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/radeon/r200.c | 550 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 550 insertions(+) create mode 100644 drivers/gpu/drm/radeon/r200.c (limited to 'drivers/gpu/drm/radeon/r200.c') diff --git a/drivers/gpu/drm/radeon/r200.c b/drivers/gpu/drm/radeon/r200.c new file mode 100644 index 000000000..f5f2ffea5 --- /dev/null +++ b/drivers/gpu/drm/radeon/r200.c @@ -0,0 +1,550 @@ +/* + * Copyright 2008 Advanced Micro Devices, Inc. + * Copyright 2008 Red Hat Inc. + * Copyright 2009 Jerome Glisse. + * + * 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: Dave Airlie + * Alex Deucher + * Jerome Glisse + */ + +#include +#include "radeon_reg.h" +#include "radeon.h" +#include "radeon_asic.h" + +#include "r100d.h" +#include "r200_reg_safe.h" + +#include "r100_track.h" + +static int r200_get_vtx_size_0(uint32_t vtx_fmt_0) +{ + int vtx_size, i; + vtx_size = 2; + + if (vtx_fmt_0 & R200_VTX_Z0) + vtx_size++; + if (vtx_fmt_0 & R200_VTX_W0) + vtx_size++; + /* blend weight */ + if (vtx_fmt_0 & (0x7 << R200_VTX_WEIGHT_COUNT_SHIFT)) + vtx_size += (vtx_fmt_0 >> R200_VTX_WEIGHT_COUNT_SHIFT) & 0x7; + if (vtx_fmt_0 & R200_VTX_PV_MATRIX_SEL) + vtx_size++; + if (vtx_fmt_0 & R200_VTX_N0) + vtx_size += 3; + if (vtx_fmt_0 & R200_VTX_POINT_SIZE) + vtx_size++; + if (vtx_fmt_0 & R200_VTX_DISCRETE_FOG) + vtx_size++; + if (vtx_fmt_0 & R200_VTX_SHININESS_0) + vtx_size++; + if (vtx_fmt_0 & R200_VTX_SHININESS_1) + vtx_size++; + for (i = 0; i < 8; i++) { + int color_size = (vtx_fmt_0 >> (11 + 2*i)) & 0x3; + switch (color_size) { + case 0: break; + case 1: vtx_size++; break; + case 2: vtx_size += 3; break; + case 3: vtx_size += 4; break; + } + } + if (vtx_fmt_0 & R200_VTX_XY1) + vtx_size += 2; + if (vtx_fmt_0 & R200_VTX_Z1) + vtx_size++; + if (vtx_fmt_0 & R200_VTX_W1) + vtx_size++; + if (vtx_fmt_0 & R200_VTX_N1) + vtx_size += 3; + return vtx_size; +} + +struct radeon_fence *r200_copy_dma(struct radeon_device *rdev, + uint64_t src_offset, + uint64_t dst_offset, + unsigned num_gpu_pages, + struct dma_resv *resv) +{ + struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]; + struct radeon_fence *fence; + uint32_t size; + uint32_t cur_size; + int i, num_loops; + int r = 0; + + /* radeon pitch is /64 */ + size = num_gpu_pages << RADEON_GPU_PAGE_SHIFT; + num_loops = DIV_ROUND_UP(size, 0x1FFFFF); + r = radeon_ring_lock(rdev, ring, num_loops * 4 + 64); + if (r) { + DRM_ERROR("radeon: moving bo (%d).\n", r); + return ERR_PTR(r); + } + /* Must wait for 2D idle & clean before DMA or hangs might happen */ + radeon_ring_write(ring, PACKET0(RADEON_WAIT_UNTIL, 0)); + radeon_ring_write(ring, (1 << 16)); + for (i = 0; i < num_loops; i++) { + cur_size = size; + if (cur_size > 0x1FFFFF) { + cur_size = 0x1FFFFF; + } + size -= cur_size; + radeon_ring_write(ring, PACKET0(0x720, 2)); + radeon_ring_write(ring, src_offset); + radeon_ring_write(ring, dst_offset); + radeon_ring_write(ring, cur_size | (1 << 31) | (1 << 30)); + src_offset += cur_size; + dst_offset += cur_size; + } + radeon_ring_write(ring, PACKET0(RADEON_WAIT_UNTIL, 0)); + radeon_ring_write(ring, RADEON_WAIT_DMA_GUI_IDLE); + r = radeon_fence_emit(rdev, &fence, RADEON_RING_TYPE_GFX_INDEX); + if (r) { + radeon_ring_unlock_undo(rdev, ring); + return ERR_PTR(r); + } + radeon_ring_unlock_commit(rdev, ring, false); + return fence; +} + + +static int r200_get_vtx_size_1(uint32_t vtx_fmt_1) +{ + int vtx_size, i, tex_size; + vtx_size = 0; + for (i = 0; i < 6; i++) { + tex_size = (vtx_fmt_1 >> (i * 3)) & 0x7; + if (tex_size > 4) + continue; + vtx_size += tex_size; + } + return vtx_size; +} + +int r200_packet0_check(struct radeon_cs_parser *p, + struct radeon_cs_packet *pkt, + unsigned idx, unsigned reg) +{ + struct radeon_bo_list *reloc; + struct r100_cs_track *track; + volatile uint32_t *ib; + uint32_t tmp; + int r; + int i; + int face; + u32 tile_flags = 0; + u32 idx_value; + + ib = p->ib.ptr; + track = (struct r100_cs_track *)p->track; + idx_value = radeon_get_ib_value(p, idx); + switch (reg) { + case RADEON_CRTC_GUI_TRIG_VLINE: + r = r100_cs_packet_parse_vline(p); + if (r) { + DRM_ERROR("No reloc for ib[%d]=0x%04X\n", + idx, reg); + radeon_cs_dump_packet(p, pkt); + return r; + } + break; + /* FIXME: only allow PACKET3 blit? easier to check for out of + * range access */ + case RADEON_DST_PITCH_OFFSET: + case RADEON_SRC_PITCH_OFFSET: + r = r100_reloc_pitch_offset(p, pkt, idx, reg); + if (r) + return r; + break; + case RADEON_RB3D_DEPTHOFFSET: + r = radeon_cs_packet_next_reloc(p, &reloc, 0); + if (r) { + DRM_ERROR("No reloc for ib[%d]=0x%04X\n", + idx, reg); + radeon_cs_dump_packet(p, pkt); + return r; + } + track->zb.robj = reloc->robj; + track->zb.offset = idx_value; + track->zb_dirty = true; + ib[idx] = idx_value + ((u32)reloc->gpu_offset); + break; + case RADEON_RB3D_COLOROFFSET: + r = radeon_cs_packet_next_reloc(p, &reloc, 0); + if (r) { + DRM_ERROR("No reloc for ib[%d]=0x%04X\n", + idx, reg); + radeon_cs_dump_packet(p, pkt); + return r; + } + track->cb[0].robj = reloc->robj; + track->cb[0].offset = idx_value; + track->cb_dirty = true; + ib[idx] = idx_value + ((u32)reloc->gpu_offset); + break; + case R200_PP_TXOFFSET_0: + case R200_PP_TXOFFSET_1: + case R200_PP_TXOFFSET_2: + case R200_PP_TXOFFSET_3: + case R200_PP_TXOFFSET_4: + case R200_PP_TXOFFSET_5: + i = (reg - R200_PP_TXOFFSET_0) / 24; + r = radeon_cs_packet_next_reloc(p, &reloc, 0); + if (r) { + DRM_ERROR("No reloc for ib[%d]=0x%04X\n", + idx, reg); + radeon_cs_dump_packet(p, pkt); + return r; + } + if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) { + if (reloc->tiling_flags & RADEON_TILING_MACRO) + tile_flags |= R200_TXO_MACRO_TILE; + if (reloc->tiling_flags & RADEON_TILING_MICRO) + tile_flags |= R200_TXO_MICRO_TILE; + + tmp = idx_value & ~(0x7 << 2); + tmp |= tile_flags; + ib[idx] = tmp + ((u32)reloc->gpu_offset); + } else + ib[idx] = idx_value + ((u32)reloc->gpu_offset); + track->textures[i].robj = reloc->robj; + track->tex_dirty = true; + break; + case