Merge branch 'remotes/lorenzo/pci/aardvark'

- Define macros for PCI_EXP_DEVCTL_PAYLOAD_* (Pali Rohár)

- Set Max Payload Size to 512 bytes per Marvell spec (Pali Rohár)

- Downgrade PIO Response Status messages to debug level (Marek Behún)

- Preserve CRS SV (Config Request Retry Software Visibility) bit in
  emulated Root Control register (Pali Rohár)

- Fix issue in configuring reference clock (Pali Rohár)

- Don't clear status bits for masked interrupts (Pali Rohár)

- Don't mask unused interrupts (Pali Rohár)

- Avoid code repetition in advk_pcie_rd_conf() (Marek Behún)

- Retry config accesses on CRS response (Pali Rohár)

- Simplify emulated Root Capabilities initialization (Pali Rohár)

- Fix several link training issues (Pali Rohár)

- Fix link-up checking via LTSSM (Pali Rohár)

- Fix reporting of Data Link Layer Link Active (Pali Rohár)

- Fix emulation of W1C bits (Marek Behún)

- Fix MSI domain .alloc() method to return zero on success (Marek Behún)

- Read entire 16-bit MSI vector in MSI handler, not just low 8 bits (Marek
  Behún)

- Clear Root Port I/O Space, Memory Space, and Bus Master Enable bits at
  startup; PCI core will set those as necessary (Pali Rohár)

- When operating as a Root Port, set class code to "PCI Bridge" instead of
  the default "Mass Storage Controller" (Pali Rohár)

- Add emulation for PCI_BRIDGE_CTL_BUS_RESET since aardvark doesn't
  implement this per spec (Pali Rohár)

- Add emulation of option ROM BAR since aardvark doesn't implement this per
  spec (Pali Rohár)

* remotes/lorenzo/pci/aardvark:
  PCI: aardvark: Fix support for PCI_ROM_ADDRESS1 on emulated bridge
  PCI: aardvark: Fix support for PCI_BRIDGE_CTL_BUS_RESET on emulated bridge
  PCI: aardvark: Set PCI Bridge Class Code to PCI Bridge
  PCI: aardvark: Fix support for bus mastering and PCI_COMMAND on emulated bridge
  PCI: aardvark: Read all 16-bits from PCIE_MSI_PAYLOAD_REG
  PCI: aardvark: Fix return value of MSI domain .alloc() method
  PCI: pci-bridge-emul: Fix emulation of W1C bits
  PCI: aardvark: Fix reporting Data Link Layer Link Active
  PCI: aardvark: Fix checking for link up via LTSSM state
  PCI: aardvark: Fix link training
  PCI: aardvark: Simplify initialization of rootcap on virtual bridge
  PCI: aardvark: Implement re-issuing config requests on CRS response
  PCI: aardvark: Deduplicate code in advk_pcie_rd_conf()
  PCI: aardvark: Do not unmask unused interrupts
  PCI: aardvark: Do not clear status bits of masked interrupts
  PCI: aardvark: Fix configuring Reference clock
  PCI: aardvark: Fix preserving PCI_EXP_RTCTL_CRSSVE flag on emulated bridge
  PCI: aardvark: Don't spam about PIO Response Status
  PCI: aardvark: Fix PCIe Max Payload Size setting
  PCI: Add PCI_EXP_DEVCTL_PAYLOAD_* macros

2 files changed, 325 insertions, 179 deletions

diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c
index 596ebcfcc82d..c5300d49807a 100644
--- a/drivers/pci/controller/pci-aardvark.c
+++ b/drivers/pci/controller/pci-aardvark.c
@@ -31,10 +31,8 @@
 /* PCIe core registers */
 #define PCIE_CORE_DEV_ID_REG					0x0
 #define PCIE_CORE_CMD_STATUS_REG				0x4
-#define     PCIE_CORE_CMD_IO_ACCESS_EN				BIT(0)
-#define     PCIE_CORE_CMD_MEM_ACCESS_EN				BIT(1)
-#define     PCIE_CORE_CMD_MEM_IO_REQ_EN				BIT(2)
 #define PCIE_CORE_DEV_REV_REG					0x8
+#define PCIE_CORE_EXP_ROM_BAR_REG				0x30
 #define PCIE_CORE_PCIEXP_CAP					0xc0
 #define PCIE_CORE_ERR_CAPCTL_REG				0x118
 #define     PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX			BIT(5)
@@ -99,6 +97,7 @@
 #define     PCIE_CORE_CTRL2_MSI_ENABLE		BIT(10)
 #define PCIE_CORE_REF_CLK_REG			(CONTROL_BASE_ADDR + 0x14)
 #define     PCIE_CORE_REF_CLK_TX_ENABLE		BIT(1)
+#define     PCIE_CORE_REF_CLK_RX_ENABLE		BIT(2)
 #define PCIE_MSG_LOG_REG			(CONTROL_BASE_ADDR + 0x30)
 #define PCIE_ISR0_REG				(CONTROL_BASE_ADDR + 0x40)
 #define PCIE_MSG_PM_PME_MASK			BIT(7)
@@ -106,18 +105,19 @@
 #define     PCIE_ISR0_MSI_INT_PENDING		BIT(24)
 #define     PCIE_ISR0_INTX_ASSERT(val)		BIT(16 + (val))
 #define     PCIE_ISR0_INTX_DEASSERT(val)	BIT(20 + (val))
-#define	    PCIE_ISR0_ALL_MASK			GENMASK(26, 0)
+#define     PCIE_ISR0_ALL_MASK			GENMASK(31, 0)
 #define PCIE_ISR1_REG				(CONTROL_BASE_ADDR + 0x48)
 #define PCIE_ISR1_MASK_REG			(CONTROL_BASE_ADDR + 0x4C)
 #define     PCIE_ISR1_POWER_STATE_CHANGE	BIT(4)
 #define     PCIE_ISR1_FLUSH			BIT(5)
 #define     PCIE_ISR1_INTX_ASSERT(val)		BIT(8 + (val))
-#define     PCIE_ISR1_ALL_MASK			GENMASK(11, 4)
+#define     PCIE_ISR1_ALL_MASK			GENMASK(31, 0)
 #define PCIE_MSI_ADDR_LOW_REG			(CONTROL_BASE_ADDR + 0x50)
 #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_PAYLOAD_REG			(CONTROL_BASE_ADDR + 0x9C)
+#define     PCIE_MSI_DATA_MASK			GENMASK(15, 0)
 
