1 files changed, 172 insertions, 54 deletions

diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c
index d5fc31f8345f..ffaded8f2df7 100644
--- a/drivers/pci/controller/dwc/pcie-designware-host.c
+++ b/drivers/pci/controller/dwc/pcie-designware-host.c
@@ -48,8 +48,9 @@ static struct irq_chip dw_pcie_msi_irq_chip = {
 };
 
 static struct msi_domain_info dw_pcie_msi_domain_info = {
-	.flags	= (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
-		   MSI_FLAG_PCI_MSIX | MSI_FLAG_MULTI_PCI_MSI),
+	.flags	= MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+		  MSI_FLAG_NO_AFFINITY | MSI_FLAG_PCI_MSIX |
+		  MSI_FLAG_MULTI_PCI_MSI,
 	.chip	= &dw_pcie_msi_irq_chip,
 };
 
@@ -116,12 +117,6 @@ static void dw_pci_setup_msi_msg(struct irq_data *d, struct msi_msg *msg)
 		(int)d->hwirq, msg->address_hi, msg->address_lo);
 }
 
-static int dw_pci_msi_set_affinity(struct irq_data *d,
-				   const struct cpumask *mask, bool force)
-{
-	return -EINVAL;
-}
-
 static void dw_pci_bottom_mask(struct irq_data *d)
 {
 	struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(d);
@@ -177,7 +172,6 @@ static struct irq_chip dw_pci_msi_bottom_irq_chip = {
 	.name = "DWPCI-MSI",
 	.irq_ack = dw_pci_bottom_ack,
 	.irq_compose_msi_msg = dw_pci_setup_msi_msg,
-	.irq_set_affinity = dw_pci_msi_set_affinity,
 	.irq_mask = dw_pci_bottom_mask,
 	.irq_unmask = dw_pci_bottom_unmask,
 };
@@ -328,7 +322,7 @@ static int dw_pcie_msi_host_init(struct dw_pcie_rp *pp)
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct device *dev = pci->dev;
 	struct platform_device *pdev = to_platform_device(dev);
-	u64 *msi_vaddr;
+	u64 *msi_vaddr = NULL;
 	int ret;
 	u32 ctrl, num_ctrls;
 
@@ -379,20 +373,51 @@ static int dw_pcie_msi_host_init(struct dw_pcie_rp *pp)
 	 * memory.
 	 */
 	ret = dma_set_coherent_mask(dev, DMA_BIT_MASK(32));
-	if (ret)
-		dev_warn(dev, "Failed to set DMA mask to 32-bit. Devices with only 32-bit MSI support may not work properly\n");
+	if (!ret)
+		msi_vaddr = dmam_alloc_coherent(dev, sizeof(u64), &pp->msi_data,
+						GFP_KERNEL);
 
-	msi_vaddr = dmam_alloc_coherent(dev, sizeof(u64), &pp->msi_data,
-					GFP_KERNEL);
 	if (!msi_vaddr) {
-		dev_err(dev, "Failed to alloc and map MSI data\n");
-		dw_pcie_free_msi(pp);
-		return -ENOMEM;
+		dev_warn(dev, "Failed to allocate 32-bit MSI address\n");
+		dma_set_coherent_mask(dev, DMA_BIT_MASK(64));
+		msi_vaddr = dmam_alloc_coherent(dev, sizeof(u64), &pp->msi_data,
+						GFP_KERNEL);
+		if (!msi_vaddr) {
+			dev_err(dev, "Failed to allocate MSI address\n");
+			dw_pcie_free_msi(pp);
+			return -ENOMEM;
+		}
 	}
 
