Merge branch 'pci/controller/qcom'

- Use devm_clk_bulk_get_all() to get all the clocks from DT to avoid
  writing out all the clock names (Manivannan Sadhasivam)

- Add DT binding and driver support for the SA8775P SoC (Mrinmay Sarkar)

- Refactor dw_pcie_edma_find_chip() to enable adding support for Hyper DMA
  (HDMA) (Manivannan Sadhasivam)

- Enable drivers to supply the eDMA channel count since some can't auto
  detect this (Manivannan Sadhasivam)

- Add HDMA support for the SA8775P SoC (Mrinmay Sarkar)

- Override the SA8775P NO_SNOOP default to avoid possible memory corruption
  (Mrinmay Sarkar)

- Make sure resources are disabled during PERST# assertion, even if the
  link is already disabled (Manivannan Sadhasivam)

- Vote for the CPU-PCIe ICC (interconnect) path to ensure it stays active
  even if other drivers don't vote for it (Krishna chaitanya chundru)

- Add Operating Performance Points (OPP) to scale performance state based
  on aggregate link bandwidth to improve SoC power efficiency (Krishna
  chaitanya chundru)

- Return failure instead of success if dev_pm_opp_find_freq_floor() fails
  (Dan Carpenter)

- Avoid an error pointer dereference if dev_pm_opp_find_freq_exact() fails
  (Dan Carpenter)

- Prevent use of uninitialized data in qcom_pcie_suspend_noirq() (Dan
  Carpenter)

* pci/controller/qcom:
  PCI: qcom: Prevent use of uninitialized data in qcom_pcie_suspend_noirq()
  PCI: qcom: Prevent potential error pointer dereference
  PCI: qcom: Fix missing error code in qcom_pcie_probe()
  PCI: qcom: Add OPP support to scale performance
  PCI: Bring the PCIe speed to MBps logic to new pcie_dev_speed_mbps()
  PCI: qcom: Add ICC bandwidth vote for CPU to PCIe path
  PCI: qcom-ep: Disable resources unconditionally during PERST# assert
  PCI: qcom-ep: Override NO_SNOOP attribute for SA8775P EP
  PCI: qcom: Override NO_SNOOP attribute for SA8775P RC
  PCI: epf-mhi: Enable HDMA for SA8775P SoC
  PCI: qcom-ep: Add HDMA support for SA8775P SoC
  PCI: dwc: Pass the eDMA mapping format flag directly from glue drivers
  PCI: dwc: Skip finding eDMA channels count for HDMA platforms
  PCI: dwc: Refactor dw_pcie_edma_find_chip() API
  PCI: qcom-ep: Add support for SA8775P SOC
  dt-bindings: PCI: qcom-ep: Add support for SA8775P SoC
  PCI: qcom: Use devm_clk_bulk_get_all() API

8 files changed, 314 insertions, 186 deletions

diff --git a/drivers/pci/controller/dwc/pcie-designware.c b/drivers/pci/controller/dwc/pcie-designware.c
index 26ecf0472f86..1b5aba1f0c92 100644
--- a/drivers/pci/controller/dwc/pcie-designware.c
+++ b/drivers/pci/controller/dwc/pcie-designware.c
@@ -870,30 +870,40 @@ 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;
 
@@ -902,15 +912,25 @@ 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 ||
@@ -920,6 +940,19 @@ 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);
diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h
index 069c72f318a7..f49f493b0344 100644
--- a/drivers/pci/controller/dwc/pcie-designware.h
+++ b/drivers/pci/controller/dwc/pcie-designware.h
@@ -51,9 +51,8 @@
 
 /* DWC PCIe controller capabilities */
 #define DW_PCIE_CAP_REQ_RES		0
-#define DW_PCIE_CAP_EDMA_UNROLL		1
-#define DW_PCIE_CAP_IATU_UNROLL		2
-#define DW_PCIE_CAP_CDM_CHECK		3
+#define DW_PCIE_CAP_IATU_UNROLL		1
+#define DW_PCIE_CAP_CDM_CHECK		2
 
 #define dw_pcie_cap_is(_pci, _cap) \
 	test_bit(DW_PCIE_CAP_ ## _cap, &(_pci)->caps)
diff --git a/drivers/pci/controller/dwc/pcie-qcom-ep.c b/drivers/pci/controller/dwc/pcie-qcom-ep.c
index 02a2a871a91f..236229f66c80 100644
--- a/drivers/pci/controller/dwc/pcie-qcom-ep.c
+++ b/drivers/pci/controller/dwc/pcie-qcom-ep.c
@@ -47,6 +47,7 @@
 #define PARF_DBI_BASE_ADDR_HI			0x354
 #define PARF_SLV_ADDR_SPACE_SIZE		0x358
 #define PARF_SLV_ADDR_SPACE_SIZE_HI		0x35c
+#define PARF_NO_SNOOP_OVERIDE			0x3d4
 #define PARF_ATU_BASE_ADDR			0x634
 #define PARF_ATU_BASE_ADDR_HI			0x638
 #define PARF_SRIS_MODE				0x644
@@ -86,6 +87,10 @@
 #define PARF_DEBUG_INT_CFG_BUS_MASTER_EN	BIT(2)
 #define PARF_DEBUG_INT_RADM_PM_TURNOFF		BIT(3)
 
+/* PARF_NO_SNOOP_OVERIDE register fields */
+#define WR_NO_SNOOP_OVERIDE_EN                 BIT(1)
+#define RD_NO_SNOOP_OVERIDE_EN                 BIT(3)
+
 /* PARF_DEVICE_TYPE register fields */
 #define PARF_DEVICE_TYPE_EP			0x0
 