R200_PP_CUBIC_OFFSET_F1_0: + case R200_PP_CUBIC_OFFSET_F2_0: + case R200_PP_CUBIC_OFFSET_F3_0: + case R200_PP_CUBIC_OFFSET_F4_0: + case R200_PP_CUBIC_OFFSET_F5_0: + case R200_PP_CUBIC_OFFSET_F1_1: + case R200_PP_CUBIC_OFFSET_F2_1: + case R200_PP_CUBIC_OFFSET_F3_1: + case R200_PP_CUBIC_OFFSET_F4_1: + case R200_PP_CUBIC_OFFSET_F5_1: + case R200_PP_CUBIC_OFFSET_F1_2: + case R200_PP_CUBIC_OFFSET_F2_2: + case R200_PP_CUBIC_OFFSET_F3_2: + case R200_PP_CUBIC_OFFSET_F4_2: + case R200_PP_CUBIC_OFFSET_F5_2: + case R200_PP_CUBIC_OFFSET_F1_3: + case R200_PP_CUBIC_OFFSET_F2_3: + case R200_PP_CUBIC_OFFSET_F3_3: + case R200_PP_CUBIC_OFFSET_F4_3: + case R200_PP_CUBIC_OFFSET_F5_3: + case R200_PP_CUBIC_OFFSET_F1_4: + case R200_PP_CUBIC_OFFSET_F2_4: + case R200_PP_CUBIC_OFFSET_F3_4: + case R200_PP_CUBIC_OFFSET_F4_4: + case R200_PP_CUBIC_OFFSET_F5_4: + case R200_PP_CUBIC_OFFSET_F1_5: + case R200_PP_CUBIC_OFFSET_F2_5: + case R200_PP_CUBIC_OFFSET_F3_5: + case R200_PP_CUBIC_OFFSET_F4_5: + case R200_PP_CUBIC_OFFSET_F5_5: + i = (reg - R200_PP_TXOFFSET_0) / 24; + face = (reg - ((i * 24) + R200_PP_TXOFFSET_0)) / 4; + r = radeon_cs_packet_next_reloc(p, &reloc, 0); + if (r) { + DRM_ERROR("No reloc for ib[%d]=0x%04X\n", + idx, reg); + radeon_cs_dump_packet(p, pkt); + return r; + } + track->textures[i].cube_info[face - 1].offset = idx_value; + ib[idx] = idx_value + ((u32)reloc->gpu_offset); + track->textures[i].cube_info[face - 1].robj = reloc->robj; + track->tex_dirty = true; + break; + case RADEON_RE_WIDTH_HEIGHT: + track->maxy = ((idx_value >> 16) & 0x7FF); + track->cb_dirty = true; + track->zb_dirty = true; + break; + case RADEON_RB3D_COLORPITCH: + r = radeon_cs_packet_next_reloc(p, &reloc, 0); + if (r) { + DRM_ERROR("No reloc for ib[%d]=0x%04X\n", + idx, reg); + radeon_cs_dump_packet(p, pkt); + return r; + } + + if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) { + if (reloc->tiling_flags & RADEON_TILING_MACRO) + tile_flags |= RADEON_COLOR_TILE_ENABLE; + if (reloc->tiling_flags & RADEON_TILING_MICRO) + tile_flags |= RADEON_COLOR_MICROTILE_ENABLE; + + tmp = idx_value & ~(0x7 << 16); + tmp |= tile_flags; + ib[idx] = tmp; + } else + ib[idx] = idx_value; + + track->cb[0].pitch = idx_value & RADEON_COLORPITCH_MASK; + track->cb_dirty = true; + break; + case RADEON_RB3D_DEPTHPITCH: + track->zb.pitch = idx_value & RADEON_DEPTHPITCH_MASK; + track->zb_dirty = true; + break; + case RADEON_RB3D_CNTL: + switch ((idx_value >> RADEON_RB3D_COLOR_FORMAT_SHIFT) & 0x1f) { + case 7: + case 8: + case 9: + case 11: + case 12: + track->cb[0].cpp = 1; + break; + case 3: + case 4: + case 15: + track->cb[0].cpp = 2; + break; + case 6: + track->cb[0].cpp = 4; + break; + default: + DRM_ERROR("Invalid color buffer format (%d) !\n", + ((idx_value >> RADEON_RB3D_COLOR_FORMAT_SHIFT) & 0x1f)); + return -EINVAL; + } + if (idx_value & RADEON_DEPTHXY_OFFSET_ENABLE) { + DRM_ERROR("No support for depth xy offset in kms\n"); + return -EINVAL; + } + + track->z_enabled = !!