Update Linux to v5.10.157

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.157.tar.xz

Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
Change-Id: I7b30d9e98d8c465d6b44de8e7433b4a40b3289ba
diff --git a/drivers/pci/controller/cadence/pcie-cadence-ep.c b/drivers/pci/controller/cadence/pcie-cadence-ep.c
index 1af1447..4c5e634 100644
--- a/drivers/pci/controller/cadence/pcie-cadence-ep.c
+++ b/drivers/pci/controller/cadence/pcie-cadence-ep.c
@@ -154,8 +154,7 @@
 	struct cdns_pcie *pcie = &ep->pcie;
 	u32 r;
 
-	r = find_first_zero_bit(&ep->ob_region_map,
-				sizeof(ep->ob_region_map) * BITS_PER_LONG);
+	r = find_first_zero_bit(&ep->ob_region_map, BITS_PER_LONG);
 	if (r >= ep->max_regions - 1) {
 		dev_err(&epc->dev, "no free outbound region\n");
 		return -EINVAL;
diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c
index 5cf1ef1..ceb4815 100644
--- a/drivers/pci/controller/dwc/pci-imx6.c
+++ b/drivers/pci/controller/dwc/pci-imx6.c
@@ -401,6 +401,11 @@
 			dev_err(dev, "failed to disable vpcie regulator: %d\n",
 				ret);
 	}
+
+	/* Some boards don't have PCIe reset GPIO. */
+	if (gpio_is_valid(imx6_pcie->reset_gpio))
+		gpio_set_value_cansleep(imx6_pcie->reset_gpio,
+					imx6_pcie->gpio_active_high);
 }
 
 static unsigned int imx6_pcie_grp_offset(const struct imx6_pcie *imx6_pcie)
@@ -523,15 +528,6 @@
 	/* allow the clocks to stabilize */
 	usleep_range(200, 500);
 
-	/* Some boards don't have PCIe reset GPIO. */
-	if (gpio_is_valid(imx6_pcie->reset_gpio)) {
-		gpio_set_value_cansleep(imx6_pcie->reset_gpio,
-					imx6_pcie->gpio_active_high);
-		msleep(100);
-		gpio_set_value_cansleep(imx6_pcie->reset_gpio,
-					!imx6_pcie->gpio_active_high);
-	}
-
 	switch (imx6_pcie->drvdata->variant) {
 	case IMX8MQ:
 		reset_control_deassert(imx6_pcie->pciephy_reset);
@@ -574,6 +570,15 @@
 		break;
 	}
 
+	/* Some boards don't have PCIe reset GPIO. */
+	if (gpio_is_valid(imx6_pcie->reset_gpio)) {
+		msleep(100);
+		gpio_set_value_cansleep(imx6_pcie->reset_gpio,
+					!imx6_pcie->gpio_active_high);
+		/* Wait for 100ms after PERST# deassertion (PCIe r5.0, 6.6.1) */
+		msleep(100);
+	}
+
 	return;
 
 err_ref_clk:
diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index ad7da4e..95ed719 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -773,8 +773,9 @@
 	ep->msi_mem = pci_epc_mem_alloc_addr(epc, &ep->msi_mem_phys,
 					     epc->mem->window.page_size);
 	if (!ep->msi_mem) {
+		ret = -ENOMEM;
 		dev_err(dev, "Failed to reserve memory for MSI/MSI-X\n");
-		return -ENOMEM;
+		goto err_exit_epc_mem;
 	}
 
