1 files changed, 212 insertions, 72 deletions

diff --git a/drivers/pci/controller/dwc/pcie-designware.c b/drivers/pci/controller/dwc/pcie-designware.c
index 250cf7f40b85..97d76d3dc066 100644
--- a/drivers/pci/controller/dwc/pcie-designware.c
+++ b/drivers/pci/controller/dwc/pcie-designware.c
@@ -16,6 +16,8 @@
 #include <linux/gpio/consumer.h>
 #include <linux/ioport.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/pcie-dwc.h>
 #include <linux/platform_device.h>
 #include <linux/sizes.h>
 #include <linux/types.h>
@@ -112,6 +114,7 @@ int dw_pcie_get_resources(struct dw_pcie *pci)
 		pci->dbi_base = devm_pci_remap_cfg_resource(pci->dev, res);
 		if (IS_ERR(pci->dbi_base))
 			return PTR_ERR(pci->dbi_base);
+		pci->dbi_phys_addr = res->start;
 	}
 
 	/* DBI2 is mainly useful for the endpoint controller */
@@ -134,6 +137,7 @@ int dw_pcie_get_resources(struct dw_pcie *pci)
 			pci->atu_base = devm_ioremap_resource(pci->dev, res);
 			if (IS_ERR(pci->atu_base))
 				return PTR_ERR(pci->atu_base);
+			pci->atu_phys_addr = res->start;
 		} else {
 			pci->atu_base = pci->dbi_base + DEFAULT_DBI_ATU_OFFSET;
 		}
@@ -166,8 +170,8 @@ int dw_pcie_get_resources(struct dw_pcie *pci)
 			return ret;
 	}
 
-	if (pci->link_gen < 1)
-		pci->link_gen = of_pci_get_max_link_speed(np);
+	if (pci->max_link_speed < 1)
+		pci->max_link_speed = of_pci_get_max_link_speed(np);
 
 	of_property_read_u32(np, "num-lanes", &pci->num_lanes);
 
@@ -281,6 +285,51 @@ u16 dw_pcie_find_ext_capability(struct dw_pcie *pci, u8 cap)
 }
 EXPORT_SYMBOL_GPL(dw_pcie_find_ext_capability);
 
+static u16 __dw_pcie_find_vsec_capability(struct dw_pcie *pci, u16 vendor_id,
+					  u16 vsec_id)
+{
+	u16 vsec = 0;
+	u32 header;
+
+	if (vendor_id != dw_pcie_readw_dbi(pci, PCI_VENDOR_ID))
+		return 0;
+
+	while ((vsec = dw_pcie_find_next_ext_capability(pci, vsec,
+						       PCI_EXT_CAP_ID_VNDR))) {
+		header = dw_pcie_readl_dbi(pci, vsec + PCI_VNDR_HEADER);
+		if (PCI_VNDR_HEADER_ID(header) == vsec_id)
+			return vsec;
+	}
+
+	return 0;
+}
+
+static u16 dw_pcie_find_vsec_capability(struct dw_pcie *pci,
+					const struct dwc_pcie_vsec_id *vsec_ids)
+{
+	const struct dwc_pcie_vsec_id *vid;
+	u16 vsec;
+	u32 header;
+
+	for (vid = vsec_ids; vid->vendor_id; vid++) {
+		vsec = __dw_pcie_find_vsec_capability(pci, vid->vendor_id,
+						      vid->vsec_id);
+		if (vsec) {
+			header = dw_pcie_readl_dbi(pci, vsec + PCI_VNDR_HEADER);
+			if (PCI_VNDR_HEADER_REV(header) == vid->vsec_rev)
+				return vsec;
+		}
+	}
+
+	return 0;
+}
+
+u16 dw_pcie_find_rasdes_capability(struct dw_pcie *pci)
+{
+	return dw_pcie_find_vsec_capability(pci, dwc_pcie_rasdes_vsec_ids);
+}
+EXPORT_SYMBOL_GPL(dw_pcie_find_rasdes_capability);
+
 int dw_pcie_read(void __iomem *addr, int size, u32 *val)
 {
 	if (!IS_ALIGNED((uintptr_t)addr, size)) {
@@ -465,56 +514,58 @@ static inline u32 dw_pcie_enable_ecrc(u32 val)
 	return val | PCIE_ATU_TD;
 }
 
