- set_memory_decrypted((unsigned long)v_overflow_buffer,
- io_tlb_overflow >> PAGE_SHIFT);
- memset(v_overflow_buffer, 0, io_tlb_overflow);
- io_tlb_overflow_buffer = virt_to_phys(v_overflow_buffer);
/*
* Allocate and initialize the free list array. This array is used
@@ -375,7 +366,7 @@
goto cleanup4;
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_index = 0;
@@ -394,14 +385,7 @@
sizeof(int)));
io_tlb_list = NULL;
cleanup3:
- free_pages((unsigned long)v_overflow_buffer,
- get_order(io_tlb_overflow));
- io_tlb_overflow_buffer = 0;
-cleanup2:
- io_tlb_end = 0;
- io_tlb_start = 0;
- io_tlb_nslabs = 0;
- max_segment = 0;
+ swiotlb_cleanup();
return -ENOMEM;
}
@@ -411,8 +395,6 @@
return;
if (late_alloc) {
- free_pages((unsigned long)phys_to_virt(io_tlb_overflow_buffer),
- get_order(io_tlb_overflow));
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 *
@@ -420,8 +402,6 @@
free_pages((unsigned long)phys_to_virt(io_tlb_start),
get_order(io_tlb_nslabs << IO_TLB_SHIFT));
} else {
- memblock_free_late(io_tlb_overflow_buffer,
- PAGE_ALIGN(io_tlb_overflow));
memblock_free_late(__pa(io_tlb_orig_addr),
PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)));
memblock_free_late(__pa(io_tlb_list),
@@ -429,17 +409,11 @@
memblock_free_late(io_tlb_start,
PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
}
- io_tlb_nslabs = 0;
- max_segment = 0;
-}
-
-int is_swiotlb_buffer(phys_addr_t paddr)
-{
- return paddr >= io_tlb_start && paddr < io_tlb_end;
+ swiotlb_cleanup();
}
/*
- * Bounce: copy the swiotlb buffer back to the original dma location
+ * Bounce: copy the swiotlb buffer from or back to the original dma location
*/
static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr,
size_t size, enum dma_data_direction dir)
@@ -478,70 +452,74 @@
}
}
-phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
- dma_addr_t tbl_dma_addr,
- phys_addr_t orig_addr, size_t size,
- enum dma_data_direction dir,
- unsigned long attrs)
+static inline phys_addr_t slot_addr(phys_addr_t start, phys_addr_t idx)
{
+ return start + (idx << IO_TLB_SHIFT);
+}
+
+/*
+ * 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);
+}
+
+/*
+ * 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);
+}
+
+static unsigned int wrap_index(unsigned int index)
+{
+ if (index >= io_tlb_nslabs)
+ return 0;
+ return index;
+}
+
+/*
+ * 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;
- phys_addr_t tlb_addr;
- unsigned int nslots, stride, index, wrap;
- int i;
- unsigned long mask;
- unsigned long offset_slots;
- unsigned long max_slots;
-
- 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("%s is active and system is using DMA bounce buffers\n",
- sme_active() ? "SME" : "SEV");
-
- mask = dma_get_seg_boundary(hwdev);
-
- tbl_dma_addr &= mask;
-
- offset_slots = ALIGN(tbl_dma_addr, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
-
- /*
- * 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);
-
- /*
- * For mappings greater than or equal to a page, we limit the stride
- * (and hence alignment) to a page size.
- */
- nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
- if (size >= PAGE_SIZE)
- stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT));
- else
- stride = 1;
BUG_ON(!nslots);
/*
- * Find suitable number of IO TLB entries size that will fit this
- * request and allocate a buffer from that IO TLB pool.
+ * 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.
