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/amd/amdgpu/jpeg_v1_0.c | 613 +++++++++++++++++++++++++++++++++ 1 file changed, 613 insertions(+) create mode 100644 drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c (limited to 'drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c') diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c new file mode 100644 index 000000000..9360204da --- /dev/null +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c @@ -0,0 +1,613 @@ +/* + * Copyright 2019 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. + * + */ + +#include "amdgpu.h" +#include "amdgpu_jpeg.h" +#include "soc15.h" +#include "soc15d.h" +#include "vcn_v1_0.h" +#include "jpeg_v1_0.h" + +#include "vcn/vcn_1_0_offset.h" +#include "vcn/vcn_1_0_sh_mask.h" + +static void jpeg_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev); +static void jpeg_v1_0_set_irq_funcs(struct amdgpu_device *adev); +static void jpeg_v1_0_ring_begin_use(struct amdgpu_ring *ring); + +static void jpeg_v1_0_decode_ring_patch_wreg(struct amdgpu_ring *ring, uint32_t *ptr, uint32_t reg_offset, uint32_t val) +{ + struct amdgpu_device *adev = ring->adev; + ring->ring[(*ptr)++] = PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0); + if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) || + ((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) { + ring->ring[(*ptr)++] = 0; + ring->ring[(*ptr)++] = PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE0); + } else { + ring->ring[(*ptr)++] = reg_offset; + ring->ring[(*ptr)++] = PACKETJ(0, 0, 0, PACKETJ_TYPE0); + } + ring->ring[(*ptr)++] = val; +} + +static void jpeg_v1_0_decode_ring_set_patch_ring(struct amdgpu_ring *ring, uint32_t ptr) +{ + struct amdgpu_device *adev = ring->adev; + + uint32_t reg, reg_offset, val, mask, i; + + // 1st: program mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW + reg = SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW); + reg_offset = (reg << 2); + val = lower_32_bits(ring->gpu_addr); + jpeg_v1_0_decode_ring_patch_wreg(ring, &ptr, reg_offset, val); + + // 2nd: program mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH + reg = SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH); + reg_offset = (reg << 2); + val = upper_32_bits(ring->gpu_addr); + jpeg_v1_0_decode_ring_patch_wreg(ring, &ptr, reg_offset, val); + + // 3rd to 5th: issue MEM_READ commands + for (i = 0; i <= 2; i++) { + ring->ring[ptr++] = PACKETJ(0, 0, 0, PACKETJ_TYPE2); + ring->ring[ptr++] = 0; + } + + // 6th: program mmUVD_JRBC_RB_CNTL register to enable NO_FETCH and RPTR write ability + reg = SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_CNTL); + reg_offset = (reg << 2); + val = 0x13; + jpeg_v1_0_decode_ring_patch_wreg(ring, &ptr, reg_offset, val); + + // 7th: program mmUVD_JRBC_RB_REF_DATA + reg = SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_REF_DATA); + reg_offset = (reg << 2); + val = 0x1; + jpeg_v1_0_decode_ring_patch_wreg(ring, &ptr, reg_offset, val); + + // 8th: issue conditional register read mmUVD_JRBC_RB_CNTL + reg = SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_CNTL); + reg_offset = (reg << 2); + val = 0x1; + mask = 0x1; + + ring->ring[ptr++] = PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0); + ring->ring[ptr++] = 0x01400200; + ring->ring[ptr++] = PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0); + ring->ring[ptr++] = val; + ring->ring[ptr++] = PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0); + if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) || + ((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) { + ring->ring[ptr++] = 0; + ring->ring[ptr++] = PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE3); + } else { + ring->ring[ptr++] = reg_offset; + ring->ring[ptr++] = PACKETJ(0, 