 /* PCIe window configuration */
 #define OB_WIN_BASE_ADDR			0x4c00
@@ -164,8 +164,50 @@
 #define CFG_REG					(LMI_BASE_ADDR + 0x0)
 #define     LTSSM_SHIFT				24
 #define     LTSSM_MASK				0x3f
-#define     LTSSM_L0				0x10
 #define     RC_BAR_CONFIG			0x300
+
+/* LTSSM values in CFG_REG */
+enum {
+	LTSSM_DETECT_QUIET			= 0x0,
+	LTSSM_DETECT_ACTIVE			= 0x1,
+	LTSSM_POLLING_ACTIVE			= 0x2,
+	LTSSM_POLLING_COMPLIANCE		= 0x3,
+	LTSSM_POLLING_CONFIGURATION		= 0x4,
+	LTSSM_CONFIG_LINKWIDTH_START		= 0x5,
+	LTSSM_CONFIG_LINKWIDTH_ACCEPT		= 0x6,
+	LTSSM_CONFIG_LANENUM_ACCEPT		= 0x7,
+	LTSSM_CONFIG_LANENUM_WAIT		= 0x8,
+	LTSSM_CONFIG_COMPLETE			= 0x9,
+	LTSSM_CONFIG_IDLE			= 0xa,
+	LTSSM_RECOVERY_RCVR_LOCK		= 0xb,
+	LTSSM_RECOVERY_SPEED			= 0xc,
+	LTSSM_RECOVERY_RCVR_CFG			= 0xd,
+	LTSSM_RECOVERY_IDLE			= 0xe,
+	LTSSM_L0				= 0x10,
+	LTSSM_RX_L0S_ENTRY			= 0x11,
+	LTSSM_RX_L0S_IDLE			= 0x12,
+	LTSSM_RX_L0S_FTS			= 0x13,
+	LTSSM_TX_L0S_ENTRY			= 0x14,
+	LTSSM_TX_L0S_IDLE			= 0x15,
+	LTSSM_TX_L0S_FTS			= 0x16,
+	LTSSM_L1_ENTRY				= 0x17,
+	LTSSM_L1_IDLE				= 0x18,
+	LTSSM_L2_IDLE				= 0x19,
+	LTSSM_L2_TRANSMIT_WAKE			= 0x1a,
+	LTSSM_DISABLED				= 0x20,
+	LTSSM_LOOPBACK_ENTRY_MASTER		= 0x21,
+	LTSSM_LOOPBACK_ACTIVE_MASTER		= 0x22,
+	LTSSM_LOOPBACK_EXIT_MASTER		= 0x23,
+	LTSSM_LOOPBACK_ENTRY_SLAVE		= 0x24,
+	LTSSM_LOOPBACK_ACTIVE_SLAVE		= 0x25,
+	LTSSM_LOOPBACK_EXIT_SLAVE		= 0x26,
+	LTSSM_HOT_RESET				= 0x27,
+	LTSSM_RECOVERY_EQUALIZATION_PHASE0	= 0x28,
+	LTSSM_RECOVERY_EQUALIZATION_PHASE1	= 0x29,
+	LTSSM_RECOVERY_EQUALIZATION_PHASE2	= 0x2a,
+	LTSSM_RECOVERY_EQUALIZATION_PHASE3	= 0x2b,
+};
+
 #define VENDOR_ID_REG				(LMI_BASE_ADDR + 0x44)
 
 /* PCIe core controller registers */
@@ -198,7 +240,7 @@
 #define     PCIE_IRQ_MSI_INT2_DET		BIT(21)
 #define     PCIE_IRQ_RC_DBELL_DET		BIT(22)
 #define     PCIE_IRQ_EP_STATUS			BIT(23)
-#define     PCIE_IRQ_ALL_MASK			0xfff0fb
+#define     PCIE_IRQ_ALL_MASK			GENMASK(31, 0)
 #define     PCIE_IRQ_ENABLE_INTS_MASK		PCIE_IRQ_CORE_INT
 
 /* Transaction types */
@@ -257,18 +299,49 @@ static inline u32 advk_readl(struct advk_pcie *pcie, u64 reg)
 	return readl(pcie->base + reg);
 }
 
