diff options
author | 2023-02-21 18:24:12 -0800 | |
---|---|---|
committer | 2023-02-21 18:24:12 -0800 | |
commit | 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch) | |
tree | cc5c2d0a898769fd59549594fedb3ee6f84e59a0 /drivers/gpu/drm/nouveau/nouveau_ttm.c | |
download | linux-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/nouveau_ttm.c')
-rw-r--r-- | drivers/gpu/drm/nouveau/nouveau_ttm.c | 367 |
1 files changed, 367 insertions, 0 deletions
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c new file mode 100644 index 000000000..1469a8891 --- /dev/null +++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c @@ -0,0 +1,367 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (c) 2007-2008 Tungsten Graphics, Inc., Cedar Park, TX., USA, + * Copyright (c) 2009 VMware, Inc., Palo Alto, CA., USA, + * + * 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, sub license, + * 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 NON-INFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS 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. + */ + +#include <linux/limits.h> +#include <linux/swiotlb.h> + +#include <drm/ttm/ttm_range_manager.h> + +#include "nouveau_drv.h" +#include "nouveau_gem.h" +#include "nouveau_mem.h" +#include "nouveau_ttm.h" + +#include <core/tegra.h> + +static void +nouveau_manager_del(struct ttm_resource_manager *man, + struct ttm_resource *reg) +{ + nouveau_mem_del(man, reg); +} + +static bool +nouveau_manager_intersects(struct ttm_resource_manager *man, + struct ttm_resource *res, + const struct ttm_place *place, + size_t size) +{ + return nouveau_mem_intersects(res, place, size); +} + +static bool +nouveau_manager_compatible(struct ttm_resource_manager *man, + struct ttm_resource *res, + const struct ttm_place *place, + size_t size) +{ + return nouveau_mem_compatible(res, place, size); +} + +static int +nouveau_vram_manager_new(struct ttm_resource_manager *man, + struct ttm_buffer_object *bo, + const struct ttm_place *place, + struct ttm_resource **res) +{ + struct nouveau_bo *nvbo = nouveau_bo(bo); + struct nouveau_drm *drm = nouveau_bdev(bo->bdev); + int ret; + + if (drm->client.device.info.ram_size == 0) + return -ENOMEM; + + ret = nouveau_mem_new(&drm->master, nvbo->kind, nvbo->comp, res); + if (ret) + return ret; + + ttm_resource_init(bo, place, *res); + + ret = nouveau_mem_vram(*res, nvbo->contig, nvbo->page); + if (ret) { + nouveau_mem_del(man, *res); + return ret; + } + + return 0; +} + +const struct ttm_resource_manager_func nouveau_vram_manager = { + .alloc = nouveau_vram_manager_new, + .free = nouveau_manager_del, + .intersects = nouveau_manager_intersects, + .compatible = nouveau_manager_compatible, +}; + +static int +nouveau_gart_manager_new(struct ttm_resource_manager *man, + struct ttm_buffer_object *bo, + const struct ttm_place *place, + struct ttm_resource **res) +{ + struct nouveau_bo *nvbo = nouveau_bo(bo); + struct nouveau_drm *drm = nouveau_bdev(bo->bdev); + int ret; + + ret = nouveau_mem_new(&drm->master, nvbo->kind, nvbo->comp, res); + if (ret) + return ret; + + ttm_resource_init(bo, place, *res); + (*res)->start = 0; + return 0; +} + +const struct ttm_resource_manager_func nouveau_gart_manager = { + .alloc = nouveau_gart_manager_new, + .free = nouveau_manager_del, + .intersects = nouveau_manager_intersects, + .compatible = nouveau_manager_compatible, +}; + +static int +nv04_gart_manager_new(struct ttm_resource_manager *man, + struct ttm_buffer_object *bo, + const struct ttm_place *place, + struct ttm_resource **res) +{ + struct nouveau_bo *nvbo = nouveau_bo(bo); + struct nouveau_drm *drm = nouveau_bdev(bo->bdev); + struct nouveau_mem *mem; + int ret; + + ret = nouveau_mem_new(&drm->master, nvbo->kind, nvbo->comp, res); + if (ret) + return ret; + + mem = nouveau_mem(*res); + ttm_resource_init(bo, place, *res); + ret = nvif_vmm_get(&mem->cli->vmm.vmm, PTES, false, 12, 0, + (long)(*res)->size, &mem->vma[0]); + if (ret) { + nouveau_mem_del(man, *res); + return ret; + } + + (*res)->start = mem->vma[0].addr >> PAGE_SHIFT; + return 0; +} + +const struct ttm_resource_manager_func nv04_gart_manager = { + .alloc = nv04_gart_manager_new, + .free = nouveau_manager_del, + .intersects = nouveau_manager_intersects, + .compatible = nouveau_manager_compatible, +}; + +static int +nouveau_ttm_init_host(struct nouveau_drm *drm, u8 kind) +{ + struct nvif_mmu *mmu = &drm->client.mmu; + int typei; + + typei = nvif_mmu_type(mmu, NVIF_MEM_HOST | NVIF_MEM_MAPPABLE | + kind | NVIF_MEM_COHERENT); + if (typei < 0) + return -ENOSYS; + + drm->ttm.type_host[!!kind] = typei; + + typei = nvif_mmu_type(mmu, NVIF_MEM_HOST | NVIF_MEM_MAPPABLE | kind); + if (typei < 0) + return -ENOSYS; + + drm->ttm.type_ncoh[!!kind] = typei; + return 0; +} + +static int +nouveau_ttm_init_vram(struct nouveau_drm *drm) +{ + if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA) { + struct ttm_resource_manager *man = kzalloc(sizeof(*man), GFP_KERNEL); + + if (!man) + return -ENOMEM; + + man->func = &nouveau_vram_manager; + + ttm_resource_manager_init(man, &drm->ttm.bdev, + drm->gem.vram_available >> PAGE_SHIFT); + ttm_set_driver_manager(&drm->ttm.bdev, TTM_PL_VRAM, man); + ttm_resource_manager_set_used(man, true); + return 0; + } else { + return ttm_range_man_init(&drm->ttm.bdev, TTM_PL_VRAM, false, + drm->gem.vram_available >> PAGE_SHIFT); + } +} + +static void +nouveau_ttm_fini_vram(struct nouveau_drm *drm) +{ + struct ttm_resource_manager *man = ttm_manager_type(&drm->ttm.bdev, TTM_PL_VRAM); + + if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA) { + ttm_resource_manager_set_used(man, false); + ttm_resource_manager_evict_all(&drm->ttm.bdev, man); + ttm_resource_manager_cleanup(man); + ttm_set_driver_manager(&drm->ttm.bdev, TTM_PL_VRAM, NULL); + kfree(man); + } else + ttm_range_man_fini(&drm->ttm.bdev, TTM_PL_VRAM); +} + +static int +nouveau_ttm_init_gtt(struct nouveau_drm *drm) +{ + struct ttm_resource_manager *man; + unsigned long size_pages = drm->gem.gart_available >> PAGE_SHIFT; + const struct ttm_resource_manager_func *func = NULL; + + if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA) + func = &nouveau_gart_manager; + else if (!drm->agp.bridge) + func = &nv04_gart_manager; + else + return ttm_range_man_init(&drm->ttm.bdev, TTM_PL_TT, true, + size_pages); + + man = kzalloc(sizeof(*man), GFP_KERNEL); + if (!man) + return -ENOMEM; + + man->func = func; + man->use_tt = true; + ttm_resource_manager_init(man, &drm->ttm.bdev, size_pages); + ttm_set_driver_manager(&drm->ttm.bdev, TTM_PL_TT, man); + ttm_resource_manager_set_used(man, true); + return 0; +} + +static