0, 0, PACKETJ_TYPE3); + } + ring->ring[ptr++] = mask; + + //9th to 21st: insert no-op + for (i = 0; i <= 12; i++) { + ring->ring[ptr++] = PACKETJ(0, 0, 0, PACKETJ_TYPE6); + ring->ring[ptr++] = 0; + } + + //22nd: reset mmUVD_JRBC_RB_RPTR + reg = SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_RPTR); + reg_offset = (reg << 2); + val = 0; + jpeg_v1_0_decode_ring_patch_wreg(ring, &ptr, reg_offset, val); + + //23rd: program mmUVD_JRBC_RB_CNTL to disable no_fetch + reg = SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_CNTL); + reg_offset = (reg << 2); + val = 0x12; + jpeg_v1_0_decode_ring_patch_wreg(ring, &ptr, reg_offset, val); +} + +/** + * jpeg_v1_0_decode_ring_get_rptr - get read pointer + * + * @ring: amdgpu_ring pointer + * + * Returns the current hardware read pointer + */ +static uint64_t jpeg_v1_0_decode_ring_get_rptr(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + + return RREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_RPTR); +} + +/** + * jpeg_v1_0_decode_ring_get_wptr - get write pointer + * + * @ring: amdgpu_ring pointer + * + * Returns the current hardware write pointer + */ +static uint64_t jpeg_v1_0_decode_ring_get_wptr(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + + return RREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_WPTR); +} + +/** + * jpeg_v1_0_decode_ring_set_wptr - set write pointer + * + * @ring: amdgpu_ring pointer + * + * Commits the write pointer to the hardware + */ +static void jpeg_v1_0_decode_ring_set_wptr(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + + WREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_WPTR, lower_32_bits(ring->wptr)); +} + +/** + * jpeg_v1_0_decode_ring_insert_start - insert a start command + * + * @ring: amdgpu_ring pointer + * + * Write a start command to the ring. + */ +static void jpeg_v1_0_decode_ring_insert_start(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + + amdgpu_ring_write(ring, + PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0)); + amdgpu_ring_write(ring, 0x68e04); + + amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE0)); + amdgpu_ring_write(ring, 0x80010000); +} + +/** + * jpeg_v1_0_decode_ring_insert_end - insert a end command + * + * @ring: amdgpu_ring pointer + * + * Write a end command to the ring. + */ +static void jpeg_v1_0_decode_ring_insert_end(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + + amdgpu_ring_write(ring, + PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0)); + amdgpu_ring_write(ring, 0x68e04); + + amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE0)); + amdgpu_ring_write(ring, 0x00010000); +} + +/** + * jpeg_v1_0_decode_ring_emit_fence - emit an fence & trap command + * + * @ring: amdgpu_ring pointer + * @addr: address + * @seq: sequence number + * @flags: fence related flags + * + * Write a fence and a trap command to the ring. + */ +static void jpeg_v1_0_decode_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq, + unsigned flags) +{ + struct amdgpu_device *adev = ring->adev; + + WARN_ON(flags & AMDGPU_FENCE_FLAG_64BIT); + + amdgpu_ring_write(ring, + PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JPEG_GPCOM_DATA0), 0, 0, PACKETJ_TYPE0)); + amdgpu_ring_write(ring, seq); + + amdgpu_ring_write(ring, + PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JPEG_GPCOM_DATA1), 0, 0, PACKETJ_TYPE0)); + amdgpu_ring_write(ring, seq); + + amdgpu_ring_write(ring, + PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0)); + amdgpu_ring_write(ring, lower_32_bits(addr)); + + amdgpu_ring_write(ring, + PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0)); + amdgpu_ring_write(ring, upper_32_bits(addr)); + + amdgpu_ring_write(ring, + PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JPEG_GPCOM_CMD), 0, 0, PACKETJ_TYPE0)); + amdgpu_ring_write(ring, 