openwrt/target/linux/bcm27xx/patches-5.4/950-0206-PCI-brcmstb-Add-dma-range-mapping-for-inbound-traffi.patch

From d45590eb858ac7a2578d477791881ba7ffb1e615 Mon Sep 17 00:00:00 2001
From: Phil Elwell <phil@raspberrypi.org>
Date: Tue, 19 Feb 2019 22:06:59 +0000
Subject: [PATCH] PCI: brcmstb: Add dma-range mapping for inbound
 traffic

The Broadcom STB PCIe host controller is intimately related to the
memory subsystem.  This close relationship adds complexity to how cpu
system memory is mapped to PCIe memory.  Ideally, this mapping is an
identity mapping, or an identity mapping off by a constant.  Not so in
this case.

Consider the Broadcom reference board BCM97445LCC_4X8 which has 6 GB
of system memory.  Here is how the PCIe controller maps the
system memory to PCIe memory:

  memc0-a@[        0....3fffffff] <=> pci@[        0....3fffffff]
  memc0-b@[100000000...13fffffff] <=> pci@[ 40000000....7fffffff]
  memc1-a@[ 40000000....7fffffff] <=> pci@[ 80000000....bfffffff]
  memc1-b@[300000000...33fffffff] <=> pci@[ c0000000....ffffffff]
  memc2-a@[ 80000000....bfffffff] <=> pci@[100000000...13fffffff]
  memc2-b@[c00000000...c3fffffff] <=> pci@[140000000...17fffffff]

Although there are some "gaps" that can be added between the
individual mappings by software, the permutation of memory regions for
the most part is fixed by HW.  The solution of having something close
to an identity mapping is not possible.

The idea behind this HW design is that the same PCIe module can
act as an RC or EP, and if it acts as an EP it concatenates all
of system memory into a BAR so anything can be accessed.  Unfortunately,
when the PCIe block is in the role of an RC it also presents this
"BAR" to downstream PCIe devices, rather than offering an identity map
between its system memory and PCIe space.

Suppose that an endpoint driver allocs some DMA memory.  Suppose this
memory is located at 0x6000_0000, which is in the middle of memc1-a.
The driver wants a dma_addr_t value that it can pass on to the EP to
use.  Without doing any custom mapping, the EP will use this value for
DMA: the driver will get a dma_addr_t equal to 0x6000_0000.  But this
won't work; the device needs a dma_addr_t that reflects the PCIe space
address, namely 0xa000_0000.

So, essentially the solution to this problem must modify the
dma_addr_t returned by the DMA routines routines.  There are two
ways (I know of) of doing this:

(a) overriding/redefining the dma_to_phys() and phys_to_dma() calls
that are used by the dma_ops routines.  This is the approach of

	arch/mips/cavium-octeon/dma-octeon.c

In ARM and ARM64 these two routines are defiend in asm/dma-mapping.h
as static inline functions.

(b) Subscribe to a notifier that notifies when a device is added to a
bus.  When this happens, set_dma_ops() can be called for the device.
This method is mentioned in:

    http://lxr.free-electrons.com/source/drivers/of/platform.c?v=3.16#L152

where it says as a comment

    "In case if platform code need to use own special DMA
    configuration, it can use Platform bus notifier and
    handle BUS_NOTIFY_ADD_DEVICE event to fix up DMA
    configuration."

Solution (b) is what this commit does.  It uses its own set of
dma_ops which are wrappers around the arch_dma_ops.  The
wrappers translate the dma addresses before/after invoking
the arch_dma_ops, as appropriate.

Signed-off-by: Jim Quinlan <jim2101024@gmail.com>
---
 drivers/pci/controller/pcie-brcmstb.c | 420 +++++++++++++++++++++++++-
 1 file changed, 411 insertions(+), 9 deletions(-)

--- a/drivers/pci/controller/pcie-brcmstb.c
+++ b/drivers/pci/controller/pcie-brcmstb.c
@@ -4,6 +4,7 @@
 #include <linux/clk.h>
 #include <linux/compiler.h>
 #include <linux/delay.h>
+#include <linux/dma-mapping.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
@@ -319,11 +320,307 @@ static struct pci_ops brcm_pcie_ops = {
 	((val & ~reg##_##field##_MASK) | \
 	 (reg##_##field##_MASK & (field_val << reg##_##field##_SHIFT)))
 
