aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/tegra/gr2d.c
diff options
context:
space:
mode:
authorLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
committerLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
commit5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch)
treecc5c2d0a898769fd59549594fedb3ee6f84e59a0 /drivers/gpu/drm/tegra/gr2d.c
downloadlinux-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/tegra/gr2d.c')
-rw-r--r--drivers/gpu/drm/tegra/gr2d.c407
1 files changed, 407 insertions, 0 deletions
diff --git a/drivers/gpu/drm/tegra/gr2d.c b/drivers/gpu/drm/tegra/gr2d.c
new file mode 100644
index 000000000..e3bb4c99e
--- /dev/null
+++ b/drivers/gpu/drm/tegra/gr2d.c
@@ -0,0 +1,407 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2012-2013, NVIDIA Corporation.
+ */
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/iommu.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/reset.h>
+
+#include <soc/tegra/common.h>
+
+#include "drm.h"
+#include "gem.h"
+#include "gr2d.h"
+
+enum {
+ RST_MC,
+ RST_GR2D,
+ RST_GR2D_MAX,
+};
+
+struct gr2d_soc {
+ unsigned int version;
+};
+
+struct gr2d {
+ struct tegra_drm_client client;
+ struct host1x_channel *channel;
+ struct clk *clk;
+
+ struct reset_control_bulk_data resets[RST_GR2D_MAX];
+ unsigned int nresets;
+
+ const struct gr2d_soc *soc;
+
+ DECLARE_BITMAP(addr_regs, GR2D_NUM_REGS);
+};
+
+static inline struct gr2d *to_gr2d(struct tegra_drm_client *client)
+{
+ return container_of(client, struct gr2d, client);
+}
+
+static int gr2d_init(struct host1x_client *client)
+{
+ struct tegra_drm_client *drm = host1x_to_drm_client(client);
+ struct drm_device *dev = dev_get_drvdata(client->host);
+ unsigned long flags = HOST1X_SYNCPT_HAS_BASE;
+ struct gr2d *gr2d = to_gr2d(drm);
+ int err;
+
+ gr2d->channel = host1x_channel_request(client);
+ if (!gr2d->channel)
+ return -ENOMEM;
+
+ client->syncpts[0] = host1x_syncpt_request(client, flags);
+ if (!client->syncpts[0]) {
+ err = -ENOMEM;
+ dev_err(client->dev, "failed to request syncpoint: %d\n", err);
+ goto put;
+ }
+
+ err = host1x_client_iommu_attach(client);
+ if (err < 0) {
+ dev_err(client->dev, "failed to attach to domain: %d\n", err);
+ goto free;
+ }
+
+ pm_runtime_enable(client->dev);
+ pm_runtime_use_autosuspend(client->dev);
+ pm_runtime_set_autosuspend_delay(client->dev, 200);
+
+ err = tegra_drm_register_client(dev->dev_private, drm);
+ if (err < 0) {
+ dev_err(client->dev, "failed to register client: %d\n", err);
+ goto disable_rpm;
+ }
+
+ return 0;
+
+disable_rpm:
+ pm_runtime_dont_use_autosuspend(client->dev);
+ pm_runtime_force_suspend(client->dev);
+
+ host1x_client_iommu_detach(client);
+free:
+ host1x_syncpt_put(client->syncpts[0]);
+put:
+ host1x_channel_put(gr2d->channel);
+ return err;
+}
+
+static int gr2d_exit(struct host1x_client *client)
+{
+ struct tegra_drm_client *drm = host1x_to_drm_client(client);
+ struct drm_device *dev = dev_get_drvdata(client->host);
+ struct tegra_drm *tegra = dev->dev_private;
+ struct gr2d *gr2d = to_gr2d(drm);
+ int err;
+
+ err = tegra_drm_unregister_client(tegra, drm);
+ if (err < 0)
+ return err;
+
+ pm_runtime_dont_use_autosuspend(client->dev);
+ pm_runtime_force_suspend(client->dev);
+
+ host1x_client_iommu_detach(client);
+ host1x_syncpt_put(client->syncpts[0]);
+ host1x_channel_put(gr2d->channel);
+
+ gr2d->channel = NULL;
+
+ return 0;
+}
+
+static const struct host1x_client_ops gr2d_client_ops = {