0x8); + + amdgpu_ring_write(ring, + PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JPEG_GPCOM_CMD), 0, PACKETJ_CONDITION_CHECK0, PACKETJ_TYPE4)); + amdgpu_ring_write(ring, 0); + + amdgpu_ring_write(ring, + PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0)); + amdgpu_ring_write(ring, 0x01400200); + + amdgpu_ring_write(ring, + PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0)); + amdgpu_ring_write(ring, seq); + + amdgpu_ring_write(ring, + PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0)); + amdgpu_ring_write(ring, lower_32_bits(addr)); + + amdgpu_ring_write(ring, + PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0)); + amdgpu_ring_write(ring, upper_32_bits(addr)); + + amdgpu_ring_write(ring, + PACKETJ(0, 0, PACKETJ_CONDITION_CHECK3, PACKETJ_TYPE2)); + amdgpu_ring_write(ring, 0xffffffff); + + amdgpu_ring_write(ring, + PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0)); + amdgpu_ring_write(ring, 0x3fbc); + + amdgpu_ring_write(ring, + PACKETJ(0, 0, 0, PACKETJ_TYPE0)); + amdgpu_ring_write(ring, 0x1); + + /* emit trap */ + amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE7)); + amdgpu_ring_write(ring, 0); +} + +/** + * jpeg_v1_0_decode_ring_emit_ib - execute indirect buffer + * + * @ring: amdgpu_ring pointer + * @job: job to retrieve vmid from + * @ib: indirect buffer to execute + * @flags: unused + * + * Write ring commands to execute the indirect buffer. + */ +static void jpeg_v1_0_decode_ring_emit_ib(struct amdgpu_ring *ring, + struct amdgpu_job *job, + struct amdgpu_ib *ib, + uint32_t flags) +{ + struct amdgpu_device *adev = ring->adev; + unsigned vmid = AMDGPU_JOB_GET_VMID(job); + + amdgpu_ring_write(ring, + PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_IB_VMID), 0, 0, PACKETJ_TYPE0)); + amdgpu_ring_write(ring, (vmid | (vmid << 4))); + + amdgpu_ring_write(ring, + PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JPEG_VMID), 0, 0, PACKETJ_TYPE0)); + amdgpu_ring_write(ring, (vmid | (vmid << 4))); + + amdgpu_ring_write(ring, + PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_IB_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0)); + amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr)); + + amdgpu_ring_write(ring, + PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_IB_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0)); + amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr)); + + amdgpu_ring_write(ring, + PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_IB_SIZE), 0, 0, PACKETJ_TYPE0)); + amdgpu_ring_write(ring, ib->length_dw); + + amdgpu_ring_write(ring, + PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0)); + amdgpu_ring_write(ring, lower_32_bits(ring->gpu_addr)); + + amdgpu_ring_write(ring, + PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0)); + amdgpu_ring_write(ring, upper_32_bits(ring->gpu_addr)); + + amdgpu_ring_write(ring, + PACKETJ(0, 0, PACKETJ_CONDITION_CHECK0, PACKETJ_TYPE2)); + amdgpu_ring_write(ring, 0); + + amdgpu_ring_write(ring, + PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0)); + amdgpu_ring_write(ring, 0x01400200); + + amdgpu_ring_write(ring, + PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0)); + amdgpu_ring_write(ring, 0x2); + + amdgpu_ring_write(ring, + PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_STATUS), 0, PACKETJ_CONDITION_CHECK3, PACKETJ_TYPE3)); + amdgpu_ring_write(ring, 0x2); +} + +static void jpeg_v1_0_decode_ring_emit_reg_wait(struct amdgpu_ring *ring, + uint32_t reg, uint32_t val, + uint32_t mask) +{ + struct amdgpu_device *adev = ring->adev; + uint32_t reg_offset = (reg << 2); + + amdgpu_ring_write(ring, + PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0)); + amdgpu_ring_write(ring, 