*/
- spin_lock_irqsave(&io_tlb_lock, flags);
- index = ALIGN(io_tlb_index, stride);
- if (index >= io_tlb_nslabs)
- index = 0;
- wrap = index;
+ stride = (iotlb_align_mask >> IO_TLB_SHIFT) + 1;
+ if (alloc_size >= PAGE_SIZE)
+ stride = max(stride, stride << (PAGE_SHIFT - IO_TLB_SHIFT));
+ spin_lock_irqsave(&io_tlb_lock, flags);
+ if (unlikely(nslots > io_tlb_nslabs - io_tlb_used))
+ goto not_found;
+
+ 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;
}
/*
@@ -549,81 +527,101 @@
* 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:
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)\n", size);
- return SWIOTLB_MAP_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 i;
+ int index;
+ 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);
- if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
- (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
- swiotlb_bounce(orig_addr, tlb_addr, size, DMA_TO_DEVICE);
+ for (i = 0; i < nr_slots(alloc_size + offset); i++)
+ io_tlb_orig_addr[index + i] = slot_addr(orig_addr, i);
+ tlb_addr = slot_addr(io_tlb_start, index) + offset;
+ /*
+ * When dir == DMA_FROM_DEVICE we could omit the copy from the orig
+ * to the tlb buffer, if we knew for sure the device will
+ * overwirte the entire current content. But we don't. Thus
+ * unconditional bounce may prevent leaking swiotlb content (i.e.
+ * kernel memory) to user-space.
+ */
+ swiotlb_bounce(orig_addr, tlb_addr, mapping_size, DMA_TO_DEVICE);
return tlb_addr;
-}
-
-/*
- * Allocates bounce buffer and returns its physical address.
- */
-static phys_addr_t
-map_single(struct device *hwdev, phys_addr_t phys, size_t size,
- enum dma_data_direction dir, unsigned long attrs)
-{
- dma_addr_t start_dma_addr;
-
- if (swiotlb_force == SWIOTLB_NO_FORCE) {
- dev_warn_ratelimited(hwdev, "Cannot do DMA to address %pa\n",
- &phys);
- return SWIOTLB_MAP_ERROR;
- }
-
- start_dma_addr = __phys_to_dma(hwdev, io_tlb_start);
- return swiotlb_tbl_map_single(hwdev, start_dma_addr, phys, size,
- dir, attrs);
}
/*
* tlb_addr is the physical address of the bounce buffer to unmap.
*/
void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
- size_t size, enum dma_data_direction dir,
- unsigned long attrs)
+ size_t mapping_size, size_t alloc_size,
+ enum dma_data_direction dir, unsigned long attrs)
{
unsigned long flags;
- int i, count, nslots = ALIGN(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];
/*
@@ -632,7 +630,7 @@
if (orig_addr != INVALID_PHYS_ADDR &&
!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
- swiotlb_bounce(orig_addr, tlb_addr, size, DMA_FROM_DEVICE);
+ swiotlb_bounce(orig_addr, tlb_addr, mapping_size, DMA_FROM_DEVICE);
/*
* Return the buffer to the free list by setting the corresponding
@@ -641,24 +639,29 @@
* 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;
+
+ /*
+ * 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;
+ 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);
}
@@ -671,7 +674,9 @@
if (orig_addr == INVALID_PHYS_ADDR)
return;
- orig_addr += (unsigned long)tlb_addr & ((1 << IO_TLB_SHIFT) - 1);
+
+ orig_addr += (tlb_addr & (IO_TLB_SIZE - 1)) -
+ swiotlb_align_offset(hwdev, orig_addr);
switch (target) {
case SYNC_FOR_CPU:
@@ -693,367 +698,77 @@
}
}
-static inline bool dma_coherent_ok(struct device *dev, dma_addr_t addr,
- size_t size)
-{
- u64 mask = DMA_BIT_MASK(32);
-
- if (dev && dev->coherent_dma_mask)
- mask = dev->coherent_dma_mask;
- return addr + size - 1 <= mask;
-}
-
-static void *
-swiotlb_alloc_buffer(struct device *dev, size_t size, dma_addr_t *dma_handle,
- unsigned long attrs)
-{
- phys_addr_t phys_addr;
-
- if (swiotlb_force == SWIOTLB_NO_FORCE)
- goto out_warn;
-
- phys_addr = swiotlb_tbl_map_single(dev,
- __phys_to_dma(dev, io_tlb_start),
- 0, size, DMA_FROM_DEVICE, attrs);
- if (phys_addr == SWIOTLB_MAP_ERROR)
- goto out_warn;
-
- *dma_handle = __phys_to_dma(dev, phys_addr);
- if (!dma_coherent_ok(dev, *dma_handle, size))
- goto out_unmap;
-
- memset(phys_to_virt(phys_addr), 0, size);
- return phys_to_virt(phys_addr);
-
-out_unmap:
- dev_warn(dev, "hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n",
- (unsigned long long)dev->coherent_dma_mask,
- (unsigned long long)*dma_handle);
-
- /*
- * DMA_TO_DEVICE to avoid memcpy in unmap_single.
