[PATCH V3 00/29] Enable Tegra PCIe root port features

[PATCH V3 00/29] Enable Tegra PCIe root port features

[Manikanta Maddireddy]

This series of patches adds,
- Tegra root port features like Gen2, AER, etc
- Power and perf optimizations
- Fixes like "power up sequence", "dev_err prints", etc

This series of patches are tested on Tegra186 based Jetson-TX2, Tegra210
based Jetson-TX1, T124 based Jetson-TK1 platforms, Tegra20 and Tegra30
platforms.

Manikanta Maddireddy (29):
  soc/tegra: pmc: Export tegra_powergate_power_on()
  PCI: tegra: Handle failure cases in tegra_pcie_power_on()
  PCI: tegra: Rearrange Tegra PCIe driver functions
  PCI: tegra: Mask AFI_INTR in runtime suspend
  PCI: tegra: Fix PCIe host power up sequence
  PCI: tegra: Add PCIe Gen2 link speed support
  PCI: tegra: Advertise PCIe Advanced Error Reporting (AER) capability
  PCI: tegra: Program UPHY electrical settings for Tegra210
  PCI: tegra: Enable opportunistic UpdateFC and ACK
  PCI: tegra: Disable AFI dynamic clock gating
  PCI: tegra: Process pending DLL transactions before entering L1 or L2
  PCI: tegra: Enable PCIe xclk clock clamping
  PCI: tegra: Increase the deskew retry time
  PCI: tegra: Add SW fixup for RAW violations
  PCI: tegra: Update flow control timer frequency in Tegra210
  PCI: tegra: Set target speed as Gen1 before starting LTSSM
  PCI: tegra: Fix PLLE power down issue due to CLKREQ# signal
  PCI: tegra: Program AFI_CACHE* registers only for Tegra20
  PCI: tegra: Change PRSNT_SENSE IRQ log to debug
  PCI: tegra: Use legacy IRQ for port service drivers
  PCI: tegra: Add AFI_PEX2_CTRL reg offset as part of soc struct
  PCI: tegra: Access endpoint config only if PCIe link is up
  dt-bindings: pci: tegra: Document PCIe DPD pinctrl optional prop
  arm64: tegra: Add PEX DPD states as pinctrl properties
  PCI: tegra: Put PEX CLK & BIAS pads in DPD mode
  PCI: Add DT binding for "reset-gpios" property
  PCI: OF: Add of_pci_get_reset_gpio() to parse reset-gpios from DT
  PCI: tegra: Add support for GPIO based PERST#
  PCI: tegra: Change link retry log level to debug

 .../bindings/pci/nvidia,tegra20-pcie.txt      |   8 +
 Documentation/devicetree/bindings/pci/pci.txt |   3 +
 arch/arm64/boot/dts/nvidia/tegra210.dtsi      |  19 +
 drivers/pci/controller/pci-tegra.c            | 616 +++++++++++++++---
 drivers/pci/of.c                              |  18 +
 drivers/soc/tegra/pmc.c                       |   1 +
 include/linux/of_pci.h                        |  10 +
 7 files changed, 595 insertions(+), 80 deletions(-)

-- 
2.17.1

[PATCH V3 01/29] soc/tegra: pmc: Export tegra_powergate_power_on()

[Manikanta Maddireddy]

tegra_powergate_sequence_power_up() powers up partition and also enables
clock & reset. However, if a controller like PCIe have multiple clocks
& resets and they need to be enabled in a sequence, driver must use
standalone function tegra_powergate_power_on() to power up partition.

Export tegra_powergate_power_on() to allow Tegra controller drivers to
unpower gate partition independent to clock & reset.

Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
---
V3: No change

V2: No change

 drivers/soc/tegra/pmc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/soc/tegra/pmc.c b/drivers/soc/tegra/pmc.c
index 0c5f79528e5f..cb3de81348bd 100644
--- a/drivers/soc/tegra/pmc.c
+++ b/drivers/soc/tegra/pmc.c
@@ -701,6 +701,7 @@ int tegra_powergate_power_on(unsigned int id)
 
 	return tegra_powergate_set(pmc, id, true);
 }
+EXPORT_SYMBOL(tegra_powergate_power_on);
 
 /**
  * tegra_powergate_power_off() - power off partition
-- 
2.17.1

[PATCH V3 02/29] PCI: tegra: Handle failure cases in tegra_pcie_power_on()

[Manikanta Maddireddy]

Unroll the PCIe power on sequence if any one of the steps fail in
tegra_pcie_power_on().

Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
---
V3: No change

V2: New patch to handle error cleanup in tegra_pcie_power_on().

 drivers/pci/controller/pci-tegra.c | 26 +++++++++++++++++++++-----
 1 file changed, 21 insertions(+), 5 deletions(-)

diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index f4f53d092e00..8235d937951b 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -1052,7 +1052,7 @@ static int tegra_pcie_power_on(struct tegra_pcie *pcie)
 		err = clk_prepare_enable(pcie->pex_clk);
 		if (err) {
 			dev_err(dev, "failed to enable PEX clock: %d\n", err);
-			return err;
+			goto regulator_disable;
 		}
 		reset_control_deassert(pcie->pex_rst);
 	} else {
@@ -1061,7 +1061,7 @@ static int tegra_pcie_power_on(struct tegra_pcie *pcie)
 							pcie->pex_rst);
 		if (err) {
 			dev_err(dev, "powerup sequence failed: %d\n", err);
-			return err;
+			goto regulator_disable;
 		}
 	}
 
@@ -1070,24 +1070,40 @@ static int tegra_pcie_power_on(struct tegra_pcie *pcie)
 	err = clk_prepare_enable(pcie->afi_clk);
 	if (err < 0) {
 		dev_err(dev, "failed to enable AFI clock: %d\n", err);
-		return err;
+		goto powergate;
 	}
 
 	if (soc->has_cml_clk) {
 		err = clk_prepare_enable(pcie->cml_clk);
 		if (err < 0) {
 			dev_err(dev, "failed to enable CML clock: %d\n", err);
-			return err;
+			goto disable_afi_clk;
 		}
 	}
 
 	err = clk_prepare_enable(pcie->pll_e);
 	if (err < 0) {
 		dev_err(dev, "failed to enable PLLE clock: %d\n", err);
-		return err;
+		goto disable_cml_clk;
 	}
 
 	return 0;
+
+disable_cml_clk:
+	if (soc->has_cml_clk)
+		clk_disable_unprepare(pcie->cml_clk);
+disable_afi_clk:
+	clk_disable_unprepare(pcie->afi_clk);
+powergate:
+	reset_control_assert(pcie->afi_rst);
+	reset_control_assert(pcie->pex_rst);
+	clk_disable_unprepare(pcie->pex_clk);
+	if (!dev->pm_domain)
+		tegra_powergate_power_off(TEGRA_POWERGATE_PCIE);
+regulator_disable:
+	regulator_bulk_disable(pcie->num_supplies, pcie->supplies);
+
+	return err;
 }
 
 static int tegra_pcie_clocks_get(struct tegra_pcie *pcie)
-- 
2.17.1

[PATCH V3 03/29] PCI: tegra: Rearrange Tegra PCIe driver functions

[Manikanta Maddireddy]

Tegra PCIe has register spec for,
 - AXI to FPCI(AFI) bridge
 - Multiple PCIe root ports
 - PCIe PHY
 - PCIe pad control

Rearrange Tegra PCIe driver functions such that each function programs
required module only.
 - tegra_pcie_enable_controller(): Program AFI module and enable PCIe
controller.
 - tegra_pcie_phy_power_on(): Bring up PCIe PHY.
 - tegra_pcie_apply_pad_settings(): Program PCIe REFCLK pad settings.
 - tegra_pcie_enable_ports(): Program each root port and bring up PCIe
link.

Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
---
V3: No change

V2: This is new patch in V2

 drivers/pci/controller/pci-tegra.c | 70 +++++++++++++-----------------
 1 file changed, 30 insertions(+), 40 deletions(-)

diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index 8235d937951b..bb3c0af9c830 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -852,7 +852,6 @@ static int tegra_pcie_port_phy_power_off(struct tegra_pcie_port *port)
 static int tegra_pcie_phy_power_on(struct tegra_pcie *pcie)
 {
 	struct device *dev = pcie->dev;
-	const struct tegra_pcie_soc *soc = pcie->soc;
 	struct tegra_pcie_port *port;
 	int err;
 
@@ -878,12 +877,6 @@ static int tegra_pcie_phy_power_on(struct tegra_pcie *pcie)
 		}
 	}
 
-	/* Configure the reference clock driver */
-	pads_writel(pcie, soc->pads_refclk_cfg0, PADS_REFCLK_CFG0);
-
-	if (soc->num_ports > 2)
-		pads_writel(pcie, soc->pads_refclk_cfg1, PADS_REFCLK_CFG1);
-
 	return 0;
 }
 
@@ -918,13 +911,11 @@ static int tegra_pcie_phy_power_off(struct tegra_pcie *pcie)
 	return 0;
 }
 
-static int tegra_pcie_enable_controller(struct tegra_pcie *pcie)
+static void tegra_pcie_enable_controller(struct tegra_pcie *pcie)
 {
-	struct device *dev = pcie->dev;
 	const struct tegra_pcie_soc *soc = pcie->soc;
 	struct tegra_pcie_port *port;
 	unsigned long value;
-	int err;
 
 	/* enable PLL power down */
 	if (pcie->phy) {
@@ -958,14 +949,6 @@ static int tegra_pcie_enable_controller(struct tegra_pcie *pcie)
 		afi_writel(pcie, value, AFI_FUSE);
 	}
 
-	if (soc->program_uphy) {
-		err = tegra_pcie_phy_power_on(pcie);
-		if (err < 0) {
-			dev_err(dev, "failed to power on PHY(s): %d\n", err);
-			return err;
-		}
-	}
-
 	/* take the PCIe interface module out of reset */
 	reset_control_deassert(pcie->pcie_xrst);
 
@@ -989,22 +972,6 @@ static int tegra_pcie_enable_controller(struct tegra_pcie *pcie)
 
 	/* disable all exceptions */
 	afi_writel(pcie, 0, AFI_FPCI_ERROR_MASKS);
-
-	return 0;
-}
-
-static void tegra_pcie_disable_controller(struct tegra_pcie *pcie)
-{
-	int err;
-
-	reset_control_assert(pcie->pcie_xrst);
-
-	if (pcie->soc->program_uphy) {
-		err = tegra_pcie_phy_power_off(pcie);
-		if (err < 0)
-			dev_err(pcie->dev, "failed to power off PHY(s): %d\n",
-				err);
-	}
 }
 
 static void tegra_pcie_power_off(struct tegra_pcie *pcie)
@@ -1106,6 +1073,17 @@ static int tegra_pcie_power_on(struct tegra_pcie *pcie)
 	return err;
 }
 
+static void tegra_pcie_apply_pad_settings(struct tegra_pcie *pcie)
+{
+	const struct tegra_pcie_soc *soc = pcie->soc;
+
+	/* Configure the reference clock driver */
+	pads_writel(pcie, soc->pads_refclk_cfg0, PADS_REFCLK_CFG0);
+
+	if (soc->num_ports > 2)
+		pads_writel(pcie, soc->pads_refclk_cfg1, PADS_REFCLK_CFG1);
+}
+
 static int tegra_pcie_clocks_get(struct tegra_pcie *pcie)
 {
 	struct device *dev = pcie->dev;
@@ -2482,16 +2460,23 @@ static int __maybe_unused tegra_pcie_pm_suspend(struct device *dev)
 {
 	struct tegra_pcie *pcie = dev_get_drvdata(dev);
 	struct tegra_pcie_port *port;
+	int err;
 
 	list_for_each_entry(port, &pcie->ports, list)
 		tegra_pcie_pme_turnoff(port);
 
 	tegra_pcie_disable_ports(pcie);
 
+	if (pcie->soc->program_uphy) {
+		err = tegra_pcie_phy_power_off(pcie);
+		if (err < 0)
+			dev_err(dev, "failed to power off PHY(s): %d\n", err);
+	}
+
 	if (IS_ENABLED(CONFIG_PCI_MSI))
 		tegra_pcie_disable_msi(pcie);
 
-	tegra_pcie_disable_controller(pcie);
+	reset_control_assert(pcie->pcie_xrst);
 	tegra_pcie_power_off(pcie);
 
 	return 0;
@@ -2507,16 +2492,21 @@ static int __maybe_unused tegra_pcie_pm_resume(struct device *dev)
 		dev_err(dev, "tegra pcie power on fail: %d\n", err);
 		return err;
 	}
-	err = tegra_pcie_enable_controller(pcie);
-	if (err) {
-		dev_err(dev, "tegra pcie controller enable fail: %d\n", err);
-		goto poweroff;
-	}
+	tegra_pcie_enable_controller(pcie);
 	tegra_pcie_setup_translations(pcie);
 
 	if (IS_ENABLED(CONFIG_PCI_MSI))
 		tegra_pcie_enable_msi(pcie);
 
+	if (pcie->soc->program_uphy) {
+		err = tegra_pcie_phy_power_on(pcie);
+		if (err < 0) {
+			dev_err(dev, "failed to power on PHY(s): %d\n", err);
+			goto poweroff;
+		}
+	}
+
+	tegra_pcie_apply_pad_settings(pcie);
 	tegra_pcie_enable_ports(pcie);
 
 	return 0;
-- 
2.17.1

[PATCH V3 04/29] PCI: tegra: Mask AFI_INTR in runtime suspend

[Manikanta Maddireddy]

AFI_INTR is unmasked in tegra_pcie_enable_controller(), mask it to avoid
unwanted interrupts raised by AFI after pex_rst is asserted.

