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/qxl/qxl_kms.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/qxl/qxl_kms.c')
-rw-r--r-- | drivers/gpu/drm/qxl/qxl_kms.c | 322 |
1 files changed, 322 insertions, 0 deletions
diff --git a/drivers/gpu/drm/qxl/qxl_kms.c b/drivers/gpu/drm/qxl/qxl_kms.c new file mode 100644 index 000000000..dc3828db1 --- /dev/null +++ b/drivers/gpu/drm/qxl/qxl_kms.c @@ -0,0 +1,322 @@ +/* + * Copyright 2013 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: Dave Airlie + * Alon Levy + */ + +#include <linux/io-mapping.h> +#include <linux/pci.h> + +#include <drm/drm_drv.h> +#include <drm/drm_managed.h> +#include <drm/drm_probe_helper.h> + +#include "qxl_drv.h" +#include "qxl_object.h" + +static bool qxl_check_device(struct qxl_device *qdev) +{ + struct qxl_rom *rom = qdev->rom; + + if (rom->magic != 0x4f525851) { + DRM_ERROR("bad rom signature %x\n", rom->magic); + return false; + } + + DRM_INFO("Device Version %d.%d\n", rom->id, rom->update_id); + DRM_INFO("Compression level %d log level %d\n", rom->compression_level, + rom->log_level); + DRM_INFO("%d io pages at offset 0x%x\n", + rom->num_io_pages, rom->pages_offset); + DRM_INFO("%d byte draw area at offset 0x%x\n", + rom->surface0_area_size, rom->draw_area_offset); + + qdev->vram_size = rom->surface0_area_size; + DRM_INFO("RAM header offset: 0x%x\n", rom->ram_header_offset); + return true; +} + +static void setup_hw_slot(struct qxl_device *qdev, struct qxl_memslot *slot) +{ + qdev->ram_header->mem_slot.mem_start = slot->start_phys_addr; + qdev->ram_header->mem_slot.mem_end = slot->start_phys_addr + slot->size; + qxl_io_memslot_add(qdev, qdev->rom->slots_start + slot->index); +} + +static void setup_slot(struct qxl_device *qdev, + struct qxl_memslot *slot, + unsigned int slot_index, + const char *slot_name, + unsigned long start_phys_addr, + unsigned long size) +{ + uint64_t high_bits; + + slot->index = slot_index; + slot->name = slot_name; + slot->start_phys_addr = start_phys_addr; + slot->size = size; + + setup_hw_slot(qdev, slot); + + slot->generation = qdev->rom->slot_generation; + high_bits = (qdev->rom->slots_start + slot->index) + << qdev->rom->slot_gen_bits; + high_bits |= slot->generation; + high_bits <<= (64 - (qdev->rom->slot_gen_bits + qdev->rom->slot_id_bits)); + slot->high_bits = high_bits; + + DRM_INFO("slot %d (%s): base 0x%08lx, size 0x%08lx\n", + slot->index, slot->name, + (unsigned long)slot->start_phys_addr, + (unsigned long)slot->size); +} + +void qxl_reinit_memslots(struct qxl_device *qdev) +{ + setup_hw_slot(qdev, &qdev->main_slot); + setup_hw_slot(qdev, &qdev->surfaces_slot); +} + +static void qxl_gc_work(struct work_struct *work) +{ + struct qxl_device *qdev = container_of(work, struct qxl_device, gc_work); + + qxl_garbage_collect(qdev); +} + +int qxl_device_init(struct qxl_device *qdev, + struct pci_dev *pdev) +{ + int r, sb; + + pci_set_drvdata(pdev, &qdev->ddev); + + mutex_init(&qdev->gem.mutex); + mutex_init(&qdev->update_area_mutex); + mutex_init(&qdev->release_mutex); + mutex_init(&qdev->surf_evict_mutex); + qxl_gem_init(qdev); + + qdev->rom_base = pci_resource_start(pdev, 2); + qdev->rom_size = pci_resource_len(pdev, 2); + qdev->vram_base = pci_resource_start(pdev, 0); + qdev->io_base = pci_resource_start(pdev, 3); + + qdev->vram_mapping = io_mapping_create_wc(qdev->vram_base, pci_resource_len(pdev, 0)); + if (!qdev->vram_mapping) { + pr_err("Unable to create vram_mapping"); + return -ENOMEM; + } + + if (pci_resource_len(pdev, 4) > 0) { + /* 64bit surface bar present */ + sb = 4; + qdev->surfaceram_base = pci_resource_start(pdev, sb); + qdev->surfaceram_size = pci_resource_len(pdev, sb); + qdev->surface_mapping = + io_mapping_create_wc(qdev->surfaceram_base, + qdev->surfaceram_size); + } + if (qdev->surface_mapping == NULL) { + /* 64bit surface bar not present (or mapping failed) */ + sb = 1; + qdev->surfaceram_base = pci_resource_start(pdev, sb); + qdev->surfaceram_size = pci_resource_len(pdev, sb); + qdev->surface_mapping = + io_mapping_create_wc(qdev->surfaceram_base, + qdev->surfaceram_size); + if (!qdev->surface_mapping) { + pr_err("Unable to create surface_mapping"); + r = -ENOMEM; + goto vram_mapping_free; + } + } + + DRM_DEBUG_KMS("qxl: vram %llx-%llx(%dM %dk), surface %llx-%llx(%dM %dk, %s)\n", + (unsigned long