 	return 0;
 }
 
+static void dw_pcie_host_request_msg_tlp_res(struct dw_pcie_rp *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct resource_entry *win;
+	struct resource *res;
+
+	win = resource_list_first_type(&pp->bridge->windows, IORESOURCE_MEM);
+	if (win) {
+		res = devm_kzalloc(pci->dev, sizeof(*res), GFP_KERNEL);
+		if (!res)
+			return;
+
+		/*
+		 * Allocate MSG TLP region of size 'region_align' at the end of
+		 * the host bridge window.
+		 */
+		res->start = win->res->end - pci->region_align + 1;
+		res->end = win->res->end;
+		res->name = "msg";
+		res->flags = win->res->flags | IORESOURCE_BUSY;
+
+		if (!devm_request_resource(pci->dev, win->res, res))
+			pp->msg_res = res;
+	}
+}
+
 int dw_pcie_host_init(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
@@ -411,18 +436,18 @@ int dw_pcie_host_init(struct dw_pcie_rp *pp)
 		return ret;
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "config");
-	if (res) {
-		pp->cfg0_size = resource_size(res);
-		pp->cfg0_base = res->start;
-
-		pp->va_cfg0_base = devm_pci_remap_cfg_resource(dev, res);
-		if (IS_ERR(pp->va_cfg0_base))
-			return PTR_ERR(pp->va_cfg0_base);
-	} else {
-		dev_err(dev, "Missing *config* reg space\n");
+	if (!res) {
+		dev_err(dev, "Missing \"config\" reg space\n");
 		return -ENODEV;
 	}
 
+	pp->cfg0_size = resource_size(res);
+	pp->cfg0_base = res->start;
+
+	pp->va_cfg0_base = devm_pci_remap_cfg_resource(dev, res);
+	if (IS_ERR(pp->va_cfg0_base))
+		return PTR_ERR(pp->va_cfg0_base);
+
 	bridge = devm_pci_alloc_host_bridge(dev, 0);
 	if (!bridge)
 		return -ENOMEM;
@@ -449,8 +474,8 @@ int dw_pcie_host_init(struct dw_pcie_rp *pp)
 
 	if (pci_msi_enabled()) {
 		pp->has_msi_ctrl = !(pp->ops->msi_init ||
-				     of_property_read_bool(np, "msi-parent") ||
-				     of_property_read_bool(np, "msi-map"));
+				     of_property_present(np, "msi-parent") ||
+				     of_property_present(np, "msi-map"));
 
 		/*
 		 * For the has_msi_ctrl case the default assignment is handled
@@ -479,6 +504,18 @@ int dw_pcie_host_init(struct dw_pcie_rp *pp)
 
 	dw_pcie_iatu_detect(pci);
 
+	/*
+	 * Allocate the resource for MSG TLP before programming the iATU
+	 * outbound window in dw_pcie_setup_rc(). Since the allocation depends
+	 * on the value of 'region_align', this has to be done after
+	 * dw_pcie_iatu_detect().
+	 *
+	 * Glue drivers need to set 'use_atu_msg' before dw_pcie_host_init() to
+	 * make use of the generic MSG TLP implementation.
+	 */
+	if (pp->use_atu_msg)
+		dw_pcie_host_request_msg_tlp_res(pp);
+
 	ret = dw_pcie_edma_detect(pci);
 	if (ret)
 		goto err_free_msi;
@@ -493,8 +530,14 @@ int dw_pcie_host_init(struct dw_pcie_rp *pp)
 			goto err_remove_edma;
 	}
 
-	/* Ignore errors, the link may come up later */
-	dw_pcie_wait_for_link(pci);
+	/*
+	 * Note: Skip the link up delay only when a Link Up IRQ is present.
+	 * If there is no Link Up IRQ, we should not bypass the delay
+	 * because that would require users to manually rescan for devices.
+	 */
+	if (!pp->use_linkup_irq)
+		/* Ignore errors, the link may come up later */
+		dw_pcie_wait_for_link(pci);
 
 	bridge->sysdata = pp;
 
@@ -549,6 +592,7 @@ static void __iomem *dw_pcie_other_conf_map_bus(struct pci_bus *bus,
 {
 	struct dw_pcie_rp *pp = bus->sysdata;
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct dw_pcie_ob_atu_cfg atu = { 0 };
 	int type, ret;
 	u32 busdev;
 
@@ -571,8 +615,12 @@ static void __iomem *dw_pcie_other_conf_map_bus(struct pci_bus *bus,
 	else
 		type = PCIE_ATU_TYPE_CFG1;
 
-	ret = dw_pcie_prog_outbound_atu(pci, 0, type, pp->cfg0_base, busdev,
-					pp->cfg0_size);
+	atu.type = type;
+	atu.cpu_addr = pp->cfg0_base;
+	atu.pci_addr = busdev;
+	atu.size = pp->cfg0_size;
+
+	ret = dw_pcie_prog_outbound_atu(pci, &atu);
 	if (ret)
 		return NULL;
 
