August 2020 Archives by author
Starting: Sat Aug 1 00:05:43 UTC 2020
Ending: Mon Aug 31 11:13:03 UTC 2020
Messages: 2855
- [PATCH i-g-t] tests/gem_sync: test no inner loop
Marcin Bernatowicz
- [PATCH i-g-t] i915/i915_pm_lpsp: Adopt atomic commit style
Anshuman Gupta
- [PATCH 1/2] drm/i915: Compute has_drrs after compute has_psr
Anshuman Gupta
- [PATCH i-g-t] i915/i915_pm_lpsp: Adopt atomic commit style
Anshuman Gupta
- [PATCH i-g-t] tests/kms_flip: add flip-32bpp-to-64bpp-downscaled-fb subtest
Juha-Pekka Heikkila
- [PATCH i-g-t 0/3] Debug HPD interrupts
Kunal Joshi
- [PATCH i-g-t 1/3] lib/igt_kms Added a function for HPD detection
Kunal Joshi
- [PATCH i-g-t 2/3] lib/igt_chamelium Added kmsg print to debug an issue
Kunal Joshi
- [PATCH i-g-t 3/3] HAX: Run in BAT
Kunal Joshi
- [PATCH] drm/i915: Exercise device remove before first bind
Janusz Krzysztofik
- [PATCH i-g-t v2 00/16] tests/core_hotunplug: Fixes and enhancements
Janusz Krzysztofik
- [PATCH i-g-t v2 01/16] tests/core_hotunplug: Use igt_assert_fd()
Janusz Krzysztofik
- [PATCH i-g-t v2 02/16] tests/core_hotunplug: Constify dev_bus_addr string
Janusz Krzysztofik
- [PATCH i-g-t v2 03/16] tests/core_hotunplug: Consolidate duplicated debug messages
Janusz Krzysztofik
- [PATCH i-g-t v2 04/16] tests/core_hotunplug: Assert successful device filter application
Janusz Krzysztofik
- [PATCH i-g-t v2 05/16] tests/core_hotunplug: Fix missing newline
Janusz Krzysztofik
- [PATCH i-g-t v2 06/16] tests/core_hotunplug: Maintain a single data structure instance
Janusz Krzysztofik
- [PATCH i-g-t v2 07/16] tests/core_hotunplug: Pass errors via a data structure field
Janusz Krzysztofik
- [PATCH i-g-t v2 08/16] tests/core_hotunplug: Handle device close errors
Janusz Krzysztofik
- [PATCH i-g-t v2 09/16] tests/core_hotunplug: Prepare invariant data once per test run
Janusz Krzysztofik
- [PATCH i-g-t v2 10/16] tests/core_hotunplug: Skip selectively on sysfs close errors
Janusz Krzysztofik
- [PATCH i-g-t v2 11/16] tests/core_hotunplug: Follow failed subtests with health checks
Janusz Krzysztofik
- [PATCH i-g-t v2 12/16] tests/core_hotunplug: Fail subtests on device close errors
Janusz Krzysztofik
- [PATCH i-g-t v2 13/16] tests/core_hotunplug: Process return values of sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v2 14/16] tests/core_hotunplug: Assert expected device presence/absence
Janusz Krzysztofik
- [PATCH i-g-t v2 15/16] tests/core_hotunplug: Explicitly ignore unused return values
Janusz Krzysztofik
- [PATCH i-g-t 16/16] tests/core_hotunplug: Un-blocklist *unbind* subtests
Janusz Krzysztofik
- [PATCH i-g-t v3 00/13] tests/core_hotunplug: Fixes and enhancements
Janusz Krzysztofik
- [PATCH i-g-t v3 01/13] tests/core_hotunplug: Use igt_assert_fd()
Janusz Krzysztofik
- [PATCH i-g-t v3 02/13] tests/core_hotunplug: Constify dev_bus_addr string
Janusz Krzysztofik
- [PATCH i-g-t v3 03/13] tests/core_hotunplug: Consolidate duplicated debug messages
Janusz Krzysztofik
- [PATCH i-g-t v3 04/13] tests/core_hotunplug: Assert successful device filter application
Janusz Krzysztofik
- [PATCH i-g-t v3 05/13] tests/core_hotunplug: Fix missing newline
Janusz Krzysztofik
- [PATCH i-g-t v3 06/13] tests/core_hotunplug: Maintain a single data structure instance
Janusz Krzysztofik
- [PATCH i-g-t v3 07/13] tests/core_hotunplug: Pass errors via a data structure field
Janusz Krzysztofik
- [PATCH i-g-t v3 08/13] tests/core_hotunplug: Handle device close errors
Janusz Krzysztofik
- [PATCH i-g-t v3 09/13] tests/core_hotunplug: Prepare invariant data once per test run
Janusz Krzysztofik
- [PATCH i-g-t v3 10/13] tests/core_hotunplug: Skip selectively on sysfs close errors
Janusz Krzysztofik
- [PATCH i-g-t v3 11/13] tests/core_hotunplug: Follow failed subtests with health checks
Janusz Krzysztofik
- [PATCH i-g-t v3 12/13] tests/core_hotunplug: More thorough healthcheck, more careful recovery
Janusz Krzysztofik
- [PATCH i-g-t v3 13/13] tests/core_hotunplug: Un-blocklist *unbind* subtests
Janusz Krzysztofik
- [PATCH i-g-t v3 00/18] tests/core_hotunplug: Fixes and enhancements
Janusz Krzysztofik
- [PATCH i-g-t v3 01/18] tests/core_hotunplug: Use igt_assert_fd()
Janusz Krzysztofik
- [PATCH i-g-t v3 02/18] tests/core_hotunplug: Constify dev_bus_addr string
Janusz Krzysztofik
- [PATCH i-g-t v3 03/18] tests/core_hotunplug: Clean up device open error handling
Janusz Krzysztofik
- [PATCH i-g-t v3 04/18] tests/core_hotunplug: Consolidate duplicated debug messages
Janusz Krzysztofik
- [PATCH i-g-t v3 05/18] tests/core_hotunplug: Assert successful device filter application
Janusz Krzysztofik
- [PATCH i-g-t v3 06/18] tests/core_hotunplug: Maintain a single data structure instance
Janusz Krzysztofik
- [PATCH i-g-t v3 07/18] tests/core_hotunplug: Pass errors via a data structure field
Janusz Krzysztofik
- [PATCH i-g-t v3 08/18] tests/core_hotunplug: Handle device close errors
Janusz Krzysztofik
- [PATCH i-g-t v3 09/18] tests/core_hotunplug: Prepare invariant data once per test run
Janusz Krzysztofik
- [PATCH i-g-t v3 10/18] tests/core_hotunplug: Skip selectively on sysfs close errors
Janusz Krzysztofik
- [PATCH i-g-t v3 11/18] tests/core_hotunplug: Recover from subtest failures
Janusz Krzysztofik
- [PATCH i-g-t v3 12/18] tests/core_hotunplug: Fail subtests on device close errors
Janusz Krzysztofik
- [PATCH i-g-t v3 13/18] tests/core_hotunplug: Let the driver time out essential sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v3 14/18] tests/core_hotunplug: Process return values of sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v3 15/18] tests/core_hotunplug: Assert expected device presence/absence
Janusz Krzysztofik
- [PATCH i-g-t v3 16/18] tests/core_hotunplug: Explicitly ignore unused return values
Janusz Krzysztofik
- [PATCH i-g-t v3 17/18] tests/core_hotunplug: More thorough i915 healthcheck and recovery
Janusz Krzysztofik
- [PATCH i-g-t v3 18/18] tests/core_hotunplug: Un-blocklist *unbind* subtests
Janusz Krzysztofik
- [PATCH i-g-t v3 00/19] tests/core_hotunplug: Fixes and enhancements
Janusz Krzysztofik
- [PATCH i-g-t v3 01/19] tests/core_hotunplug: Use igt_assert_fd()
Janusz Krzysztofik
- [PATCH i-g-t v3 02/19] tests/core_hotunplug: Constify dev_bus_addr string
Janusz Krzysztofik
- [PATCH i-g-t v3 03/19] tests/core_hotunplug: Clean up device open error handling
Janusz Krzysztofik
- [PATCH i-g-t v3 04/19] tests/core_hotunplug: Consolidate duplicated debug messages
Janusz Krzysztofik
- [PATCH i-g-t v3 05/19] tests/core_hotunplug: Assert successful device filter application
Janusz Krzysztofik
- [PATCH i-g-t v3 06/19] tests/core_hotunplug: Maintain a single data structure instance
Janusz Krzysztofik
- [PATCH i-g-t v3 07/19] tests/core_hotunplug: Pass errors via a data structure field
Janusz Krzysztofik
- [PATCH i-g-t v3 08/19] tests/core_hotunplug: Handle device close errors
Janusz Krzysztofik
- [PATCH i-g-t v3 09/19] tests/core_hotunplug: Prepare invariant data once per test run
Janusz Krzysztofik
- [PATCH i-g-t v3 10/19] tests/core_hotunplug: Skip selectively on sysfs close errors
Janusz Krzysztofik
- [PATCH i-g-t v3 11/19] tests/core_hotunplug: Recover from subtest failures
Janusz Krzysztofik
- [PATCH i-g-t v3 12/19] tests/core_hotunplug: Fail subtests on device close errors
Janusz Krzysztofik
- [PATCH i-g-t v3 13/19] tests/core_hotunplug: Let the driver time out essential sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v3 14/19] tests/core_hotunplug: Process return values of sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v3 15/19] tests/core_hotunplug: Assert expected device presence/absence
Janusz Krzysztofik
- [PATCH i-g-t v3 16/19] tests/core_hotunplug: Explicitly ignore unused return values
Janusz Krzysztofik
- [PATCH i-g-t v3 17/19] tests/core_hotunplug: More thorough i915 healthcheck and recovery
Janusz Krzysztofik
- [PATCH i-g-t v3 18/19] tests/core_hotunplug: Duplicate debug messages in dmesg
Janusz Krzysztofik
- [PATCH i-g-t v3 19/19] tests/core_hotunplug: Un-blocklist *unbind* subtests
Janusz Krzysztofik
- [PATCH i-g-t v3 00/21] tests/core_hotunplug: Fixes and enhancements
Janusz Krzysztofik
- [PATCH i-g-t v3 01/21] tests/core_hotunplug: Use igt_assert_fd()
Janusz Krzysztofik
- [PATCH i-g-t v3 02/21] tests/core_hotunplug: Constify dev_bus_addr string
Janusz Krzysztofik
- [PATCH i-g-t v3 03/21] tests/core_hotunplug: Clean up device open error handling
Janusz Krzysztofik
- [PATCH i-g-t v3 04/21] tests/core_hotunplug: Consolidate duplicated debug messages
Janusz Krzysztofik
- [PATCH i-g-t v3 05/21] tests/core_hotunplug: Assert successful device filter application
Janusz Krzysztofik
- [PATCH i-g-t v3 06/21] tests/core_hotunplug: Maintain a single data structure instance
Janusz Krzysztofik
- [PATCH i-g-t v3 07/21] tests/core_hotunplug: Pass errors via a data structure field
Janusz Krzysztofik
- [PATCH i-g-t v3 08/21] tests/core_hotunplug: Handle device close errors
Janusz Krzysztofik
- [PATCH i-g-t v3 09/21] tests/core_hotunplug: Prepare invariant data once per test run
Janusz Krzysztofik
- [PATCH i-g-t v3 10/21] tests/core_hotunplug: Skip selectively on sysfs close errors
Janusz Krzysztofik
- [PATCH i-g-t v3 11/21] tests/core_hotunplug: Recover from subtest failures
Janusz Krzysztofik
- [PATCH i-g-t v3 12/21] tests/core_hotunplug: Fail subtests on device close errors
Janusz Krzysztofik
- [PATCH i-g-t v3 13/21] tests/core_hotunplug: Let the driver time out essential sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v3 14/21] tests/core_hotunplug: Process return values of sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v3 15/21] tests/core_hotunplug: Assert expected device presence/absence
Janusz Krzysztofik
- [PATCH i-g-t v3 16/21] tests/core_hotunplug: Explicitly ignore unused return values
Janusz Krzysztofik
- [PATCH i-g-t v3 17/21] tests/core_hotunplug: More thorough i915 healthcheck and recovery
Janusz Krzysztofik
- [PATCH i-g-t v3 18/21] tests/core_hotunplug: Add 'lateclose before restore' variants
Janusz Krzysztofik
- [PATCH i-g-t v3 19/21] tests/core_hotunplug: Un-blocklist *unbind* subtests
Janusz Krzysztofik
- [PATCH i-g-t v3 20/21] tests/core_hotunplug: Duplicate debug messages in dmesg
Janusz Krzysztofik
- [PATCH i-g-t v3 21/21] tests/core_hotunplug: Add the test to BAT scope
Janusz Krzysztofik
- [PATCH i-g-t v3 00/20] tests/core_hotunplug: Fixes and enhancements
Janusz Krzysztofik
- [PATCH i-g-t v3 01/20] tests/core_hotunplug: Use igt_assert_fd()
Janusz Krzysztofik
- [PATCH i-g-t v3 02/20] tests/core_hotunplug: Constify dev_bus_addr string
Janusz Krzysztofik
- [PATCH i-g-t v3 03/20] tests/core_hotunplug: Clean up device open error handling
Janusz Krzysztofik
- [PATCH i-g-t v3 04/20] tests/core_hotunplug: Consolidate duplicated debug messages
Janusz Krzysztofik
- [PATCH i-g-t v3 05/20] tests/core_hotunplug: Assert successful device filter application
Janusz Krzysztofik
- [PATCH i-g-t v3 06/20] tests/core_hotunplug: Maintain a single data structure instance
Janusz Krzysztofik
- [PATCH i-g-t v3 07/20] tests/core_hotunplug: Pass errors via a data structure field
Janusz Krzysztofik
- [PATCH i-g-t v3 08/20] tests/core_hotunplug: Handle device close errors
Janusz Krzysztofik
- [PATCH i-g-t v3 09/20] tests/core_hotunplug: Prepare invariant data once per test run
Janusz Krzysztofik
- [PATCH i-g-t v3 10/20] tests/core_hotunplug: Recover from subtest failures
Janusz Krzysztofik
- [PATCH i-g-t v3 11/20] tests/core_hotunplug: Fail subtests on device close errors
Janusz Krzysztofik
- [PATCH i-g-t v3 12/20] tests/core_hotunplug: Let the driver time out essential sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v3 13/20] tests/core_hotunplug: Process return values of sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v3 14/20] tests/core_hotunplug: Assert expected device presence/absence
Janusz Krzysztofik
- [PATCH i-g-t v3 15/20] tests/core_hotunplug: Explicitly ignore unused return values
Janusz Krzysztofik
- [PATCH i-g-t v3 16/20] tests/core_hotunplug: More thorough i915 healthcheck and recovery
Janusz Krzysztofik
- [PATCH i-g-t v3 17/20] tests/core_hotunplug: Add 'lateclose before restore' variants
Janusz Krzysztofik
- [PATCH i-g-t v3 18/20] tests/core_hotunplug: Un-blocklist *unbind* subtests
Janusz Krzysztofik
- [PATCH i-g-t v3 19/20] tests/core_hotunplug: Duplicate debug messages in dmesg
Janusz Krzysztofik
- [PATCH i-g-t v3 20/20] tests/core_hotunplug: Skip selectively on sysfs close errors
Janusz Krzysztofik
- [PATCH i-g-t v3 00/20] tests/core_hotunplug: Fixes and enhancements
Janusz Krzysztofik
- [PATCH i-g-t v3 01/20] tests/core_hotunplug: Use igt_assert_fd()
Janusz Krzysztofik
- [PATCH i-g-t v3 02/20] tests/core_hotunplug: Constify dev_bus_addr string
Janusz Krzysztofik
- [PATCH i-g-t v3 03/20] tests/core_hotunplug: Clean up device open error handling