-static int __dw_pcie_prog_outbound_atu(struct dw_pcie *pci, u8 func_no,
-				       int index, int type, u64 cpu_addr,
-				       u64 pci_addr, u64 size)
+int dw_pcie_prog_outbound_atu(struct dw_pcie *pci,
+			      const struct dw_pcie_ob_atu_cfg *atu)
 {
+	u64 parent_bus_addr = atu->parent_bus_addr;
 	u32 retries, val;
 	u64 limit_addr;
 
-	if (pci->ops && pci->ops->cpu_addr_fixup)
-		cpu_addr = pci->ops->cpu_addr_fixup(pci, cpu_addr);
+	limit_addr = parent_bus_addr + atu->size - 1;
 
-	limit_addr = cpu_addr + size - 1;
-
-	if ((limit_addr & ~pci->region_limit) != (cpu_addr & ~pci->region_limit) ||
-	    !IS_ALIGNED(cpu_addr, pci->region_align) ||
-	    !IS_ALIGNED(pci_addr, pci->region_align) || !size) {
+	if ((limit_addr & ~pci->region_limit) != (parent_bus_addr & ~pci->region_limit) ||
+	    !IS_ALIGNED(parent_bus_addr, pci->region_align) ||
+	    !IS_ALIGNED(atu->pci_addr, pci->region_align) || !atu->size) {
 		return -EINVAL;
 	}
 
-	dw_pcie_writel_atu_ob(pci, index, PCIE_ATU_LOWER_BASE,
-			      lower_32_bits(cpu_addr));
-	dw_pcie_writel_atu_ob(pci, index, PCIE_ATU_UPPER_BASE,
-			      upper_32_bits(cpu_addr));
+	dw_pcie_writel_atu_ob(pci, atu->index, PCIE_ATU_LOWER_BASE,
+			      lower_32_bits(parent_bus_addr));
+	dw_pcie_writel_atu_ob(pci, atu->index, PCIE_ATU_UPPER_BASE,
+			      upper_32_bits(parent_bus_addr));
 
-	dw_pcie_writel_atu_ob(pci, index, PCIE_ATU_LIMIT,
+	dw_pcie_writel_atu_ob(pci, atu->index, PCIE_ATU_LIMIT,
 			      lower_32_bits(limit_addr));
 	if (dw_pcie_ver_is_ge(pci, 460A))
-		dw_pcie_writel_atu_ob(pci, index, PCIE_ATU_UPPER_LIMIT,
+		dw_pcie_writel_atu_ob(pci, atu->index, PCIE_ATU_UPPER_LIMIT,
 				      upper_32_bits(limit_addr));
 
-	dw_pcie_writel_atu_ob(pci, index, PCIE_ATU_LOWER_TARGET,
-			      lower_32_bits(pci_addr));
-	dw_pcie_writel_atu_ob(pci, index, PCIE_ATU_UPPER_TARGET,
-			      upper_32_bits(pci_addr));
+	dw_pcie_writel_atu_ob(pci, atu->index, PCIE_ATU_LOWER_TARGET,
+			      lower_32_bits(atu->pci_addr));
+	dw_pcie_writel_atu_ob(pci, atu->index, PCIE_ATU_UPPER_TARGET,
+			      upper_32_bits(atu->pci_addr));
 