Following sequence triggers such scenario,
 - tegra_pcie_remove() triggers runtime suspend
 - pex_rst is asserted in runtime suspend
 - PRSNT_MAP bit field in RP_PRIV_MISC register changes from EP_PRSNT to
   EP_ABSNT
 - This is sensed by AFI and triggers "Slot present pin change" interrupt
 - tegra_pcie_isr() function accesses AFI register when runtime suspend
   is going through power off sequence

rmmod pci-tegra
 pci_generic_config_write32: 108 callbacks suppressed
 pci_bus 0002:00: 2-byte config write to 0002:00:02.0 offset 0x4c may corrupt adjacent RW1C bits
 pci_bus 0002:00: 2-byte config write to 0002:00:02.0 offset 0x9c may corrupt adjacent RW1C bits
 pci_bus 0002:00: 2-byte config write to 0002:00:02.0 offset 0x88 may corrupt adjacent RW1C bits
 pci_bus 0002:00: 2-byte config write to 0002:00:02.0 offset 0x90 may corrupt adjacent RW1C bits
 pci_bus 0002:00: 2-byte config write to 0002:00:02.0 offset 0x4 may corrupt adjacent RW1C bits
 igb 0002:04:00.1: removed PHC on enP2p4s0f1
 igb 0002:04:00.0: removed PHC on enP2p4s0f0
 pci_bus 0002:00: 2-byte config write to 0002:00:01.0 offset 0x4c may corrupt adjacent RW1C bits
 pci_bus 0002:00: 2-byte config write to 0002:00:01.0 offset 0x9c may corrupt adjacent RW1C bits
 pci_bus 0002:00: 2-byte config write to 0002:00:01.0 offset 0x88 may corrupt adjacent RW1C bits
 pci_bus 0002:00: 2-byte config write to 0002:00:01.0 offset 0x90 may corrupt adjacent RW1C bits
 pci_bus 0002:00: 2-byte config write to 0002:00:01.0 offset 0x4 may corrupt adjacent RW1C bits
 rcu: INFO: rcu_preempt self-detected stall on CPU
 SError Interrupt on CPU0, code 0xbf000002 -- SError
 CPU: 0 PID: 0 Comm: swapper/0 Tainted: G        W         5.1.0-rc3-next-20190405-00027-gcd8110499e6f-dirty #42
 Hardware name: NVIDIA Jetson TX1 Developer Kit (DT)
 pstate: 20000085 (nzCv daIf -PAN -UAO)
 pc : tegra_pcie_isr+0x58/0x178 [pci_tegra]
 lr : tegra_pcie_isr+0x40/0x178 [pci_tegra]
 sp : ffff000010003da0
 x29: ffff000010003da0 x28: 0000000000000000
 x27: ffff8000f9e61000 x26: ffff000010fbf420
 x25: ffff000011427f93 x24: ffff8000fa600410
 x23: ffff00001129d000 x22: ffff00001129d000
 x21: ffff8000f18bf3c0 x20: 0000000000000070
 x19: 00000000ffffffff x18: 0000000000000000
 x17: 0000000000000000 x16: 0000000000000000
 x15: 0000000000000000 x14: ffff000008d40a48
 x13: ffff000008d40a30 x12: ffff000008d40a20
 x11: ffff000008d40a10 x10: ffff000008d40a00
 x9 : ffff000008d409e8 x8 : ffff000008d40ae8
 x7 : ffff000008d40ad0 x6 : ffff000010003e58
 x5 : ffff8000fac00248 x4 : 0000000000000000
 x3 : ffff000008d40b08 x2 : fffffffffffffff8
 x1 : ffff000008d3f4e8 x0 : 00000000ffffffff
 Kernel panic - not syncing: Asynchronous SError Interrupt
 CPU: 0 PID: 0 Comm: swapper/0 Tainted: G        W         5.1.0-rc3-next-20190405-00027-gcd8110499e6f-dirty #42
 Hardware name: NVIDIA Jetson TX1 Developer Kit (DT)
 Call trace:
  dump_backtrace+0x0/0x158
  show_stack+0x14/0x20
  dump_stack+0xa8/0xcc
  panic+0x140/0x2f4
  nmi_panic+0x6c/0x70
  arm64_serror_panic+0x74/0x80
  __pte_error+0x0/0x28
  el1_error+0x84/0xf8
  tegra_pcie_isr+0x58/0x178 [pci_tegra]
  __handle_irq_event_percpu+0x70/0x198
  handle_irq_event_percpu+0x34/0x88
  handle_irq_event+0x48/0x78
  handle_fasteoi_irq+0xb4/0x190
  generic_handle_irq+0x24/0x38
  __handle_domain_irq+0x5c/0xb8
  gic_handle_irq+0x58/0xa8
  el1_irq+0xb8/0x180
  cpuidle_enter_state+0x138/0x358
  cpuidle_enter+0x18/0x20
  call_cpuidle+0x1c/0x48
  do_idle+0x230/0x2d0
  cpu_startup_entry+0x20/0x28
  rest_init+0xd4/0xe0
  arch_call_rest_init+0xc/0x14
  start_kernel+0x444/0x470

Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
---
V3:
* Update the commit log and comment to reflect why this fix is required
* MSI interrupt is not disabled

V2: This is new patch in V2

 drivers/pci/controller/pci-tegra.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index bb3c0af9c830..d0e517f084a1 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -1622,6 +1622,15 @@ static int tegra_pcie_disable_msi(struct tegra_pcie *pcie)
 	return 0;
 }
 
+static void tegra_pcie_disable_interrupts(struct tegra_pcie *pcie)
+{
+	u32 value;
+
+	value = afi_readl(pcie, AFI_INTR_MASK);
+	value &= ~AFI_INTR_MASK_INT_MASK;
+	afi_writel(pcie, value, AFI_INTR_MASK);
+}
+
 static int tegra_pcie_get_xbar_config(struct tegra_pcie *pcie, u32 lanes,
 				      u32 *xbar)
 {
@@ -2466,6 +2475,11 @@ static int __maybe_unused tegra_pcie_pm_suspend(struct device *dev)
 		tegra_pcie_pme_turnoff(port);
 
 	tegra_pcie_disable_ports(pcie);
+	/*
+	 * AFI_INTR is unmasked in tegra_pcie_enable_controller(), mask it to
+	 * avoid unwanted interrupts raised by AFI after pex_rst is asserted.
+	 */
+	tegra_pcie_disable_interrupts(pcie);
 
 	if (pcie->soc->program_uphy) {
 		err = tegra_pcie_phy_power_off(pcie);
-- 
2.17.1

[PATCH V3 05/29] PCI: tegra: Fix PCIe host power up sequence

[Manikanta Maddireddy]

PCIe host power up sequence involves programming AFI(AXI to FPCI bridge)
registers first and then PCIe registers. Otherwise AFI register settings
may not latch to PCIe IP.

PCIe root port starts LTSSM as soon as PCIe xrst is deasserted.
So deassert PCIe xrst after programming PCIe registers.

Modify PCIe power up sequence as follows,
 - Power ungate PCIe partition
 - Enable AFI clock
 - Deassert AFI reset
 - Program AFI registers
 - Enable PCIe clock
 - Deassert PCIe reset
 - Program PCIe PHY
 - Program PCIe pad control registers
 - Program PCIe root port registers
 - Deassert PCIe xrst to start LTSSM

Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
---
V3: No change

V2: Error cleanup changes are moved to new patch and only sequence
correction is done in this patch.

 drivers/pci/controller/pci-tegra.c | 52 +++++++++++++++++-------------
 1 file changed, 30 insertions(+), 22 deletions(-)

diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index d0e517f084a1..015add4e345b 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -949,9 +949,6 @@ static void tegra_pcie_enable_controller(struct tegra_pcie *pcie)
 		afi_writel(pcie, value, AFI_FUSE);
 	}
 
-	/* take the PCIe interface module out of reset */
-	reset_control_deassert(pcie->pcie_xrst);
-
 	/* finally enable PCIe */
 	value = afi_readl(pcie, AFI_CONFIGURATION);
 	value |= AFI_CONFIGURATION_EN_FPCI;
@@ -981,13 +978,11 @@ static void tegra_pcie_power_off(struct tegra_pcie *pcie)
 	int err;
 
 	reset_control_assert(pcie->afi_rst);
-	reset_control_assert(pcie->pex_rst);
 
 	clk_disable_unprepare(pcie->pll_e);
 	if (soc->has_cml_clk)
 		clk_disable_unprepare(pcie->cml_clk);
 	clk_disable_unprepare(pcie->afi_clk);
-	clk_disable_unprepare(pcie->pex_clk);
 
 	if (!dev->pm_domain)
 		tegra_powergate_power_off(TEGRA_POWERGATE_PCIE);
@@ -1015,25 +1010,19 @@ static int tegra_pcie_power_on(struct tegra_pcie *pcie)
 	if (err < 0)
 		dev_err(dev, "failed to enable regulators: %d\n", err);
 
-	if (dev->pm_domain) {
-		err = clk_prepare_enable(pcie->pex_clk);
+	if (!dev->pm_domain) {
+		err = tegra_powergate_power_on(TEGRA_POWERGATE_PCIE);
 		if (err) {
-			dev_err(dev, "failed to enable PEX clock: %d\n", err);
+			dev_err(dev, "failed to power ungate: %d\n", err);
 			goto regulator_disable;
 		}
-		reset_control_deassert(pcie->pex_rst);
-	} else {
-		err = tegra_powergate_sequence_power_up(TEGRA_POWERGATE_PCIE,
-							pcie->pex_clk,
-							pcie->pex_rst);
+		err = tegra_powergate_remove_clamping(TEGRA_POWERGATE_PCIE);
 		if (err) {
-			dev_err(dev, "powerup sequence failed: %d\n", err);
-			goto regulator_disable;
+			dev_err(dev, "failed to remove clamp: %d\n", err);
+			goto powergate;
 		}
 	}
 
-	reset_control_deassert(pcie->afi_rst);
-
 	err = clk_prepare_enable(pcie->afi_clk);
 	if (err < 0) {
 		dev_err(dev, "failed to enable AFI clock: %d\n", err);
@@ -1054,6 +1043,8 @@ static int tegra_pcie_power_on(struct tegra_pcie *pcie)
 		goto disable_cml_clk;
 	}
 
+	reset_control_deassert(pcie->afi_rst);
+
 	return 0;
 
 disable_cml_clk:
@@ -1062,9 +1053,6 @@ static int tegra_pcie_power_on(struct tegra_pcie *pcie)
 disable_afi_clk:
 	clk_disable_unprepare(pcie->afi_clk);
 powergate:
-	reset_control_assert(pcie->afi_rst);
-	reset_control_assert(pcie->pex_rst);
-	clk_disable_unprepare(pcie->pex_clk);
 	if (!dev->pm_domain)
 		tegra_powergate_power_off(TEGRA_POWERGATE_PCIE);
 regulator_disable:
@@ -2111,7 +2099,12 @@ static void tegra_pcie_enable_ports(struct tegra_pcie *pcie)
 			 port->index, port->lanes);
 
 		tegra_pcie_port_enable(port);
+	}
 
+	/* Start LTSSM from Tegra side */
+	reset_control_deassert(pcie->pcie_xrst);
+
+	list_for_each_entry_safe(port, tmp, &pcie->ports, list) {
 		if (tegra_pcie_port_check_link(port))
 			continue;
 
@@ -2126,6 +2119,8 @@ static void tegra_pcie_disable_ports(struct tegra_pcie *pcie)
 {
 	struct tegra_pcie_port *port, *tmp;
 
+	reset_control_assert(pcie->pcie_xrst);
+
 	list_for_each_entry_safe(port, tmp, &pcie->ports, list)
 		tegra_pcie_port_disable(port);
 }
@@ -2487,10 +2482,12 @@ static int __maybe_unused tegra_pcie_pm_suspend(struct device *dev)
 			dev_err(dev, "failed to power off PHY(s): %d\n", err);
 	}
 
+	reset_control_assert(pcie->pex_rst);
+	clk_disable_unprepare(pcie->pex_clk);
+
 	if (IS_ENABLED(CONFIG_PCI_MSI))
 		tegra_pcie_disable_msi(pcie);
 
-	reset_control_assert(pcie->pcie_xrst);
 	tegra_pcie_power_off(pcie);
 
 	return 0;
@@ -2512,11 +2509,19 @@ static int __maybe_unused tegra_pcie_pm_resume(struct device *dev)
 	if (IS_ENABLED(CONFIG_PCI_MSI))
 		tegra_pcie_enable_msi(pcie);
 
+	err = clk_prepare_enable(pcie->pex_clk);
+	if (err) {
+		dev_err(dev, "failed to enable PEX clock: %d\n", err);
+		goto poweroff;
+	}
+
+	reset_control_deassert(pcie->pex_rst);
+
 	if (pcie->soc->program_uphy) {
 		err = tegra_pcie_phy_power_on(pcie);
 		if (err < 0) {
 			dev_err(dev, "failed to power on PHY(s): %d\n", err);
-			goto poweroff;
+			goto disable_pex_clk;
 		}
 	}
 
@@ -2525,6 +2530,9 @@ static int __maybe_unused tegra_pcie_pm_resume(struct device *dev)
 
 	return 0;
 
+disable_pex_clk:
+	reset_control_assert(pcie->pex_rst);
+	clk_disable_unprepare(pcie->pex_clk);
 poweroff:
 	tegra_pcie_power_off(pcie);
 
-- 
2.17.1

[PATCH V3 06/29] PCI: tegra: Add PCIe Gen2 link speed support

[Manikanta Maddireddy]

Tegra124, Tegra132, Tegra210 and Tegra186 support Gen2 link speed. After
PCIe link is up in Gen1, set target link speed as Gen2 and retrain link.
Link switches to Gen2 speed if Gen2 capable end point is connected, else
link stays in Gen1.

