summaryrefslogtreecommitdiff
path: root/sys/dev/pci
AgeCommit message (Collapse)Author
2020-06-26drm/i915/gt: Move gen4 GT workarounds from init_clock_gating to workaroundsJonathan Gray
From Chris Wilson ab48267c35b46376010706cddf0b4ca6eb14e12e in linux 5.7.y/5.7.6 27582a9c917940bc71c0df0b8e022cbde8d735d2 in mainline linux
2020-06-26drm/i915/gt: Move vlv GT workarounds from init_clock_gating to workaroundsJonathan Gray
From Chris Wilson 22b2d9aae9cd38e425ef8166e5b348e9be50b4b4 in linux 5.7.y/5.7.6 695a2b11649e99bbf15d278042247042c42b8728 in mainline linux
2020-06-26drm/i915/gt: Move ilk GT workarounds from init_clock_gating to workaroundsJonathan Gray
From Chris Wilson f04e0b5884098b7805ddf40fbcd641c249f2fa88 in linux 5.7.y/5.7.6 eacf21040aa97fd1b3c6bb201bfd43820e1c49be in mainline linux
2020-06-26drm/i915/gt: Move snb GT workarounds from init_clock_gating to workaroundsJonathan Gray
From Chris Wilson 86b34963b7b3970b68428f191cef66fa10cbc51f in linux 5.7.y/5.7.6 fd2599bda5a989c3332f4956fd7760ec32bd51ee in mainline linux
2020-06-26drm/i915/gt: Move ivb GT workarounds from init_clock_gating to workaroundsJonathan Gray
From Chris Wilson f6c298aaf65ab6701654746a930362b147d042aa in linux 5.7.y/5.7.6 7237b190add0794bd95979018a23eda698f2705d in mainline linux
2020-06-26drm/i915/gt: Move hsw GT workarounds from init_clock_gating to workaroundsJonathan Gray
From Chris Wilson 24fa6c758204c83904881e78658f5cff7980938c in linux 5.7.y/5.7.6 ef50fa9bd17d13d0611e39e13b37bbd3e1ea50bf in mainline linux
2020-06-26drm/i915/gt: Incrementally check for rewindingJonathan Gray
From Chris Wilson 79eb9f19dbd2418c25e67f70d3b2fdc98a60dbea in linux 5.7.y/5.7.6 8ab3a3812aa90e488813e719308ffd807b865624 in mainline linux
2020-06-26drm/i915/tc: fix the reset of ln0Jonathan Gray
From Khaled Almahallawy 479c06981236d3fea7ac4cf6a4f61fe896acacc1 in linux 5.7.y/5.7.6 a43555ac908c604f45ed98628805aec9355b9737 in mainline linux
2020-06-26drm/i915/icl+: Fix hotplug interrupt disabling after storm detectionJonathan Gray
From Imre Deak 2e61678ba2383c0d10a7c862721150a37ffe4eee in linux 5.7.y/5.7.6 a3005c2edf7e8c3478880db1ca84028a2b6819bb in mainline linux
2020-06-26stuff for PPCNT - Ports Performance Counters RegisterDavid Gwynne
2020-06-26drm/amd/display: Use kvfree() to free coeff in build_regamma()Jonathan Gray
From Denis Efremov b89722d873c7544fe74f50b7a26e3f2ae50e32ae in linux 5.7.y/5.7.6 81921a828b94ce2816932c19a5ec74d302972833 in mainline linux
2020-06-26drm/amdkfd: Use correct major in devcgroup checkJonathan Gray
From Lorenz Brun 48d3b36959153cc427964c519b5430024fd61e10 in linux 5.7.y/5.7.6 99c7b309472787026ce52fd2bc5d00630567a872 in mainline linux
2020-06-26drm/connector: notify userspace on hotplug after register completeJonathan Gray
From Jeykumar Sankaran e1f81dfa5b88861a1cdda9cfd8f019ede3da7e8b in linux 5.7.y/5.7.6 968d81a64a883af2d16dd3f8a6ad6b67db2fde58 in mainline linux
2020-06-26drm/i915: Whitelist context-local timestamp in the gen9 cmdparserJonathan Gray
From Chris Wilson f11a45d13e11a238868afa6dbe1790ae816ef8af in linux 5.7.y/5.7.6 273500ae71711c040d258a7b3f4b6f44c368fff2 in mainline linux
2020-06-26drm/i915/gem: Avoid iterating an empty listJonathan Gray
From Chris Wilson 42765cb3887c2eea8a65f665a58f42b4ee6333c1 in linux 5.7.y/5.7.6 757a9395f33c51c4e6eff2c7c0fbd50226a58224 in mainline linux
2020-06-26drm/i915: Fix AUX power domain toggling across TypeC mode resetsJonathan Gray
From Imre Deak fa48b63218d09c080dfcdbc04efd282ba5849d98 in linux 5.7.y/5.7.6 d96536f0fe699729a0974eb5b65eb0d87cc747e1 in mainline linux
2020-06-26drm/dp_mst: Increase ACT retry timeout to 3sJonathan Gray