-	val = type | PCIE_ATU_FUNC_NUM(func_no);
-	if (upper_32_bits(limit_addr) > upper_32_bits(cpu_addr) &&
+	val = atu->type | atu->routing | PCIE_ATU_FUNC_NUM(atu->func_no);
+	if (upper_32_bits(limit_addr) > upper_32_bits(parent_bus_addr) &&
 	    dw_pcie_ver_is_ge(pci, 460A))
 		val |= PCIE_ATU_INCREASE_REGION_SIZE;
 	if (dw_pcie_ver_is(pci, 490A))
 		val = dw_pcie_enable_ecrc(val);
-	dw_pcie_writel_atu_ob(pci, index, PCIE_ATU_REGION_CTRL1, val);
+	dw_pcie_writel_atu_ob(pci, atu->index, PCIE_ATU_REGION_CTRL1, val);
 
-	dw_pcie_writel_atu_ob(pci, index, PCIE_ATU_REGION_CTRL2, PCIE_ATU_ENABLE);
+	val = PCIE_ATU_ENABLE;
+	if (atu->type == PCIE_ATU_TYPE_MSG) {
+		/* The data-less messages only for now */
+		val |= PCIE_ATU_INHIBIT_PAYLOAD | atu->code;
+	}
+	dw_pcie_writel_atu_ob(pci, atu->index, PCIE_ATU_REGION_CTRL2, val);
 
 	/*
 	 * Make sure ATU enable takes effect before any subsequent config
 	 * and I/O accesses.
 	 */
 	for (retries = 0; retries < LINK_WAIT_MAX_IATU_RETRIES; retries++) {
-		val = dw_pcie_readl_atu_ob(pci, index, PCIE_ATU_REGION_CTRL2);
+		val = dw_pcie_readl_atu_ob(pci, atu->index, PCIE_ATU_REGION_CTRL2);
 		if (val & PCIE_ATU_ENABLE)
 			return 0;
 
@@ -526,21 +577,6 @@ static int __dw_pcie_prog_outbound_atu(struct dw_pcie *pci, u8 func_no,
 	return -ETIMEDOUT;
 }
 
-int dw_pcie_prog_outbound_atu(struct dw_pcie *pci, int index, int type,
-			      u64 cpu_addr, u64 pci_addr, u64 size)
-{
-	return __dw_pcie_prog_outbound_atu(pci, 0, index, type,
-					   cpu_addr, pci_addr, size);
-}
-
-int dw_pcie_prog_ep_outbound_atu(struct dw_pcie *pci, u8 func_no, int index,
-				 int type, u64 cpu_addr, u64 pci_addr,
-				 u64 size)
-{
-	return __dw_pcie_prog_outbound_atu(pci, func_no, index, type,
-					   cpu_addr, pci_addr, size);
-}
-
 static inline u32 dw_pcie_readl_atu_ib(struct dw_pcie *pci, u32 index, u32 reg)
 {
 	return dw_pcie_readl_atu(pci, PCIE_ATU_REGION_DIR_IB, index, reg);
@@ -553,13 +589,13 @@ static inline void dw_pcie_writel_atu_ib(struct dw_pcie *pci, u32 index, u32 reg
 }
 
 int dw_pcie_prog_inbound_atu(struct dw_pcie *pci, int index, int type,
-			     u64 cpu_addr, u64 pci_addr, u64 size)
+			     u64 parent_bus_addr, u64 pci_addr, u64 size)
 {
 	u64 limit_addr = pci_addr + size - 1;
 	u32 retries, val;
 
 	if ((limit_addr & ~pci->region_limit) != (pci_addr & ~pci->region_limit) ||
-	    !IS_ALIGNED(cpu_addr, pci->region_align) ||
+	    !IS_ALIGNED(parent_bus_addr, pci->region_align) ||
 	    !IS_ALIGNED(pci_addr, pci->region_align) || !size) {
 		return -EINVAL;
 	}
@@ -576,9 +612,9 @@ int dw_pcie_prog_inbound_atu(struct dw_pcie *pci, int index, int type,
 				      upper_32_bits(limit_addr));
 
