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/radeon/radeon_test.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/radeon/radeon_test.c')
-rw-r--r-- | drivers/gpu/drm/radeon/radeon_test.c | 580 |
1 files changed, 580 insertions, 0 deletions
diff --git a/drivers/gpu/drm/radeon/radeon_test.c b/drivers/gpu/drm/radeon/radeon_test.c new file mode 100644 index 000000000..a5e1d2139 --- /dev/null +++ b/drivers/gpu/drm/radeon/radeon_test.c @@ -0,0 +1,580 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright 2009 VMware, 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: Michel Dänzer + */ + +#include <drm/radeon_drm.h> +#include "radeon_reg.h" +#include "radeon.h" + +#define RADEON_TEST_COPY_BLIT 1 +#define RADEON_TEST_COPY_DMA 0 + + +/* Test BO GTT->VRAM and VRAM->GTT GPU copies across the whole GTT aperture */ +static void radeon_do_test_moves(struct radeon_device *rdev, int flag) +{ + struct radeon_bo *vram_obj = NULL; + struct radeon_bo **gtt_obj = NULL; + uint64_t gtt_addr, vram_addr; + unsigned n, size; + int i, r, ring; + + switch (flag) { + case RADEON_TEST_COPY_DMA: + ring = radeon_copy_dma_ring_index(rdev); + break; + case RADEON_TEST_COPY_BLIT: + ring = radeon_copy_blit_ring_index(rdev); + break; + default: + DRM_ERROR("Unknown copy method\n"); + return; + } + + size = 1024 * 1024; + + /* Number of tests = + * (Total GTT - IB pool - writeback page - ring buffers) / test size + */ + n = rdev->mc.gtt_size - rdev->gart_pin_size; + n /= size; + + gtt_obj = kcalloc(n, sizeof(*gtt_obj), GFP_KERNEL); + if (!gtt_obj) { + DRM_ERROR("Failed to allocate %d pointers\n", n); + r = 1; + goto out_cleanup; + } + + r = radeon_bo_create(rdev, size, PAGE_SIZE, true, RADEON_GEM_DOMAIN_VRAM, + 0, NULL, NULL, &vram_obj); + if (r) { + DRM_ERROR("Failed to create VRAM object\n"); + goto out_cleanup; + } + r = radeon_bo_reserve(vram_obj, false); + if (unlikely(r != 0)) + goto out_unref; + r = radeon_bo_pin(vram_obj, RADEON_GEM_DOMAIN_VRAM, &vram_addr); + if (r) { + DRM_ERROR("Failed to pin VRAM object\n"); + goto out_unres; + } + for (i = 0; i < n; i++) { + void *gtt_map, *vram_map; + void **gtt_start, **gtt_end; + void **vram_start, **vram_end; + struct radeon_fence *fence = NULL; + + r = radeon_bo_create(rdev, size, PAGE_SIZE, true, + RADEON_GEM_DOMAIN_GTT, 0, NULL, NULL, + gtt_obj + i); + if (r) { + DRM_ERROR("Failed to create GTT object %d\n", i); + goto out_lclean; + } + + r = radeon_bo_reserve(gtt_obj[i], false); + if (unlikely(r != 0)) + goto out_lclean_unref; + r = radeon_bo_pin(gtt_obj[i], RADEON_GEM_DOMAIN_GTT, >t_addr); + if (r) { + DRM_ERROR("Failed to pin GTT object %d\n", i); + goto out_lclean_unres; + } + + r = radeon_bo_kmap(gtt_obj[i], >t_map); + if (r) { + DRM_ERROR("Failed to map GTT object %d\n", i); + goto out_lclean_unpin; + } + + for (gtt_start = gtt_map, gtt_end = gtt_map + size; + gtt_start < gtt_end; + gtt_start++) + *gtt_start = gtt_start; + + radeon_bo_kunmap(gtt_obj[i]); + + if (ring == R600_RING_TYPE_DMA_INDEX) + fence = radeon_copy_dma(rdev, gtt_addr, vram_addr, + size / RADEON_GPU_PAGE_SIZE, + vram_obj->tbo.base.resv); + else + fence = radeon_copy_blit(rdev, gtt_addr, vram_addr, + size / RADEON_GPU_PAGE_SIZE, + vram_obj->tbo.base.resv); + if (IS_ERR(fence)) { + DRM_ERROR("Failed GTT->VRAM copy %d\n", i); + r = PTR_ERR(fence); + goto out_lclean_unpin; + } + + r = radeon_fence_wait(fence, false); + if (r) { + DRM_ERROR("Failed to wait for GTT->VRAM fence %d\n", i); + goto out_lclean_unpin; + } + + radeon_fence_unref(&fence); + + r = radeon_bo_kmap(vram_obj, &vram_map); + if (r) { + DRM_ERROR("Failed to map VRAM object after copy %d\n", i); + goto out_lclean_unpin; + } + + for (gtt_start = gtt_map, gtt_end = gtt_map + size, + vram_start = vram_map, vram_end = vram_map + size; + vram_start < vram_end; + gtt_start++, vram_start++) { + if (*vram_start != gtt_start) { + DRM_ERROR("Incorrect GTT->VRAM copy %d: Got 0x%p, " + "expected 0x%p (GTT/VRAM offset " + "0x%16llx/0x%16llx)\n", + i, *vram_start, gtt_start, + (unsigned long long) + (gtt_addr - rdev->mc.gtt_start + + (void*)gtt_start - gtt_map), + (unsigned long long) + (vram_addr - rdev->mc.vram_start + + (void*)gtt_start - gtt_map)); + radeon_bo_kunmap(vram_obj); + goto out_lclean_unpin; + } + *vram_start = vram_start; + } + + radeon_bo_kunmap(vram_obj); + + if (ring == R600_RING_TYPE_DMA_INDEX) + fence = radeon_copy_dma(rdev, vram_addr, gtt_addr, + size / RADEON_GPU_PAGE_SIZE, + vram_obj->tbo.base.resv); + else + fence = radeon_copy_blit(rdev, vram_addr, gtt_addr, + size / RADEON_GPU_PAGE_SIZE, + vram_obj->tbo.base.resv); + if (IS_ERR(fence)) { + DRM_ERROR("Failed VRAM->GTT copy %d\n", i); + r = PTR_ERR(fence); + goto out_lclean_unpin; + } + + r = radeon_fence_wait(fence, false); + if (r) { + DRM_ERROR("Failed to wait for VRAM->GTT fence %d\n", i); + goto out_lclean_unpin; + } + + radeon_fence_unref(&fence); + + r = radeon_bo_kmap(gtt_obj[i], >t_map); + if (r) { + DRM_ERROR("Failed to map GTT object after copy %d\n", i); + goto out_lclean_unpin; + } + + for (gtt_start = gtt_map, gtt_end = gtt_map + size, + vram_start = vram_map, vram_end = vram_map + size; + gtt_start < gtt_end; + gtt_start++, vram_start++) { + if (*gtt_start != vram_start) { + DRM_ERROR("Incorrect VRAM->GTT copy %d: Got 0x%p, " + "expected 0x%p (VRAM/GTT offset " + "0x%16llx/0x%16llx)\n", + i, *gtt_start, vram_start, + (unsigned long long) + (vram_addr - rdev->mc.vram_start + + (void*)vram_start - vram_map), + (unsigned long long) + (gtt_addr - rdev->mc.gtt_start + + (void*)vram_start - vram_map)); + radeon_bo_kunmap(gtt_obj[i]); + goto out_lclean_unpin; + } + } + + radeon_bo_kunmap(gtt_obj[i]); + + DRM_INFO("Tested GTT->VRAM and VRAM->GTT copy for GTT offset 0x%llx\n", + gtt_addr - rdev->mc.gtt_start); + continue; + +out_lclean_unpin: + radeon_bo_unpin(gtt_obj[i]); +out_lclean_unres: + radeon_bo_unreserve(gtt_obj[i]); +out_lclean_unref: + radeon_bo_unref(>t_obj[i]); +out_lclean: + for (--i; i >= 0; --i) { + radeon_bo_unpin(gtt_obj[i]); + radeon_bo_unreserve(gtt_obj[i]); + radeon_bo_unref(>t_obj[i]); + } + if (fence && !IS_ERR(fence)) + radeon_fence_unref(&fence); + break; + } + + radeon_bo_unpin(vram_obj); +out_unres: + radeon_bo_unreserve(vram_obj); +out_unref: + radeon_bo_unref(&vram_obj); +out_cleanup: + kfree(gtt_obj); + if (r) { + pr_warn("Error while testing BO move\n"); + } +} + +void radeon_test_moves(struct radeon_device *rdev) +{ + if (rdev->asic->copy.dma) + radeon_do_test_moves(rdev, RADEON_TEST_COPY_DMA); + if (rdev->asic->copy.blit) + radeon_do_test_moves(rdev, RADEON_TEST_COPY_BLIT); +} + +static int radeon_test_create_and_emit_fence(struct radeon_device *rdev, + struct radeon_ring *ring, + struct radeon_fence **fence) +{ + uint32_t handle = ring->idx ^ 0xdeafbeef; + int r; + + if (ring->idx == R600_RING_TYPE_UVD_INDEX) { + r = radeon_uvd_get_create_msg(rdev, ring->idx, handle, NULL); + if (r) { + DRM_ERROR("Failed to get dummy create msg\n"); + return r; + } + + r = radeon_uvd_get_destroy_msg(rdev, ring->idx, handle, fence); + if (r) { + DRM_ERROR("Failed to get dummy destroy msg\n"); + return r; + } + + } else if (ring->idx == TN_RING_TYPE_VCE1_INDEX || + ring->idx == TN_RING_TYPE_VCE2_INDEX) { + r = radeon_vce_get_create_msg(rdev, ring->idx, handle, NULL); + if (r) { + DRM_ERROR("Failed to get dummy create msg\n"); + return r; + } + + r = radeon_vce_get_destroy_msg(rdev, ring->idx, handle, fence); + if (r) { + DRM_ERROR("Failed to get dummy destroy msg\n"); + return r; + } + + } else { + r = radeon_ring_lock(rdev, ring, 64); + if (r) { + DRM_ERROR("Failed to lock ring A %d\n", ring->idx); + return r; + } + r = radeon_fence_emit(rdev, fence, ring->idx); + if (r) { + DRM_ERROR("Failed to emit fence\n"); + radeon_ring_unlock_undo(rdev, ring); + return r; + } + radeon_ring_unlock_commit(rdev, ring, false); + } + return 0; +} + +void radeon_test_ring_sync(struct radeon_device *rdev, + struct radeon_ring *ringA, + struct radeon_ring *ringB) +{ + struct radeon_fence *fence1 = NULL, *fence2 = NULL; + struct radeon_semaphore *semaphore = NULL; + int r; + + r = radeon_semaphore_create(rdev, &semaphore); + if (r) { + DRM_ERROR("Failed to create semaphore\n"); + goto out_cleanup; + } + + r = radeon_ring_lock(rdev, ringA, 64); + if (r) { + DRM_ERROR("Failed to lock ring A %d\n", ringA->idx); + goto out_cleanup; + } + radeon_semaphore_emit_wait(rdev, ringA->idx, semaphore); + radeon_ring_unlock_commit(rdev, ringA, false); + + r = radeon_test_create_and_emit_fence(rdev, ringA, &fence1); + if (r) + goto out_cleanup; + + r = radeon_ring_lock(rdev, ringA, 64); + if (r) { + DRM_ERROR("Failed to lock ring A %d\n", ringA->idx); + goto out_cleanup; + } + radeon_semaphore_emit_wait(rdev, ringA->idx, semaphore); + radeon_ring_unlock_commit(rdev, ringA, false); + + r = radeon_test_create_and_emit_fence(rdev, ringA, &fence2); + if (r) + goto out_cleanup; + + msleep(1000); + + if (radeon_fence_signaled(fence1)) { + DRM_ERROR("Fence 1 signaled without waiting for semaphore.