@@ -150,6 +155,16 @@ enum qcom_pcie_ep_link_status {
 };
 
 /**
+ * struct qcom_pcie_ep_cfg - Per SoC config struct
+ * @hdma_support: HDMA support on this SoC
+ * @override_no_snoop: Override NO_SNOOP attribute in TLP to enable cache snooping
+ */
+struct qcom_pcie_ep_cfg {
+	bool hdma_support;
+	bool override_no_snoop;
+};
+
+/**
  * struct qcom_pcie_ep - Qualcomm PCIe Endpoint Controller
  * @pci: Designware PCIe controller struct
  * @parf: Qualcomm PCIe specific PARF register base
@@ -167,6 +182,7 @@ enum qcom_pcie_ep_link_status {
  * @num_clks: PCIe clocks count
  * @perst_en: Flag for PERST enable
  * @perst_sep_en: Flag for PERST separation enable
+ * @cfg: PCIe EP config struct
  * @link_status: PCIe Link status
  * @global_irq: Qualcomm PCIe specific Global IRQ
  * @perst_irq: PERST# IRQ
@@ -194,6 +210,7 @@ struct qcom_pcie_ep {
 	u32 perst_en;
 	u32 perst_sep_en;
 
+	const struct qcom_pcie_ep_cfg *cfg;
 	enum qcom_pcie_ep_link_status link_status;
 	int global_irq;
 	int perst_irq;
@@ -489,6 +506,10 @@ static int qcom_pcie_perst_deassert(struct dw_pcie *pci)
 	val |= BIT(8);
 	writel_relaxed(val, pcie_ep->parf + PARF_LTSSM);
 
+	if (pcie_ep->cfg && pcie_ep->cfg->override_no_snoop)
+		writel_relaxed(WR_NO_SNOOP_OVERIDE_EN | RD_NO_SNOOP_OVERIDE_EN,
+				pcie_ep->parf + PARF_NO_SNOOP_OVERIDE);
+
 	return 0;
 
 err_disable_resources:
@@ -500,12 +521,6 @@ err_disable_resources:
 static void qcom_pcie_perst_assert(struct dw_pcie *pci)
 {
 	struct qcom_pcie_ep *pcie_ep = to_pcie_ep(pci);
-	struct device *dev = pci->dev;
-
-	if (pcie_ep->link_status == QCOM_PCIE_EP_LINK_DISABLED) {
-		dev_dbg(dev, "Link is already disabled\n");
-		return;
-	}
 
 	pci_epc_deinit_notify(pci->ep.epc);
 	dw_pcie_ep_cleanup(&pci->ep);
@@ -817,6 +832,14 @@ static int qcom_pcie_ep_probe(struct platform_device *pdev)
 	pcie_ep->pci.ops = &pci_ops;
 	pcie_ep->pci.ep.ops = &pci_ep_ops;
 	pcie_ep->pci.edma.nr_irqs = 1;
+
+	pcie_ep->cfg = of_device_get_match_data(dev);
+	if (pcie_ep->cfg && pcie_ep->cfg->hdma_support) {
+		pcie_ep->pci.edma.ll_wr_cnt = 8;
+		pcie_ep->pci.edma.ll_rd_cnt = 8;
+		pcie_ep->pci.edma.mf = EDMA_MF_HDMA_NATIVE;
+	}
+
 	platform_set_drvdata(pdev, pcie_ep);
 
 	ret = qcom_pcie_ep_get_resources(pdev, pcie_ep);
@@ -875,7 +898,13 @@ static void qcom_pcie_ep_remove(struct platform_device *pdev)
 	qcom_pcie_disable_resources(pcie_ep);
 }
 
+static const struct qcom_pcie_ep_cfg cfg_1_34_0 = {
+	.hdma_support = true,
+	.override_no_snoop = true,
+};
+
 static const struct of_device_id qcom_pcie_ep_match[] = {
+	{ .compatible = "qcom,sa8775p-pcie-ep", .data = &cfg_1_34_0},
 	{ .compatible = "qcom,sdx55-pcie-ep", },
 	{ .compatible = "qcom,sm8450-pcie-ep", },
 	{ }
diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
index 436076612c8f..0180edf3310e 100644
--- a/drivers/pci/controller/dwc/pcie-qcom.c
+++ b/drivers/pci/controller/dwc/pcie-qcom.c
@@ -18,9 +18,11 @@
 #include <linux/io.h>
 #include <linux/iopoll.h>
 #include <linux/kernel.h>
+#include <linux/limits.h>
 #include <linux/init.h>
 #include <linux/of.h>
 #include <linux/pci.h>
+#include <linux/pm_opp.h>
 #include <linux/pm_runtime.h>
 #include <linux/platform_device.h>
 #include <linux/phy/pcie.h>
@@ -29,6 +31,7 @@
 #include <linux/reset.h>
 #include <linux/slab.h>
 #include <linux/types.h>
+#include <linux/units.h>
 
 #include "../../pci.h"
 #include "pcie-designware.h"
@@ -50,6 +53,7 @@
 #define PARF_SID_OFFSET				0x234
 #define PARF_BDF_TRANSLATE_CFG			0x24c
 #define PARF_SLV_ADDR_SPACE_SIZE		0x358
+#define PARF_NO_SNOOP_OVERIDE			0x3d4
 #define PARF_DEVICE_TYPE			0x1000
 #define PARF_BDF_TO_SID_TABLE_N			0x2000
 #define PARF_BDF_TO_SID_CFG			0x2c00
@@ -117,6 +121,10 @@
 /* PARF_LTSSM register fields */
 #define LTSSM_EN				BIT(8)
 
