diff options
author | 2023-02-21 18:24:12 -0800 | |
---|---|---|
committer | 2023-02-21 18:24:12 -0800 | |
commit | 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch) | |
tree | cc5c2d0a898769fd59549594fedb3ee6f84e59a0 /drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c | |
download | linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.gz linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.zip |
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().
...
Diffstat (limited to 'drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c')
-rw-r--r-- | drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c | 1452 |
1 files changed, 1452 insertions, 0 deletions
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c new file mode 100644 index 000000000..b8767be1e --- /dev/null +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c @@ -0,0 +1,1452 @@ +/* + * Copyright 2016 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * Authors: AMD + * + */ + + +#include "dm_services.h" +#include "dm_helpers.h" +#include "core_types.h" +#include "resource.h" +#include "dccg.h" +#include "dce/dce_hwseq.h" +#include "dcn30/dcn30_cm_common.h" +#include "reg_helper.h" +#include "abm.h" +#include "hubp.h" +#include "dchubbub.h" +#include "timing_generator.h" +#include "opp.h" +#include "ipp.h" +#include "mpc.h" +#include "mcif_wb.h" +#include "dc_dmub_srv.h" +#include "link_hwss.h" +#include "dpcd_defs.h" +#include "dcn32_hwseq.h" +#include "clk_mgr.h" +#include "dsc.h" +#include "dcn20/dcn20_optc.h" +#include "dmub_subvp_state.h" +#include "dce/dmub_hw_lock_mgr.h" +#include "dcn32_resource.h" +#include "dc_link_dp.h" +#include "dmub/inc/dmub_subvp_state.h" + +#define DC_LOGGER_INIT(logger) + +#define CTX \ + hws->ctx +#define REG(reg)\ + hws->regs->reg +#define DC_LOGGER \ + dc->ctx->logger + + +#undef FN +#define FN(reg_name, field_name) \ + hws->shifts->field_name, hws->masks->field_name + +void dcn32_dsc_pg_control( + struct dce_hwseq *hws, + unsigned int dsc_inst, + bool power_on) +{ + uint32_t power_gate = power_on ? 0 : 1; + uint32_t pwr_status = power_on ? 0 : 2; + uint32_t org_ip_request_cntl = 0; + + if (hws->ctx->dc->debug.disable_dsc_power_gate) + return; + + REG_GET(DC_IP_REQUEST_CNTL, IP_REQUEST_EN, &org_ip_request_cntl); + if (org_ip_request_cntl == 0) + REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1); + + switch (dsc_inst) { + case 0: /* DSC0 */ + REG_UPDATE(DOMAIN16_PG_CONFIG, + DOMAIN_POWER_GATE, power_gate); + + REG_WAIT(DOMAIN16_PG_STATUS, + DOMAIN_PGFSM_PWR_STATUS, pwr_status, + 1, 1000); + break; + case 1: /* DSC1 */ + REG_UPDATE(DOMAIN17_PG_CONFIG, + DOMAIN_POWER_GATE, power_gate); + + REG_WAIT(DOMAIN17_PG_STATUS, + DOMAIN_PGFSM_PWR_STATUS, pwr_status, + 1, 1000); + break; + case 2: /* DSC2 */ + REG_UPDATE(DOMAIN18_PG_CONFIG, + DOMAIN_POWER_GATE, power_gate); + + REG_WAIT(DOMAIN18_PG_STATUS, + DOMAIN_PGFSM_PWR_STATUS, pwr_status, + 1, 1000); + break; + case 3: /* DSC3 */ + REG_UPDATE(DOMAIN19_PG_CONFIG, + DOMAIN_POWER_GATE, power_gate); + + REG_WAIT(DOMAIN19_PG_STATUS, + DOMAIN_PGFSM_PWR_STATUS, pwr_status, + 1, 1000); + break; + default: + BREAK_TO_DEBUGGER(); + break; + } + + if (org_ip_request_cntl == 0) + REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 0); +} + + +void dcn32_enable_power_gating_plane( + struct dce_hwseq *hws, + bool enable) +{ + bool force_on = true; /* disable power gating */ + + if (enable) + force_on = false; + + /* DCHUBP0/1/2/3 */ + REG_UPDATE(DOMAIN0_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); + REG_UPDATE(DOMAIN1_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); + REG_UPDATE(DOMAIN2_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); + REG_UPDATE(DOMAIN3_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); + + /* DCS0/1/2/3 */ + REG_UPDATE(DOMAIN16_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); + REG_UPDATE(DOMAIN17_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); + REG_UPDATE(DOMAIN18_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); + REG_UPDATE(DOMAIN19_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); +} + +void dcn32_hubp_pg_control(struct dce_hwseq *hws, unsigned int hubp_inst, bool power_on) +{ + uint32_t power_gate = power_on ? 0 : 1; + uint32_t pwr_status = power_on ? 0 : 2; + + if (hws->ctx->dc->debug.disable_hubp_power_gate) + return; + + if (REG(DOMAIN0_PG_CONFIG) == 0) + return; + + switch (hubp_inst) { + case 0: + REG_SET(DOMAIN0_PG_CONFIG, 0, DOMAIN_POWER_GATE, power_gate); + REG_WAIT(DOMAIN0_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 1000); + break; + case 1: + REG_SET(DOMAIN1_PG_CONFIG, 0, DOMAIN_POWER_GATE, power_gate); + REG_WAIT(DOMAIN1_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 1000); + break; + case 2: + REG_SET(DOMAIN2_PG_CONFIG, 0, DOMAIN_POWER_GATE, power_gate); + REG_WAIT(DOMAIN2_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 1000); + break; + case 3: + REG_SET(DOMAIN3_PG_CONFIG, 0, DOMAIN_POWER_GATE, power_gate); + REG_WAIT(DOMAIN3_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 1000); + break; + default: + BREAK_TO_DEBUGGER(); + break; + } +} + +static bool dcn32_check_no_memory_request_for_cab(struct dc *dc) +{ + int i; + + /* First, check no-memory-request case */ + for (i = 0; i < dc->current_state->stream_count; i++) { + if (dc->current_state->stream_status[i].plane_count) + /* Fail eligibility on a visible stream */ + break; + } + + if (i == dc->current_state->stream_count) + return true; + + return false; +} + + +/* This function loops through every surface that needs to be cached in CAB for SS, + * and calculates the total number of ways required to store all surfaces (primary, + * meta, cursor). + */ +static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *ctx) +{ + int i, j; + struct dc_stream_state *stream = NULL; + struct dc_plane_state *plane = NULL; + uint32_t cursor_size = 0; + uint32_t total_lines = 0; + uint32_t lines_per_way = 0; + uint8_t num_ways = 0; + uint8_t bytes_per_pixel = 0; + uint8_t cursor_bpp = 0; + uint16_t mblk_width = 0; + uint16_t mblk_height = 0; + uint16_t mall_alloc_width_blk_aligned = 0; + uint16_t mall_alloc_height_blk_aligned = 0; + uint16_t num_mblks = 0; + uint32_t bytes_in_mall = 0; + uint32_t cache_lines_used = 0; + uint32_t cache_lines_per_plane = 0; + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i]; + + /* If PSR is supported on an eDP panel that's connected, but that panel is + * not in PSR at the time of trying to enter MALL SS, we have to include it + * in the static screen CAB calculation + */ + if (!pipe->stream || !pipe->plane_state || + (pipe->stream->link->psr_settings.psr_version != DC_PSR_VERSION_UNSUPPORTED && + pipe->stream->link->psr_settings.psr_allow_active) || + pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) + continue; + + bytes_per_pixel = pipe->plane_state->format >= SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616 ? 8 : 4; + mblk_width = DCN3_2_MBLK_WIDTH; + mblk_height = bytes_per_pixel == 4 ? DCN3_2_MBLK_HEIGHT_4BPE : DCN3_2_MBLK_HEIGHT_8BPE; + + /* full_vp_width_blk_aligned = FLOOR(vp_x_start + full_vp_width + blk_width - 1, blk_width) - + * FLOOR(vp_x_start, blk_width) + * + * mall_alloc_width_blk_aligned_l/c = full_vp_width_blk_aligned_l/c + */ + mall_alloc_width_blk_aligned = ((pipe->plane_res.scl_data.viewport.x + + pipe->plane_res.scl_data.viewport.width + mblk_width - 1) / mblk_width * mblk_width) - + (pipe->plane_res.scl_data.viewport.x / mblk_width * mblk_width); + + /* full_vp_height_blk_aligned = FLOOR(vp_y_start + full_vp_height + blk_height - 1, blk_height) - + * FLOOR(vp_y_start, blk_height) + * + * mall_alloc_height_blk_aligned_l/c = full_vp_height_blk_aligned_l/c + */ + mall_alloc_height_blk_aligned = ((pipe->plane_res.scl_data.viewport.y + + pipe->plane_res.scl_data.viewport.height + mblk_height - 1) / mblk_height * mblk_height) - + (pipe->plane_res.scl_data.viewport.y / mblk_height * mblk_height); + + num_mblks = ((mall_alloc_width_blk_aligned + mblk_width - 1) / mblk_width) * + ((mall_alloc_height_blk_aligned + mblk_height - 1) / mblk_height); + + /*For DCC: + * meta_num_mblk = CEILING(meta_pitch*full_vp_height*Bpe/256/mblk_bytes, 1) + */ + if (pipe->plane_state->dcc.enable) + num_mblks += (pipe->plane_state->dcc.meta_pitch * pipe->plane_res.scl_data.viewport.height * bytes_per_pixel + + (256 * DCN3_2_MALL_MBLK_SIZE_BYTES) - 1) / (256 * DCN3_2_MALL_MBLK_SIZE_BYTES); + + bytes_in_mall = num_mblks * DCN3_2_MALL_MBLK_SIZE_BYTES; + + /* (cache lines used is total bytes / cache_line size. Add +2 for worst case alignment + * (MALL is 64-byte aligned) + */ + cache_lines_per_plane = bytes_in_mall / dc->caps.cache_line_size + 2; + cache_lines_used += cache_lines_per_plane; + } + + // Include cursor size for CAB allocation + for (j = 0; j < dc->res_pool->pipe_count; j++) { + struct pipe_ctx *pipe = &ctx->res_ctx.pipe_ctx[j]; + struct hubp *hubp = pipe->plane_res.hubp; + + if (pipe->stream && pipe->plane_state && hubp) + /* Find the cursor plane and use the exact size instead of + using the max for calculation */ + + if (hubp->curs_attr.width > 0) { + cursor_size = hubp->curs_attr.pitch * hubp->curs_attr.height; + + switch (pipe->stream->cursor_attributes.color_format) { + case CURSOR_MODE_MONO: + cursor_size /= 2; + cursor_bpp = 4; + break; + case CURSOR_MODE_COLOR_1BIT_AND: + case CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA: + case CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA: + cursor_size *= 4; + cursor_bpp = 4; + break; + + case CURSOR_MODE_COLOR_64BIT_FP_PRE_MULTIPLIED: + case CURSOR_MODE_COLOR_64BIT_FP_UN_PRE_MULTIPLIED: + cursor_size *= 8; + cursor_bpp = 8; + break; + } + + if (pipe->stream->cursor_position.enable && !dc->debug.alloc_extra_way_for_cursor && + cursor_size > 16384) { + /* cursor_num_mblk = CEILING(num_cursors*cursor_width*cursor_width*cursor_Bpe/mblk_bytes, 1) + */ + cache_lines_used += (((cursor_size + DCN3_2_MALL_MBLK_SIZE_BYTES - 1) / + DCN3_2_MALL_MBLK_SIZE_BYTES) * DCN3_2_MALL_MBLK_SIZE_BYTES) / + dc->caps.cache_line_size + 2; + break; + } + } + } + + // Convert number of cache lines required to number of ways + total_lines = dc->caps.max_cab_allocation_bytes / dc->caps.cache_line_size; + lines_per_way = total_lines / dc->caps.cache_num_ways; + num_ways = cache_lines_used / lines_per_way; + + if (cache_lines_used % lines_per_way > 0) + num_ways++; + + for (i = 0; i < ctx->stream_count; i++) { + stream = ctx->streams[i]; + for (j = 0; j < ctx->stream_status[i].plane_count; j++) { + plane = ctx->stream_status[i].plane_states[j]; + + if (stream->cursor_position.enable && plane && + dc->debug.alloc_extra_way_for_cursor && + cursor_size > 16384) { + /* Cursor caching is not supported since it won't be on the same line. + * So we need an extra line to accommodate it. With large cursors and a single 4k monitor + * this case triggers corruption. If we're at the edge, then dont trigger display refresh + * from MALL. We only need to cache cursor if its greater that 64x64 at 4 bpp. + */ + num_ways++; + /* We only expect one cursor plane */ + break; + } + } + } + if (dc->debug.force_mall_ss_num_ways > 0) { + num_ways = dc->debug.force_mall_ss_num_ways; + } + return num_ways; +} + +bool dcn32_apply_idle_power_optimizations(struct dc *dc, bool enable) +{ + union dmub_rb_cmd cmd; + uint8_t ways, i; + int j; + bool mall_ss_unsupported = false; + struct dc_plane_state *plane = NULL; + + if (!dc->ctx->dmub_srv) + return false; + + if (enable) { + if (dc->current_state) { + + /* 1. Check no memory request case for CAB. + * If no memory request case, send CAB_ACTION NO_DF_REQ DMUB message + */ + if (dcn32_check_no_memory_request_for_cab(dc)) { + /* Enable no-memory-requests case */ + memset(&cmd, 0, sizeof(cmd)); + cmd.cab.header.type = DMUB_CMD__CAB_FOR_SS; + cmd.cab.header.sub_type = DMUB_CMD__CAB_NO_DCN_REQ; + cmd.cab.header.payload_bytes = sizeof(cmd.cab) - sizeof(cmd.cab.header); + + dc_dmub_srv_cmd_queue(dc->ctx->dmub_srv, &cmd); + dc_dmub_srv_cmd_execute(dc->ctx->dmub_srv); + + return true; + } + + /* 2. Check if all surfaces can fit in CAB. + * If surfaces can fit into CAB, send CAB_ACTION_ALLOW DMUB message + * and configure HUBP's to fetch from MALL + */ + ways = dcn32_calculate_cab_allocation(dc, dc->current_state); + + /* MALL not supported with Stereo3D or TMZ surface. If any plane is using stereo, + * or TMZ surface, don't try to enter MALL. + */ + for (i = 0; i < dc->current_state->stream_count; i++) { + for (j = 0; j < dc->current_state->stream_status[i].plane_count; j++) { + plane = dc->current_state->stream_status[i].plane_states[j]; + + if (plane->address.type == PLN_ADDR_TYPE_GRPH_STEREO || + plane->address.tmz_surface) { + mall_ss_unsupported = true; + break; + } + } + if (mall_ss_unsupported) + break; + } + if (ways <= dc->caps.cache_num_ways && !mall_ss_unsupported) { + memset(&cmd, 0, sizeof(cmd)); + cmd.cab.header.type = DMUB_CMD__CAB_FOR_SS; + cmd.cab.header.sub_type = DMUB_CMD__CAB_DCN_SS_FIT_IN_CAB; + cmd.cab.header.payload_bytes = sizeof(cmd.cab) - sizeof(cmd.cab.header); + cmd.cab.cab_alloc_ways = ways; + + dc_dmub_srv_cmd_queue(dc->ctx->dmub_srv, &cmd); + dc_dmub_srv_cmd_execute(dc->ctx->dmub_srv); + + return true; + } + + } + return false; + } + + /* Disable CAB */ + memset(&cmd, 0, sizeof(cmd)); + cmd.cab.header.type = DMUB_CMD__CAB_FOR_SS; + cmd.cab.header.sub_type = DMUB_CMD__CAB_NO_IDLE_OPTIMIZATION; + cmd.cab.header.payload_bytes = + sizeof(cmd.cab) - sizeof(cmd.cab.header); + + dc_dmub_srv_cmd_queue(dc->ctx->dmub_srv, &cmd); + dc_dmub_srv_cmd_execute(dc->ctx->dmub_srv); + dc_dmub_srv_wait_idle(dc->ctx->dmub_srv); + + return true; +} + +/* Send DMCUB message with SubVP pipe info + * - For each pipe in context, populate payload with required SubVP information + * if the pipe is using SubVP for MCLK switch + * - This function must be called while the DMUB HW lock is acquired by driver + */ +void dcn32_commit_subvp_config(struct dc *dc, struct dc_state *context) +{ + int i; + bool enable_subvp = false; + + if (!dc->ctx || !dc->ctx->dmub_srv) + return; + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i]; + + if (pipe_ctx->stream && pipe_ctx->stream->mall_stream_config.paired_stream && + pipe_ctx->stream->mall_stream_config.type == SUBVP_MAIN) { + // There is at least 1 SubVP pipe, so enable SubVP + enable_subvp = true; + break; + } + } + dc_dmub_setup_subvp_dmub_command(dc, context, enable_subvp); +} + +/* Sub-Viewport DMUB lock needs to be acquired by driver whenever SubVP is active and: + * 1. Any full update for any SubVP main pipe + * 2. Any immediate flip for any SubVP pipe + * 3. Any flip for DRR pipe + * 4. If SubVP was previously in use (i.e. in old context) + */ +void dcn32_subvp_pipe_control_lock(struct dc *dc, + struct dc_state *context, + bool lock, + bool should_lock_all_pipes, + struct pipe_ctx *top_pipe_to_program, + bool subvp_prev_use) +{ + unsigned int i = 0; + bool subvp_immediate_flip = false; + bool subvp_in_use = false; + struct pipe_ctx *pipe; + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + pipe = &context->res_ctx.pipe_ctx[i]; + + if (pipe->stream && pipe->plane_state && pipe->stream->mall_stream_config.type == SUBVP_MAIN) { + subvp_in_use = true; + break; + } + } + + if (top_pipe_to_program && top_pipe_to_program->stream && top_pipe_to_program->plane_state) { + if (top_pipe_to_program->stream->mall_stream_config.type == SUBVP_MAIN && + top_pipe_to_program->plane_state->flip_immediate) + subvp_immediate_flip = true; + } + + // Don't need to lock for DRR VSYNC flips -- FW will wait for DRR pending update cleared. + if ((subvp_in_use && (should_lock_all_pipes || subvp_immediate_flip)) || (!subvp_in_use && subvp_prev_use)) { + union dmub_inbox0_cmd_lock_hw hw_lock_cmd = { 0 }; + + if (!lock) { + for (i = 0; i < dc->res_pool->pipe_count; i++) { + pipe = &context->res_ctx.pipe_ctx[i]; + if (pipe->stream && pipe->plane_state && pipe->stream->mall_stream_config.type == SUBVP_MAIN && + should_lock_all_pipes) + pipe->stream_res.tg->funcs->wait_for_state(pipe->stream_res.tg, CRTC_STATE_VBLANK); + } + } + + hw_lock_cmd.bits.command_code = DMUB_INBOX0_CMD__HW_LOCK; + hw_lock_cmd.bits.hw_lock_client = HW_LOCK_CLIENT_DRIVER; + hw_lock_cmd.bits.lock = lock; + hw_lock_cmd.bits.should_release = !lock; + dmub_hw_lock_mgr_inbox0_cmd(dc->ctx->dmub_srv, hw_lock_cmd); + } +} + + +static bool dcn32_set_mpc_shaper_3dlut( + struct pipe_ctx *pipe_ctx, const struct dc_stream_state *stream) +{ + struct dpp *dpp_base = pipe_ctx->plane_res.dpp; + int mpcc_id = pipe_ctx->plane_res.hubp->inst; + struct mpc *mpc = pipe_ctx->stream_res.opp->ctx->dc->res_pool->mpc; + bool result = false; + + const struct pwl_params *shaper_lut = NULL; + //get the shaper lut params + if (stream->func_shaper) { + if (stream->func_shaper->type == TF_TYPE_HWPWL) + shaper_lut = &stream->func_shaper->pwl; + else if (stream->func_shaper->type == TF_TYPE_DISTRIBUTED_POINTS) { + cm_helper_translate_curve_to_hw_format( + stream->func_shaper, + &dpp_base->shaper_params, true); + shaper_lut = &dpp_base->shaper_params; + } + } + + if (stream->lut3d_func && + stream->lut3d_func->state.bits.initialized == 1) { + + result = mpc->funcs->program_3dlut(mpc, + &stream->lut3d_func->lut_3d, + mpcc_id); + + result = mpc->funcs->program_shaper(mpc, + shaper_lut, + mpcc_id); + } + + return result; +} + +bool dcn32_set_mcm_luts( + struct pipe_ctx *pipe_ctx, const struct dc_plane_state *plane_state) +{ + struct dpp *dpp_base = pipe_ctx->plane_res.dpp; + int mpcc_id = pipe_ctx->plane_res.hubp->inst; + struct mpc *mpc = pipe_ctx->stream_res.opp->ctx->dc->res_pool->mpc; + bool result = true; + struct pwl_params *lut_params = NULL; + + // 1D LUT + if (plane_state->blend_tf) { + if (plane_state->blend_tf->type == TF_TYPE_HWPWL) + lut_params = &plane_state->blend_tf->pwl; + else if (plane_state->blend_tf->type == TF_TYPE_DISTRIBUTED_POINTS) { + cm_helper_translate_curve_to_hw_format( + plane_state->blend_tf, + &dpp_base->regamma_params, false); + lut_params = &dpp_base->regamma_params; + } + } + result = mpc->funcs->program_1dlut(mpc, lut_params, mpcc_id); + + // Shaper + if (plane_state->in_shaper_func) { + if (plane_state->in_shaper_func->type == TF_TYPE_HWPWL) + lut_params = &plane_state->in_shaper_func->pwl; + else if (plane_state->in_shaper_func->type == TF_TYPE_DISTRIBUTED_POINTS) { + // TODO: dpp_base replace + ASSERT(false); + cm_helper_translate_curve_to_hw_format( + plane_state->in_shaper_func, + &dpp_base->shaper_params, true); + lut_params = &dpp_base->shaper_params; + } + } + + result = mpc->funcs->program_shaper(mpc, lut_params, mpcc_id); + + // 3D + if (plane_state->lut3d_func && plane_state->lut3d_func->state.bits.initialized == 1) + result = mpc->funcs->program_3dlut(mpc, &plane_state->lut3d_func->lut_3d, mpcc_id); + else + result = mpc->funcs->program_3dlut(mpc, NULL, mpcc_id); + + return result; +} + +bool dcn32_set_input_transfer_func(struct dc *dc, + struct pipe_ctx *pipe_ctx, + const struct dc_plane_state *plane_state) +{ + struct dce_hwseq *hws = dc->hwseq; + struct mpc *mpc = dc->res_pool->mpc; + struct dpp *dpp_base = pipe_ctx->plane_res.dpp; + + enum dc_transfer_func_predefined tf; + bool result = true; + struct pwl_params *params = NULL; + + if (mpc == NULL || plane_state == NULL) + return false; + + tf = TRANSFER_FUNCTION_UNITY; + + if (plane_state->in_transfer_func && + plane_state->in_transfer_func->type == TF_TYPE_PREDEFINED) + tf = plane_state->in_transfer_func->tf; + + dpp_base->funcs->dpp_set_pre_degam(dpp_base, tf); + + if (plane_state->in_transfer_func) { + if (plane_state->in_transfer_func->type == TF_TYPE_HWPWL) + params = &plane_state->in_transfer_func->pwl; + else if (plane_state->in_transfer_func->type == TF_TYPE_DISTRIBUTED_POINTS && + cm3_helper_translate_curve_to_hw_format(plane_state->in_transfer_func, + &dpp_base->degamma_params, false)) + params = &dpp_base->degamma_params; + } + + dpp_base->funcs->dpp_program_gamcor_lut(dpp_base, params); + + if (pipe_ctx->stream_res.opp && + pipe_ctx->stream_res.opp->ctx && + hws->funcs.set_mcm_luts) + result = hws->funcs.set_mcm_luts(pipe_ctx, plane_state); + + return result; +} + +bool dcn32_set_output_transfer_func(struct dc *dc, + struct pipe_ctx *pipe_ctx, + const struct dc_stream_state *stream) +{ + int mpcc_id = pipe_ctx->plane_res.hubp->inst; + struct mpc *mpc = pipe_ctx->stream_res.opp->ctx->dc->res_pool->mpc; + struct pwl_params *params = NULL; + bool ret = false; + + /* program OGAM or 3DLUT only for the top pipe*/ + if (pipe_ctx->top_pipe == NULL) { + /*program shaper and 3dlut in MPC*/ + ret = dcn32_set_mpc_shaper_3dlut(pipe_ctx, stream); + if (ret == false && mpc->funcs->set_output_gamma && stream->out_transfer_func) { + if (stream->out_transfer_func->type == TF_TYPE_HWPWL) + params = &stream->out_transfer_func->pwl; + else if (pipe_ctx->stream->out_transfer_func->type == + TF_TYPE_DISTRIBUTED_POINTS && + cm3_helper_translate_curve_to_hw_format( + stream->out_transfer_func, + &mpc->blender_params, false)) + params = &mpc->blender_params; + /* there are no ROM LUTs in OUTGAM */ + if (stream->out_transfer_func->type == TF_TYPE_PREDEFINED) + BREAK_TO_DEBUGGER(); + } + } + + mpc->funcs->set_output_gamma(mpc, mpcc_id, params); + return ret; +} + +/* Program P-State force value according to if pipe is using SubVP or not: + * 1. Reset P-State force on all pipes first + * 2. For each main pipe, force P-State disallow (P-State allow moderated by DMUB) + */ +void dcn32_subvp_update_force_pstate(struct dc *dc, struct dc_state *context) +{ + int i; + int num_subvp = 0; + /* Unforce p-state for each pipe + */ + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; + struct hubp *hubp = pipe->plane_res.hubp; + + if (hubp && hubp->funcs->hubp_update_force_pstate_disallow) + hubp->funcs->hubp_update_force_pstate_disallow(hubp, false); + if (pipe->stream && pipe->stream->mall_stream_config.type == SUBVP_MAIN) + num_subvp++; + } + + if (num_subvp == 0) + return; + + /* Loop through each pipe -- for each subvp main pipe force p-state allow equal to false. + */ + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; + + if (pipe->stream && pipe->plane_state && (pipe->stream->mall_stream_config.type == SUBVP_MAIN)) { + struct hubp *hubp = pipe->plane_res.hubp; + + if (hubp && hubp->funcs->hubp_update_force_pstate_disallow) + hubp->funcs->hubp_update_force_pstate_disallow(hubp, true); + } + } +} + +/* Update MALL_SEL register based on if pipe / plane + * is a phantom pipe, main pipe, and if using MALL + * for SS. + */ +void dcn32_update_mall_sel(struct dc *dc, struct dc_state *context) +{ + int i; + unsigned int num_ways = dcn32_calculate_cab_allocation(dc, context); + bool cache_cursor = false; + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; + struct hubp *hubp = pipe->plane_res.hubp; + + if (pipe->stream && pipe->plane_state && hubp && hubp->funcs->hubp_update_mall_sel) { + int cursor_size = hubp->curs_attr.pitch * hubp->curs_attr.height; + + switch (hubp->curs_attr.color_format) { + case CURSOR_MODE_MONO: + cursor_size /= 2; + break; + case CURSOR_MODE_COLOR_1BIT_AND: + case CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA: + case CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA: + cursor_size *= 4; + break; + + case CURSOR_MODE_COLOR_64BIT_FP_PRE_MULTIPLIED: + case CURSOR_MODE_COLOR_64BIT_FP_UN_PRE_MULTIPLIED: + default: + cursor_size *= 8; + break; + } + + if (cursor_size > 16384) + cache_cursor = true; + + if (pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) { + hubp->funcs->hubp_update_mall_sel(hubp, 1, false); + } else { + // MALL not supported with Stereo3D + hubp->funcs->hubp_update_mall_sel(hubp, + num_ways <= dc->caps.cache_num_ways && + pipe->stream->link->psr_settings.psr_version == DC_PSR_VERSION_UNSUPPORTED && + pipe->plane_state->address.type != PLN_ADDR_TYPE_GRPH_STEREO && + !pipe->plane_state->address.tmz_surface ? 