Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 664 insertions, 0 deletions

diff --git a/drivers/gpu/drm/vc4/vc4_render_cl.c b/drivers/gpu/drm/vc4/vc4_render_cl.c
new file mode 100644
index 000000000..1bda5010f
--- /dev/null
+++ b/drivers/gpu/drm/vc4/vc4_render_cl.c
@@ -0,0 +1,664 @@
+/*
+ * Copyright © 2014-2015 Broadcom
+ *
+ * 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 (including the next
+ * paragraph) 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 AUTHORS OR COPYRIGHT HOLDERS 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.
+ */
+
+/**
+ * DOC: Render command list generation
+ *
+ * In the V3D hardware, render command lists are what load and store
+ * tiles of a framebuffer and optionally call out to binner-generated
+ * command lists to do the 3D drawing for that tile.
+ *
+ * In the VC4 driver, render command list generation is performed by the
+ * kernel instead of userspace.  We do this because validating a
+ * user-submitted command list is hard to get right and has high CPU overhead,
+ * while the number of valid configurations for render command lists is
+ * actually fairly low.
+ */
+
+#include "uapi/drm/vc4_drm.h"
+#include "vc4_drv.h"
+#include "vc4_packet.h"
+
+struct vc4_rcl_setup {
+	struct drm_gem_dma_object *color_read;
+	struct drm_gem_dma_object *color_write;
+	struct drm_gem_dma_object *zs_read;
+	struct drm_gem_dma_object *zs_write;
+	struct drm_gem_dma_object *msaa_color_write;
+	struct drm_gem_dma_object *msaa_zs_write;
+
+	struct drm_gem_dma_object *rcl;
+	u32 next_offset;
+
+	u32 next_write_bo_index;
+};
+
+static inline void rcl_u8(struct vc4_rcl_setup *setup, u8 val)
+{
+	*(u8 *)(setup->rcl->vaddr + setup->next_offset) = val;
+	setup->next_offset += 1;
+}
+
+static inline void rcl_u16(struct vc4_rcl_setup *setup, u16 val)
+{
+	*(u16 *)(setup->rcl->vaddr + setup->next_offset) = val;
+	setup->next_offset += 2;
+}
+
+static inline void rcl_u32(struct vc4_rcl_setup *setup, u32 val)
+{
+	*(u32 *)(setup->rcl->vaddr + setup->next_offset) = val;
+	setup->next_offset += 4;
+}
+
+/*
+ * Emits a no-op STORE_TILE_BUFFER_GENERAL.
+ *
+ * If we emit a PACKET_TILE_COORDINATES, it must be followed by a store of
+ * some sort before another load is triggered.
+ */
+static void vc4_store_before_load(struct vc4_rcl_setup *setup)
+{
+	rcl_u8(setup, VC4_PACKET_STORE_TILE_BUFFER_GENERAL);
+	rcl_u16(setup,
+		VC4_SET_FIELD(VC4_LOADSTORE_TILE_BUFFER_NONE,
+			      VC4_LOADSTORE_TILE_BUFFER_BUFFER) |
+		VC4_STORE_TILE_BUFFER_DISABLE_COLOR_CLEAR |
+		VC4_STORE_TILE_BUFFER_DISABLE_ZS_CLEAR |
+		VC4_STORE_TILE_BUFFER_DISABLE_VG_MASK_CLEAR);
+	rcl_u32(setup, 0); /* no address, since we're in None mode */
+}
+
+/*
+ * Calculates the physical address of the start of a tile in a RCL surface.
+ *
+ * Unlike the other load/store packets,
+ * VC4_PACKET_LOAD/STORE_FULL_RES_TILE_BUFFER don't look at the tile
+ * coordinates packet, and instead just store to the address given.