-static inline u16 advk_read16(struct advk_pcie *pcie, u64 reg)
+static u8 advk_pcie_ltssm_state(struct advk_pcie *pcie)
 {
-	return advk_readl(pcie, (reg & ~0x3)) >> ((reg & 0x3) * 8);
+	u32 val;
+	u8 ltssm_state;
+
+	val = advk_readl(pcie, CFG_REG);
+	ltssm_state = (val >> LTSSM_SHIFT) & LTSSM_MASK;
+	return ltssm_state;
 }
 
-static int advk_pcie_link_up(struct advk_pcie *pcie)
+static inline bool advk_pcie_link_up(struct advk_pcie *pcie)
 {
-	u32 val, ltssm_state;
+	/* check if LTSSM is in normal operation - some L* state */
+	u8 ltssm_state = advk_pcie_ltssm_state(pcie);
+	return ltssm_state >= LTSSM_L0 && ltssm_state < LTSSM_DISABLED;
+}
 
-	val = advk_readl(pcie, CFG_REG);
-	ltssm_state = (val >> LTSSM_SHIFT) & LTSSM_MASK;
-	return ltssm_state >= LTSSM_L0;
+static inline bool advk_pcie_link_active(struct advk_pcie *pcie)
+{
+	/*
+	 * According to PCIe Base specification 3.0, Table 4-14: Link
+	 * Status Mapped to the LTSSM, and 4.2.6.3.6 Configuration.Idle
+	 * is Link Up mapped to LTSSM Configuration.Idle, Recovery, L0,
+	 * L0s, L1 and L2 states. And according to 3.2.1. Data Link
+	 * Control and Management State Machine Rules is DL Up status
+	 * reported in DL Active state.
+	 */
+	u8 ltssm_state = advk_pcie_ltssm_state(pcie);
+	return ltssm_state >= LTSSM_CONFIG_IDLE && ltssm_state < LTSSM_DISABLED;
+}
+
+static inline bool advk_pcie_link_training(struct advk_pcie *pcie)
+{
+	/*
+	 * According to PCIe Base specification 3.0, Table 4-14: Link
+	 * Status Mapped to the LTSSM is Link Training mapped to LTSSM
+	 * Configuration and Recovery states.
+	 */
+	u8 ltssm_state = advk_pcie_ltssm_state(pcie);
+	return ((ltssm_state >= LTSSM_CONFIG_LINKWIDTH_START &&
+		 ltssm_state < LTSSM_L0) ||
+		(ltssm_state >= LTSSM_RECOVERY_EQUALIZATION_PHASE0 &&
+		 ltssm_state <= LTSSM_RECOVERY_EQUALIZATION_PHASE3));
 }
 
 static int advk_pcie_wait_for_link(struct advk_pcie *pcie)
@@ -291,7 +364,7 @@ static void advk_pcie_wait_for_retrain(struct advk_pcie *pcie)
 	size_t retries;
 
 	for (retries = 0; retries < RETRAIN_WAIT_MAX_RETRIES; ++retries) {
-		if (!advk_pcie_link_up(pcie))
+		if (advk_pcie_link_training(pcie))
 			break;
 		udelay(RETRAIN_WAIT_USLEEP_US);
 	}
@@ -299,23 +372,9 @@ static void advk_pcie_wait_for_retrain(struct advk_pcie *pcie)
 
 static void advk_pcie_issue_perst(struct advk_pcie *pcie)
 {
-	u32 reg;
-
 	if (!pcie->reset_gpio)
 		return;
 
-	/*
-	 * As required by PCI Express spec (PCI Express Base Specification, REV.
-	 * 4.0 PCI Express, February 19 2014, 6.6.1 Conventional Reset) a delay
-	 * for at least 100ms after de-asserting PERST# signal is needed before
-	 * link training is enabled. So ensure that link training is disabled
-	 * prior de-asserting PERST# signal to fulfill that PCI Express spec
-	 * requirement.
-	 */
-	reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
-	reg &= ~LINK_TRAINING_EN;
-	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
-
 	/* 10ms delay is needed for some cards */
 	dev_info(&pcie->pdev->dev, "issuing PERST via reset GPIO for 10ms\n");
 	gpiod_set_value_cansleep(pcie->reset_gpio, 1);
@@ -323,54 +382,47 @@ static void advk_pcie_issue_perst(struct advk_pcie *pcie)
 	gpiod_set_value_cansleep(pcie->reset_gpio, 0);
 }
 
-static int advk_pcie_train_at_gen(struct advk_pcie *pcie, int gen)
+static void advk_pcie_train_link(struct advk_pcie *pcie)
 {
-	int ret, neg_gen;
+	struct device *dev = &pcie->pdev->dev;
 	u32 reg;
+	int ret;
 
-	/* Setup link speed */
+	/*
+	 * Setup PCIe rev / gen compliance based on device tree property
+	 * 'max-link-speed' which also forces maximal link speed.
+	 */
 	reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
 	reg &= ~PCIE_GEN_SEL_MSK;
-	if (gen == 3)
+	if (pcie->link_gen == 3)
 		reg |= SPEED_GEN_3;
-	else if (gen == 2)
+	else if (pcie->link_gen == 2)
 		reg |= SPEED_GEN_2;
 	else
 		reg |= SPEED_GEN_1;
 	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
 