2 : 0, + cache_cursor); + } + } + } +} + +/* Program the sub-viewport pipe configuration after the main / phantom pipes + * have been programmed in hardware. + * 1. Update force P-State for all the main pipes (disallow P-state) + * 2. Update MALL_SEL register + * 3. Program FORCE_ONE_ROW_FOR_FRAME for main subvp pipes + */ +void dcn32_program_mall_pipe_config(struct dc *dc, struct dc_state *context) +{ + int i; + struct dce_hwseq *hws = dc->hwseq; + + // Don't force p-state disallow -- can't block dummy p-state + + // Update MALL_SEL register for each pipe + if (hws && hws->funcs.update_mall_sel) + hws->funcs.update_mall_sel(dc, context); + + //update subvp force pstate + if (hws && hws->funcs.subvp_update_force_pstate) + dc->hwseq->funcs.subvp_update_force_pstate(dc, context); + + // Program FORCE_ONE_ROW_FOR_FRAME and CURSOR_REQ_MODE for main subvp pipes + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; + struct hubp *hubp = pipe->plane_res.hubp; + + if (pipe->stream && hubp && hubp->funcs->hubp_prepare_subvp_buffering) { + /* TODO - remove setting CURSOR_REQ_MODE to 0 for legacy cases + * - need to investigate single pipe MPO + SubVP case to + * see if CURSOR_REQ_MODE will be back to 1 for SubVP + * when it should be 0 for MPO + */ + if (pipe->stream->mall_stream_config.type == SUBVP_MAIN) { + hubp->funcs->hubp_prepare_subvp_buffering(hubp, true); + } + } + } +} + +void dcn32_init_hw(struct dc *dc) +{ + struct abm **abms = dc->res_pool->multiple_abms; + struct dce_hwseq *hws = dc->hwseq; + struct dc_bios *dcb = dc->ctx->dc_bios; + struct resource_pool *res_pool = dc->res_pool; + int i; + int edp_num; + uint32_t backlight = MAX_BACKLIGHT_LEVEL; + + if (dc->clk_mgr && dc->clk_mgr->funcs->init_clocks) + dc->clk_mgr->funcs->init_clocks(dc->clk_mgr); + + // Initialize the dccg + if (res_pool->dccg->funcs->dccg_init) + res_pool->dccg->funcs->dccg_init(res_pool->dccg); + + if (!dcb->funcs->is_accelerated_mode(dcb)) { + hws->funcs.bios_golden_init(dc); + hws->funcs.disable_vga(dc->hwseq); + } + + // Set default OPTC memory power states + if (dc->debug.enable_mem_low_power.bits.optc) { + // Shutdown when unassigned and light sleep in VBLANK + REG_SET_2(ODM_MEM_PWR_CTRL3, 0, ODM_MEM_UNASSIGNED_PWR_MODE, 3, ODM_MEM_VBLANK_PWR_MODE, 1); + } + + if (dc->debug.enable_mem_low_power.bits.vga) { + // Power down VGA memory + REG_UPDATE(MMHUBBUB_MEM_PWR_CNTL, VGA_MEM_PWR_FORCE, 1); + } + + if (dc->ctx->dc_bios->fw_info_valid) { + res_pool->ref_clocks.xtalin_clock_inKhz = + dc->ctx->dc_bios->fw_info.pll_info.crystal_frequency; + + if (res_pool->dccg && res_pool->hubbub) { + (res_pool->dccg->funcs->get_dccg_ref_freq)(res_pool->dccg, + dc->ctx->dc_bios->fw_info.pll_info.crystal_frequency, + &res_pool->ref_clocks.dccg_ref_clock_inKhz); + + (res_pool->hubbub->funcs->get_dchub_ref_freq)(res_pool->hubbub, + res_pool->ref_clocks.dccg_ref_clock_inKhz, + &res_pool->ref_clocks.dchub_ref_clock_inKhz); + } else { + // Not all ASICs have DCCG sw component + res_pool->ref_clocks.dccg_ref_clock_inKhz = + res_pool->ref_clocks.xtalin_clock_inKhz; + res_pool->ref_clocks.dchub_ref_clock_inKhz = + res_pool->ref_clocks.xtalin_clock_inKhz; + } + } else + ASSERT_CRITICAL(false); + + for (i = 0; i < dc->link_count; i++) { + /* Power up AND update implementation according to the + * required signal (which may be different from the + * default signal on connector). + */ + struct dc_link *link = dc->links[i]; + + link->link_enc->funcs->hw_init(link->link_enc); + + /* Check for enabled DIG to identify enabled display */ + if (link->link_enc->funcs->is_dig_enabled && + link->link_enc->funcs->is_dig_enabled(link->link_enc)) { + link->link_status.link_active = true; + link->phy_state.symclk_state = SYMCLK_ON_TX_ON; + if (link->link_enc->funcs->fec_is_active && + link->link_enc->funcs->fec_is_active(link->link_enc)) + link->fec_state = dc_link_fec_enabled; + } + } + + /* Power gate DSCs */ + for (i = 0; i < res_pool->res_cap->num_dsc; i++) + if (hws->funcs.dsc_pg_control != NULL) + hws->funcs.dsc_pg_control(hws, res_pool->dscs[i]->inst, false); + + /* we want to turn off all dp displays before doing detection */ + dc_link_blank_all_dp_displays(dc); + + /* If taking control over from VBIOS, we may want to optimize our first + * mode set, so we need to skip powering down pipes until we know which + * pipes we want to use. + * Otherwise, if taking control is not possible, we need to power + * everything down. + */ + if (dcb->funcs->is_accelerated_mode(dcb) || !dc->config.seamless_boot_edp_requested) { + hws->funcs.init_pipes(dc, dc->current_state); + if (dc->res_pool->hubbub->funcs->allow_self_refresh_control) + dc->res_pool->hubbub->funcs->allow_self_refresh_control(dc->res_pool->hubbub, + !dc->res_pool->hubbub->ctx->dc->debug.disable_stutter); + } + + /* In headless boot cases, DIG may be turned + * on which causes HW/SW discrepancies. + * To avoid this, power down hardware on boot + * if DIG is turned on and seamless boot not enabled + */ + if (!dc->config.seamless_boot_edp_requested) { + struct dc_link *edp_links[MAX_NUM_EDP]; + struct dc_link *edp_link; + + get_edp_links(dc, edp_links, &edp_num); + if (edp_num) { + for (i = 0; i < edp_num; i++) { + edp_link = edp_links[i]; + if (edp_link->link_enc->funcs->is_dig_enabled && + edp_link->link_enc->funcs->is_dig_enabled(edp_link->link_enc) && + dc->hwss.edp_backlight_control && + dc->hwss.power_down && + dc->hwss.edp_power_control) { + dc->hwss.edp_backlight_control(edp_link, false); + dc->hwss.power_down(dc); + dc->hwss.edp_power_control(edp_link, false); + } + } + } else { + for (i = 0; i < dc->link_count; i++) { + struct