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, 409 insertions, 0 deletions

diff --git a/drivers/media/platform/mediatek/jpeg/mtk_jpeg_enc_hw.c b/drivers/media/platform/mediatek/jpeg/mtk_jpeg_enc_hw.c
new file mode 100644
index 000000000..1bbb712d7
--- /dev/null
+++ b/drivers/media/platform/mediatek/jpeg/mtk_jpeg_enc_hw.c
@@ -0,0 +1,409 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2019 MediaTek Inc.
+ * Author: Xia Jiang <xia.jiang@mediatek.com>
+ *
+ */
+
+#include <linux/clk.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/slab.h>
+#include <media/media-device.h>
+#include <media/videobuf2-core.h>
+#include <media/videobuf2-dma-contig.h>
+#include <media/videobuf2-v4l2.h>
+#include <media/v4l2-mem2mem.h>
+#include <media/v4l2-dev.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-fh.h>
+#include <media/v4l2-event.h>
+
+#include "mtk_jpeg_core.h"
+#include "mtk_jpeg_enc_hw.h"
+
+static const struct mtk_jpeg_enc_qlt mtk_jpeg_enc_quality[] = {
+	{.quality_param = 34, .hardware_value = JPEG_ENC_QUALITY_Q34},
+	{.quality_param = 39, .hardware_value = JPEG_ENC_QUALITY_Q39},
+	{.quality_param = 48, .hardware_value = JPEG_ENC_QUALITY_Q48},
+	{.quality_param = 60, .hardware_value = JPEG_ENC_QUALITY_Q60},
+	{.quality_param = 64, .hardware_value = JPEG_ENC_QUALITY_Q64},
+	{.quality_param = 68, .hardware_value = JPEG_ENC_QUALITY_Q68},
+	{.quality_param = 74, .hardware_value = JPEG_ENC_QUALITY_Q74},
+	{.quality_param = 80, .hardware_value = JPEG_ENC_QUALITY_Q80},
+	{.quality_param = 82, .hardware_value = JPEG_ENC_QUALITY_Q82},
+	{.quality_param = 84, .hardware_value = JPEG_ENC_QUALITY_Q84},
+	{.quality_param = 87, .hardware_value = JPEG_ENC_QUALITY_Q87},
+	{.quality_param = 90, .hardware_value = JPEG_ENC_QUALITY_Q90},
+	{.quality_param = 92, .hardware_value = JPEG_ENC_QUALITY_Q92},
+	{.quality_param = 95, .hardware_value = JPEG_ENC_QUALITY_Q95},
+	{.quality_param = 97, .hardware_value = JPEG_ENC_QUALITY_Q97},
+};
+
+#if defined(CONFIG_OF)
+static const struct of_device_id mtk_jpegenc_drv_ids[] = {
+	{
+		.compatible = "mediatek,mt8195-jpgenc-hw",
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, mtk_jpegenc_drv_ids);
+#endif
+
+void mtk_jpeg_enc_reset(void __iomem *base)
+{
+	writel(0, base + JPEG_ENC_RSTB);
+	writel(JPEG_ENC_RESET_BIT, base + JPEG_ENC_RSTB);
+	writel(0, base + JPEG_ENC_CODEC_SEL);
+}
+EXPORT_SYMBOL_GPL(mtk_jpeg_enc_reset);
+
+u32 mtk_jpeg_enc_get_file_size(void __iomem *base)
+{
+	return readl(base + JPEG_ENC_DMA_ADDR0) -
+	       readl(base + JPEG_ENC_DST_ADDR0);
+}
+EXPORT_SYMBOL_GPL(mtk_jpeg_enc_get_file_size);
+
+void mtk_jpeg_enc_start(void __iomem *base)
+{
+	u32 value;
+
+	value = readl(base + JPEG_ENC_CTRL);
+	value |= JPEG_ENC_CTRL_INT_EN_BIT | JPEG_ENC_CTRL_ENABLE_BIT;
+	writel(value, base + JPEG_ENC_CTRL);
+}
+EXPORT_SYMBOL_GPL(mtk_jpeg_enc_start);
+
+void mtk_jpeg_set_enc_src(struct mtk_jpeg_ctx *ctx,  void __iomem *base,
+			  struct vb2_buffer *src_buf)
+{
+	int i;
+	dma_addr_t dma_addr;
+
+	for (i = 0; i < src_buf->num_planes; i++) {
+		dma_addr = vb2_dma_contig_plane_dma_addr(src_buf, i) +
