Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 908 insertions, 0 deletions

diff --git a/drivers/gpu/drm/hisilicon/kirin/dw_drm_dsi.c b/drivers/gpu/drm/hisilicon/kirin/dw_drm_dsi.c
new file mode 100644
index 000000000..d9978b798
--- /dev/null
+++ b/drivers/gpu/drm/hisilicon/kirin/dw_drm_dsi.c
@@ -0,0 +1,908 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * DesignWare MIPI DSI Host Controller v1.02 driver
+ *
+ * Copyright (c) 2016 Linaro Limited.
+ * Copyright (c) 2014-2016 HiSilicon Limited.
+ *
+ * Author:
+ *	Xinliang Liu <z.liuxinliang@hisilicon.com>
+ *	Xinliang Liu <xinliang.liu@linaro.org>
+ *	Xinwei Kong <kong.kongxinwei@hisilicon.com>
+ */
+
+#include <linux/clk.h>
+#include <linux/component.h>
+#include <linux/delay.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_bridge.h>
+#include <drm/drm_device.h>
+#include <drm/drm_mipi_dsi.h>
+#include <drm/drm_of.h>
+#include <drm/drm_print.h>
+#include <drm/drm_probe_helper.h>
+#include <drm/drm_simple_kms_helper.h>
+
+#include "dw_dsi_reg.h"
+
+#define MAX_TX_ESC_CLK		10
+#define ROUND(x, y)		((x) / (y) + \
+				((x) % (y) * 10 / (y) >= 5 ? 1 : 0))
+#define PHY_REF_CLK_RATE	19200000
+#define PHY_REF_CLK_PERIOD_PS	(1000000000 / (PHY_REF_CLK_RATE / 1000))
+
+#define encoder_to_dsi(encoder) \
+	container_of(encoder, struct dw_dsi, encoder)
+#define host_to_dsi(host) \
+	container_of(host, struct dw_dsi, host)
+
+struct mipi_phy_params {
+	u32 clk_t_lpx;
+	u32 clk_t_hs_prepare;
+	u32 clk_t_hs_zero;
+	u32 clk_t_hs_trial;
+	u32 clk_t_wakeup;
+	u32 data_t_lpx;
+	u32 data_t_hs_prepare;
+	u32 data_t_hs_zero;
+	u32 data_t_hs_trial;
+	u32 data_t_ta_go;
+	u32 data_t_ta_get;
+	u32 data_t_wakeup;
+	u32 hstx_ckg_sel;
+	u32 pll_fbd_div5f;
+	u32 pll_fbd_div1f;
+	u32 pll_fbd_2p;
+	u32 pll_enbwt;
+	u32 pll_fbd_p;
+	u32 pll_fbd_s;
+	u32 pll_pre_div1p;
+	u32 pll_pre_p;
+	u32 pll_vco_750M;
+	u32 pll_lpf_rs;
+	u32 pll_lpf_cs;
+	u32 clklp2hs_time;
+	u32 clkhs2lp_time;
+	u32 lp2hs_time;
+	u32 hs2lp_time;
+	u32 clk_to_data_delay;
+	u32 data_to_clk_delay;
+	u32 lane_byte_clk_kHz;
+	u32 clk_division;
+};
+
+struct dsi_hw_ctx {
+	void __iomem *base;
+	struct clk *pclk;
+};
+
+struct dw_dsi {
+	struct drm_encoder encoder;
+	struct device *dev;
+	struct mipi_dsi_host host;
+	struct drm_display_mode cur_mode;
+	struct dsi_hw_ctx *ctx;
+	struct mipi_phy_params phy;
+
+	u32 lanes;
+	enum mipi_dsi_pixel_format format;
+	unsigned long mode_flags;
+	bool enable;
+};
+
+struct dsi_data {
+	struct dw_dsi dsi;
+	struct dsi_hw_ctx ctx;
+};
+
+struct dsi_phy_range {
+	u32 min_range_kHz;
+	u32 max_range_kHz;
+	u32 pll_vco_750M;
+	u32 hstx_ckg_sel;
+};
+
+static const struct dsi_phy_range dphy_range_info[] = {
+	{   46875,    62500,   1,    7 },
+	{   62500,    93750,   0,    7 },
+	{   93750,   125000,   1,    6 },
+	{  125000,   187500,   0,    6 },
+	{  187500,   250000,   1,    5 },
+	{  250000,   375000,   0,    5 },
+	{  375000,   500000,   1,    4 },
+	{  500000,   750000,   0,    4 },
+	{  750000,  1000000,   1,    0 },
+	{ 1000000,  1500000,   0,    0 }
+};
+
+static u32 dsi_calc_phy_rate(u32 req_kHz, struct mipi_phy_params *phy)
+{
+	u32 ref_clk_ps = PHY_REF_CLK_PERIOD_PS;
+	u32 tmp_kHz = req_kHz;
+	u32 i = 0;
+	u32 q_pll = 1;
+	u32 m_pll = 0;
+	u32 n_pll = 0;
+	u32 r_pll = 1;
+	u32 m_n = 0;
+	u32 m_n_int = 0;
+	u32 f_kHz = 0;
+	u64 temp;
+
+	/*
+	 * Find a rate >= req_kHz.