- * DMA_ATTR_SKIP_CPU_SYNC is optional.
- */
- swiotlb_tbl_unmap_single(dev, phys_addr, size, DMA_TO_DEVICE,
- DMA_ATTR_SKIP_CPU_SYNC);
-out_warn:
- if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) {
- dev_warn(dev,
- "swiotlb: coherent allocation failed, size=%zu\n",
- size);
- dump_stack();
- }
- return NULL;
-}
-
-static bool swiotlb_free_buffer(struct device *dev, size_t size,
- dma_addr_t dma_addr)
-{
- phys_addr_t phys_addr = dma_to_phys(dev, dma_addr);
-
- WARN_ON_ONCE(irqs_disabled());
-
- if (!is_swiotlb_buffer(phys_addr))
- return false;
-
- /*
- * DMA_TO_DEVICE to avoid memcpy in swiotlb_tbl_unmap_single.
- * DMA_ATTR_SKIP_CPU_SYNC is optional.
- */
- swiotlb_tbl_unmap_single(dev, phys_addr, size, DMA_TO_DEVICE,
- DMA_ATTR_SKIP_CPU_SYNC);
- return true;
-}
-
/*
- * Map a single buffer of the indicated size for DMA in streaming mode. The
- * physical address to use is returned.
- *
- * Once the device is given the dma address, the device owns this memory until
- * either swiotlb_unmap_page or swiotlb_dma_sync_single is performed.
+ * Create a swiotlb mapping for the buffer at @paddr, and in case of DMAing
+ * to the device copy the data into it as well.
*/
-dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction dir,
- unsigned long attrs)
+dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size,
+ enum dma_data_direction dir, unsigned long attrs)
{
- phys_addr_t map, phys = page_to_phys(page) + offset;
- dma_addr_t dev_addr = phys_to_dma(dev, phys);
+ phys_addr_t swiotlb_addr;
+ dma_addr_t dma_addr;
- BUG_ON(dir == DMA_NONE);
- /*
- * If the address happens to be in the device's DMA window,
- * we can safely return the device addr and not worry about bounce
- * buffering it.
- */
- if (dma_capable(dev, dev_addr, size) && swiotlb_force != SWIOTLB_FORCE)
- return dev_addr;
+ trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size,
+ swiotlb_force);
- trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
-
- /* Oh well, have to allocate and map a bounce buffer. */
- map = map_single(dev, phys, size, dir, attrs);
- if (map == SWIOTLB_MAP_ERROR)
- return __phys_to_dma(dev, io_tlb_overflow_buffer);
-
- dev_addr = __phys_to_dma(dev, map);
+ swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, size, dir,
+ attrs);
+ if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR)
+ return DMA_MAPPING_ERROR;
/* Ensure that the address returned is DMA'ble */
- if (dma_capable(dev, dev_addr, size))
- return dev_addr;
-
- attrs |= DMA_ATTR_SKIP_CPU_SYNC;
- swiotlb_tbl_unmap_single(dev, map, size, dir, attrs);
-
- return __phys_to_dma(dev, io_tlb_overflow_buffer);
-}
-
-/*
- * Unmap a single streaming mode DMA translation. The dma_addr and size must
- * match what was provided for in a previous swiotlb_map_page call. All
- * other usages are undefined.
- *
- * After this call, reads by the cpu to the buffer are guaranteed to see
- * whatever the device wrote there.
- */
-static void unmap_single(struct device *hwdev, dma_addr_t dev_addr,
- size_t size, enum dma_data_direction dir,
- unsigned long attrs)
-{
- phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
-
- BUG_ON(dir == DMA_NONE);
-
- if (is_swiotlb_buffer(paddr)) {
- swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, attrs);
- return;
+ dma_addr = phys_to_dma_unencrypted(dev, swiotlb_addr);
+ if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
+ swiotlb_tbl_unmap_single(dev, swiotlb_addr, size, size, dir,
+ attrs | DMA_ATTR_SKIP_CPU_SYNC);
+ dev_WARN_ONCE(dev, 1,
+ "swiotlb addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
+ &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
+ return DMA_MAPPING_ERROR;
}
- if (dir != DMA_FROM_DEVICE)
- return;
+ if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+ arch_sync_dma_for_device(swiotlb_addr, size, dir);
+ return dma_addr;
+}
+
+size_t swiotlb_max_mapping_size(struct device *dev)
+{
+ int min_align_mask = dma_get_min_align_mask(dev);
+ int min_align = 0;
/*
- * phys_to_virt doesn't work with hihgmem page but we could
- * call dma_mark_clean() with hihgmem page here. However, we
- * are fine since dma_mark_clean() is null on POWERPC. We can
- * make dma_mark_clean() take a physical address if necessary.