 	if (ep->ops->get_features) {
@@ -783,6 +784,19 @@
 			return 0;
 	}
 
-	return dw_pcie_ep_init_complete(ep);
+	ret = dw_pcie_ep_init_complete(ep);
+	if (ret)
+		goto err_free_epc_mem;
+
+	return 0;
+
+err_free_epc_mem:
+	pci_epc_mem_free_addr(epc, ep->msi_mem_phys, ep->msi_mem,
+			      epc->mem->window.page_size);
+
+err_exit_epc_mem:
+	pci_epc_mem_exit(epc);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(dw_pcie_ep_init);
diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c
index 44c2a65..42d8116 100644
--- a/drivers/pci/controller/dwc/pcie-designware-host.c
+++ b/drivers/pci/controller/dwc/pcie-designware-host.c
@@ -392,7 +392,8 @@
 						      sizeof(pp->msi_msg),
 						      DMA_FROM_DEVICE,
 						      DMA_ATTR_SKIP_CPU_SYNC);
-			if (dma_mapping_error(pci->dev, pp->msi_data)) {
+			ret = dma_mapping_error(pci->dev, pp->msi_data);
+			if (ret) {
 				dev_err(pci->dev, "Failed to map MSI data\n");
 				pp->msi_data = 0;
 				goto err_free_msi;
diff --git a/drivers/pci/controller/dwc/pcie-designware.c b/drivers/pci/controller/dwc/pcie-designware.c
index c2dea8f..2b74ff8 100644
--- a/drivers/pci/controller/dwc/pcie-designware.c
+++ b/drivers/pci/controller/dwc/pcie-designware.c
@@ -439,7 +439,7 @@
 void dw_pcie_disable_atu(struct dw_pcie *pci, int index,
 			 enum dw_pcie_region_type type)
 {
-	int region;
+	u32 region;
 
 	switch (type) {
 	case DW_PCIE_REGION_INBOUND:
@@ -452,8 +452,18 @@
 		return;
 	}
 
-	dw_pcie_writel_dbi(pci, PCIE_ATU_VIEWPORT, region | index);
-	dw_pcie_writel_dbi(pci, PCIE_ATU_CR2, ~(u32)PCIE_ATU_ENABLE);
+	if (pci->iatu_unroll_enabled) {
+		if (region == PCIE_ATU_REGION_INBOUND) {
+			dw_pcie_writel_ib_unroll(pci, index, PCIE_ATU_UNR_REGION_CTRL2,
+						 ~(u32)PCIE_ATU_ENABLE);
+		} else {
+			dw_pcie_writel_ob_unroll(pci, index, PCIE_ATU_UNR_REGION_CTRL2,
+						 ~(u32)PCIE_ATU_ENABLE);
+		}
+	} else {
+		dw_pcie_writel_dbi(pci, PCIE_ATU_VIEWPORT, region | index);
+		dw_pcie_writel_dbi(pci, PCIE_ATU_CR2, ~(u32)PCIE_ATU_ENABLE);
+	}
 }
 
 int dw_pcie_wait_for_link(struct dw_pcie *pci)
@@ -588,6 +598,13 @@
 	val |= PORT_LINK_DLL_LINK_EN;
 	dw_pcie_writel_dbi(pci, PCIE_PORT_LINK_CONTROL, val);
 
+	if (of_property_read_bool(np, "snps,enable-cdm-check")) {
+		val = dw_pcie_readl_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS);
+		val |= PCIE_PL_CHK_REG_CHK_REG_CONTINUOUS |
+		       PCIE_PL_CHK_REG_CHK_REG_START;
+		dw_pcie_writel_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS, val);
+	}
+
 	of_property_read_u32(np, "num-lanes", &pci->num_lanes);
 	if (!pci->num_lanes) {
 		dev_dbg(pci->dev, "Using h/w default number of lanes\n");
@@ -634,11 +651,4 @@
 		break;
 	}
 	dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, val);
-
-	if (of_property_read_bool(np, "snps,enable-cdm-check")) {
-		val = dw_pcie_readl_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS);
-		val |= PCIE_PL_CHK_REG_CHK_REG_CONTINUOUS |
-		       PCIE_PL_CHK_REG_CHK_REG_START;
-		dw_pcie_writel_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS, val);
-	}
 }
diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
index 557554f..5fbd809 100644
--- a/drivers/pci/controller/dwc/pcie-qcom.c
+++ b/drivers/pci/controller/dwc/pcie-qcom.c
@@ -320,8 +320,6 @@
 	reset_control_assert(res->ext_reset);
 	reset_control_assert(res->phy_reset);
 
-	writel(1, pcie->parf + PCIE20_PARF_PHY_CTRL);
-
 	ret = regulator_bulk_enable(ARRAY_SIZE(res->supplies), res->supplies);
 	if (ret < 0) {
 		dev_err(dev, "cannot enable regulators\n");
@@ -364,15 +362,15 @@
 		goto err_deassert_axi;
 	}
 
-	ret = clk_bulk_prepare_enable(ARRAY_SIZE(res->clks), res->clks);
-	if (ret)
-		goto err_clks;
-
 	/* enable PCIe clocks and resets */
 	val = readl(pcie->parf + PCIE20_PARF_PHY_CTRL);
 	val &= ~BIT(0);
 	writel(val, pcie->parf + PCIE20_PARF_PHY_CTRL);
 