+	 */
+	do {
+		f_kHz = tmp_kHz;
+
+		for (i = 0; i < ARRAY_SIZE(dphy_range_info); i++)
+			if (f_kHz >= dphy_range_info[i].min_range_kHz &&
+			    f_kHz <= dphy_range_info[i].max_range_kHz)
+				break;
+
+		if (i == ARRAY_SIZE(dphy_range_info)) {
+			DRM_ERROR("%dkHz out of range\n", f_kHz);
+			return 0;
+		}
+
+		phy->pll_vco_750M = dphy_range_info[i].pll_vco_750M;
+		phy->hstx_ckg_sel = dphy_range_info[i].hstx_ckg_sel;
+
+		if (phy->hstx_ckg_sel <= 7 &&
+		    phy->hstx_ckg_sel >= 4)
+			q_pll = 0x10 >> (7 - phy->hstx_ckg_sel);
+
+		temp = f_kHz * (u64)q_pll * (u64)ref_clk_ps;
+		m_n_int = temp / (u64)1000000000;
+		m_n = (temp % (u64)1000000000) / (u64)100000000;
+
+		if (m_n_int % 2 == 0) {
+			if (m_n * 6 >= 50) {
+				n_pll = 2;
+				m_pll = (m_n_int + 1) * n_pll;
+			} else if (m_n * 6 >= 30) {
+				n_pll = 3;
+				m_pll = m_n_int * n_pll + 2;
+			} else {
+				n_pll = 1;
+				m_pll = m_n_int * n_pll;
+			}
+		} else {
+			if (m_n * 6 >= 50) {
+				n_pll = 1;
+				m_pll = (m_n_int + 1) * n_pll;
+			} else if (m_n * 6 >= 30) {
+				n_pll = 1;
+				m_pll = (m_n_int + 1) * n_pll;
+			} else if (m_n * 6 >= 10) {
+				n_pll = 3;
+				m_pll = m_n_int * n_pll + 1;
+			} else {
+				n_pll = 2;
+				m_pll = m_n_int * n_pll;
+			}
+		}
+
+		if (n_pll == 1) {
+			phy->pll_fbd_p = 0;
+			phy->pll_pre_div1p = 1;
+		} else {
+			phy->pll_fbd_p = n_pll;
+			phy->pll_pre_div1p = 0;
+		}
+
+		if (phy->pll_fbd_2p <= 7 && phy->pll_fbd_2p >= 4)
+			r_pll = 0x10 >> (7 - phy->pll_fbd_2p);
+
+		if (m_pll == 2) {
+			phy->pll_pre_p = 0;
+			phy->pll_fbd_s = 0;
+			phy->pll_fbd_div1f = 0;
+			phy->pll_fbd_div5f = 1;
+		} else if (m_pll >= 2 * 2 * r_pll && m_pll <= 2 * 4 * r_pll) {
+			phy->pll_pre_p = m_pll / (2 * r_pll);
+			phy->pll_fbd_s = 0;
+			phy->pll_fbd_div1f = 1;
+			phy->pll_fbd_div5f = 0;
+		} else if (m_pll >= 2 * 5 * r_pll && m_pll <= 2 * 150 * r_pll) {
+			if (((m_pll / (2 * r_pll)) % 2) == 0) {
+				phy->pll_pre_p =
+					(m_pll / (2 * r_pll)) / 2 - 1;
+				phy->pll_fbd_s =
+					(m_pll / (2 * r_pll)) % 2 + 2;
+			} else {
+				phy->pll_pre_p =
+					(m_pll / (2 * r_pll)) / 2;
+				phy->pll_fbd_s =
+					(m_pll / (2 * r_pll)) % 2;
+			}
+			phy->pll_fbd_div1f = 0;
+			phy->pll_fbd_div5f = 0;
+		} else {
+			phy->pll_pre_p = 0;
+			phy->pll_fbd_s = 0;
+			phy->pll_fbd_div1f = 0;
+			phy->pll_fbd_div5f = 1;
+		}
+
+		f_kHz = (u64)1000000000 * (u64)m_pll /
+			((u64)ref_clk_ps * (u64)n_pll * (u64)q_pll);
+
