From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next 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(). ... --- drivers/gpu/drm/pl111/pl111_display.c | 596 ++++++++++++++++++++++++++++++++++ 1 file changed, 596 insertions(+) create mode 100644 drivers/gpu/drm/pl111/pl111_display.c (limited to 'drivers/gpu/drm/pl111/pl111_display.c') diff --git a/drivers/gpu/drm/pl111/pl111_display.c b/drivers/gpu/drm/pl111/pl111_display.c new file mode 100644 index 000000000..6afdf260a --- /dev/null +++ b/drivers/gpu/drm/pl111/pl111_display.c @@ -0,0 +1,596 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * (C) COPYRIGHT 2012-2013 ARM Limited. All rights reserved. + * + * Parts of this file were based on sources as follows: + * + * Copyright (c) 2006-2008 Intel Corporation + * Copyright (c) 2007 Dave Airlie + * Copyright (C) 2011 Texas Instruments + */ + +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include + +#include "pl111_drm.h" + +irqreturn_t pl111_irq(int irq, void *data) +{ + struct pl111_drm_dev_private *priv = data; + u32 irq_stat; + irqreturn_t status = IRQ_NONE; + + irq_stat = readl(priv->regs + CLCD_PL111_MIS); + + if (!irq_stat) + return IRQ_NONE; + + if (irq_stat & CLCD_IRQ_NEXTBASE_UPDATE) { + drm_crtc_handle_vblank(&priv->pipe.crtc); + + status = IRQ_HANDLED; + } + + /* Clear the interrupt once done */ + writel(irq_stat, priv->regs + CLCD_PL111_ICR); + + return status; +} + +static enum drm_mode_status +pl111_mode_valid(struct drm_simple_display_pipe *pipe, + const struct drm_display_mode *mode) +{ + struct drm_device *drm = pipe->crtc.dev; + struct pl111_drm_dev_private *priv = drm->dev_private; + u32 cpp = priv->variant->fb_bpp / 8; + u64 bw; + + /* + * We use the pixelclock to also account for interlaced modes, the + * resulting bandwidth is in bytes per second. + */ + bw = mode->clock * 1000ULL; /* In Hz */ + bw = bw * mode->hdisplay * mode->vdisplay * cpp; + bw = div_u64(bw, mode->htotal * mode->vtotal); + + /* + * If no bandwidth constraints, anything goes, else + * check if we are too fast. + */ + if (priv->memory_bw && (bw > priv->memory_bw)) { + DRM_DEBUG_KMS("%d x %d @ %d Hz, %d cpp, bw %llu too fast\n", + mode->hdisplay, mode->vdisplay, + mode->clock * 1000, cpp, bw); + + return MODE_BAD; + } + DRM_DEBUG_KMS("%d x %d @ %d Hz, %d cpp, bw %llu bytes/s OK\n", + mode->hdisplay, mode->vdisplay, + mode->clock * 1000, cpp, bw); + + return MODE_OK; +} + +static int pl111_display_check(struct drm_simple_display_pipe *pipe, + struct drm_plane_state *pstate, + struct drm_crtc_state *cstate) +{ + const struct drm_display_mode *mode = &cstate->mode; + struct drm_framebuffer *old_fb = pipe->plane.state->fb; + struct drm_framebuffer *fb = pstate->fb; + + if (mode->hdisplay % 16) + return -EINVAL; + + if (fb) { + u32 offset = drm_fb_dma_get_gem_addr(fb, pstate, 0); + + /* FB base address must be dword aligned. */ + if (offset & 3) + return -EINVAL; + + /* There's no pitch register -- the mode's hdisplay + * controls it. + */ + if (fb->pitches[0] != mode->hdisplay * fb->format->cpp[0]) + return -EINVAL; + + /* We can't change the FB format in a flicker-free + * manner (and only update it during CRTC enable). + */ + if (old_fb && old_fb->format != fb->format) + cstate->mode_changed = true; + } + + return 0; +} + +static void pl111_display_enable(struct drm_simple_display_pipe *pipe, + struct drm_crtc_state *cstate, + struct drm_plane_state *plane_state) +{ + struct drm_crtc *crtc = &pipe->crtc; + struct drm_plane *plane = &pipe->plane; + struct drm_device *drm = crtc->dev; + struct pl111_drm_dev_private *priv = drm->dev_private; + const struct drm_display_mode *mode = &cstate->mode; + struct drm_framebuffer *fb = plane->state->fb; + struct drm_connector *connector = priv->connector; + struct drm_bridge *bridge = priv->bridge; + bool grayscale = false; + u32 cntl; + u32 ppl, hsw, hfp, hbp; + u32 lpp, vsw, vfp, vbp; + u32 cpl, tim2; + int ret; + + ret = clk_set_rate(priv->clk, mode->clock * 1000); + if (ret) { + dev_err(drm->dev, + "Failed to set pixel clock rate to %d: %d\n", + mode->clock * 1000, ret); + } + + clk_prepare_enable(priv->clk); + + ppl = (mode->hdisplay / 16) - 1; + hsw = mode->hsync_end - mode->hsync_start - 1; + hfp = mode->hsync_start - mode->hdisplay - 1; + hbp = mode->htotal - mode->hsync_end - 1; + + lpp = mode->vdisplay - 1; + vsw = mode->vsync_end - mode->vsync_start - 1; + vfp = mode->vsync_start - mode->vdisplay; + vbp = mode->vtotal - mode->vsync_end; + + cpl = mode->hdisplay - 1; + + writel((ppl << 2) | + (hsw << 8) | + (hfp << 16) | + (hbp << 24), + priv->regs + CLCD_TIM0); + writel(lpp | + (vsw << 10) | + (vfp << 16) | + (vbp << 24), + priv->regs + CLCD_TIM1); + + spin_lock(&priv->tim2_lock); + + tim2 = readl(priv->regs + CLCD_TIM2); + tim2 &= (TIM2_BCD | TIM2_PCD_LO_MASK | TIM2_PCD_HI_MASK); + + if (priv->variant->broken_clockdivider) + tim2 |= TIM2_BCD; + + if (mode->flags & DRM_MODE_FLAG_NHSYNC) + tim2 |= TIM2_IHS; + + if (mode->flags & DRM_MODE_FLAG_NVSYNC) + tim2 |= TIM2_IVS; + + if (connector) { + if (connector->display_info.bus_flags & DRM_BUS_FLAG_DE_LOW) + tim2 |= TIM2_IOE; + + if (connector->display_info.bus_flags & + DRM_BUS_FLAG_PIXDATA_DRIVE_NEGEDGE) + tim2 |= TIM2_IPC; + + if (connector->display_info.num_bus_formats == 1 && + connector->display_info.bus_formats[0] == + MEDIA_BUS_FMT_Y8_1X8) + grayscale = true; + + /* + * The AC pin bias frequency is set to max count when using + * grayscale so at least once in a while we will reverse + * polarity and get rid of any DC built up that could + * damage the display. + */ + if (grayscale) + tim2 |= TIM2_ACB_MASK; + } + + if (bridge) { + const struct drm_bridge_timings *btimings = bridge->timings; + + /* + * Here is when things get really fun. Sometimes the bridge + * timings are such that the signal out from PL11x is not + * stable before the receiving bridge (such as a dumb VGA DAC + * or similar) samples it. If that happens, we compensate by + * the only method we have: output the data on the opposite + * edge of the clock so it is for sure stable when it gets + * sampled. + * + * The PL111 manual does not contain proper timining diagrams + * or data for these details, but we know from experiments + * that the setup time is more than 3000 picoseconds (3 ns). + * If we have a bridge that requires the signal to be stable + * earlier than 3000 ps before the clock pulse, we have to + * output the data on the opposite edge to avoid flicker. + */ + if (btimings && btimings->setup_time_ps >= 3000) + tim2 ^= TIM2_IPC; + } + + tim2 |= cpl << 16; + writel(tim2, priv->regs + CLCD_TIM2); + spin_unlock(&priv->tim2_lock); + + writel(0, priv->regs + CLCD_TIM3); + + /* + * Detect grayscale bus format. We do not support a grayscale mode + * toward userspace, instead we expose an RGB24 buffer and then the + * hardware will activate its grayscaler to convert to the grayscale + * format. + */ + if (grayscale) + cntl = CNTL_LCDEN | CNTL_LCDMONO8; + else + /* Else we assume TFT display */ + cntl = CNTL_LCDEN | CNTL_LCDTFT | CNTL_LCDVCOMP(1); + + /* On the ST Micro variant, assume all 24 bits are connected */ + if (priv->variant->st_bitmux_control) + cntl |= CNTL_ST_CDWID_24; + + /* + * Note that the ARM hardware's format reader takes 'r' from + * the low bit, while DRM formats list channels from high bit + * to low bit as you read left to right. The ST Micro version of + * the PL110 (LCDC) however uses the standard DRM format. + */ + switch (fb->format->format) { + case DRM_FORMAT_BGR888: + /* Only supported on the ST Micro variant */ + if (priv->variant->st_bitmux_control) + cntl |= CNTL_ST_LCDBPP24_PACKED | CNTL_BGR; + break; + case DRM_FORMAT_RGB888: + /* Only supported on the ST Micro variant */ + if (priv->variant->st_bitmux_control) + cntl |= CNTL_ST_LCDBPP24_PACKED; + break; + case DRM_FORMAT_ABGR8888: + case DRM_FORMAT_XBGR8888: + if (priv->variant->st_bitmux_control) + cntl |= CNTL_LCDBPP24 | CNTL_BGR; + else + cntl |= CNTL_LCDBPP24; + break; + case DRM_FORMAT_ARGB8888: + case DRM_FORMAT_XRGB8888: + if (priv->variant->st_bitmux_control) + cntl |= CNTL_LCDBPP24; + else + cntl |= CNTL_LCDBPP24 | CNTL_BGR; + break; + case DRM_FORMAT_BGR565: + if (priv->variant->is_pl110) + cntl |= CNTL_LCDBPP16; + else if (priv->variant->st_bitmux_control) + cntl |= CNTL_LCDBPP16 | CNTL_ST_1XBPP_565 | CNTL_BGR; + else + cntl |= CNTL_LCDBPP16_565; + break; + case DRM_FORMAT_RGB565: + if (priv->variant->is_pl110) + cntl |= CNTL_LCDBPP16 | CNTL_BGR; + else if (priv->variant->st_bitmux_control) + cntl |= CNTL_LCDBPP16 | CNTL_ST_1XBPP_565; + else + cntl |= CNTL_LCDBPP16_565 | CNTL_BGR; + break; + case DRM_FORMAT_ABGR1555: + case DRM_FORMAT_XBGR1555: + cntl |= CNTL_LCDBPP16; + if (priv->variant->st_bitmux_control) + cntl |= CNTL_ST_1XBPP_5551 | CNTL_BGR; + break; + case DRM_FORMAT_ARGB1555: + case DRM_FORMAT_XRGB1555: + cntl |= CNTL_LCDBPP16; + if (priv->variant->st_bitmux_control) + cntl |= CNTL_ST_1XBPP_5551; + else + cntl |= CNTL_BGR; + break; + case DRM_FORMAT_ABGR4444: + case DRM_FORMAT_XBGR4444: + cntl |= CNTL_LCDBPP16_444; + if (priv->variant->st_bitmux_control) + cntl |= CNTL_ST_1XBPP_444 | CNTL_BGR; + break; + case DRM_FORMAT_ARGB4444: + case DRM_FORMAT_XRGB4444: + cntl |= CNTL_LCDBPP16_444; + if (priv->variant->st_bitmux_control) + cntl |= CNTL_ST_1XBPP_444; + else + cntl |= CNTL_BGR; + break; + default: + WARN_ONCE(true, "Unknown FB format 0x%08x\n", + fb->format->format); + break; + } + + /* The PL110 in Integrator/Versatile does the BGR routing externally */ + if (priv->variant->external_bgr) + cntl &= ~CNTL_BGR; + + /* Power sequence: first enable and chill */ + writel(cntl, priv->regs + priv->ctrl); + + /* + * We expect this