 	/*
-	 * Enable link training. This is not needed in every call to this
-	 * function, just once suffices, but it does not break anything either.
+	 * Set maximal link speed value also into PCIe Link Control 2 register.
+	 * Armada 3700 Functional Specification says that default value is based
+	 * on SPEED_GEN but tests showed that default value is always 8.0 GT/s.
 	 */
+	reg = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL2);
+	reg &= ~PCI_EXP_LNKCTL2_TLS;
+	if (pcie->link_gen == 3)
+		reg |= PCI_EXP_LNKCTL2_TLS_8_0GT;
+	else if (pcie->link_gen == 2)
+		reg |= PCI_EXP_LNKCTL2_TLS_5_0GT;
+	else
+		reg |= PCI_EXP_LNKCTL2_TLS_2_5GT;
+	advk_writel(pcie, reg, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL2);
+
+	/* Enable link training after selecting PCIe generation */
 	reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
 	reg |= LINK_TRAINING_EN;
 	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
 
 	/*
-	 * Start link training immediately after enabling it.
-	 * This solves problems for some buggy cards.
-	 */
-	reg = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL);
-	reg |= PCI_EXP_LNKCTL_RL;
-	advk_writel(pcie, reg, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL);
-
-	ret = advk_pcie_wait_for_link(pcie);
-	if (ret)
-		return ret;
-
-	reg = advk_read16(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKSTA);
-	neg_gen = reg & PCI_EXP_LNKSTA_CLS;
-
-	return neg_gen;
-}
-
-static void advk_pcie_train_link(struct advk_pcie *pcie)
-{
-	struct device *dev = &pcie->pdev->dev;
-	int neg_gen = -1, gen;
-
-	/*
 	 * Reset PCIe card via PERST# signal. Some cards are not detected
 	 * during link training when they are in some non-initial state.
 	 */
@@ -380,41 +432,18 @@ static void advk_pcie_train_link(struct advk_pcie *pcie)
 	 * PERST# signal could have been asserted by pinctrl subsystem before
 	 * probe() callback has been called or issued explicitly by reset gpio
 	 * function advk_pcie_issue_perst(), making the endpoint going into
-	 * fundamental reset. As required by PCI Express spec a delay for at
-	 * least 100ms after such a reset before link training is needed.
+	 * fundamental reset. As required by PCI Express spec (PCI Express
+	 * Base Specification, REV. 4.0 PCI Express, February 19 2014, 6.6.1
+	 * Conventional Reset) a delay for at least 100ms after such a reset
+	 * before sending a Configuration Request to the device is needed.
+	 * So wait until PCIe link is up. Function advk_pcie_wait_for_link()
+	 * waits for link at least 900ms.
 	 */
-	msleep(PCI_PM_D3COLD_WAIT);
-
-	/*
-	 * Try link training at link gen specified by device tree property
-	 * 'max-link-speed'. If this fails, iteratively train at lower gen.
-	 */
-	for (gen = pcie->link_gen; gen > 0; --gen) {
-		neg_gen = advk_pcie_train_at_gen(pcie, gen);
-		if (neg_gen > 0)
-			break;
-	}
-
-	if (neg_gen < 0)
-		goto err;
-
-	/*
-	 * After successful training if negotiated gen is lower than requested,
-	 * train again on negotiated gen. This solves some stability issues for
-	 * some buggy gen1 cards.
-	 */
-	if (neg_gen < gen) {
-		gen = neg_gen;
-		neg_gen = advk_pcie_train_at_gen(pcie, gen);
-	}
-
-	if (neg_gen == gen) {
-		dev_info(dev, "link up at gen %i\n", gen);
-		return;
-	}
-
-err:
-	dev_err(dev, "link never came up\n");
+	ret = advk_pcie_wait_for_link(pcie);
+	if (ret < 0)
+		dev_err(dev, "link never came up\n");
+	else
+		dev_info(dev, "link up\n");
 }
 
 /*
@@ -451,9 +480,15 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie)
 	u32 reg;
 	int i;
 
-	/* Enable TX */
+	/*
+	 * Configure PCIe Reference clock. Direction is from the PCIe
+	 * controller to the endpoint card, so enable transmitting of
+	 * Reference clock differential signal off-chip and disable
+	 * receiving off-chip differential signal.
+	 */
 	reg = advk_readl(pcie, PCIE_CORE_REF_CLK_REG);
 	reg |= PCIE_CORE_REF_CLK_TX_ENABLE;
+	reg &= ~PCIE_CORE_REF_CLK_RX_ENABLE;
 	advk_writel(pcie, reg, PCIE_CORE_REF_CLK_REG);
 
 	/* Set to Direct mode */
@@ -477,6 +512,31 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie)
 	reg = (PCI_VENDOR_ID_MARVELL << 16) | PCI_VENDOR_ID_MARVELL;
 	advk_writel(pcie, reg, VENDOR_ID_REG);
 