Janusz Krzysztofik
- [PATCH i-g-t v3 04/20] tests/core_hotunplug: Consolidate duplicated debug messages
Janusz Krzysztofik
- [PATCH i-g-t v3 05/20] tests/core_hotunplug: Assert successful device filter application
Janusz Krzysztofik
- [PATCH i-g-t v3 06/20] tests/core_hotunplug: Maintain a single data structure instance
Janusz Krzysztofik
- [PATCH i-g-t v3 07/20] tests/core_hotunplug: Pass errors via a data structure field
Janusz Krzysztofik
- [PATCH i-g-t v3 08/20] tests/core_hotunplug: Handle device close errors
Janusz Krzysztofik
- [PATCH i-g-t v3 09/20] tests/core_hotunplug: Prepare invariant data once per test run
Janusz Krzysztofik
- [PATCH i-g-t v3 10/20] tests/core_hotunplug: Skip selectively on sysfs close errors
Janusz Krzysztofik
- [PATCH i-g-t v3 11/20] tests/core_hotunplug: Recover from subtest failures
Janusz Krzysztofik
- [PATCH i-g-t v3 12/20] tests/core_hotunplug: Fail subtests on device close errors
Janusz Krzysztofik
- [PATCH i-g-t v3 13/20] tests/core_hotunplug: Let the driver time out essential sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v3 14/20] tests/core_hotunplug: Process return values of sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v3 15/20] tests/core_hotunplug: Assert expected device presence/absence
Janusz Krzysztofik
- [PATCH i-g-t v3 16/20] tests/core_hotunplug: Explicitly ignore unused return values
Janusz Krzysztofik
- [PATCH i-g-t v3 17/20] tests/core_hotunplug: More thorough i915 healthcheck and recovery
Janusz Krzysztofik
- [PATCH i-g-t v3 18/20] tests/core_hotunplug: Add 'lateclose before restore' variants
Janusz Krzysztofik
- [PATCH i-g-t v3 19/20] tests/core_hotunplug: Un-blocklist *bind* subtests
Janusz Krzysztofik
- [PATCH i-g-t v3 20/20] tests/core_hotunplug: Duplicate debug messages in dmesg
Janusz Krzysztofik
- [PATCH i-g-t v4 00/20] tests/core_hotunplug: Fixes and enhancements
Janusz Krzysztofik
- [PATCH i-g-t v4 01/20] tests/core_hotunplug: Use igt_assert_fd()
Janusz Krzysztofik
- [PATCH i-g-t v4 02/20] tests/core_hotunplug: Constify dev_bus_addr string
Janusz Krzysztofik
- [PATCH i-g-t v4 03/20] tests/core_hotunplug: Clean up device open error handling
Janusz Krzysztofik
- [PATCH i-g-t v4 04/20] tests/core_hotunplug: Consolidate duplicated debug messages
Janusz Krzysztofik
- [PATCH i-g-t v4 05/20] tests/core_hotunplug: Assert successful device filter application
Janusz Krzysztofik
- [PATCH i-g-t v4 06/20] tests/core_hotunplug: Maintain a single data structure instance
Janusz Krzysztofik
- [PATCH i-g-t v4 07/20] tests/core_hotunplug: Pass errors via a data structure field
Janusz Krzysztofik
- [PATCH i-g-t v4 08/20] tests/core_hotunplug: Handle device close errors
Janusz Krzysztofik
- [PATCH i-g-t v4 09/20] tests/core_hotunplug: Prepare invariant data once per test run
Janusz Krzysztofik
- [PATCH i-g-t v4 10/20] tests/core_hotunplug: Skip selectively on sysfs close errors
Janusz Krzysztofik
- [PATCH i-g-t v4 11/20] tests/core_hotunplug: Recover from subtest failures
Janusz Krzysztofik
- [PATCH i-g-t v4 12/20] tests/core_hotunplug: Fail subtests on device close errors
Janusz Krzysztofik
- [PATCH i-g-t v4 13/20] tests/core_hotunplug: Let the driver time out essential sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v4 14/20] tests/core_hotunplug: Process return values of sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v4 15/20] tests/core_hotunplug: Assert expected device presence/absence
Janusz Krzysztofik
- [PATCH i-g-t v4 16/20] tests/core_hotunplug: Explicitly ignore unused return values
Janusz Krzysztofik
- [PATCH i-g-t v4 17/20] tests/core_hotunplug: More thorough i915 healthcheck and recovery
Janusz Krzysztofik
- [PATCH i-g-t v4 18/20] tests/core_hotunplug: Add 'lateclose before restore' variants
Janusz Krzysztofik
- [PATCH i-g-t v4 19/20] tests/core_hotunplug: Un-blocklist *bind* subtests
Janusz Krzysztofik
- [PATCH i-g-t v4 20/20] tests/core_hotunplug: Duplicate debug messages in dmesg
Janusz Krzysztofik
- [PATCH i-g-t v5 00/22] tests/core_hotunplug: Fixes and enhancements
Janusz Krzysztofik
- [PATCH i-g-t v5 01/22] tests/core_hotunplug: Use igt_assert_fd()
Janusz Krzysztofik
- [PATCH i-g-t v5 02/22] tests/core_hotunplug: Constify dev_bus_addr string
Janusz Krzysztofik
- [PATCH i-g-t v5 03/22] tests/core_hotunplug: Clean up device open error handling
Janusz Krzysztofik
- [PATCH i-g-t v5 04/22] tests/core_hotunplug: Consolidate duplicated debug messages
Janusz Krzysztofik
- [PATCH i-g-t v5 05/22] tests/core_hotunplug: Assert successful device filter application
Janusz Krzysztofik
- [PATCH i-g-t v5 06/22] tests/core_hotunplug: Maintain a single data structure instance
Janusz Krzysztofik
- [PATCH i-g-t v5 07/22] tests/core_hotunplug: Pass errors via a data structure field
Janusz Krzysztofik
- [PATCH i-g-t v5 08/22] tests/core_hotunplug: Handle device close errors
Janusz Krzysztofik
- [PATCH i-g-t v5 09/22] tests/core_hotunplug: Prepare invariant data once per test run
Janusz Krzysztofik
- [PATCH i-g-t v5 10/22] tests/core_hotunplug: Skip selectively on sysfs close errors
Janusz Krzysztofik
- [PATCH i-g-t v5 11/22] tests/core_hotunplug: Recover from subtest failures
Janusz Krzysztofik
- [PATCH i-g-t v5 12/22] tests/core_hotunplug: Fail subtests on device close errors
Janusz Krzysztofik
- [PATCH i-g-t v5 13/22] tests/core_hotunplug: Let the driver time out essential sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v5 14/22] tests/core_hotunplug: Process return values of sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v5 15/22] tests/core_hotunplug: Assert expected device presence/absence
Janusz Krzysztofik
- [PATCH i-g-t v5 16/22] tests/core_hotunplug: Explicitly ignore unused return values
Janusz Krzysztofik
- [PATCH i-g-t v5 17/22] tests/core_hotunplug: More thorough i915 healthcheck and recovery
Janusz Krzysztofik
- [PATCH i-g-t v5 18/22] tests/core_hotunplug: Add 'lateclose before restore' variants
Janusz Krzysztofik
- [PATCH i-g-t v5 19/22] tests/core_hotunplug: Duplicate debug messages in dmesg
Janusz Krzysztofik
- [PATCH i-g-t v5 20/22] tests/core_hotunplug: Un-blocklist *bind* subtests
Janusz Krzysztofik
- [PATCH i-g-t v5 21/22] tests/core_hotunplug: HSW audio issue workaround
Janusz Krzysztofik
- [PATCH i-g-t v5 22/22] tests/core_hotunplug: Add the test to BAT scope
Janusz Krzysztofik
- [PATCH i-g-t v5 00/22] tests/core_hotunplug: Fixes and enhancements
Janusz Krzysztofik
- [PATCH i-g-t v5 01/22] tests/core_hotunplug: Use igt_assert_fd()
Janusz Krzysztofik
- [PATCH i-g-t v5 02/22] tests/core_hotunplug: Constify dev_bus_addr string
Janusz Krzysztofik
- [PATCH i-g-t v5 03/22] tests/core_hotunplug: Clean up device open error handling
Janusz Krzysztofik
- [PATCH i-g-t v5 04/22] tests/core_hotunplug: Consolidate duplicated debug messages
Janusz Krzysztofik
- [PATCH i-g-t v5 05/22] tests/core_hotunplug: Assert successful device filter application
Janusz Krzysztofik
- [PATCH i-g-t v5 06/22] tests/core_hotunplug: Maintain a single data structure instance
Janusz Krzysztofik
- [PATCH i-g-t v5 07/22] tests/core_hotunplug: Pass errors via a data structure field
Janusz Krzysztofik
- [PATCH i-g-t v5 08/22] tests/core_hotunplug: Handle device close errors
Janusz Krzysztofik
- [PATCH i-g-t v5 09/22] tests/core_hotunplug: Prepare invariant data once per test run
Janusz Krzysztofik
- [PATCH i-g-t v5 10/22] tests/core_hotunplug: Skip selectively on sysfs close errors
Janusz Krzysztofik
- [PATCH i-g-t v5 11/22] tests/core_hotunplug: Recover from subtest failures
Janusz Krzysztofik
- [PATCH i-g-t v5 12/22] tests/core_hotunplug: Fail subtests on device close errors
Janusz Krzysztofik
- [PATCH i-g-t v5 13/22] tests/core_hotunplug: Let the driver time out essential sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v5 14/22] tests/core_hotunplug: Process return values of sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v5 15/22] tests/core_hotunplug: Assert expected device presence/absence
Janusz Krzysztofik
- [PATCH i-g-t v5 16/22] tests/core_hotunplug: Explicitly ignore unused return values
Janusz Krzysztofik
- [PATCH i-g-t v5 17/22] tests/core_hotunplug: More thorough i915 healthcheck and recovery
Janusz Krzysztofik
- [PATCH i-g-t v5 18/22] tests/core_hotunplug: Add 'lateclose before restore' variants
Janusz Krzysztofik
- [PATCH i-g-t v5 19/22] tests/core_hotunplug: Duplicate debug messages in dmesg
Janusz Krzysztofik
- [PATCH i-g-t v5 20/22] tests/core_hotunplug: Un-blocklist *bind* subtests
Janusz Krzysztofik
- [PATCH i-g-t v5 21/22] tests/core_hotunplug: HSW audio issue workaround
Janusz Krzysztofik
- [PATCH i-g-t v5 22/22] tests/core_hotunplug: Add the test to BAT scope
Janusz Krzysztofik
- [PATCH i-g-t v5 00/21] tests/core_hotunplug: Fixes and enhancements
Janusz Krzysztofik
- [PATCH i-g-t v5 01/21] tests/core_hotunplug: Use igt_assert_fd()
Janusz Krzysztofik
- [PATCH i-g-t v5 02/21] tests/core_hotunplug: Constify dev_bus_addr string
Janusz Krzysztofik
- [PATCH i-g-t v5 03/21] tests/core_hotunplug: Clean up device open error handling
Janusz Krzysztofik
- [PATCH i-g-t v5 04/21] tests/core_hotunplug: Consolidate duplicated debug messages
Janusz Krzysztofik
- [PATCH i-g-t v5 05/21] tests/core_hotunplug: Assert successful device filter application
Janusz Krzysztofik
- [PATCH i-g-t v5 06/21] tests/core_hotunplug: Maintain a single data structure instance
Janusz Krzysztofik
- [PATCH i-g-t v5 07/21] tests/core_hotunplug: Pass errors via a data structure field
Janusz Krzysztofik
- [PATCH i-g-t v5 08/21] tests/core_hotunplug: Handle device close errors
Janusz Krzysztofik
- [PATCH i-g-t v5 09/21] tests/core_hotunplug: Prepare invariant data once per test run
Janusz Krzysztofik
- [PATCH i-g-t v5 10/21] tests/core_hotunplug: Skip selectively on sysfs close errors
Janusz Krzysztofik
- [PATCH i-g-t v5 11/21] tests/core_hotunplug: Recover from subtest failures
Janusz Krzysztofik
- [PATCH i-g-t v5 12/21] tests/core_hotunplug: Fail subtests on device close errors
Janusz Krzysztofik
- [PATCH i-g-t v5 13/21] tests/core_hotunplug: Let the driver time out essential sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v5 14/21] tests/core_hotunplug: Process return values of sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v5 15/21] tests/core_hotunplug: Assert expected device presence/absence
Janusz Krzysztofik
- [PATCH i-g-t v5 16/21] tests/core_hotunplug: Explicitly ignore unused return values
Janusz Krzysztofik
- [PATCH i-g-t v5 17/21] tests/core_hotunplug: More thorough i915 healthcheck and recovery
Janusz Krzysztofik
- [PATCH i-g-t v5 18/21] tests/core_hotunplug: Add 'lateclose before restore' variants
Janusz Krzysztofik
- [PATCH i-g-t v5 19/21] tests/core_hotunplug: Duplicate debug messages in dmesg
Janusz Krzysztofik
- [PATCH i-g-t v5 20/21] tests/core_hotunplug: HSW audio issue workaround
Janusz Krzysztofik
- [PATCH i-g-t v5 21/21] tests/core_hotunplug: Un-blocklist *bind* subtests
Janusz Krzysztofik
- [PATCH i-g-t v5 00/21] tests/core_hotunplug: Fixes and enhancements
Janusz Krzysztofik
- [PATCH i-g-t v5 01/21] tests/core_hotunplug: Use igt_assert_fd()
Janusz Krzysztofik
- [PATCH i-g-t v5 02/21] tests/core_hotunplug: Constify dev_bus_addr string
Janusz Krzysztofik
- [PATCH i-g-t v5 03/21] tests/core_hotunplug: Clean up device open error handling
Janusz Krzysztofik
- [PATCH i-g-t v5 04/21] tests/core_hotunplug: Consolidate duplicated debug messages
Janusz Krzysztofik
- [PATCH i-g-t v5 05/21] tests/core_hotunplug: Assert successful device filter application
Janusz Krzysztofik
- [PATCH i-g-t v5 06/21] tests/core_hotunplug: Maintain a single data structure instance
Janusz Krzysztofik
- [PATCH i-g-t v5 07/21] tests/core_hotunplug: Pass errors via a data structure field
Janusz Krzysztofik
- [PATCH i-g-t v5 08/21] tests/core_hotunplug: Handle device close errors
Janusz Krzysztofik
- [PATCH i-g-t v5 09/21] tests/core_hotunplug: Prepare invariant data once per test run
Janusz Krzysztofik
- [PATCH i-g-t v5 10/21] tests/core_hotunplug: Skip selectively on sysfs close errors
Janusz Krzysztofik
- [PATCH i-g-t v5 11/21] tests/core_hotunplug: Recover from subtest failures
Janusz Krzysztofik
- [PATCH i-g-t v5 12/21] tests/core_hotunplug: Fail subtests on device close errors
Janusz Krzysztofik
- [PATCH i-g-t v5 13/21] tests/core_hotunplug: Let the driver time out essential sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v5 14/21] tests/core_hotunplug: Process return values of sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v5 15/21] tests/core_hotunplug: Assert expected device presence/absence
Janusz Krzysztofik
- [PATCH i-g-t v5 16/21] tests/core_hotunplug: Explicitly ignore unused return values
Janusz Krzysztofik
- [PATCH i-g-t v5 17/21] tests/core_hotunplug: More thorough i915 healthcheck and recovery
Janusz Krzysztofik