+		if (f_kHz >= req_kHz)
+			break;
+
+		tmp_kHz += 10;
+
+	} while (true);
+
+	return f_kHz;
+}
+
+static void dsi_get_phy_params(u32 phy_req_kHz,
+			       struct mipi_phy_params *phy)
+{
+	u32 ref_clk_ps = PHY_REF_CLK_PERIOD_PS;
+	u32 phy_rate_kHz;
+	u32 ui;
+
+	memset(phy, 0, sizeof(*phy));
+
+	phy_rate_kHz = dsi_calc_phy_rate(phy_req_kHz, phy);
+	if (!phy_rate_kHz)
+		return;
+
+	ui = 1000000 / phy_rate_kHz;
+
+	phy->clk_t_lpx = ROUND(50, 8 * ui);
+	phy->clk_t_hs_prepare = ROUND(133, 16 * ui) - 1;
+
+	phy->clk_t_hs_zero = ROUND(262, 8 * ui);
+	phy->clk_t_hs_trial = 2 * (ROUND(60, 8 * ui) - 1);
+	phy->clk_t_wakeup = ROUND(1000000, (ref_clk_ps / 1000) - 1);
+	if (phy->clk_t_wakeup > 0xff)
+		phy->clk_t_wakeup = 0xff;
+	phy->data_t_wakeup = phy->clk_t_wakeup;
+	phy->data_t_lpx = phy->clk_t_lpx;
+	phy->data_t_hs_prepare = ROUND(125 + 10 * ui, 16 * ui) - 1;
+	phy->data_t_hs_zero = ROUND(105 + 6 * ui, 8 * ui);
+	phy->data_t_hs_trial = 2 * (ROUND(60 + 4 * ui, 8 * ui) - 1);
+	phy->data_t_ta_go = 3;
+	phy->data_t_ta_get = 4;
+
+	phy->pll_enbwt = 1;
+	phy->clklp2hs_time = ROUND(407, 8 * ui) + 12;
+	phy->clkhs2lp_time = ROUND(105 + 12 * ui, 8 * ui);
+	phy->lp2hs_time = ROUND(240 + 12 * ui, 8 * ui) + 1;
+	phy->hs2lp_time = phy->clkhs2lp_time;
+	phy->clk_to_data_delay = 1 + phy->clklp2hs_time;
+	phy->data_to_clk_delay = ROUND(60 + 52 * ui, 8 * ui) +
+				phy->clkhs2lp_time;
+
+	phy->lane_byte_clk_kHz = phy_rate_kHz / 8;
+	phy->clk_division =
+		DIV_ROUND_UP(phy->lane_byte_clk_kHz, MAX_TX_ESC_CLK);
+}
+
+static u32 dsi_get_dpi_color_coding(enum mipi_dsi_pixel_format format)
+{
+	u32 val;
+
+	/*
+	 * TODO: only support RGB888 now, to support more
+	 */
+	switch (format) {
+	case MIPI_DSI_FMT_RGB888:
+		val = DSI_24BITS_1;
+		break;
+	default:
+		val = DSI_24BITS_1;
+		break;
+	}
+
+	return val;
+}
+
+/*
+ * dsi phy reg write function
+ */
+static void dsi_phy_tst_set(void __iomem *base, u32 reg, u32 val)
+{
+	u32 reg_write = 0x10000 + reg;
+
+	/*
+	 * latch reg first
+	 */
+	writel(reg_write, base + PHY_TST_CTRL1);
+	writel(0x02, base + PHY_TST_CTRL0);
+	writel(0x00, base + PHY_TST_CTRL0);
+
+	/*
+	 * then latch value
+	 */
+	writel(val, base + PHY_TST_CTRL1);
+	writel(0x02, base + PHY_TST_CTRL0);
+	writel(0x00, base + PHY_TST_CTRL0);
+}
+
+static void dsi_set_phy_timer(void __iomem *base,
+			      struct mipi_phy_params *phy,
+			      u32 lanes)
+{
+	u32 val;
+
+	/*
+	 * Set lane value and phy stop wait time.