+			   src_buf->planes[i].data_offset;
+		if (!i)
+			writel(dma_addr, base + JPEG_ENC_SRC_LUMA_ADDR);
+		else
+			writel(dma_addr, base + JPEG_ENC_SRC_CHROMA_ADDR);
+	}
+}
+EXPORT_SYMBOL_GPL(mtk_jpeg_set_enc_src);
+
+void mtk_jpeg_set_enc_dst(struct mtk_jpeg_ctx *ctx, void __iomem *base,
+			  struct vb2_buffer *dst_buf)
+{
+	dma_addr_t dma_addr;
+	size_t size;
+	u32 dma_addr_offset;
+	u32 dma_addr_offsetmask;
+
+	dma_addr = vb2_dma_contig_plane_dma_addr(dst_buf, 0);
+	dma_addr_offset = ctx->enable_exif ? MTK_JPEG_MAX_EXIF_SIZE : 0;
+	dma_addr_offsetmask = dma_addr & JPEG_ENC_DST_ADDR_OFFSET_MASK;
+	size = vb2_plane_size(dst_buf, 0);
+
+	writel(dma_addr_offset & ~0xf, base + JPEG_ENC_OFFSET_ADDR);
+	writel(dma_addr_offsetmask & 0xf, base + JPEG_ENC_BYTE_OFFSET_MASK);
+	writel(dma_addr & ~0xf, base + JPEG_ENC_DST_ADDR0);
+	writel((dma_addr + size) & ~0xf, base + JPEG_ENC_STALL_ADDR0);
+}
+EXPORT_SYMBOL_GPL(mtk_jpeg_set_enc_dst);
+
+void mtk_jpeg_set_enc_params(struct mtk_jpeg_ctx *ctx,  void __iomem *base)
+{
+	u32 value;
+	u32 width = ctx->out_q.enc_crop_rect.width;
+	u32 height = ctx->out_q.enc_crop_rect.height;
+	u32 enc_format = ctx->out_q.fmt->fourcc;
+	u32 bytesperline = ctx->out_q.pix_mp.plane_fmt[0].bytesperline;
+	u32 blk_num;
+	u32 img_stride;
+	u32 mem_stride;
+	u32 i, enc_quality;
+
+	value = width << 16 | height;
+	writel(value, base + JPEG_ENC_IMG_SIZE);
+
+	if (enc_format == V4L2_PIX_FMT_NV12M ||
+	    enc_format == V4L2_PIX_FMT_NV21M)
+	    /*
+	     * Total 8 x 8 block number of luma and chroma.
+	     * The number of blocks is counted from 0.
+	     */
+		blk_num = DIV_ROUND_UP(width, 16) *
+			  DIV_ROUND_UP(height, 16) * 6 - 1;
+	else
+		blk_num = DIV_ROUND_UP(width, 16) *
+			  DIV_ROUND_UP(height, 8) * 4 - 1;
+	writel(blk_num, base + JPEG_ENC_BLK_NUM);
+
+	if (enc_format == V4L2_PIX_FMT_NV12M ||
+	    enc_format == V4L2_PIX_FMT_NV21M) {
+		/* 4:2:0 */
+		img_stride = round_up(width, 16);
+		mem_stride = bytesperline;
+	} else {
+		/* 4:2:2 */
+		img_stride = round_up(width * 2, 32);
+		mem_stride = img_stride;
+	}
+	writel(img_stride, base + JPEG_ENC_IMG_STRIDE);
+	writel(mem_stride, base + JPEG_ENC_STRIDE);
+
+	enc_quality = mtk_jpeg_enc_quality[0].hardware_value;
+	for (i = 0; i < ARRAY_SIZE(mtk_jpeg_enc_quality); i++) {
+		if (ctx->enc_quality <= mtk_jpeg_enc_quality[i].quality_param) {
+			enc_quality = mtk_jpeg_enc_quality[i].hardware_value;
+			break;
+		}
+	}
+	writel(enc_quality, base + JPEG_ENC_QUALITY);
+
+	value = readl(base + JPEG_ENC_CTRL);
+	value &= ~JPEG_ENC_CTRL_YUV_FORMAT_MASK;
+	value |= (ctx->out_q.fmt->hw_format & 3) << 3;
+	if (ctx->enable_exif)
+		value |= JPEG_ENC_CTRL_FILE_FORMAT_BIT;
+	else
+		value &= ~JPEG_ENC_CTRL_FILE_FORMAT_BIT;
+	if (ctx->restart_interval)
+		value |= JPEG_ENC_CTRL_RESTART_EN_BIT;
+	else
+		value &= ~JPEG_ENC_CTRL_RESTART_EN_BIT;
+	writel(value, base + JPEG_ENC_CTRL);
+
+	writel(ctx->restart_interval, base + JPEG_ENC_RST_MCU_NUM);
+}
+EXPORT_SYMBOL_GPL(mtk_jpeg_set_enc_params);
+
+static void mtk_jpegenc_put_buf(struct mtk_jpegenc_comp_dev *jpeg)
+{
+	struct mtk_jpeg_ctx *ctx;