- [PATCH i-g-t v5 18/21] tests/core_hotunplug: Add 'lateclose before restore' variants
Janusz Krzysztofik
- [PATCH i-g-t v5 19/21] tests/core_hotunplug: Duplicate debug messages in dmesg
Janusz Krzysztofik
- [PATCH i-g-t v5 20/21] tests/core_hotunplug: HSW audio issue workaround
Janusz Krzysztofik
- [PATCH i-g-t v5 21/21] tests/core_hotunplug: Un-blocklist *bind* subtests
Janusz Krzysztofik
- [PATCH i-g-t v5 00/22] tests/core_hotunplug: Fixes and enhancements
Janusz Krzysztofik
- [PATCH i-g-t v5 01/22] tests/core_hotunplug: Use igt_assert_fd()
Janusz Krzysztofik
- [PATCH i-g-t v5 02/22] tests/core_hotunplug: Constify dev_bus_addr string
Janusz Krzysztofik
- [PATCH i-g-t v5 03/22] tests/core_hotunplug: Clean up device open error handling
Janusz Krzysztofik
- [PATCH i-g-t v5 04/22] tests/core_hotunplug: Consolidate duplicated debug messages
Janusz Krzysztofik
- [PATCH i-g-t v5 05/22] tests/core_hotunplug: Assert successful device filter application
Janusz Krzysztofik
- [PATCH i-g-t v5 06/22] tests/core_hotunplug: Maintain a single data structure instance
Janusz Krzysztofik
- [PATCH i-g-t v5 07/22] tests/core_hotunplug: Pass errors via a data structure field
Janusz Krzysztofik
- [PATCH i-g-t v5 08/22] tests/core_hotunplug: Handle device close errors
Janusz Krzysztofik
- [PATCH i-g-t v5 09/22] tests/core_hotunplug: Prepare invariant data once per test run
Janusz Krzysztofik
- [PATCH i-g-t v5 10/22] tests/core_hotunplug: Skip selectively on sysfs close errors
Janusz Krzysztofik
- [PATCH i-g-t v5 11/22] tests/core_hotunplug: Recover from subtest failures
Janusz Krzysztofik
- [PATCH i-g-t v5 12/22] tests/core_hotunplug: Fail subtests on device close errors
Janusz Krzysztofik
- [PATCH i-g-t v5 13/22] tests/core_hotunplug: Let the driver time out essential sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v5 14/22] tests/core_hotunplug: Process return values of sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v5 15/22] tests/core_hotunplug: Assert expected device presence/absence
Janusz Krzysztofik
- [PATCH i-g-t v5 16/22] tests/core_hotunplug: Explicitly ignore unused return values
Janusz Krzysztofik
- [PATCH i-g-t v5 17/22] tests/core_hotunplug: More thorough i915 healthcheck and recovery
Janusz Krzysztofik
- [PATCH i-g-t v5 18/22] tests/core_hotunplug: Add 'lateclose before restore' variants
Janusz Krzysztofik
- [PATCH i-g-t v5 19/22] tests/core_hotunplug: Duplicate debug messages in dmesg
Janusz Krzysztofik
- [PATCH i-g-t v5 20/22] tests/core_hotunplug: HSW audio issue workaround
Janusz Krzysztofik
- [PATCH i-g-t v5 21/22] tests/core_hotunplug: Un-blocklist *bind* subtests
Janusz Krzysztofik
- [PATCH i-g-t v5 22/22] tests/core_hotunplug: A few more fixes
Janusz Krzysztofik
- [PATCH i-g-t v5 00/22] tests/core_hotunplug: Fixes and enhancements
Janusz Krzysztofik
- [PATCH i-g-t v5 01/22] tests/core_hotunplug: Use igt_assert_fd()
Janusz Krzysztofik
- [PATCH i-g-t v5 02/22] tests/core_hotunplug: Constify dev_bus_addr string
Janusz Krzysztofik
- [PATCH i-g-t v5 03/22] tests/core_hotunplug: Clean up device open error handling
Janusz Krzysztofik
- [PATCH i-g-t v5 04/22] tests/core_hotunplug: Consolidate duplicated debug messages
Janusz Krzysztofik
- [PATCH i-g-t v5 05/22] tests/core_hotunplug: Assert successful device filter application
Janusz Krzysztofik
- [PATCH i-g-t v5 06/22] tests/core_hotunplug: Maintain a single data structure instance
Janusz Krzysztofik
- [PATCH i-g-t v5 07/22] tests/core_hotunplug: Pass errors via a data structure field
Janusz Krzysztofik
- [PATCH i-g-t v5 08/22] tests/core_hotunplug: Handle device close errors
Janusz Krzysztofik
- [PATCH i-g-t v5 09/22] tests/core_hotunplug: Prepare invariant data once per test run
Janusz Krzysztofik
- [PATCH i-g-t v5 10/22] tests/core_hotunplug: Skip selectively on sysfs close errors
Janusz Krzysztofik
- [PATCH i-g-t v5 11/22] tests/core_hotunplug: Recover from subtest failures
Janusz Krzysztofik
- [PATCH i-g-t v5 12/22] tests/core_hotunplug: Fail subtests on device close errors
Janusz Krzysztofik
- [PATCH i-g-t v5 13/22] tests/core_hotunplug: Let the driver time out essential sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v5 14/22] tests/core_hotunplug: Process return values of sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v5 15/22] tests/core_hotunplug: Assert expected device presence/absence
Janusz Krzysztofik
- [PATCH i-g-t v5 16/22] tests/core_hotunplug: Explicitly ignore unused return values
Janusz Krzysztofik
- [PATCH i-g-t v5 17/22] tests/core_hotunplug: More thorough i915 healthcheck and recovery
Janusz Krzysztofik
- [PATCH i-g-t v5 18/22] tests/core_hotunplug: Add 'lateclose before restore' variants
Janusz Krzysztofik
- [PATCH i-g-t v5 19/22] tests/core_hotunplug: Duplicate debug messages in dmesg
Janusz Krzysztofik
- [PATCH i-g-t v5 20/22] tests/core_hotunplug: HSW audio issue workaround
Janusz Krzysztofik
- [PATCH i-g-t v5 21/22] tests/core_hotunplug: Un-blocklist *bind* subtests
Janusz Krzysztofik
- [PATCH i-g-t v5 22/22] tests/core_hotunplug: A few more fixes
Janusz Krzysztofik
- [PATCH i-g-t v5 00/22] tests/core_hotunplug: Fixes and enhancements
Janusz Krzysztofik
- [PATCH i-g-t v5 01/22] tests/core_hotunplug: Use igt_assert_fd()
Janusz Krzysztofik
- [PATCH i-g-t v5 02/22] tests/core_hotunplug: Constify dev_bus_addr string
Janusz Krzysztofik
- [PATCH i-g-t v5 03/22] tests/core_hotunplug: Clean up device open error handling
Janusz Krzysztofik
- [PATCH i-g-t v5 04/22] tests/core_hotunplug: Consolidate duplicated debug messages
Janusz Krzysztofik
- [PATCH i-g-t v5 05/22] tests/core_hotunplug: Assert successful device filter application
Janusz Krzysztofik
- [PATCH i-g-t v5 06/22] tests/core_hotunplug: Maintain a single data structure instance
Janusz Krzysztofik
- [PATCH i-g-t v5 07/22] tests/core_hotunplug: Pass errors via a data structure field
Janusz Krzysztofik
- [PATCH i-g-t v5 08/22] tests/core_hotunplug: Handle device close errors
Janusz Krzysztofik
- [PATCH i-g-t v5 09/22] tests/core_hotunplug: Prepare invariant data once per test run
Janusz Krzysztofik
- [PATCH i-g-t v5 10/22] tests/core_hotunplug: Skip selectively on sysfs close errors
Janusz Krzysztofik
- [PATCH i-g-t v5 11/22] tests/core_hotunplug: Recover from subtest failures
Janusz Krzysztofik
- [PATCH i-g-t v5 12/22] tests/core_hotunplug: Fail subtests on device close errors
Janusz Krzysztofik
- [PATCH i-g-t v5 13/22] tests/core_hotunplug: Let the driver time out essential sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v5 14/22] tests/core_hotunplug: Process return values of sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v5 15/22] tests/core_hotunplug: Assert expected device presence/absence
Janusz Krzysztofik
- [PATCH i-g-t v5 16/22] tests/core_hotunplug: Explicitly ignore unused return values
Janusz Krzysztofik
- [PATCH i-g-t v5 17/22] tests/core_hotunplug: More thorough i915 healthcheck and recovery
Janusz Krzysztofik
- [PATCH i-g-t v5 18/22] tests/core_hotunplug: Add 'lateclose before restore' variants
Janusz Krzysztofik
- [PATCH i-g-t v5 19/22] tests/core_hotunplug: Duplicate debug messages in dmesg
Janusz Krzysztofik
- [PATCH i-g-t v5 20/22] tests/core_hotunplug: HSW audio issue workaround
Janusz Krzysztofik
- [PATCH i-g-t v5 21/22] tests/core_hotunplug: Un-blocklist *bind* subtests
Janusz Krzysztofik
- [PATCH i-g-t v5 22/22] tests/core_hotunplug: A few more fixes
Janusz Krzysztofik
- [PATCH i-g-t v5 00/22] tests/core_hotunplug: Fixes and enhancements
Janusz Krzysztofik
- [PATCH i-g-t v5 01/22] tests/core_hotunplug: Use igt_assert_fd()
Janusz Krzysztofik
- [PATCH i-g-t v5 02/22] tests/core_hotunplug: Constify dev_bus_addr string
Janusz Krzysztofik
- [PATCH i-g-t v5 03/22] tests/core_hotunplug: Clean up device open error handling
Janusz Krzysztofik
- [PATCH i-g-t v5 04/22] tests/core_hotunplug: Consolidate duplicated debug messages
Janusz Krzysztofik
- [PATCH i-g-t v5 05/22] tests/core_hotunplug: Assert successful device filter application
Janusz Krzysztofik
- [PATCH i-g-t v5 06/22] tests/core_hotunplug: Maintain a single data structure instance
Janusz Krzysztofik
- [PATCH i-g-t v5 07/22] tests/core_hotunplug: Pass errors via a data structure field
Janusz Krzysztofik
- [PATCH i-g-t v5 08/22] tests/core_hotunplug: Handle device close errors
Janusz Krzysztofik
- [PATCH i-g-t v5 09/22] tests/core_hotunplug: Prepare invariant data once per test run
Janusz Krzysztofik
- [PATCH i-g-t v5 10/22] tests/core_hotunplug: Skip selectively on sysfs close errors
Janusz Krzysztofik
- [PATCH i-g-t v5 11/22] tests/core_hotunplug: Recover from subtest failures
Janusz Krzysztofik
- [PATCH i-g-t v5 12/22] tests/core_hotunplug: Fail subtests on device close errors
Janusz Krzysztofik
- [PATCH i-g-t v5 13/22] tests/core_hotunplug: Let the driver time out essential sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v5 14/22] tests/core_hotunplug: Process return values of sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v5 15/22] tests/core_hotunplug: Assert expected device presence/absence
Janusz Krzysztofik
- [PATCH i-g-t v5 16/22] tests/core_hotunplug: Explicitly ignore unused return values
Janusz Krzysztofik
- [PATCH i-g-t v5 17/22] tests/core_hotunplug: More thorough i915 healthcheck and recovery
Janusz Krzysztofik
- [PATCH i-g-t v5 18/22] tests/core_hotunplug: Add 'lateclose before restore' variants
Janusz Krzysztofik
- [PATCH i-g-t v5 19/22] tests/core_hotunplug: Duplicate debug messages in dmesg
Janusz Krzysztofik
- [PATCH i-g-t v5 20/22] tests/core_hotunplug: HSW audio issue workaround
Janusz Krzysztofik
- [PATCH i-g-t v5 21/22] tests/core_hotunplug: Un-blocklist *bind* subtests
Janusz Krzysztofik
- [PATCH i-g-t v5 22/22] tests/core_hotunplug: A few more fixes
Janusz Krzysztofik
- [PATCH i-g-t v5 00/21] tests/core_hotunplug: Fixes and enhancements
Janusz Krzysztofik
- [PATCH i-g-t v5 01/21] tests/core_hotunplug: Use igt_assert_fd()
Janusz Krzysztofik
- [PATCH i-g-t v5 02/21] tests/core_hotunplug: Constify dev_bus_addr string
Janusz Krzysztofik
- [PATCH i-g-t v5 03/21] tests/core_hotunplug: Clean up device open error handling
Janusz Krzysztofik
- [PATCH i-g-t v5 04/21] tests/core_hotunplug: Consolidate duplicated debug messages
Janusz Krzysztofik
- [PATCH i-g-t v5 05/21] tests/core_hotunplug: Assert successful device filter application
Janusz Krzysztofik
- [PATCH i-g-t v5 06/21] tests/core_hotunplug: Maintain a single data structure instance
Janusz Krzysztofik
- [PATCH i-g-t v5 07/21] tests/core_hotunplug: Pass errors via a data structure field
Janusz Krzysztofik
- [PATCH i-g-t v5 08/21] tests/core_hotunplug: Handle device close errors
Janusz Krzysztofik
- [PATCH i-g-t v5 09/21] tests/core_hotunplug: Prepare invariant data once per test run
Janusz Krzysztofik
- [PATCH i-g-t v5 10/21] tests/core_hotunplug: Skip selectively on sysfs close errors
Janusz Krzysztofik
- [PATCH i-g-t v5 11/21] tests/core_hotunplug: Recover from subtest failures
Janusz Krzysztofik
- [PATCH i-g-t v5 12/21] tests/core_hotunplug: Fail subtests on device close errors
Janusz Krzysztofik
- [PATCH i-g-t v5 13/21] tests/core_hotunplug: Let the driver time out essential sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v5 14/21] tests/core_hotunplug: Process return values of sysfs operations
Janusz Krzysztofik
- [PATCH i-g-t v5 15/21] tests/core_hotunplug: Assert expected device presence/absence
Janusz Krzysztofik
- [PATCH i-g-t v5 16/21] tests/core_hotunplug: Explicitly ignore unused return values
Janusz Krzysztofik
- [PATCH i-g-t v5 17/21] tests/core_hotunplug: More thorough i915 healthcheck and recovery
Janusz Krzysztofik
- [PATCH i-g-t v5 18/21] tests/core_hotunplug: Add 'lateclose before restore' variants
Janusz Krzysztofik
- [PATCH i-g-t v5 19/21] tests/core_hotunplug: Duplicate debug messages in dmesg
Janusz Krzysztofik
- [PATCH i-g-t v5 20/21] tests/core_hotunplug: HSW audio issue workaround
Janusz Krzysztofik
- [PATCH i-g-t v5 21/21] tests/core_hotunplug: Un-blocklist *bind* subtests
Janusz Krzysztofik
- [PATCH 01/28] Revert "drm/i915/gem: Async GPU relocations only"
Maarten Lankhorst
- [PATCH 02/28] drm/i915: Revert relocation chaining commits.
Maarten Lankhorst
- [PATCH 03/28] Revert "drm/i915/gem: Drop relocation slowpath".
Maarten Lankhorst
- [PATCH 04/28] Revert "drm/i915/gem: Split eb_vma into its own allocation"
Maarten Lankhorst
- [PATCH 05/28] drm/i915: Add an implementation for i915_gem_ww_ctx locking, v2.
Maarten Lankhorst
- [PATCH 06/28] drm/i915: Remove locking from i915_gem_object_prepare_read/write
Maarten Lankhorst
- [PATCH 07/28] drm/i915: Parse command buffer earlier in eb_relocate(slow)
Maarten Lankhorst
- [PATCH 08/28] drm/i915: Use per object locking in execbuf, v12.
Maarten Lankhorst
- [PATCH 09/28] drm/i915: Use ww locking in intel_renderstate.