+/* PARF_NO_SNOOP_OVERIDE register fields */
+#define WR_NO_SNOOP_OVERIDE_EN			BIT(1)
+#define RD_NO_SNOOP_OVERIDE_EN			BIT(3)
+
 /* PARF_DEVICE_TYPE register fields */
 #define DEVICE_TYPE_RC				0x4
 
@@ -153,58 +161,56 @@
 #define QCOM_PCIE_LINK_SPEED_TO_BW(speed) \
 		Mbps_to_icc(PCIE_SPEED2MBS_ENC(pcie_link_speed[speed]))
 
-#define QCOM_PCIE_1_0_0_MAX_CLOCKS		4
 struct qcom_pcie_resources_1_0_0 {
-	struct clk_bulk_data clks[QCOM_PCIE_1_0_0_MAX_CLOCKS];
+	struct clk_bulk_data *clks;
+	int num_clks;
 	struct reset_control *core;
 	struct regulator *vdda;
 };
 
-#define QCOM_PCIE_2_1_0_MAX_CLOCKS		5
 #define QCOM_PCIE_2_1_0_MAX_RESETS		6
 #define QCOM_PCIE_2_1_0_MAX_SUPPLY		3
 struct qcom_pcie_resources_2_1_0 {
-	struct clk_bulk_data clks[QCOM_PCIE_2_1_0_MAX_CLOCKS];
+	struct clk_bulk_data *clks;
+	int num_clks;
 	struct reset_control_bulk_data resets[QCOM_PCIE_2_1_0_MAX_RESETS];
 	int num_resets;
 	struct regulator_bulk_data supplies[QCOM_PCIE_2_1_0_MAX_SUPPLY];
 };
 
-#define QCOM_PCIE_2_3_2_MAX_CLOCKS		4
 #define QCOM_PCIE_2_3_2_MAX_SUPPLY		2
 struct qcom_pcie_resources_2_3_2 {
-	struct clk_bulk_data clks[QCOM_PCIE_2_3_2_MAX_CLOCKS];
+	struct clk_bulk_data *clks;
+	int num_clks;
 	struct regulator_bulk_data supplies[QCOM_PCIE_2_3_2_MAX_SUPPLY];
 };
 
-#define QCOM_PCIE_2_3_3_MAX_CLOCKS		5
 #define QCOM_PCIE_2_3_3_MAX_RESETS		7
 struct qcom_pcie_resources_2_3_3 {
-	struct clk_bulk_data clks[QCOM_PCIE_2_3_3_MAX_CLOCKS];
+	struct clk_bulk_data *clks;
+	int num_clks;
 	struct reset_control_bulk_data rst[QCOM_PCIE_2_3_3_MAX_RESETS];
 };
 
-#define QCOM_PCIE_2_4_0_MAX_CLOCKS		4
 #define QCOM_PCIE_2_4_0_MAX_RESETS		12
 struct qcom_pcie_resources_2_4_0 {
-	struct clk_bulk_data clks[QCOM_PCIE_2_4_0_MAX_CLOCKS];
+	struct clk_bulk_data *clks;
 	int num_clks;
 	struct reset_control_bulk_data resets[QCOM_PCIE_2_4_0_MAX_RESETS];
 	int num_resets;
 };
 
-#define QCOM_PCIE_2_7_0_MAX_CLOCKS		15
 #define QCOM_PCIE_2_7_0_MAX_SUPPLIES		2
 struct qcom_pcie_resources_2_7_0 {
-	struct clk_bulk_data clks[QCOM_PCIE_2_7_0_MAX_CLOCKS];
+	struct clk_bulk_data *clks;
 	int num_clks;
 	struct regulator_bulk_data supplies[QCOM_PCIE_2_7_0_MAX_SUPPLIES];
 	struct reset_control *rst;
 };
 
-#define QCOM_PCIE_2_9_0_MAX_CLOCKS		5
 struct qcom_pcie_resources_2_9_0 {
-	struct clk_bulk_data clks[QCOM_PCIE_2_9_0_MAX_CLOCKS];
+	struct clk_bulk_data *clks;
+	int num_clks;
 	struct reset_control *rst;
 };
 
@@ -230,8 +236,15 @@ struct qcom_pcie_ops {
 	int (*config_sid)(struct qcom_pcie *pcie);
 };
 
+ /**
+  * struct qcom_pcie_cfg - Per SoC config struct
+  * @ops: qcom PCIe ops structure
+  * @override_no_snoop: Override NO_SNOOP attribute in TLP to enable cache
+  * snooping
+  */
 struct qcom_pcie_cfg {
 	const struct qcom_pcie_ops *ops;
+	bool override_no_snoop;
 	bool no_l0s;
 };
 
@@ -244,6 +257,7 @@ struct qcom_pcie {
 	struct phy *phy;
 	struct gpio_desc *reset;
 	struct icc_path *icc_mem;
+	struct icc_path *icc_cpu;
 	const struct qcom_pcie_cfg *cfg;
 	struct dentry *debugfs;
 	bool suspended;
@@ -336,21 +350,11 @@ static int qcom_pcie_get_resources_2_1_0(struct qcom_pcie *pcie)
 	if (ret)
 		return ret;
 
