aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gk20a.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/nouveau/nvkm/subdev/volt/gk20a.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/nouveau/nvkm/subdev/volt/gk20a.c')
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/volt/gk20a.c186
1 files changed, 186 insertions, 0 deletions
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gk20a.c b/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gk20a.c
new file mode 100644
index 000000000..8c2faa964
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gk20a.c
@@ -0,0 +1,186 @@
+/*
+ * Copyright (c) 2014-2016, NVIDIA CORPORATION. All rights reserved.
+ *
+ * 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 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.
+ */
+#define gk20a_volt(p) container_of((p), struct gk20a_volt, base)
+#include "priv.h"
+
+#include <core/tegra.h>
+
+#include "gk20a.h"
+
+static const struct cvb_coef gk20a_cvb_coef[] = {
+ /* MHz, c0, c1, c2, c3, c4, c5 */
+ /* 72 */ { 1209886, -36468, 515, 417, -13123, 203},
+ /* 108 */ { 1130804, -27659, 296, 298, -10834, 221},
+ /* 180 */ { 1162871, -27110, 247, 238, -10681, 268},
+ /* 252 */ { 1220458, -28654, 247, 179, -10376, 298},
+ /* 324 */ { 1280953, -30204, 247, 119, -9766, 304},
+ /* 396 */ { 1344547, -31777, 247, 119, -8545, 292},
+ /* 468 */ { 1420168, -34227, 269, 60, -7172, 256},
+ /* 540 */ { 1490757, -35955, 274, 60, -5188, 197},
+ /* 612 */ { 1599112, -42583, 398, 0, -1831, 119},
+ /* 648 */ { 1366986, -16459, -274, 0, -3204, 72},
+ /* 684 */ { 1391884, -17078, -274, -60, -1526, 30},
+ /* 708 */ { 1415522, -17497, -274, -60, -458, 0},
+ /* 756 */ { 1464061, -18331, -274, -119, 1831, -72},
+ /* 804 */ { 1524225, -20064, -254, -119, 4272, -155},
+ /* 852 */ { 1608418, -21643, -269, 0, 763, -48},
+};
+
+/**
+ * cvb_mv = ((c2 * speedo / s_scale + c1) * speedo / s_scale + c0)
+ */
+static inline int
+gk20a_volt_get_cvb_voltage(int speedo, int s_scale, const struct cvb_coef *coef)
+{
+ int mv;
+
+ mv = DIV_ROUND_CLOSEST(coef->c2 * speedo, s_scale);
+ mv = DIV_ROUND_CLOSEST((mv + coef->c1) * speedo, s_scale) + coef->c0;
+ return mv;
+}
+
+/**
+ * cvb_t_mv =
+ * ((c2 * speedo / s_scale + c1) * speedo / s_scale + c0) +
+ * ((c3 * speedo / s_scale + c4 + c5 * T / t_scale) * T / t_scale)
+ */
+static inline int
+gk20a_volt_get_cvb_t_voltage(int speedo, int temp, int s_scale, int t_scale,
+ const struct cvb_coef *coef)
+{
+ int cvb_mv, mv;
+
+ cvb_mv = gk20a_volt_get_cvb_voltage(speedo, s_scale, coef);
+
+ mv = DIV_ROUND_CLOSEST(coef->c3 * speedo, s_scale) + coef->c4 +
+ DIV_ROUND_CLOSEST(coef->c5 * temp, t_scale);
+ mv = DIV_ROUND_CLOSEST(mv * temp, t_scale) + cvb_mv;
+ return mv;
+}
+
+static int
+gk20a_volt_calc_voltage(const struct cvb_coef *coef, int speedo)
+{
+ static const int v_scale = 1000;
+ int mv;
+
+ mv = gk20a_volt_get_cvb_t_voltage(speedo, -10, 100, 10, coef);
+ mv = DIV_ROUND_UP(mv, v_scale);
+
+ return mv * 1000;
+}
+
+static int
+gk20a_volt_vid_get(struct nvkm_volt *base)
+{
+ struct gk20a_volt *volt = gk20a_volt(base);
+ int i, uv;
+
+ uv = regulator_get_voltage(volt->vdd);
+
+ for (i = 0; i < volt->base.vid_nr; i++)
+ if (volt->base.vid[i].uv >= uv)
+ return i;
+
+ return -EINVAL;
+}
+
+static int
+gk20a_volt_vid_set(struct nvkm_volt *base, u8 vid)
+{
+ struct gk20a_volt *volt = gk20a_volt(base);
+ struct nvkm_subdev *subdev = &volt->base.subdev;
+
+ nvkm_debug(subdev, "set voltage as %duv\n", volt->base.vid[vid].uv);
+ return regulator_set_voltage(volt->vdd, volt->base.vid[vid].uv, 1200000);
+}
+
+static int
+gk20a_volt_set_id(struct nvkm_volt *base, u8 id, int condition)
+{
+ struct gk20a_volt *volt = gk20a_volt(base);
+ struct nvkm_subdev *subdev = &volt->base.subdev;
+ int prev_uv = regulator_get_voltage(volt->vdd);
+ int target_uv = volt->base.vid[id].uv;
+ int ret;
+
+ nvkm_debug(subdev, "prev=%d, target=%d, condition=%d\n",
+ prev_uv, target_uv, condition);
+ if (!condition ||
+ (condition < 0 && target_uv < prev_uv) ||
+ (condition > 0 && target_uv > prev_uv)) {
+ ret = gk20a_volt_vid_set(&volt->base, volt->base.vid[id].vid);
+ } else {
+ ret = 0;
+ }
+
+ return ret;
+}
+
+static const struct nvkm_volt_func
+gk20a_volt = {
+ .vid_get = gk20a_volt_vid_get,
+ .vid_set = gk20a_volt_vid_set,
+ .set_id = gk20a_volt_set_id,
+};
+
+int
+gk20a_volt_ctor(struct nvkm_device *device, enum nvkm_subdev_type type, int inst,
+ const struct cvb_coef *coefs, int nb_coefs,
+ int vmin, struct gk20a_volt *volt)
+{
+ struct nvkm_device_tegra *tdev = device->func->tegra(device);
+ int i, uv;
+
+ nvkm_volt_ctor(&gk20a_volt, device, type, inst, &volt->base);
+
+ uv = regulator_get_voltage(tdev->vdd);
+ nvkm_debug(&volt->base.subdev, "the default voltage is %duV\n", uv);
+
+ volt->vdd = tdev->vdd;
+
+ volt->base.vid_nr = nb_coefs;
+ for (i = 0; i < volt->base.vid_nr; i++) {
+ volt->base.vid[i].vid = i;
+ volt->base.vid[i].uv = max(
+ gk20a_volt_calc_voltage(&coefs[i], tdev->gpu_speedo),
+ vmin);
+ nvkm_debug(&volt->base.subdev, "%2d: vid=%d, uv=%d\n", i,
+ volt->base.vid[i].vid, volt->base.vid[i].uv);
+ }
+
+ return 0;
+}
+
+int
+gk20a_volt_new(struct nvkm_device *device, enum nvkm_subdev_type type, int inst, struct nvkm_volt **pvolt)
+{
+ struct gk20a_volt *volt;
+
+ volt = kzalloc(sizeof(*volt), GFP_KERNEL);
+ if (!volt)
+ return -ENOMEM;
+ *pvolt = &volt->base;
+
+ return gk20a_volt_ctor(device, type, inst, gk20a_cvb_coef,
+ ARRAY_SIZE(gk20a_cvb_coef), 0, volt);
+}