+ */
+static uint32_t vc4_full_res_offset(struct vc4_exec_info *exec,
+				    struct drm_gem_dma_object *bo,
+				    struct drm_vc4_submit_rcl_surface *surf,
+				    uint8_t x, uint8_t y)
+{
+	return bo->dma_addr + surf->offset + VC4_TILE_BUFFER_SIZE *
+		(DIV_ROUND_UP(exec->args->width, 32) * y + x);
+}
+
+/*
+ * Emits a PACKET_TILE_COORDINATES if one isn't already pending.
+ *
+ * The tile coordinates packet triggers a pending load if there is one, are
+ * used for clipping during rendering, and determine where loads/stores happen
+ * relative to their base address.
+ */
+static void vc4_tile_coordinates(struct vc4_rcl_setup *setup,
+				 uint32_t x, uint32_t y)
+{
+	rcl_u8(setup, VC4_PACKET_TILE_COORDINATES);
+	rcl_u8(setup, x);
+	rcl_u8(setup, y);
+}
+
+static void emit_tile(struct vc4_exec_info *exec,
+		      struct vc4_rcl_setup *setup,
+		      uint8_t x, uint8_t y, bool first, bool last)
+{
+	struct drm_vc4_submit_cl *args = exec->args;
+	bool has_bin = args->bin_cl_size != 0;
+
+	/* Note that the load doesn't actually occur until the
+	 * tile coords packet is processed, and only one load
+	 * may be outstanding at a time.
+	 */
+	if (setup->color_read) {
+		if (args->color_read.flags &
+		    VC4_SUBMIT_RCL_SURFACE_READ_IS_FULL_RES) {
+			rcl_u8(setup, VC4_PACKET_LOAD_FULL_RES_TILE_BUFFER);
+			rcl_u32(setup,
+				vc4_full_res_offset(exec, setup->color_read,
+						    &args->color_read, x, y) |
+				VC4_LOADSTORE_FULL_RES_DISABLE_ZS);
+		} else {
+			rcl_u8(setup, VC4_PACKET_LOAD_TILE_BUFFER_GENERAL);
+			rcl_u16(setup, args->color_read.bits);
+			rcl_u32(setup, setup->color_read->dma_addr +
+				args->color_read.offset);
+		}
+	}
+
+	if (setup->zs_read) {
+		if (setup->color_read) {
+			/* Exec previous load. */
+			vc4_tile_coordinates(setup, x, y);
+			vc4_store_before_load(setup);
+		}
+
+		if (args->zs_read.flags &
+		    VC4_SUBMIT_RCL_SURFACE_READ_IS_FULL_RES) {
+			rcl_u8(setup, VC4_PACKET_LOAD_FULL_RES_TILE_BUFFER);
+			rcl_u32(setup,
+				vc4_full_res_offset(exec, setup->zs_read,
+						    &args->zs_read, x, y) |
+				VC4_LOADSTORE_FULL_RES_DISABLE_COLOR);
+		} else {
+			rcl_u8(setup, VC4_PACKET_LOAD_TILE_BUFFER_GENERAL);
+			rcl_u16(setup, args->zs_read.bits);
+			rcl_u32(setup, setup->zs_read->dma_addr +
+				args->zs_read.offset);
+		}
+	}
+
+	/* Clipping depends on tile coordinates having been
+	 * emitted, so we always need one here.
+	 */
+	vc4_tile_coordinates(setup, x, y);
+
+	/* Wait for the binner before jumping to the first
+	 * tile's lists.