+static const struct dma_map_ops *arch_dma_ops;
+static const struct dma_map_ops *brcm_dma_ops_ptr;
+static struct of_pci_range *dma_ranges;
+static int num_dma_ranges;
+
 static phys_addr_t scb_size[BRCM_MAX_SCB];
 static int num_memc;
 static int num_pcie;
 static DEFINE_MUTEX(brcm_pcie_lock);
 
+static dma_addr_t brcm_to_pci(dma_addr_t addr)
+{
+	struct of_pci_range *p;
+
+	if (!num_dma_ranges)
+		return addr;
+
+	for (p = dma_ranges; p < &dma_ranges[num_dma_ranges]; p++)
+		if (addr >= p->cpu_addr && addr < (p->cpu_addr + p->size))
+			return addr - p->cpu_addr + p->pci_addr;
+
+	return addr;
+}
+
+static dma_addr_t brcm_to_cpu(dma_addr_t addr)
+{
+	struct of_pci_range *p;
+
+	if (!num_dma_ranges)
+		return addr;
+
+	for (p = dma_ranges; p < &dma_ranges[num_dma_ranges]; p++)
+		if (addr >= p->pci_addr && addr < (p->pci_addr + p->size))
+			return addr - p->pci_addr + p->cpu_addr;
+
+	return addr;
+}
+
+static void *brcm_alloc(struct device *dev, size_t size, dma_addr_t *handle,
+			gfp_t gfp, unsigned long attrs)
+{
+	void *ret;
+
+	ret = arch_dma_ops->alloc(dev, size, handle, gfp, attrs);
+	if (ret)
+		*handle = brcm_to_pci(*handle);
+	return ret;
+}
+
+static void brcm_free(struct device *dev, size_t size, void *cpu_addr,
+		      dma_addr_t handle, unsigned long attrs)
+{
+	handle = brcm_to_cpu(handle);
+	arch_dma_ops->free(dev, size, cpu_addr, handle, attrs);
+}
+
+static int brcm_mmap(struct device *dev, struct vm_area_struct *vma,
+		     void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		     unsigned long attrs)
+{
+	dma_addr = brcm_to_cpu(dma_addr);
+	return arch_dma_ops->mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
+}
+
+static int brcm_get_sgtable(struct device *dev, struct sg_table *sgt,
+			    void *cpu_addr, dma_addr_t handle, size_t size,
+			    unsigned long attrs)
+{
+	handle = brcm_to_cpu(handle);
+	return arch_dma_ops->get_sgtable(dev, sgt, cpu_addr, handle, size,
+				       attrs);
+}
+
+static dma_addr_t brcm_map_page(struct device *dev, struct page *page,
+				unsigned long offset, size_t size,
+				enum dma_data_direction dir,
+				unsigned long attrs)
+{
+	return brcm_to_pci(arch_dma_ops->map_page(dev, page, offset, size,
+						  dir, attrs));
+}
+
+static void brcm_unmap_page(struct device *dev, dma_addr_t handle,
+			    size_t size, enum dma_data_direction dir,
+			    unsigned long attrs)
+{
+	handle = brcm_to_cpu(handle);
+	arch_dma_ops->unmap_page(dev, handle, size, dir, attrs);
+}
+
+static int brcm_map_sg(struct device *dev, struct scatterlist *sgl,
+		       int nents, enum dma_data_direction dir,
+		       unsigned long attrs)
+{
+	int i, j;
+	struct scatterlist *sg;
+
+	for_each_sg(sgl, sg, nents, i) {
+#ifdef CONFIG_NEED_SG_DMA_LENGTH
+		sg->dma_length = sg->length;
+#endif
+		sg->dma_address =
+			brcm_dma_ops_ptr->map_page(dev, sg_page(sg), sg->offset,
+						   sg->length, dir, attrs);
+		if (dma_mapping_error(dev, sg->dma_address))
+			goto bad_mapping;
+	}
+	return nents;
+
+bad_mapping:
+	for_each_sg(sgl, sg, i, j)
+		brcm_dma_ops_ptr->unmap_page(dev, sg_dma_address(sg),
+					     sg_dma_len(sg), dir, attrs);
+	return 0;
+}
+
+static void brcm_unmap_sg(struct device *dev,
+			  struct scatterlist *sgl, int nents,
+			  enum dma_data_direction dir,
+			  unsigned long attrs)
+{
+	int i;
+	struct scatterlist *sg;
+
+	for_each_sg(sgl, sg, nents, i)
+		brcm_dma_ops_ptr->unmap_page(dev, sg_dma_address(sg),
+					     sg_dma_len(sg), dir, attrs);
+}
+
+static void brcm_sync_single_for_cpu(struct device *dev,
+				     dma_addr_t handle, size_t size,
+				     enum dma_data_direction dir)
+{
+	handle = brcm_to_cpu(handle);
+	arch_dma_ops->sync_single_for_cpu(dev, handle, size, dir);
+}
+
+static void brcm_sync_single_for_device(struct device *dev,
+					dma_addr_t handle, size_t size,
+					enum dma_data_direction dir)
+{
+	handle = brcm_to_cpu(handle);
+	arch_dma_ops->sync_single_for_device(dev, handle, size, dir);
+}
+
+static dma_addr_t brcm_map_resource(struct device *dev, phys_addr_t phys,
+				    size_t size,
+				    enum dma_data_direction dir,
+				    unsigned long attrs)
+{
+	if (arch_dma_ops->map_resource)
