Update Linux to v5.10.109

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz

Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index f99b79d..0ed0e1f 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -22,6 +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>
@@ -49,9 +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))
 
 /*
@@ -92,7 +90,7 @@ static unsigned int io_tlb_index;
  * 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
@@ -171,12 +169,20 @@ void swiotlb_print_info(void)
 		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);
+}
+
 /*
  * Early SWIOTLB allocation may be too early to allow an architecture to
  * perform the desired operations.  This function allows the architecture to
@@ -226,7 +232,7 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
 		      __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;
@@ -360,7 +366,7 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
 		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;
@@ -446,22 +452,120 @@ static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr,
 	}
 }
 
-phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
-				   dma_addr_t tbl_dma_addr,
-				   phys_addr_t orig_addr,
-				   size_t mapping_size,
-				   size_t alloc_size,
-				   enum dma_data_direction dir,
-				   unsigned long attrs)
+#define slot_addr(start, idx)	((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;
+
+	BUG_ON(!nslots);
+
+	/*
+	 * 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.
+	 */
+	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 {
+		if ((slot_addr(tbl_dma_addr, index) & iotlb_align_mask) !=
+		    (orig_addr & iotlb_align_mask)) {
+			index = wrap_index(index + 1);
+			continue;
+		}
+
+		/*
+		 * If we find a slot that indicates we have 'nslots' number of
+		 * contiguous buffers, we allocate the buffers from that slot
+		 * and mark the entries as '0' indicating unavailable.
+		 */
+		if (!iommu_is_span_boundary(index, nslots,
+					    nr_slots(tbl_dma_addr),
+					    max_slots)) {
+			if (io_tlb_list[index] >= nslots)
+				goto found;
+		}
+		index = wrap_index(index + stride);
+	} while (index != wrap);
+
+not_found:
+	spin_unlock_irqrestore(&io_tlb_lock, flags);
+	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;
-	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");
@@ -470,111 +574,32 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
 		pr_warn_once("Memory encryption is active and system is using DMA bounce buffers\n");
 
 	if (mapping_size > alloc_size) {
-		dev_warn_once(hwdev, "Invalid sizes (mapping: %zd bytes, alloc: %zd bytes)",
+		dev_warn_once(dev, "Invalid sizes (mapping: %zd bytes, alloc: %zd bytes)",
 			      mapping_size, alloc_size);
 		return (phys_addr_t)DMA_MAPPING_ERROR;
 	}
 
-	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(alloc_size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
-	if (alloc_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.
-	 */
-	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;
-
-	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 we find a slot that indicates we have 'nslots' number of
-		 * 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;
-		}
-		index += stride;
-		if (index >= io_tlb_nslabs)
-			index = 0;
-	} 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;
-found:
-	io_tlb_used += nslots;
-	spin_unlock_irqrestore(&io_tlb_lock, flags);
+	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);
+
+	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;
 }
 
@@ -586,8 +611,9 @@ 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];
 
 	/*
@@ -605,26 +631,29 @@ 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;
 	}
+
+	/*
+	 * 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);
 }
 
@@ -637,7 +666,9 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr,
 
 	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:
@@ -660,40 +691,42 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr,
 }
 
 /*
- * Create a swiotlb mapping for the buffer at @phys, and in case of DMAing
+ * Create a swiotlb mapping for the buffer at @paddr, and in case of DMAing
  * to the device copy the data into it as well.
  */
-bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr,
-		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)
 {
-	trace_swiotlb_bounced(dev, *dma_addr, size, swiotlb_force);
+	phys_addr_t swiotlb_addr;
+	dma_addr_t dma_addr;
 
-	if (unlikely(swiotlb_force == SWIOTLB_NO_FORCE)) {
-		dev_warn_ratelimited(dev,
-			"Cannot do DMA to address %pa\n", phys);
-		return false;
-	}
+	trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size,
+			      swiotlb_force);
 
-	/* Oh well, have to allocate and map a bounce buffer. */
-	*phys = swiotlb_tbl_map_single(dev, __phys_to_dma(dev, io_tlb_start),
-			*phys, size, size, dir, attrs);
-	if (*phys == (phys_addr_t)DMA_MAPPING_ERROR)
-		return false;
+	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 */
-	*dma_addr = __phys_to_dma(dev, *phys);
-	if (unlikely(!dma_capable(dev, *dma_addr, size))) {
-		swiotlb_tbl_unmap_single(dev, *phys, size, size, dir,
+	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);
-		return false;
+		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;
 	}
 
-	return true;
+	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)
 {
-	return ((size_t)1 << IO_TLB_SHIFT) * IO_TLB_SEGSIZE;
+	return ((size_t)IO_TLB_SIZE) * IO_TLB_SEGSIZE;
 }
 
 bool is_swiotlb_active(void)