+	 */
+	if (first && has_bin)
+		rcl_u8(setup, VC4_PACKET_WAIT_ON_SEMAPHORE);
+
+	if (has_bin) {
+		rcl_u8(setup, VC4_PACKET_BRANCH_TO_SUB_LIST);
+		rcl_u32(setup, (exec->tile_alloc_offset +
+				(y * exec->bin_tiles_x + x) * 32));
+	}
+
+	if (setup->msaa_color_write) {
+		bool last_tile_write = (!setup->msaa_zs_write &&
+					!setup->zs_write &&
+					!setup->color_write);
+		uint32_t bits = VC4_LOADSTORE_FULL_RES_DISABLE_ZS;
+
+		if (!last_tile_write)
+			bits |= VC4_LOADSTORE_FULL_RES_DISABLE_CLEAR_ALL;
+		else if (last)
+			bits |= VC4_LOADSTORE_FULL_RES_EOF;
+		rcl_u8(setup, VC4_PACKET_STORE_FULL_RES_TILE_BUFFER);
+		rcl_u32(setup,
+			vc4_full_res_offset(exec, setup->msaa_color_write,
+					    &args->msaa_color_write, x, y) |
+			bits);
+	}
+
+	if (setup->msaa_zs_write) {
+		bool last_tile_write = (!setup->zs_write &&
+					!setup->color_write);
+		uint32_t bits = VC4_LOADSTORE_FULL_RES_DISABLE_COLOR;
+
+		if (setup->msaa_color_write)
+			vc4_tile_coordinates(setup, x, y);
+		if (!last_tile_write)
+			bits |= VC4_LOADSTORE_FULL_RES_DISABLE_CLEAR_ALL;
+		else if (last)
+			bits |= VC4_LOADSTORE_FULL_RES_EOF;
+		rcl_u8(setup, VC4_PACKET_STORE_FULL_RES_TILE_BUFFER);
+		rcl_u32(setup,
+			vc4_full_res_offset(exec, setup->msaa_zs_write,
+					    &args->msaa_zs_write, x, y) |
+			bits);
+	}
+
+	if (setup->zs_write) {
+		bool last_tile_write = !setup->color_write;
+
+		if (setup->msaa_color_write || setup->msaa_zs_write)
+			vc4_tile_coordinates(setup, x, y);
+
+		rcl_u8(setup, VC4_PACKET_STORE_TILE_BUFFER_GENERAL);
+		rcl_u16(setup, args->zs_write.bits |
+			(last_tile_write ?
+			 0 : VC4_STORE_TILE_BUFFER_DISABLE_COLOR_CLEAR));
+		rcl_u32(setup,
+			(setup->zs_write->dma_addr + args->zs_write.offset) |
+			((last && last_tile_write) ?
+			 VC4_LOADSTORE_TILE_BUFFER_EOF : 0));
+	}
+
+	if (setup->color_write) {
+		if (setup->msaa_color_write || setup->msaa_zs_write ||
+		    setup->zs_write) {
+			vc4_tile_coordinates(setup, x, y);
+		}
+
+		if (last)
+			rcl_u8(setup, VC4_PACKET_STORE_MS_TILE_BUFFER_AND_EOF);
+		else
+			rcl_u8(setup, VC4_PACKET_STORE_MS_TILE_BUFFER);
+	}
+}
+
+static int vc4_create_rcl_bo(struct drm_device *dev, struct vc4_exec_info *exec,
+			     struct vc4_rcl_setup *setup)
+{
+	struct drm_vc4_submit_cl *args = exec->args;
+	bool has_bin = args->bin_cl_size != 0;
+	uint8_t min_x_tile = args->min_x_tile;
+	uint8_t min_y_tile = args->min_y_tile;
+	uint8_t max_x_tile = args->max_x_tile;
+	uint8_t max_y_tile = args->max_y_tile;
+	uint8_t xtiles = max_x_tile - min_x_tile + 1;
+	uint8_t ytiles = max_y_tile - min_y_tile + 1;