void +nouveau_ttm_fini_gtt(struct nouveau_drm *drm) +{ + struct ttm_resource_manager *man = ttm_manager_type(&drm->ttm.bdev, TTM_PL_TT); + + if (drm->client.device.info.family < NV_DEVICE_INFO_V0_TESLA && + drm->agp.bridge) + ttm_range_man_fini(&drm->ttm.bdev, TTM_PL_TT); + else { + ttm_resource_manager_set_used(man, false); + ttm_resource_manager_evict_all(&drm->ttm.bdev, man); + ttm_resource_manager_cleanup(man); + ttm_set_driver_manager(&drm->ttm.bdev, TTM_PL_TT, NULL); + kfree(man); + } +} + +int +nouveau_ttm_init(struct nouveau_drm *drm) +{ + struct nvkm_device *device = nvxx_device(&drm->client.device); + struct nvkm_pci *pci = device->pci; + struct nvif_mmu *mmu = &drm->client.mmu; + struct drm_device *dev = drm->dev; + bool need_swiotlb = false; + int typei, ret; + + ret = nouveau_ttm_init_host(drm, 0); + if (ret) + return ret; + + if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA && + drm->client.device.info.chipset != 0x50) { + ret = nouveau_ttm_init_host(drm, NVIF_MEM_KIND); + if (ret) + return ret; + } + + if (drm->client.device.info.platform != NV_DEVICE_INFO_V0_SOC && + drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA) { + typei = nvif_mmu_type(mmu, NVIF_MEM_VRAM | NVIF_MEM_MAPPABLE | + NVIF_MEM_KIND | + NVIF_MEM_COMP | + NVIF_MEM_DISP); + if (typei < 0) + return -ENOSYS; + + drm->ttm.type_vram = typei; + } else { + drm->ttm.type_vram = -1; + } + + if (pci && pci->agp.bridge) { + drm->agp.bridge = pci->agp.bridge; + drm->agp.base = pci->agp.base; + drm->agp.size = pci->agp.size; + drm->agp.cma = pci->agp.cma; + } + +#if IS_ENABLED(CONFIG_SWIOTLB) && IS_ENABLED(CONFIG_X86) + need_swiotlb = is_swiotlb_active(dev->dev); +#endif + + ret = ttm_device_init(&drm->ttm.bdev, &nouveau_bo_driver, drm->dev->dev, + dev->anon_inode->i_mapping, + dev->vma_offset_manager, need_swiotlb, + drm->client.mmu.dmabits <= 32); + if (ret) { + NV_ERROR(drm, "error initialising bo driver, %d\n", ret); + return ret; + } + + /* VRAM init */ + drm->gem.vram_available = drm->client.device.info.ram_user; + + arch_io_reserve_memtype_wc(device->func->resource_addr(device, 1), + device->func->resource_size(device, 1)); + + ret = nouveau_ttm_init_vram(drm); + if (ret) { + NV_ERROR(drm, "VRAM mm init failed, %d\n", ret); + return ret; + } + + drm->ttm.mtrr = arch_phys_wc_add(device->func->resource_addr(device, 1), + device->func->resource_size(device, 1)); + + /* GART init */ + if (!drm->agp.bridge) { + drm->gem.gart_available = drm->client.vmm.vmm.limit; + } else { + drm->gem.gart_available = drm->agp.size; + } + + ret = nouveau_ttm_init_gtt(drm); + if (ret) { + NV_ERROR(drm, "GART mm init failed, %d\n", ret); + return ret; + } + + mutex_init(&drm->ttm.io_reserve_mutex); + INIT_LIST_HEAD(&drm->ttm.io_reserve_lru); + + NV_INFO(drm, "VRAM: %d MiB\n", (u32)(drm->gem.vram_available >> 20)); + NV_INFO(drm, "GART: %d MiB\n", (u32)(drm->gem.gart_available >> 20)); + return 0; +} + +void +nouveau_ttm_fini(struct nouveau_drm *drm) +{ + struct nvkm_device *device = nvxx_device(&drm->client.device); + + nouveau_ttm_fini_vram(drm); + nouveau_ttm_fini_gtt(drm); + + ttm_device_fini(&drm->ttm.bdev); + + arch_phys_wc_del(drm->ttm.mtrr); + drm->ttm.mtrr = 0; + arch_io_free_memtype_wc(device->func->resource_addr(device, 1), + device->func->resource_size(device, 1)); + +} |