+	 */
+	val = (lanes - 1) | (PHY_STOP_WAIT_TIME << 8);
+	writel(val, base + PHY_IF_CFG);
+
+	/*
+	 * Set phy clk division.
+	 */
+	val = readl(base + CLKMGR_CFG) | phy->clk_division;
+	writel(val, base + CLKMGR_CFG);
+
+	/*
+	 * Set lp and hs switching params.
+	 */
+	dw_update_bits(base + PHY_TMR_CFG, 24, MASK(8), phy->hs2lp_time);
+	dw_update_bits(base + PHY_TMR_CFG, 16, MASK(8), phy->lp2hs_time);
+	dw_update_bits(base + PHY_TMR_LPCLK_CFG, 16, MASK(10),
+		       phy->clkhs2lp_time);
+	dw_update_bits(base + PHY_TMR_LPCLK_CFG, 0, MASK(10),
+		       phy->clklp2hs_time);
+	dw_update_bits(base + CLK_DATA_TMR_CFG, 8, MASK(8),
+		       phy->data_to_clk_delay);
+	dw_update_bits(base + CLK_DATA_TMR_CFG, 0, MASK(8),
+		       phy->clk_to_data_delay);
+}
+
+static void dsi_set_mipi_phy(void __iomem *base,
+			     struct mipi_phy_params *phy,
+			     u32 lanes)
+{
+	u32 delay_count;
+	u32 val;
+	u32 i;
+
+	/* phy timer setting */
+	dsi_set_phy_timer(base, phy, lanes);
+
+	/*
+	 * Reset to clean up phy tst params.
+	 */
+	writel(0, base + PHY_RSTZ);
+	writel(0, base + PHY_TST_CTRL0);
+	writel(1, base + PHY_TST_CTRL0);
+	writel(0, base + PHY_TST_CTRL0);
+
+	/*
+	 * Clock lane timing control setting: TLPX, THS-PREPARE,
+	 * THS-ZERO, THS-TRAIL, TWAKEUP.
+	 */
+	dsi_phy_tst_set(base, CLK_TLPX, phy->clk_t_lpx);
+	dsi_phy_tst_set(base, CLK_THS_PREPARE, phy->clk_t_hs_prepare);
+	dsi_phy_tst_set(base, CLK_THS_ZERO, phy->clk_t_hs_zero);
+	dsi_phy_tst_set(base, CLK_THS_TRAIL, phy->clk_t_hs_trial);
+	dsi_phy_tst_set(base, CLK_TWAKEUP, phy->clk_t_wakeup);
+
+	/*
+	 * Data lane timing control setting: TLPX, THS-PREPARE,
+	 * THS-ZERO, THS-TRAIL, TTA-GO, TTA-GET, TWAKEUP.
+	 */
+	for (i = 0; i < lanes; i++) {
+		dsi_phy_tst_set(base, DATA_TLPX(i), phy->data_t_lpx);
+		dsi_phy_tst_set(base, DATA_THS_PREPARE(i),
+				phy->data_t_hs_prepare);
+		dsi_phy_tst_set(base, DATA_THS_ZERO(i), phy->data_t_hs_zero);
+		dsi_phy_tst_set(base, DATA_THS_TRAIL(i), phy->data_t_hs_trial);
+		dsi_phy_tst_set(base, DATA_TTA_GO(i), phy->data_t_ta_go);
+		dsi_phy_tst_set(base, DATA_TTA_GET(i), phy->data_t_ta_get);
+		dsi_phy_tst_set(base, DATA_TWAKEUP(i), phy->data_t_wakeup);
+	}
+
+	/*
+	 * physical configuration: I, pll I, pll II, pll III,
+	 * pll IV, pll V.