+		return brcm_to_pci(arch_dma_ops->map_resource
+				   (dev, phys, size, dir, attrs));
+	return brcm_to_pci((dma_addr_t)phys);
+}
+
+static void brcm_unmap_resource(struct device *dev, dma_addr_t handle,
+				size_t size, enum dma_data_direction dir,
+				unsigned long attrs)
+{
+	if (arch_dma_ops->unmap_resource)
+		arch_dma_ops->unmap_resource(dev, brcm_to_cpu(handle), size,
+					     dir, attrs);
+}
+
+void brcm_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl,
+			  int nents, enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nents, i)
+		brcm_dma_ops_ptr->sync_single_for_cpu(dev, sg_dma_address(sg),
+						      sg->length, dir);
+}
+
+void brcm_sync_sg_for_device(struct device *dev, struct scatterlist *sgl,
+			     int nents, enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nents, i)
+		brcm_dma_ops_ptr->sync_single_for_device(dev,
+							 sg_dma_address(sg),
+							 sg->length, dir);
+}
+
+static int brcm_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	return arch_dma_ops->mapping_error(dev, dma_addr);
+}
+
+static int brcm_dma_supported(struct device *dev, u64 mask)
+{
+	if (num_dma_ranges) {
+		/*
+		 * It is our translated addresses that the EP will "see", so
+		 * we check all of the ranges for the largest possible value.
+		 */
+		int i;
+
+		for (i = 0; i < num_dma_ranges; i++)
+			if (dma_ranges[i].pci_addr + dma_ranges[i].size - 1
+			    > mask)
+				return 0;
+		return 1;
+	}
+
+	return arch_dma_ops->dma_supported(dev, mask);
+}
+
+#ifdef ARCH_HAS_DMA_GET_REQUIRED_MASK
+u64 brcm_get_required_mask)(struct device *dev)
+{
+	return arch_dma_ops->get_required_mask(dev);
+}
+#endif
+
+static const struct dma_map_ops brcm_dma_ops = {
+	.alloc			= brcm_alloc,
+	.free			= brcm_free,
+	.mmap			= brcm_mmap,
+	.get_sgtable		= brcm_get_sgtable,
+	.map_page		= brcm_map_page,
+	.unmap_page		= brcm_unmap_page,
+	.map_sg			= brcm_map_sg,
+	.unmap_sg		= brcm_unmap_sg,
+	.map_resource		= brcm_map_resource,
+	.unmap_resource		= brcm_unmap_resource,
+	.sync_single_for_cpu	= brcm_sync_single_for_cpu,
+	.sync_single_for_device	= brcm_sync_single_for_device,
+	.sync_sg_for_cpu	= brcm_sync_sg_for_cpu,
+	.sync_sg_for_device	= brcm_sync_sg_for_device,
+	.mapping_error		= brcm_mapping_error,
+	.dma_supported		= brcm_dma_supported,
+#ifdef ARCH_HAS_DMA_GET_REQUIRED_MASK
+	.get_required_mask	= brcm_get_required_mask,
+#endif
+};
+
+static void brcm_set_dma_ops(struct device *dev)
+{
+	int ret;
+
+	if (IS_ENABLED(CONFIG_ARM64)) {
+		/*
+		 * We are going to invoke get_dma_ops().  That
+		 * function, at this point in time, invokes
+		 * get_arch_dma_ops(), and for ARM64 that function
+		 * returns a pointer to dummy_dma_ops.  So then we'd
+		 * like to call arch_setup_dma_ops(), but that isn't
+		 * exported.  Instead, we call of_dma_configure(),
+		 * which is exported, and this calls
+		 * arch_setup_dma_ops().  Once we do this the call to
+		 * get_dma_ops() will work properly because
+		 * dev->dma_ops will be set.
+		 */
+		ret = of_dma_configure(dev, dev->of_node, true);
+		if (ret) {
+			dev_err(dev, "of_dma_configure() failed: %d\n", ret);
+			return;
+		}
+	}
+
+	arch_dma_ops = get_dma_ops(dev);
+	if (!arch_dma_ops) {
+		dev_err(dev, "failed to get arch_dma_ops\n");
+		return;
+	}
+
+	set_dma_ops(dev, &brcm_dma_ops);
+}
+
+static int brcmstb_platform_notifier(struct notifier_block *nb,
+				     unsigned long event, void *__dev)
+{
+	struct device *dev = __dev;
+
+	brcm_dma_ops_ptr = &brcm_dma_ops;
+	if (event != BUS_NOTIFY_ADD_DEVICE)
+		return NOTIFY_DONE;
+
+	brcm_set_dma_ops(dev);
+	return NOTIFY_OK;
+}
+
+static struct notifier_block brcmstb_platform_nb = {
+	.notifier_call = brcmstb_platform_notifier,
+};
+
+static int brcm_register_notifier(void)
+{
+	return bus_register_notifier(&pci_bus_type, &brcmstb_platform_nb);
+}
+
+static int brcm_unregister_notifier(void)
+{
+	return bus_unregister_notifier(&pci_bus_type, &brcmstb_platform_nb);
+}
+
 static u32 rd_fld(void __iomem *p, u32 mask, int shift)
 {
 	return (bcm_readl(p) & mask) >> shift;
@@ -597,9 +894,71 @@ static inline void brcm_pcie_perst_set(s
 		WR_FLD_RB(pcie->base, PCIE_MISC_PCIE_CTRL, PCIE_PERSTB, !val);
 }
 