Maarten Lankhorst
- [PATCH 10/28] drm/i915: Add ww context handling to context_barrier_task
Maarten Lankhorst
- [PATCH 11/28] drm/i915: Nuke arguments to eb_pin_engine
Maarten Lankhorst
- [PATCH 12/28] drm/i915: Pin engine before pinning all objects, v5.
Maarten Lankhorst
- [PATCH 13/28] drm/i915: Rework intel_context pinning to do everything outside of pin_mutex
Maarten Lankhorst
- [PATCH 14/28] drm/i915: Make sure execbuffer always passes ww state to i915_vma_pin.
Maarten Lankhorst
- [PATCH 15/28] drm/i915: Convert i915_gem_object/client_blt.c to use ww locking as well, v2.
Maarten Lankhorst
- [PATCH 16/28] drm/i915: Kill last user of intel_context_create_request outside of selftests
Maarten Lankhorst
- [PATCH 17/28] drm/i915: Convert i915_perf to ww locking as well
Maarten Lankhorst
- [PATCH 18/28] drm/i915: Dirty hack to fix selftests locking inversion
Maarten Lankhorst
- [PATCH 19/28] drm/i915/selftests: Fix locking inversion in lrc selftest.
Maarten Lankhorst
- [PATCH 20/28] drm/i915: Use ww pinning for intel_context_create_request()
Maarten Lankhorst
- [PATCH 21/28] drm/i915: Move i915_vma_lock in the selftests to avoid lock inversion, v3.
Maarten Lankhorst
- [PATCH 22/28] drm/i915: Add ww locking to vm_fault_gtt
Maarten Lankhorst
- [PATCH 23/28] drm/i915: Add ww locking to pin_to_display_plane
Maarten Lankhorst
- [PATCH 24/28] drm/i915: Ensure we hold the object mutex in pin correctly.
Maarten Lankhorst
- [PATCH 25/28] drm/i915: Add gem object locking to madvise.
Maarten Lankhorst
- [PATCH 26/28] drm/i915: Convert i915_gem_object_attach_phys() to ww locking
Maarten Lankhorst
- [PATCH 27/28] drm/i915: Fix userptr so we do not have to worry about obj->mm.lock
Maarten Lankhorst
- [PATCH 28/28] fixup userptr implementation
Maarten Lankhorst
- [PATCH 01/28] Revert "drm/i915/gem: Async GPU relocations only"
Maarten Lankhorst
- [PATCH 02/28] drm/i915: Revert relocation chaining commits.
Maarten Lankhorst
- [PATCH 03/28] Revert "drm/i915/gem: Drop relocation slowpath".
Maarten Lankhorst
- [PATCH 04/28] Revert "drm/i915/gem: Split eb_vma into its own allocation"
Maarten Lankhorst
- [PATCH 05/28] drm/i915: Add an implementation for i915_gem_ww_ctx locking, v2.
Maarten Lankhorst
- [PATCH 06/28] drm/i915: Remove locking from i915_gem_object_prepare_read/write
Maarten Lankhorst
- [PATCH 07/28] drm/i915: Parse command buffer earlier in eb_relocate(slow)
Maarten Lankhorst
- [PATCH 08/28] drm/i915: Use per object locking in execbuf, v12.
Maarten Lankhorst
- [PATCH 09/28] drm/i915: Use ww locking in intel_renderstate.
Maarten Lankhorst
- [PATCH 10/28] drm/i915: Add ww context handling to context_barrier_task
Maarten Lankhorst
- [PATCH 11/28] drm/i915: Nuke arguments to eb_pin_engine
Maarten Lankhorst
- [PATCH 12/28] drm/i915: Pin engine before pinning all objects, v5.
Maarten Lankhorst
- [PATCH 13/28] drm/i915: Rework intel_context pinning to do everything outside of pin_mutex
Maarten Lankhorst
- [PATCH 14/28] drm/i915: Make sure execbuffer always passes ww state to i915_vma_pin.
Maarten Lankhorst
- [PATCH 15/28] drm/i915: Convert i915_gem_object/client_blt.c to use ww locking as well, v2.
Maarten Lankhorst
- [PATCH 16/28] drm/i915: Kill last user of intel_context_create_request outside of selftests
Maarten Lankhorst
- [PATCH 17/28] drm/i915: Convert i915_perf to ww locking as well
Maarten Lankhorst
- [PATCH 18/28] drm/i915: Dirty hack to fix selftests locking inversion
Maarten Lankhorst
- [PATCH 19/28] drm/i915/selftests: Fix locking inversion in lrc selftest.
Maarten Lankhorst
- [PATCH 20/28] drm/i915: Use ww pinning for intel_context_create_request()
Maarten Lankhorst
- [PATCH 21/28] drm/i915: Move i915_vma_lock in the selftests to avoid lock inversion, v3.
Maarten Lankhorst
- [PATCH 22/28] drm/i915: Add ww locking to vm_fault_gtt
Maarten Lankhorst
- [PATCH 23/28] drm/i915: Add ww locking to pin_to_display_plane
Maarten Lankhorst
- [PATCH 24/28] drm/i915: Ensure we hold the object mutex in pin correctly.
Maarten Lankhorst
- [PATCH 25/28] drm/i915: Add gem object locking to madvise.
Maarten Lankhorst
- [PATCH 26/28] drm/i915: Convert i915_gem_object_attach_phys() to ww locking
Maarten Lankhorst
- [PATCH 27/28] drm/i915: Fix userptr so we do not have to worry about obj->mm.lock
Maarten Lankhorst
- [PATCH 28/28] fixup userptr implementation
Maarten Lankhorst
- [PATCH 01/29] Revert "drm/i915/gem: Async GPU relocations only"
Maarten Lankhorst
- [PATCH 02/29] drm/i915: Revert relocation chaining commits.
Maarten Lankhorst
- [PATCH 03/29] Revert "drm/i915/gem: Drop relocation slowpath".
Maarten Lankhorst
- [PATCH 04/29] Revert "drm/i915/gem: Split eb_vma into its own allocation"
Maarten Lankhorst
- [PATCH 05/29] drm/i915: Add an implementation for i915_gem_ww_ctx locking, v2.
Maarten Lankhorst
- [PATCH 06/29] drm/i915: Remove locking from i915_gem_object_prepare_read/write
Maarten Lankhorst
- [PATCH 07/29] drm/i915: Parse command buffer earlier in eb_relocate(slow)
Maarten Lankhorst
- [PATCH 08/29] drm/i915: Use per object locking in execbuf, v12.
Maarten Lankhorst
- [PATCH 09/29] drm/i915: Use ww locking in intel_renderstate.
Maarten Lankhorst
- [PATCH 10/29] drm/i915: Add ww context handling to context_barrier_task
Maarten Lankhorst
- [PATCH 11/29] drm/i915: Nuke arguments to eb_pin_engine
Maarten Lankhorst
- [PATCH 12/29] drm/i915: Pin engine before pinning all objects, v5.
Maarten Lankhorst
- [PATCH 13/29] drm/i915: Rework intel_context pinning to do everything outside of pin_mutex
Maarten Lankhorst
- [PATCH 14/29] drm/i915: Make sure execbuffer always passes ww state to i915_vma_pin.
Maarten Lankhorst
- [PATCH 15/29] drm/i915: Convert i915_gem_object/client_blt.c to use ww locking as well, v2.
Maarten Lankhorst
- [PATCH 16/29] drm/i915: Kill last user of intel_context_create_request outside of selftests
Maarten Lankhorst
- [PATCH 17/29] drm/i915: Convert i915_perf to ww locking as well
Maarten Lankhorst
- [PATCH 18/29] drm/i915: Dirty hack to fix selftests locking inversion
Maarten Lankhorst
- [PATCH 19/29] drm/i915/selftests: Fix locking inversion in lrc selftest.
Maarten Lankhorst
- [PATCH 20/29] drm/i915: Use ww pinning for intel_context_create_request()
Maarten Lankhorst
- [PATCH 21/29] drm/i915: Move i915_vma_lock in the selftests to avoid lock inversion, v3.
Maarten Lankhorst
- [PATCH 22/29] drm/i915: Add ww locking to vm_fault_gtt
Maarten Lankhorst
- [PATCH 23/29] drm/i915: Add ww locking to pin_to_display_plane
Maarten Lankhorst
- [PATCH 24/29] drm/i915: Ensure we hold the object mutex in pin correctly.
Maarten Lankhorst
- [PATCH 25/29] drm/i915: Add gem object locking to madvise.
Maarten Lankhorst
- [PATCH 26/29] drm/i915: Convert i915_gem_object_attach_phys() to ww locking
Maarten Lankhorst
- [PATCH 27/29] drm/i915: Fix userptr so we do not have to worry about obj->mm.lock
Maarten Lankhorst
- [PATCH 28/29] drm/i915: Flatten obj->mm.lock
Maarten Lankhorst
- [PATCH 29/29] make lockdep slightly happier
Maarten Lankhorst
- [PATCH 01/28] Revert "drm/i915/gem: Async GPU relocations only"
Maarten Lankhorst
- [PATCH 02/28] drm/i915: Revert relocation chaining commits.
Maarten Lankhorst
- [PATCH 03/28] Revert "drm/i915/gem: Drop relocation slowpath".
Maarten Lankhorst
- [PATCH 04/28] Revert "drm/i915/gem: Split eb_vma into its own allocation"
Maarten Lankhorst
- [PATCH 05/28] drm/i915: Add an implementation for i915_gem_ww_ctx locking, v2.
Maarten Lankhorst
- [PATCH 06/28] drm/i915: Remove locking from i915_gem_object_prepare_read/write
Maarten Lankhorst
- [PATCH 07/28] drm/i915: Parse command buffer earlier in eb_relocate(slow)
Maarten Lankhorst
- [PATCH 01/29] Revert "drm/i915/gem: Async GPU relocations only"
Maarten Lankhorst
- [PATCH 08/28] drm/i915: Use per object locking in execbuf, v12.
Maarten Lankhorst
- [PATCH 02/29] drm/i915: Revert relocation chaining commits.
Maarten Lankhorst
- [PATCH 09/28] drm/i915: Use ww locking in intel_renderstate.
Maarten Lankhorst
- [PATCH 03/29] Revert "drm/i915/gem: Drop relocation slowpath".
Maarten Lankhorst
- [PATCH 10/28] drm/i915: Add ww context handling to context_barrier_task
Maarten Lankhorst
- [PATCH 04/29] Revert "drm/i915/gem: Split eb_vma into its own allocation"
Maarten Lankhorst
- [PATCH 11/28] drm/i915: Nuke arguments to eb_pin_engine
Maarten Lankhorst
- [PATCH 05/29] drm/i915: Add an implementation for i915_gem_ww_ctx locking, v2.
Maarten Lankhorst
- [PATCH 12/28] drm/i915: Pin engine before pinning all objects, v5.
Maarten Lankhorst
- [PATCH 06/29] drm/i915: Remove locking from i915_gem_object_prepare_read/write
Maarten Lankhorst
- [PATCH 13/28] drm/i915: Rework intel_context pinning to do everything outside of pin_mutex
Maarten Lankhorst
- [PATCH 07/29] drm/i915: Parse command buffer earlier in eb_relocate(slow)
Maarten Lankhorst
- [PATCH 14/28] drm/i915: Make sure execbuffer always passes ww state to i915_vma_pin.
Maarten Lankhorst
- [PATCH 08/29] drm/i915: Use per object locking in execbuf, v12.
Maarten Lankhorst
- [PATCH 15/28] drm/i915: Convert i915_gem_object/client_blt.c to use ww locking as well, v2.
Maarten Lankhorst
- [PATCH 09/29] drm/i915: Use ww locking in intel_renderstate.
Maarten Lankhorst
- [PATCH 16/28] drm/i915: Kill last user of intel_context_create_request outside of selftests
Maarten Lankhorst
- [PATCH 10/29] drm/i915: Add ww context handling to context_barrier_task
Maarten Lankhorst
- [PATCH 17/28] drm/i915: Convert i915_perf to ww locking as well
Maarten Lankhorst
- [PATCH 11/29] drm/i915: Nuke arguments to eb_pin_engine
Maarten Lankhorst
- [PATCH 18/28] drm/i915: Dirty hack to fix selftests locking inversion
Maarten Lankhorst
- [PATCH 12/29] drm/i915: Pin engine before pinning all objects, v5.
Maarten Lankhorst
- [PATCH 19/28] drm/i915/selftests: Fix locking inversion in lrc selftest.
Maarten Lankhorst
- [PATCH 13/29] drm/i915: Rework intel_context pinning to do everything outside of pin_mutex
Maarten Lankhorst
- [PATCH 20/28] drm/i915: Use ww pinning for intel_context_create_request()
Maarten Lankhorst
- [PATCH 14/29] drm/i915: Make sure execbuffer always passes ww state to i915_vma_pin.
Maarten Lankhorst
- [PATCH 21/28] drm/i915: Move i915_vma_lock in the selftests to avoid lock inversion, v3.
Maarten Lankhorst
- [PATCH 15/29] drm/i915: Convert i915_gem_object/client_blt.c to use ww locking as well, v2.
Maarten Lankhorst
- [PATCH 22/28] drm/i915: Add ww locking to vm_fault_gtt
Maarten Lankhorst
- [PATCH 16/29] drm/i915: Kill last user of intel_context_create_request outside of selftests
Maarten Lankhorst
- [PATCH 23/28] drm/i915: Add ww locking to pin_to_display_plane
Maarten Lankhorst
- [PATCH 17/29] drm/i915: Convert i915_perf to ww locking as well
Maarten Lankhorst
- [PATCH 24/28] drm/i915: Ensure we hold the object mutex in pin correctly.
Maarten Lankhorst
- [PATCH 18/29] drm/i915: Dirty hack to fix selftests locking inversion
Maarten Lankhorst
- [PATCH 25/28] drm/i915: Add gem object locking to madvise.
Maarten Lankhorst
- [PATCH 19/29] drm/i915/selftests: Fix locking inversion in lrc selftest.
Maarten Lankhorst
- [PATCH 26/28] drm/i915: Convert i915_gem_object_attach_phys() to ww locking
Maarten Lankhorst
- [PATCH 20/29] drm/i915: Use ww pinning for intel_context_create_request()
Maarten Lankhorst
- [PATCH 27/28] drm/i915: Fix userptr so we do not have to worry about obj->mm.lock
Maarten Lankhorst
- [PATCH 21/29] drm/i915: Move i915_vma_lock in the selftests to avoid lock inversion, v3.
Maarten Lankhorst
- [PATCH 28/28] make lockdep slightly happier
Maarten Lankhorst
- [PATCH 22/29] drm/i915: Add ww locking to vm_fault_gtt
Maarten Lankhorst
- [PATCH 23/29] drm/i915: Add ww locking to pin_to_display_plane
Maarten Lankhorst
- [PATCH 24/29] drm/i915: Ensure we hold the object mutex in pin correctly.
Maarten Lankhorst
- [PATCH 25/29] drm/i915: Add gem object locking to madvise.
Maarten Lankhorst
- [PATCH 26/29] drm/i915: Convert i915_gem_object_attach_phys() to ww locking
Maarten Lankhorst
- [PATCH 27/29] drm/i915: Fix userptr so we do not have to worry about obj->mm.lock
Maarten Lankhorst
- [PATCH 28/29] make lockdep slightly happier
Maarten Lankhorst
- [PATCH 29/29] drm/i915: Flatten obj->mm.lock
Maarten Lankhorst
- [PATCH 01/31] Revert "drm/i915/gem: Async GPU relocations only"
Maarten Lankhorst
- [PATCH 02/31] drm/i915: Revert relocation chaining commits.
Maarten Lankhorst
- [PATCH 03/31] Revert "drm/i915/gem: Drop relocation slowpath".