+ .init = gr2d_init,
+ .exit = gr2d_exit,
+};
+
+static int gr2d_open_channel(struct tegra_drm_client *client,
+ struct tegra_drm_context *context)
+{
+ struct gr2d *gr2d = to_gr2d(client);
+
+ context->channel = host1x_channel_get(gr2d->channel);
+ if (!context->channel)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static void gr2d_close_channel(struct tegra_drm_context *context)
+{
+ host1x_channel_put(context->channel);
+}
+
+static int gr2d_is_addr_reg(struct device *dev, u32 class, u32 offset)
+{
+ struct gr2d *gr2d = dev_get_drvdata(dev);
+
+ switch (class) {
+ case HOST1X_CLASS_HOST1X:
+ if (offset == 0x2b)
+ return 1;
+
+ break;
+
+ case HOST1X_CLASS_GR2D:
+ case HOST1X_CLASS_GR2D_SB:
+ if (offset >= GR2D_NUM_REGS)
+ break;
+
+ if (test_bit(offset, gr2d->addr_regs))
+ return 1;
+
+ break;
+ }
+
+ return 0;
+}
+
+static int gr2d_is_valid_class(u32 class)
+{
+ return (class == HOST1X_CLASS_GR2D ||
+ class == HOST1X_CLASS_GR2D_SB);
+}
+
+static const struct tegra_drm_client_ops gr2d_ops = {
+ .open_channel = gr2d_open_channel,
+ .close_channel = gr2d_close_channel,
+ .is_addr_reg = gr2d_is_addr_reg,
+ .is_valid_class = gr2d_is_valid_class,
+ .submit = tegra_drm_submit,
+};
+
+static const struct gr2d_soc tegra20_gr2d_soc = {
+ .version = 0x20,
+};
+
+static const struct gr2d_soc tegra30_gr2d_soc = {
+ .version = 0x30,
+};
+
+static const struct gr2d_soc tegra114_gr2d_soc = {
+ .version = 0x35,
+};
+
+static const struct of_device_id gr2d_match[] = {
+ { .compatible = "nvidia,tegra114-gr2d", .data = &tegra114_gr2d_soc },
+ { .compatible = "nvidia,tegra30-gr2d", .data = &tegra30_gr2d_soc },
+ { .compatible = "nvidia,tegra20-gr2d", .data = &tegra20_gr2d_soc },
+ { },
+};
+MODULE_DEVICE_TABLE(of, gr2d_match);
+
+static const u32 gr2d_addr_regs[] = {
+ GR2D_UA_BASE_ADDR,
+ GR2D_VA_BASE_ADDR,
+ GR2D_PAT_BASE_ADDR,
+ GR2D_DSTA_BASE_ADDR,
+ GR2D_DSTB_BASE_ADDR,
+ GR2D_DSTC_BASE_ADDR,
+ GR2D_SRCA_BASE_ADDR,
+ GR2D_SRCB_BASE_ADDR,
+ GR2D_PATBASE_ADDR,
+ GR2D_SRC_BASE_ADDR_SB,
+ GR2D_DSTA_BASE_ADDR_SB,
+ GR2D_DSTB_BASE_ADDR_SB,
+ GR2D_UA_BASE_ADDR_SB,
+ GR2D_VA_BASE_ADDR_SB,
+};
+
+static int gr2d_get_resets(struct device *dev, struct gr2d *gr2d)
+{
+ int err;
+
+ gr2d->resets[RST_MC].id = "mc";
+ gr2d->resets[RST_GR2D].id = "2d";
+ gr2d->nresets = RST_GR2D_MAX;
+
+ err = devm_reset_control_bulk_get_optional_exclusive_released(
+ dev, gr2d->nresets, gr2d->resets);
+ if (err) {
+ dev_err(dev, "failed to get reset: %d\n", err);
+ return err;
+ }
+
+ if (WARN_ON(!gr2d->resets[RST_GR2D].rstc))
+ return -ENOENT;
+
+ return 0;
+}
+
+static int gr2d_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct host1x_syncpt **syncpts;
+ struct gr2d *gr2d;
+ unsigned int i;
+ int err;
+
+ gr2d = devm_kzalloc(dev, sizeof(*gr2d), GFP_KERNEL);
+ if (!gr2d)
+ return -ENOMEM;
+
+ platform_set_drvdata(pdev, gr2d);
+
+ gr2d->soc = of_device_get_match_data(dev);
+
+ syncpts = devm_kzalloc(dev, sizeof(*syncpts), GFP_KERNEL);
+ if (!syncpts)
+ return -ENOMEM;
+
+ gr2d->clk = devm_clk_get(dev, NULL);
+ if (IS_ERR(gr2d->clk)) {
+ dev_err(dev, "cannot get clock\n");
+ return PTR_ERR(gr2d->clk);
+ }
+
+ err = gr2d_get_resets(dev, gr2d);
+ if (err)
+ return err;
+
+ INIT_LIST_HEAD(&gr2d->client.base.list);
+ gr2d->client.base.ops = &gr2d_client_ops;
+ gr2d->client.base.dev = dev;
+ gr2d->client.base.class = HOST1X_CLASS_GR2D;
+ gr2d->client.base.syncpts = syncpts;
+ gr2d->client.base.num_syncpts = 1;