 	dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_LOWER_TARGET,
-			      lower_32_bits(cpu_addr));
+			      lower_32_bits(parent_bus_addr));
 	dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_UPPER_TARGET,
-			      upper_32_bits(cpu_addr));
+			      upper_32_bits(parent_bus_addr));
 
 	val = type;
 	if (upper_32_bits(limit_addr) > upper_32_bits(pci_addr) &&
@@ -605,17 +641,18 @@ int dw_pcie_prog_inbound_atu(struct dw_pcie *pci, int index, int type,
 }
 
 int dw_pcie_prog_ep_inbound_atu(struct dw_pcie *pci, u8 func_no, int index,
-				int type, u64 cpu_addr, u8 bar)
+				int type, u64 parent_bus_addr, u8 bar, size_t size)
 {
 	u32 retries, val;
 
-	if (!IS_ALIGNED(cpu_addr, pci->region_align))
+	if (!IS_ALIGNED(parent_bus_addr, pci->region_align) ||
+	    !IS_ALIGNED(parent_bus_addr, size))
 		return -EINVAL;
 
 	dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_LOWER_TARGET,
-			      lower_32_bits(cpu_addr));
+			      lower_32_bits(parent_bus_addr));
 	dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_UPPER_TARGET,
-			      upper_32_bits(cpu_addr));
+			      upper_32_bits(parent_bus_addr));
 
 	dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_REGION_CTRL1, type |
 			      PCIE_ATU_FUNC_NUM(func_no));
@@ -655,7 +692,7 @@ int dw_pcie_wait_for_link(struct dw_pcie *pci)
 		if (dw_pcie_link_up(pci))
 			break;
 
-		usleep_range(LINK_WAIT_USLEEP_MIN, LINK_WAIT_USLEEP_MAX);
+		msleep(LINK_WAIT_SLEEP_MS);
 	}
 
 	if (retries >= LINK_WAIT_MAX_RETRIES) {
@@ -697,16 +734,27 @@ void dw_pcie_upconfig_setup(struct dw_pcie *pci)
 }
 EXPORT_SYMBOL_GPL(dw_pcie_upconfig_setup);
 
-static void dw_pcie_link_set_max_speed(struct dw_pcie *pci, u32 link_gen)
+static void dw_pcie_link_set_max_speed(struct dw_pcie *pci)
 {
 	u32 cap, ctrl2, link_speed;
 	u8 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP);
 
 	cap = dw_pcie_readl_dbi(pci, offset + PCI_EXP_LNKCAP);
+
+	/*
+	 * Even if the platform doesn't want to limit the maximum link speed,
+	 * just cache the hardware default value so that the vendor drivers can
+	 * use it to do any link specific configuration.
+	 */
+	if (pci->max_link_speed < 1) {
+		pci->max_link_speed = FIELD_GET(PCI_EXP_LNKCAP_SLS, cap);
+		return;
+	}
+
 	ctrl2 = dw_pcie_readl_dbi(pci, offset + PCI_EXP_LNKCTL2);
 	ctrl2 &= ~PCI_EXP_LNKCTL2_TLS;
 
-	switch (pcie_link_speed[link_gen]) {
+	switch (pcie_link_speed[pci->max_link_speed]) {
 	case PCIE_SPEED_2_5GT:
 		link_speed = PCI_EXP_LNKCTL2_TLS_2_5GT;
 		break;
@@ -880,30 +928,40 @@ static struct dw_edma_plat_ops dw_pcie_edma_ops = {
 	.irq_vector = dw_pcie_edma_irq_vector,
 };
 
-static int dw_pcie_edma_find_chip(struct dw_pcie *pci)
+static void dw_pcie_edma_init_data(struct dw_pcie *pci)
+{
+	pci->edma.dev = pci->dev;
+
+	if (!pci->edma.ops)
+		pci->edma.ops = &dw_pcie_edma_ops;
+
+	pci->edma.flags |= DW_EDMA_CHIP_LOCAL;
+}
+
+static int dw_pcie_edma_find_mf(struct dw_pcie *pci)
 {
 	u32 val;
 