From Lyude Paul 6326202d7a9b39203d6e5f3873750d91fb2b0aaf in linux 5.7.y/5.7.6 873a95e0d59ac06901ae261dda0b7165ffd002b8 in mainline linux
2020-06-26drm/amdgpu: Replace invalid device ID with a valid device IDJonathan Gray
From Sandeep Raghuraman a3d6d880d6e5af2c89d4ad7023272410e7d43755 in linux 5.7.y/5.7.6 790243d3bf78f9830a3b2ffbca1ed0f528295d48 in mainline linux
2020-06-26drm/amdgpu/display: use blanked rather than plane state for sync groupsJonathan Gray
From Alex Deucher fba8f9ef7e1405ee6f422beb874791e8a5eb489c in linux 5.7.y/5.7.6 b7f839d292948142eaab77cedd031aad0bfec872 in mainline linux
2020-06-26drm/dp_mst: Reformat drm_dp_check_act_status() a bitJonathan Gray
From Lyude Paul 5c6be713f9d0c84909a96b3978e1c543b8ea7ffd in linux 5.7.y/5.7.6 a5cb5fa6c3a5c2cf492db667b8670ee7b044b79f in mainline linux
2020-06-26drm: encoder_slave: fix refcouting error for modulesJonathan Gray
From Wolfram Sang 50bda152c4d98ddf8f880edf21eb167758584c45 in linux 5.7.y/5.7.6 f78d4032de60f50fd4afaa0fb68ea03b985f820a in mainline linux
2020-06-26drm/amd/display: Revalidate bandwidth before commiting DC updatesJonathan Gray
From Nicholas Kazlauskas b5232e2ee8df85891514c73472cac09921e5d51d in linux 5.7.y/5.7.6 a24eaa5c51255b344d5a321f1eeb3205f2775498 in mainline linux
2020-06-26add readx_poll_timeout() required for 5.7.6 drmJonathan Gray
with help from cheloha@
2020-06-26add some whitespace to let things breathe a bit.David Gwynne
"sure" jmatthew@
2020-06-26whitespace fixes, no functional change.David Gwynne
2020-06-26fix link state handling so we can see link go both up and down.David Gwynne
2020-06-25LUT writes go through actual regsiters on 710s, not ctl writes.David Gwynne
found by jmatthew@
2020-06-25add rss/toeplitz support for 710 chips.David Gwynne
this basically distributes incoming packets over the rx rings, where without this they would all land on ring 0. note that the 722 stuff is stubbed out at the moment. i don't have an x722 to test with, so it's hard to get motivated to write the code for it. this is based on stuff supplied by christiano haesbaert.
2020-06-25use the ixl_chip struct to store different rss_hena settings for 710/722David Gwynne
2020-06-25add definitions for rss bits.David Gwynne
based on info from christiano haesbaert
2020-06-25we're close to a point where the differences between 710s and 722s matter.David Gwynne
this adds a struct ixl_chip, which should hold the differences in functionality between 710s and 722s. this adds which type of chip each product is to the ixl_devices array. based on stuff from christiano haesbaert
2020-06-25use intrmap to set up multiple queues across multiple cpus.David Gwynne
ixl(4) is only enabled on amd64 and sparc64, and both of them now support pci_intr_establish_cpu(), so it is safe to apply this. a few things to note: - the chip only supports a power of 2 number of queues, (ie, 1, 2, 4, 8, etc), so this also tests the INTRMAP_POWEROF2 flag to intrmap_create. i tested this on a box with 6 cpus and it did the right thing. - the chip can support a lot of vectors, but we're limiting it to 8 for now. - rss with toeplitz is not implemented yet, so all rxed packets end up on the 0th queue for now. jmatthew@ had done most of the work already, and christiano haesbaert provided some hints to motivate me to work on this bit of it. tested by jmatthew@ on sparc64 ok jmatthew@
2020-06-25bump the ifq maxlen like i just did for ixl(4).David Gwynne
this should enable tx mitigation, and hopefully provide a speed bump here too. iavf is a cut up ixl, so it inherited the IFQ_SETMAXLEN 1. ok jmatthew@
2020-06-25report rx ring state for all rings, not just the first one.David Gwynne
systat mbuf looks a bit better now.