-	res->clks[0].id = "iface";
-	res->clks[1].id = "core";
-	res->clks[2].id = "phy";
-	res->clks[3].id = "aux";
-	res->clks[4].id = "ref";
-
-	/* iface, core, phy are required */
-	ret = devm_clk_bulk_get(dev, 3, res->clks);
-	if (ret < 0)
-		return ret;
-
-	/* aux, ref are optional */
-	ret = devm_clk_bulk_get_optional(dev, 2, res->clks + 3);
-	if (ret < 0)
-		return ret;
+	res->num_clks = devm_clk_bulk_get_all(dev, &res->clks);
+	if (res->num_clks < 0) {
+		dev_err(dev, "Failed to get clocks\n");
+		return res->num_clks;
+	}
 
 	res->resets[0].id = "pci";
 	res->resets[1].id = "axi";
@@ -372,7 +376,7 @@ static void qcom_pcie_deinit_2_1_0(struct qcom_pcie *pcie)
 {
 	struct qcom_pcie_resources_2_1_0 *res = &pcie->res.v2_1_0;
 
-	clk_bulk_disable_unprepare(ARRAY_SIZE(res->clks), res->clks);
+	clk_bulk_disable_unprepare(res->num_clks, res->clks);
 	reset_control_bulk_assert(res->num_resets, res->resets);
 
 	writel(1, pcie->parf + PARF_PHY_CTRL);
@@ -424,7 +428,7 @@ static int qcom_pcie_post_init_2_1_0(struct qcom_pcie *pcie)
 	val &= ~PHY_TEST_PWR_DOWN;
 	writel(val, pcie->parf + PARF_PHY_CTRL);
 
-	ret = clk_bulk_prepare_enable(ARRAY_SIZE(res->clks), res->clks);
+	ret = clk_bulk_prepare_enable(res->num_clks, res->clks);
 	if (ret)
 		return ret;
 
@@ -475,20 +479,16 @@ static int qcom_pcie_get_resources_1_0_0(struct qcom_pcie *pcie)
 	struct qcom_pcie_resources_1_0_0 *res = &pcie->res.v1_0_0;
 	struct dw_pcie *pci = pcie->pci;
 	struct device *dev = pci->dev;
-	int ret;
 
 	res->vdda = devm_regulator_get(dev, "vdda");
 	if (IS_ERR(res->vdda))
 		return PTR_ERR(res->vdda);
 
-	res->clks[0].id = "iface";
-	res->clks[1].id = "aux";
-	res->clks[2].id = "master_bus";
-	res->clks[3].id = "slave_bus";
-
-	ret = devm_clk_bulk_get(dev, ARRAY_SIZE(res->clks), res->clks);
-	if (ret < 0)
-		return ret;
+	res->num_clks = devm_clk_bulk_get_all(dev, &res->clks);
+	if (res->num_clks < 0) {
+		dev_err(dev, "Failed to get clocks\n");
+		return res->num_clks;
+	}
 
 	res->core = devm_reset_control_get_exclusive(dev, "core");
 	return PTR_ERR_OR_ZERO(res->core);
@@ -499,7 +499,7 @@ static void qcom_pcie_deinit_1_0_0(struct qcom_pcie *pcie)
 	struct qcom_pcie_resources_1_0_0 *res = &pcie->res.v1_0_0;
 
 	reset_control_assert(res->core);
-	clk_bulk_disable_unprepare(ARRAY_SIZE(res->clks), res->clks);
+	clk_bulk_disable_unprepare(res->num_clks, res->clks);
 	regulator_disable(res->vdda);
 }
 
@@ -516,7 +516,7 @@ static int qcom_pcie_init_1_0_0(struct qcom_pcie *pcie)
 		return ret;
 	}
 
-	ret = clk_bulk_prepare_enable(ARRAY_SIZE(res->clks), res->clks);
+	ret = clk_bulk_prepare_enable(res->num_clks, res->clks);
 	if (ret) {
 		dev_err(dev, "cannot prepare/enable clocks\n");
 		goto err_assert_reset;
@@ -531,7 +531,7 @@ static int qcom_pcie_init_1_0_0(struct qcom_pcie *pcie)
 	return 0;
 
 err_disable_clks:
-	clk_bulk_disable_unprepare(ARRAY_SIZE(res->clks), res->clks);
+	clk_bulk_disable_unprepare(res->num_clks, res->clks);
 err_assert_reset:
 	reset_control_assert(res->core);
 
@@ -579,14 +579,11 @@ static int qcom_pcie_get_resources_2_3_2(struct qcom_pcie *pcie)
 	if (ret)
 		return ret;
 
-	res->clks[0].id = "aux";
-	res->clks[1].id = "cfg";
-	res->clks[2].id = "bus_master";
-	res->clks[3].id = "bus_slave";
-
-	ret = devm_clk_bulk_get(dev, ARRAY_SIZE(res->clks), res->clks);
-	if (ret < 0)
-		return ret;
+	res->num_clks = devm_clk_bulk_get_all(dev, &res->clks);
+	if (res->num_clks < 0) {
+		dev_err(dev, "Failed to get clocks\n");
+		return res->num_clks;
+	}
 
 	return 0;
 }
@@ -595,7 +592,7 @@ static void qcom_pcie_deinit_2_3_2(struct qcom_pcie *pcie)
 {
 	struct qcom_pcie_resources_2_3_2 *res = &pcie->res.v2_3_2;
 
-	clk_bulk_disable_unprepare(ARRAY_SIZE(res->clks), res->clks);
+	clk_bulk_disable_unprepare(res->num_clks, res->clks);
 	regulator_bulk_disable(ARRAY_SIZE(res->supplies), res->supplies);
 }
 
@@ -612,7 +609,7 @@ static int qcom_pcie_init_2_3_2(struct qcom_pcie *pcie)
 		return ret;
 	}
 