 	/*
+	 * Bail out finding the mapping format if it is already set by the glue
+	 * driver. Also ensure that the edma.reg_base is pointing to a valid
+	 * memory region.
+	 */
+	if (pci->edma.mf != EDMA_MF_EDMA_LEGACY)
+		return pci->edma.reg_base ? 0 : -ENODEV;
+
+	/*
 	 * Indirect eDMA CSRs access has been completely removed since v5.40a
 	 * thus no space is now reserved for the eDMA channels viewport and
 	 * former DMA CTRL register is no longer fixed to FFs.
-	 *
-	 * Note that Renesas R-Car S4-8's PCIe controllers for unknown reason
-	 * have zeros in the eDMA CTRL register even though the HW-manual
-	 * explicitly states there must FFs if the unrolled mapping is enabled.
-	 * For such cases the low-level drivers are supposed to manually
-	 * activate the unrolled mapping to bypass the auto-detection procedure.
 	 */
-	if (dw_pcie_ver_is_ge(pci, 540A) || dw_pcie_cap_is(pci, EDMA_UNROLL))
+	if (dw_pcie_ver_is_ge(pci, 540A))
 		val = 0xFFFFFFFF;
 	else
 		val = dw_pcie_readl_dbi(pci, PCIE_DMA_VIEWPORT_BASE + PCIE_DMA_CTRL);
 
 	if (val == 0xFFFFFFFF && pci->edma.reg_base) {
 		pci->edma.mf = EDMA_MF_EDMA_UNROLL;
-
-		val = dw_pcie_readl_dma(pci, PCIE_DMA_CTRL);
 	} else if (val != 0xFFFFFFFF) {
 		pci->edma.mf = EDMA_MF_EDMA_LEGACY;
 
@@ -912,15 +970,25 @@ static int dw_pcie_edma_find_chip(struct dw_pcie *pci)
 		return -ENODEV;
 	}
 
-	pci->edma.dev = pci->dev;
+	return 0;
+}
 
-	if (!pci->edma.ops)
-		pci->edma.ops = &dw_pcie_edma_ops;
+static int dw_pcie_edma_find_channels(struct dw_pcie *pci)
+{
+	u32 val;
 
-	pci->edma.flags |= DW_EDMA_CHIP_LOCAL;
+	/*
+	 * Autodetect the read/write channels count only for non-HDMA platforms.
+	 * HDMA platforms with native CSR mapping doesn't support autodetect,
+	 * so the glue drivers should've passed the valid count already. If not,
+	 * the below sanity check will catch it.
+	 */
+	if (pci->edma.mf != EDMA_MF_HDMA_NATIVE) {
+		val = dw_pcie_readl_dma(pci, PCIE_DMA_CTRL);
 
-	pci->edma.ll_wr_cnt = FIELD_GET(PCIE_DMA_NUM_WR_CHAN, val);
-	pci->edma.ll_rd_cnt = FIELD_GET(PCIE_DMA_NUM_RD_CHAN, val);
+		pci->edma.ll_wr_cnt = FIELD_GET(PCIE_DMA_NUM_WR_CHAN, val);
+		pci->edma.ll_rd_cnt = FIELD_GET(PCIE_DMA_NUM_RD_CHAN, val);
+	}
 
 	/* Sanity check the channels count if the mapping was incorrect */
 	if (!pci->edma.ll_wr_cnt || pci->edma.ll_wr_cnt > EDMA_MAX_WR_CH ||
@@ -930,11 +998,24 @@ static int dw_pcie_edma_find_chip(struct dw_pcie *pci)
 	return 0;
 }
 