0x01400200); + + amdgpu_ring_write(ring, + PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0)); + amdgpu_ring_write(ring, val); + + amdgpu_ring_write(ring, + PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0)); + if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) || + ((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) { + amdgpu_ring_write(ring, 0); + amdgpu_ring_write(ring, + PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE3)); + } else { + amdgpu_ring_write(ring, reg_offset); + amdgpu_ring_write(ring, + PACKETJ(0, 0, 0, PACKETJ_TYPE3)); + } + amdgpu_ring_write(ring, mask); +} + +static void jpeg_v1_0_decode_ring_emit_vm_flush(struct amdgpu_ring *ring, + unsigned vmid, uint64_t pd_addr) +{ + struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub]; + uint32_t data0, data1, mask; + + pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr); + + /* wait for register write */ + data0 = hub->ctx0_ptb_addr_lo32 + vmid * hub->ctx_addr_distance; + data1 = lower_32_bits(pd_addr); + mask = 0xffffffff; + jpeg_v1_0_decode_ring_emit_reg_wait(ring, data0, data1, mask); +} + +static void jpeg_v1_0_decode_ring_emit_wreg(struct amdgpu_ring *ring, + uint32_t reg, uint32_t val) +{ + struct amdgpu_device *adev = ring->adev; + uint32_t reg_offset = (reg << 2); + + amdgpu_ring_write(ring, + PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0)); + if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) || + ((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) { + amdgpu_ring_write(ring, 0); + amdgpu_ring_write(ring, + PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE0)); + } else { + amdgpu_ring_write(ring, reg_offset); + amdgpu_ring_write(ring, + PACKETJ(0, 0, 0, PACKETJ_TYPE0)); + } + amdgpu_ring_write(ring, val); +} + +static void jpeg_v1_0_decode_ring_nop(struct amdgpu_ring *ring, uint32_t count) +{ + int i; + + WARN_ON(ring->wptr % 2 || count % 2); + + for (i = 0; i < count / 2; i++) { + amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE6)); + amdgpu_ring_write(ring, 0); + } +} + +static int jpeg_v1_0_set_interrupt_state(struct amdgpu_device *adev, + struct amdgpu_irq_src *source, + unsigned type, + enum amdgpu_interrupt_state state) +{ + return 0; +} + +static int jpeg_v1_0_process_interrupt(struct amdgpu_device *adev, + struct amdgpu_irq_src *source, + struct amdgpu_iv_entry *entry) +{ + DRM_DEBUG("IH: JPEG decode TRAP\n"); + + switch (entry->src_id) { + case 126: + amdgpu_fence_process(&adev->jpeg.inst->ring_dec); + break; + default: + DRM_ERROR("Unhandled interrupt: %d %d\n", + entry->src_id, entry->src_data[0]); + break; + } + + return 0; +} + +/** + * jpeg_v1_0_early_init - set function pointers + * + * @handle: amdgpu_device pointer + * + * Set ring and irq function pointers + */ +int jpeg_v1_0_early_init(void *handle) +{ + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + + adev->jpeg.num_jpeg_inst = 1; + + jpeg_v1_0_set_dec_ring_funcs(adev); + jpeg_v1_0_set_irq_funcs(adev); + + return 0; +} + +/** + * jpeg_v1_0_sw_init - sw init for JPEG block + * + * @handle: amdgpu_device pointer + * + */ +int jpeg_v1_0_sw_init(void *handle) +{ + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_ring *ring; + int r; + + /* JPEG TRAP */ + r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, 126, &adev->jpeg.inst->irq); + if (r) + return r; + + ring = &adev->jpeg.inst->ring_dec; + sprintf(ring->name, "jpeg_dec"); + r = amdgpu_ring_init(adev, ring, 512, &adev->jpeg.inst->irq, + 0, AMDGPU_RING_PRIO_DEFAULT, NULL); + if (r) + return r; + + adev->jpeg.internal.jpeg_pitch = adev->jpeg.inst->external.jpeg_pitch = + SOC15_REG_OFFSET(JPEG, 0, mmUVD_JPEG_PITCH); + + return 0; +} + +/** + * jpeg_v1_0_sw_fini - sw fini for JPEG block + * + * @handle: amdgpu_device pointer + * + * JPEG free up sw allocation + */ +void jpeg_v1_0_sw_fini(void *handle) +{ + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + + amdgpu_ring_fini(&adev->jpeg.inst[0].ring_dec); +} + +/** + * jpeg_v1_0_start - start JPEG block + * + * @adev: amdgpu_device pointer + * @mode: SPG or DPG mode + * + * Setup and start the JPEG block + */ +void jpeg_v1_0_start(struct amdgpu_device *adev, int mode) +{ + struct amdgpu_ring *ring = &adev->jpeg.inst->ring_dec; + + if (mode == 0) { + WREG32_SOC15(JPEG, 0, mmUVD_LMI_JRBC_RB_VMID, 0); + WREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_CNTL, UVD_JRBC_RB_CNTL__RB_NO_FETCH_MASK | + UVD_JRBC_RB_CNTL__RB_RPTR_WR_EN_MASK); + WREG32_SOC15(JPEG, 0, mmUVD_LMI_JRBC_RB_64BIT_BAR_LOW, lower_32_bits(ring->gpu_addr)); + WREG32_SOC15(JPEG, 0, mmUVD_LMI_JRBC_RB_64BIT_BAR_HIGH, upper_32_bits(ring->gpu_addr)); + WREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_RPTR, 0); + WREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_WPTR, 0); + WREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_CNTL, UVD_JRBC_RB_CNTL__RB_RPTR_WR_EN_MASK); + } + + /* initialize wptr */ + ring->wptr = RREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_WPTR); + + /* copy patch commands to the jpeg ring */ + jpeg_v1_0_decode_ring_set_patch_ring(ring, + (ring->wptr + ring->max_dw * amdgpu_sched_hw_submission)); +} + +static const struct amdgpu_ring_funcs jpeg_v1_0_decode_ring_vm_funcs = { + .type = AMDGPU_RING_TYPE_VCN_JPEG, + .align_mask = 0xf, + .nop = PACKET0(0x81ff, 0), + .support_64bit_ptrs = false, + .no_user_fence = true, + .vmhub = AMDGPU_MMHUB_0, + .extra_dw = 64, + .get_rptr = jpeg_v1_0_decode_ring_get_rptr, + .get_wptr = jpeg_v1_0_decode_ring_get_wptr, + .set_wptr = jpeg_v1_0_decode_ring_set_wptr, + .emit_frame_size = + 6 + 6 + /* hdp invalidate / flush */ + SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 + + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 + + 8 + /* jpeg_v1_0_decode_ring_emit_vm_flush */ + 26 + 26 + /* jpeg_v1_0_decode_ring_emit_fence x2 vm fence */ + 6, + .emit_ib_size = 22, /* jpeg_v1_0_decode_ring_emit_ib */ + .emit_ib = jpeg_v1_0_decode_ring_emit_ib, + .emit_fence = jpeg_v1_0_decode_ring_emit_fence, + .emit_vm_flush = jpeg_v1_0_decode_ring_emit_vm_flush, + .test_ring = amdgpu_jpeg_dec_ring_test_ring, + .test_ib = amdgpu_jpeg_dec_ring_test_ib, + .insert_nop = jpeg_v1_0_decode_ring_nop, + .insert_start = jpeg_v1_0_decode_ring_insert_start, + .insert_end = jpeg_v1_0_decode_ring_insert_end, + .pad_ib = amdgpu_ring_generic_pad_ib, + .begin_use = jpeg_v1_0_ring_begin_use, + .end_use = vcn_v1_0_ring_end_use, + .emit_wreg = jpeg_v1_0_decode_ring_emit_wreg, + .emit_reg_wait = jpeg_v1_0_decode_ring_emit_reg_wait, + .emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper, +}; + +static void jpeg_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev) +{ + adev->jpeg.inst->ring_dec.funcs = &jpeg_v1_0_decode_ring_vm_funcs; + DRM_INFO("JPEG decode is enabled in VM mode\n"); +} + +static const struct amdgpu_irq_src_funcs jpeg_v1_0_irq_funcs = { + .set = jpeg_v1_0_set_interrupt_state, + .process = jpeg_v1_0_process_interrupt, +}; + +static void jpeg_v1_0_set_irq_funcs(struct amdgpu_device *adev) +{ + adev->jpeg.inst->irq.funcs = &jpeg_v1_0_irq_funcs; +} + +static void jpeg_v1_0_ring_begin_use(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + bool set_clocks = !cancel_delayed_work_sync(&adev->vcn.idle_work); + int cnt = 0; + + mutex_lock(&adev->vcn.vcn1_jpeg1_workaround); + + if (amdgpu_fence_wait_empty(&adev->vcn.inst->ring_dec)) + DRM_ERROR("JPEG dec: vcn dec ring may not be empty\n"); + + for (cnt = 0; cnt < adev->vcn.num_enc_rings; cnt++) { + if (amdgpu_fence_wait_empty(&adev->vcn.inst->ring_enc[cnt])) + DRM_ERROR("JPEG dec: vcn enc ring[%d] may not be empty\n", cnt); + } + + vcn_v1_0_set_pg_for_begin_use(ring, set_clocks); +} -- cgit v1.2.3