dc_link *link = dc->links[i]; + + if (link->link_enc->funcs->is_dig_enabled && + link->link_enc->funcs->is_dig_enabled(link->link_enc) && + dc->hwss.power_down) { + dc->hwss.power_down(dc); + break; + } + + } + } + } + + for (i = 0; i < res_pool->audio_count; i++) { + struct audio *audio = res_pool->audios[i]; + + audio->funcs->hw_init(audio); + } + + for (i = 0; i < dc->link_count; i++) { + struct dc_link *link = dc->links[i]; + + if (link->panel_cntl) + backlight = link->panel_cntl->funcs->hw_init(link->panel_cntl); + } + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + if (abms[i] != NULL && abms[i]->funcs != NULL) + abms[i]->funcs->abm_init(abms[i], backlight); + } + + /* power AFMT HDMI memory TODO: may move to dis/en output save power*/ + REG_WRITE(DIO_MEM_PWR_CTRL, 0); + + if (!dc->debug.disable_clock_gate) { + /* enable all DCN clock gating */ + REG_WRITE(DCCG_GATE_DISABLE_CNTL, 0); + + REG_WRITE(DCCG_GATE_DISABLE_CNTL2, 0); + + REG_UPDATE(DCFCLK_CNTL, DCFCLK_GATE_DIS, 0); + } + if (hws->funcs.enable_power_gating_plane) + hws->funcs.enable_power_gating_plane(dc->hwseq, true); + + if (!dcb->funcs->is_accelerated_mode(dcb) && dc->res_pool->hubbub->funcs->init_watermarks) + dc->res_pool->hubbub->funcs->init_watermarks(dc->res_pool->hubbub); + + if (dc->clk_mgr->funcs->notify_wm_ranges) + dc->clk_mgr->funcs->notify_wm_ranges(dc->clk_mgr); + + if (dc->clk_mgr->funcs->set_hard_max_memclk) + dc->clk_mgr->funcs->set_hard_max_memclk(dc->clk_mgr); + + if (dc->res_pool->hubbub->funcs->force_pstate_change_control) + dc->res_pool->hubbub->funcs->force_pstate_change_control( + dc->res_pool->hubbub, false, false); + + if (dc->res_pool->hubbub->funcs->init_crb) + dc->res_pool->hubbub->funcs->init_crb(dc->res_pool->hubbub); + + if (dc->res_pool->hubbub->funcs->set_request_limit && dc->config.sdpif_request_limit_words_per_umc > 0) + dc->res_pool->hubbub->funcs->set_request_limit(dc->res_pool->hubbub, dc->ctx->dc_bios->vram_info.num_chans, dc->config.sdpif_request_limit_words_per_umc); + + // Get DMCUB capabilities + if (dc->ctx->dmub_srv) { + dc_dmub_srv_query_caps_cmd(dc->ctx->dmub_srv->dmub); + dc->caps.dmub_caps.psr = dc->ctx->dmub_srv->dmub->feature_caps.psr; + } +} + +static int calc_mpc_flow_ctrl_cnt(const struct dc_stream_state *stream, + int opp_cnt) +{ + bool hblank_halved = optc2_is_two_pixels_per_containter(&stream->timing); + int flow_ctrl_cnt; + + if (opp_cnt >= 2) + hblank_halved = true; + + flow_ctrl_cnt = stream->timing.h_total - stream->timing.h_addressable - + stream->timing.h_border_left - + stream->timing.h_border_right; + + if (hblank_halved) + flow_ctrl_cnt /= 2; + + /* ODM combine 4:1 case */ + if (opp_cnt == 4) + flow_ctrl_cnt /= 2; + + return flow_ctrl_cnt; +} + +static void update_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable) +{ + struct display_stream_compressor *dsc = pipe_ctx->stream_res.dsc; + struct dc_stream_state *stream = pipe_ctx->stream; + struct pipe_ctx *odm_pipe; + int opp_cnt = 1; + + ASSERT(dsc); + for (odm_pipe = pipe_ctx->next_odm_pipe; odm_pipe; odm_pipe = odm_pipe->next_odm_pipe) + opp_cnt++; + + if (enable) { + struct dsc_config dsc_cfg; + struct dsc_optc_config dsc_optc_cfg; + enum optc_dsc_mode optc_dsc_mode; + + /* Enable DSC hw block */ + dsc_cfg.pic_width = (stream->timing.h_addressable + stream->timing.h_border_left + stream->timing.h_border_right) / opp_cnt; + dsc_cfg.pic_height = stream->timing.v_addressable + stream->timing.v_border_top + stream->timing.v_border_bottom; + dsc_cfg.pixel_encoding = stream->timing.pixel_encoding; + dsc_cfg.color_depth = stream->timing.display_color_depth; + dsc_cfg.is_odm = pipe_ctx->next_odm_pipe ? true : false; + dsc_cfg.dc_dsc_cfg = stream->timing.dsc_cfg; + ASSERT(dsc_cfg.dc_dsc_cfg.num_slices_h % opp_cnt == 0); + dsc_cfg.dc_dsc_cfg.num_slices_h /= opp_cnt; + + dsc->funcs->dsc_set_config(dsc, &dsc_cfg, &dsc_optc_cfg); + dsc->funcs->dsc_enable(dsc, pipe_ctx->stream_res.opp->inst); + for (odm_pipe = pipe_ctx->next_odm_pipe; odm_pipe; odm_pipe = odm_pipe->next_odm_pipe) { + struct display_stream_compressor *odm_dsc = odm_pipe->stream_res.dsc; + + ASSERT(odm_dsc); + odm_dsc->funcs->dsc_set_config(odm_dsc, &dsc_cfg, &dsc_optc_cfg); + odm_dsc->funcs->dsc_enable(odm_dsc, odm_pipe->stream_res.opp->inst); + } + dsc_cfg.dc_dsc_cfg.num_slices_h *= opp_cnt; + dsc_cfg.pic_width *= opp_cnt; + + optc_dsc_mode = dsc_optc_cfg.is_pixel_format_444 ? OPTC_DSC_ENABLED_444 : OPTC_DSC_ENABLED_NATIVE_SUBSAMPLED; + + /* Enable DSC in OPTC */ + DC_LOG_DSC("Setting optc DSC config for tg instance %d:", pipe_ctx->stream_res.tg->inst); + pipe_ctx->stream_res.tg->funcs->set_dsc_config(pipe_ctx->stream_res.tg, + optc_dsc_mode, + dsc_optc_cfg.bytes_per_pixel, + dsc_optc_cfg.slice_width); + } else { + /* disable DSC in OPTC */ + pipe_ctx->stream_res.tg->funcs->set_dsc_config( + pipe_ctx->stream_res.tg, + OPTC_DSC_DISABLED, 0, 0); + + /* disable DSC block */ + dsc->funcs->dsc_disable(pipe_ctx->stream_res.dsc); + for (odm_pipe = pipe_ctx->next_odm_pipe; odm_pipe; odm_pipe = odm_pipe->next_odm_pipe) { + ASSERT(odm_pipe->stream_res.dsc); + odm_pipe->stream_res.dsc->funcs->dsc_disable(odm_pipe->stream_res.dsc); + } + } +} + +/* +* Given any pipe_ctx, return the total ODM combine factor, and optionally return +* the OPPids which are used +* */ +static unsigned int get_odm_config(struct pipe_ctx *pipe_ctx, unsigned int *opp_instances) +{ + unsigned int opp_count = 1; + struct pipe_ctx *odm_pipe; + + /* First get to the top pipe */ + for (odm_pipe = pipe_ctx; odm_pipe->prev_odm_pipe; odm_pipe = odm_pipe->prev_odm_pipe) + ; + + /* First pipe is always used */ + if (opp_instances) + opp_instances[0] = odm_pipe->stream_res.opp->inst; + + /* Find and count odm pipes, if any */ + for (odm_pipe = odm_pipe->next_odm_pipe; odm_pipe; odm_pipe = odm_pipe->next_odm_pipe) { + if (opp_instances) + opp_instances[opp_count] = odm_pipe->stream_res.opp->inst; + opp_count++; + } + + return