@@ -584,6 +632,7 @@ static int dw_pcie_rd_other_conf(struct pci_bus *bus, unsigned int devfn,
 {
 	struct dw_pcie_rp *pp = bus->sysdata;
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct dw_pcie_ob_atu_cfg atu = { 0 };
 	int ret;
 
 	ret = pci_generic_config_read(bus, devfn, where, size, val);
@@ -591,9 +640,12 @@ static int dw_pcie_rd_other_conf(struct pci_bus *bus, unsigned int devfn,
 		return ret;
 
 	if (pp->cfg0_io_shared) {
-		ret = dw_pcie_prog_outbound_atu(pci, 0, PCIE_ATU_TYPE_IO,
-						pp->io_base, pp->io_bus_addr,
-						pp->io_size);
+		atu.type = PCIE_ATU_TYPE_IO;
+		atu.cpu_addr = pp->io_base;
+		atu.pci_addr = pp->io_bus_addr;
+		atu.size = pp->io_size;
+
+		ret = dw_pcie_prog_outbound_atu(pci, &atu);
 		if (ret)
 			return PCIBIOS_SET_FAILED;
 	}
@@ -606,6 +658,7 @@ static int dw_pcie_wr_other_conf(struct pci_bus *bus, unsigned int devfn,
 {
 	struct dw_pcie_rp *pp = bus->sysdata;
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct dw_pcie_ob_atu_cfg atu = { 0 };
 	int ret;
 
 	ret = pci_generic_config_write(bus, devfn, where, size, val);
@@ -613,9 +666,12 @@ static int dw_pcie_wr_other_conf(struct pci_bus *bus, unsigned int devfn,
 		return ret;
 
 	if (pp->cfg0_io_shared) {
-		ret = dw_pcie_prog_outbound_atu(pci, 0, PCIE_ATU_TYPE_IO,
-						pp->io_base, pp->io_bus_addr,
-						pp->io_size);
+		atu.type = PCIE_ATU_TYPE_IO;
+		atu.cpu_addr = pp->io_base;
+		atu.pci_addr = pp->io_bus_addr;
+		atu.size = pp->io_size;
+
+		ret = dw_pcie_prog_outbound_atu(pci, &atu);
 		if (ret)
 			return PCIBIOS_SET_FAILED;
 	}
@@ -650,6 +706,7 @@ static struct pci_ops dw_pcie_ops = {
 static int dw_pcie_iatu_setup(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct dw_pcie_ob_atu_cfg atu = { 0 };
 	struct resource_entry *entry;
 	int i, ret;
 
@@ -677,10 +734,19 @@ static int dw_pcie_iatu_setup(struct dw_pcie_rp *pp)
 		if (pci->num_ob_windows <= ++i)
 			break;
 
-		ret = dw_pcie_prog_outbound_atu(pci, i, PCIE_ATU_TYPE_MEM,
-						entry->res->start,
-						entry->res->start - entry->offset,
-						resource_size(entry->res));
+		atu.index = i;
+		atu.type = PCIE_ATU_TYPE_MEM;
+		atu.cpu_addr = entry->res->start;
+		atu.pci_addr = entry->res->start - entry->offset;
+
+		/* Adjust iATU size if MSG TLP region was allocated before */
+		if (pp->msg_res && pp->msg_res->parent == entry->res)
+			atu.size = resource_size(entry->res) -
+					resource_size(pp->msg_res);
+		else
+			atu.size = resource_size(entry->res);
+
+		ret = dw_pcie_prog_outbound_atu(pci, &atu);
 		if (ret) {
 			dev_err(pci->dev, "Failed to set MEM range %pr\n",
 				entry->res);
@@ -690,10 +756,13 @@ static int dw_pcie_iatu_setup(struct dw_pcie_rp *pp)
 
 	if (pp->io_size) {
 		if (pci->num_ob_windows > ++i) {
-			ret = dw_pcie_prog_outbound_atu(pci, i, PCIE_ATU_TYPE_IO,
-							pp->io_base,
-							pp->io_bus_addr,
-							pp->io_size);
+			atu.index = i;
+			atu.type = PCIE_ATU_TYPE_IO;
+			atu.cpu_addr = pp->io_base;
+			atu.pci_addr = pp->io_bus_addr;
+			atu.size = pp->io_size;
+
+			ret = dw_pcie_prog_outbound_atu(pci, &atu);
 			if (ret) {
 				dev_err(pci->dev, "Failed to set IO range %pr\n",
 					entry->res);
@@ -708,6 +777,8 @@ static int dw_pcie_iatu_setup(struct dw_pcie_rp *pp)
 		dev_warn(pci->dev, "Ranges exceed outbound iATU size (%d)\n",
 			 pci->num_ob_windows);
 