2020-06-24set IFQ_SET_MAXLEN to the number of slots on the tx ring, not 1.David Gwynne
this effectively enables tx mitigation on this chip. hrvoje popovski tested it and discovered it adds about 20% to forwarding performance on his test machine, and brings it more in line with ix(4) performance. jmatthew thinks i copied setting it to 1 from myx, but myx resets it to a proper value later on when it figures out what the chip is capable of. how embarrassment.
2020-06-24kernel: use gettime(9)/getuptime(9) in lieu of time_second(9)/time_uptime(9)cheloha
time_second(9) and time_uptime(9) are widely used in the kernel to quickly get the system UTC or system uptime as a time_t. However, time_t is 64-bit everywhere, so it is not generally safe to use them on 32-bit platforms: you have a split-read problem if your hardware cannot perform atomic 64-bit reads. This patch replaces time_second(9) with gettime(9), a safer successor interface, throughout the kernel. Similarly, time_uptime(9) is replaced with getuptime(9). There is a performance cost on 32-bit platforms in exchange for eliminating the split-read problem: instead of two register reads you now have a lockless read loop to pull the values from the timehands. This is really not *too* bad in the grand scheme of things, but compared to what we were doing before it is several times slower. There is no performance cost on 64-bit (__LP64__) platforms. With input from visa@, dlg@, and tedu@. Several bugs squashed by visa@. ok kettenis@
2020-06-24Use SDEV_NO_ADAPTER_TARGET instead of the value that is beingKenneth R Westerback
aassigned to adapter_buswidth to indicate the adapter is not a target on the bus. ok dlg@ as part of a larger diff.
2020-06-24Use SDEV_NO_ADAPTER_TARGET instead of -1 to indicateKenneth R Westerback
the adapter is not a target on the bus. ok dlg@ as part of a larger diff.
2020-06-24get rid of the per device sff lock because we only use the global one.David Gwynne
no functional change
2020-06-24actually use pci_intr_establish_cpu with cpus from the intrmap.David Gwynne
sigh, i don't know how i forgot this. yes jmatthew@
2020-06-22Remove AMRR/MiRA support from iwx(4). Tx rate selection happens in firmware.Stefan Sperling
2020-06-22Remove unused code for parsing non-volatile memory (NVM) from iwx(4).Stefan Sperling
2020-06-22Some connectors attach late when the drm driver is registers. ForMark Kettenis
that reason we have to delay attaching Backlight properties to those connectors until after drm driver registration. However the drm midlayer code now warns about attaching new properties to connectors after driver registration. So add some workarounds to suppress these warning messages. Figured out by jcs@ ok jsg@, jcs@
2020-06-22apart from the lock wait_queue_head struct is unused so replace itJonathan Gray
2020-06-22don't try to decrement if completion flag is UINT_MAXJonathan Gray
2020-06-22drm/amdgpu: Sync with VM root BO when switching VM to CPU update modeJonathan Gray
From Felix Kuehling 8db9696c1fdfa3d80e29ee80d002f315e4e344a9 in linux 5.7.y/5.7.5 90ca78deb004abe75b5024968a199acb96bb70f9 in mainline linux
2020-06-22drm/amd/powerpay: Disable gfxoff when setting manual mode on picasso and ravenJonathan Gray
From chen gong 4e88ff94dd359871f609da9f430712fcf7025164 in linux 5.7.y/5.7.5 cbd2d08c7463e78d625a69e9db27ad3004cbbd99 in mainline linux
2020-06-22drm/amd/display: Do not disable pipe split if mode is not supportedJonathan Gray
From Sung Lee dbf0a8fce6a9c867c315a400176f9f0e3a963d1e in linux 5.7.y/5.7.5 1dfedb39d38f813357885e19badd1971c17f79a7 in mainline linux
2020-06-22drm/amd/display: dmcu wait loop calculation is incorrect in RVJonathan Gray
From Paul Hsieh 11bce5915166fd50a395716755db8c6a3d3f2eb0 in linux 5.7.y/5.7.5 7fc5c319efceaed1a23b7ef35c333553ce39fecf in mainline linux
2020-06-22drm/amd/display: Correct updating logic of dcn21's pipe VM flagsJonathan Gray
From Dale Zhao 21b7c6033823d3888a195a24271cbea34279dd62 in linux 5.7.y/5.7.5 2a28fe92220a116735ef45939b7edcfee83cc6b0 in mainline linux
generated by cgit v1.2.3 (git 2.25.1) at 2024-12-12 11:48:03 +0000