+	 */
+	dsi_phy_tst_set(base, PHY_CFG_I, phy->hstx_ckg_sel);
+	val = (phy->pll_fbd_div5f << 5) + (phy->pll_fbd_div1f << 4) +
+				(phy->pll_fbd_2p << 1) + phy->pll_enbwt;
+	dsi_phy_tst_set(base, PHY_CFG_PLL_I, val);
+	dsi_phy_tst_set(base, PHY_CFG_PLL_II, phy->pll_fbd_p);
+	dsi_phy_tst_set(base, PHY_CFG_PLL_III, phy->pll_fbd_s);
+	val = (phy->pll_pre_div1p << 7) + phy->pll_pre_p;
+	dsi_phy_tst_set(base, PHY_CFG_PLL_IV, val);
+	val = (5 << 5) + (phy->pll_vco_750M << 4) + (phy->pll_lpf_rs << 2) +
+		phy->pll_lpf_cs;
+	dsi_phy_tst_set(base, PHY_CFG_PLL_V, val);
+
+	writel(PHY_ENABLECLK, base + PHY_RSTZ);
+	udelay(1);
+	writel(PHY_ENABLECLK | PHY_UNSHUTDOWNZ, base + PHY_RSTZ);
+	udelay(1);
+	writel(PHY_ENABLECLK | PHY_UNRSTZ | PHY_UNSHUTDOWNZ, base + PHY_RSTZ);
+	usleep_range(1000, 1500);
+
+	/*
+	 * wait for phy's clock ready
+	 */
+	delay_count = 100;
+	while (delay_count) {
+		val = readl(base +  PHY_STATUS);
+		if ((BIT(0) | BIT(2)) & val)
+			break;
+
+		udelay(1);
+		delay_count--;
+	}
+
+	if (!delay_count)
+		DRM_INFO("phylock and phystopstateclklane is not ready.\n");
+}
+
+static void dsi_set_mode_timing(void __iomem *base,
+				u32 lane_byte_clk_kHz,
+				struct drm_display_mode *mode,
+				enum mipi_dsi_pixel_format format)
+{
+	u32 hfp, hbp, hsw, vfp, vbp, vsw;
+	u32 hline_time;
+	u32 hsa_time;
+	u32 hbp_time;
+	u32 pixel_clk_kHz;
+	int htot, vtot;
+	u32 val;
+	u64 tmp;
+
+	val = dsi_get_dpi_color_coding(format);
+	writel(val, base + DPI_COLOR_CODING);
+
+	val = (mode->flags & DRM_MODE_FLAG_NHSYNC ? 1 : 0) << 2;
+	val |= (mode->flags & DRM_MODE_FLAG_NVSYNC ? 1 : 0) << 1;
+	writel(val, base +  DPI_CFG_POL);
+
+	/*
+	 * The DSI IP accepts vertical timing using lines as normal,
+	 * but horizontal timing is a mixture of pixel-clocks for the
+	 * active region and byte-lane clocks for the blanking-related
+	 * timings.  hfp is specified as the total hline_time in byte-
+	 * lane clocks minus hsa, hbp and active.
+	 */
+	pixel_clk_kHz = mode->clock;
+	htot = mode->htotal;
+	vtot = mode->vtotal;
+	hfp = mode->hsync_start - mode->hdisplay;
+	hbp = mode->htotal - mode->hsync_end;
+	hsw = mode->hsync_end - mode->hsync_start;
+	vfp = mode->vsync_start - mode->vdisplay;
+	vbp = mode->vtotal - mode->vsync_end;
+	vsw = mode->vsync_end - mode->vsync_start;
+	if (vsw > 15) {
+		DRM_DEBUG_DRIVER("vsw exceeded 15\n");
+		vsw = 15;
+	}
+
+	hsa_time = (hsw * lane_byte_clk_kHz) / pixel_clk_kHz;
+	hbp_time = (hbp * lane_byte_clk_kHz) / pixel_clk_kHz;
+	tmp = (u64)htot * (u64)lane_byte_clk_kHz;
+	hline_time = DIV_ROUND_UP(tmp, pixel_clk_kHz);
+
+	/* all specified in byte-lane clocks */
+	writel(hsa_time, base + VID_HSA_TIME);
+	writel(hbp_time, base + VID_HBP_TIME);
+	writel(hline_time, base + VID_HLINE_TIME);
+
+	writel(vsw, base + VID_VSA_LINES);
+	writel(vbp, base + VID_VBP_LINES);
+	writel(vfp, base + VID_VFP_LINES);
+	writel(mode->vdisplay, base + VID_VACTIVE_LINES);
+	writel(mode->hdisplay, base + VID_PKT_SIZE);
+
+	DRM_DEBUG_DRIVER("htot=%d, hfp=%d, hbp=%d, hsw=%d\n",
+			 htot, hfp, hbp, hsw);
+	DRM_DEBUG_DRIVER("vtol=%d, vfp=%d, vbp=%d, vsw=%d\n",
+			 vtot, vfp, vbp, vsw);
+	DRM_DEBUG_DRIVER("hsa_time=%d, hbp_time=%d, hline_time=%d\n",
+			 hsa_time, hbp_time, hline_time);
+}
+
+static void dsi_set_video_mode(void __iomem *base, unsigned long flags)
+{
+	u32 val;
+	u32 mode_mask = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_BURST |
+		MIPI_DSI_MODE_VIDEO_SYNC_PULSE;
+	u32 non_burst_sync_pulse = MIPI_DSI_MODE_VIDEO |
+		MIPI_DSI_MODE_VIDEO_SYNC_PULSE;