+	/*
+	 * Change Class Code of PCI Bridge device to PCI Bridge (0x600400),
+	 * because the default value is Mass storage controller (0x010400).
+	 *
+	 * Note that this Aardvark PCI Bridge does not have compliant Type 1
+	 * Configuration Space and it even cannot be accessed via Aardvark's
+	 * PCI config space access method. Something like config space is
+	 * available in internal Aardvark registers starting at offset 0x0
+	 * and is reported as Type 0. In range 0x10 - 0x34 it has totally
+	 * different registers.
+	 *
+	 * Therefore driver uses emulation of PCI Bridge which emulates
+	 * access to configuration space via internal Aardvark registers or
+	 * emulated configuration buffer.
+	 */
+	reg = advk_readl(pcie, PCIE_CORE_DEV_REV_REG);
+	reg &= ~0xffffff00;
+	reg |= (PCI_CLASS_BRIDGE_PCI << 8) << 8;
+	advk_writel(pcie, reg, PCIE_CORE_DEV_REV_REG);
+
+	/* Disable Root Bridge I/O space, memory space and bus mastering */
+	reg = advk_readl(pcie, PCIE_CORE_CMD_STATUS_REG);
+	reg &= ~(PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER);
+	advk_writel(pcie, reg, PCIE_CORE_CMD_STATUS_REG);
+
 	/* Set Advanced Error Capabilities and Control PF0 register */
 	reg = PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX |
 		PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX_EN |
@@ -488,8 +548,9 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie)
 	reg = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_DEVCTL);
 	reg &= ~PCI_EXP_DEVCTL_RELAX_EN;
 	reg &= ~PCI_EXP_DEVCTL_NOSNOOP_EN;
+	reg &= ~PCI_EXP_DEVCTL_PAYLOAD;
 	reg &= ~PCI_EXP_DEVCTL_READRQ;
-	reg |= PCI_EXP_DEVCTL_PAYLOAD; /* Set max payload size */
+	reg |= PCI_EXP_DEVCTL_PAYLOAD_512B;
 	reg |= PCI_EXP_DEVCTL_READRQ_512B;
 	advk_writel(pcie, reg, PCIE_CORE_PCIEXP_CAP + PCI_EXP_DEVCTL);
 
@@ -574,19 +635,6 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie)
 		advk_pcie_disable_ob_win(pcie, i);
 
 	advk_pcie_train_link(pcie);
-
-	/*
-	 * FIXME: The following register update is suspicious. This register is
-	 * applicable only when the PCI controller is configured for Endpoint
-	 * mode, not as a Root Complex. But apparently when this code is
-	 * removed, some cards stop working. This should be investigated and
-	 * a comment explaining this should be put here.
-	 */
-	reg = advk_readl(pcie, PCIE_CORE_CMD_STATUS_REG);
-	reg |= PCIE_CORE_CMD_MEM_ACCESS_EN |
-		PCIE_CORE_CMD_IO_ACCESS_EN |
-		PCIE_CORE_CMD_MEM_IO_REQ_EN;
-	advk_writel(pcie, reg, PCIE_CORE_CMD_STATUS_REG);
 }
 
 static int advk_pcie_check_pio_status(struct advk_pcie *pcie, bool allow_crs, u32 *val)
@@ -595,6 +643,7 @@ static int advk_pcie_check_pio_status(struct advk_pcie *pcie, bool allow_crs, u3
 	u32 reg;
 	unsigned int status;
 	char *strcomp_status, *str_posted;
+	int ret;
 
 	reg = advk_readl(pcie, PIO_STAT);
 	status = (reg & PIO_COMPLETION_STATUS_MASK) >>
@@ -619,6 +668,7 @@ static int advk_pcie_check_pio_status(struct advk_pcie *pcie, bool allow_crs, u3
 	case PIO_COMPLETION_STATUS_OK:
 		if (reg & PIO_ERR_STATUS) {
 			strcomp_status = "COMP_ERR";
+			ret = -EFAULT;
 			break;
 		}
 		/* Get the read result */
@@ -626,9 +676,11 @@ static int advk_pcie_check_pio_status(struct advk_pcie *pcie, bool allow_crs, u3
 			*val = advk_readl(pcie, PIO_RD_DATA);
 		/* No error */
 		strcomp_status = NULL;
+		ret = 0;
 		break;
 	case PIO_COMPLETION_STATUS_UR:
 		strcomp_status = "UR";
+		ret = -EOPNOTSUPP;
 		break;
 	case PIO_COMPLETION_STATUS_CRS:
 		if (allow_crs && val) {
@@ -646,6 +698,7 @@ static int advk_pcie_check_pio_status(struct advk_pcie *pcie, bool allow_crs, u3
 			 */
 			*val = CFG_RD_CRS_VAL;
 			strcomp_status = NULL;
+			ret = 0;
 			break;
 		}
 		/* PCIe r4.0, sec 2.3.2, says:
@@ -661,31 +714,34 @@ static int advk_pcie_check_pio_status(struct advk_pcie *pcie, bool allow_crs, u3
 		 * Request and taking appropriate action, e.g., complete the
 		 * Request to the host as a failed transaction.
 		 *
-		 * To simplify implementation do not re-issue the Configuration
-		 * Request and complete the Request as a failed transaction.
+		 * So return -EAGAIN and caller (pci-aardvark.c driver) will
+		 * re-issue request again up to the PIO_RETRY_CNT retries.
 		 */
 		strcomp_status = "CRS";
+		ret = -EAGAIN;
 		break;
 	case PIO_COMPLETION_STATUS_CA:
 		strcomp_status = "CA";
+		ret = -ECANCELED;
 		break;
 	default:
 		strcomp_status = "Unknown";
+		ret = -EINVAL;
 		break;
 	}
 
 	if (!strcomp_status)
-		return 0;
+		return ret;
 
 	if (reg & PIO_NON_POSTED_REQ)
 		str_posted = "Non-posted";
 	else
 		str_posted = "Posted";
 
-	dev_err(dev, "%s PIO Response Status: %s, %#x @ %#x\n",
+	dev_dbg(dev, "%s PIO Response Status: %s, %#x @ %#x\n",
 		str_posted, strcomp_status, reg, advk_readl(pcie, PIO_ADDR_LS));
 