+	uint8_t xi, yi;
+	uint32_t size, loop_body_size;
+	bool positive_x = true;
+	bool positive_y = true;
+
+	if (args->flags & VC4_SUBMIT_CL_FIXED_RCL_ORDER) {
+		if (!(args->flags & VC4_SUBMIT_CL_RCL_ORDER_INCREASING_X))
+			positive_x = false;
+		if (!(args->flags & VC4_SUBMIT_CL_RCL_ORDER_INCREASING_Y))
+			positive_y = false;
+	}
+
+	size = VC4_PACKET_TILE_RENDERING_MODE_CONFIG_SIZE;
+	loop_body_size = VC4_PACKET_TILE_COORDINATES_SIZE;
+
+	if (args->flags & VC4_SUBMIT_CL_USE_CLEAR_COLOR) {
+		size += VC4_PACKET_CLEAR_COLORS_SIZE +
+			VC4_PACKET_TILE_COORDINATES_SIZE +
+			VC4_PACKET_STORE_TILE_BUFFER_GENERAL_SIZE;
+	}
+
+	if (setup->color_read) {
+		if (args->color_read.flags &
+		    VC4_SUBMIT_RCL_SURFACE_READ_IS_FULL_RES) {
+			loop_body_size += VC4_PACKET_LOAD_FULL_RES_TILE_BUFFER_SIZE;
+		} else {
+			loop_body_size += VC4_PACKET_LOAD_TILE_BUFFER_GENERAL_SIZE;
+		}
+	}
+	if (setup->zs_read) {
+		if (setup->color_read) {
+			loop_body_size += VC4_PACKET_TILE_COORDINATES_SIZE;
+			loop_body_size += VC4_PACKET_STORE_TILE_BUFFER_GENERAL_SIZE;
+		}
+
+		if (args->zs_read.flags &
+		    VC4_SUBMIT_RCL_SURFACE_READ_IS_FULL_RES) {
+			loop_body_size += VC4_PACKET_LOAD_FULL_RES_TILE_BUFFER_SIZE;
+		} else {
+			loop_body_size += VC4_PACKET_LOAD_TILE_BUFFER_GENERAL_SIZE;
+		}
+	}
+
+	if (has_bin) {
+		size += VC4_PACKET_WAIT_ON_SEMAPHORE_SIZE;
+		loop_body_size += VC4_PACKET_BRANCH_TO_SUB_LIST_SIZE;
+	}
+
+	if (setup->msaa_color_write)
+		loop_body_size += VC4_PACKET_STORE_FULL_RES_TILE_BUFFER_SIZE;
+	if (setup->msaa_zs_write)
+		loop_body_size += VC4_PACKET_STORE_FULL_RES_TILE_BUFFER_SIZE;
+
+	if (setup->zs_write)
+		loop_body_size += VC4_PACKET_STORE_TILE_BUFFER_GENERAL_SIZE;
+	if (setup->color_write)
+		loop_body_size += VC4_PACKET_STORE_MS_TILE_BUFFER_SIZE;
+
+	/* We need a VC4_PACKET_TILE_COORDINATES in between each store. */
+	loop_body_size += VC4_PACKET_TILE_COORDINATES_SIZE *
+		((setup->msaa_color_write != NULL) +
+		 (setup->msaa_zs_write != NULL) +
+		 (setup->color_write != NULL) +
+		 (setup->zs_write != NULL) - 1);
+
+	size += xtiles * ytiles * loop_body_size;
+
+	setup->rcl = &vc4_bo_create(dev, size, true, VC4_BO_TYPE_RCL)->base;
+	if (IS_ERR(setup->rcl))
+		return PTR_ERR(setup->rcl);
+	list_add_tail(&to_vc4_bo(&setup->rcl->base)->unref_head,
+		      &exec->unref_list);
+
+	/* The tile buffer gets cleared when the previous tile is stored.  If
+	 * the clear values changed between frames, then the tile buffer has
+	 * stale clear values in it, so we have to do a store in None mode (no
+	 * writes) so that we trigger the tile buffer clear.