-	ret = clk_bulk_prepare_enable(ARRAY_SIZE(res->clks), res->clks);
+	ret = clk_bulk_prepare_enable(res->num_clks, res->clks);
 	if (ret) {
 		dev_err(dev, "cannot prepare/enable clocks\n");
 		regulator_bulk_disable(ARRAY_SIZE(res->supplies), res->supplies);
@@ -660,17 +657,11 @@ static int qcom_pcie_get_resources_2_4_0(struct qcom_pcie *pcie)
 	bool is_ipq = of_device_is_compatible(dev->of_node, "qcom,pcie-ipq4019");
 	int ret;
 
-	res->clks[0].id = "aux";
-	res->clks[1].id = "master_bus";
-	res->clks[2].id = "slave_bus";
-	res->clks[3].id = "iface";
-
-	/* qcom,pcie-ipq4019 is defined without "iface" */
-	res->num_clks = is_ipq ? 3 : 4;
-
-	ret = devm_clk_bulk_get(dev, res->num_clks, res->clks);
-	if (ret < 0)
-		return ret;
+	res->num_clks = devm_clk_bulk_get_all(dev, &res->clks);
+	if (res->num_clks < 0) {
+		dev_err(dev, "Failed to get clocks\n");
+		return res->num_clks;
+	}
 
 	res->resets[0].id = "axi_m";
 	res->resets[1].id = "axi_s";
@@ -741,15 +732,11 @@ static int qcom_pcie_get_resources_2_3_3(struct qcom_pcie *pcie)
 	struct device *dev = pci->dev;
 	int ret;
 
-	res->clks[0].id = "iface";
-	res->clks[1].id = "axi_m";
-	res->clks[2].id = "axi_s";
-	res->clks[3].id = "ahb";
-	res->clks[4].id = "aux";
-
-	ret = devm_clk_bulk_get(dev, ARRAY_SIZE(res->clks), res->clks);
-	if (ret < 0)
-		return ret;
+	res->num_clks = devm_clk_bulk_get_all(dev, &res->clks);
+	if (res->num_clks < 0) {
+		dev_err(dev, "Failed to get clocks\n");
+		return res->num_clks;
+	}
 
 	res->rst[0].id = "axi_m";
 	res->rst[1].id = "axi_s";
@@ -770,7 +757,7 @@ static void qcom_pcie_deinit_2_3_3(struct qcom_pcie *pcie)
 {
 	struct qcom_pcie_resources_2_3_3 *res = &pcie->res.v2_3_3;
 
-	clk_bulk_disable_unprepare(ARRAY_SIZE(res->clks), res->clks);
+	clk_bulk_disable_unprepare(res->num_clks, res->clks);
 }
 
 static int qcom_pcie_init_2_3_3(struct qcom_pcie *pcie)
@@ -800,7 +787,7 @@ static int qcom_pcie_init_2_3_3(struct qcom_pcie *pcie)
 	 */
 	usleep_range(2000, 2500);
 
-	ret = clk_bulk_prepare_enable(ARRAY_SIZE(res->clks), res->clks);
+	ret = clk_bulk_prepare_enable(res->num_clks, res->clks);
 	if (ret) {
 		dev_err(dev, "cannot prepare/enable clocks\n");
 		goto err_assert_resets;
@@ -861,8 +848,6 @@ static int qcom_pcie_get_resources_2_7_0(struct qcom_pcie *pcie)
 	struct qcom_pcie_resources_2_7_0 *res = &pcie->res.v2_7_0;
 	struct dw_pcie *pci = pcie->pci;
 	struct device *dev = pci->dev;
-	unsigned int num_clks, num_opt_clks;
-	unsigned int idx;
 	int ret;
 
 	res->rst = devm_reset_control_array_get_exclusive(dev);
@@ -876,36 +861,11 @@ static int qcom_pcie_get_resources_2_7_0(struct qcom_pcie *pcie)
 	if (ret)
 		return ret;
 
-	idx = 0;
-	res->clks[idx++].id = "aux";
-	res->clks[idx++].id = "cfg";
-	res->clks[idx++].id = "bus_master";
-	res->clks[idx++].id = "bus_slave";
-	res->clks[idx++].id = "slave_q2a";
-
-	num_clks = idx;
-
-	ret = devm_clk_bulk_get(dev, num_clks, res->clks);
-	if (ret < 0)
-		return ret;
-
-	res->clks[idx++].id = "tbu";
-	res->clks[idx++].id = "ddrss_sf_tbu";
-	res->clks[idx++].id = "aggre0";
-	res->clks[idx++].id = "aggre1";
-	res->clks[idx++].id = "noc_aggr";
-	res->clks[idx++].id = "noc_aggr_4";
-	res->clks[idx++].id = "noc_aggr_south_sf";
-	res->clks[idx++].id = "cnoc_qx";
-	res->clks[idx++].id = "sleep";
-	res->clks[idx++].id = "cnoc_sf_axi";
-
-	num_opt_clks = idx - num_clks;
-	res->num_clks = idx;
-
-	ret = devm_clk_bulk_get_optional(dev, num_opt_clks, res->clks + num_clks);
-	if (ret < 0)
-		return ret;
+	res->num_clks = devm_clk_bulk_get_all(dev, &res->clks);
+	if (res->num_clks < 0) {
+		dev_err(dev, "Failed to get clocks\n");
+		return res->num_clks;
+	}
 
 	return 0;
 }
@@ -985,6 +945,12 @@ err_disable_regulators:
 
 static int qcom_pcie_post_init_2_7_0(struct qcom_pcie *pcie)
 {
+	const struct qcom_pcie_cfg *pcie_cfg = pcie->cfg;
+
+	if (pcie_cfg->override_no_snoop)
+		writel(WR_NO_SNOOP_OVERIDE_EN | RD_NO_SNOOP_OVERIDE_EN,
+				pcie->parf + PARF_NO_SNOOP_OVERIDE);
+
 	qcom_pcie_clear_aspm_l0s(pcie->pci);
 	qcom_pcie_clear_hpc(pcie->pci);
 