-	return -EFAULT;
+	return ret;
 }
 
 static int advk_pcie_wait_pio(struct advk_pcie *pcie)
@@ -693,13 +749,13 @@ static int advk_pcie_wait_pio(struct advk_pcie *pcie)
 	struct device *dev = &pcie->pdev->dev;
 	int i;
 
-	for (i = 0; i < PIO_RETRY_CNT; i++) {
+	for (i = 1; i <= PIO_RETRY_CNT; i++) {
 		u32 start, isr;
 
 		start = advk_readl(pcie, PIO_START);
 		isr = advk_readl(pcie, PIO_ISR);
 		if (!start && isr)
-			return 0;
+			return i;
 		udelay(PIO_RETRY_DELAY);
 	}
 
@@ -707,6 +763,72 @@ static int advk_pcie_wait_pio(struct advk_pcie *pcie)
 	return -ETIMEDOUT;
 }
 
+static pci_bridge_emul_read_status_t
+advk_pci_bridge_emul_base_conf_read(struct pci_bridge_emul *bridge,
+				    int reg, u32 *value)
+{
+	struct advk_pcie *pcie = bridge->data;
+
+	switch (reg) {
+	case PCI_COMMAND:
+		*value = advk_readl(pcie, PCIE_CORE_CMD_STATUS_REG);
+		return PCI_BRIDGE_EMUL_HANDLED;
+
+	case PCI_ROM_ADDRESS1:
+		*value = advk_readl(pcie, PCIE_CORE_EXP_ROM_BAR_REG);
+		return PCI_BRIDGE_EMUL_HANDLED;
+
+	case PCI_INTERRUPT_LINE: {
+		/*
+		 * From the whole 32bit register we support reading from HW only
+		 * one bit: PCI_BRIDGE_CTL_BUS_RESET.
+		 * Other bits are retrieved only from emulated config buffer.
+		 */
+		__le32 *cfgspace = (__le32 *)&bridge->conf;
+		u32 val = le32_to_cpu(cfgspace[PCI_INTERRUPT_LINE / 4]);
+		if (advk_readl(pcie, PCIE_CORE_CTRL1_REG) & HOT_RESET_GEN)
+			val |= PCI_BRIDGE_CTL_BUS_RESET << 16;
+		else
+			val &= ~(PCI_BRIDGE_CTL_BUS_RESET << 16);
+		*value = val;
+		return PCI_BRIDGE_EMUL_HANDLED;
+	}
+
+	default:
+		return PCI_BRIDGE_EMUL_NOT_HANDLED;
+	}
+}
+
+static void
+advk_pci_bridge_emul_base_conf_write(struct pci_bridge_emul *bridge,
+				     int reg, u32 old, u32 new, u32 mask)
+{
+	struct advk_pcie *pcie = bridge->data;
+
+	switch (reg) {
+	case PCI_COMMAND:
+		advk_writel(pcie, new, PCIE_CORE_CMD_STATUS_REG);
+		break;
+
+	case PCI_ROM_ADDRESS1:
+		advk_writel(pcie, new, PCIE_CORE_EXP_ROM_BAR_REG);
+		break;
+
+	case PCI_INTERRUPT_LINE:
+		if (mask & (PCI_BRIDGE_CTL_BUS_RESET << 16)) {
+			u32 val = advk_readl(pcie, PCIE_CORE_CTRL1_REG);
+			if (new & (PCI_BRIDGE_CTL_BUS_RESET << 16))
+				val |= HOT_RESET_GEN;
+			else
+				val &= ~HOT_RESET_GEN;
+			advk_writel(pcie, val, PCIE_CORE_CTRL1_REG);
+		}
+		break;
+
+	default:
+		break;
+	}
+}
 
 static pci_bridge_emul_read_status_t
 advk_pci_bridge_emul_pcie_conf_read(struct pci_bridge_emul *bridge,
@@ -723,6 +845,7 @@ advk_pci_bridge_emul_pcie_conf_read(struct pci_bridge_emul *bridge,
 	case PCI_EXP_RTCTL: {
 		u32 val = advk_readl(pcie, PCIE_ISR0_MASK_REG);
 		*value = (val & PCIE_MSG_PM_PME_MASK) ? 0 : PCI_EXP_RTCTL_PMEIE;
+		*value |= le16_to_cpu(bridge->pcie_conf.rootctl) & PCI_EXP_RTCTL_CRSSVE;
 		*value |= PCI_EXP_RTCAP_CRSVIS << 16;
 		return PCI_BRIDGE_EMUL_HANDLED;
 	}
@@ -734,12 +857,26 @@ advk_pci_bridge_emul_pcie_conf_read(struct pci_bridge_emul *bridge,
 		return PCI_BRIDGE_EMUL_HANDLED;
 	}
 