+	 */
+	if (args->flags & VC4_SUBMIT_CL_USE_CLEAR_COLOR) {
+		rcl_u8(setup, VC4_PACKET_CLEAR_COLORS);
+		rcl_u32(setup, args->clear_color[0]);
+		rcl_u32(setup, args->clear_color[1]);
+		rcl_u32(setup, args->clear_z);
+		rcl_u8(setup, args->clear_s);
+
+		vc4_tile_coordinates(setup, 0, 0);
+
+		rcl_u8(setup, VC4_PACKET_STORE_TILE_BUFFER_GENERAL);
+		rcl_u16(setup, VC4_LOADSTORE_TILE_BUFFER_NONE);
+		rcl_u32(setup, 0); /* no address, since we're in None mode */
+	}
+
+	rcl_u8(setup, VC4_PACKET_TILE_RENDERING_MODE_CONFIG);
+	rcl_u32(setup,
+		(setup->color_write ? (setup->color_write->dma_addr +
+				       args->color_write.offset) :
+		 0));
+	rcl_u16(setup, args->width);
+	rcl_u16(setup, args->height);
+	rcl_u16(setup, args->color_write.bits);
+
+	for (yi = 0; yi < ytiles; yi++) {
+		int y = positive_y ? min_y_tile + yi : max_y_tile - yi;
+		for (xi = 0; xi < xtiles; xi++) {
+			int x = positive_x ? min_x_tile + xi : max_x_tile - xi;
+			bool first = (xi == 0 && yi == 0);
+			bool last = (xi == xtiles - 1 && yi == ytiles - 1);
+
+			emit_tile(exec, setup, x, y, first, last);
+		}
+	}
+
+	BUG_ON(setup->next_offset != size);
+	exec->ct1ca = setup->rcl->dma_addr;
+	exec->ct1ea = setup->rcl->dma_addr + setup->next_offset;
+
+	return 0;
+}
+
+static int vc4_full_res_bounds_check(struct vc4_exec_info *exec,
+				     struct drm_gem_dma_object *obj,
+				     struct drm_vc4_submit_rcl_surface *surf)
+{
+	struct drm_vc4_submit_cl *args = exec->args;
+	u32 render_tiles_stride = DIV_ROUND_UP(exec->args->width, 32);
+
+	if (surf->offset > obj->base.size) {
+		DRM_DEBUG("surface offset %d > BO size %zd\n",
+			  surf->offset, obj->base.size);
+		return -EINVAL;
+	}
+
+	if ((obj->base.size - surf->offset) / VC4_TILE_BUFFER_SIZE <
+	    render_tiles_stride * args->max_y_tile + args->max_x_tile) {
+		DRM_DEBUG("MSAA tile %d, %d out of bounds "
+			  "(bo size %zd, offset %d).\n",
+			  args->max_x_tile, args->max_y_tile,
+			  obj->base.size,
+			  surf->offset);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int vc4_rcl_msaa_surface_setup(struct vc4_exec_info *exec,
+				      struct drm_gem_dma_object **obj,
+				      struct drm_vc4_submit_rcl_surface *surf)
+{
+	if (surf->flags != 0 || surf->bits != 0) {
+		DRM_DEBUG("MSAA surface had nonzero flags/bits\n");
+		return -EINVAL;
+	}
+
+	if (surf->hindex == ~0)
+		return 0;
+
+	*obj = vc4_use_bo(exec, surf->hindex);
+	if (!*obj)
+		return -EINVAL;
+
+	exec->rcl_write_bo[exec->rcl_write_bo_count++] = *obj;
+
+	if (surf->offset & 0xf) {
+		DRM_DEBUG("MSAA write must be 16b aligned.\n");
+		return -EINVAL;
+	}
+
+	return vc4_full_res_bounds_check(exec, *obj, surf);
+}
+
+static int vc4_rcl_surface_setup(struct vc4_exec_info *exec,
+				 struct drm_gem_dma_object **obj,
+				 struct drm_vc4_submit_rcl_surface *surf,
+				 bool is_write)
+{