@@ -1100,17 +1066,12 @@ static int qcom_pcie_get_resources_2_9_0(struct qcom_pcie *pcie)
 	struct qcom_pcie_resources_2_9_0 *res = &pcie->res.v2_9_0;
 	struct dw_pcie *pci = pcie->pci;
 	struct device *dev = pci->dev;
-	int ret;
 
-	res->clks[0].id = "iface";
-	res->clks[1].id = "axi_m";
-	res->clks[2].id = "axi_s";
-	res->clks[3].id = "axi_bridge";
-	res->clks[4].id = "rchng";
-
-	ret = devm_clk_bulk_get(dev, ARRAY_SIZE(res->clks), res->clks);
-	if (ret < 0)
-		return ret;
+	res->num_clks = devm_clk_bulk_get_all(dev, &res->clks);
+	if (res->num_clks < 0) {
+		dev_err(dev, "Failed to get clocks\n");
+		return res->num_clks;
+	}
 
 	res->rst = devm_reset_control_array_get_exclusive(dev);
 	if (IS_ERR(res->rst))
@@ -1123,7 +1084,7 @@ static void qcom_pcie_deinit_2_9_0(struct qcom_pcie *pcie)
 {
 	struct qcom_pcie_resources_2_9_0 *res = &pcie->res.v2_9_0;
 
-	clk_bulk_disable_unprepare(ARRAY_SIZE(res->clks), res->clks);
+	clk_bulk_disable_unprepare(res->num_clks, res->clks);
 }
 
 static int qcom_pcie_init_2_9_0(struct qcom_pcie *pcie)
@@ -1152,7 +1113,7 @@ static int qcom_pcie_init_2_9_0(struct qcom_pcie *pcie)
 
 	usleep_range(2000, 2500);
 
-	return clk_bulk_prepare_enable(ARRAY_SIZE(res->clks), res->clks);
+	return clk_bulk_prepare_enable(res->num_clks, res->clks);
 }
 
 static int qcom_pcie_post_init_2_9_0(struct qcom_pcie *pcie)
@@ -1365,6 +1326,11 @@ static const struct qcom_pcie_cfg cfg_1_9_0 = {
 	.ops = &ops_1_9_0,
 };
 
+static const struct qcom_pcie_cfg cfg_1_34_0 = {
+	.ops = &ops_1_9_0,
+	.override_no_snoop = true,
+};
+
 static const struct qcom_pcie_cfg cfg_2_1_0 = {
 	.ops = &ops_2_1_0,
 };
@@ -1408,6 +1374,9 @@ static int qcom_pcie_icc_init(struct qcom_pcie *pcie)
 	if (IS_ERR(pcie->icc_mem))
 		return PTR_ERR(pcie->icc_mem);
 
+	pcie->icc_cpu = devm_of_icc_get(pci->dev, "cpu-pcie");
+	if (IS_ERR(pcie->icc_cpu))
+		return PTR_ERR(pcie->icc_cpu);
 	/*
 	 * Some Qualcomm platforms require interconnect bandwidth constraints
 	 * to be set before enabling interconnect clocks.
@@ -1417,23 +1386,35 @@ static int qcom_pcie_icc_init(struct qcom_pcie *pcie)
 	 */
 	ret = icc_set_bw(pcie->icc_mem, 0, QCOM_PCIE_LINK_SPEED_TO_BW(1));
 	if (ret) {
-		dev_err(pci->dev, "failed to set interconnect bandwidth: %d\n",
+		dev_err(pci->dev, "Failed to set bandwidth for PCIe-MEM interconnect path: %d\n",
+			ret);
+		return ret;
+	}
+
+	/*
+	 * Since the CPU-PCIe path is only used for activities like register
+	 * access of the host controller and endpoint Config/BAR space access,
+	 * HW team has recommended to use a minimal bandwidth of 1KBps just to
+	 * keep the path active.
+	 */
+	ret = icc_set_bw(pcie->icc_cpu, 0, kBps_to_icc(1));
+	if (ret) {
+		dev_err(pci->dev, "Failed to set bandwidth for CPU-PCIe interconnect path: %d\n",
 			ret);
+		icc_set_bw(pcie->icc_mem, 0, 0);
 		return ret;
 	}
 
 	return 0;
 }
 
-static void qcom_pcie_icc_update(struct qcom_pcie *pcie)
+static void qcom_pcie_icc_opp_update(struct qcom_pcie *pcie)
 {
+	u32 offset, status, width, speed;
 	struct dw_pcie *pci = pcie->pci;
-	u32 offset, status;
-	int speed, width;
-	int ret;
-
-	if (!pcie->icc_mem)
-		return;
+	unsigned long freq_kbps;
+	struct dev_pm_opp *opp;
+	int ret, freq_mbps;
 
 	offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP);
 	status = readw(pci->dbi_base + offset + PCI_EXP_LNKSTA);
@@ -1445,10 +1426,28 @@ static void qcom_pcie_icc_update(struct qcom_pcie *pcie)
 	speed = FIELD_GET(PCI_EXP_LNKSTA_CLS, status);
 	width = FIELD_GET(PCI_EXP_LNKSTA_NLW, status);
 