+static int pci_dma_range_parser_init(struct of_pci_range_parser *parser,
+				     struct device_node *node)
+{
+	const int na = 3, ns = 2;
+	int rlen;
+
+	parser->node = node;
+	parser->pna = of_n_addr_cells(node);
+	parser->np = parser->pna + na + ns;
+
+	parser->range = of_get_property(node, "dma-ranges", &rlen);
+	if (!parser->range)
+		return -ENOENT;
+
+	parser->end = parser->range + rlen / sizeof(__be32);
+
+	return 0;
+}
+
+static int brcm_pcie_parse_map_dma_ranges(struct brcm_pcie *pcie)
+{
+	int i;
+	struct of_pci_range_parser parser;
+	struct device_node *dn = pcie->dn;
+
+	/*
+	 * Parse dma-ranges property if present.  If there are multiple
+	 * PCIe controllers, we only have to parse from one of them since
+	 * the others will have an identical mapping.
+	 */
+	if (!pci_dma_range_parser_init(&parser, dn)) {
+		unsigned int max_ranges
+			= (parser.end - parser.range) / parser.np;
+
+		dma_ranges = kcalloc(max_ranges, sizeof(struct of_pci_range),
+				     GFP_KERNEL);
+		if (!dma_ranges)
+			return -ENOMEM;
+
+		for (i = 0; of_pci_range_parser_one(&parser, dma_ranges + i);
+		     i++)
+			num_dma_ranges++;
+	}
+
+	for (i = 0, num_memc = 0; i < BRCM_MAX_SCB; i++) {
+		u64 size = brcmstb_memory_memc_size(i);
+
+		if (size == (u64)-1) {
+			dev_err(pcie->dev, "cannot get memc%d size", i);
+			return -EINVAL;
+		} else if (size) {
+			scb_size[i] = roundup_pow_of_two_64(size);
+			num_memc++;
+		} else {
+			break;
+		}
+	}
+
+	return 0;
+}
+
 static int brcm_pcie_add_controller(struct brcm_pcie *pcie)
 {
 	int i, ret = 0;
+	struct device *dev = pcie->dev;
 
 	mutex_lock(&brcm_pcie_lock);
 	if (num_pcie > 0) {
@@ -607,12 +966,21 @@ static int brcm_pcie_add_controller(stru
 		goto done;
 	}
 