+	u32 non_burst_sync_event = MIPI_DSI_MODE_VIDEO;
+
+	/*
+	 * choose video mode type
+	 */
+	if ((flags & mode_mask) == non_burst_sync_pulse)
+		val = DSI_NON_BURST_SYNC_PULSES;
+	else if ((flags & mode_mask) == non_burst_sync_event)
+		val = DSI_NON_BURST_SYNC_EVENTS;
+	else
+		val = DSI_BURST_SYNC_PULSES_1;
+	writel(val, base + VID_MODE_CFG);
+
+	writel(PHY_TXREQUESTCLKHS, base + LPCLK_CTRL);
+	writel(DSI_VIDEO_MODE, base + MODE_CFG);
+}
+
+static void dsi_mipi_init(struct dw_dsi *dsi)
+{
+	struct dsi_hw_ctx *ctx = dsi->ctx;
+	struct mipi_phy_params *phy = &dsi->phy;
+	struct drm_display_mode *mode = &dsi->cur_mode;
+	u32 bpp = mipi_dsi_pixel_format_to_bpp(dsi->format);
+	void __iomem *base = ctx->base;
+	u32 dphy_req_kHz;
+
+	/*
+	 * count phy params
+	 */
+	dphy_req_kHz = mode->clock * bpp / dsi->lanes;
+	dsi_get_phy_params(dphy_req_kHz, phy);
+
+	/* reset Core */
+	writel(RESET, base + PWR_UP);
+
+	/* set dsi phy params */
+	dsi_set_mipi_phy(base, phy, dsi->lanes);
+
+	/* set dsi mode timing */
+	dsi_set_mode_timing(base, phy->lane_byte_clk_kHz, mode, dsi->format);
+
+	/* set dsi video mode */
+	dsi_set_video_mode(base, dsi->mode_flags);
+
+	/* dsi wake up */
+	writel(POWERUP, base + PWR_UP);
+
+	DRM_DEBUG_DRIVER("lanes=%d, pixel_clk=%d kHz, bytes_freq=%d kHz\n",
+			 dsi->lanes, mode->clock, phy->lane_byte_clk_kHz);
+}
+
+static void dsi_encoder_disable(struct drm_encoder *encoder)
+{
+	struct dw_dsi *dsi = encoder_to_dsi(encoder);
+	struct dsi_hw_ctx *ctx = dsi->ctx;
+	void __iomem *base = ctx->base;
+
+	if (!dsi->enable)
+		return;
+
+	writel(0, base + PWR_UP);
+	writel(0, base + LPCLK_CTRL);
+	writel(0, base + PHY_RSTZ);
+	clk_disable_unprepare(ctx->pclk);
+
+	dsi->enable = false;
+}
+
+static void dsi_encoder_enable(struct drm_encoder *encoder)
+{
+	struct dw_dsi *dsi = encoder_to_dsi(encoder);
+	struct dsi_hw_ctx *ctx = dsi->ctx;
+	int ret;
+
+	if (dsi->enable)
+		return;
+
+	ret = clk_prepare_enable(ctx->pclk);
+	if (ret) {
+		DRM_ERROR("fail to enable pclk: %d\n", ret);
+		return;
+	}
+
+	dsi_mipi_init(dsi);
+
+	dsi->enable = true;
+}
+
+static enum drm_mode_status dsi_encoder_phy_mode_valid(
+					struct drm_encoder *encoder,
+					const struct drm_display_mode *mode)
+{
+	struct dw_dsi *dsi = encoder_to_dsi(encoder);
+	struct mipi_phy_params phy;
+	u32 bpp = mipi_dsi_pixel_format_to_bpp(dsi->format);
+	u32 req_kHz, act_kHz, lane_byte_clk_kHz;
+
+	/* Calculate the lane byte clk using the adjusted mode clk */
+	memset(&phy, 0, sizeof(phy));
+	req_kHz = mode->clock * bpp / dsi->lanes;
+	act_kHz = dsi_calc_phy_rate(req_kHz, &phy);
+	lane_byte_clk_kHz = act_kHz / 8;
+
+	DRM_DEBUG_DRIVER("Checking mode %ix%i-%i@%i clock: %i...",
+			mode->hdisplay, mode->vdisplay, bpp,
+			drm_mode_vrefresh(mode), mode->clock);
+
+	/*
+	 * Make sure the adjusted mode clock and the lane byte clk
+	 * have a common denominator base frequency
+	 */
+	if (mode->clock/dsi->lanes == lane_byte_clk_kHz/3) {
+		DRM_DEBUG_DRIVER("OK!\n");
+		return MODE_OK;
+	}
+
+	DRM_DEBUG_DRIVER("BAD!\n");
+	return MODE_BAD;
+}
+
+static enum drm_mode_status dsi_encoder_mode_valid(struct drm_encoder *encoder,
+					const struct drm_display_mode *mode)
+
+{
+	const struct drm_crtc_helper_funcs *crtc_funcs = NULL;
+	struct drm_crtc *crtc = NULL;
+	struct drm_display_mode adj_mode;
+	enum drm_mode_status ret;
+
+	/*
+	 * The crtc might adjust the mode, so go through the
+	 * possible crtcs (technically just one) and call
+	 * mode_fixup to figure out the adjusted mode before we
+	 * validate it.