+	pp->msg_atu_index = i;
+
 	i = 0;
 	resource_list_for_each_entry(entry, &pp->bridge->dma_ranges) {
 		if (resource_type(entry->res) != IORESOURCE_MEM)
@@ -813,6 +884,42 @@ int dw_pcie_setup_rc(struct dw_pcie_rp *pp)
 }
 EXPORT_SYMBOL_GPL(dw_pcie_setup_rc);
 
+static int dw_pcie_pme_turn_off(struct dw_pcie *pci)
+{
+	struct dw_pcie_ob_atu_cfg atu = { 0 };
+	void __iomem *mem;
+	int ret;
+
+	if (pci->num_ob_windows <= pci->pp.msg_atu_index)
+		return -ENOSPC;
+
+	if (!pci->pp.msg_res)
+		return -ENOSPC;
+
+	atu.code = PCIE_MSG_CODE_PME_TURN_OFF;
+	atu.routing = PCIE_MSG_TYPE_R_BC;
+	atu.type = PCIE_ATU_TYPE_MSG;
+	atu.size = resource_size(pci->pp.msg_res);
+	atu.index = pci->pp.msg_atu_index;
+
+	atu.cpu_addr = pci->pp.msg_res->start;
+
+	ret = dw_pcie_prog_outbound_atu(pci, &atu);
+	if (ret)
+		return ret;
+
+	mem = ioremap(atu.cpu_addr, pci->region_align);
+	if (!mem)
+		return -ENOMEM;
+
+	/* A dummy write is converted to a Msg TLP */
+	writel(0, mem);
+
+	iounmap(mem);
+
+	return 0;
+}
+
 int dw_pcie_suspend_noirq(struct dw_pcie *pci)
 {
 	u8 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP);
@@ -826,22 +933,33 @@ int dw_pcie_suspend_noirq(struct dw_pcie *pci)
 	if (dw_pcie_readw_dbi(pci, offset + PCI_EXP_LNKCTL) & PCI_EXP_LNKCTL_ASPM_L1)
 		return 0;
 
-	if (dw_pcie_get_ltssm(pci) <= DW_PCIE_LTSSM_DETECT_ACT)
-		return 0;
-
-	if (!pci->pp.ops->pme_turn_off)
-		return 0;
-
-	pci->pp.ops->pme_turn_off(&pci->pp);
+	if (pci->pp.ops->pme_turn_off) {
+		pci->pp.ops->pme_turn_off(&pci->pp);
+	} else {
+		ret = dw_pcie_pme_turn_off(pci);
+		if (ret)
+			return ret;
+	}
 
-	ret = read_poll_timeout(dw_pcie_get_ltssm, val, val == DW_PCIE_LTSSM_L2_IDLE,
+	ret = read_poll_timeout(dw_pcie_get_ltssm, val,
+				val == DW_PCIE_LTSSM_L2_IDLE ||
+				val <= DW_PCIE_LTSSM_DETECT_WAIT,
 				PCIE_PME_TO_L2_TIMEOUT_US/10,
 				PCIE_PME_TO_L2_TIMEOUT_US, false, pci);
 	if (ret) {
+		/* Only log message when LTSSM isn't in DETECT or POLL */
 		dev_err(pci->dev, "Timeout waiting for L2 entry! LTSSM: 0x%x\n", val);
 		return ret;
 	}
 
+	/*
+	 * Per PCIe r6.0, sec 5.3.3.2.1, software should wait at least
+	 * 100ns after L2/L3 Ready before turning off refclock and
+	 * main power. This is harmless when no endpoint is connected.
+	 */
+	udelay(1);
+
+	dw_pcie_stop_link(pci);
 	if (pci->pp.ops->deinit)
 		pci->pp.ops->deinit(&pci->pp);