opp_count; +} + +void dcn32_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx *pipe_ctx) +{ + struct pipe_ctx *odm_pipe; + int opp_cnt = 0; + int opp_inst[MAX_PIPES] = {0}; + bool rate_control_2x_pclk = (pipe_ctx->stream->timing.flags.INTERLACE || optc2_is_two_pixels_per_containter(&pipe_ctx->stream->timing)); + struct mpc_dwb_flow_control flow_control; + struct mpc *mpc = dc->res_pool->mpc; + int i; + + opp_cnt = get_odm_config(pipe_ctx, opp_inst); + + if (opp_cnt > 1) + pipe_ctx->stream_res.tg->funcs->set_odm_combine( + pipe_ctx->stream_res.tg, + opp_inst, opp_cnt, + &pipe_ctx->stream->timing); + else + pipe_ctx->stream_res.tg->funcs->set_odm_bypass( + pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing); + + rate_control_2x_pclk = rate_control_2x_pclk || opp_cnt > 1; + flow_control.flow_ctrl_mode = 0; + flow_control.flow_ctrl_cnt0 = 0x80; + flow_control.flow_ctrl_cnt1 = calc_mpc_flow_ctrl_cnt(pipe_ctx->stream, opp_cnt); + if (mpc->funcs->set_out_rate_control) { + for (i = 0; i < opp_cnt; ++i) { + mpc->funcs->set_out_rate_control( + mpc, opp_inst[i], + true, + rate_control_2x_pclk, + &flow_control); + } + } + + for (odm_pipe = pipe_ctx->next_odm_pipe; odm_pipe; odm_pipe = odm_pipe->next_odm_pipe) { + odm_pipe->stream_res.opp->funcs->opp_pipe_clock_control( + odm_pipe->stream_res.opp, + true); + } + + if (pipe_ctx->stream_res.dsc) { + struct pipe_ctx *current_pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[pipe_ctx->pipe_idx]; + + update_dsc_on_stream(pipe_ctx, pipe_ctx->stream->timing.flags.DSC); + + /* Check if no longer using pipe for ODM, then need to disconnect DSC for that pipe */ + if (!pipe_ctx->next_odm_pipe && current_pipe_ctx->next_odm_pipe && + current_pipe_ctx->next_odm_pipe->stream_res.dsc) { + struct display_stream_compressor *dsc = current_pipe_ctx->next_odm_pipe->stream_res.dsc; + /* disconnect DSC block from stream */ + dsc->funcs->dsc_disconnect(dsc); + } + } +} + +unsigned int dcn32_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsigned int *k1_div, unsigned int *k2_div) +{ + struct dc_stream_state *stream = pipe_ctx->stream; + unsigned int odm_combine_factor = 0; + bool two_pix_per_container = false; + + // For phantom pipes, use the same programming as the main pipes + if (pipe_ctx->stream->mall_stream_config.type == SUBVP_PHANTOM) { + stream = pipe_ctx->stream->mall_stream_config.paired_stream; + } + two_pix_per_container = optc2_is_two_pixels_per_containter(&stream->timing); + odm_combine_factor = get_odm_config(pipe_ctx, NULL); + + if (is_dp_128b_132b_signal(pipe_ctx)) { + *k1_div = PIXEL_RATE_DIV_BY_1; + *k2_div = PIXEL_RATE_DIV_BY_1; + } else if (dc_is_hdmi_tmds_signal(pipe_ctx->stream->signal) || dc_is_dvi_signal(pipe_ctx->stream->signal)) { + *k1_div = PIXEL_RATE_DIV_BY_1; + if (stream->timing.pixel_encoding == PIXEL_ENCODING_YCBCR420) + *k2_div = PIXEL_RATE_DIV_BY_2; + else + *k2_div = PIXEL_RATE_DIV_BY_4; + } else if (dc_is_dp_signal(pipe_ctx->stream->signal) || dc_is_virtual_signal(pipe_ctx->stream->signal)) { + if (two_pix_per_container) { + *k1_div = PIXEL_RATE_DIV_BY_1; + *k2_div = PIXEL_RATE_DIV_BY_2; + } else { + *k1_div = PIXEL_RATE_DIV_BY_1; + *k2_div = PIXEL_RATE_DIV_BY_4; + if ((odm_combine_factor == 2) || dcn32_is_dp_dig_pixel_rate_div_policy(pipe_ctx)) + *k2_div = PIXEL_RATE_DIV_BY_2; + } + } + + if ((*k1_div == PIXEL_RATE_DIV_NA) && (*k2_div == PIXEL_RATE_DIV_NA)) + ASSERT(false); + + return odm_combine_factor; +} + +void dcn32_set_pixels_per_cycle(struct pipe_ctx *pipe_ctx) +{ + uint32_t pix_per_cycle = 1; + uint32_t odm_combine_factor = 1; + + if (!pipe_ctx || !pipe_ctx->stream || !pipe_ctx->stream_res.stream_enc) + return; + + odm_combine_factor = get_odm_config(pipe_ctx, NULL); + if (optc2_is_two_pixels_per_containter(&pipe_ctx->stream->timing) || odm_combine_factor > 1 + || dcn32_is_dp_dig_pixel_rate_div_policy(pipe_ctx)) + pix_per_cycle = 2; + + if (pipe_ctx->stream_res.stream_enc->funcs->set_input_mode) + pipe_ctx->stream_res.stream_enc->funcs->set_input_mode(pipe_ctx->stream_res.stream_enc, + pix_per_cycle); +} + +void dcn32_unblank_stream(struct pipe_ctx *pipe_ctx, + struct dc_link_settings *link_settings) +{ + struct encoder_unblank_param params = {0}; + struct dc_stream_state *stream = pipe_ctx->stream; + struct dc_link *link = stream->link; + struct dce_hwseq *hws = link->dc->hwseq; + struct pipe_ctx *odm_pipe; + uint32_t pix_per_cycle = 1; + + params.opp_cnt = 1; + for (odm_pipe = pipe_ctx->next_odm_pipe; odm_pipe; odm_pipe = odm_pipe->next_odm_pipe) + params.opp_cnt++; + + /* only 3 items below are used by unblank */ + params.timing = pipe_ctx->stream->timing; + + params.link_settings.link_rate = link_settings->link_rate; + + if (is_dp_128b_132b_signal(pipe_ctx)) { + /* TODO - DP2.0 HW: Set ODM mode in dp hpo encoder here */ + pipe_ctx->stream_res.hpo_dp_stream_enc->funcs->dp_unblank( + pipe_ctx->stream_res.hpo_dp_stream_enc, + pipe_ctx->stream_res.tg->inst); + } else if (dc_is_dp_signal(pipe_ctx->stream->signal)) { + if (optc2_is_two_pixels_per_containter(&stream->timing) || params.opp_cnt > 1 + || dcn32_is_dp_dig_pixel_rate_div_policy(pipe_ctx)) { + params.timing.pix_clk_100hz /= 2; + pix_per_cycle = 2; + } + pipe_ctx->stream_res.stream_enc->funcs->dp_set_odm_combine( + pipe_ctx->stream_res.stream_enc, pix_per_cycle > 1); + pipe_ctx->stream_res.stream_enc->funcs->dp_unblank(link, pipe_ctx->stream_res.stream_enc, ¶ms); + } + + if (link->local_sink && link->local_sink->sink_signal == SIGNAL_TYPE_EDP) + hws->funcs.edp_backlight_control(link, true); +} + +bool dcn32_is_dp_dig_pixel_rate_div_policy(struct pipe_ctx *pipe_ctx) +{ + struct dc *dc = pipe_ctx->stream->ctx->dc; + + if (!is_h_timing_divisible_by_2(pipe_ctx->stream)) + return false; + + if (dc_is_dp_signal(pipe_ctx->stream->signal) && !is_dp_128b_132b_signal(pipe_ctx) && + dc->debug.enable_dp_dig_pixel_rate_div_policy) + return