long)qdev->vram_base, + (unsigned long long)pci_resource_end(pdev, 0), + (int)pci_resource_len(pdev, 0) / 1024 / 1024, + (int)pci_resource_len(pdev, 0) / 1024, + (unsigned long long)qdev->surfaceram_base, + (unsigned long long)pci_resource_end(pdev, sb), + (int)qdev->surfaceram_size / 1024 / 1024, + (int)qdev->surfaceram_size / 1024, + (sb == 4) ? "64bit" : "32bit"); + + qdev->rom = ioremap_wc(qdev->rom_base, qdev->rom_size); + if (!qdev->rom) { + pr_err("Unable to ioremap ROM\n"); + r = -ENOMEM; + goto surface_mapping_free; + } + + if (!qxl_check_device(qdev)) { + r = -ENODEV; + goto rom_unmap; + } + + r = qxl_bo_init(qdev); + if (r) { + DRM_ERROR("bo init failed %d\n", r); + goto rom_unmap; + } + + qdev->ram_header = ioremap_wc(qdev->vram_base + + qdev->rom->ram_header_offset, + sizeof(*qdev->ram_header)); + if (!qdev->ram_header) { + DRM_ERROR("Unable to ioremap RAM header\n"); + r = -ENOMEM; + goto bo_fini; + } + + qdev->command_ring = qxl_ring_create(&(qdev->ram_header->cmd_ring_hdr), + sizeof(struct qxl_command), + QXL_COMMAND_RING_SIZE, + qdev->io_base + QXL_IO_NOTIFY_CMD, + &qdev->display_event); + if (!qdev->command_ring) { + DRM_ERROR("Unable to create command ring\n"); + r = -ENOMEM; + goto ram_header_unmap; + } + + qdev->cursor_ring = qxl_ring_create( + &(qdev->ram_header->cursor_ring_hdr), + sizeof(struct qxl_command), + QXL_CURSOR_RING_SIZE, + qdev->io_base + QXL_IO_NOTIFY_CURSOR, + &qdev->cursor_event); + + if (!qdev->cursor_ring) { + DRM_ERROR("Unable to create cursor ring\n"); + r = -ENOMEM; + goto command_ring_free; + } + + qdev->release_ring = qxl_ring_create( + &(qdev->ram_header->release_ring_hdr), + sizeof(uint64_t), + QXL_RELEASE_RING_SIZE, 0, + NULL); + + if (!qdev->release_ring) { + DRM_ERROR("Unable to create release ring\n"); + r = -ENOMEM; + goto cursor_ring_free; + } + + idr_init_base(&qdev->release_idr, 1); + spin_lock_init(&qdev->release_idr_lock); + spin_lock_init(&qdev->release_lock); + + idr_init_base(&qdev->surf_id_idr, 1); + spin_lock_init(&qdev->surf_id_idr_lock); + + mutex_init(&qdev->async_io_mutex); + + /* reset the device into a known state - no memslots, no primary + * created, no surfaces. */ + qxl_io_reset(qdev); + + /* must initialize irq before first async io - slot creation */ + r = qxl_irq_init(qdev); + if (r) { + DRM_ERROR("Unable to init qxl irq\n"); + goto release_ring_free; + } + + /* + * Note that virtual is surface0. We rely on the single ioremap done + * before. + */ + setup_slot(qdev, &qdev->main_slot, 0, "main", + (unsigned long)qdev->vram_base, + (unsigned long)qdev->rom->ram_header_offset); + setup_slot(qdev, &qdev->surfaces_slot, 1, "surfaces", + (unsigned long)qdev->surfaceram_base, + (unsigned long)qdev->surfaceram_size); + + INIT_WORK(&qdev->gc_work, qxl_gc_work); + + return 0; + +release_ring_free: + qxl_ring_free(qdev->release_ring); +cursor_ring_free: + qxl_ring_free(qdev->cursor_ring); +command_ring_free: + qxl_ring_free(qdev->command_ring); +ram_header_unmap: + iounmap(qdev->ram_header); +bo_fini: + qxl_bo_fini(qdev); +rom_unmap: + iounmap(qdev->rom); +surface_mapping_free: + io_mapping_free(qdev->surface_mapping); +vram_mapping_free: + io_mapping_free(qdev->vram_mapping); + return r; +} + +void qxl_device_fini(struct qxl_device *qdev) +{ + int cur_idx; + + /* check if qxl_device_init() was successful (gc_work is initialized last) */ + if (!qdev->gc_work.func) + return; + + for (cur_idx = 0; cur_idx < 3; cur_idx++) { + if (!qdev->current_release_bo[cur_idx]) + continue; + qxl_bo_unpin(qdev->current_release_bo[cur_idx]); + qxl_bo_unref(&qdev->current_release_bo[cur_idx]); + qdev->current_release_bo_offset[cur_idx] = 0; + qdev->current_release_bo[cur_idx] = NULL; + } + + /* + * Ask host to release resources (+fill release ring), + * then wait for the release actually happening. + */ + qxl_io_notify_oom(qdev); + wait_event_timeout(qdev->release_event, + atomic_read(&qdev->release_count) == 0, + HZ); + flush_work(&qdev->gc_work); + qxl_surf_evict(qdev); + qxl_vram_evict(qdev); + + qxl_gem_fini(qdev); + qxl_bo_fini(qdev); + qxl_ring_free(qdev->command_ring); + qxl_ring_free(qdev->cursor_ring); + qxl_ring_free(qdev->release_ring); + io_mapping_free(qdev->surface_mapping); + io_mapping_free(qdev->vram_mapping); + iounmap(qdev->ram_header); + iounmap(qdev->rom); + qdev->rom = NULL; +} |