+	uint8_t tiling = VC4_GET_FIELD(surf->bits,
+				       VC4_LOADSTORE_TILE_BUFFER_TILING);
+	uint8_t buffer = VC4_GET_FIELD(surf->bits,
+				       VC4_LOADSTORE_TILE_BUFFER_BUFFER);
+	uint8_t format = VC4_GET_FIELD(surf->bits,
+				       VC4_LOADSTORE_TILE_BUFFER_FORMAT);
+	int cpp;
+	int ret;
+
+	if (surf->flags & ~VC4_SUBMIT_RCL_SURFACE_READ_IS_FULL_RES) {
+		DRM_DEBUG("Extra flags set\n");
+		return -EINVAL;
+	}
+
+	if (surf->hindex == ~0)
+		return 0;
+
+	*obj = vc4_use_bo(exec, surf->hindex);
+	if (!*obj)
+		return -EINVAL;
+
+	if (is_write)
+		exec->rcl_write_bo[exec->rcl_write_bo_count++] = *obj;
+
+	if (surf->flags & VC4_SUBMIT_RCL_SURFACE_READ_IS_FULL_RES) {
+		if (surf == &exec->args->zs_write) {
+			DRM_DEBUG("general zs write may not be a full-res.\n");
+			return -EINVAL;
+		}
+
+		if (surf->bits != 0) {
+			DRM_DEBUG("load/store general bits set with "
+				  "full res load/store.\n");
+			return -EINVAL;
+		}
+
+		ret = vc4_full_res_bounds_check(exec, *obj, surf);
+		if (ret)
+			return ret;
+
+		return 0;
+	}
+
+	if (surf->bits & ~(VC4_LOADSTORE_TILE_BUFFER_TILING_MASK |
+			   VC4_LOADSTORE_TILE_BUFFER_BUFFER_MASK |
+			   VC4_LOADSTORE_TILE_BUFFER_FORMAT_MASK)) {
+		DRM_DEBUG("Unknown bits in load/store: 0x%04x\n",
+			  surf->bits);
+		return -EINVAL;
+	}
+
+	if (tiling > VC4_TILING_FORMAT_LT) {
+		DRM_DEBUG("Bad tiling format\n");
+		return -EINVAL;
+	}
+
+	if (buffer == VC4_LOADSTORE_TILE_BUFFER_ZS) {
+		if (format != 0) {
+			DRM_DEBUG("No color format should be set for ZS\n");
+			return -EINVAL;
+		}
+		cpp = 4;
+	} else if (buffer == VC4_LOADSTORE_TILE_BUFFER_COLOR) {
+		switch (format) {
+		case VC4_LOADSTORE_TILE_BUFFER_BGR565:
+		case VC4_LOADSTORE_TILE_BUFFER_BGR565_DITHER:
+			cpp = 2;
+			break;
+		case VC4_LOADSTORE_TILE_BUFFER_RGBA8888:
+			cpp = 4;
+			break;
+		default:
+			DRM_DEBUG("Bad tile buffer format\n");
+			return -EINVAL;
+		}
+	} else {
+		DRM_DEBUG("Bad load/store buffer %d.\n", buffer);
+		return -EINVAL;
+	}
+
+	if (surf->offset & 0xf) {
+		DRM_DEBUG("load/store buffer must be 16b aligned.\n");
+		return -EINVAL;
+	}
+
+	if (!vc4_check_tex_size(exec, *obj, surf->offset, tiling,
+				exec->args->width, exec->args->height, cpp)) {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int
+vc4_rcl_render_config_surface_setup(struct vc4_exec_info *exec,
+				    struct vc4_rcl_setup *setup,
+				    struct drm_gem_dma_object **obj,
+				    struct drm_vc4_submit_rcl_surface *surf)
+{
+	uint8_t tiling = VC4_GET_FIELD(surf->bits,
+				       VC4_RENDER_CONFIG_MEMORY_FORMAT);
+	uint8_t format = VC4_GET_FIELD(surf->bits,
+				       VC4_RENDER_CONFIG_FORMAT);
+	int cpp;
+
+	if (surf->flags != 0) {
+		DRM_DEBUG("No flags supported on render config.\n");
+		return -EINVAL;
+	}
+
+	if (surf->bits & ~(VC4_RENDER_CONFIG_MEMORY_FORMAT_MASK |
+			   VC4_RENDER_CONFIG_FORMAT_MASK |