-	ret = icc_set_bw(pcie->icc_mem, 0, width * QCOM_PCIE_LINK_SPEED_TO_BW(speed));
-	if (ret) {
-		dev_err(pci->dev, "failed to set interconnect bandwidth: %d\n",
-			ret);
+	if (pcie->icc_mem) {
+		ret = icc_set_bw(pcie->icc_mem, 0,
+				 width * QCOM_PCIE_LINK_SPEED_TO_BW(speed));
+		if (ret) {
+			dev_err(pci->dev, "Failed to set bandwidth for PCIe-MEM interconnect path: %d\n",
+				ret);
+		}
+	} else {
+		freq_mbps = pcie_dev_speed_mbps(pcie_link_speed[speed]);
+		if (freq_mbps < 0)
+			return;
+
+		freq_kbps = freq_mbps * KILO;
+		opp = dev_pm_opp_find_freq_exact(pci->dev, freq_kbps * width,
+						 true);
+		if (!IS_ERR(opp)) {
+			ret = dev_pm_opp_set_opp(pci->dev, opp);
+			if (ret)
+				dev_err(pci->dev, "Failed to set OPP for freq (%lu): %d\n",
+					freq_kbps * width, ret);
+			dev_pm_opp_put(opp);
+		}
 	}
 }
 
@@ -1492,7 +1491,9 @@ static void qcom_pcie_init_debugfs(struct qcom_pcie *pcie)
 static int qcom_pcie_probe(struct platform_device *pdev)
 {
 	const struct qcom_pcie_cfg *pcie_cfg;
+	unsigned long max_freq = ULONG_MAX;
 	struct device *dev = &pdev->dev;
+	struct dev_pm_opp *opp;
 	struct qcom_pcie *pcie;
 	struct dw_pcie_rp *pp;
 	struct resource *res;
@@ -1560,9 +1561,43 @@ static int qcom_pcie_probe(struct platform_device *pdev)
 		goto err_pm_runtime_put;
 	}
 
-	ret = qcom_pcie_icc_init(pcie);
-	if (ret)
+	/* OPP table is optional */
+	ret = devm_pm_opp_of_add_table(dev);
+	if (ret && ret != -ENODEV) {
+		dev_err_probe(dev, ret, "Failed to add OPP table\n");
 		goto err_pm_runtime_put;
+	}
+
+	/*
+	 * Before the PCIe link is initialized, vote for highest OPP in the OPP
+	 * table, so that we are voting for maximum voltage corner for the
+	 * link to come up in maximum supported speed. At the end of the
+	 * probe(), OPP will be updated using qcom_pcie_icc_opp_update().
+	 */
+	if (!ret) {
+		opp = dev_pm_opp_find_freq_floor(dev, &max_freq);
+		if (IS_ERR(opp)) {
+			ret = PTR_ERR(opp);
+			dev_err_probe(pci->dev, ret,
+				      "Unable to find max freq OPP\n");
+			goto err_pm_runtime_put;
+		} else {
+			ret = dev_pm_opp_set_opp(dev, opp);
+		}
+
+		dev_pm_opp_put(opp);
+		if (ret) {
+			dev_err_probe(pci->dev, ret,
+				      "Failed to set OPP for freq %lu\n",
+				      max_freq);
+			goto err_pm_runtime_put;
+		}
+	} else {
+		/* Skip ICC init if OPP is supported as it is handled by OPP */
+		ret = qcom_pcie_icc_init(pcie);
+		if (ret)
+			goto err_pm_runtime_put;
+	}
 
 	ret = pcie->cfg->ops->get_resources(pcie);
 	if (ret)
@@ -1582,7 +1617,7 @@ static int qcom_pcie_probe(struct platform_device *pdev)
 		goto err_phy_exit;
 	}
 
-	qcom_pcie_icc_update(pcie);
+	qcom_pcie_icc_opp_update(pcie);
 
 	if (pcie->mhi)
 		qcom_pcie_init_debugfs(pcie);
@@ -1601,16 +1636,20 @@ err_pm_runtime_put:
 static int qcom_pcie_suspend_noirq(struct device *dev)
 {
 	struct qcom_pcie *pcie = dev_get_drvdata(dev);
-	int ret;
+	int ret = 0;
 
 	/*
 	 * Set minimum bandwidth required to keep data path functional during
 	 * suspend.
 	 */
-	ret = icc_set_bw(pcie->icc_mem, 0, kBps_to_icc(1));
-	if (ret) {
-		dev_err(dev, "Failed to set interconnect bandwidth: %d\n", ret);
-		return ret;
+	if (pcie->icc_mem) {
+		ret = icc_set_bw(pcie->icc_mem, 0, kBps_to_icc(1));
+		if (ret) {
+			dev_err(dev,
+				"Failed to set bandwidth for PCIe-MEM interconnect path: %d\n",
+				ret);
+			return ret;
+		}
 	}
 
 	/*
@@ -1633,7 +1672,21 @@ static int qcom_pcie_suspend_noirq(struct device *dev)
 		pcie->suspended = true;
 	}
 
-	return 0;
+	/*
+	 * Only disable CPU-PCIe interconnect path if the suspend is non-S2RAM.
+	 * Because on some platforms, DBI access can happen very late during the
+	 * S2RAM and a non-active CPU-PCIe interconnect path may lead to NoC
+	 * error.
+	 */
+	if (pm_suspend_target_state != PM_SUSPEND_MEM) {
+		ret = icc_disable(pcie->icc_cpu);
+		if (ret)
+			dev_err(dev, "Failed to disable CPU-PCIe interconnect path: %d\n", ret);
+
+		if (!pcie->icc_mem)
+			dev_pm_opp_set_opp(pcie->pci->dev, NULL);
+	}
+	return ret;
 }
 
 static int qcom_pcie_resume_noirq(struct device *dev)
@@ -1641,6 +1694,14 @@ static int qcom_pcie_resume_noirq(struct device *dev)
 	struct qcom_pcie *pcie = dev_get_drvdata(dev);
 	int ret;
 