Per PCIe 4.0r0.9 sec 7.6.3.7 implementation note, driver need to wait for
PCIe LTSSM to come back from recovery before retraining the link.

Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
---
V3: Added blank line after each while loop.

V2: Changed "for loop" to "while", to make it compact and handled coding
style comments.

 drivers/pci/controller/pci-tegra.c | 64 ++++++++++++++++++++++++++++++
 1 file changed, 64 insertions(+)

diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index 015add4e345b..cd542a8af618 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -191,6 +191,8 @@
 #define  RP_LINK_CONTROL_STATUS_DL_LINK_ACTIVE	0x20000000
 #define  RP_LINK_CONTROL_STATUS_LINKSTAT_MASK	0x3fff0000
 
+#define RP_LINK_CONTROL_STATUS_2		0x000000b0
+
 #define PADS_CTL_SEL		0x0000009c
 
 #define PADS_CTL		0x000000a0
@@ -226,6 +228,7 @@
 #define PADS_REFCLK_CFG_DRVI_SHIFT		12 /* 15:12 */
 
 #define PME_ACK_TIMEOUT 10000
+#define LINK_RETRAIN_TIMEOUT 100000 /* in usec */
 
 struct tegra_msi {
 	struct msi_controller chip;
@@ -2089,6 +2092,64 @@ static bool tegra_pcie_port_check_link(struct tegra_pcie_port *port)
 	return false;
 }
 
+static void tegra_pcie_change_link_speed(struct tegra_pcie *pcie)
+{
+	struct device *dev = pcie->dev;
+	struct tegra_pcie_port *port, *tmp;
+	ktime_t deadline;
+	u32 value;
+
+	list_for_each_entry_safe(port, tmp, &pcie->ports, list) {
+		/*
+		 * "Supported Link Speeds Vector" in "Link Capabilities 2"
+		 * is not supported by Tegra. tegra_pcie_change_link_speed()
+		 * is called only for Tegra chips which support Gen2.
+		 * So there no harm if supported link speed is not verified.
+		 */
+		value = readl(port->base + RP_LINK_CONTROL_STATUS_2);
+		value &= ~PCI_EXP_LNKSTA_CLS;
+		value |= PCI_EXP_LNKSTA_CLS_5_0GB;
+		writel(value, port->base + RP_LINK_CONTROL_STATUS_2);
+
+		/*
+		 * Poll until link comes back from recovery to avoid race
+		 * condition.
+		 */
+		deadline = ktime_add_us(ktime_get(), LINK_RETRAIN_TIMEOUT);
+
+		while (ktime_before(ktime_get(), deadline)) {
+			value = readl(port->base + RP_LINK_CONTROL_STATUS);
+			if ((value & PCI_EXP_LNKSTA_LT) == 0)
+				break;
+
+			usleep_range(2000, 3000);
+		}
+
+		if (value & PCI_EXP_LNKSTA_LT)
+			dev_warn(dev, "PCIe port %u link is in recovery\n",
+				 port->index);
+
+		/* Retrain the link */
+		value = readl(port->base + RP_LINK_CONTROL_STATUS);
+		value |= PCI_EXP_LNKCTL_RL;
+		writel(value, port->base + RP_LINK_CONTROL_STATUS);
+
+		deadline = ktime_add_us(ktime_get(), LINK_RETRAIN_TIMEOUT);
+
+		while (ktime_before(ktime_get(), deadline)) {
+			value = readl(port->base + RP_LINK_CONTROL_STATUS);
+			if ((value & PCI_EXP_LNKSTA_LT) == 0)
+				break;
+
+			usleep_range(2000, 3000);
+		}
+
+		if (value & PCI_EXP_LNKSTA_LT)
+			dev_err(dev, "failed to retrain link of port %u\n",
+				port->index);
+	}
+}
+
 static void tegra_pcie_enable_ports(struct tegra_pcie *pcie)
 {
 	struct device *dev = pcie->dev;
@@ -2113,6 +2174,9 @@ static void tegra_pcie_enable_ports(struct tegra_pcie *pcie)
 		tegra_pcie_port_disable(port);
 		tegra_pcie_port_free(port);
 	}
+
+	if (pcie->soc->has_gen2)
+		tegra_pcie_change_link_speed(pcie);
 }
 
 static void tegra_pcie_disable_ports(struct tegra_pcie *pcie)
-- 
2.17.1

[PATCH V3 07/29] PCI: tegra: Advertise PCIe Advanced Error Reporting (AER) capability

[Manikanta Maddireddy]

Default root port setting hides AER capability. This patch enables the
advertisement of AER capability by root port.

Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
---
V3: No change

V2: No change

 drivers/pci/controller/pci-tegra.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index cd542a8af618..e402627bd221 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -180,6 +180,9 @@
 #define RP_VEND_XP	0x00000f00
 #define  RP_VEND_XP_DL_UP	(1 << 30)
 
+#define RP_VEND_CTL1	0x00000f48
+#define  RP_VEND_CTL1_ERPT	(1 << 13)
+
 #define RP_VEND_CTL2 0x00000fa8
 #define  RP_VEND_CTL2_PCA_ENABLE (1 << 7)
 
@@ -479,6 +482,16 @@ static void tegra_pcie_port_reset(struct tegra_pcie_port *port)
 	afi_writel(port->pcie, value, ctrl);
 }
 
+static void tegra_pcie_enable_rp_features(struct tegra_pcie_port *port)
+{
+	u32 value;
+
+	/* Enable AER capability */
+	value = readl(port->base + RP_VEND_CTL1);
+	value |= RP_VEND_CTL1_ERPT;
+	writel(value, port->base + RP_VEND_CTL1);
+}
+
 static void tegra_pcie_port_enable(struct tegra_pcie_port *port)
 {
 	unsigned long ctrl = tegra_pcie_port_get_pex_ctrl(port);
@@ -503,6 +516,8 @@ static void tegra_pcie_port_enable(struct tegra_pcie_port *port)
 		value |= RP_VEND_CTL2_PCA_ENABLE;
 		writel(value, port->base + RP_VEND_CTL2);
 	}
+
+	tegra_pcie_enable_rp_features(port);
 }
 
 static void tegra_pcie_port_disable(struct tegra_pcie_port *port)
-- 
2.17.1

[PATCH V3 08/29] PCI: tegra: Program UPHY electrical settings for Tegra210

[Manikanta Maddireddy]

UPHY electrical programming guidelines are documented in Tegra210 TRM.
Program these electrical settings for proper eye diagram in Gen1 and Gen2
link speeds.

Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
---
V3: No change

V2: Addressed coding style comments

 drivers/pci/controller/pci-tegra.c | 107 +++++++++++++++++++++++++++++
 1 file changed, 107 insertions(+)

diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index e402627bd221..76d913ef5bf4 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -177,6 +177,32 @@
 
 #define AFI_PEXBIAS_CTRL_0		0x168
 
+#define RP_ECTL_2_R1	0x00000e84
+#define  RP_ECTL_2_R1_RX_CTLE_1C_MASK		0xffff
+
+#define RP_ECTL_4_R1	0x00000e8c
+#define  RP_ECTL_4_R1_RX_CDR_CTRL_1C_MASK	(0xffff << 16)
+#define  RP_ECTL_4_R1_RX_CDR_CTRL_1C_SHIFT	16
+
+#define RP_ECTL_5_R1	0x00000e90
+#define  RP_ECTL_5_R1_RX_EQ_CTRL_L_1C_MASK	0xffffffff
+
+#define RP_ECTL_6_R1	0x00000e94
+#define  RP_ECTL_6_R1_RX_EQ_CTRL_H_1C_MASK	0xffffffff
+
+#define RP_ECTL_2_R2	0x00000ea4
+#define  RP_ECTL_2_R2_RX_CTLE_1C_MASK	0xffff
+
+#define RP_ECTL_4_R2	0x00000eac
+#define  RP_ECTL_4_R2_RX_CDR_CTRL_1C_MASK	(0xffff << 16)
+#define  RP_ECTL_4_R2_RX_CDR_CTRL_1C_SHIFT	16
+
+#define RP_ECTL_5_R2	0x00000eb0
+#define  RP_ECTL_5_R2_RX_EQ_CTRL_L_1C_MASK	0xffffffff
+
+#define RP_ECTL_6_R2	0x00000eb4
+#define  RP_ECTL_6_R2_RX_EQ_CTRL_H_1C_MASK	0xffffffff
+
 #define RP_VEND_XP	0x00000f00
 #define  RP_VEND_XP_DL_UP	(1 << 30)
 
@@ -266,6 +292,19 @@ struct tegra_pcie_soc {
 	bool has_gen2;
 	bool force_pca_enable;
 	bool program_uphy;
+	struct {
+		struct {
+			u32 rp_ectl_2_r1;
+			u32 rp_ectl_4_r1;
+			u32 rp_ectl_5_r1;
+			u32 rp_ectl_6_r1;
+			u32 rp_ectl_2_r2;
+			u32 rp_ectl_4_r2;
+			u32 rp_ectl_5_r2;
+			u32 rp_ectl_6_r2;
+		} regs;
+		bool enable;
+	} ectl;
 };
 
 static inline struct tegra_msi *to_tegra_msi(struct msi_controller *chip)
@@ -492,6 +531,54 @@ static void tegra_pcie_enable_rp_features(struct tegra_pcie_port *port)
 	writel(value, port->base + RP_VEND_CTL1);
 }
 
+static void tegra_pcie_program_ectl_settings(struct tegra_pcie_port *port)
+{
+	const struct tegra_pcie_soc *soc = port->pcie->soc;
+	u32 value;
+
+	value = readl(port->base + RP_ECTL_2_R1);
+	value &= ~RP_ECTL_2_R1_RX_CTLE_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_2_r1;
+	writel(value, port->base + RP_ECTL_2_R1);
+
+	value = readl(port->base + RP_ECTL_4_R1);
+	value &= ~RP_ECTL_4_R1_RX_CDR_CTRL_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_4_r1 <<
+				RP_ECTL_4_R1_RX_CDR_CTRL_1C_SHIFT;
+	writel(value, port->base + RP_ECTL_4_R1);
+
+	value = readl(port->base + RP_ECTL_5_R1);
+	value &= ~RP_ECTL_5_R1_RX_EQ_CTRL_L_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_5_r1;
+	writel(value, port->base + RP_ECTL_5_R1);
+
+	value = readl(port->base + RP_ECTL_6_R1);
+	value &= ~RP_ECTL_6_R1_RX_EQ_CTRL_H_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_6_r1;
+	writel(value, port->base + RP_ECTL_6_R1);
+
+	value = readl(port->base + RP_ECTL_2_R2);
+	value &= ~RP_ECTL_2_R2_RX_CTLE_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_2_r2;
+	writel(value, port->base + RP_ECTL_2_R2);
+
+	value = readl(port->base + RP_ECTL_4_R2);
+	value &= ~RP_ECTL_4_R2_RX_CDR_CTRL_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_4_r2 <<
+				RP_ECTL_4_R2_RX_CDR_CTRL_1C_SHIFT;
+	writel(value, port->base + RP_ECTL_4_R2);
+
+	value = readl(port->base + RP_ECTL_5_R2);
+	value &= ~RP_ECTL_5_R2_RX_EQ_CTRL_L_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_5_r2;
+	writel(value, port->base + RP_ECTL_5_R2);
+
+	value = readl(port->base + RP_ECTL_6_R2);
+	value &= ~RP_ECTL_6_R2_RX_EQ_CTRL_H_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_6_r2;
+	writel(value, port->base + RP_ECTL_6_R2);
+}
+
 static void tegra_pcie_port_enable(struct tegra_pcie_port *port)
 {
 	unsigned long ctrl = tegra_pcie_port_get_pex_ctrl(port);
@@ -518,6 +605,9 @@ static void tegra_pcie_port_enable(struct tegra_pcie_port *port)
 	}
 