+	 */
+	drm_for_each_crtc(crtc, encoder->dev) {
+		/*
+		 * reset adj_mode to the mode value each time,
+		 * so we don't adjust the mode twice
+		 */
+		drm_mode_init(&adj_mode, mode);
+
+		crtc_funcs = crtc->helper_private;
+		if (crtc_funcs && crtc_funcs->mode_fixup)
+			if (!crtc_funcs->mode_fixup(crtc, mode, &adj_mode))
+				return MODE_BAD;
+
+		ret = dsi_encoder_phy_mode_valid(encoder, &adj_mode);
+		if (ret != MODE_OK)
+			return ret;
+	}
+	return MODE_OK;
+}
+
+static void dsi_encoder_mode_set(struct drm_encoder *encoder,
+				 struct drm_display_mode *mode,
+				 struct drm_display_mode *adj_mode)
+{
+	struct dw_dsi *dsi = encoder_to_dsi(encoder);
+
+	drm_mode_copy(&dsi->cur_mode, adj_mode);
+}
+
+static int dsi_encoder_atomic_check(struct drm_encoder *encoder,
+				    struct drm_crtc_state *crtc_state,
+				    struct drm_connector_state *conn_state)
+{
+	/* do nothing */
+	return 0;
+}
+
+static const struct drm_encoder_helper_funcs dw_encoder_helper_funcs = {
+	.atomic_check	= dsi_encoder_atomic_check,
+	.mode_valid	= dsi_encoder_mode_valid,
+	.mode_set	= dsi_encoder_mode_set,
+	.enable		= dsi_encoder_enable,
+	.disable	= dsi_encoder_disable
+};
+
+static int dw_drm_encoder_init(struct device *dev,
+			       struct drm_device *drm_dev,
+			       struct drm_encoder *encoder)
+{
+	int ret;
+	u32 crtc_mask = drm_of_find_possible_crtcs(drm_dev, dev->of_node);
+
+	if (!crtc_mask) {
+		DRM_ERROR("failed to find crtc mask\n");
+		return -EINVAL;
+	}
+
+	encoder->possible_crtcs = crtc_mask;
+	ret = drm_simple_encoder_init(drm_dev, encoder, DRM_MODE_ENCODER_DSI);
+	if (ret) {
+		DRM_ERROR("failed to init dsi encoder\n");
+		return ret;
+	}
+
+	drm_encoder_helper_add(encoder, &dw_encoder_helper_funcs);
+
+	return 0;
+}
+
+static const struct component_ops dsi_ops;
+static int dsi_host_attach(struct mipi_dsi_host *host,
+			   struct mipi_dsi_device *mdsi)
+{
+	struct dw_dsi *dsi = host_to_dsi(host);
+	struct device *dev = host->dev;
+	int ret;
+
+	if (mdsi->lanes < 1 || mdsi->lanes > 4) {
+		DRM_ERROR("dsi device params invalid\n");
+		return -EINVAL;
+	}
+
+	dsi->lanes = mdsi->lanes;
+	dsi->format = mdsi->format;
+	dsi->mode_flags = mdsi->mode_flags;
+
+	ret = component_add(dev, &dsi_ops);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int dsi_host_detach(struct mipi_dsi_host *host,
+			   struct mipi_dsi_device *mdsi)
+{
+	struct device *dev = host->dev;
+
+	component_del(dev, &dsi_ops);
+
+	return 0;
+}
+
+static const struct mipi_dsi_host_ops dsi_host_ops = {
+	.attach = dsi_host_attach,
+	.detach = dsi_host_detach,
+};
+
+static int dsi_host_init(struct device *dev, struct dw_dsi *dsi)
+{
+	struct mipi_dsi_host *host = &dsi->host;
+	int ret;
+
+	host->dev = dev;
+	host->ops = &dsi_host_ops;
+	ret = mipi_dsi_host_register(host);
+	if (ret) {
+		DRM_ERROR("failed to register dsi host\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int dsi_bridge_init(struct drm_device *dev, struct dw_dsi *dsi)
+{
+	struct drm_encoder *encoder = &dsi->encoder;
+	struct drm_bridge *bridge;
+	struct device_node *np = dsi->dev->of_node;
+	int ret;
+
+	/*
+	 * Get the endpoint node. In our case, dsi has one output port1
+	 * to which the external HDMI bridge is connected.