+	if (pm_suspend_target_state != PM_SUSPEND_MEM) {
+		ret = icc_enable(pcie->icc_cpu);
+		if (ret) {
+			dev_err(dev, "Failed to enable CPU-PCIe interconnect path: %d\n", ret);
+			return ret;
+		}
+	}
+
 	if (pcie->suspended) {
 		ret = qcom_pcie_host_init(&pcie->pci->pp);
 		if (ret)
@@ -1649,7 +1710,7 @@ static int qcom_pcie_resume_noirq(struct device *dev)
 		pcie->suspended = false;
 	}
 
-	qcom_pcie_icc_update(pcie);
+	qcom_pcie_icc_opp_update(pcie);
 
 	return 0;
 }
@@ -1666,7 +1727,7 @@ static const struct of_device_id qcom_pcie_match[] = {
 	{ .compatible = "qcom,pcie-msm8996", .data = &cfg_2_3_2 },
 	{ .compatible = "qcom,pcie-qcs404", .data = &cfg_2_4_0 },
 	{ .compatible = "qcom,pcie-sa8540p", .data = &cfg_sc8280xp },
-	{ .compatible = "qcom,pcie-sa8775p", .data = &cfg_1_9_0},
+	{ .compatible = "qcom,pcie-sa8775p", .data = &cfg_1_34_0},
 	{ .compatible = "qcom,pcie-sc7280", .data = &cfg_1_9_0 },
 	{ .compatible = "qcom,pcie-sc8180x", .data = &cfg_1_9_0 },
 	{ .compatible = "qcom,pcie-sc8280xp", .data = &cfg_sc8280xp },
diff --git a/drivers/pci/controller/dwc/pcie-rcar-gen4.c b/drivers/pci/controller/dwc/pcie-rcar-gen4.c
index 237a6a8818de..74ccc927a9cb 100644
--- a/drivers/pci/controller/dwc/pcie-rcar-gen4.c
+++ b/drivers/pci/controller/dwc/pcie-rcar-gen4.c
@@ -255,7 +255,7 @@ static struct rcar_gen4_pcie *rcar_gen4_pcie_alloc(struct platform_device *pdev)
 	rcar->dw.ops = &dw_pcie_ops;
 	rcar->dw.dev = dev;
 	rcar->pdev = pdev;
-	dw_pcie_cap_set(&rcar->dw, EDMA_UNROLL);
+	rcar->dw.edma.mf = EDMA_MF_EDMA_UNROLL;
 	dw_pcie_cap_set(&rcar->dw, REQ_RES);
 	platform_set_drvdata(pdev, rcar);
 
diff --git a/drivers/pci/endpoint/functions/pci-epf-mhi.c b/drivers/pci/endpoint/functions/pci-epf-mhi.c
index 5832989e55e8..7d070b1def11 100644
--- a/drivers/pci/endpoint/functions/pci-epf-mhi.c
+++ b/drivers/pci/endpoint/functions/pci-epf-mhi.c
@@ -137,6 +137,7 @@ static const struct pci_epf_mhi_ep_info sa8775p_info = {
 	.epf_flags = PCI_BASE_ADDRESS_MEM_TYPE_32,
 	.msi_count = 32,
 	.mru = 0x8000,
+	.flags = MHI_EPF_USE_DMA,
 };
 
 struct pci_epf_mhi {
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 8cf0941f70d1..02b1d81b1419 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -6100,24 +6100,7 @@ int pcie_link_speed_mbps(struct pci_dev *pdev)
 	if (err)
 		return err;
 
-	switch (to_pcie_link_speed(lnksta)) {
-	case PCIE_SPEED_2_5GT:
-		return 2500;
-	case PCIE_SPEED_5_0GT:
-		return 5000;
-	case PCIE_SPEED_8_0GT:
-		return 8000;
-	case PCIE_SPEED_16_0GT:
-		return 16000;
-	case PCIE_SPEED_32_0GT:
-		return 32000;
-	case PCIE_SPEED_64_0GT:
-		return 64000;
-	default:
-		break;
-	}
-
-	return -EINVAL;
+	return pcie_dev_speed_mbps(to_pcie_link_speed(lnksta));
 }
 EXPORT_SYMBOL(pcie_link_speed_mbps);
 
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index cd18205a5d0d..49a705bef180 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -326,6 +326,28 @@ void pci_bus_put(struct pci_bus *bus);
 	 (speed) == PCIE_SPEED_2_5GT  ?  2500*8/10 : \
 	 0)
 
+static inline int pcie_dev_speed_mbps(enum pci_bus_speed speed)
+{
+	switch (speed) {
+	case PCIE_SPEED_2_5GT:
+		return 2500;
+	case PCIE_SPEED_5_0GT:
+		return 5000;
+	case PCIE_SPEED_8_0GT:
+		return 8000;
+	case PCIE_SPEED_16_0GT:
+		return 16000;
+	case PCIE_SPEED_32_0GT:
+		return 32000;
+	case PCIE_SPEED_64_0GT:
+		return 64000;
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+
 const char *pci_speed_string(enum pci_bus_speed speed);
 enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev);
 enum pcie_link_width pcie_get_width_cap(struct pci_dev *dev);