+	ret = clk_bulk_prepare_enable(ARRAY_SIZE(res->clks), res->clks);
+	if (ret)
+		goto err_clks;
+
 	if (of_device_is_compatible(node, "qcom,pcie-ipq8064") ||
 	    of_device_is_compatible(node, "qcom,pcie-ipq8064-v2")) {
 		writel(PCS_DEEMPH_TX_DEEMPH_GEN1(24) |
@@ -1192,12 +1190,6 @@
 		goto err_disable_clocks;
 	}
 
-	ret = clk_prepare_enable(res->pipe_clk);
-	if (ret) {
-		dev_err(dev, "cannot prepare/enable pipe clock\n");
-		goto err_disable_clocks;
-	}
-
 	/* configure PCIe to RC mode */
 	writel(DEVICE_TYPE_RC, pcie->parf + PCIE20_PARF_DEVICE_TYPE);
 
@@ -1443,22 +1435,21 @@
 	}
 
 	ret = phy_init(pcie->phy);
-	if (ret) {
-		pm_runtime_disable(&pdev->dev);
+	if (ret)
 		goto err_pm_runtime_put;
-	}
 
 	platform_set_drvdata(pdev, pcie);
 
 	ret = dw_pcie_host_init(pp);
 	if (ret) {
 		dev_err(dev, "cannot initialize host\n");
-		pm_runtime_disable(&pdev->dev);
-		goto err_pm_runtime_put;
+		goto err_phy_exit;
 	}
 
 	return 0;
 
+err_phy_exit:
+	phy_exit(pcie->phy);
 err_pm_runtime_put:
 	pm_runtime_put(dev);
 	pm_runtime_disable(dev);
diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c
index a5b677e..1222f57 100644
--- a/drivers/pci/controller/dwc/pcie-tegra194.c
+++ b/drivers/pci/controller/dwc/pcie-tegra194.c
@@ -370,15 +370,14 @@
 	struct tegra_pcie_dw *pcie = arg;
 	struct dw_pcie *pci = &pcie->pci;
 	struct pcie_port *pp = &pci->pp;
-	u32 val, tmp;
+	u32 val, status_l0, status_l1;
 	u16 val_w;
 
-	val = appl_readl(pcie, APPL_INTR_STATUS_L0);
-	if (val & APPL_INTR_STATUS_L0_LINK_STATE_INT) {
-		val = appl_readl(pcie, APPL_INTR_STATUS_L1_0_0);
-		if (val & APPL_INTR_STATUS_L1_0_0_LINK_REQ_RST_NOT_CHGED) {
-			appl_writel(pcie, val, APPL_INTR_STATUS_L1_0_0);
-
+	status_l0 = appl_readl(pcie, APPL_INTR_STATUS_L0);
+	if (status_l0 & APPL_INTR_STATUS_L0_LINK_STATE_INT) {
+		status_l1 = appl_readl(pcie, APPL_INTR_STATUS_L1_0_0);
+		appl_writel(pcie, status_l1, APPL_INTR_STATUS_L1_0_0);
+		if (status_l1 & APPL_INTR_STATUS_L1_0_0_LINK_REQ_RST_NOT_CHGED) {
 			/* SBR & Surprise Link Down WAR */
 			val = appl_readl(pcie, APPL_CAR_RESET_OVRD);
 			val &= ~APPL_CAR_RESET_OVRD_CYA_OVERRIDE_CORE_RST_N;
@@ -394,15 +393,15 @@
 		}
 	}
 
-	if (val & APPL_INTR_STATUS_L0_INT_INT) {
-		val = appl_readl(pcie, APPL_INTR_STATUS_L1_8_0);
-		if (val & APPL_INTR_STATUS_L1_8_0_AUTO_BW_INT_STS) {
+	if (status_l0 & APPL_INTR_STATUS_L0_INT_INT) {
+		status_l1 = appl_readl(pcie, APPL_INTR_STATUS_L1_8_0);
+		if (status_l1 & APPL_INTR_STATUS_L1_8_0_AUTO_BW_INT_STS) {
 			appl_writel(pcie,
 				    APPL_INTR_STATUS_L1_8_0_AUTO_BW_INT_STS,
 				    APPL_INTR_STATUS_L1_8_0);
 			apply_bad_link_workaround(pp);
 		}
-		if (val & APPL_INTR_STATUS_L1_8_0_BW_MGT_INT_STS) {
+		if (status_l1 & APPL_INTR_STATUS_L1_8_0_BW_MGT_INT_STS) {
 			appl_writel(pcie,
 				    APPL_INTR_STATUS_L1_8_0_BW_MGT_INT_STS,
 				    APPL_INTR_STATUS_L1_8_0);
@@ -414,25 +413,24 @@
 		}
 	}
 