Maarten Lankhorst
- [PATCH 04/31] Revert "drm/i915/gem: Split eb_vma into its own allocation"
Maarten Lankhorst
- [PATCH 05/31] drm/i915: Add an implementation for i915_gem_ww_ctx locking, v2.
Maarten Lankhorst
- [PATCH 06/31] drm/i915: Remove locking from i915_gem_object_prepare_read/write
Maarten Lankhorst
- [PATCH 07/31] drm/i915: Parse command buffer earlier in eb_relocate(slow)
Maarten Lankhorst
- [PATCH 08/31] drm/i915: Use per object locking in execbuf, v12.
Maarten Lankhorst
- [PATCH 09/31] drm/i915: Use ww locking in intel_renderstate.
Maarten Lankhorst
- [PATCH 10/31] drm/i915: Add ww context handling to context_barrier_task
Maarten Lankhorst
- [PATCH 11/31] drm/i915: Nuke arguments to eb_pin_engine
Maarten Lankhorst
- [PATCH 12/31] drm/i915: Pin engine before pinning all objects, v5.
Maarten Lankhorst
- [PATCH 13/31] drm/i915: Rework intel_context pinning to do everything outside of pin_mutex
Maarten Lankhorst
- [PATCH 14/31] drm/i915: Make sure execbuffer always passes ww state to i915_vma_pin.
Maarten Lankhorst
- [PATCH 15/31] drm/i915: Convert i915_gem_object/client_blt.c to use ww locking as well, v2.
Maarten Lankhorst
- [PATCH 16/31] drm/i915: Kill last user of intel_context_create_request outside of selftests
Maarten Lankhorst
- [PATCH 17/31] drm/i915: Convert i915_perf to ww locking as well
Maarten Lankhorst
- [PATCH 18/31] drm/i915: Dirty hack to fix selftests locking inversion
Maarten Lankhorst
- [PATCH 19/31] drm/i915/selftests: Fix locking inversion in lrc selftest.
Maarten Lankhorst
- [PATCH 20/31] drm/i915: Use ww pinning for intel_context_create_request()
Maarten Lankhorst
- [PATCH 21/31] drm/i915: Move i915_vma_lock in the selftests to avoid lock inversion, v3.
Maarten Lankhorst
- [PATCH 22/31] drm/i915: Add ww locking to vm_fault_gtt
Maarten Lankhorst
- [PATCH 23/31] drm/i915: Add ww locking to pin_to_display_plane
Maarten Lankhorst
- [PATCH 24/31] drm/i915: Ensure we hold the object mutex in pin correctly.
Maarten Lankhorst
- [PATCH 25/31] drm/i915: Add gem object locking to madvise.
Maarten Lankhorst
- [PATCH 26/31] drm/i915: Convert i915_gem_object_attach_phys() to ww locking
Maarten Lankhorst
- [PATCH 27/31] drm/i915: Fix userptr so we do not have to worry about obj->mm.lock
Maarten Lankhorst
- [PATCH 28/31] make lockdep slightly happier
Maarten Lankhorst
- [PATCH 29/31] drm/i915: Flatten obj->mm.lock
Maarten Lankhorst
- [PATCH 30/31] drm/i915: Add freed object debugging by freeing synchronously.
Maarten Lankhorst
- [PATCH 31/31] remove obj->mm.lock
Maarten Lankhorst
- [PATCH 01/29] Revert "drm/i915/gem: Async GPU relocations only"
Maarten Lankhorst
- [PATCH 02/29] drm/i915: Revert relocation chaining commits.
Maarten Lankhorst
- [PATCH 03/29] Revert "drm/i915/gem: Drop relocation slowpath".
Maarten Lankhorst
- [PATCH 04/29] Revert "drm/i915/gem: Split eb_vma into its own allocation"
Maarten Lankhorst
- [PATCH 05/29] drm/i915: Add an implementation for i915_gem_ww_ctx locking, v2.
Maarten Lankhorst
- [PATCH 06/29] drm/i915: Remove locking from i915_gem_object_prepare_read/write
Maarten Lankhorst
- [PATCH 07/29] drm/i915: Parse command buffer earlier in eb_relocate(slow)
Maarten Lankhorst
- [PATCH 08/29] drm/i915: Use per object locking in execbuf, v12.
Maarten Lankhorst
- [PATCH 09/29] drm/i915: make lockdep slightly happier about execbuf.
Maarten Lankhorst
- [PATCH 10/29] drm/i915: Use ww locking in intel_renderstate.
Maarten Lankhorst
- [PATCH 11/29] drm/i915: Add ww context handling to context_barrier_task
Maarten Lankhorst
- [PATCH 12/29] drm/i915: Nuke arguments to eb_pin_engine
Maarten Lankhorst
- [PATCH 13/29] drm/i915: Pin engine before pinning all objects, v5.
Maarten Lankhorst
- [PATCH 14/29] drm/i915: Rework intel_context pinning to do everything outside of pin_mutex
Maarten Lankhorst
- [PATCH 15/29] drm/i915: Make sure execbuffer always passes ww state to i915_vma_pin.
Maarten Lankhorst
- [PATCH 16/29] drm/i915: Convert i915_gem_object/client_blt.c to use ww locking as well, v2.
Maarten Lankhorst
- [PATCH 17/29] drm/i915: Kill last user of intel_context_create_request outside of selftests
Maarten Lankhorst
- [PATCH 18/29] drm/i915: Convert i915_perf to ww locking as well
Maarten Lankhorst
- [PATCH 19/29] drm/i915: Dirty hack to fix selftests locking inversion
Maarten Lankhorst
- [PATCH 20/29] drm/i915/selftests: Fix locking inversion in lrc selftest.
Maarten Lankhorst
- [PATCH 21/29] drm/i915: Use ww pinning for intel_context_create_request()
Maarten Lankhorst
- [PATCH 22/29] drm/i915: Move i915_vma_lock in the selftests to avoid lock inversion, v3.
Maarten Lankhorst
- [PATCH 23/29] drm/i915: Add ww locking to vm_fault_gtt
Maarten Lankhorst
- [PATCH 24/29] drm/i915: Add ww locking to pin_to_display_plane
Maarten Lankhorst
- [PATCH 25/29] drm/i915: Ensure we hold the object mutex in pin correctly.
Maarten Lankhorst
- [PATCH 26/29] drm/i915: Add gem object locking to madvise.
Maarten Lankhorst
- [PATCH 27/29] drm/i915: Convert i915_gem_object_attach_phys() to ww locking
Maarten Lankhorst
- [PATCH 28/29] drm/i915: Fix userptr so we do not have to worry about obj->mm.lock
Maarten Lankhorst
- [PATCH 29/29] drm/i915: Flatten obj->mm.lock
Maarten Lankhorst
- [PATCH 01/23] Revert "drm/i915/gem: Async GPU relocations only"
Maarten Lankhorst
- [PATCH 02/23] drm/i915: Revert relocation chaining commits.
Maarten Lankhorst
- [PATCH 03/23] Revert "drm/i915/gem: Drop relocation slowpath".
Maarten Lankhorst
- [PATCH 04/23] Revert "drm/i915/gem: Split eb_vma into its own allocation"
Maarten Lankhorst
- [PATCH 05/23] drm/i915: Add an implementation for i915_gem_ww_ctx locking, v2.
Maarten Lankhorst
- [PATCH 06/23] drm/i915: Remove locking from i915_gem_object_prepare_read/write
Maarten Lankhorst
- [PATCH 07/23] drm/i915: Parse command buffer earlier in eb_relocate(slow)
Maarten Lankhorst
- [PATCH 08/23] drm/i915: Use per object locking in execbuf, v12.
Maarten Lankhorst
- [PATCH 09/23] drm/i915: Use ww locking in intel_renderstate.
Maarten Lankhorst
- [PATCH 10/23] drm/i915: Add ww context handling to context_barrier_task
Maarten Lankhorst
- [PATCH 11/23] drm/i915: Nuke arguments to eb_pin_engine
Maarten Lankhorst
- [PATCH 12/23] drm/i915: Pin engine before pinning all objects, v5.
Maarten Lankhorst
- [PATCH 13/23] drm/i915: Rework intel_context pinning to do everything outside of pin_mutex
Maarten Lankhorst
- [PATCH 14/23] drm/i915: Make sure execbuffer always passes ww state to i915_vma_pin.
Maarten Lankhorst
- [PATCH 15/23] drm/i915: Convert i915_gem_object/client_blt.c to use ww locking as well, v2.
Maarten Lankhorst
- [PATCH 16/23] drm/i915: Kill last user of intel_context_create_request outside of selftests
Maarten Lankhorst
- [PATCH 17/23] drm/i915: Convert i915_perf to ww locking as well
Maarten Lankhorst
- [PATCH 18/23] drm/i915: Dirty hack to fix selftests locking inversion
Maarten Lankhorst
- [PATCH 19/23] drm/i915/selftests: Fix locking inversion in lrc selftest.
Maarten Lankhorst
- [PATCH 20/23] drm/i915: Use ww pinning for intel_context_create_request()
Maarten Lankhorst
- [PATCH 21/23] drm/i915: Move i915_vma_lock in the selftests to avoid lock inversion, v3.
Maarten Lankhorst
- [PATCH 22/23] drm/i915: Add ww locking to vm_fault_gtt
Maarten Lankhorst
- [PATCH 23/23] drm/i915: Add ww locking to pin_to_display_plane
Maarten Lankhorst
- [PATCH 01/27] Revert "drm/i915/gem: Async GPU relocations only"
Maarten Lankhorst
- [PATCH 02/27] drm/i915: Revert relocation chaining commits.
Maarten Lankhorst
- [PATCH 03/27] Revert "drm/i915/gem: Drop relocation slowpath".
Maarten Lankhorst
- [PATCH 04/27] Revert "drm/i915/gem: Split eb_vma into its own allocation"
Maarten Lankhorst
- [PATCH 05/27] drm/i915: Add an implementation for i915_gem_ww_ctx locking, v2.
Maarten Lankhorst
- [PATCH 06/27] drm/i915: Remove locking from i915_gem_object_prepare_read/write
Maarten Lankhorst
- [PATCH 07/27] drm/i915: Parse command buffer earlier in eb_relocate(slow)
Maarten Lankhorst
- [PATCH 08/27] drm/i915: Use per object locking in execbuf, v12.
Maarten Lankhorst
- [PATCH 09/27] drm/i915: Use ww locking in intel_renderstate.
Maarten Lankhorst
- [PATCH 10/27] drm/i915: Add ww context handling to context_barrier_task
Maarten Lankhorst
- [PATCH 11/27] drm/i915: Nuke arguments to eb_pin_engine
Maarten Lankhorst
- [PATCH 12/27] drm/i915: Pin engine before pinning all objects, v5.
Maarten Lankhorst
- [PATCH 13/27] drm/i915: Rework intel_context pinning to do everything outside of pin_mutex
Maarten Lankhorst
- [PATCH 14/27] drm/i915: Make sure execbuffer always passes ww state to i915_vma_pin.
Maarten Lankhorst
- [PATCH 15/27] drm/i915: Convert i915_gem_object/client_blt.c to use ww locking as well, v2.
Maarten Lankhorst
- [PATCH 16/27] drm/i915: Kill last user of intel_context_create_request outside of selftests
Maarten Lankhorst
- [PATCH 17/27] drm/i915: Convert i915_perf to ww locking as well
Maarten Lankhorst
- [PATCH 18/27] drm/i915: Dirty hack to fix selftests locking inversion
Maarten Lankhorst
- [PATCH 19/27] drm/i915/selftests: Fix locking inversion in lrc selftest.
Maarten Lankhorst
- [PATCH 20/27] drm/i915: Use ww pinning for intel_context_create_request()
Maarten Lankhorst
- [PATCH 21/27] drm/i915: Move i915_vma_lock in the selftests to avoid lock inversion, v3.
Maarten Lankhorst
- [PATCH 22/27] drm/i915: Add ww locking to vm_fault_gtt
Maarten Lankhorst
- [PATCH 23/27] drm/i915: Add ww locking to pin_to_display_plane
Maarten Lankhorst
- [PATCH 24/27] drm/i915: Ensure we hold the object mutex in pin correctly.
Maarten Lankhorst
- [PATCH 25/27] drm/i915: Add gem object locking to madvise.
Maarten Lankhorst
- [PATCH 26/27] drm/i915: Convert i915_gem_object_attach_phys() to ww locking
Maarten Lankhorst
- [PATCH 27/27] drm/i915: Do not share hwsp across contexts any more
Maarten Lankhorst
- [PATCH 01/27] Revert "drm/i915/gem: Async GPU relocations only"
Maarten Lankhorst
- [PATCH 02/27] drm/i915: Revert relocation chaining commits.
Maarten Lankhorst
- [PATCH 03/27] Revert "drm/i915/gem: Drop relocation slowpath".
Maarten Lankhorst
- [PATCH 04/27] Revert "drm/i915/gem: Split eb_vma into its own allocation"
Maarten Lankhorst
- [PATCH 05/27] drm/i915: Add an implementation for i915_gem_ww_ctx locking, v2.
Maarten Lankhorst
- [PATCH 06/27] drm/i915: Remove locking from i915_gem_object_prepare_read/write
Maarten Lankhorst
- [PATCH 07/27] drm/i915: Parse command buffer earlier in eb_relocate(slow)
Maarten Lankhorst
- [PATCH 08/27] drm/i915: Use per object locking in execbuf, v12.
Maarten Lankhorst
- [PATCH 09/27] drm/i915: Use ww locking in intel_renderstate.
Maarten Lankhorst
- [PATCH 10/27] drm/i915: Add ww context handling to context_barrier_task
Maarten Lankhorst
- [PATCH 11/27] drm/i915: Nuke arguments to eb_pin_engine
Maarten Lankhorst
- [PATCH 12/27] drm/i915: Pin engine before pinning all objects, v5.
Maarten Lankhorst
- [PATCH 13/27] drm/i915: Rework intel_context pinning to do everything outside of pin_mutex
Maarten Lankhorst
- [PATCH 14/27] drm/i915: Make sure execbuffer always passes ww state to i915_vma_pin.
Maarten Lankhorst
- [PATCH 15/27] drm/i915: Convert i915_gem_object/client_blt.c to use ww locking as well, v2.
Maarten Lankhorst
- [PATCH 16/27] drm/i915: Kill last user of intel_context_create_request outside of selftests
Maarten Lankhorst
- [PATCH 17/27] drm/i915: Convert i915_perf to ww locking as well
Maarten Lankhorst
- [PATCH 18/27] drm/i915: Dirty hack to fix selftests locking inversion
Maarten Lankhorst
- [PATCH 19/27] drm/i915/selftests: Fix locking inversion in lrc selftest.
Maarten Lankhorst
- [PATCH 20/27] drm/i915: Use ww pinning for intel_context_create_request()
Maarten Lankhorst
- [PATCH 21/27] drm/i915: Move i915_vma_lock in the selftests to avoid lock inversion, v3.
Maarten Lankhorst
- [PATCH 22/27] drm/i915: Add ww locking to vm_fault_gtt
Maarten Lankhorst
- [PATCH 23/27] drm/i915: Add ww locking to pin_to_display_plane
Maarten Lankhorst
- [PATCH 24/27] drm/i915: Ensure we hold the object mutex in pin correctly.
Maarten Lankhorst
- [PATCH 25/27] drm/i915: Add gem object locking to madvise.
Maarten Lankhorst
- [PATCH 26/27] drm/i915: Convert i915_gem_object_attach_phys() to ww locking
Maarten Lankhorst
- [PATCH 27/27] FIXME: drm/i915: Do not share hwsp across contexts any more
Maarten Lankhorst
- [PATCH 01/27] Revert "drm/i915/gem: Async GPU relocations only"
Maarten Lankhorst
- [PATCH 02/27] drm/i915: Revert relocation chaining commits.