(idx_value & RADEON_Z_ENABLE); + track->cb_dirty = true; + track->zb_dirty = true; + break; + case RADEON_RB3D_ZSTENCILCNTL: + switch (idx_value & 0xf) { + case 0: + track->zb.cpp = 2; + break; + case 2: + case 3: + case 4: + case 5: + case 9: + case 11: + track->zb.cpp = 4; + break; + default: + break; + } + track->zb_dirty = true; + break; + case RADEON_RB3D_ZPASS_ADDR: + r = radeon_cs_packet_next_reloc(p, &reloc, 0); + if (r) { + DRM_ERROR("No reloc for ib[%d]=0x%04X\n", + idx, reg); + radeon_cs_dump_packet(p, pkt); + return r; + } + ib[idx] = idx_value + ((u32)reloc->gpu_offset); + break; + case RADEON_PP_CNTL: + { + uint32_t temp = idx_value >> 4; + for (i = 0; i < track->num_texture; i++) + track->textures[i].enabled = !!(temp & (1 << i)); + track->tex_dirty = true; + } + break; + case RADEON_SE_VF_CNTL: + track->vap_vf_cntl = idx_value; + break; + case 0x210c: + /* VAP_VF_MAX_VTX_INDX */ + track->max_indx = idx_value & 0x00FFFFFFUL; + break; + case R200_SE_VTX_FMT_0: + track->vtx_size = r200_get_vtx_size_0(idx_value); + break; + case R200_SE_VTX_FMT_1: + track->vtx_size += r200_get_vtx_size_1(idx_value); + break; + case R200_PP_TXSIZE_0: + case R200_PP_TXSIZE_1: + case R200_PP_TXSIZE_2: + case R200_PP_TXSIZE_3: + case R200_PP_TXSIZE_4: + case R200_PP_TXSIZE_5: + i = (reg - R200_PP_TXSIZE_0) / 32; + track->textures[i].width = (idx_value & RADEON_TEX_USIZE_MASK) + 1; + track->textures[i].height = ((idx_value & RADEON_TEX_VSIZE_MASK) >> RADEON_TEX_VSIZE_SHIFT) + 1; + track->tex_dirty = true; + break; + case R200_PP_TXPITCH_0: + case R200_PP_TXPITCH_1: + case R200_PP_TXPITCH_2: + case R200_PP_TXPITCH_3: + case R200_PP_TXPITCH_4: + case R200_PP_TXPITCH_5: + i = (reg - R200_PP_TXPITCH_0) / 32; + track->textures[i].pitch = idx_value + 32; + track->tex_dirty = true; + break; + case R200_PP_TXFILTER_0: + case R200_PP_TXFILTER_1: + case R200_PP_TXFILTER_2: + case R200_PP_TXFILTER_3: + case R200_PP_TXFILTER_4: + case R200_PP_TXFILTER_5: + i = (reg - R200_PP_TXFILTER_0) / 32; + track->textures[i].num_levels = ((idx_value & R200_MAX_MIP_LEVEL_MASK) + >> R200_MAX_MIP_LEVEL_SHIFT); + tmp = (idx_value >> 23) & 0x7; + if (tmp == 2 || tmp == 6) + track->textures[i].roundup_w = false; + tmp = (idx_value >> 27) & 0x7; + if (tmp == 2 || tmp == 6) + track->textures[i].roundup_h = false; + track->tex_dirty = true; + break; + case R200_PP_TXMULTI_CTL_0: + case R200_PP_TXMULTI_CTL_1: + case R200_PP_TXMULTI_CTL_2: + case R200_PP_TXMULTI_CTL_3: + case R200_PP_TXMULTI_CTL_4: + case R200_PP_TXMULTI_CTL_5: + i = (reg - R200_PP_TXMULTI_CTL_0) / 32; + break; + case R200_PP_TXFORMAT_X_0: + case R200_PP_TXFORMAT_X_1: + case R200_PP_TXFORMAT_X_2: + case R200_PP_TXFORMAT_X_3: + case R200_PP_TXFORMAT_X_4: + case R200_PP_TXFORMAT_X_5: + i = (reg - R200_PP_TXFORMAT_X_0) / 32; + track->textures[i].txdepth = idx_value & 0x7; + tmp = (idx_value >> 16) & 0x3; + /* 2D, 3D, CUBE */ + switch (tmp) { + case 0: + case 3: + case 4: + case 5: + case 6: + case 7: + /* 1D/2D */ + track->textures[i].tex_coord_type = 0; + break; + case 1: + /* CUBE */ + track->textures[i].tex_coord_type = 2; + break; + case 2: + /* 3D */ + track->textures[i].tex_coord_type = 1; + break; + } + track->tex_dirty = true; + break; + case R200_PP_TXFORMAT_0: + case R200_PP_TXFORMAT_1: + case R200_PP_TXFORMAT_2: + case R200_PP_TXFORMAT_3: + case R200_PP_TXFORMAT_4: + case R200_PP_TXFORMAT_5: + i = (reg - R200_PP_TXFORMAT_0) / 32; + if (idx_value & R200_TXFORMAT_NON_POWER2) { + track->textures[i].use_pitch = 1; + } else { + track->textures[i].use_pitch = 0; + track->textures[i].width = 1 << ((idx_value & RADEON_TXFORMAT_WIDTH_MASK) >> RADEON_TXFORMAT_WIDTH_SHIFT); + track->textures[i].height = 1 << ((idx_value & RADEON_TXFORMAT_HEIGHT_MASK) >> RADEON_TXFORMAT_HEIGHT_SHIFT); + } + if (idx_value & R200_TXFORMAT_LOOKUP_DISABLE) + track->textures[i].lookup_disable = true; + switch ((idx_value & RADEON_TXFORMAT_FORMAT_MASK)) { + case R200_TXFORMAT_I8: + case R200_TXFORMAT_RGB332: + case R200_TXFORMAT_Y8: + track->textures[i].cpp = 1; + track->textures[i].compress_format = R100_TRACK_COMP_NONE; + break; + case R200_TXFORMAT_AI88: + case R200_TXFORMAT_ARGB1555: + case R200_TXFORMAT_RGB565: + case R200_TXFORMAT_ARGB4444: + case R200_TXFORMAT_VYUY422: + case R200_TXFORMAT_YVYU422: + case R200_TXFORMAT_LDVDU655: + case R200_TXFORMAT_DVDU88: + case R200_TXFORMAT_AVYU4444: + track->textures[i].cpp = 2; + track->textures[i].compress_format = R100_TRACK_COMP_NONE; + break; + case R200_TXFORMAT_ARGB8888: + case R200_TXFORMAT_RGBA8888: + case R200_TXFORMAT_ABGR8888: + case R200_TXFORMAT_BGR111110: + case R200_TXFORMAT_LDVDU8888: + track->textures[i].cpp = 4; + track->textures[i].compress_format = R100_TRACK_COMP_NONE; + break; + case R200_TXFORMAT_DXT1: + track->textures[i].cpp = 1; + track->textures[i].compress_format = R100_TRACK_COMP_DXT1; + break; + case R200_TXFORMAT_DXT23: + case R200_TXFORMAT_DXT45: + track->textures[i].cpp = 1; + track->textures[i].compress_format = R100_TRACK_COMP_DXT1; + break; + } + track->textures[i].cube_info[4].width = 1 << ((idx_value >> 16) & 0xf); + track->textures[i].cube_info[4].height = 1 << ((idx_value >> 20) & 0xf); + track->tex_dirty = true; + break; + case R200_PP_CUBIC_FACES_0: + case R200_PP_CUBIC_FACES_1: + case R200_PP_CUBIC_FACES_2: + case R200_PP_CUBIC_FACES_3: + case R200_PP_CUBIC_FACES_4: + case R200_PP_CUBIC_FACES_5: + tmp = idx_value; + i = (reg - R200_PP_CUBIC_FACES_0) / 32; + for (face = 0; face < 4; face++) { + track->textures[i].cube_info[face].width = 1 << ((tmp >> (face * 8)) & 0xf); + track->textures[i].cube_info[face].height = 1 << ((tmp >> ((face * 8) + 4)) & 0xf); + } + track->tex_dirty = true; + break; + default: + pr_err("Forbidden register 0x%04X in cs at %d\n", reg, idx); + return -EINVAL; + } + return 0; +} + +void r200_set_safe_registers(struct radeon_device *rdev) +{ + rdev->config.r100.reg_safe_bm = r200_reg_safe_bm; + rdev->config.r100.reg_safe_bm_size = ARRAY_SIZE(r200_reg_safe_bm); +} -- cgit v1.2.3