-	val = appl_readl(pcie, APPL_INTR_STATUS_L0);
-	if (val & APPL_INTR_STATUS_L0_CDM_REG_CHK_INT) {
-		val = appl_readl(pcie, APPL_INTR_STATUS_L1_18);
-		tmp = dw_pcie_readl_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS);
-		if (val & APPL_INTR_STATUS_L1_18_CDM_REG_CHK_CMPLT) {
+	if (status_l0 & APPL_INTR_STATUS_L0_CDM_REG_CHK_INT) {
+		status_l1 = appl_readl(pcie, APPL_INTR_STATUS_L1_18);
+		val = dw_pcie_readl_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS);
+		if (status_l1 & APPL_INTR_STATUS_L1_18_CDM_REG_CHK_CMPLT) {
 			dev_info(pci->dev, "CDM check complete\n");
-			tmp |= PCIE_PL_CHK_REG_CHK_REG_COMPLETE;
+			val |= PCIE_PL_CHK_REG_CHK_REG_COMPLETE;
 		}
-		if (val & APPL_INTR_STATUS_L1_18_CDM_REG_CHK_CMP_ERR) {
+		if (status_l1 & APPL_INTR_STATUS_L1_18_CDM_REG_CHK_CMP_ERR) {
 			dev_err(pci->dev, "CDM comparison mismatch\n");
-			tmp |= PCIE_PL_CHK_REG_CHK_REG_COMPARISON_ERROR;
+			val |= PCIE_PL_CHK_REG_CHK_REG_COMPARISON_ERROR;
 		}
-		if (val & APPL_INTR_STATUS_L1_18_CDM_REG_CHK_LOGIC_ERR) {
+		if (status_l1 & APPL_INTR_STATUS_L1_18_CDM_REG_CHK_LOGIC_ERR) {
 			dev_err(pci->dev, "CDM Logic error\n");
-			tmp |= PCIE_PL_CHK_REG_CHK_REG_LOGIC_ERROR;
+			val |= PCIE_PL_CHK_REG_CHK_REG_LOGIC_ERROR;
 		}
-		dw_pcie_writel_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS, tmp);
-		tmp = dw_pcie_readl_dbi(pci, PCIE_PL_CHK_REG_ERR_ADDR);
-		dev_err(pci->dev, "CDM Error Address Offset = 0x%08X\n", tmp);
+		dw_pcie_writel_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS, val);
+		val = dw_pcie_readl_dbi(pci, PCIE_PL_CHK_REG_ERR_ADDR);
+		dev_err(pci->dev, "CDM Error Address Offset = 0x%08X\n", val);
 	}
 
 	return IRQ_HANDLED;
@@ -965,7 +963,7 @@
 		offset = dw_pcie_find_ext_capability(pci, PCI_EXT_CAP_ID_DLF);
 		val = dw_pcie_readl_dbi(pci, offset + PCI_DLF_CAP);
 		val &= ~PCI_DLF_EXCHANGE_ENABLE;
-		dw_pcie_writel_dbi(pci, offset, val);
+		dw_pcie_writel_dbi(pci, offset + PCI_DLF_CAP, val);
 
 		tegra_pcie_prepare_host(pp);
 
@@ -1970,6 +1968,7 @@
 	if (ret) {
 		dev_err(dev, "Failed to initialize DWC Endpoint subsystem: %d\n",
 			ret);
+		pm_runtime_disable(dev);
 		return ret;
 	}
 
diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c
index f30144c..0c603e0 100644
--- a/drivers/pci/controller/pci-aardvark.c
+++ b/drivers/pci/controller/pci-aardvark.c
@@ -114,6 +114,7 @@
 #define PCIE_MSI_ADDR_HIGH_REG			(CONTROL_BASE_ADDR + 0x54)
 #define PCIE_MSI_STATUS_REG			(CONTROL_BASE_ADDR + 0x58)
 #define PCIE_MSI_MASK_REG			(CONTROL_BASE_ADDR + 0x5C)
+#define     PCIE_MSI_ALL_MASK			GENMASK(31, 0)
 #define PCIE_MSI_PAYLOAD_REG			(CONTROL_BASE_ADDR + 0x9C)
 #define     PCIE_MSI_DATA_MASK			GENMASK(15, 0)
 