+	struct vb2_v4l2_buffer *dst_buffer;
+	struct list_head *temp_entry;
+	struct list_head *pos = NULL;
+	struct mtk_jpeg_src_buf *dst_done_buf, *tmp_dst_done_buf;
+	unsigned long flags;
+
+	ctx = jpeg->hw_param.curr_ctx;
+	if (!ctx) {
+		dev_err(jpeg->dev, "comp_jpeg ctx fail !!!\n");
+		return;
+	}
+
+	dst_buffer = jpeg->hw_param.dst_buffer;
+	if (!dst_buffer) {
+		dev_err(jpeg->dev, "comp_jpeg dst_buffer fail !!!\n");
+		return;
+	}
+
+	dst_done_buf = container_of(dst_buffer,
+				    struct mtk_jpeg_src_buf, b);
+
+	spin_lock_irqsave(&ctx->done_queue_lock, flags);
+	list_add_tail(&dst_done_buf->list, &ctx->dst_done_queue);
+	while (!list_empty(&ctx->dst_done_queue) &&
+	       (pos != &ctx->dst_done_queue)) {
+		list_for_each_prev_safe(pos, temp_entry, &ctx->dst_done_queue) {
+			tmp_dst_done_buf = list_entry(pos,
+						      struct mtk_jpeg_src_buf,
+						      list);
+			if (tmp_dst_done_buf->frame_num ==
+				ctx->last_done_frame_num) {
+				list_del(&tmp_dst_done_buf->list);
+				v4l2_m2m_buf_done(&tmp_dst_done_buf->b,
+						  VB2_BUF_STATE_DONE);
+				ctx->last_done_frame_num++;
+			}
+		}
+	}
+	spin_unlock_irqrestore(&ctx->done_queue_lock, flags);
+}
+
+static void mtk_jpegenc_timeout_work(struct work_struct *work)
+{
+	struct delayed_work *dly_work = to_delayed_work(work);
+	struct mtk_jpegenc_comp_dev *cjpeg =
+		container_of(dly_work,
+			     struct mtk_jpegenc_comp_dev,
+			     job_timeout_work);
+	struct mtk_jpeg_dev *master_jpeg = cjpeg->master_dev;
+	enum vb2_buffer_state buf_state = VB2_BUF_STATE_ERROR;
+	struct vb2_v4l2_buffer *src_buf, *dst_buf;
+
+	src_buf = cjpeg->hw_param.src_buffer;
+	dst_buf = cjpeg->hw_param.dst_buffer;
+	v4l2_m2m_buf_copy_metadata(src_buf, dst_buf, true);
+
+	mtk_jpeg_enc_reset(cjpeg->reg_base);
+	clk_disable_unprepare(cjpeg->venc_clk.clks->clk);
+	pm_runtime_put(cjpeg->dev);
+	cjpeg->hw_state = MTK_JPEG_HW_IDLE;
+	atomic_inc(&master_jpeg->enchw_rdy);
+	wake_up(&master_jpeg->enc_hw_wq);
+	v4l2_m2m_buf_done(src_buf, buf_state);
+	mtk_jpegenc_put_buf(cjpeg);
+}
+
+static irqreturn_t mtk_jpegenc_hw_irq_handler(int irq, void *priv)
+{
+	struct vb2_v4l2_buffer *src_buf, *dst_buf;
+	enum vb2_buffer_state buf_state;
+	struct mtk_jpeg_ctx *ctx;
+	u32 result_size;
+	u32 irq_status;
+
+	struct mtk_jpegenc_comp_dev *jpeg = priv;
+	struct mtk_jpeg_dev *master_jpeg = jpeg->master_dev;
+
+	cancel_delayed_work(&jpeg->job_timeout_work);
+
+	ctx = jpeg->hw_param.curr_ctx;
+	src_buf = jpeg->hw_param.src_buffer;
+	dst_buf = jpeg->hw_param.dst_buffer;
+	v4l2_m2m_buf_copy_metadata(src_buf, dst_buf, true);
+
+	irq_status = readl(jpeg->reg_base + JPEG_ENC_INT_STS) &
+		JPEG_ENC_INT_STATUS_MASK_ALLIRQ;
+	if (irq_status)
+		writel(0, jpeg->reg_base + JPEG_ENC_INT_STS);
+	if (!(irq_status & JPEG_ENC_INT_STATUS_DONE))
+		dev_warn(jpeg->dev, "Jpg Enc occurs unknown Err.");
+
+	result_size = mtk_jpeg_enc_get_file_size(jpeg->reg_base);
+	vb2_set_plane_payload(&dst_buf->vb2_buf, 0, result_size);
+	buf_state = VB2_BUF_STATE_DONE;
+	v4l2_m2m_buf_done(src_buf, buf_state);
+	mtk_jpegenc_put_buf(jpeg);
+	pm_runtime_put(ctx->jpeg->dev);