+static int dw_pcie_edma_find_chip(struct dw_pcie *pci)
+{
+	int ret;
+
+	dw_pcie_edma_init_data(pci);
+
+	ret = dw_pcie_edma_find_mf(pci);
+	if (ret)
+		return ret;
+
+	return dw_pcie_edma_find_channels(pci);
+}
+
 static int dw_pcie_edma_irq_verify(struct dw_pcie *pci)
 {
 	struct platform_device *pdev = to_platform_device(pci->dev);
 	u16 ch_cnt = pci->edma.ll_wr_cnt + pci->edma.ll_rd_cnt;
-	char name[6];
+	char name[15];
 	int ret;
 
 	if (pci->edma.nr_irqs == 1)
@@ -1035,8 +1116,7 @@ void dw_pcie_setup(struct dw_pcie *pci)
 {
 	u32 val;
 
-	if (pci->link_gen > 0)
-		dw_pcie_link_set_max_speed(pci, pci->link_gen);
+	dw_pcie_link_set_max_speed(pci);
 
 	/* Configure Gen1 N_FTS */
 	if (pci->n_fts[0]) {
@@ -1069,3 +1149,63 @@ void dw_pcie_setup(struct dw_pcie *pci)
 
 	dw_pcie_link_set_max_link_width(pci, pci->num_lanes);
 }
+
+resource_size_t dw_pcie_parent_bus_offset(struct dw_pcie *pci,
+					  const char *reg_name,
+					  resource_size_t cpu_phys_addr)
+{
+	struct device *dev = pci->dev;
+	struct device_node *np = dev->of_node;
+	int index;
+	u64 reg_addr, fixup_addr;
+	u64 (*fixup)(struct dw_pcie *pcie, u64 cpu_addr);
+
+	/* Look up reg_name address on parent bus */
+	index = of_property_match_string(np, "reg-names", reg_name);
+
+	if (index < 0) {
+		dev_err(dev, "No %s in devicetree \"reg\" property\n", reg_name);
+		return 0;
+	}
+
+	of_property_read_reg(np, index, &reg_addr, NULL);
+
+	fixup = pci->ops ? pci->ops->cpu_addr_fixup : NULL;
+	if (fixup) {
+		fixup_addr = fixup(pci, cpu_phys_addr);
+		if (reg_addr == fixup_addr) {
+			dev_info(dev, "%s reg[%d] %#010llx == %#010llx == fixup(cpu %#010llx); %ps is redundant with this devicetree\n",
+				 reg_name, index, reg_addr, fixup_addr,
+				 (unsigned long long) cpu_phys_addr, fixup);
+		} else {
+			dev_warn(dev, "%s reg[%d] %#010llx != %#010llx == fixup(cpu %#010llx); devicetree is broken\n",
+				 reg_name, index, reg_addr, fixup_addr,
+				 (unsigned long long) cpu_phys_addr);
+			reg_addr = fixup_addr;
+		}
+
+		return cpu_phys_addr - reg_addr;
+	}
+
+	if (pci->use_parent_dt_ranges) {
+
+		/*
+		 * This platform once had a fixup, presumably because it
+		 * translates between CPU and PCI controller addresses.
+		 * Log a note if devicetree didn't describe a translation.
+		 */
+		if (reg_addr == cpu_phys_addr)
+			dev_info(dev, "%s reg[%d] %#010llx == cpu %#010llx\n; no fixup was ever needed for this devicetree\n",
+				 reg_name, index, reg_addr,
+				 (unsigned long long) cpu_phys_addr);
+	} else {
+		if (reg_addr != cpu_phys_addr) {
+			dev_warn(dev, "%s reg[%d] %#010llx != cpu %#010llx; no fixup and devicetree \"ranges\" is broken, assuming no translation\n",
+				 reg_name, index, reg_addr,
+				 (unsigned long long) cpu_phys_addr);
+			return 0;
+		}
+	}
+
+	return cpu_phys_addr - reg_addr;
+}