Maarten Lankhorst
- [PATCH 03/27] Revert "drm/i915/gem: Drop relocation slowpath".
Maarten Lankhorst
- [PATCH 04/27] Revert "drm/i915/gem: Split eb_vma into its own allocation"
Maarten Lankhorst
- [PATCH 05/27] drm/i915: Add an implementation for i915_gem_ww_ctx locking, v2.
Maarten Lankhorst
- [PATCH 06/27] drm/i915: Remove locking from i915_gem_object_prepare_read/write
Maarten Lankhorst
- [PATCH 07/27] drm/i915: Parse command buffer earlier in eb_relocate(slow)
Maarten Lankhorst
- [PATCH 08/27] drm/i915: Use per object locking in execbuf, v12.
Maarten Lankhorst
- [PATCH 09/27] drm/i915: Use ww locking in intel_renderstate.
Maarten Lankhorst
- [PATCH 10/27] drm/i915: Add ww context handling to context_barrier_task
Maarten Lankhorst
- [PATCH 11/27] drm/i915: Nuke arguments to eb_pin_engine
Maarten Lankhorst
- [PATCH 12/27] drm/i915: Pin engine before pinning all objects, v5.
Maarten Lankhorst
- [PATCH 13/27] drm/i915: Rework intel_context pinning to do everything outside of pin_mutex
Maarten Lankhorst
- [PATCH 14/27] drm/i915: Make sure execbuffer always passes ww state to i915_vma_pin.
Maarten Lankhorst
- [PATCH 15/27] drm/i915: Convert i915_gem_object/client_blt.c to use ww locking as well, v2.
Maarten Lankhorst
- [PATCH 16/27] drm/i915: Kill last user of intel_context_create_request outside of selftests
Maarten Lankhorst
- [PATCH 17/27] drm/i915: Convert i915_perf to ww locking as well
Maarten Lankhorst
- [PATCH 18/27] drm/i915: Dirty hack to fix selftests locking inversion
Maarten Lankhorst
- [PATCH 19/27] drm/i915/selftests: Fix locking inversion in lrc selftest.
Maarten Lankhorst
- [PATCH 20/27] drm/i915: Use ww pinning for intel_context_create_request()
Maarten Lankhorst
- [PATCH 21/27] drm/i915: Move i915_vma_lock in the selftests to avoid lock inversion, v3.
Maarten Lankhorst
- [PATCH 22/27] drm/i915: Add ww locking to vm_fault_gtt
Maarten Lankhorst
- [PATCH 23/27] drm/i915: Add ww locking to pin_to_display_plane
Maarten Lankhorst
- [PATCH 24/27] drm/i915: Ensure we hold the object mutex in pin correctly.
Maarten Lankhorst
- [PATCH 25/27] drm/i915: Add gem object locking to madvise.
Maarten Lankhorst
- [PATCH 26/27] drm/i915: Convert i915_gem_object_attach_phys() to ww locking
Maarten Lankhorst
- [PATCH 27/27] drm/i915: Do not share hwsp across contexts any more
Maarten Lankhorst
- [PATCH 01/27] Revert "drm/i915/gem: Async GPU relocations only"
Maarten Lankhorst
- [PATCH 02/27] drm/i915: Revert relocation chaining commits.
Maarten Lankhorst
- [PATCH 03/27] Revert "drm/i915/gem: Drop relocation slowpath".
Maarten Lankhorst
- [PATCH 04/27] Revert "drm/i915/gem: Split eb_vma into its own allocation"
Maarten Lankhorst
- [PATCH 05/27] drm/i915: Add an implementation for i915_gem_ww_ctx locking, v2.
Maarten Lankhorst
- [PATCH 06/27] drm/i915: Remove locking from i915_gem_object_prepare_read/write
Maarten Lankhorst
- [PATCH 07/27] drm/i915: Parse command buffer earlier in eb_relocate(slow)
Maarten Lankhorst
- [PATCH 08/27] drm/i915: Use per object locking in execbuf, v12.
Maarten Lankhorst
- [PATCH 09/27] drm/i915: Use ww locking in intel_renderstate.
Maarten Lankhorst
- [PATCH 10/27] drm/i915: Add ww context handling to context_barrier_task
Maarten Lankhorst
- [PATCH 11/27] drm/i915: Nuke arguments to eb_pin_engine
Maarten Lankhorst
- [PATCH 12/27] drm/i915: Pin engine before pinning all objects, v5.
Maarten Lankhorst
- [PATCH 13/27] drm/i915: Rework intel_context pinning to do everything outside of pin_mutex
Maarten Lankhorst
- [PATCH 14/27] drm/i915: Make sure execbuffer always passes ww state to i915_vma_pin.
Maarten Lankhorst
- [PATCH 15/27] drm/i915: Convert i915_gem_object/client_blt.c to use ww locking as well, v2.
Maarten Lankhorst
- [PATCH 16/27] drm/i915: Kill last user of intel_context_create_request outside of selftests
Maarten Lankhorst
- [PATCH 17/27] drm/i915: Convert i915_perf to ww locking as well
Maarten Lankhorst
- [PATCH 18/27] drm/i915: Dirty hack to fix selftests locking inversion
Maarten Lankhorst
- [PATCH 19/27] drm/i915/selftests: Fix locking inversion in lrc selftest.
Maarten Lankhorst
- [PATCH 20/27] drm/i915: Use ww pinning for intel_context_create_request()
Maarten Lankhorst
- [PATCH 21/27] drm/i915: Move i915_vma_lock in the selftests to avoid lock inversion, v3.
Maarten Lankhorst
- [PATCH 22/27] drm/i915: Add ww locking to vm_fault_gtt
Maarten Lankhorst
- [PATCH 23/27] drm/i915: Add ww locking to pin_to_display_plane
Maarten Lankhorst
- [PATCH 24/27] drm/i915: Ensure we hold the object mutex in pin correctly.
Maarten Lankhorst
- [PATCH 25/27] drm/i915: Add gem object locking to madvise.
Maarten Lankhorst
- [PATCH 26/27] drm/i915: Convert i915_gem_object_attach_phys() to ww locking
Maarten Lankhorst
- [PATCH 27/27] drm/i915: Do not share hwsp across contexts any more
Maarten Lankhorst
- [PATCH 01/29] Revert "drm/i915/gem: Async GPU relocations only"
Maarten Lankhorst
- [PATCH 02/29] drm/i915: Revert relocation chaining commits.
Maarten Lankhorst
- [PATCH 03/29] Revert "drm/i915/gem: Drop relocation slowpath".
Maarten Lankhorst
- [PATCH 04/29] Revert "drm/i915/gem: Split eb_vma into its own allocation"
Maarten Lankhorst
- [PATCH 05/29] drm/i915: Add an implementation for i915_gem_ww_ctx locking, v2.
Maarten Lankhorst
- [PATCH 06/29] drm/i915: Remove locking from i915_gem_object_prepare_read/write
Maarten Lankhorst
- [PATCH 07/29] drm/i915: Parse command buffer earlier in eb_relocate(slow)
Maarten Lankhorst
- [PATCH 01/30] Revert "drm/i915/gem: Async GPU relocations only"
Maarten Lankhorst
- [PATCH 08/29] drm/i915: Use per object locking in execbuf, v12.
Maarten Lankhorst
- [PATCH 02/30] drm/i915: Revert relocation chaining commits.
Maarten Lankhorst
- [PATCH 09/29] drm/i915: Use ww locking in intel_renderstate.
Maarten Lankhorst
- [PATCH 03/30] Revert "drm/i915/gem: Drop relocation slowpath".
Maarten Lankhorst
- [PATCH 10/29] drm/i915: Add ww context handling to context_barrier_task
Maarten Lankhorst
- [PATCH 04/30] Revert "drm/i915/gem: Split eb_vma into its own allocation"
Maarten Lankhorst
- [PATCH 11/29] drm/i915: Nuke arguments to eb_pin_engine
Maarten Lankhorst
- [PATCH 05/30] drm/i915: Add an implementation for i915_gem_ww_ctx locking, v2.
Maarten Lankhorst
- [PATCH 12/29] drm/i915: Pin engine before pinning all objects, v5.
Maarten Lankhorst
- [PATCH 06/30] drm/i915: Remove locking from i915_gem_object_prepare_read/write
Maarten Lankhorst
- [PATCH 13/29] drm/i915: Rework intel_context pinning to do everything outside of pin_mutex
Maarten Lankhorst
- [PATCH 07/30] drm/i915: Parse command buffer earlier in eb_relocate(slow)
Maarten Lankhorst
- [PATCH 14/29] drm/i915: Make sure execbuffer always passes ww state to i915_vma_pin.
Maarten Lankhorst
- [PATCH 08/30] drm/i915: Use per object locking in execbuf, v12.
Maarten Lankhorst
- [PATCH 15/29] drm/i915: Convert i915_gem_object/client_blt.c to use ww locking as well, v2.
Maarten Lankhorst
- [PATCH 09/30] drm/i915: Use ww locking in intel_renderstate.
Maarten Lankhorst
- [PATCH 16/29] drm/i915: Kill last user of intel_context_create_request outside of selftests
Maarten Lankhorst
- [PATCH 10/30] drm/i915: Add ww context handling to context_barrier_task
Maarten Lankhorst
- [PATCH 17/29] drm/i915: Convert i915_perf to ww locking as well
Maarten Lankhorst
- [PATCH 11/30] drm/i915: Nuke arguments to eb_pin_engine
Maarten Lankhorst
- [PATCH 18/29] drm/i915: Dirty hack to fix selftests locking inversion
Maarten Lankhorst
- [PATCH 12/30] drm/i915: Pin engine before pinning all objects, v5.
Maarten Lankhorst
- [PATCH 19/29] drm/i915/selftests: Fix locking inversion in lrc selftest.
Maarten Lankhorst
- [PATCH 13/30] drm/i915: Rework intel_context pinning to do everything outside of pin_mutex
Maarten Lankhorst
- [PATCH 20/29] drm/i915: Use ww pinning for intel_context_create_request()
Maarten Lankhorst
- [PATCH 14/30] drm/i915: Make sure execbuffer always passes ww state to i915_vma_pin.
Maarten Lankhorst
- [PATCH 21/29] drm/i915: Move i915_vma_lock in the selftests to avoid lock inversion, v3.
Maarten Lankhorst
- [PATCH 15/30] drm/i915: Convert i915_gem_object/client_blt.c to use ww locking as well, v2.
Maarten Lankhorst
- [PATCH 22/29] drm/i915: Add ww locking to vm_fault_gtt
Maarten Lankhorst
- [PATCH 16/30] drm/i915: Kill last user of intel_context_create_request outside of selftests
Maarten Lankhorst
- [PATCH 23/29] drm/i915: Add ww locking to pin_to_display_plane
Maarten Lankhorst
- [PATCH 17/30] drm/i915: Convert i915_perf to ww locking as well
Maarten Lankhorst
- [PATCH 24/29] drm/i915: Ensure we hold the object mutex in pin correctly.
Maarten Lankhorst
- [PATCH 18/30] drm/i915: Dirty hack to fix selftests locking inversion
Maarten Lankhorst
- [PATCH 25/29] drm/i915: Add gem object locking to madvise.
Maarten Lankhorst
- [PATCH 19/30] drm/i915/selftests: Fix locking inversion in lrc selftest.
Maarten Lankhorst
- [PATCH 26/29] drm/i915: Convert i915_gem_object_attach_phys() to ww locking
Maarten Lankhorst
- [PATCH 20/30] drm/i915: Use ww pinning for intel_context_create_request()
Maarten Lankhorst
- [PATCH 27/29] drm/i915: Do not share hwsp across contexts any more
Maarten Lankhorst
- [PATCH 21/30] drm/i915: Move i915_vma_lock in the selftests to avoid lock inversion, v3.
Maarten Lankhorst
- [PATCH 28/29] drm/i915: make lockdep slightly happier about execbuf.
Maarten Lankhorst
- [PATCH 22/30] drm/i915: Add ww locking to vm_fault_gtt
Maarten Lankhorst
- [PATCH 29/29] drm/i915: Fix userptr so we do not have to worry about obj->mm.lock
Maarten Lankhorst
- [PATCH 23/30] drm/i915: Add ww locking to pin_to_display_plane
Maarten Lankhorst
- [PATCH 24/30] drm/i915: Ensure we hold the object mutex in pin correctly.
Maarten Lankhorst
- [PATCH 25/30] drm/i915: Add gem object locking to madvise.
Maarten Lankhorst
- [PATCH 26/30] drm/i915: Convert i915_gem_object_attach_phys() to ww locking
Maarten Lankhorst
- [PATCH 27/30] drm/i915: Do not share hwsp across contexts any more
Maarten Lankhorst
- [PATCH 28/30] drm/i915: make lockdep slightly happier about execbuf.
Maarten Lankhorst
- [PATCH 29/30] drm/i915: Fix userptr so we do not have to worry about obj->mm.lock
Maarten Lankhorst
- [PATCH 30/30] drm/i915: Flatten obj->mm.lock
Maarten Lankhorst
- [PATCH 01/27] Revert "drm/i915/gem: Async GPU relocations only"
Maarten Lankhorst
- [PATCH 02/27] drm/i915: Revert relocation chaining commits.
Maarten Lankhorst
- [PATCH 03/27] Revert "drm/i915/gem: Drop relocation slowpath".
Maarten Lankhorst
- [PATCH 04/27] Revert "drm/i915/gem: Split eb_vma into its own allocation"
Maarten Lankhorst
- [PATCH 05/27] drm/i915: Add an implementation for i915_gem_ww_ctx locking, v2.
Maarten Lankhorst
- [PATCH 06/27] drm/i915: Remove locking from i915_gem_object_prepare_read/write
Maarten Lankhorst
- [PATCH 07/27] drm/i915: Parse command buffer earlier in eb_relocate(slow)
Maarten Lankhorst
- [PATCH 08/27] drm/i915: Use per object locking in execbuf, v12.
Maarten Lankhorst
- [PATCH 09/27] drm/i915: Use ww locking in intel_renderstate.
Maarten Lankhorst
- [PATCH 10/27] drm/i915: Add ww context handling to context_barrier_task
Maarten Lankhorst
- [PATCH 11/27] drm/i915: Nuke arguments to eb_pin_engine
Maarten Lankhorst
- [PATCH 12/27] drm/i915: Pin engine before pinning all objects, v5.
Maarten Lankhorst
- [PATCH 13/27] drm/i915: Rework intel_context pinning to do everything outside of pin_mutex
Maarten Lankhorst
- [PATCH 14/27] drm/i915: Make sure execbuffer always passes ww state to i915_vma_pin.
Maarten Lankhorst
- [PATCH 15/27] drm/i915: Convert i915_gem_object/client_blt.c to use ww locking as well, v2.
Maarten Lankhorst
- [PATCH 16/27] drm/i915: Kill last user of intel_context_create_request outside of selftests
Maarten Lankhorst
- [PATCH 17/27] drm/i915: Convert i915_perf to ww locking as well
Maarten Lankhorst
- [PATCH 18/27] drm/i915: Dirty hack to fix selftests locking inversion
Maarten Lankhorst
- [PATCH 19/27] drm/i915/selftests: Fix locking inversion in lrc selftest.
Maarten Lankhorst
- [PATCH 20/27] drm/i915: Use ww pinning for intel_context_create_request()
Maarten Lankhorst
- [PATCH 21/27] drm/i915: Move i915_vma_lock in the selftests to avoid lock inversion, v3.