\n"); + goto out_cleanup; + } + + r = radeon_ring_lock(rdev, ringB, 64); + if (r) { + DRM_ERROR("Failed to lock ring B %p\n", ringB); + goto out_cleanup; + } + radeon_semaphore_emit_signal(rdev, ringB->idx, semaphore); + radeon_ring_unlock_commit(rdev, ringB, false); + + r = radeon_fence_wait(fence1, false); + if (r) { + DRM_ERROR("Failed to wait for sync fence 1\n"); + goto out_cleanup; + } + + msleep(1000); + + if (radeon_fence_signaled(fence2)) { + DRM_ERROR("Fence 2 signaled without waiting for semaphore.\n"); + goto out_cleanup; + } + + r = radeon_ring_lock(rdev, ringB, 64); + if (r) { + DRM_ERROR("Failed to lock ring B %p\n", ringB); + goto out_cleanup; + } + radeon_semaphore_emit_signal(rdev, ringB->idx, semaphore); + radeon_ring_unlock_commit(rdev, ringB, false); + + r = radeon_fence_wait(fence2, false); + if (r) { + DRM_ERROR("Failed to wait for sync fence 1\n"); + goto out_cleanup; + } + +out_cleanup: + radeon_semaphore_free(rdev, &semaphore, NULL); + + if (fence1) + radeon_fence_unref(&fence1); + + if (fence2) + radeon_fence_unref(&fence2); + + if (r) + pr_warn("Error while testing ring sync (%d)\n", r); +} + +static void radeon_test_ring_sync2(struct radeon_device *rdev, + struct radeon_ring *ringA, + struct radeon_ring *ringB, + struct radeon_ring *ringC) +{ + struct radeon_fence *fenceA = NULL, *fenceB = NULL; + struct radeon_semaphore *semaphore = NULL; + bool sigA, sigB; + int i, r; + + r = radeon_semaphore_create(rdev, &semaphore); + if (r) { + DRM_ERROR("Failed to create semaphore\n"); + goto out_cleanup; + } + + r = radeon_ring_lock(rdev, ringA, 64); + if (r) { + DRM_ERROR("Failed to lock ring A %d\n", ringA->idx); + goto out_cleanup; + } + radeon_semaphore_emit_wait(rdev, ringA->idx, semaphore); + radeon_ring_unlock_commit(rdev, ringA, false); + + r = radeon_test_create_and_emit_fence(rdev, ringA, &fenceA); + if (r) + goto out_cleanup; + + r = radeon_ring_lock(rdev, ringB, 64); + if (r) { + DRM_ERROR("Failed to lock ring B %d\n", ringB->idx); + goto out_cleanup; + } + radeon_semaphore_emit_wait(rdev, ringB->idx, semaphore); + radeon_ring_unlock_commit(rdev, ringB, false); + r = radeon_test_create_and_emit_fence(rdev, ringB, &fenceB); + if (r) + goto out_cleanup; + + msleep(1000); + + if (radeon_fence_signaled(fenceA)) { + DRM_ERROR("Fence A signaled without waiting for semaphore.\n"); + goto out_cleanup; + } + if (radeon_fence_signaled(fenceB)) { + DRM_ERROR("Fence B signaled without waiting for semaphore.