aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv40.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/instmem/nv40.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/instmem/nv40.c')
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv40.c263
1 files changed, 263 insertions, 0 deletions
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv40.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv40.c
new file mode 100644
index 000000000..6b462f960
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv40.c
@@ -0,0 +1,263 @@
+/*
+ * Copyright 2012 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs
+ */
+#define nv40_instmem(p) container_of((p), struct nv40_instmem, base)
+#include "priv.h"
+
+#include <core/ramht.h>
+#include <engine/gr/nv40.h>
+
+struct nv40_instmem {
+ struct nvkm_instmem base;
+ struct nvkm_mm heap;
+ void __iomem *iomem;
+};
+
+/******************************************************************************
+ * instmem object implementation
+ *****************************************************************************/
+#define nv40_instobj(p) container_of((p), struct nv40_instobj, base.memory)
+
+struct nv40_instobj {
+ struct nvkm_instobj base;
+ struct nv40_instmem *imem;
+ struct nvkm_mm_node *node;
+};
+
+static void
+nv40_instobj_wr32(struct nvkm_memory *memory, u64 offset, u32 data)
+{
+ struct nv40_instobj *iobj = nv40_instobj(memory);
+ iowrite32_native(data, iobj->imem->iomem + iobj->node->offset + offset);
+}
+
+static u32
+nv40_instobj_rd32(struct nvkm_memory *memory, u64 offset)
+{
+ struct nv40_instobj *iobj = nv40_instobj(memory);
+ return ioread32_native(iobj->imem->iomem + iobj->node->offset + offset);
+}
+
+static const struct nvkm_memory_ptrs
+nv40_instobj_ptrs = {
+ .rd32 = nv40_instobj_rd32,
+ .wr32 = nv40_instobj_wr32,
+};
+
+static void
+nv40_instobj_release(struct nvkm_memory *memory)
+{
+ wmb();
+}
+
+static void __iomem *
+nv40_instobj_acquire(struct nvkm_memory *memory)
+{
+ struct nv40_instobj *iobj = nv40_instobj(memory);
+ return iobj->imem->iomem + iobj->node->offset;
+}
+
+static u64
+nv40_instobj_size(struct nvkm_memory *memory)
+{
+ return nv40_instobj(memory)->node->length;
+}
+
+static u64
+nv40_instobj_addr(struct nvkm_memory *memory)
+{
+ return nv40_instobj(memory)->node->offset;
+}
+
+static enum nvkm_memory_target
+nv40_instobj_target(struct nvkm_memory *memory)
+{
+ return NVKM_MEM_TARGET_INST;
+}
+
+static void *
+nv40_instobj_dtor(struct nvkm_memory *memory)
+{
+ struct nv40_instobj *iobj = nv40_instobj(memory);
+ mutex_lock(&iobj->imem->base.mutex);
+ nvkm_mm_free(&iobj->imem->heap, &iobj->node);
+ mutex_unlock(&iobj->imem->base.mutex);
+ nvkm_instobj_dtor(&iobj->imem->base, &iobj->base);
+ return iobj;
+}
+
+static const struct nvkm_memory_func
+nv40_instobj_func = {
+ .dtor = nv40_instobj_dtor,
+ .target = nv40_instobj_target,
+ .size = nv40_instobj_size,
+ .addr = nv40_instobj_addr,
+ .acquire = nv40_instobj_acquire,
+ .release = nv40_instobj_release,
+};
+
+static int
+nv40_instobj_new(struct nvkm_instmem *base, u32 size, u32 align, bool zero,
+ struct nvkm_memory **pmemory)
+{
+ struct nv40_instmem *imem = nv40_instmem(base);
+ struct nv40_instobj *iobj;
+ int ret;
+
+ if (!(iobj = kzalloc(sizeof(*iobj), GFP_KERNEL)))
+ return -ENOMEM;
+ *pmemory = &iobj->base.memory;
+
+ nvkm_instobj_ctor(&nv40_instobj_func, &imem->base, &iobj->base);
+ iobj->base.memory.ptrs = &nv40_instobj_ptrs;
+ iobj->imem = imem;
+
+ mutex_lock(&imem->base.mutex);
+ ret = nvkm_mm_head(&imem->heap, 0, 1, size, size, align ? align : 1, &iobj->node);