@@ -577,6 +578,7 @@
 	advk_writel(pcie, reg, PCIE_CORE_CTRL2_REG);
 
 	/* Clear all interrupts */
+	advk_writel(pcie, PCIE_MSI_ALL_MASK, PCIE_MSI_STATUS_REG);
 	advk_writel(pcie, PCIE_ISR0_ALL_MASK, PCIE_ISR0_REG);
 	advk_writel(pcie, PCIE_ISR1_ALL_MASK, PCIE_ISR1_REG);
 	advk_writel(pcie, PCIE_IRQ_ALL_MASK, HOST_CTRL_INT_STATUS_REG);
@@ -589,7 +591,7 @@
 	advk_writel(pcie, PCIE_ISR1_ALL_MASK, PCIE_ISR1_MASK_REG);
 
 	/* Unmask all MSIs */
-	advk_writel(pcie, 0, PCIE_MSI_MASK_REG);
+	advk_writel(pcie, ~(u32)PCIE_MSI_ALL_MASK, PCIE_MSI_MASK_REG);
 
 	/* Enable summary interrupt for GIC SPI source */
 	reg = PCIE_IRQ_ALL_MASK & (~PCIE_IRQ_ENABLE_INTS_MASK);
@@ -851,7 +853,9 @@
 	case PCI_EXP_RTSTA: {
 		u32 isr0 = advk_readl(pcie, PCIE_ISR0_REG);
 		u32 msglog = advk_readl(pcie, PCIE_MSG_LOG_REG);
-		*value = (isr0 & PCIE_MSG_PM_PME_MASK) << 16 | (msglog >> 16);
+		*value = msglog >> 16;
+		if (isr0 & PCIE_MSG_PM_PME_MASK)
+			*value |= PCI_EXP_RTSTA_PME;
 		return PCI_BRIDGE_EMUL_HANDLED;
 	}
 
@@ -1184,7 +1188,7 @@
 
 	msg->address_lo = lower_32_bits(msi_msg);
 	msg->address_hi = upper_32_bits(msi_msg);
-	msg->data = data->irq;
+	msg->data = data->hwirq;
 }
 
 static int advk_msi_set_affinity(struct irq_data *irq_data,
@@ -1201,15 +1205,11 @@
 	int hwirq, i;
 
 	mutex_lock(&pcie->msi_used_lock);
-	hwirq = bitmap_find_next_zero_area(pcie->msi_used, MSI_IRQ_NUM,
-					   0, nr_irqs, 0);
-	if (hwirq >= MSI_IRQ_NUM) {
-		mutex_unlock(&pcie->msi_used_lock);
-		return -ENOSPC;
-	}
-
-	bitmap_set(pcie->msi_used, hwirq, nr_irqs);
+	hwirq = bitmap_find_free_region(pcie->msi_used, MSI_IRQ_NUM,
+					order_base_2(nr_irqs));
 	mutex_unlock(&pcie->msi_used_lock);
+	if (hwirq < 0)
+		return -ENOSPC;
 
 	for (i = 0; i < nr_irqs; i++)
 		irq_domain_set_info(domain, virq + i, hwirq + i,
@@ -1227,7 +1227,7 @@
 	struct advk_pcie *pcie = domain->host_data;
 
 	mutex_lock(&pcie->msi_used_lock);
-	bitmap_clear(pcie->msi_used, d->hwirq, nr_irqs);
+	bitmap_release_region(pcie->msi_used, d->hwirq, order_base_2(nr_irqs));
 	mutex_unlock(&pcie->msi_used_lock);
 }
 
@@ -1388,23 +1388,19 @@
 static void advk_pcie_handle_msi(struct advk_pcie *pcie)
 {
 	u32 msi_val, msi_mask, msi_status, msi_idx;
-	u16 msi_data;
+	int virq;
 
 	msi_mask = advk_readl(pcie, PCIE_MSI_MASK_REG);
 	msi_val = advk_readl(pcie, PCIE_MSI_STATUS_REG);
-	msi_status = msi_val & ~msi_mask;
+	msi_status = msi_val & ((~msi_mask) & PCIE_MSI_ALL_MASK);
 
 	for (msi_idx = 0; msi_idx < MSI_IRQ_NUM; msi_idx++) {
 		if (!(BIT(msi_idx) & msi_status))
 			continue;
 