+	clk_disable_unprepare(jpeg->venc_clk.clks->clk);
+	if (!list_empty(&ctx->fh.m2m_ctx->out_q_ctx.rdy_queue) ||
+	    !list_empty(&ctx->fh.m2m_ctx->cap_q_ctx.rdy_queue)) {
+		queue_work(master_jpeg->workqueue, &ctx->jpeg_work);
+	}
+
+	jpeg->hw_state = MTK_JPEG_HW_IDLE;
+	wake_up(&master_jpeg->enc_hw_wq);
+	atomic_inc(&master_jpeg->enchw_rdy);
+
+	return IRQ_HANDLED;
+}
+
+static int mtk_jpegenc_hw_init_irq(struct mtk_jpegenc_comp_dev *dev)
+{
+	struct platform_device *pdev = dev->plat_dev;
+	int ret;
+
+	dev->jpegenc_irq = platform_get_irq(pdev, 0);
+	if (dev->jpegenc_irq < 0)
+		return dev->jpegenc_irq;
+
+	ret = devm_request_irq(&pdev->dev,
+			       dev->jpegenc_irq,
+			       mtk_jpegenc_hw_irq_handler,
+			       0,
+			       pdev->name, dev);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to devm_request_irq %d (%d)",
+			dev->jpegenc_irq, ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int mtk_jpegenc_hw_probe(struct platform_device *pdev)
+{
+	struct mtk_jpegenc_clk *jpegenc_clk;
+	struct mtk_jpeg_dev *master_dev;
+	struct mtk_jpegenc_comp_dev *dev;
+	int ret, i;
+
+	struct device *decs = &pdev->dev;
+
+	if (!decs->parent)
+		return -EPROBE_DEFER;
+
+	master_dev = dev_get_drvdata(decs->parent);
+	if (!master_dev)
+		return -EPROBE_DEFER;
+
+	dev = devm_kzalloc(&pdev->dev, sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return -ENOMEM;
+
+	dev->plat_dev = pdev;
+	dev->dev = &pdev->dev;
+
+	if (!master_dev->is_jpgenc_multihw) {
+		master_dev->is_jpgenc_multihw = true;
+		for (i = 0; i < MTK_JPEGENC_HW_MAX; i++)
+			master_dev->enc_hw_dev[i] = NULL;
+
+		init_waitqueue_head(&master_dev->enc_hw_wq);
+		master_dev->workqueue = alloc_ordered_workqueue(MTK_JPEG_NAME,
+								WQ_MEM_RECLAIM
+								| WQ_FREEZABLE);
+		if (!master_dev->workqueue)
+			return -EINVAL;
+	}
+
+	atomic_set(&master_dev->enchw_rdy, MTK_JPEGENC_HW_MAX);
+	spin_lock_init(&dev->hw_lock);
+	dev->hw_state = MTK_JPEG_HW_IDLE;
+
+	INIT_DELAYED_WORK(&dev->job_timeout_work,
+			  mtk_jpegenc_timeout_work);
+
+	jpegenc_clk = &dev->venc_clk;
+
+	jpegenc_clk->clk_num = devm_clk_bulk_get_all(&pdev->dev,
+						     &jpegenc_clk->clks);
+	if (jpegenc_clk->clk_num < 0)
+		return dev_err_probe(&pdev->dev, jpegenc_clk->clk_num,
+				     "Failed to get jpegenc clock count\n");
+
+	dev->reg_base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(dev->reg_base))
+		return PTR_ERR(dev->reg_base);
+
+	ret = mtk_jpegenc_hw_init_irq(dev);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < MTK_JPEGENC_HW_MAX; i++) {
+		if (master_dev->enc_hw_dev[i])
+			continue;
+
+		master_dev->enc_hw_dev[i] = dev;
+		master_dev->reg_encbase[i] = dev->reg_base;
+		dev->master_dev = master_dev;
+	}
+
+	platform_set_drvdata(pdev, dev);
+	pm_runtime_enable(&pdev->dev);
+
+	return 0;
+}
+
+static struct platform_driver mtk_jpegenc_hw_driver = {
+	.probe = mtk_jpegenc_hw_probe,
+	.driver = {
+		.name = "mtk-jpegenc-hw",
+		.of_match_table = of_match_ptr(mtk_jpegenc_drv_ids),
+	},
+};
+
+module_platform_driver(mtk_jpegenc_hw_driver);
+
+MODULE_DESCRIPTION("MediaTek JPEG encode HW driver");
+MODULE_LICENSE("GPL");