true; + return false; +} + +static void apply_symclk_on_tx_off_wa(struct dc_link *link) +{ + /* There are use cases where SYMCLK is referenced by OTG. For instance + * for TMDS signal, OTG relies SYMCLK even if TX video output is off. + * However current link interface will power off PHY when disabling link + * output. This will turn off SYMCLK generated by PHY. The workaround is + * to identify such case where SYMCLK is still in use by OTG when we + * power off PHY. When this is detected, we will temporarily power PHY + * back on and move PHY's SYMCLK state to SYMCLK_ON_TX_OFF by calling + * program_pix_clk interface. When OTG is disabled, we will then power + * off PHY by calling disable link output again. + * + * In future dcn generations, we plan to rework transmitter control + * interface so that we could have an option to set SYMCLK ON TX OFF + * state in one step without this workaround + */ + + struct dc *dc = link->ctx->dc; + struct pipe_ctx *pipe_ctx = NULL; + uint8_t i; + + if (link->phy_state.symclk_ref_cnts.otg > 0) { + for (i = 0; i < MAX_PIPES; i++) { + pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i]; + if (pipe_ctx->stream && pipe_ctx->stream->link == link && pipe_ctx->top_pipe == NULL) { + pipe_ctx->clock_source->funcs->program_pix_clk( + pipe_ctx->clock_source, + &pipe_ctx->stream_res.pix_clk_params, + dp_get_link_encoding_format(&pipe_ctx->link_config.dp_link_settings), + &pipe_ctx->pll_settings); + link->phy_state.symclk_state = SYMCLK_ON_TX_OFF; + break; + } + } + } +} + +void dcn32_disable_link_output(struct dc_link *link, + const struct link_resource *link_res, + enum signal_type signal) +{ + struct dc *dc = link->ctx->dc; + const struct link_hwss *link_hwss = get_link_hwss(link, link_res); + struct dmcu *dmcu = dc->res_pool->dmcu; + + if (signal == SIGNAL_TYPE_EDP && + link->dc->hwss.edp_backlight_control) + link->dc->hwss.edp_backlight_control(link, false); + else if (dmcu != NULL && dmcu->funcs->lock_phy) + dmcu->funcs->lock_phy(dmcu); + + link_hwss->disable_link_output(link, link_res, signal); + link->phy_state.symclk_state = SYMCLK_OFF_TX_OFF; + + if (signal == SIGNAL_TYPE_EDP && + link->dc->hwss.edp_backlight_control) + link->dc->hwss.edp_power_control(link, false); + else if (dmcu != NULL && dmcu->funcs->lock_phy) + dmcu->funcs->unlock_phy(dmcu); + + dp_source_sequence_trace(link, DPCD_SOURCE_SEQ_AFTER_DISABLE_LINK_PHY); + + apply_symclk_on_tx_off_wa(link); +} + +/* For SubVP the main pipe can have a viewport position change + * without a full update. In this case we must also update the + * viewport positions for the phantom pipe accordingly. + */ +void dcn32_update_phantom_vp_position(struct dc *dc, + struct dc_state *context, + struct pipe_ctx *phantom_pipe) +{ + uint32_t i; + struct dc_plane_state *phantom_plane = phantom_pipe->plane_state; + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; + + if (pipe->stream && pipe->stream->mall_stream_config.type == SUBVP_MAIN && + pipe->stream->mall_stream_config.paired_stream == phantom_pipe->stream) { + if (pipe->plane_state && pipe->plane_state->update_flags.bits.position_change) { + + phantom_plane->src_rect.x = pipe->plane_state->src_rect.x; + phantom_plane->src_rect.y = pipe->plane_state->src_rect.y; + phantom_plane->clip_rect.x = pipe->plane_state->clip_rect.x; + phantom_plane->dst_rect.x = pipe->plane_state->dst_rect.x; + phantom_plane->dst_rect.y = pipe->plane_state->dst_rect.y; + + phantom_pipe->plane_state->update_flags.bits.position_change = 1; + resource_build_scaling_params(phantom_pipe); + return; + } + } + } +} + +/* Treat the phantom pipe as if it needs to be fully enabled. + * If the pipe was previously in use but not phantom, it would + * have been disabled earlier in the sequence so we need to run + * the full enable sequence. + */ +void dcn32_apply_update_flags_for_phantom(struct pipe_ctx *phantom_pipe) +{ + phantom_pipe->update_flags.raw = 0; + if (phantom_pipe->stream && phantom_pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) { + if (phantom_pipe->stream && phantom_pipe->plane_state) { + phantom_pipe->update_flags.bits.enable = 1; + phantom_pipe->update_flags.bits.mpcc = 1; + phantom_pipe->update_flags.bits.dppclk = 1; + phantom_pipe->update_flags.bits.hubp_interdependent = 1; + phantom_pipe->update_flags.bits.hubp_rq_dlg_ttu = 1; + phantom_pipe->update_flags.bits.gamut_remap = 1; + phantom_pipe->update_flags.bits.scaler = 1; + phantom_pipe->update_flags.bits.viewport = 1; + phantom_pipe->update_flags.bits.det_size = 1; + if (!phantom_pipe->top_pipe && !phantom_pipe->prev_odm_pipe) { + phantom_pipe->update_flags.bits.odm = 1; + phantom_pipe->update_flags.bits.global_sync = 1; + } + } + } +} + +bool dcn32_dsc_pg_status( + struct dce_hwseq *hws, + unsigned int dsc_inst) +{ + uint32_t pwr_status = 0; + + switch (dsc_inst) { + case 0: /* DSC0 */ + REG_GET(DOMAIN16_PG_STATUS, + DOMAIN_PGFSM_PWR_STATUS, &pwr_status); + break; + case 1: /* DSC1 */ + + REG_GET(DOMAIN17_PG_STATUS, + DOMAIN_PGFSM_PWR_STATUS, &pwr_status); + break; + case 2: /* DSC2 */ + REG_GET(DOMAIN18_PG_STATUS, + DOMAIN_PGFSM_PWR_STATUS, &pwr_status); + break; + case 3: /* DSC3 */ + REG_GET(DOMAIN19_PG_STATUS, + DOMAIN_PGFSM_PWR_STATUS, &pwr_status); + break; + default: + BREAK_TO_DEBUGGER(); + break; + } + + return pwr_status == 0; +} + +void dcn32_update_dsc_pg(struct dc *dc, + struct dc_state *context, + bool safe_to_disable) +{ + struct dce_hwseq *hws = dc->hwseq; + int i; + + for (i = 0; i < dc->res_pool->res_cap->num_dsc; i++) { + struct display_stream_compressor *dsc = dc->res_pool->dscs[i]; + bool is_dsc_ungated = hws->funcs.dsc_pg_status(hws, dsc->inst); + + if (context->res_ctx.is_dsc_acquired[i]) { + if (!is_dsc_ungated) { + hws->funcs.dsc_pg_control(hws, dsc->inst, true); + } + } else if (safe_to_disable) { + if (is_dsc_ungated) { + hws->funcs.dsc_pg_control(hws, dsc->inst, false); + } + } + } +} |