+ mutex_unlock(&imem->base.mutex);
+ return ret;
+}
+
+/******************************************************************************
+ * instmem subdev implementation
+ *****************************************************************************/
+
+static u32
+nv40_instmem_rd32(struct nvkm_instmem *base, u32 addr)
+{
+ return ioread32_native(nv40_instmem(base)->iomem + addr);
+}
+
+static void
+nv40_instmem_wr32(struct nvkm_instmem *base, u32 addr, u32 data)
+{
+ iowrite32_native(data, nv40_instmem(base)->iomem + addr);
+}
+
+static int
+nv40_instmem_oneinit(struct nvkm_instmem *base)
+{
+ struct nv40_instmem *imem = nv40_instmem(base);
+ struct nvkm_device *device = imem->base.subdev.device;
+ int ret, vs;
+
+ /* PRAMIN aperture maps over the end of vram, reserve enough space
+ * to fit graphics contexts for every channel, the magics come
+ * from engine/gr/nv40.c
+ */
+ vs = hweight8((nvkm_rd32(device, 0x001540) & 0x0000ff00) >> 8);
+ if (device->chipset == 0x40) imem->base.reserved = 0x6aa0 * vs;
+ else if (device->chipset < 0x43) imem->base.reserved = 0x4f00 * vs;
+ else if (nv44_gr_class(device)) imem->base.reserved = 0x4980 * vs;
+ else imem->base.reserved = 0x4a40 * vs;
+ imem->base.reserved += 16 * 1024;
+ imem->base.reserved *= 32; /* per-channel */
+ imem->base.reserved += 512 * 1024; /* pci(e)gart table */
+ imem->base.reserved += 512 * 1024; /* object storage */
+ imem->base.reserved = round_up(imem->base.reserved, 4096);
+
+ ret = nvkm_mm_init(&imem->heap, 0, 0, imem->base.reserved, 1);
+ if (ret)
+ return ret;
+
+ /* 0x00000-0x10000: reserve for probable vbios image */
+ ret = nvkm_memory_new(device, NVKM_MEM_TARGET_INST, 0x10000, 0, false,
+ &imem->base.vbios);
+ if (ret)
+ return ret;
+
+ /* 0x10000-0x18000: reserve for RAMHT */
+ ret = nvkm_ramht_new(device, 0x08000, 0, NULL, &imem->base.ramht);
+ if (ret)
+ return ret;
+
+ /* 0x18000-0x18200: reserve for RAMRO
+ * 0x18200-0x20000: padding
+ */
+ ret = nvkm_memory_new(device, NVKM_MEM_TARGET_INST, 0x08000, 0, false,
+ &imem->base.ramro);
+ if (ret)
+ return ret;
+
+ /* 0x20000-0x21000: reserve for RAMFC
+ * 0x21000-0x40000: padding and some unknown crap
+ */
+ ret = nvkm_memory_new(device, NVKM_MEM_TARGET_INST, 0x20000, 0, true,
+ &imem->base.ramfc);
+ if (ret)
+ return ret;
+
+ return 0;
+}
+
+static void *
+nv40_instmem_dtor(struct nvkm_instmem *base)
+{
+ struct nv40_instmem *imem = nv40_instmem(base);
+ nvkm_memory_unref(&imem->base.ramfc);
+ nvkm_memory_unref(&imem->base.ramro);
+ nvkm_ramht_del(&imem->base.ramht);
+ nvkm_memory_unref(&imem->base.vbios);
+ nvkm_mm_fini(&imem->heap);
+ if (imem->iomem)
+ iounmap(imem->iomem);
+ return imem;
+}
+
+static const struct nvkm_instmem_func
+nv40_instmem = {
+ .dtor = nv40_instmem_dtor,
+ .oneinit = nv40_instmem_oneinit,
+ .rd32 = nv40_instmem_rd32,
+ .wr32 = nv40_instmem_wr32,
+ .memory_new = nv40_instobj_new,
+ .zero = false,
+};
+
+int
+nv40_instmem_new(struct nvkm_device *device, enum nvkm_subdev_type type, int inst,
+ struct nvkm_instmem **pimem)
+{
+ struct nv40_instmem *imem;
+ int bar;
+
+ if (!(imem = kzalloc(sizeof(*imem), GFP_KERNEL)))
+ return -ENOMEM;
+ nvkm_instmem_ctor(&nv40_instmem, device, type, inst, &imem->base);
+ *pimem = &imem->base;
+
+ /* map bar */
+ if (device->func->resource_size(device, 2))
+ bar = 2;
+ else
+ bar = 3;
+
+ imem->iomem = ioremap_wc(device->func->resource_addr(device, bar),
+ device->func->resource_size(device, bar));
+ if (!imem->iomem) {
+ nvkm_error(&imem->base.subdev, "unable to map PRAMIN BAR\n");
+ return -EFAULT;
+ }
+
+ return 0;
+}