+ * swiotlb_find_slots() skips slots according to
+ * min align mask. This affects max mapping size.
+ * Take it into acount here.
*/
- dma_mark_clean(phys_to_virt(paddr), size);
+ if (min_align_mask)
+ min_align = roundup(min_align_mask, IO_TLB_SIZE);
+
+ return ((size_t)IO_TLB_SIZE) * IO_TLB_SEGSIZE - min_align;
}
-void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
- size_t size, enum dma_data_direction dir,
- unsigned long attrs)
+bool is_swiotlb_active(void)
{
- unmap_single(hwdev, dev_addr, size, dir, attrs);
-}
-
-/*
- * Make physical memory consistent for a single streaming mode DMA translation
- * after a transfer.
- *
- * If you perform a swiotlb_map_page() but wish to interrogate the buffer
- * using the cpu, yet do not wish to teardown the dma mapping, you must
- * call this function before doing so. At the next point you give the dma
- * address back to the card, you must first perform a
- * swiotlb_dma_sync_for_device, and then the device again owns the buffer
- */
-static void
-swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
- size_t size, enum dma_data_direction dir,
- enum dma_sync_target target)
-{
- phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
-
- BUG_ON(dir == DMA_NONE);
-
- if (is_swiotlb_buffer(paddr)) {
- swiotlb_tbl_sync_single(hwdev, paddr, size, dir, target);
- return;
- }
-
- if (dir != DMA_FROM_DEVICE)
- return;
-
- dma_mark_clean(phys_to_virt(paddr), size);
-}
-
-void
-swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
- size_t size, enum dma_data_direction dir)
-{
- swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_CPU);
-}
-
-void
-swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr,
- size_t size, enum dma_data_direction dir)
-{
- swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_DEVICE);
-}
-
-/*
- * Map a set of buffers described by scatterlist in streaming mode for DMA.
- * This is the scatter-gather version of the above swiotlb_map_page
- * interface. Here the scatter gather list elements are each tagged with the
- * appropriate dma address and length. They are obtained via
- * sg_dma_{address,length}(SG).
- *
- * NOTE: An implementation may be able to use a smaller number of
- * DMA address/length pairs than there are SG table elements.
- * (for example via virtual mapping capabilities)
- * The routine returns the number of addr/length pairs actually
- * used, at most nents.
- *
- * Device ownership issues as mentioned above for swiotlb_map_page are the
- * same here.
- */
-int
-swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
- enum dma_data_direction dir, unsigned long attrs)
-{
- struct scatterlist *sg;
- int i;
-
- BUG_ON(dir == DMA_NONE);
-
- for_each_sg(sgl, sg, nelems, i) {
- phys_addr_t paddr = sg_phys(sg);
- dma_addr_t dev_addr = phys_to_dma(hwdev, paddr);
-
- if (swiotlb_force == SWIOTLB_FORCE ||
- !dma_capable(hwdev, dev_addr, sg->length)) {
- phys_addr_t map = map_single(hwdev, sg_phys(sg),
- sg->length, dir, attrs);
- if (map == SWIOTLB_MAP_ERROR) {
- /* Don't panic here, we expect map_sg users
- to do proper error handling. */
- attrs |= DMA_ATTR_SKIP_CPU_SYNC;
- swiotlb_unmap_sg_attrs(hwdev, sgl, i, dir,
- attrs);
- sg_dma_len(sgl) = 0;
- return 0;
- }
- sg->dma_address = __phys_to_dma(hwdev, map);
- } else
- sg->dma_address = dev_addr;
- sg_dma_len(sg) = sg->length;
- }
- return nelems;
-}
-
-/*
- * Unmap a set of streaming mode DMA translations. Again, cpu read rules
- * concerning calls here are the same as for swiotlb_unmap_page() above.