-		/*
-		 * msi_idx contains bits [4:0] of the msi_data and msi_data
-		 * contains 16bit MSI interrupt number
-		 */
 		advk_writel(pcie, BIT(msi_idx), PCIE_MSI_STATUS_REG);
-		msi_data = advk_readl(pcie, PCIE_MSI_PAYLOAD_REG) & PCIE_MSI_DATA_MASK;
-		generic_handle_irq(msi_data);
+		virq = irq_find_mapping(pcie->msi_inner_domain, msi_idx);
+		generic_handle_irq(virq);
 	}
 
 	advk_writel(pcie, PCIE_ISR0_MSI_INT_PENDING,
diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index a070e69..4353443 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -1118,6 +1118,10 @@
 		u8 buffer[sizeof(struct pci_delete_interrupt)];
 	} ctxt;
 
+	if (!int_desc->vector_count) {
+		kfree(int_desc);
+		return;
+	}
 	memset(&ctxt, 0, sizeof(ctxt));
 	int_pkt = (struct pci_delete_interrupt *)&ctxt.pkt.message;
 	int_pkt->message_type.type =
@@ -1180,6 +1184,28 @@
 	pci_msi_mask_irq(data);
 }
 
+static unsigned int hv_msi_get_int_vector(struct irq_data *data)
+{
+	struct irq_cfg *cfg = irqd_cfg(data);
+
+	return cfg->vector;
+}
+
+static int hv_msi_prepare(struct irq_domain *domain, struct device *dev,
+			  int nvec, msi_alloc_info_t *info)
+{
+	int ret = pci_msi_prepare(domain, dev, nvec, info);
+
+	/*
+	 * By using the interrupt remapper in the hypervisor IOMMU, contiguous
+	 * CPU vectors is not needed for multi-MSI
+	 */
+	if (info->type == X86_IRQ_ALLOC_TYPE_PCI_MSI)
+		info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS;
+
+	return ret;
+}
+
 /**
  * hv_irq_unmask() - "Unmask" the IRQ by setting its current
  * affinity.
@@ -1195,6 +1221,7 @@
 	struct msi_desc *msi_desc = irq_data_get_msi_desc(data);
 	struct irq_cfg *cfg = irqd_cfg(data);
 	struct hv_retarget_device_interrupt *params;
+	struct tran_int_desc *int_desc;
 	struct hv_pcibus_device *hbus;
 	struct cpumask *dest;
 	cpumask_var_t tmp;
@@ -1209,6 +1236,7 @@
 	pdev = msi_desc_to_pci_dev(msi_desc);
 	pbus = pdev->bus;
 	hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata);
+	int_desc = data->chip_data;
 
 	spin_lock_irqsave(&hbus->retarget_msi_interrupt_lock, flags);
 
@@ -1216,7 +1244,8 @@
 	memset(params, 0, sizeof(*params));
 	params->partition_id = HV_PARTITION_ID_SELF;
 	params->int_entry.source = 1; /* MSI(-X) */
-	hv_set_msi_entry_from_desc(&params->int_entry.msi_entry, msi_desc);
+	params->int_entry.msi_entry.address = int_desc->address & 0xffffffff;
+	params->int_entry.msi_entry.data = int_desc->data;
 	params->device_id = (hbus->hdev->dev_instance.b[5] << 24) |
 			   (hbus->hdev->dev_instance.b[4] << 16) |
 			   (hbus->hdev->dev_instance.b[7] << 8) |
@@ -1317,12 +1346,12 @@
 
 static u32 hv_compose_msi_req_v1(
 	struct pci_create_interrupt *int_pkt, struct cpumask *affinity,
-	u32 slot, u8 vector)
+	u32 slot, u8 vector, u8 vector_count)
 {
 	int_pkt->message_type.type = PCI_CREATE_INTERRUPT_MESSAGE;
 	int_pkt->wslot.slot = slot;
 	int_pkt->int_desc.vector = vector;
-	int_pkt->int_desc.vector_count = 1;
+	int_pkt->int_desc.vector_count = vector_count;
 	int_pkt->int_desc.delivery_mode = dest_Fixed;
 