\n"); + goto out_cleanup; + } + + r = radeon_ring_lock(rdev, ringC, 64); + if (r) { + DRM_ERROR("Failed to lock ring B %p\n", ringC); + goto out_cleanup; + } + radeon_semaphore_emit_signal(rdev, ringC->idx, semaphore); + radeon_ring_unlock_commit(rdev, ringC, false); + + for (i = 0; i < 30; ++i) { + msleep(100); + sigA = radeon_fence_signaled(fenceA); + sigB = radeon_fence_signaled(fenceB); + if (sigA || sigB) + break; + } + + if (!sigA && !sigB) { + DRM_ERROR("Neither fence A nor B has been signaled\n"); + goto out_cleanup; + } else if (sigA && sigB) { + DRM_ERROR("Both fence A and B has been signaled\n"); + goto out_cleanup; + } + + DRM_INFO("Fence %c was first signaled\n", sigA ? 'A' : 'B'); + + r = radeon_ring_lock(rdev, ringC, 64); + if (r) { + DRM_ERROR("Failed to lock ring B %p\n", ringC); + goto out_cleanup; + } + radeon_semaphore_emit_signal(rdev, ringC->idx, semaphore); + radeon_ring_unlock_commit(rdev, ringC, false); + + msleep(1000); + + r = radeon_fence_wait(fenceA, false); + if (r) { + DRM_ERROR("Failed to wait for sync fence A\n"); + goto out_cleanup; + } + r = radeon_fence_wait(fenceB, false); + if (r) { + DRM_ERROR("Failed to wait for sync fence B\n"); + goto out_cleanup; + } + +out_cleanup: + radeon_semaphore_free(rdev, &semaphore, NULL); + + if (fenceA) + radeon_fence_unref(&fenceA); + + if (fenceB) + radeon_fence_unref(&fenceB); + + if (r) + pr_warn("Error while testing ring sync (%d)\n", r); +} + +static bool radeon_test_sync_possible(struct radeon_ring *ringA, + struct radeon_ring *ringB) +{ + if (ringA->idx == TN_RING_TYPE_VCE2_INDEX && + ringB->idx == TN_RING_TYPE_VCE1_INDEX) + return false; + + return true; +} + +void radeon_test_syncing(struct radeon_device *rdev) +{ + int i, j, k; + + for (i = 1; i < RADEON_NUM_RINGS; ++i) { + struct radeon_ring *ringA = &rdev->ring[i]; + if (!ringA->ready) + continue; + + for (j = 0; j < i; ++j) { + struct radeon_ring *ringB = &rdev->ring[j]; + if (!ringB->ready) + continue; + + if (!radeon_test_sync_possible(ringA, ringB)) + continue; + + DRM_INFO("Testing syncing between rings %d and %d...\n", i, j); + radeon_test_ring_sync(rdev, ringA, ringB); + + DRM_INFO("Testing syncing between rings %d and %d...\n", j, i); + radeon_test_ring_sync(rdev, ringB, ringA); + + for (k = 0; k < j; ++k) { + struct radeon_ring *ringC = &rdev->ring[k]; + if (!ringC->ready) + continue; + + if (!radeon_test_sync_possible(ringA, ringC)) + continue; + + if (!radeon_test_sync_possible(ringB, ringC)) + continue; + + DRM_INFO("Testing syncing between rings %d, %d and %d...\n", i, j, k); + radeon_test_ring_sync2(rdev, ringA, ringB, ringC); + + DRM_INFO("Testing syncing between rings %d, %d and %d...\n", i, k, j); + radeon_test_ring_sync2(rdev, ringA, ringC, ringB); + + DRM_INFO("Testing syncing between rings %d, %d and %d...\n", j, i, k); + radeon_test_ring_sync2(rdev, ringB, ringA, ringC); + + DRM_INFO("Testing syncing between rings %d, %d and %d...\n", j, k, i); + radeon_test_ring_sync2(rdev, ringB, ringC, ringA); + + DRM_INFO("Testing syncing between rings %d, %d and %d...\n", k, i, j); + radeon_test_ring_sync2(rdev, ringC, ringA, ringB); + + DRM_INFO("Testing syncing between rings %d, %d and %d...\n", k, j, i); + radeon_test_ring_sync2(rdev, ringC, ringB, ringA); + } + } + } +} |