+	ret = brcm_register_notifier();
+	if (ret) {
+		dev_err(dev, "failed to register pci bus notifier\n");
+		goto done;
+	}
+	ret = brcm_pcie_parse_map_dma_ranges(pcie);
+	if (ret)
+		goto done;
+
 	/* Determine num_memc and their sizes */
 	for (i = 0, num_memc = 0; i < BRCM_MAX_SCB; i++) {
 		u64 size = brcmstb_memory_memc_size(i);
 
 		if (size == (u64)-1) {
-			dev_err(pcie->dev, "cannot get memc%d size\n", i);
+			dev_err(dev, "cannot get memc%d size\n", i);
 			ret = -EINVAL;
 			goto done;
 		} else if (size) {
@@ -636,8 +1004,16 @@ done:
 static void brcm_pcie_remove_controller(struct brcm_pcie *pcie)
 {
 	mutex_lock(&brcm_pcie_lock);
-	if (--num_pcie == 0)
-		num_memc = 0;
+	if (--num_pcie > 0)
+		goto out;
+
+	if (brcm_unregister_notifier())
+		dev_err(pcie->dev, "failed to unregister pci bus notifier\n");
+	kfree(dma_ranges);
+	dma_ranges = NULL;
+	num_dma_ranges = 0;
+	num_memc = 0;
+out:
 	mutex_unlock(&brcm_pcie_lock);
 }
 
@@ -757,6 +1133,38 @@ static int brcm_pcie_setup(struct brcm_p
 	 */
 	rc_bar2_offset = 0;
 
+	if (dma_ranges) {
+		/*
+		 * The best-case scenario is to place the inbound
+		 * region in the first 4GB of pci-space, as some
+		 * legacy devices can only address 32bits.
+		 * We would also like to put the MSI under 4GB
+		 * as well, since some devices require a 32bit
+		 * MSI target address.
+		 */
+		if (total_mem_size <= 0xc0000000ULL &&
+		    rc_bar2_size <= 0x100000000ULL) {
+			rc_bar2_offset = 0;
+		} else {
+			/*
+			 * The system memory is 4GB or larger so we
+			 * cannot start the inbound region at location
+			 * 0 (since we have to allow some space for
+			 * outbound memory @ 3GB).  So instead we
+			 * start it at the 1x multiple of its size
+			 */
+			rc_bar2_offset = rc_bar2_size;
+		}
+
+	} else {
+		/*
+		 * Set simple configuration based on memory sizes
+		 * only.  We always start the viewport at address 0,
+		 * and set the MSI target address accordingly.
+		 */
+		rc_bar2_offset = 0;
+	}
+
 	tmp = lower_32_bits(rc_bar2_offset);
 	tmp = INSERT_FIELD(tmp, PCIE_MISC_RC_BAR2_CONFIG_LO, SIZE,
 			   encode_ibar_size(rc_bar2_size));
@@ -967,7 +1375,6 @@ static int brcm_pcie_probe(struct platfo
 	struct brcm_pcie *pcie;
 	struct resource *res;
 	void __iomem *base;
-	u32 tmp;
 	struct pci_host_bridge *bridge;
 	struct pci_bus *child;
 
@@ -984,11 +1391,6 @@ static int brcm_pcie_probe(struct platfo
 		return -EINVAL;
 	}
 
-	if (of_property_read_u32(dn, "dma-ranges", &tmp) == 0) {
-		dev_err(&pdev->dev, "cannot yet handle dma-ranges\n");
-		return -EINVAL;
-	}
-
 	data = of_id->data;
 	pcie->reg_offsets = data->offsets;
 	pcie->reg_field_info = data->reg_field_info;