Maarten Lankhorst
- [PATCH 22/27] drm/i915: Add ww locking to vm_fault_gtt
Maarten Lankhorst
- [PATCH 23/27] drm/i915: Add ww locking to pin_to_display_plane
Maarten Lankhorst
- [PATCH 24/27] drm/i915: Ensure we hold the object mutex in pin correctly.
Maarten Lankhorst
- [PATCH 25/27] drm/i915: Add gem object locking to madvise.
Maarten Lankhorst
- [PATCH 26/27] drm/i915: Convert i915_gem_object_attach_phys() to ww locking
Maarten Lankhorst
- [PATCH 27/27] drm/i915: Do not share hwsp across contexts any more
Maarten Lankhorst
- [PATCH 01/30] Revert "drm/i915/gem: Async GPU relocations only"
Maarten Lankhorst
- [PATCH 02/30] drm/i915: Revert relocation chaining commits.
Maarten Lankhorst
- [PATCH 03/30] Revert "drm/i915/gem: Drop relocation slowpath".
Maarten Lankhorst
- [PATCH 04/30] Revert "drm/i915/gem: Split eb_vma into its own allocation"
Maarten Lankhorst
- [PATCH 05/30] drm/i915: Add an implementation for i915_gem_ww_ctx locking, v2.
Maarten Lankhorst
- [PATCH 06/30] drm/i915: Remove locking from i915_gem_object_prepare_read/write
Maarten Lankhorst
- [PATCH 07/30] drm/i915: Parse command buffer earlier in eb_relocate(slow)
Maarten Lankhorst
- [PATCH 08/30] drm/i915: Use per object locking in execbuf, v12.
Maarten Lankhorst
- [PATCH 09/30] drm/i915: Use ww locking in intel_renderstate.
Maarten Lankhorst
- [PATCH 10/30] drm/i915: Add ww context handling to context_barrier_task
Maarten Lankhorst
- [PATCH 11/30] drm/i915: Nuke arguments to eb_pin_engine
Maarten Lankhorst
- [PATCH 12/30] drm/i915: Pin engine before pinning all objects, v5.
Maarten Lankhorst
- [PATCH 13/30] drm/i915: Rework intel_context pinning to do everything outside of pin_mutex
Maarten Lankhorst
- [PATCH 14/30] drm/i915: Make sure execbuffer always passes ww state to i915_vma_pin.
Maarten Lankhorst
- [PATCH 15/30] drm/i915: Convert i915_gem_object/client_blt.c to use ww locking as well, v2.
Maarten Lankhorst
- [PATCH 16/30] drm/i915: Kill last user of intel_context_create_request outside of selftests
Maarten Lankhorst
- [PATCH 17/30] drm/i915: Convert i915_perf to ww locking as well
Maarten Lankhorst
- [PATCH 18/30] drm/i915: Dirty hack to fix selftests locking inversion
Maarten Lankhorst
- [PATCH 19/30] drm/i915/selftests: Fix locking inversion in lrc selftest.
Maarten Lankhorst
- [PATCH 20/30] drm/i915: Use ww pinning for intel_context_create_request()
Maarten Lankhorst
- [PATCH 21/30] drm/i915: Move i915_vma_lock in the selftests to avoid lock inversion, v3.
Maarten Lankhorst
- [PATCH 22/30] drm/i915: Add ww locking to vm_fault_gtt
Maarten Lankhorst
- [PATCH 23/30] drm/i915: Add ww locking to pin_to_display_plane, v2.
Maarten Lankhorst
- [PATCH 24/30] drm/i915: Do not share hwsp across contexts any more
Maarten Lankhorst
- [PATCH 25/30] drm/i915: Ensure we hold the object mutex in pin correctly.
Maarten Lankhorst
- [PATCH 26/30] drm/i915: Add gem object locking to madvise.
Maarten Lankhorst
- [PATCH 27/30] drm/i915: Convert i915_gem_object_attach_phys() to ww locking
Maarten Lankhorst
- [PATCH 28/30] drm/i915: make lockdep slightly happier about execbuf.
Maarten Lankhorst
- [PATCH 29/30] drm/i915: Fix userptr so we do not have to worry about obj->mm.lock
Maarten Lankhorst
- [PATCH 30/30] drm/i915: Flatten obj->mm.lock
Maarten Lankhorst
- [PATCH 1/6] drm/i915: Ensure we hold the object mutex in pin correctly.
Maarten Lankhorst
- [PATCH 2/6] drm/i915: Add gem object locking to madvise.
Maarten Lankhorst
- [PATCH 3/6] drm/i915: Convert i915_gem_object_attach_phys() to ww locking
Maarten Lankhorst
- [PATCH 4/6] drm/i915: make lockdep slightly happier about execbuf.
Maarten Lankhorst
- [PATCH 5/6] drm/i915: Fix userptr so we do not have to worry about obj->mm.lock
Maarten Lankhorst
- [PATCH 6/6] drm/i915: Flatten obj->mm.lock
Maarten Lankhorst
- [PATCH] drm/i915: Experimental w/a for TGL according to BSpec
Stanislav Lisovskiy
- [PATCH v2] drm/i915: Experimental w/a for TGL according to BSpec
Stanislav Lisovskiy
- [PATCH] drm/i915: Check if dsabling SAGV and possibly some C States, helps against periodical exceeding pipe update time, apparently caused my mmios ocassionally taking longer than expected.
Stanislav Lisovskiy
- [PATCH 1/3] drm/i915/dsb: multi dsb instance support in prepare() and cleanup()
Animesh Manna
- [PATCH 2/3] drm/i915/dsb: multi dsb instance support in dsb-write()
Animesh Manna
- [PATCH 3/3] drm/i915/dsb: multi dsb instance support in dsb-commit()
Animesh Manna
- [PATCH] drm/i915/display: make update_ref_clks vfunc mandatory
Lucas De Marchi
- [PATCH i-g-t] tests/kms_pipe_crc_basic: Sanity check for CRC mismatches
Bhanuprakash Modem
- [PATCH] drm: fix drm_dp_mst_port refcount leaks in drm_dp_mst_allocate_vcpi
Ankit Nautiyal
- [PATCH 1/2] Revert "drm/i915/display/fbc: Disable fbc by default on TGL"
Ankit Nautiyal
- [PATCH 2/2] drm/i915/display: Add an extra vblank wait before fbc activation
Ankit Nautiyal
- ✓ Fi.CI.BAT: success for series starting with [1/4] drm/i915/perf: Ensure observation logic is not clock gated
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [01/27] drm/i915/gt: Move intel_breadcrumbs_arm_irq earlier
Patchwork
- ✓ Fi.CI.IGT: success for series starting with [01/37] drm/i915/gt: Move intel_breadcrumbs_arm_irq earlier
Patchwork
- ✓ Fi.CI.IGT: success for series starting with [1/4] drm/i915/perf: Ensure observation logic is not clock gated
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [01/62] drm/i915/gt: Move intel_breadcrumbs_arm_irq earlier
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [01/41] drm/i915/gem: Don't drop the timeline lock during execbuf
Patchwork
- ✓ Fi.CI.BAT: success for drm/i915/gem: Don't drop the timeline lock during execbuf
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [01/41] drm/i915/gem: Don't drop the timeline lock during execbuf
Patchwork
- ✗ Fi.CI.IGT: failure for drm/i915/gem: Don't drop the timeline lock during execbuf
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/39] drm/i915/gem: Don't drop the timeline lock during execbuf
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [01/39] drm/i915/gem: Don't drop the timeline lock during execbuf
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/2] drm/i915/gem: Don't drop the timeline lock during execbuf
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/41] drm/i915/gem: Don't drop the timeline lock during execbuf
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [1/2] drm/i915/gem: Don't drop the timeline lock during execbuf
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [01/41] drm/i915/gem: Don't drop the timeline lock during execbuf
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/41] drm/i915/gem: Don't drop the timeline lock during execbuf
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [01/41] drm/i915/gem: Don't drop the timeline lock during execbuf
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/28] Revert "drm/i915/gem: Async GPU relocations only"
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [01/28] Revert "drm/i915/gem: Async GPU relocations only"
Patchwork
- ✗ Fi.CI.BAT: failure for drm/i915: Encode fence specific waitqueue behaviour into the wait.flags
Patchwork
- ✗ Fi.CI.BAT: failure for drm/i915: Experimental w/a for TGL according to BSpec
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/7] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✗ Fi.CI.BAT: failure for drm: fix drm_dp_mst_port refcount leaks in drm_dp_mst_allocate_vcpi
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/28] Revert "drm/i915/gem: Async GPU relocations only"
Patchwork
- ✓ Fi.CI.IGT: success for series starting with [1/7] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [01/28] Revert "drm/i915/gem: Async GPU relocations only"
Patchwork
- ✗ Fi.CI.BUILD: failure for series starting with [01/36] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [01/38] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/38] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/4] drm/i915/perf: Ensure observation logic is not clock gated
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/44] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✓ Fi.CI.IGT: success for series starting with [01/38] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✓ Fi.CI.BAT: success for drm/i915/display: Ensure that ret is always initialized in icl_combo_phy_verify_state (rev2)
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [1/4] drm/i915/perf: Ensure observation logic is not clock gated
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [01/44] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✗ Fi.CI.IGT: failure for drm/i915/display: Ensure that ret is always initialized in icl_combo_phy_verify_state (rev2)
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/44] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [01/44] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/44] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/37] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [01/44] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [01/37] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✓ Fi.CI.BAT: success for Allow privileged user to map the OA buffer
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/37] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✗ Fi.CI.IGT: failure for Allow privileged user to map the OA buffer
Patchwork
- ✓ Fi.CI.BAT: success for cyclic-ids
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/49] cyclic-ids
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [01/37] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✓ Fi.CI.BAT: success for cyclic-ids (rev2)
Patchwork
- ✓ Fi.CI.IGT: success for cyclic-ids
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [01/49] cyclic-ids
Patchwork
- ✗ Fi.CI.BAT: failure for cyclic-ids (rev3)
Patchwork
- ✗ Fi.CI.BAT: failure for cyclic-ids (rev4)
Patchwork
- ✗ Fi.CI.BUILD: failure for series starting with [01/29] Revert "drm/i915/gem: Async GPU relocations only"
Patchwork
- ✓ Fi.CI.BAT: success for cyclic-ids (rev7)
Patchwork
- ✗ Fi.CI.IGT: failure for cyclic-ids (rev7)
Patchwork
- ✓ Fi.CI.BAT: success for drm/i915: Experimental w/a for TGL according to BSpec (rev2)
Patchwork
- ✗ Fi.CI.BAT: failure for drm/i915/display: Enable KBL WA 1142
Patchwork
- ✗ Fi.CI.BAT: failure for tests/kms_pipe_crc_basic: Sanity check for CRC mismatches
Patchwork
- ✗ Fi.CI.IGT: failure for drm/i915: Experimental w/a for TGL according to BSpec (rev2)
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [1/8] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✗ Fi.CI.BUILD: failure for series starting with [01/39] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [1/8] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [01/38] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/4] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/7] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [1/4] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [1/7] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/4] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [1/4] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [1/4] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/4] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [01/28] Revert "drm/i915/gem: Async GPU relocations only"
Patchwork
- ✓ Fi.CI.IGT: success for series starting with [1/4] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✗ Fi.CI.BUILD: failure for series starting with [01/31] Revert "drm/i915/gem: Async GPU relocations only"
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [01/29] Revert "drm/i915/gem: Async GPU relocations only"
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/7] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [1/7] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/3] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✓ Fi.CI.BAT: success for tests/core_hotunplug: Fixes and enhancements (rev7)
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/6] drm/i915/gt: Protect context lifetime with RCU
Patchwork
- ✓ Fi.CI.IGT: success for series starting with [1/3] drm/i915/gem: Reduce context termination list iteration guard to RCU
Patchwork
- ✗ Fi.CI.IGT: failure for tests/core_hotunplug: Fixes and enhancements (rev7)
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [1/6] drm/i915/gt: Protect context lifetime with RCU
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [01/29] Revert "drm/i915/gem: Async GPU relocations only"
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/7] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/4] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Patchwork
- ✓ Fi.CI.BAT: success for drm/i915: Encode fence specific waitqueue behaviour into the wait.flags (rev2)
Patchwork
- ✗ Fi.CI.BAT: failure for drm/i915/gt: Rejig "Forcibly evict stable csb entries" for Tigerlake
Patchwork
- ✓ Fi.CI.BAT: success for bruce
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [1/7] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [1/4] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Patchwork
- ✓ Fi.CI.IGT: success for drm/i915: Encode fence specific waitqueue behaviour into the wait.flags (rev2)
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [01/80] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Patchwork
- ✓ Fi.CI.IGT: success for bruce
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/2] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [1/2] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/2] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling() (rev2)
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [1/2] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling() (rev2)
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/4] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/2] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/3] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Patchwork
- ✓ Fi.CI.IGT: success for series starting with [1/4] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Patchwork
- ✓ Fi.CI.IGT: success for series starting with [1/2] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/9] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [1/3] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Patchwork
- ✓ Fi.CI.IGT: success for series starting with [1/9] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/8] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [1/8] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Patchwork
- ✓ Fi.CI.BAT: success for drm/i915/gt: Signal cancelled requests upon wedging (rev2)
Patchwork
- ✓ Fi.CI.BAT: success for drm/i915: Encode fence specific waitqueue behaviour into the wait.flags (rev3)
Patchwork
- ✓ Fi.CI.IGT: success for drm/i915/gt: Signal cancelled requests upon wedging (rev2)
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/8] drm/i915/gt: Signal cancelled requests upon wedging
Patchwork
- ✓ Fi.CI.IGT: success for drm/i915: Encode fence specific waitqueue behaviour into the wait.flags (rev3)
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [01/78] drm/i915/gt: Signal cancelled requests upon wedging
Patchwork
- ✓ Fi.CI.IGT: success for series starting with [1/8] drm/i915/gt: Signal cancelled requests upon wedging
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [1/9] drm/i915/gt: Signal cancelled requests upon wedging
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [01/39] drm/i915/gt: Signal cancelled requests upon wedging
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [01/28] drm/i915/gt: Signal cancelled requests upon wedging
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [01/16] drm/i915/gt: Signal cancelled requests upon wedging
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/16] drm/i915/gt: Signal cancelled requests upon wedging
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/8] drm/i915/gt: Signal cancelled requests upon wedging
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [01/16] drm/i915/gt: Signal cancelled requests upon wedging
Patchwork
- ✗ Fi.CI.BUILD: failure for retire-request-onfini
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/8] retire-request-onfini
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [1/8] drm/i915/gt: Signal cancelled requests upon wedging
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [1/8] retire-request-onfini
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/10] drm/i915/gt: Signal cancelled requests
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/10] drm/i915/gt: Signal cancelled requests (rev2)
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [1/3] drm/i915/dsb: multi dsb instance support in prepare() and cleanup()
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [01/10] drm/i915/gt: Signal cancelled requests (rev2)
Patchwork
- ✓ Fi.CI.BAT: success for tests/core_hotunplug: Fixes and enhancements (rev8)
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/10] drm/i915/gt: Signal cancelled requests (rev3)
Patchwork
- ✗ Fi.CI.BUILD: failure for series starting with [1/2] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Patchwork
- ✗ Fi.CI.IGT: failure for tests/core_hotunplug: Fixes and enhancements (rev8)
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [1/2] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [01/10] drm/i915/gt: Signal cancelled requests (rev3)
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/2] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Patchwork
- ✓ Fi.CI.IGT: success for series starting with [1/2] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Patchwork
- ✓ Fi.CI.BAT: success for i915/i915_pm_lpsp: Adopt atomic commit style
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/23] Revert "drm/i915/gem: Async GPU relocations only"
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [1/2] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Patchwork
- ✗ Fi.CI.BUILD: failure for series starting with [1/2] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Patchwork
- ✗ Fi.CI.IGT: failure for i915/i915_pm_lpsp: Adopt atomic commit style
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [01/23] Revert "drm/i915/gem: Async GPU relocations only"
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [1/2] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [1/2] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Patchwork
- ✓ Fi.CI.BAT: success for drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock (rev2)
Patchwork
- ✗ Fi.CI.IGT: failure for drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock (rev2)
Patchwork
- ✓ Fi.CI.BAT: success for tests/gem_sync: test no inner loop
Patchwork
- ✓ Fi.CI.IGT: success for tests/gem_sync: test no inner loop
Patchwork
- ✓ Fi.CI.BAT: success for drm/i915/display: Ensure that ret is always initialized in icl_combo_phy_verify_state (rev3)
Patchwork
- ✗ Fi.CI.IGT: failure for drm/i915/display: Ensure that ret is always initialized in icl_combo_phy_verify_state (rev3)
Patchwork
- ✗ Fi.CI.BAT: failure for drm/i915/display: make update_ref_clks vfunc mandatory
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [01/27] Revert "drm/i915/gem: Async GPU relocations only"
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [1/2] drm/i915: Update TGL and RKL DMC firmware versions
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [1/2] drm/i915: Update TGL and RKL DMC firmware versions (rev2)
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [1/2] drm/i915: Update TGL and RKL DMC firmware versions (rev3)
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/2] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/3] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [1/2] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/3] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [1/3] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [1/2] drm/i915: Update TGL and RKL DMC firmware versions (rev4)
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [1/3] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/19] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Patchwork
- ✗ Fi.CI.BUILD: failure for PR for new firmwares v4
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [01/19] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/2] drm/i915: Update TGL and RKL DMC firmware versions (rev5)
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [1/2] drm/i915: Update TGL and RKL DMC firmware versions (rev5)
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [01/18] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [1/8] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Patchwork
- ✓ Fi.CI.BAT: success for drm/i915: Check if dsabling SAGV and possibly some C States, helps against periodical exceeding pipe update time, apparently caused my mmios ocassionally taking longer than expected.