+	 */
+	ret = drm_of_find_panel_or_bridge(np, 1, 0, NULL, &bridge);
+	if (ret)
+		return ret;
+
+	/* associate the bridge to dsi encoder */
+	return drm_bridge_attach(encoder, bridge, NULL, 0);
+}
+
+static int dsi_bind(struct device *dev, struct device *master, void *data)
+{
+	struct dsi_data *ddata = dev_get_drvdata(dev);
+	struct dw_dsi *dsi = &ddata->dsi;
+	struct drm_device *drm_dev = data;
+	int ret;
+
+	ret = dw_drm_encoder_init(dev, drm_dev, &dsi->encoder);
+	if (ret)
+		return ret;
+
+	ret = dsi_bridge_init(drm_dev, dsi);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static void dsi_unbind(struct device *dev, struct device *master, void *data)
+{
+	/* do nothing */
+}
+
+static const struct component_ops dsi_ops = {
+	.bind	= dsi_bind,
+	.unbind	= dsi_unbind,
+};
+
+static int dsi_parse_dt(struct platform_device *pdev, struct dw_dsi *dsi)
+{
+	struct dsi_hw_ctx *ctx = dsi->ctx;
+	struct resource *res;
+
+	ctx->pclk = devm_clk_get(&pdev->dev, "pclk");
+	if (IS_ERR(ctx->pclk)) {
+		DRM_ERROR("failed to get pclk clock\n");
+		return PTR_ERR(ctx->pclk);
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	ctx->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(ctx->base)) {
+		DRM_ERROR("failed to remap dsi io region\n");
+		return PTR_ERR(ctx->base);
+	}
+
+	return 0;
+}
+
+static int dsi_probe(struct platform_device *pdev)
+{
+	struct dsi_data *data;
+	struct dw_dsi *dsi;
+	struct dsi_hw_ctx *ctx;
+	int ret;
+
+	data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL);
+	if (!data) {
+		DRM_ERROR("failed to allocate dsi data.\n");
+		return -ENOMEM;
+	}
+	dsi = &data->dsi;
+	ctx = &data->ctx;
+	dsi->ctx = ctx;
+	dsi->dev = &pdev->dev;
+
+	ret = dsi_parse_dt(pdev, dsi);
+	if (ret)
+		return ret;
+
+	platform_set_drvdata(pdev, data);
+
+	ret = dsi_host_init(&pdev->dev, dsi);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int dsi_remove(struct platform_device *pdev)
+{
+	struct dsi_data *data = platform_get_drvdata(pdev);
+	struct dw_dsi *dsi = &data->dsi;
+
+	mipi_dsi_host_unregister(&dsi->host);
+
+	return 0;
+}
+
+static const struct of_device_id dsi_of_match[] = {
+	{.compatible = "hisilicon,hi6220-dsi"},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, dsi_of_match);
+
+static struct platform_driver dsi_driver = {
+	.probe = dsi_probe,
+	.remove = dsi_remove,
+	.driver = {
+		.name = "dw-dsi",
+		.of_match_table = dsi_of_match,
+	},
+};
+
+module_platform_driver(dsi_driver);
+
+MODULE_AUTHOR("Xinliang Liu <xinliang.liu@linaro.org>");
+MODULE_AUTHOR("Xinliang Liu <z.liuxinliang@hisilicon.com>");
+MODULE_AUTHOR("Xinwei Kong <kong.kongxinwei@hisilicon.com>");
+MODULE_DESCRIPTION("DesignWare MIPI DSI Host Controller v1.02 driver");
+MODULE_LICENSE("GPL v2");