+
+ INIT_LIST_HEAD(&gr2d->client.list);
+ gr2d->client.version = gr2d->soc->version;
+ gr2d->client.ops = &gr2d_ops;
+
+ err = devm_tegra_core_dev_init_opp_table_common(dev);
+ if (err)
+ return err;
+
+ err = host1x_client_register(&gr2d->client.base);
+ if (err < 0) {
+ dev_err(dev, "failed to register host1x client: %d\n", err);
+ return err;
+ }
+
+ /* initialize address register map */
+ for (i = 0; i < ARRAY_SIZE(gr2d_addr_regs); i++)
+ set_bit(gr2d_addr_regs[i], gr2d->addr_regs);
+
+ return 0;
+}
+
+static int gr2d_remove(struct platform_device *pdev)
+{
+ struct gr2d *gr2d = platform_get_drvdata(pdev);
+ int err;
+
+ err = host1x_client_unregister(&gr2d->client.base);
+ if (err < 0) {
+ dev_err(&pdev->dev, "failed to unregister host1x client: %d\n",
+ err);
+ return err;
+ }
+
+ return 0;
+}
+
+static int __maybe_unused gr2d_runtime_suspend(struct device *dev)
+{
+ struct gr2d *gr2d = dev_get_drvdata(dev);
+ int err;
+
+ host1x_channel_stop(gr2d->channel);
+ reset_control_bulk_release(gr2d->nresets, gr2d->resets);
+
+ /*
+ * GR2D module shouldn't be reset while hardware is idling, otherwise
+ * host1x's cmdproc will stuck on trying to access any G2 register
+ * after reset. GR2D module could be either hot-reset or reset after
+ * power-gating of the HEG partition. Hence we will put in reset only
+ * the memory client part of the module, the HEG GENPD will take care
+ * of resetting GR2D module across power-gating.
+ *
+ * On Tegra20 there is no HEG partition, but it's okay to have
+ * undetermined h/w state since userspace is expected to reprogram
+ * the state on each job submission anyways.
+ */
+ err = reset_control_acquire(gr2d->resets[RST_MC].rstc);
+ if (err) {
+ dev_err(dev, "failed to acquire MC reset: %d\n", err);
+ goto acquire_reset;
+ }
+
+ err = reset_control_assert(gr2d->resets[RST_MC].rstc);
+ reset_control_release(gr2d->resets[RST_MC].rstc);
+ if (err) {
+ dev_err(dev, "failed to assert MC reset: %d\n", err);
+ goto acquire_reset;
+ }
+
+ clk_disable_unprepare(gr2d->clk);
+
+ return 0;
+
+acquire_reset:
+ reset_control_bulk_acquire(gr2d->nresets, gr2d->resets);
+ reset_control_bulk_deassert(gr2d->nresets, gr2d->resets);
+
+ return err;
+}
+
+static int __maybe_unused gr2d_runtime_resume(struct device *dev)
+{
+ struct gr2d *gr2d = dev_get_drvdata(dev);
+ int err;
+
+ err = reset_control_bulk_acquire(gr2d->nresets, gr2d->resets);
+ if (err) {
+ dev_err(dev, "failed to acquire reset: %d\n", err);
+ return err;
+ }
+
+ err = clk_prepare_enable(gr2d->clk);
+ if (err) {
+ dev_err(dev, "failed to enable clock: %d\n", err);
+ goto release_reset;
+ }
+
+ usleep_range(2000, 4000);
+
+ /* this is a reset array which deasserts both 2D MC and 2D itself */
+ err = reset_control_bulk_deassert(gr2d->nresets, gr2d->resets);
+ if (err) {
+ dev_err(dev, "failed to deassert reset: %d\n", err);
+ goto disable_clk;
+ }
+
+ return 0;
+
+disable_clk:
+ clk_disable_unprepare(gr2d->clk);
+release_reset:
+ reset_control_bulk_release(gr2d->nresets, gr2d->resets);
+
+ return err;
+}
+
+static const struct dev_pm_ops tegra_gr2d_pm = {
+ SET_RUNTIME_PM_OPS(gr2d_runtime_suspend, gr2d_runtime_resume, NULL)
+ SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+ pm_runtime_force_resume)
+};
+
+struct platform_driver tegra_gr2d_driver = {
+ .driver = {
+ .name = "tegra-gr2d",
+ .of_match_table = gr2d_match,
+ .pm = &tegra_gr2d_pm,
+ },
+ .probe = gr2d_probe,
+ .remove = gr2d_remove,
+};