 	/*
@@ -1336,14 +1365,14 @@
 
 static u32 hv_compose_msi_req_v2(
 	struct pci_create_interrupt2 *int_pkt, struct cpumask *affinity,
-	u32 slot, u8 vector)
+	u32 slot, u8 vector, u8 vector_count)
 {
 	int cpu;
 
 	int_pkt->message_type.type = PCI_CREATE_INTERRUPT_MESSAGE2;
 	int_pkt->wslot.slot = slot;
 	int_pkt->int_desc.vector = vector;
-	int_pkt->int_desc.vector_count = 1;
+	int_pkt->int_desc.vector_count = vector_count;
 	int_pkt->int_desc.delivery_mode = dest_Fixed;
 
 	/*
@@ -1371,7 +1400,6 @@
  */
 static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 {
-	struct irq_cfg *cfg = irqd_cfg(data);
 	struct hv_pcibus_device *hbus;
 	struct vmbus_channel *channel;
 	struct hv_pci_dev *hpdev;
@@ -1380,6 +1408,8 @@
 	struct cpumask *dest;
 	struct compose_comp_ctxt comp;
 	struct tran_int_desc *int_desc;
+	struct msi_desc *msi_desc;
+	u8 vector, vector_count;
 	struct {
 		struct pci_packet pci_pkt;
 		union {
@@ -1391,7 +1421,17 @@
 	u32 size;
 	int ret;
 
-	pdev = msi_desc_to_pci_dev(irq_data_get_msi_desc(data));
+	/* Reuse the previous allocation */
+	if (data->chip_data) {
+		int_desc = data->chip_data;
+		msg->address_hi = int_desc->address >> 32;
+		msg->address_lo = int_desc->address & 0xffffffff;
+		msg->data = int_desc->data;
+		return;
+	}
+
+	msi_desc  = irq_data_get_msi_desc(data);
+	pdev = msi_desc_to_pci_dev(msi_desc);
 	dest = irq_data_get_effective_affinity_mask(data);
 	pbus = pdev->bus;
 	hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata);
@@ -1400,17 +1440,40 @@
 	if (!hpdev)
 		goto return_null_message;
 
-	/* Free any previous message that might have already been composed. */
-	if (data->chip_data) {
-		int_desc = data->chip_data;
-		data->chip_data = NULL;
-		hv_int_desc_free(hpdev, int_desc);
-	}
-
 	int_desc = kzalloc(sizeof(*int_desc), GFP_ATOMIC);
 	if (!int_desc)
 		goto drop_reference;
 
+	if (!msi_desc->msi_attrib.is_msix && msi_desc->nvec_used > 1) {
+		/*
+		 * If this is not the first MSI of Multi MSI, we already have
+		 * a mapping.  Can exit early.
+		 */
+		if (msi_desc->irq != data->irq) {
+			data->chip_data = int_desc;
+			int_desc->address = msi_desc->msg.address_lo |
+					    (u64)msi_desc->msg.address_hi << 32;
+			int_desc->data = msi_desc->msg.data +
+					 (data->irq - msi_desc->irq);
+			msg->address_hi = msi_desc->msg.address_hi;
+			msg->address_lo = msi_desc->msg.address_lo;
+			msg->data = int_desc->data;
+			put_pcichild(hpdev);
+			return;
+		}
+		/*
+		 * The vector we select here is a dummy value.  The correct
+		 * value gets sent to the hypervisor in unmask().  This needs
+		 * to be aligned with the count, and also not zero.  Multi-msi
+		 * is powers of 2 up to 32, so 32 will always work here.
+		 */
+		vector = 32;
+		vector_count = msi_desc->nvec_used;
+	} else {
+		vector = hv_msi_get_int_vector(data);
+		vector_count = 1;
+	}
+
 	memset(&ctxt, 0, sizeof(ctxt));
 	init_completion(&comp.comp_pkt.host_event);
 	ctxt.pci_pkt.completion_func = hv_pci_compose_compl;
@@ -1421,7 +1484,8 @@
 		size = hv_compose_msi_req_v1(&ctxt.int_pkts.v1,
 					dest,
 					hpdev->desc.win_slot.slot,
-					cfg->vector);
+					vector,
+					vector_count);
 		break;
 
 	case PCI_PROTOCOL_VERSION_1_2:
@@ -1429,7 +1493,8 @@
 		size = hv_compose_msi_req_v2(&ctxt.int_pkts.v2,
 					dest,
 					hpdev->desc.win_slot.slot,
-					cfg->vector);
+					vector,
+					vector_count);
 		break;
 
 	default:
@@ -1545,7 +1610,7 @@
 };
 
 static struct msi_domain_ops hv_msi_ops = {
-	.msi_prepare	= pci_msi_prepare,
+	.msi_prepare	= hv_msi_prepare,
 	.msi_free	= hv_msi_free,
 };
 
diff --git a/drivers/pci/controller/pci-xgene.c b/drivers/pci/controller/pci-xgene.c
index b651b6f..e1c2daa 100644
--- a/drivers/pci/controller/pci-xgene.c
+++ b/drivers/pci/controller/pci-xgene.c
@@ -467,7 +467,7 @@
 		return 1;
 	}
 