- */
-void
-swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
- int nelems, enum dma_data_direction dir,
- unsigned long attrs)
-{
- struct scatterlist *sg;
- int i;
-
- BUG_ON(dir == DMA_NONE);
-
- for_each_sg(sgl, sg, nelems, i)
- unmap_single(hwdev, sg->dma_address, sg_dma_len(sg), dir,
- attrs);
-}
-
-/*
- * Make physical memory consistent for a set of streaming mode DMA translations
- * after a transfer.
- *
- * The same as swiotlb_sync_single_* but for a scatter-gather list, same rules
- * and usage.
- */
-static void
-swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl,
- int nelems, enum dma_data_direction dir,
- enum dma_sync_target target)
-{
- struct scatterlist *sg;
- int i;
-
- for_each_sg(sgl, sg, nelems, i)
- swiotlb_sync_single(hwdev, sg->dma_address,
- sg_dma_len(sg), dir, target);
-}
-
-void
-swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
- int nelems, enum dma_data_direction dir)
-{
- swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_CPU);
-}
-
-void
-swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
- int nelems, enum dma_data_direction dir)
-{
- swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE);
-}
-
-int
-swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
-{
- return (dma_addr == __phys_to_dma(hwdev, io_tlb_overflow_buffer));
-}
-
-/*
- * Return whether the given device DMA address mask can be supported
- * properly. For example, if your device can only drive the low 24-bits
- * during bus mastering, then you would pass 0x00ffffff as the mask to
- * this function.
- */
-int
-swiotlb_dma_supported(struct device *hwdev, u64 mask)
-{
- return __phys_to_dma(hwdev, io_tlb_end - 1) <= mask;
-}
-
-void *swiotlb_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
- gfp_t gfp, unsigned long attrs)
-{
- void *vaddr;
-
- /* temporary workaround: */
- if (gfp & __GFP_NOWARN)
- attrs |= DMA_ATTR_NO_WARN;
-
/*
- * Don't print a warning when the first allocation attempt fails.
- * swiotlb_alloc_coherent() will print a warning when the DMA memory
- * allocation ultimately failed.
+ * When SWIOTLB is initialized, even if io_tlb_start points to physical
+ * address zero, io_tlb_end surely doesn't.
*/
- gfp |= __GFP_NOWARN;
-
- vaddr = dma_direct_alloc(dev, size, dma_handle, gfp, attrs);
- if (!vaddr)
- vaddr = swiotlb_alloc_buffer(dev, size, dma_handle, attrs);
- return vaddr;
+ return io_tlb_end != 0;
}
-void swiotlb_free(struct device *dev, size_t size, void *vaddr,
- dma_addr_t dma_addr, unsigned long attrs)
+#ifdef CONFIG_DEBUG_FS
+
+static int __init swiotlb_create_debugfs(void)
{
- if (!swiotlb_free_buffer(dev, size, dma_addr))
- dma_direct_free(dev, size, vaddr, dma_addr, attrs);
+ struct dentry *root;
+
+ root = debugfs_create_dir("swiotlb", NULL);
+ debugfs_create_ulong("io_tlb_nslabs", 0400, root, &io_tlb_nslabs);
+ debugfs_create_ulong("io_tlb_used", 0400, root, &io_tlb_used);
+ return 0;
}
-const struct dma_map_ops swiotlb_dma_ops = {
- .mapping_error = swiotlb_dma_mapping_error,
- .alloc = swiotlb_alloc,
- .free = swiotlb_free,
- .sync_single_for_cpu = swiotlb_sync_single_for_cpu,
- .sync_single_for_device = swiotlb_sync_single_for_device,
- .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
- .sync_sg_for_device = swiotlb_sync_sg_for_device,
- .map_sg = swiotlb_map_sg_attrs,
- .unmap_sg = swiotlb_unmap_sg_attrs,
- .map_page = swiotlb_map_page,
- .unmap_page = swiotlb_unmap_page,
- .dma_supported = dma_direct_supported,
-};
-EXPORT_SYMBOL(swiotlb_dma_ops);
+late_initcall(swiotlb_create_debugfs);
+
+#endif
--
Gitblit v1.6.2