+	case PCI_EXP_LNKCAP: {
+		u32 val = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + reg);
+		/*
+		 * PCI_EXP_LNKCAP_DLLLARC bit is hardwired in aardvark HW to 0.
+		 * But support for PCI_EXP_LNKSTA_DLLLA is emulated via ltssm
+		 * state so explicitly enable PCI_EXP_LNKCAP_DLLLARC flag.
+		 */
+		val |= PCI_EXP_LNKCAP_DLLLARC;
+		*value = val;
+		return PCI_BRIDGE_EMUL_HANDLED;
+	}
+
 	case PCI_EXP_LNKCTL: {
 		/* u32 contains both PCI_EXP_LNKCTL and PCI_EXP_LNKSTA */
 		u32 val = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + reg) &
 			~(PCI_EXP_LNKSTA_LT << 16);
-		if (!advk_pcie_link_up(pcie))
+		if (advk_pcie_link_training(pcie))
 			val |= (PCI_EXP_LNKSTA_LT << 16);
+		if (advk_pcie_link_active(pcie))
+			val |= (PCI_EXP_LNKSTA_DLLLA << 16);
 		*value = val;
 		return PCI_BRIDGE_EMUL_HANDLED;
 	}
@@ -747,7 +884,6 @@ advk_pci_bridge_emul_pcie_conf_read(struct pci_bridge_emul *bridge,
 	case PCI_CAP_LIST_ID:
 	case PCI_EXP_DEVCAP:
 	case PCI_EXP_DEVCTL:
-	case PCI_EXP_LNKCAP:
 		*value = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + reg);
 		return PCI_BRIDGE_EMUL_HANDLED;
 	default:
@@ -794,6 +930,8 @@ advk_pci_bridge_emul_pcie_conf_write(struct pci_bridge_emul *bridge,
 }
 
 static struct pci_bridge_emul_ops advk_pci_bridge_emul_ops = {
+	.read_base = advk_pci_bridge_emul_base_conf_read,
+	.write_base = advk_pci_bridge_emul_base_conf_write,
 	.read_pcie = advk_pci_bridge_emul_pcie_conf_read,
 	.write_pcie = advk_pci_bridge_emul_pcie_conf_write,
 };
@@ -805,7 +943,6 @@ static struct pci_bridge_emul_ops advk_pci_bridge_emul_ops = {
 static int advk_sw_pci_bridge_init(struct advk_pcie *pcie)
 {
 	struct pci_bridge_emul *bridge = &pcie->bridge;
-	int ret;
 
 	bridge->conf.vendor =
 		cpu_to_le16(advk_readl(pcie, PCIE_CORE_DEV_ID_REG) & 0xffff);
@@ -825,19 +962,14 @@ static int advk_sw_pci_bridge_init(struct advk_pcie *pcie)
 	/* Support interrupt A for MSI feature */
 	bridge->conf.intpin = PCIE_CORE_INT_A_ASSERT_ENABLE;
 
+	/* Indicates supports for Completion Retry Status */
+	bridge->pcie_conf.rootcap = cpu_to_le16(PCI_EXP_RTCAP_CRSVIS);
+
 	bridge->has_pcie = true;
 	bridge->data = pcie;
 	bridge->ops = &advk_pci_bridge_emul_ops;
 
-	/* PCIe config space can be initialized after pci_bridge_emul_init() */
-	ret = pci_bridge_emul_init(bridge, 0);
-	if (ret < 0)
-		return ret;
-
-	/* Indicates supports for Completion Retry Status */
-	bridge->pcie_conf.rootcap = cpu_to_le16(PCI_EXP_RTCAP_CRSVIS);
-
-	return 0;
+	return pci_bridge_emul_init(bridge, 0);
 }
 
 static bool advk_pcie_valid_device(struct advk_pcie *pcie, struct pci_bus *bus,
@@ -889,6 +1021,7 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn,
 			     int where, int size, u32 *val)
 {
 	struct advk_pcie *pcie = bus->sysdata;
+	int retry_count;
 	bool allow_crs;
 	u32 reg;
 	int ret;
@@ -911,18 +1044,8 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn,
 		    (le16_to_cpu(pcie->bridge.pcie_conf.rootctl) &
 		     PCI_EXP_RTCTL_CRSSVE);
 
-	if (advk_pcie_pio_is_running(pcie)) {
-		/*
-		 * If it is possible return Completion Retry Status so caller
-		 * tries to issue the request again instead of failing.
-		 */
-		if (allow_crs) {
-			*val = CFG_RD_CRS_VAL;
-			return PCIBIOS_SUCCESSFUL;
-		}
-		*val = 0xffffffff;
-		return PCIBIOS_SET_FAILED;
-	}
+	if (advk_pcie_pio_is_running(pcie))
+		goto try_crs;
 
 	/* Program the control register */
 	reg = advk_readl(pcie, PIO_CTRL);
@@ -941,30 +1064,24 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn,
 	/* Program the data strobe */
 	advk_writel(pcie, 0xf, PIO_WR_DATA_STRB);
 
-	/* Clear PIO DONE ISR and start the transfer */
-	advk_writel(pcie, 1, PIO_ISR);
-	advk_writel(pcie, 1, PIO_START);
+	retry_count = 0;
+	do {
+		/* Clear PIO DONE ISR and start the transfer */
+		advk_writel(pcie, 1, PIO_ISR);
+		advk_writel(pcie, 1, PIO_START);
 
-	ret = advk_pcie_wait_pio(pcie);
-	if (ret < 0) {
-		/*
-		 * If it is possible return Completion Retry Status so caller
-		 * tries to issue the request again instead of failing.
-		 */
-		if (allow_crs) {
-			*val = CFG_RD_CRS_VAL;
-			return PCIBIOS_SUCCESSFUL;
-		}
-		*val = 0xffffffff;
-		return PCIBIOS_SET_FAILED;
-	}
+		ret = advk_pcie_wait_pio(pcie);
+		if (ret < 0)
+			goto try_crs;
 