-	if ((size > SZ_1K) && (size < SZ_4G) && !(*ib_reg_mask & (1 << 0))) {
+	if ((size > SZ_1K) && (size < SZ_1T) && !(*ib_reg_mask & (1 << 0))) {
 		*ib_reg_mask |= (1 << 0);
 		return 0;
 	}
@@ -481,28 +481,27 @@
 }
 
 static void xgene_pcie_setup_ib_reg(struct xgene_pcie_port *port,
-				    struct resource_entry *entry,
-				    u8 *ib_reg_mask)
+				    struct of_pci_range *range, u8 *ib_reg_mask)
 {
 	void __iomem *cfg_base = port->cfg_base;
 	struct device *dev = port->dev;
 	void *bar_addr;
 	u32 pim_reg;
-	u64 cpu_addr = entry->res->start;
-	u64 pci_addr = cpu_addr - entry->offset;
-	u64 size = resource_size(entry->res);
+	u64 cpu_addr = range->cpu_addr;
+	u64 pci_addr = range->pci_addr;
+	u64 size = range->size;
 	u64 mask = ~(size - 1) | EN_REG;
 	u32 flags = PCI_BASE_ADDRESS_MEM_TYPE_64;
 	u32 bar_low;
 	int region;
 
-	region = xgene_pcie_select_ib_reg(ib_reg_mask, size);
+	region = xgene_pcie_select_ib_reg(ib_reg_mask, range->size);
 	if (region < 0) {
 		dev_warn(dev, "invalid pcie dma-range config\n");
 		return;
 	}
 
-	if (entry->res->flags & IORESOURCE_PREFETCH)
+	if (range->flags & IORESOURCE_PREFETCH)
 		flags |= PCI_BASE_ADDRESS_MEM_PREFETCH;
 
 	bar_low = pcie_bar_low_val((u32)cpu_addr, flags);
@@ -533,13 +532,25 @@
 
 static int xgene_pcie_parse_map_dma_ranges(struct xgene_pcie_port *port)
 {
-	struct pci_host_bridge *bridge = pci_host_bridge_from_priv(port);
-	struct resource_entry *entry;
+	struct device_node *np = port->node;
+	struct of_pci_range range;
+	struct of_pci_range_parser parser;
+	struct device *dev = port->dev;
 	u8 ib_reg_mask = 0;
 
-	resource_list_for_each_entry(entry, &bridge->dma_ranges)
-		xgene_pcie_setup_ib_reg(port, entry, &ib_reg_mask);
+	if (of_pci_dma_range_parser_init(&parser, np)) {
+		dev_err(dev, "missing dma-ranges property\n");
+		return -EINVAL;
+	}
 
+	/* Get the dma-ranges from DT */
+	for_each_of_pci_range(&parser, &range) {
+		u64 end = range.cpu_addr + range.size - 1;
+
+		dev_dbg(dev, "0x%08x 0x%016llx..0x%016llx -> 0x%016llx\n",
+			range.flags, range.cpu_addr, end, range.pci_addr);
+		xgene_pcie_setup_ib_reg(port, &range, &ib_reg_mask);
+	}
 	return 0;
 }
 
diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c
index 7631dc3..379cde5 100644
--- a/drivers/pci/controller/pcie-rockchip-ep.c
+++ b/drivers/pci/controller/pcie-rockchip-ep.c
@@ -264,8 +264,7 @@
 	struct rockchip_pcie *pcie = &ep->rockchip;
 	u32 r;
 
-	r = find_first_zero_bit(&ep->ob_region_map,
-				sizeof(ep->ob_region_map) * BITS_PER_LONG);
+	r = find_first_zero_bit(&ep->ob_region_map, BITS_PER_LONG);
 	/*
 	 * Region 0 is reserved for configuration space and shouldn't
 	 * be used elsewhere per TRM, so leave it out.