 	tegra_pcie_enable_rp_features(port);
+
+	if (soc->ectl.enable)
+		tegra_pcie_program_ectl_settings(port);
 }
 
 static void tegra_pcie_port_disable(struct tegra_pcie_port *port)
@@ -2223,6 +2313,7 @@ static const struct tegra_pcie_soc tegra20_pcie = {
 	.has_gen2 = false,
 	.force_pca_enable = false,
 	.program_uphy = true,
+	.ectl.enable = false,
 };
 
 static const struct tegra_pcie_port_soc tegra30_pcie_ports[] = {
@@ -2246,6 +2337,7 @@ static const struct tegra_pcie_soc tegra30_pcie = {
 	.has_gen2 = false,
 	.force_pca_enable = false,
 	.program_uphy = true,
+	.ectl.enable = false,
 };
 
 static const struct tegra_pcie_soc tegra124_pcie = {
@@ -2262,6 +2354,7 @@ static const struct tegra_pcie_soc tegra124_pcie = {
 	.has_gen2 = true,
 	.force_pca_enable = false,
 	.program_uphy = true,
+	.ectl.enable = false,
 };
 
 static const struct tegra_pcie_soc tegra210_pcie = {
@@ -2278,6 +2371,19 @@ static const struct tegra_pcie_soc tegra210_pcie = {
 	.has_gen2 = true,
 	.force_pca_enable = true,
 	.program_uphy = true,
+	.ectl = {
+		.regs = {
+			.rp_ectl_2_r1 = 0x0000000f,
+			.rp_ectl_4_r1 = 0x00000067,
+			.rp_ectl_5_r1 = 0x55010000,
+			.rp_ectl_6_r1 = 0x00000001,
+			.rp_ectl_2_r2 = 0x0000008f,
+			.rp_ectl_4_r2 = 0x000000c7,
+			.rp_ectl_5_r2 = 0x55010000,
+			.rp_ectl_6_r2 = 0x00000001,
+		},
+		.enable = true,
+	},
 };
 
 static const struct tegra_pcie_port_soc tegra186_pcie_ports[] = {
@@ -2301,6 +2407,7 @@ static const struct tegra_pcie_soc tegra186_pcie = {
 	.has_gen2 = true,
 	.force_pca_enable = false,
 	.program_uphy = false,
+	.ectl.enable = false,
 };
 
 static const struct of_device_id tegra_pcie_of_match[] = {
-- 
2.17.1

[PATCH V3 09/29] PCI: tegra: Enable opportunistic UpdateFC and ACK

[Manikanta Maddireddy]

Enable opportunistic UpdateFC and ACK to allow data link layer send
pending ACKs and UpdateFC packets when link is idle instead of waiting
for timers to expire. This improves the PCIe performance due to better
utilization of PCIe bandwidth.

Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
---
V3: No change

V2: No change

 drivers/pci/controller/pci-tegra.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index 76d913ef5bf4..b1e2e398b4e8 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -204,7 +204,9 @@
 #define  RP_ECTL_6_R2_RX_EQ_CTRL_H_1C_MASK	0xffffffff
 
 #define RP_VEND_XP	0x00000f00
-#define  RP_VEND_XP_DL_UP	(1 << 30)
+#define  RP_VEND_XP_DL_UP			(1 << 30)
+#define  RP_VEND_XP_OPPORTUNISTIC_ACK		(1 << 27)
+#define  RP_VEND_XP_OPPORTUNISTIC_UPDATEFC	(1 << 28)
 
 #define RP_VEND_CTL1	0x00000f48
 #define  RP_VEND_CTL1_ERPT	(1 << 13)
@@ -529,6 +531,12 @@ static void tegra_pcie_enable_rp_features(struct tegra_pcie_port *port)
 	value = readl(port->base + RP_VEND_CTL1);
 	value |= RP_VEND_CTL1_ERPT;
 	writel(value, port->base + RP_VEND_CTL1);
+
+	/* Optimal settings to enhance bandwidth */
+	value = readl(port->base + RP_VEND_XP);
+	value |= RP_VEND_XP_OPPORTUNISTIC_ACK;
+	value |= RP_VEND_XP_OPPORTUNISTIC_UPDATEFC;
+	writel(value, port->base + RP_VEND_XP);
 }
 
 static void tegra_pcie_program_ectl_settings(struct tegra_pcie_port *port)
-- 
2.17.1

[PATCH V3 10/29] PCI: tegra: Disable AFI dynamic clock gating

[Manikanta Maddireddy]

Outstanding write counter in AFI is used to generate idle signal to
dynamically gate the AFI clock. When there are 32 outstanding writes
from AFI to memory, the outstanding write counter overflows and
indicates that there are "0" outstanding write transactions.

When memory controller is under heavy load, write completions to AFI
gets delayed and AFI write counter overflows. This causes AFI clock gating
even when there are outstanding transactions towards memory controller
resulting in system hang.

Disable dynamic clock gating of AFI clock to avoid system hang.

CLKEN_OVERRIDE bit is not defined in Tegra20 and Tegra30, however
programming this bit doesn't cause any side effects. Program this
bit for all Tegra SoCs to avoid conditional check.

Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
---
V3: No change

V2: No change

 drivers/pci/controller/pci-tegra.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index b1e2e398b4e8..17c6d858ddc6 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -95,7 +95,8 @@
 #define AFI_MSI_EN_VEC7		0xa8
 
 #define AFI_CONFIGURATION		0xac
-#define  AFI_CONFIGURATION_EN_FPCI	(1 << 0)
+#define  AFI_CONFIGURATION_EN_FPCI		(1 << 0)
+#define  AFI_CONFIGURATION_CLKEN_OVERRIDE	(1 << 31)
 
 #define AFI_FPCI_ERROR_MASKS	0xb0
 
@@ -1065,9 +1066,10 @@ static void tegra_pcie_enable_controller(struct tegra_pcie *pcie)
 		afi_writel(pcie, value, AFI_FUSE);
 	}
 
-	/* finally enable PCIe */
+	/* Disable AFI dynamic clock gating and enable PCIe */
 	value = afi_readl(pcie, AFI_CONFIGURATION);
 	value |= AFI_CONFIGURATION_EN_FPCI;
+	value |= AFI_CONFIGURATION_CLKEN_OVERRIDE;
 	afi_writel(pcie, value, AFI_CONFIGURATION);
 
 	value = AFI_INTR_EN_INI_SLVERR | AFI_INTR_EN_INI_DECERR |
-- 
2.17.1

[PATCH V3 11/29] PCI: tegra: Process pending DLL transactions before entering L1 or L2

[Manikanta Maddireddy]

PM message are truncated while entering L1 or L2, which is resulting in
receiver errors. Set the required bit to finish processing DLLP before
link enter L1 or L2.

Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
---
V3: No change

V2: No change

 drivers/pci/controller/pci-tegra.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index 17c6d858ddc6..d3da03a10e04 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -212,6 +212,9 @@
 #define RP_VEND_CTL1	0x00000f48
 #define  RP_VEND_CTL1_ERPT	(1 << 13)
 
+#define RP_VEND_XP_BIST	0x00000f4c
+#define  RP_VEND_XP_BIST_GOTO_L1_L2_AFTER_DLLP_DONE	(1 << 28)
+
 #define RP_VEND_CTL2 0x00000fa8
 #define  RP_VEND_CTL2_PCA_ENABLE (1 << 7)
 
@@ -538,6 +541,14 @@ static void tegra_pcie_enable_rp_features(struct tegra_pcie_port *port)
 	value |= RP_VEND_XP_OPPORTUNISTIC_ACK;
 	value |= RP_VEND_XP_OPPORTUNISTIC_UPDATEFC;
 	writel(value, port->base + RP_VEND_XP);
+
+	/*
+	 * LTSSM will wait for DLLP to finish before entering L1 or L2,
+	 * to avoid truncation of PM messages which results in receiver errors
+	 */
+	value = readl(port->base + RP_VEND_XP_BIST);
+	value |= RP_VEND_XP_BIST_GOTO_L1_L2_AFTER_DLLP_DONE;
+	writel(value, port->base + RP_VEND_XP_BIST);
 }
 
 static void tegra_pcie_program_ectl_settings(struct tegra_pcie_port *port)
-- 
2.17.1

[PATCH V3 12/29] PCI: tegra: Enable PCIe xclk clock clamping

[Manikanta Maddireddy]

Enable xclk clock clamping when entering L1. Clamp threshold will
determine the time spent waiting for clock module to turn on xclk after
signaling it. Default threshold value in Tegra124 and Tegra210 is not
enough to turn on xclk clock. Increase the clamp threshold to meet the
clock module timing in Tegra124 and Tegra210. Default threshold value is
enough in Tegra20, Tegra30 and Tegra186.

Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
---
V3: No change

V2: Took care of typos in commit log and coding style comments.

 drivers/pci/controller/pci-tegra.c | 30 ++++++++++++++++++++++++++++--
 1 file changed, 28 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index d3da03a10e04..96cd75821872 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -219,8 +219,14 @@
 #define  RP_VEND_CTL2_PCA_ENABLE (1 << 7)
 
 #define RP_PRIV_MISC	0x00000fe0
-#define  RP_PRIV_MISC_PRSNT_MAP_EP_PRSNT (0xe << 0)
-#define  RP_PRIV_MISC_PRSNT_MAP_EP_ABSNT (0xf << 0)
+#define  RP_PRIV_MISC_PRSNT_MAP_EP_PRSNT		(0xe << 0)
+#define  RP_PRIV_MISC_PRSNT_MAP_EP_ABSNT		(0xf << 0)
+#define  RP_PRIV_MISC_CTLR_CLK_CLAMP_THRESHOLD_MASK	(0x7f << 16)
+#define  RP_PRIV_MISC_CTLR_CLK_CLAMP_THRESHOLD		(0xf << 16)
+#define  RP_PRIV_MISC_CTLR_CLK_CLAMP_ENABLE		(1 << 23)
+#define  RP_PRIV_MISC_TMS_CLK_CLAMP_THRESHOLD_MASK	(0x7f << 24)
+#define  RP_PRIV_MISC_TMS_CLK_CLAMP_THRESHOLD		(0xf << 24)
+#define  RP_PRIV_MISC_TMS_CLK_CLAMP_ENABLE		(1 << 31)
 
 #define RP_LINK_CONTROL_STATUS			0x00000090
 #define  RP_LINK_CONTROL_STATUS_DL_LINK_ACTIVE	0x20000000
@@ -298,6 +304,7 @@ struct tegra_pcie_soc {
 	bool has_gen2;
 	bool force_pca_enable;
 	bool program_uphy;
+	bool update_clamp_threshold;
 	struct {
 		struct {
 			u32 rp_ectl_2_r1;
@@ -529,6 +536,7 @@ static void tegra_pcie_port_reset(struct tegra_pcie_port *port)
 
 static void tegra_pcie_enable_rp_features(struct tegra_pcie_port *port)
 {
+	const struct tegra_pcie_soc *soc = port->pcie->soc;
 	u32 value;
 
 	/* Enable AER capability */
@@ -549,6 +557,19 @@ static void tegra_pcie_enable_rp_features(struct tegra_pcie_port *port)
 	value = readl(port->base + RP_VEND_XP_BIST);
 	value |= RP_VEND_XP_BIST_GOTO_L1_L2_AFTER_DLLP_DONE;
 	writel(value, port->base + RP_VEND_XP_BIST);
+
+	value = readl(port->base + RP_PRIV_MISC);
+	value |= RP_PRIV_MISC_CTLR_CLK_CLAMP_ENABLE;
+	value |= RP_PRIV_MISC_TMS_CLK_CLAMP_ENABLE;
+
+	if (soc->update_clamp_threshold) {
+		value &= ~(RP_PRIV_MISC_CTLR_CLK_CLAMP_THRESHOLD_MASK |
+				RP_PRIV_MISC_TMS_CLK_CLAMP_THRESHOLD_MASK);
+		value |= RP_PRIV_MISC_CTLR_CLK_CLAMP_THRESHOLD |
+			RP_PRIV_MISC_TMS_CLK_CLAMP_THRESHOLD;
+	}
+
+	writel(value, port->base + RP_PRIV_MISC);
 }
 
 static void tegra_pcie_program_ectl_settings(struct tegra_pcie_port *port)
@@ -2334,6 +2355,7 @@ static const struct tegra_pcie_soc tegra20_pcie = {
 	.has_gen2 = false,
 	.force_pca_enable = false,
 	.program_uphy = true,
+	.update_clamp_threshold = false,
 	.ectl.enable = false,
 };
 
@@ -2358,6 +2380,7 @@ static const struct tegra_pcie_soc tegra30_pcie = {
 	.has_gen2 = false,
 	.force_pca_enable = false,
 	.program_uphy = true,
+	.update_clamp_threshold = false,
 	.ectl.enable = false,
 };
 
@@ -2375,6 +2398,7 @@ static const struct tegra_pcie_soc tegra124_pcie = {
 	.has_gen2 = true,
 	.force_pca_enable = false,
 	.program_uphy = true,
+	.update_clamp_threshold = true,
 	.ectl.enable = false,
 };
 
@@ -2392,6 +2416,7 @@ static const struct tegra_pcie_soc tegra210_pcie = {
 	.has_gen2 = true,
 	.force_pca_enable = true,
 	.program_uphy = true,
+	.update_clamp_threshold = true,
 	.ectl = {
 		.regs = {
 			.rp_ectl_2_r1 = 0x0000000f,
@@ -2428,6 +2453,7 @@ static const struct tegra_pcie_soc tegra186_pcie = {
 	.has_gen2 = true,
 	.force_pca_enable = false,
 	.program_uphy = false,
+	.update_clamp_threshold = false,
 	.ectl.enable = false,
 };
 
-- 
2.17.1

[PATCH V3 13/29] PCI: tegra: Increase the deskew retry time

[Manikanta Maddireddy]

Sometimes link speed change from Gen2 to Gen1 fails due to instability
in deskew logic on lane-0 in Tegra210. Increase the deskew retry time
to resolve this issue.

Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
---
V3: No change

V2: Took care of typos in commit log and coding style comments.

 drivers/pci/controller/pci-tegra.c | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index 96cd75821872..9c28f1d9f177 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -209,6 +209,10 @@
 #define  RP_VEND_XP_OPPORTUNISTIC_ACK		(1 << 27)
 #define  RP_VEND_XP_OPPORTUNISTIC_UPDATEFC	(1 << 28)
 
+#define RP_VEND_CTL0	0x00000f44
+#define  RP_VEND_CTL0_DSK_RST_PULSE_WIDTH_MASK	(0xf << 12)
+#define  RP_VEND_CTL0_DSK_RST_PULSE_WIDTH	(0x9 << 12)
+
 #define RP_VEND_CTL1	0x00000f48
 #define  RP_VEND_CTL1_ERPT	(1 << 13)
 
@@ -305,6 +309,7 @@ struct tegra_pcie_soc {
 	bool force_pca_enable;
 	bool program_uphy;
 	bool update_clamp_threshold;
+	bool program_deskew_time;
 	struct {
 		struct {
 			u32 rp_ectl_2_r1;
@@ -620,6 +625,24 @@ static void tegra_pcie_program_ectl_settings(struct tegra_pcie_port *port)
 	writel(value, port->base + RP_ECTL_6_R2);
 }
 
+static void tegra_pcie_apply_sw_fixup(struct tegra_pcie_port *port)
+{
+	const struct tegra_pcie_soc *soc = port->pcie->soc;
+	u32 value;
+
+	/*
+	 * Sometimes link speed change from Gen2 to Gen1 fails due to
+	 * instability in deskew logic on lane-0. Increase the deskew
+	 * retry time to resolve this issue.
+	 */
+	if (soc->program_deskew_time) {
+		value = readl(port->base + RP_VEND_CTL0);
+		value &= ~RP_VEND_CTL0_DSK_RST_PULSE_WIDTH_MASK;
+		value |= RP_VEND_CTL0_DSK_RST_PULSE_WIDTH;
+		writel(value, port->base + RP_VEND_CTL0);
+	}
+}
+
 static void tegra_pcie_port_enable(struct tegra_pcie_port *port)
 {
 	unsigned long ctrl = tegra_pcie_port_get_pex_ctrl(port);
@@ -649,6 +672,8 @@ static void tegra_pcie_port_enable(struct tegra_pcie_port *port)
 
 	if (soc->ectl.enable)
 		tegra_pcie_program_ectl_settings(port);
+
+	tegra_pcie_apply_sw_fixup(port);
 }
 
 static void tegra_pcie_port_disable(struct tegra_pcie_port *port)
@@ -2356,6 +2381,7 @@ static const struct tegra_pcie_soc tegra20_pcie = {
 	.force_pca_enable = false,
 	.program_uphy = true,
 	.update_clamp_threshold = false,
+	.program_deskew_time = false,
 	.ectl.enable = false,
 };
 
@@ -2381,6 +2407,7 @@ static const struct tegra_pcie_soc tegra30_pcie = {
 	.force_pca_enable = false,
 	.program_uphy = true,
 	.update_clamp_threshold = false,
+	.program_deskew_time = false,
 	.ectl.enable = false,
 };
 
@@ -2399,6 +2426,7 @@ static const struct tegra_pcie_soc tegra124_pcie = {
 	.force_pca_enable = false,
 	.program_uphy = true,
 	.update_clamp_threshold = true,
+	.program_deskew_time = false,
 	.ectl.enable = false,
 };
 
@@ -2417,6 +2445,7 @@ static const struct tegra_pcie_soc tegra210_pcie = {
 	.force_pca_enable = true,
 	.program_uphy = true,
 	.update_clamp_threshold = true,
+	.program_deskew_time = true,
 	.ectl = {
 		.regs = {
 			.rp_ectl_2_r1 = 0x0000000f,
@@ -2454,6 +2483,7 @@ static const struct tegra_pcie_soc tegra186_pcie = {
 	.force_pca_enable = false,
 	.program_uphy = false,
 	.update_clamp_threshold = false,
+	.program_deskew_time = false,
 	.ectl.enable = false,
 };
 
-- 
2.17.1

[PATCH V3 14/29] PCI: tegra: Add SW fixup for RAW violations

[Manikanta Maddireddy]

The logic which blocks read requests till AFI gets ACK for all outstanding
writes from memory controller does not behave correctly when number of
outstanding writes become more than 32 in Tegra124 and Tegra132.

SW fixup is to prevent writes from accumulating more than 32 by,
 - limiting outstanding posted writes to 14
 - modifying Gen1 and Gen2 UpdateFC timer frequency

UpdateFC timer frequency is equal to twice the value of register content
in nsec. These settings are recommended after stress testing with different
values.

Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
---
V3: No change

V2: Changed update_fc_val to update_fc_threshold

 drivers/pci/controller/pci-tegra.c | 34 ++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)

diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index 9c28f1d9f177..be39f28a7a28 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -178,6 +178,13 @@
 
 #define AFI_PEXBIAS_CTRL_0		0x168
 
+#define RP_PRIV_XP_DL		0x00000494
+#define  RP_PRIV_XP_DL_GEN2_UPD_FC_TSHOLD	(0x1ff << 1)
+
+#define RP_RX_HDR_LIMIT		0x00000e00
+#define  RP_RX_HDR_LIMIT_PW_MASK	(0xff << 8)
+#define  RP_RX_HDR_LIMIT_PW		(0x0e << 8)
+
 #define RP_ECTL_2_R1	0x00000e84
 #define  RP_ECTL_2_R1_RX_CTLE_1C_MASK		0xffff
 
@@ -208,6 +215,7 @@
 #define  RP_VEND_XP_DL_UP			(1 << 30)
 #define  RP_VEND_XP_OPPORTUNISTIC_ACK		(1 << 27)
 #define  RP_VEND_XP_OPPORTUNISTIC_UPDATEFC	(1 << 28)
+#define  RP_VEND_XP_UPDATE_FC_THRESHOLD_MASK	(0xff << 18)
 
 #define RP_VEND_CTL0	0x00000f44
 #define  RP_VEND_CTL0_DSK_RST_PULSE_WIDTH_MASK	(0xf << 12)
@@ -301,6 +309,7 @@ struct tegra_pcie_soc {
 	u32 tx_ref_sel;
 	u32 pads_refclk_cfg0;
 	u32 pads_refclk_cfg1;
+	u32 update_fc_threshold;
 	bool has_pex_clkreq_en;
 	bool has_pex_bias_ctrl;
 	bool has_intr_prsnt_sense;
@@ -310,6 +319,7 @@ struct tegra_pcie_soc {
 	bool program_uphy;
 	bool update_clamp_threshold;
 	bool program_deskew_time;
+	bool raw_violation_fixup;
 	struct {
 		struct {
 			u32 rp_ectl_2_r1;
@@ -641,6 +651,23 @@ static void tegra_pcie_apply_sw_fixup(struct tegra_pcie_port *port)
 		value |= RP_VEND_CTL0_DSK_RST_PULSE_WIDTH;
 		writel(value, port->base + RP_VEND_CTL0);
 	}
+
+	/* Fixup for read after write violation. */
+	if (soc->raw_violation_fixup) {
+		value = readl(port->base + RP_RX_HDR_LIMIT);
+		value &= ~RP_RX_HDR_LIMIT_PW_MASK;
+		value |= RP_RX_HDR_LIMIT_PW;
+		writel(value, port->base + RP_RX_HDR_LIMIT);
+
+		value = readl(port->base + RP_PRIV_XP_DL);
+		value |= RP_PRIV_XP_DL_GEN2_UPD_FC_TSHOLD;
+		writel(value, port->base + RP_PRIV_XP_DL);
+
+		value = readl(port->base + RP_VEND_XP);
+		value &= ~RP_VEND_XP_UPDATE_FC_THRESHOLD_MASK;
+		value |= soc->update_fc_threshold;
+		writel(value, port->base + RP_VEND_XP);
+	}
 }
 
 static void tegra_pcie_port_enable(struct tegra_pcie_port *port)
@@ -2382,6 +2409,7 @@ static const struct tegra_pcie_soc tegra20_pcie = {
 	.program_uphy = true,
 	.update_clamp_threshold = false,
 	.program_deskew_time = false,
+	.raw_violation_fixup = false,
 	.ectl.enable = false,
 };
 
@@ -2408,6 +2436,7 @@ static const struct tegra_pcie_soc tegra30_pcie = {
 	.program_uphy = true,
 	.update_clamp_threshold = false,
 	.program_deskew_time = false,
+	.raw_violation_fixup = false,
 	.ectl.enable = false,
 };
 
@@ -2418,6 +2447,8 @@ static const struct tegra_pcie_soc tegra124_pcie = {
 	.pads_pll_ctl = PADS_PLL_CTL_TEGRA30,
 	.tx_ref_sel = PADS_PLL_CTL_TXCLKREF_BUF_EN,
 	.pads_refclk_cfg0 = 0x44ac44ac,
+	/* FC threshold is bit[25:18] */
+	.update_fc_threshold = 0x03fc0000,
 	.has_pex_clkreq_en = true,
 	.has_pex_bias_ctrl = true,
 	.has_intr_prsnt_sense = true,
@@ -2427,6 +2458,7 @@ static const struct tegra_pcie_soc tegra124_pcie = {
 	.program_uphy = true,
 	.update_clamp_threshold = true,
 	.program_deskew_time = false,
+	.raw_violation_fixup = true,
 	.ectl.enable = false,
 };
 
@@ -2446,6 +2478,7 @@ static const struct tegra_pcie_soc tegra210_pcie = {
 	.program_uphy = true,
 	.update_clamp_threshold = true,
 	.program_deskew_time = true,
+	.raw_violation_fixup = false,
 	.ectl = {
 		.regs = {
 			.rp_ectl_2_r1 = 0x0000000f,
@@ -2484,6 +2517,7 @@ static const struct tegra_pcie_soc tegra186_pcie = {
 	.program_uphy = false,
 	.update_clamp_threshold = false,
 	.program_deskew_time = false,
+	.raw_violation_fixup = false,
 	.ectl.enable = false,
 };
 
-- 
2.17.1

[PATCH V3 15/29] PCI: tegra: Update flow control timer frequency in Tegra210

[Manikanta Maddireddy]

Recommended UpdateFC threshold in Tegra210 is 0x60 for best performance
of x1 link. Setting this to 0x60 provides the best balance between number
of UpdateFC packets and read data sent over the link.

UpdateFC timer frequency is equal to twice the value of register content
in nsec, i.e (2 * 0x60) = 192 nsec.

Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
---
V3: No change

V2: Changed update_fc_val to update_fc_threshold

 drivers/pci/controller/pci-tegra.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index be39f28a7a28..16d4d3cba3ff 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -320,6 +320,7 @@ struct tegra_pcie_soc {
 	bool update_clamp_threshold;
 	bool program_deskew_time;
 	bool raw_violation_fixup;
+	bool update_fc_timer;
 	struct {
 		struct {
 			u32 rp_ectl_2_r1;
@@ -668,6 +669,13 @@ static void tegra_pcie_apply_sw_fixup(struct tegra_pcie_port *port)
 		value |= soc->update_fc_threshold;
 		writel(value, port->base + RP_VEND_XP);
 	}
+
+	if (soc->update_fc_timer) {
+		value = readl(port->base + RP_VEND_XP);
+		value &= ~RP_VEND_XP_UPDATE_FC_THRESHOLD_MASK;
+		value |= soc->update_fc_threshold;
+		writel(value, port->base + RP_VEND_XP);
+	}
 }
 
 static void tegra_pcie_port_enable(struct tegra_pcie_port *port)
@@ -2410,6 +2418,7 @@ static const struct tegra_pcie_soc tegra20_pcie = {
 	.update_clamp_threshold = false,
 	.program_deskew_time = false,
 	.raw_violation_fixup = false,
+	.update_fc_timer = false,
 	.ectl.enable = false,
 };
 
@@ -2437,6 +2446,7 @@ static const struct tegra_pcie_soc tegra30_pcie = {
 	.update_clamp_threshold = false,
 	.program_deskew_time = false,
 	.raw_violation_fixup = false,
+	.update_fc_timer = false,
 	.ectl.enable = false,
 };
 
@@ -2459,6 +2469,7 @@ static const struct tegra_pcie_soc tegra124_pcie = {
 	.update_clamp_threshold = true,
 	.program_deskew_time = false,
 	.raw_violation_fixup = true,
+	.update_fc_timer = false,
 	.ectl.enable = false,
 };
 
@@ -2469,6 +2480,8 @@ static const struct tegra_pcie_soc tegra210_pcie = {
 	.pads_pll_ctl = PADS_PLL_CTL_TEGRA30,
 	.tx_ref_sel = PADS_PLL_CTL_TXCLKREF_BUF_EN,
 	.pads_refclk_cfg0 = 0x90b890b8,
+	/* FC threshold is bit[25:18] */
+	.update_fc_threshold = 0x01800000,
 	.has_pex_clkreq_en = true,
 	.has_pex_bias_ctrl = true,
 	.has_intr_prsnt_sense = true,
@@ -2479,6 +2492,7 @@ static const struct tegra_pcie_soc tegra210_pcie = {
 	.update_clamp_threshold = true,
 	.program_deskew_time = true,
 	.raw_violation_fixup = false,
+	.update_fc_timer = true,
 	.ectl = {
 		.regs = {
 			.rp_ectl_2_r1 = 0x0000000f,
@@ -2518,6 +2532,7 @@ static const struct tegra_pcie_soc tegra186_pcie = {
 	.update_clamp_threshold = false,
 	.program_deskew_time = false,
 	.raw_violation_fixup = false,
+	.update_fc_timer = false,
 	.ectl.enable = false,
 };
 
-- 
2.17.1

[PATCH V3 16/29] PCI: tegra: Set target speed as Gen1 before starting LTSSM

[Manikanta Maddireddy]

PCIe link up fails with few legacy endpoints if root port advertises both
Gen-1 and Gen-2 speeds in Tegra. This is because link number negotiation
fails if both Gen1 & Gen2 are advertised. Tegra doesn't retry link up by
advertising only Gen1. Hence, the strategy followed here is to initially
advertise only Gen-1 and after link is up, retrain link to Gen-2 speed.

Tegra doesn't support HW autonomous speed change. Link comes up in Gen1
even if Gen2 is advertised, so there is no downside of this change.

This behavior is observed with following two PCIe devices on Tegra,
 - Fusion HDTV 5 Express card
 - IOGear SIL - PCIE - SATA card

Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
---
V3: No change

V2: Updated commit log to reflect why this issue is observed on Tegra with
these particular cards

 drivers/pci/controller/pci-tegra.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index 16d4d3cba3ff..9ee111062ab7 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -676,6 +676,17 @@ static void tegra_pcie_apply_sw_fixup(struct tegra_pcie_port *port)
 		value |= soc->update_fc_threshold;
 		writel(value, port->base + RP_VEND_XP);
 	}
+
+	/*
+	 * PCIe link doesn't come up with few legacy PCIe endpoints if
+	 * root port advertises both Gen-1 and Gen-2 speeds in Tegra.
+	 * Hence, the strategy followed here is to initially advertise
+	 * only Gen-1 and after link is up, retrain link to Gen-2 speed
+	 */
+	value = readl(port->base + RP_LINK_CONTROL_STATUS_2);
+	value &= ~PCI_EXP_LNKSTA_CLS;
+	value |= PCI_EXP_LNKSTA_CLS_2_5GB;
+	writel(value, port->base + RP_LINK_CONTROL_STATUS_2);
 }
 
 static void tegra_pcie_port_enable(struct tegra_pcie_port *port)
-- 
2.17.1

[PATCH V3 17/29] PCI: tegra: Fix PLLE power down issue due to CLKREQ# signal

[Manikanta Maddireddy]

Disable controllers which failed to link up and configure CLKREQ# signals
of these controllers as GPIO. This is required to avoid CLKREQ# signal of
inactive controllers interfering with PLLE power down sequence.

PCIE_CLKREQ_GPIO bits are defined only in Tegra186, however programming
these bits in other SoCs doesn't cause any side effects. Program these
bits for all Tegra SoCs to avoid conditional check.

Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
---
V3: No change

V2: Corrected the comment in driver

 drivers/pci/controller/pci-tegra.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index 9ee111062ab7..4767af9f3b88 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -160,6 +160,8 @@
 #define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_211	(0x1 << 20)
 #define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_411	(0x2 << 20)
 #define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_111	(0x2 << 20)
+#define  AFI_PCIE_CONFIG_PCIE_CLKREQ_GPIO(x)		(1 << ((x) + 29))
+#define  AFI_PCIE_CONFIG_PCIE_CLKREQ_GPIO_ALL		(0x7 << 29)
 
 #define AFI_FUSE			0x104
 #define  AFI_FUSE_PCIE_T0_GEN2_DIS	(1 << 2)
@@ -741,6 +743,12 @@ static void tegra_pcie_port_disable(struct tegra_pcie_port *port)
 
 	value &= ~AFI_PEX_CTRL_REFCLK_EN;
 	afi_writel(port->pcie, value, ctrl);
+
+	/* disable PCIe port and set CLKREQ# as GPIO to allow PLLE power down */
+	value = afi_readl(port->pcie, AFI_PCIE_CONFIG);
+	value |= AFI_PCIE_CONFIG_PCIE_DISABLE(port->index);
+	value |= AFI_PCIE_CONFIG_PCIE_CLKREQ_GPIO(port->index);
+	afi_writel(port->pcie, value, AFI_PCIE_CONFIG);
 }
 
 static void tegra_pcie_port_free(struct tegra_pcie_port *port)
@@ -1153,9 +1161,12 @@ static void tegra_pcie_enable_controller(struct tegra_pcie *pcie)
 	value = afi_readl(pcie, AFI_PCIE_CONFIG);
 	value &= ~AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_MASK;
 	value |= AFI_PCIE_CONFIG_PCIE_DISABLE_ALL | pcie->xbar_config;
+	value |= AFI_PCIE_CONFIG_PCIE_CLKREQ_GPIO_ALL;
 
-	list_for_each_entry(port, &pcie->ports, list)
+	list_for_each_entry(port, &pcie->ports, list) {
 		value &= ~AFI_PCIE_CONFIG_PCIE_DISABLE(port->index);
+		value &= ~AFI_PCIE_CONFIG_PCIE_CLKREQ_GPIO(port->index);
+	}
 
 	afi_writel(pcie, value, AFI_PCIE_CONFIG);
 
-- 
2.17.1

[PATCH V3 18/29] PCI: tegra: Program AFI_CACHE* registers only for Tegra20

[Manikanta Maddireddy]

Cacheable upstream transactions are supported in Tegra20 and Tegra186 only.
AFI_CACHE* registers are available in Tegra20 to support cacheable upstream
transactions. In Tegra186, AFI_AXCACHE register is defined instead of
AFI_CACHE* to be in line with its MSS design. Therefore, program AFI_CACHE*
registers only for Tegra20.

Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
---
V3: Initialized has_cache_bars variable for each soc data structure.

V2: Used soc variable for comparision instead of compatible string.

 drivers/pci/controller/pci-tegra.c | 18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index 4767af9f3b88..0f02f54f8a61 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -323,6 +323,7 @@ struct tegra_pcie_soc {
 	bool program_deskew_time;
 	bool raw_violation_fixup;
 	bool update_fc_timer;
+	bool has_cache_bars;
 	struct {
 		struct {
 			u32 rp_ectl_2_r1;
@@ -932,11 +933,13 @@ static void tegra_pcie_setup_translations(struct tegra_pcie *pcie)
 	afi_writel(pcie, 0, AFI_AXI_BAR5_SZ);
 	afi_writel(pcie, 0, AFI_FPCI_BAR5);
 
-	/* map all upstream transactions as uncached */
-	afi_writel(pcie, 0, AFI_CACHE_BAR0_ST);
-	afi_writel(pcie, 0, AFI_CACHE_BAR0_SZ);
-	afi_writel(pcie, 0, AFI_CACHE_BAR1_ST);
-	afi_writel(pcie, 0, AFI_CACHE_BAR1_SZ);
+	if (pcie->soc->has_cache_bars) {
+		/* map all upstream transactions as uncached */
+		afi_writel(pcie, 0, AFI_CACHE_BAR0_ST);
+		afi_writel(pcie, 0, AFI_CACHE_BAR0_SZ);
+		afi_writel(pcie, 0, AFI_CACHE_BAR1_ST);
+		afi_writel(pcie, 0, AFI_CACHE_BAR1_SZ);
+	}
 
 	/* MSI translations are setup only when needed */
 	afi_writel(pcie, 0, AFI_MSI_FPCI_BAR_ST);
@@ -2441,6 +2444,7 @@ static const struct tegra_pcie_soc tegra20_pcie = {
 	.program_deskew_time = false,
 	.raw_violation_fixup = false,
 	.update_fc_timer = false,
+	.has_cache_bars = true,
 	.ectl.enable = false,
 };
 
@@ -2469,6 +2473,7 @@ static const struct tegra_pcie_soc tegra30_pcie = {
 	.program_deskew_time = false,
 	.raw_violation_fixup = false,
 	.update_fc_timer = false,
+	.has_cache_bars = false,
 	.ectl.enable = false,
 };
 
@@ -2492,6 +2497,7 @@ static const struct tegra_pcie_soc tegra124_pcie = {
 	.program_deskew_time = false,
 	.raw_violation_fixup = true,
 	.update_fc_timer = false,
+	.has_cache_bars = false,
 	.ectl.enable = false,
 };
 
@@ -2515,6 +2521,7 @@ static const struct tegra_pcie_soc tegra210_pcie = {
 	.program_deskew_time = true,
 	.raw_violation_fixup = false,
 	.update_fc_timer = true,
+	.has_cache_bars = false,
 	.ectl = {
 		.regs = {
 			.rp_ectl_2_r1 = 0x0000000f,
@@ -2555,6 +2562,7 @@ static const struct tegra_pcie_soc tegra186_pcie = {
 	.program_deskew_time = false,
 	.raw_violation_fixup = false,
 	.update_fc_timer = false,
+	.has_cache_bars = false,
 	.ectl.enable = false,
 };
 
-- 
2.17.1

[PATCH V3 19/29] PCI: tegra: Change PRSNT_SENSE IRQ log to debug

[Manikanta Maddireddy]

PRSNT_MAP bit field is programmed to update the slot present status.
PRSNT_SENSE IRQ is triggered when this bit field is programmed, which is
not an error. Add a new if condition to trap PRSNT_SENSE code and print it
with debug log level.

Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
---
V3: Correct typos in commit log

V2: If-else to switch-case conversion patch is dropped, this patch is
rebased to stay with if-else statements

 drivers/pci/controller/pci-tegra.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index 0f02f54f8a61..ac57c5badd9b 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -864,7 +864,7 @@ static irqreturn_t tegra_pcie_isr(int irq, void *arg)
 	 * do not pollute kernel log with master abort reports since they
 	 * happen a lot during enumeration
 	 */
-	if (code == AFI_INTR_MASTER_ABORT)
+	if (code == AFI_INTR_MASTER_ABORT || code == AFI_INTR_PE_PRSNT_SENSE)
 		dev_dbg(dev, "%s, signature: %08x\n", err_msg[code], signature);
 	else
 		dev_err(dev, "%s, signature: %08x\n", err_msg[code], signature);
-- 
2.17.1

[PATCH V3 20/29] PCI: tegra: Use legacy IRQ for port service drivers

[Manikanta Maddireddy]

Tegra signals PCIe services like AER, PME, etc. over legacy IRQ line.
By default, service drivers register interrupt routine over MSI IRQ line.
Use pcie_pme_disable_msi() function to disable MSI for service drivers.

PME and AER interrupts registered to MSI without this change,
cat /proc/interrupts | grep -i pci
36: 21 0 0 0 0 0 GICv2 104 Level       PCIE
37: 35 0 0 0 0 0 GICv2 105 Level       Tegra PCIe MSI
76: 0  0 0 0 0 0 Tegra PCIe MSI 0 Edge PCIe PME, aerdrv, PCIe BW notif

PME and AER interrupts registered to legacy IRQ with this change,
cat /proc/interrupts | grep -i pci
36: 33 0 0 0 0 0 GICv2 104 Level      PCIE, PCIe PME, aerdrv, PCIe BW notif
37: 52 0 0 0 0 0 GICv2 105 Level      Tegra PCIe MSI

Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
---
V3: Corrected typo in commit log

V2: No change

 drivers/pci/controller/pci-tegra.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index ac57c5badd9b..0024bc42b400 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -41,6 +41,7 @@
 #include <soc/tegra/pmc.h>
 
 #include "../pci.h"
+#include "../pcie/portdrv.h"
 
 #define INT_PCI_MSI_NR (8 * 32)
 
@@ -2725,6 +2726,9 @@ static int tegra_pcie_probe(struct platform_device *pdev)
 		goto put_resources;
 	}
 
+	/* Switch to legacy IRQ for PCIe services like AER, PME*/
+	pcie_pme_disable_msi();
+
 	pm_runtime_enable(pcie->dev);
 	err = pm_runtime_get_sync(pcie->dev);
 	if (err) {
-- 
2.17.1

[PATCH V3 21/29] PCI: tegra: Add AFI_PEX2_CTRL reg offset as part of soc struct

[Manikanta Maddireddy]

Tegra186 and Tegra30 have three PCIe root ports. AFI_PEX2_CTRL register
is defined for third root port. Offset of this register in Tegra186 is
different from Tegra30, so add offset as part of soc data structure.

Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
---
V3: No change

V2: No change

 drivers/pci/controller/pci-tegra.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index 0024bc42b400..d20c88a79e00 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -169,7 +169,6 @@
 
 #define AFI_PEX0_CTRL			0x110
 #define AFI_PEX1_CTRL			0x118
-#define AFI_PEX2_CTRL			0x128
 #define  AFI_PEX_CTRL_RST		(1 << 0)
 #define  AFI_PEX_CTRL_CLKREQ_EN		(1 << 1)
 #define  AFI_PEX_CTRL_REFCLK_EN		(1 << 3)
@@ -308,6 +307,7 @@ struct tegra_pcie_soc {
 	unsigned int num_ports;
 	const struct tegra_pcie_port_soc *ports;
 	unsigned int msi_base_shift;
+	unsigned long afi_pex2_ctrl;
 	u32 pads_pll_ctl;
 	u32 tx_ref_sel;
 	u32 pads_refclk_cfg0;
@@ -518,6 +518,7 @@ static struct pci_ops tegra_pcie_ops = {
 
 static unsigned long tegra_pcie_port_get_pex_ctrl(struct tegra_pcie_port *port)
 {
+	const struct tegra_pcie_soc *soc = port->pcie->soc;
 	unsigned long ret = 0;
 
 	switch (port->index) {
@@ -530,7 +531,7 @@ static unsigned long tegra_pcie_port_get_pex_ctrl(struct tegra_pcie_port *port)
 		break;
 
 	case 2:
-		ret = AFI_PEX2_CTRL;
+		ret = soc->afi_pex2_ctrl;
 		break;
 	}
 
@@ -2431,6 +2432,7 @@ static const struct tegra_pcie_soc tegra20_pcie = {
 	.num_ports = 2,
 	.ports = tegra20_pcie_ports,
 	.msi_base_shift = 0,
+	.afi_pex2_ctrl = 0x128,
 	.pads_pll_ctl = PADS_PLL_CTL_TEGRA20,
 	.tx_ref_sel = PADS_PLL_CTL_TXCLKREF_DIV10,
 	.pads_refclk_cfg0 = 0xfa5cfa5c,
@@ -2548,6 +2550,7 @@ static const struct tegra_pcie_soc tegra186_pcie = {
 	.num_ports = 3,
 	.ports = tegra186_pcie_ports,
 	.msi_base_shift = 8,
+	.afi_pex2_ctrl = 0x19c,
 	.pads_pll_ctl = PADS_PLL_CTL_TEGRA30,
 	.tx_ref_sel = PADS_PLL_CTL_TXCLKREF_BUF_EN,
 	.pads_refclk_cfg0 = 0x80b880b8,
-- 
2.17.1

[PATCH V3 22/29] PCI: tegra: Access endpoint config only if PCIe link is up

[Manikanta Maddireddy]

Few endpoints like Wi-Fi supports power on/off and to leverage that
root port must support hot-plug and hot-unplug. Tegra PCIe doesn't
support hot-plug and hot-unplug, however it supports endpoint power
on/off feature as follows,
 - Power off sequence:
   - Transition of PCIe link to L2
   - Power off endpoint
   - Leave root port in power up state with the link in L2
 - Power on sequence:
   - Power on endpoint
   - Apply hot reset to get PCIe link up

PCIe client driver stops accessing PCIe endpoint config and BAR registers
after endpoint is powered off. However, software applications like x11
server or lspci can access endpoint config registers in which case
host controller raises "response decoding" errors. To avoid this scenario,
add PCIe link up check in config read and write callback functions before
accessing endpoint config registers.

Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
---
V3: Update the commit log with explanation for the need of this patch

V2: Change tegra_pcie_link_status() to tegra_pcie_link_up()

 drivers/pci/controller/pci-tegra.c | 38 ++++++++++++++++++++++++++++++
 1 file changed, 38 insertions(+)

diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index d20c88a79e00..33f4dfab9e35 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -428,6 +428,14 @@ static inline u32 pads_readl(struct tegra_pcie *pcie, unsigned long offset)
 	return readl(pcie->pads + offset);
 }
 
+static bool tegra_pcie_link_up(struct tegra_pcie_port *port)
+{
+	u32 value;
+
+	value = readl(port->base + RP_LINK_CONTROL_STATUS);
+	return !!(value & RP_LINK_CONTROL_STATUS_DL_LINK_ACTIVE);
+}
+
 /*
  * The configuration space mapping on Tegra is somewhat similar to the ECAM
  * defined by PCIe. However it deviates a bit in how the 4 bits for extended
@@ -493,20 +501,50 @@ static void __iomem *tegra_pcie_map_bus(struct pci_bus *bus,
 static int tegra_pcie_config_read(struct pci_bus *bus, unsigned int devfn,
 				  int where, int size, u32 *value)
 {
+	struct tegra_pcie *pcie = bus->sysdata;
+	struct pci_dev *bridge;
+	struct tegra_pcie_port *port;
+
 	if (bus->number == 0)
 		return pci_generic_config_read32(bus, devfn, where, size,
 						 value);
 
+	bridge = pcie_find_root_port(bus->self);
+
+	list_for_each_entry(port, &pcie->ports, list)
+		if (port->index + 1 == PCI_SLOT(bridge->devfn))
+			break;
+
+	/* If there is no link, then there is no device */
+	if (!tegra_pcie_link_up(port)) {
+		*value = 0xffffffff;
+		return PCIBIOS_DEVICE_NOT_FOUND;
+	}
+
 	return pci_generic_config_read(bus, devfn, where, size, value);
 }
 
 static int tegra_pcie_config_write(struct pci_bus *bus, unsigned int devfn,
 				   int where, int size, u32 value)
 {
+	struct tegra_pcie *pcie = bus->sysdata;
+	struct tegra_pcie_port *port;
+	struct pci_dev *bridge;
+
 	if (bus->number == 0)
 		return pci_generic_config_write32(bus, devfn, where, size,
 						  value);
 
+	bridge = pcie_find_root_port(bus->self);
+
+	list_for_each_entry(port, &pcie->ports, list)
+		if (port->index + 1 == PCI_SLOT(bridge->devfn))
+			break;
+
+	/* If there is no link, then there is no device */
+	if (!tegra_pcie_link_up(port))
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
 	return pci_generic_config_write(bus, devfn, where, size, value);
 }
 
-- 
2.17.1

[PATCH V3 23/29] dt-bindings: pci: tegra: Document PCIe DPD pinctrl optional prop

[Manikanta Maddireddy]

Document PCIe DPD pinctrl optional property to put PEX clk & BIAS pads
in low power mode.

Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Acked-by: Thierry Reding <treding@nvidia.com>
---
V3: No change

V2: Using standard pinctrl names, default and idle

 .../devicetree/bindings/pci/nvidia,tegra20-pcie.txt       | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/Documentation/devicetree/bindings/pci/nvidia,tegra20-pcie.txt b/Documentation/devicetree/bindings/pci/nvidia,tegra20-pcie.txt
index 145a4f04194f..7939bca47861 100644
--- a/Documentation/devicetree/bindings/pci/nvidia,tegra20-pcie.txt
+++ b/Documentation/devicetree/bindings/pci/nvidia,tegra20-pcie.txt
@@ -65,6 +65,14 @@ Required properties:
   - afi
   - pcie_x
 
+Optional properties:
+- pinctrl-names: A list of pinctrl state names. Must contain the following
+  entries:
+  - "default": active state, puts PCIe I/O out of deep power down state
+  - "idle": puts PCIe I/O into deep power down state
+- pinctrl-0: phandle for the default/active state of pin configurations.
+- pinctrl-1: phandle for the idle state of pin configurations.
+
 Required properties on Tegra124 and later (deprecated):
 - phys: Must contain an entry for each entry in phy-names.
 - phy-names: Must include the following entries:
-- 
2.17.1

[PATCH V3 24/29] arm64: tegra: Add PEX DPD states as pinctrl properties

[Manikanta Maddireddy]

Add PEX deep power down states as pinctrl properties to set in PCIe driver.
In Tegra210, BIAS pads are not in power down mode when clamps are applied.
To set the pads in DPD, pass the PEX DPD states as pinctrl properties to
PCIe driver.

Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
---
V3: No change

V2: Using standard pinctrl names, default and idle

 arch/arm64/boot/dts/nvidia/tegra210.dtsi | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/arch/arm64/boot/dts/nvidia/tegra210.dtsi b/arch/arm64/boot/dts/nvidia/tegra210.dtsi
index a550c0a4d572..3899c54ea28f 100644
--- a/arch/arm64/boot/dts/nvidia/tegra210.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra210.dtsi
@@ -48,6 +48,11 @@
 			 <&tegra_car 72>,
 			 <&tegra_car 74>;
 		reset-names = "pex", "afi", "pcie_x";
+
+		pinctrl-names = "default", "idle";
+		pinctrl-0 = <&pex_dpd_disable>;
+		pinctrl-1 = <&pex_dpd_enable>;
+
 		status = "disabled";
 
 		pci@1,0 {
@@ -848,6 +853,20 @@
 			pins = "sdmmc3";
 			power-source = <TEGRA_IO_PAD_VOLTAGE_1V8>;
 		};
+
+		pex_dpd_disable: pex_en {
+			pex-dpd-disable {
+				pins = "pex-bias", "pex-clk1", "pex-clk2";
+				low-power-disable;
+			};
+		};
+
+		pex_dpd_enable: pex_dis {
+			pex-dpd-enable {
+				pins = "pex-bias", "pex-clk1", "pex-clk2";
+				low-power-enable;
+			};
+		};
 	};
 
 	fuse@7000f800 {
-- 
2.17.1

[PATCH V3 25/29] PCI: tegra: Put PEX CLK & BIAS pads in DPD mode

[Manikanta Maddireddy]

In Tegra210 AFI design has clamp value for the BIAS pad as 0, which keeps
the bias pad in non power down mode. This is leading to power consumption
of 2 mW in BIAS pad, even if the PCIe partition is powergated. To avoid
unnecessary power consumption, put PEX CLK & BIAS pads in deep power down
mode when PCIe partition is power gated.

Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
---
V3: No change

V2: Using standard pinctrl functions to apply default and idle states

 drivers/pci/controller/pci-tegra.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index 33f4dfab9e35..06b99fcbf382 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -30,6 +30,7 @@
 #include <linux/of_platform.h>
 #include <linux/pci.h>
 #include <linux/phy/phy.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
 #include <linux/reset.h>
 #include <linux/sizes.h>
@@ -2875,6 +2876,7 @@ static int __maybe_unused tegra_pcie_pm_suspend(struct device *dev)
 	if (IS_ENABLED(CONFIG_PCI_MSI))
 		tegra_pcie_disable_msi(pcie);
 
+	pinctrl_pm_select_idle_state(dev);
 	tegra_pcie_power_off(pcie);
 
 	return 0;
@@ -2890,6 +2892,13 @@ static int __maybe_unused tegra_pcie_pm_resume(struct device *dev)
 		dev_err(dev, "tegra pcie power on fail: %d\n", err);
 		return err;
 	}
+
+	err = pinctrl_pm_select_default_state(dev);
+	if (err < 0) {
+		dev_err(dev, "failed to disable PCIe IO DPD: %d\n", err);
+		goto poweroff;
+	}
+
 	tegra_pcie_enable_controller(pcie);
 	tegra_pcie_setup_translations(pcie);
 
@@ -2899,7 +2908,7 @@ static int __maybe_unused tegra_pcie_pm_resume(struct device *dev)
 	err = clk_prepare_enable(pcie->pex_clk);
 	if (err) {
 		dev_err(dev, "failed to enable PEX clock: %d\n", err);
-		goto poweroff;
+		goto pex_dpd_enable;
 	}
 
 	reset_control_deassert(pcie->pex_rst);
@@ -2920,6 +2929,8 @@ static int __maybe_unused tegra_pcie_pm_resume(struct device *dev)
 disable_pex_clk:
 	reset_control_assert(pcie->pex_rst);
 	clk_disable_unprepare(pcie->pex_clk);
+pex_dpd_enable:
+	pinctrl_pm_select_idle_state(dev);
 poweroff:
 	tegra_pcie_power_off(pcie);
 
-- 
2.17.1

[PATCH V3 26/29] PCI: Add DT binding for "reset-gpios" property

[Manikanta Maddireddy]

Add DT binding for "reset-gpios" property which supports GPIO based PERST#
signal.

Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
---
V3: Moved to common pci binding doc

V2: Using standard "reset-gpio" property

 Documentation/devicetree/bindings/pci/pci.txt | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/devicetree/bindings/pci/pci.txt b/Documentation/devicetree/bindings/pci/pci.txt
index c77981c5dd18..79124898aa5b 100644
--- a/Documentation/devicetree/bindings/pci/pci.txt
+++ b/Documentation/devicetree/bindings/pci/pci.txt
@@ -24,3 +24,6 @@ driver implementation may support the following properties:
    unsupported link speed, for instance, trying to do training for
    unsupported link speed, etc.  Must be '4' for gen4, '3' for gen3, '2'
    for gen2, and '1' for gen1. Any other values are invalid.
+- reset-gpios:
+   If present this property specifies PERST# GPIO. Host drivers can parse the
+   GPIO and apply fundamental reset to endpoints.
-- 
2.17.1

Re: [PATCH V3 26/29] PCI: Add DT binding for "reset-gpios" property

[Rob Herring]

On Mon, 13 May 2019 23:37:41 +0530, Manikanta Maddireddy wrote:
> Add DT binding for "reset-gpios" property which supports GPIO based PERST#
> signal.
> 
> Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
> Acked-by: Thierry Reding <treding@nvidia.com>
> ---
> V3: Moved to common pci binding doc
> 
> V2: Using standard "reset-gpio" property
> 
>  Documentation/devicetree/bindings/pci/pci.txt | 3 +++
>  1 file changed, 3 insertions(+)
> 

Reviewed-by: Rob Herring <robh@kernel.org>

[PATCH V3 27/29] PCI: OF: Add of_pci_get_reset_gpio() to parse reset-gpios from DT

[Manikanta Maddireddy]

This new helper function could be used by host drivers to get the reset
GPIO descriptor. If the property isn't assigned, it will return NULL to
the caller.

Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
---
V3: New patch to add helper function to parse "reset-gpios"

 drivers/pci/of.c       | 18 ++++++++++++++++++
 include/linux/of_pci.h | 10 ++++++++++
 2 files changed, 28 insertions(+)

diff --git a/drivers/pci/of.c b/drivers/pci/of.c
index 9454c90980c9..2a0282115ff0 100644
--- a/drivers/pci/of.c
+++ b/drivers/pci/of.c
@@ -6,6 +6,7 @@
  */
 #define pr_fmt(fmt)	"PCI: OF: " fmt
 
+#include <linux/gpio/consumer.h>
 #include <linux/irqdomain.h>
 #include <linux/kernel.h>
 #include <linux/pci.h>
@@ -224,6 +225,23 @@ int of_pci_get_max_link_speed(struct device_node *node)
 }
 EXPORT_SYMBOL_GPL(of_pci_get_max_link_speed);
 
+/**
+ * of_pci_get_reset_gpio() - Get PCI reset gpio descriptor.
+ *
+ * @node: device node
+ *
+ * Returns PCI reset gpio descriptor from DT, or an ERR_PTR() if the
+ * required property is invalid.
+ */
+struct gpio_desc *of_pci_get_reset_gpio(struct device *dev,
+					struct device_node *node,
+					int dflags, char *label)
+{
+	return devm_gpiod_get_from_of_node(dev, node, "reset-gpios", 0, dflags,
+					   label);
+}
+EXPORT_SYMBOL_GPL(of_pci_get_reset_gpio);
+
 /**
  * of_pci_check_probe_only - Setup probe only mode if linux,pci-probe-only
  *                           is present and valid
diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h
index 21a89c4880fa..230ddc813ef9 100644
--- a/include/linux/of_pci.h
+++ b/include/linux/of_pci.h
@@ -13,6 +13,9 @@ struct device_node;
 struct device_node *of_pci_find_child_device(struct device_node *parent,
 					     unsigned int devfn);
 int of_pci_get_devfn(struct device_node *np);
+struct gpio_desc *of_pci_get_reset_gpio(struct device *dev,
+					struct device_node *np,
+					int dflags, char *label);
 void of_pci_check_probe_only(void);
 #else
 static inline struct device_node *of_pci_find_child_device(struct device_node *parent,
@@ -26,6 +29,13 @@ static inline int of_pci_get_devfn(struct device_node *np)
 	return -EINVAL;
 }
 
+static inline struct gpio_desc *of_pci_get_reset_gpio(struct device *dev,
+						      struct device_node *np,
+						      int dflags, char *label)
+{
+	return -EINVAL;
+}
+
 static inline void of_pci_check_probe_only(void) { }
 #endif
 
-- 
2.17.1

Re: [PATCH V3 27/29] PCI: OF: Add of_pci_get_reset_gpio() to parse reset-gpios from DT

[Rob Herring]

On Mon, May 13, 2019 at 11:37:42PM +0530, Manikanta Maddireddy wrote:
> This new helper function could be used by host drivers to get the reset
> GPIO descriptor. If the property isn't assigned, it will return NULL to
> the caller.
> 
> Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
> ---
> V3: New patch to add helper function to parse "reset-gpios"
> 
>  drivers/pci/of.c       | 18 ++++++++++++++++++
>  include/linux/of_pci.h | 10 ++++++++++
>  2 files changed, 28 insertions(+)
> 
> diff --git a/drivers/pci/of.c b/drivers/pci/of.c
> index 9454c90980c9..2a0282115ff0 100644
> --- a/drivers/pci/of.c
> +++ b/drivers/pci/of.c
> @@ -6,6 +6,7 @@
>   */
>  #define pr_fmt(fmt)	"PCI: OF: " fmt
>  
> +#include <linux/gpio/consumer.h>
>  #include <linux/irqdomain.h>
>  #include <linux/kernel.h>
>  #include <linux/pci.h>
> @@ -224,6 +225,23 @@ int of_pci_get_max_link_speed(struct device_node *node)
>  }
>  EXPORT_SYMBOL_GPL(of_pci_get_max_link_speed);
>  
> +/**
> + * of_pci_get_reset_gpio() - Get PCI reset gpio descriptor.
> + *
> + * @node: device node
> + *
> + * Returns PCI reset gpio descriptor from DT, or an ERR_PTR() if the
> + * required property is invalid.
> + */
> +struct gpio_desc *of_pci_get_reset_gpio(struct device *dev,
> +					struct device_node *node,
> +					int dflags, char *label)
> +{
> +	return devm_gpiod_get_from_of_node(dev, node, "reset-gpios", 0, dflags,
> +					   label);
> +}

There's nothing PCI specific about this and 'reset-gpios' is pretty 
widely used. Either we should have this somewhere common or perhaps not 
worth a wrapper to save 1 parameter.

Also, I believe you can pass just 'reset' so the deprecated form 
'reset-gpio' can also be supported. 

Rob

Re: [PATCH V3 27/29] PCI: OF: Add of_pci_get_reset_gpio() to parse reset-gpios from DT

[Manikanta Maddireddy]

On 15-May-19 12:01 AM, Rob Herring wrote:
> On Mon, May 13, 2019 at 11:37:42PM +0530, Manikanta Maddireddy wrote:
>> This new helper function could be used by host drivers to get the reset
>> GPIO descriptor. If the property isn't assigned, it will return NULL to
>> the caller.
>>
>> Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
>> ---
>> V3: New patch to add helper function to parse "reset-gpios"
>>
>>  drivers/pci/of.c       | 18 ++++++++++++++++++
>>  include/linux/of_pci.h | 10 ++++++++++
>>  2 files changed, 28 insertions(+)
>>
>> diff --git a/drivers/pci/of.c b/drivers/pci/of.c
>> index 9454c90980c9..2a0282115ff0 100644
>> --- a/drivers/pci/of.c
>> +++ b/drivers/pci/of.c
>> @@ -6,6 +6,7 @@
>>   */
>>  #define pr_fmt(fmt)	"PCI: OF: " fmt
>>  
>> +#include <linux/gpio/consumer.h>
>>  #include <linux/irqdomain.h>
>>  #include <linux/kernel.h>
>>  #include <linux/pci.h>
>> @@ -224,6 +225,23 @@ int of_pci_get_max_link_speed(struct device_node *node)
>>  }
>>  EXPORT_SYMBOL_GPL(of_pci_get_max_link_speed);
>>  
>> +/**
>> + * of_pci_get_reset_gpio() - Get PCI reset gpio descriptor.
>> + *
>> + * @node: device node
>> + *
>> + * Returns PCI reset gpio descriptor from DT, or an ERR_PTR() if the
>> + * required property is invalid.
>> + */
>> +struct gpio_desc *of_pci_get_reset_gpio(struct device *dev,
>> +					struct device_node *node,
>> +					int dflags, char *label)
>> +{
>> +	return devm_gpiod_get_from_of_node(dev, node, "reset-gpios", 0, dflags,
>> +					   label);
>> +}
> There's nothing PCI specific about this and 'reset-gpios' is pretty 
> widely used. Either we should have this somewhere common or perhaps not 
> worth a wrapper to save 1 parameter.
>
> Also, I believe you can pass just 'reset' so the deprecated form 
> 'reset-gpio' can also be supported. 
>
> Rob

I also think that it doesn't need a wrapper to save one parameter.
I will drop this patch and use devm_gpiod_get_from_of_node() directly
in pci-tegra driver.

Manikanta

[PATCH V3 28/29] PCI: tegra: Add support for GPIO based PERST#

[Manikanta Maddireddy]

Add support for GPIO based PERST# signal. GPIO number comes from per port
PCIe device tree node.

Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
---
V3: Using helper function to get reset-gpios

V2: Using standard "reset-gpio" property

 drivers/pci/controller/pci-tegra.c | 42 +++++++++++++++++++++++++-----
 1 file changed, 36 insertions(+), 6 deletions(-)

diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index 06b99fcbf382..b021863303f1 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -17,6 +17,7 @@
 #include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/export.h>
+#include <linux/gpio.h>
 #include <linux/interrupt.h>
 #include <linux/iopoll.h>
 #include <linux/irq.h>
@@ -400,6 +401,8 @@ struct tegra_pcie_port {
 	unsigned int lanes;
 
 	struct phy **phys;
+
+	struct gpio_desc *reset_gpiod;
 };
 
 struct tegra_pcie_bus {
@@ -583,15 +586,23 @@ static void tegra_pcie_port_reset(struct tegra_pcie_port *port)
 	unsigned long value;
 
 	/* pulse reset signal */
-	value = afi_readl(port->pcie, ctrl);
-	value &= ~AFI_PEX_CTRL_RST;
-	afi_writel(port->pcie, value, ctrl);
+	if (port->reset_gpiod) {
+		gpiod_set_value(port->reset_gpiod, 0);
+	} else {
+		value = afi_readl(port->pcie, ctrl);
+		value &= ~AFI_PEX_CTRL_RST;
+		afi_writel(port->pcie, value, ctrl);
+	}
 
 	usleep_range(1000, 2000);
 
-	value = afi_readl(port->pcie, ctrl);
-	value |= AFI_PEX_CTRL_RST;
-	afi_writel(port->pcie, value, ctrl);
+	if (port->reset_gpiod) {
+		gpiod_set_value(port->reset_gpiod, 1);
+	} else {
+		value = afi_readl(port->pcie, ctrl);
+		value |= AFI_PEX_CTRL_RST;
+		afi_writel(port->pcie, value, ctrl);
+	}
 }
 
 static void tegra_pcie_enable_rp_features(struct tegra_pcie_port *port)
@@ -2238,6 +2249,7 @@ static int tegra_pcie_parse_dt(struct tegra_pcie *pcie)
 		struct tegra_pcie_port *rp;
 		unsigned int index;
 		u32 value;
+		char *label;
 
 		err = of_pci_get_devfn(port);
 		if (err < 0) {
@@ -2296,6 +2308,24 @@ static int tegra_pcie_parse_dt(struct tegra_pcie *pcie)
 		if (IS_ERR(rp->base))
 			return PTR_ERR(rp->base);
 
+		label = kasprintf(GFP_KERNEL, "pex-reset-%u", index);
+		if (!label) {
+			dev_err(dev, "failed to create reset GPIO label\n");
+			return -ENOMEM;
+		}
+
+		rp->reset_gpiod = of_pci_get_reset_gpio(dev, port,
+							GPIOD_OUT_LOW, label);
+		kfree(label);
+		if (!rp->reset_gpiod) {
+			dev_dbg(dev, "missing optional reset-gpios prop\n");
+		} else if (IS_ERR(rp->reset_gpiod)) {
+			err = PTR_ERR(rp->reset_gpiod);
+			rp->reset_gpiod = NULL;
+			dev_err(dev, "failed to get reset GPIO: %d\n", err);
+			return err;
+		}
+
 		list_add_tail(&rp->list, &pcie->ports);
 	}
 
-- 
2.17.1

[PATCH V3 29/29] PCI: tegra: Change link retry log level to debug

[Manikanta Maddireddy]

Driver checks for link up three times before giving up, each retry attempt
is printed as an error. Letting users know that PCIe link is down and in the
process of being brought up again is for debug, not an error condition.

Signed-off-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
---
V3: Changed dev_err to dev_dbg

V2: Updated commit log

 drivers/pci/controller/pci-tegra.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index b021863303f1..1370d0015f50 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -2373,7 +2373,7 @@ static bool tegra_pcie_port_check_link(struct tegra_pcie_port *port)
 		} while (--timeout);
 
 		if (!timeout) {
-			dev_err(dev, "link %u down, retrying\n", port->index);
+			dev_dbg(dev, "link %u down, retrying\n", port->index);
 			goto retry;
 		}
 
-- 
2.17.1