+			   VC4_RENDER_CONFIG_MS_MODE_4X |
+			   VC4_RENDER_CONFIG_DECIMATE_MODE_4X)) {
+		DRM_DEBUG("Unknown bits in render config: 0x%04x\n",
+			  surf->bits);
+		return -EINVAL;
+	}
+
+	if (surf->hindex == ~0)
+		return 0;
+
+	*obj = vc4_use_bo(exec, surf->hindex);
+	if (!*obj)
+		return -EINVAL;
+
+	exec->rcl_write_bo[exec->rcl_write_bo_count++] = *obj;
+
+	if (tiling > VC4_TILING_FORMAT_LT) {
+		DRM_DEBUG("Bad tiling format\n");
+		return -EINVAL;
+	}
+
+	switch (format) {
+	case VC4_RENDER_CONFIG_FORMAT_BGR565_DITHERED:
+	case VC4_RENDER_CONFIG_FORMAT_BGR565:
+		cpp = 2;
+		break;
+	case VC4_RENDER_CONFIG_FORMAT_RGBA8888:
+		cpp = 4;
+		break;
+	default:
+		DRM_DEBUG("Bad tile buffer format\n");
+		return -EINVAL;
+	}
+
+	if (!vc4_check_tex_size(exec, *obj, surf->offset, tiling,
+				exec->args->width, exec->args->height, cpp)) {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int vc4_get_rcl(struct drm_device *dev, struct vc4_exec_info *exec)
+{
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_rcl_setup setup = {0};
+	struct drm_vc4_submit_cl *args = exec->args;
+	bool has_bin = args->bin_cl_size != 0;
+	int ret;
+
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
+	if (args->min_x_tile > args->max_x_tile ||
+	    args->min_y_tile > args->max_y_tile) {
+		DRM_DEBUG("Bad render tile set (%d,%d)-(%d,%d)\n",
+			  args->min_x_tile, args->min_y_tile,
+			  args->max_x_tile, args->max_y_tile);
+		return -EINVAL;
+	}
+
+	if (has_bin &&
+	    (args->max_x_tile > exec->bin_tiles_x ||
+	     args->max_y_tile > exec->bin_tiles_y)) {
+		DRM_DEBUG("Render tiles (%d,%d) outside of bin config "
+			  "(%d,%d)\n",
+			  args->max_x_tile, args->max_y_tile,
+			  exec->bin_tiles_x, exec->bin_tiles_y);
+		return -EINVAL;
+	}
+
+	ret = vc4_rcl_render_config_surface_setup(exec, &setup,
+						  &setup.color_write,
+						  &args->color_write);
+	if (ret)
+		return ret;
+
+	ret = vc4_rcl_surface_setup(exec, &setup.color_read, &args->color_read,
+				    false);
+	if (ret)
+		return ret;
+
+	ret = vc4_rcl_surface_setup(exec, &setup.zs_read, &args->zs_read,
+				    false);
+	if (ret)
+		return ret;
+
+	ret = vc4_rcl_surface_setup(exec, &setup.zs_write, &args->zs_write,
+				    true);
+	if (ret)
+		return ret;
+
+	ret = vc4_rcl_msaa_surface_setup(exec, &setup.msaa_color_write,
+					 &args->msaa_color_write);
+	if (ret)
+		return ret;
+
+	ret = vc4_rcl_msaa_surface_setup(exec, &setup.msaa_zs_write,
+					 &args->msaa_zs_write);
+	if (ret)
+		return ret;
+
+	/* We shouldn't even have the job submitted to us if there's no
+	 * surface to write out.
+	 */
+	if (!setup.color_write && !setup.zs_write &&
+	    !setup.msaa_color_write && !setup.msaa_zs_write) {
+		DRM_DEBUG("RCL requires color or Z/S write\n");
+		return -EINVAL;
+	}
+
+	return vc4_create_rcl_bo(dev, exec, &setup);
+}