delay to stabilize the contrast + * voltage Vee as stipulated by the manual + */ + msleep(20); + + if (priv->variant_display_enable) + priv->variant_display_enable(drm, fb->format->format); + + /* Power Up */ + cntl |= CNTL_LCDPWR; + writel(cntl, priv->regs + priv->ctrl); + + if (!priv->variant->broken_vblank) + drm_crtc_vblank_on(crtc); +} + +static void pl111_display_disable(struct drm_simple_display_pipe *pipe) +{ + struct drm_crtc *crtc = &pipe->crtc; + struct drm_device *drm = crtc->dev; + struct pl111_drm_dev_private *priv = drm->dev_private; + u32 cntl; + + if (!priv->variant->broken_vblank) + drm_crtc_vblank_off(crtc); + + /* Power Down */ + cntl = readl(priv->regs + priv->ctrl); + if (cntl & CNTL_LCDPWR) { + cntl &= ~CNTL_LCDPWR; + writel(cntl, priv->regs + priv->ctrl); + } + + /* + * We expect this delay to stabilize the contrast voltage Vee as + * stipulated by the manual + */ + msleep(20); + + if (priv->variant_display_disable) + priv->variant_display_disable(drm); + + /* Disable */ + writel(0, priv->regs + priv->ctrl); + + clk_disable_unprepare(priv->clk); +} + +static void pl111_display_update(struct drm_simple_display_pipe *pipe, + struct drm_plane_state *old_pstate) +{ + struct drm_crtc *crtc = &pipe->crtc; + struct drm_device *drm = crtc->dev; + struct pl111_drm_dev_private *priv = drm->dev_private; + struct drm_pending_vblank_event *event = crtc->state->event; + struct drm_plane *plane = &pipe->plane; + struct drm_plane_state *pstate = plane->state; + struct drm_framebuffer *fb = pstate->fb; + + if (fb) { + u32 addr = drm_fb_dma_get_gem_addr(fb, pstate, 0); + + writel(addr, priv->regs + CLCD_UBAS); + } + + if (event) { + crtc->state->event = NULL; + + spin_lock_irq(&crtc->dev->event_lock); + if (crtc->state->active && drm_crtc_vblank_get(crtc) == 0) + drm_crtc_arm_vblank_event(crtc, event); + else + drm_crtc_send_vblank_event(crtc, event); + spin_unlock_irq(&crtc->dev->event_lock); + } +} + +static int pl111_display_enable_vblank(struct drm_simple_display_pipe *pipe) +{ + struct drm_crtc *crtc = &pipe->crtc; + struct drm_device *drm = crtc->dev; + struct pl111_drm_dev_private *priv = drm->dev_private; + + writel(CLCD_IRQ_NEXTBASE_UPDATE, priv->regs + priv->ienb); + + return 0; +} + +static void pl111_display_disable_vblank(struct drm_simple_display_pipe *pipe) +{ + struct drm_crtc *crtc = &pipe->crtc; + struct drm_device *drm = crtc->dev; + struct pl111_drm_dev_private *priv = drm->dev_private; + + writel(0, priv->regs + priv->ienb); +} + +static struct drm_simple_display_pipe_funcs pl111_display_funcs = { + .mode_valid = pl111_mode_valid, + .check = pl111_display_check, + .enable = pl111_display_enable, + .disable = pl111_display_disable, + .update = pl111_display_update, +}; + +static int pl111_clk_div_choose_div(struct clk_hw *hw, unsigned long rate, + unsigned long *prate, bool set_parent) +{ + int best_div = 1, div; + struct clk_hw *parent = clk_hw_get_parent(hw); + unsigned long best_prate = 0; + unsigned long best_diff = ~0ul; + int max_div = (1 << (TIM2_PCD_LO_BITS + TIM2_PCD_HI_BITS)) - 1; + + for (div = 1; div < max_div; div++) { + unsigned long this_prate, div_rate, diff; + + if (set_parent) + this_prate = clk_hw_round_rate(parent, rate * div); + else + this_prate = *prate; + div_rate = DIV_ROUND_UP_ULL(this_prate, div); + diff = abs(rate - div_rate); + + if (diff < best_diff) { + best_div = div; + best_diff = diff; + best_prate = this_prate; + } + } + + *prate = best_prate; + return best_div; +} + +static long pl111_clk_div_round_rate(struct clk_hw *hw, unsigned long rate, + unsigned long *prate) +{ + int div = pl111_clk_div_choose_div(hw, rate, prate, true); + + return DIV_ROUND_UP_ULL(*prate, div); +} + +static unsigned long pl111_clk_div_recalc_rate(struct clk_hw *hw, + unsigned long prate) +{ + struct pl111_drm_dev_private *priv = + container_of(hw, struct pl111_drm_dev_private, clk_div); + u32 tim2 = readl(priv->regs + CLCD_TIM2); + int div; + + if (tim2 & TIM2_BCD) + return prate; + + div = tim2 & TIM2_PCD_LO_MASK; + div |= (tim2 & TIM2_PCD_HI_MASK) >> + (TIM2_PCD_HI_SHIFT - TIM2_PCD_LO_BITS); + div += 2; + + return DIV_ROUND_UP_ULL(prate, div); +} + +static int pl111_clk_div_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long prate) +{ + struct pl111_drm_dev_private *priv = + container_of(hw, struct pl111_drm_dev_private, clk_div); + int div = pl111_clk_div_choose_div(hw, rate, &prate, false); + u32 tim2; + + spin_lock(&priv->tim2_lock); + tim2 = readl(priv->regs + CLCD_TIM2); + tim2 &= ~(TIM2_BCD | TIM2_PCD_LO_MASK | TIM2_PCD_HI_MASK); + + if (div == 1) { + tim2 |= TIM2_BCD; + } else { + div -= 2; + tim2 |= div & TIM2_PCD_LO_MASK; + tim2 |= (div >> TIM2_PCD_LO_BITS) << TIM2_PCD_HI_SHIFT; + } + + writel(tim2, priv->regs + CLCD_TIM2); + spin_unlock(&priv->tim2_lock); + + return 0; +} + +static const struct clk_ops pl111_clk_div_ops = { + .recalc_rate = pl111_clk_div_recalc_rate, + .round_rate = pl111_clk_div_round_rate, + .set_rate = pl111_clk_div_set_rate, +}; + +static int +pl111_init_clock_divider(struct drm_device *drm) +{ + struct pl111_drm_dev_private *priv = drm->dev_private; + struct clk *parent = devm_clk_get(drm->dev, "clcdclk"); + struct clk_hw *div = &priv->clk_div; + const char *parent_name; + struct clk_init_data init = { + .name = "pl111_div", + .ops = &pl111_clk_div_ops, + .parent_names = &parent_name, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + }; + int ret; + + if (IS_ERR(parent)) { + dev_err(drm->dev, "CLCD: unable to get clcdclk.\n"); + return PTR_ERR(parent); + } + + spin_lock_init(&priv->tim2_lock); + + /* If the clock divider is broken, use the parent directly */ + if (priv->variant->broken_clockdivider) { + priv->clk = parent; + return 0; + } + parent_name = __clk_get_name(parent); + div->init = &init; + + ret = devm_clk_hw_register(drm->dev, div); + + priv->clk = div->clk; + return ret; +} + +int pl111_display_init(struct drm_device *drm) +{ + struct pl111_drm_dev_private *priv = drm->dev_private; + int ret; + + ret = pl111_init_clock_divider(drm); + if (ret) + return ret; + + if (!priv->variant->broken_vblank) { + pl111_display_funcs.enable_vblank = pl111_display_enable_vblank; + pl111_display_funcs.disable_vblank = pl111_display_disable_vblank; + } + + ret = drm_simple_display_pipe_init(drm, &priv->pipe, + &pl111_display_funcs, + priv->variant->formats, + priv->variant->nformats, + NULL, + priv->connector); + if (ret) + return ret; + + return 0; +} -- cgit v1.2.3