-	/* Check PIO status and get the read result */
-	ret = advk_pcie_check_pio_status(pcie, allow_crs, val);
-	if (ret < 0) {
-		*val = 0xffffffff;
-		return PCIBIOS_SET_FAILED;
-	}
+		retry_count += ret;
+
+		/* Check PIO status and get the read result */
+		ret = advk_pcie_check_pio_status(pcie, allow_crs, val);
+	} while (ret == -EAGAIN && retry_count < PIO_RETRY_CNT);
+
+	if (ret < 0)
+		goto fail;
 
 	if (size == 1)
 		*val = (*val >> (8 * (where & 3))) & 0xff;
@@ -972,6 +1089,20 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn,
 		*val = (*val >> (8 * (where & 3))) & 0xffff;
 
 	return PCIBIOS_SUCCESSFUL;
+
+try_crs:
+	/*
+	 * If it is possible, return Completion Retry Status so that caller
+	 * tries to issue the request again instead of failing.
+	 */
+	if (allow_crs) {
+		*val = CFG_RD_CRS_VAL;
+		return PCIBIOS_SUCCESSFUL;
+	}
+
+fail:
+	*val = 0xffffffff;
+	return PCIBIOS_SET_FAILED;
 }
 
 static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn,
@@ -980,6 +1111,7 @@ static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn,
 	struct advk_pcie *pcie = bus->sysdata;
 	u32 reg;
 	u32 data_strobe = 0x0;
+	int retry_count;
 	int offset;
 	int ret;
 
@@ -1021,19 +1153,22 @@ static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn,
 	/* Program the data strobe */
 	advk_writel(pcie, data_strobe, PIO_WR_DATA_STRB);
 
-	/* Clear PIO DONE ISR and start the transfer */
-	advk_writel(pcie, 1, PIO_ISR);
-	advk_writel(pcie, 1, PIO_START);
+	retry_count = 0;
+	do {
+		/* Clear PIO DONE ISR and start the transfer */
+		advk_writel(pcie, 1, PIO_ISR);
+		advk_writel(pcie, 1, PIO_START);
 
-	ret = advk_pcie_wait_pio(pcie);
-	if (ret < 0)
-		return PCIBIOS_SET_FAILED;
+		ret = advk_pcie_wait_pio(pcie);
+		if (ret < 0)
+			return PCIBIOS_SET_FAILED;
 
-	ret = advk_pcie_check_pio_status(pcie, false, NULL);
-	if (ret < 0)
-		return PCIBIOS_SET_FAILED;
+		retry_count += ret;
 
-	return PCIBIOS_SUCCESSFUL;
+		ret = advk_pcie_check_pio_status(pcie, false, NULL);
+	} while (ret == -EAGAIN && retry_count < PIO_RETRY_CNT);
+
+	return ret < 0 ? PCIBIOS_SET_FAILED : PCIBIOS_SUCCESSFUL;
 }
 
 static struct pci_ops advk_pcie_ops = {
@@ -1082,7 +1217,7 @@ static int advk_msi_irq_domain_alloc(struct irq_domain *domain,
 				    domain->host_data, handle_simple_irq,
 				    NULL, NULL);
 
-	return hwirq;
+	return 0;
 }
 
 static void advk_msi_irq_domain_free(struct irq_domain *domain,
@@ -1263,8 +1398,12 @@ static void advk_pcie_handle_msi(struct advk_pcie *pcie)
 		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) & 0xFF;
+		msi_data = advk_readl(pcie, PCIE_MSI_PAYLOAD_REG) & PCIE_MSI_DATA_MASK;
 		generic_handle_irq(msi_data);
 	}
 
@@ -1286,12 +1425,6 @@ static void advk_pcie_handle_int(struct advk_pcie *pcie)
 	isr1_mask = advk_readl(pcie, PCIE_ISR1_MASK_REG);
 	isr1_status = isr1_val & ((~isr1_mask) & PCIE_ISR1_ALL_MASK);
 
-	if (!isr0_status && !isr1_status) {
-		advk_writel(pcie, isr0_val, PCIE_ISR0_REG);
-		advk_writel(pcie, isr1_val, PCIE_ISR1_REG);
-		return;
-	}
-
 	/* Process MSI interrupts */
 	if (isr0_status & PCIE_ISR0_MSI_INT_PENDING)
 		advk_pcie_handle_msi(pcie);
diff --git a/drivers/pci/pci-bridge-emul.c b/drivers/pci/pci-bridge-emul.c
index fdaf86a888b7..db97cddfc85e 100644
--- a/drivers/pci/pci-bridge-emul.c
+++ b/drivers/pci/pci-bridge-emul.c
@@ -431,8 +431,21 @@ int pci_bridge_emul_conf_write(struct pci_bridge_emul *bridge, int where,
 	/* Clear the W1C bits */
 	new &= ~((value << shift) & (behavior[reg / 4].w1c & mask));
 
+	/* Save the new value with the cleared W1C bits into the cfgspace */
 	cfgspace[reg / 4] = cpu_to_le32(new);
 
+	/*
+	 * Clear the W1C bits not specified by the write mask, so that the
+	 * write_op() does not clear them.
+	 */
+	new &= ~(behavior[reg / 4].w1c & ~mask);
+
+	/*
+	 * Set the W1C bits specified by the write mask, so that write_op()
+	 * knows about that they are to be cleared.
+	 */
+	new |= (value << shift) & (behavior[reg / 4].w1c & mask);
+
 	if (write_op)
 		write_op(bridge, reg, old, new, mask);