Patchwork
- ✗ Fi.CI.IGT: failure for drm/i915: Check if dsabling SAGV and possibly some C States, helps against periodical exceeding pipe update time, apparently caused my mmios ocassionally taking longer than expected.
Patchwork
- ✓ Fi.CI.BAT: success for tests/core_hotunplug: Fixes and enhancements (rev9)
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/17] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Patchwork
- ✗ Fi.CI.IGT: failure for tests/core_hotunplug: Fixes and enhancements (rev9)
Patchwork
- ✓ Fi.CI.IGT: success for series starting with [01/17] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Patchwork
- ✗ Fi.CI.BUILD: failure for drm/i915: Add debugs to catch delays during updates (rev7)
Patchwork
- ✓ Fi.CI.BAT: success for tests/core_hotunplug: Fixes and enhancements (rev10)
Patchwork
- ✗ Fi.CI.IGT: failure for tests/core_hotunplug: Fixes and enhancements (rev10)
Patchwork
- ✓ Fi.CI.BAT: success for drm/i915/display: Check if low_vswing is still required in GEN11+
Patchwork
- ✓ Fi.CI.IGT: success for drm/i915/display: Check if low_vswing is still required in GEN11+
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [01/27] Revert "drm/i915/gem: Async GPU relocations only"
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/5] Critical KclockWork Fixes - intel_atomi.c PossibleNullPtr Dereference
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [1/5] Critical KclockWork Fixes - intel_atomi.c PossibleNullPtr Dereference
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [01/27] Revert "drm/i915/gem: Async GPU relocations only"
Patchwork
- ✗ Fi.CI.BAT: failure for tests/core_hotunplug: Fixes and enhancements (rev11)
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/19] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [01/19] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Patchwork
- ✓ Fi.CI.BAT: success for tests/kms_flip: add flip-32bpp-to-64bpp-downscaled-fb subtest
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/20] drm/i915/selftests: Push the fake iommu device from the stack to data
Patchwork
- ✓ Fi.CI.BAT: success for drm/i915/display/tgl: Use TGL DP tables for eDP ports without low power support
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/27] drm/i915/selftests: Push the fake iommu device from the stack to data
Patchwork
- ✓ Fi.CI.IGT: success for tests/kms_flip: add flip-32bpp-to-64bpp-downscaled-fb subtest
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [01/27] drm/i915/selftests: Push the fake iommu device from the stack to data
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/30] drm/i915/selftests: Push the fake iommu device from the stack to data
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/3] drm/i915/display/tgl: Use TGL DP tables for eDP ports without low power support
Patchwork
- ✓ Fi.CI.BAT: success for drm/i915/tgl: Fix stepping matching
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [01/20] drm/i915/selftests: Push the fake iommu device from the stack to data
Patchwork
- ✗ Fi.CI.IGT: failure for drm/i915/display/tgl: Use TGL DP tables for eDP ports without low power support
Patchwork
- ✓ Fi.CI.IGT: success for series starting with [01/27] drm/i915/selftests: Push the fake iommu device from the stack to data
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [01/30] drm/i915/selftests: Push the fake iommu device from the stack to data
Patchwork
- ✗ Fi.CI.BUILD: failure for series starting with [01/29] Revert "drm/i915/gem: Async GPU relocations only"
Patchwork
- ✗ Fi.CI.BUILD: failure for series starting with [01/30] Revert "drm/i915/gem: Async GPU relocations only"
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [01/27] Revert "drm/i915/gem: Async GPU relocations only"
Patchwork
- ✓ Fi.CI.IGT: success for series starting with [1/3] drm/i915/display/tgl: Use TGL DP tables for eDP ports without low power support
Patchwork
- ✓ Fi.CI.IGT: success for drm/i915/tgl: Fix stepping matching
Patchwork
- ✓ Fi.CI.BAT: success for Debug HPD interrupts
Patchwork
- ✓ Fi.CI.BAT: success for tests/core_hotunplug: Fixes and enhancements (rev12)
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/27] Revert "drm/i915/gem: Async GPU relocations only"
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [01/35] drm/i915/gem: Replace reloc chain with terminator on error unwind
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/36] drm/i915/gem: Replace reloc chain with terminator on error unwind
Patchwork
- ✗ Fi.CI.IGT: failure for Debug HPD interrupts
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/2] drm/i915/display: Ensure that ret is always initialized in icl_combo_phy_verify_state
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/2] drm/i915: Compute has_drrs after compute has_psr
Patchwork
- ✗ Fi.CI.IGT: failure for tests/core_hotunplug: Fixes and enhancements (rev12)
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [01/27] Revert "drm/i915/gem: Async GPU relocations only"
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [01/38] drm/i915/gem: Replace reloc chain with terminator on error unwind
Patchwork
- ✓ Fi.CI.IGT: success for series starting with [01/36] drm/i915/gem: Replace reloc chain with terminator on error unwind
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/38] drm/i915/gem: Replace reloc chain with terminator on error unwind
Patchwork
- ✓ Fi.CI.BAT: success for i915/gem_softpin: Active rebinds
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [1/2] drm/i915/display: Ensure that ret is always initialized in icl_combo_phy_verify_state
Patchwork
- ✓ Fi.CI.IGT: success for series starting with [1/2] drm/i915: Compute has_drrs after compute has_psr
Patchwork
- ✓ Fi.CI.IGT: success for series starting with [01/38] drm/i915/gem: Replace reloc chain with terminator on error unwind
Patchwork
- ✗ Fi.CI.IGT: failure for i915/gem_softpin: Active rebinds
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [1/2] Revert "drm/i915/display/fbc: Disable fbc by default on TGL"
Patchwork
- ✓ Fi.CI.BAT: success for tests/core_hotunplug: Fixes and enhancements (rev13)
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/4] mm: Export flush_vm_area() to sync the PTEs upon construction
Patchwork
- ✗ Fi.CI.IGT: failure for tests/core_hotunplug: Fixes and enhancements (rev13)
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [1/4] mm: Export flush_vm_area() to sync the PTEs upon construction
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [01/30] Revert "drm/i915/gem: Async GPU relocations only"
Patchwork
- ✓ Fi.CI.BAT: success for tests/core_hotunplug: Fixes and enhancements (rev14)
Patchwork
- ✓ Fi.CI.IGT: success for tests/core_hotunplug: Fixes and enhancements (rev14)
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/41] drm/i915/gem: Use set_pte_at() for assigning the vmapped PTE
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/42] drm/i915/gem: Use set_pte_at() for assigning the vmapped PTE
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/5] Fixing Possible Null Pointer Dereference
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [01/41] drm/i915/gem: Use set_pte_at() for assigning the vmapped PTE
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [01/42] drm/i915/gem: Use set_pte_at() for assigning the vmapped PTE
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [01/40] drm/i915/gem: Use set_pte_at() for assigning the vmapped PTE
Patchwork
- ✓ Fi.CI.IGT: success for series starting with [1/5] Fixing Possible Null Pointer Dereference
Patchwork
- ✗ Fi.CI.BAT: failure for drm/i915/display: Add an extra vblank wait before fbc activation
Patchwork
- ✗ Fi.CI.BAT: failure for tests/core_hotunplug: Fixes and enhancements (rev15)
Patchwork
- ✗ Fi.CI.BAT: failure for tests/core_hotunplug: Fixes and enhancements (rev16)
Patchwork
- ✗ Fi.CI.BUILD: failure for tests/core_hotunplug: Fixes and enhancements (rev17)
Patchwork
- ✓ Fi.CI.BAT: success for tests/core_hotunplug: Fixes and enhancements (rev18)
Patchwork
- ✗ Fi.CI.IGT: failure for tests/core_hotunplug: Fixes and enhancements (rev18)
Patchwork
- ✗ Fi.CI.BAT: failure for tests/core_hotunplug: Fixes and enhancements (rev19)
Patchwork
- ✓ Fi.CI.BAT: success for tests/core_hotunplug: Fixes and enhancements (rev20)
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/28] drm/i915/gem: Use set_pte_at() for assigning the vmapped PTE
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [01/39] drm/i915/gem: Use set_pte_at() for assigning the vmapped PTE
Patchwork
- ✓ Fi.CI.IGT: success for tests/core_hotunplug: Fixes and enhancements (rev20)
Patchwork
- ✗ Fi.CI.BAT: failure for series starting with [01/39] drm/i915/gem: Use set_pte_at() for assigning the vmapped PTE
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/6] drm/i915: Ensure we hold the object mutex in pin correctly.
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [01/28] drm/i915/gem: Use set_pte_at() for assigning the vmapped PTE
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [01/39] drm/i915/gem: Use set_pte_at() for assigning the vmapped PTE
Patchwork
- ✓ Fi.CI.BAT: success for tests/core_hotunplug: Fixes and enhancements (rev21)
Patchwork
- ✓ Fi.CI.BAT: success for series starting with [1/2] drm/i915/display: Ensure that ret is always initialized in icl_combo_phy_verify_state (rev2)
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [1/6] drm/i915: Ensure we hold the object mutex in pin correctly.
Patchwork
- ✗ Fi.CI.IGT: failure for tests/core_hotunplug: Fixes and enhancements (rev21)
Patchwork
- ✗ Fi.CI.IGT: failure for series starting with [1/2] drm/i915/display: Ensure that ret is always initialized in icl_combo_phy_verify_state (rev2)
Patchwork
- ✓ Fi.CI.BAT: success for tests/core_hotunplug: Fixes and enhancements (rev22)
Patchwork
- ✗ Fi.CI.IGT: failure for tests/core_hotunplug: Fixes and enhancements (rev22)
Patchwork
- ✓ Fi.CI.BAT: success for tests/core_hotunplug: Fixes and enhancements (rev23)
Patchwork
- ✗ Fi.CI.IGT: failure for tests/core_hotunplug: Fixes and enhancements (rev23)
Patchwork
- ✗ Fi.CI.BAT: failure for i915/i915_pm_lpsp: Adopt atomic commit style (rev2)
Patchwork
- [PATCH 1/4] drm/i915/perf: Ensure observation logic is not clock gated
Umesh Nerlige Ramappa
- [PATCH 2/4] drm/i915/perf: Whitelist OA report trigger registers
Umesh Nerlige Ramappa
- [PATCH 3/4] drm/i915/perf: Whitelist OA counter and buffer registers
Umesh Nerlige Ramappa
- [PATCH 4/4] drm/i915/perf: Map OA buffer to user space for gen12 performance query
Umesh Nerlige Ramappa
- [PATCH 0/4] Allow privileged user to map the OA buffer
Umesh Nerlige Ramappa
- [PATCH 1/4] drm/i915/perf: Ensure observation logic is not clock gated
Umesh Nerlige Ramappa
- [PATCH 2/4] drm/i915/perf: Whitelist OA report trigger registers
Umesh Nerlige Ramappa
- [PATCH 3/4] drm/i915/perf: Whitelist OA counter and buffer registers
Umesh Nerlige Ramappa
- [PATCH 4/4] drm/i915/perf: Map OA buffer to user space for gen12 performance query
Umesh Nerlige Ramappa
- [PATCH] drm/i915/display: Enable KBL WA 1142
Uma Shankar
- [PATCH] drm/i915/display: Add an extra vblank wait before fbc activation
Uma Shankar
- [PATCH] drm/i915/display: Ensure that ret is always initialized in icl_combo_phy_verify_state
José Roberto de Souza
- [PATCH 1/2] drm/i915: Update TGL and RKL DMC firmware versions
José Roberto de Souza
- [PATCH 2/2] drm/i915: Update TGL and RKL HuC firmware versions
José Roberto de Souza
- [CI] PR for new firmwares v4
José Roberto de Souza
- [PATCH] drm/i915/display: Check if low_vswing is still required in GEN11+
José Roberto de Souza
- [PATCH] drm/i915/display/tgl: Use TGL DP tables for eDP ports without low power support
José Roberto de Souza
- [PATCH 1/3] drm/i915/display/tgl: Use TGL DP tables for eDP ports without low power support
José Roberto de Souza
- [PATCH 2/3] drm/i915/display/ehl: Use EHL DP tables for eDP ports without low power support
José Roberto de Souza
- [PATCH 3/3] drm/i915/ehl: Update voltage swing table
José Roberto de Souza
- [PATCH] drm/i915/tgl: Fix stepping matching
José Roberto de Souza
- [PATCH 1/2] drm/i915/display: Ensure that ret is always initialized in icl_combo_phy_verify_state
José Roberto de Souza
- [PATCH 2/2] debug
José Roberto de Souza
- [PATCH 1/2] drm/i915: Compute has_drrs after compute has_psr
José Roberto de Souza
- [PATCH 2/2] drm/i915/drrs: Disable DRRS when needed in fastsets
José Roberto de Souza
- [PATCH 1/5] Critical KclockWork Fixes - intel_atomi.c PossibleNullPtr Dereference
Nischal Varide
- [PATCH 2/5] Critical KlockWork Fixes - intel_display.c Possible Null Dereference
Nischal Varide
- [PATCH 3/5] Critical KlockWorks Fix - intel_sdvo.c Possible Null Ptr Dereference
Nischal Varide
- [PATCH 4/5] Critical KlockWork Fix - intel_tv.c -Possible Null Pointer Dereference
Nischal Varide
- [PATCH 5/5] Critical KlockWorks Fix - intel_crt.c Possible Null Dereference
Nischal Varide
- [PATCH 1/5] Fixing Possible Null Pointer Dereference
Nischal Varide
- [PATCH 2/5] Fixing Possible Null Pointer Dereference.
Nischal Varide
- [PATCH 3/5] Fixing a Possible Null Pointer Dereference.
Nischal Varide
- [PATCH 4/5] Fixing Possible Null Pointer Dereference.
Nischal Varide
- [PATCH 5/5] Fixing a Possible Null Pointer Dereference.
Nischal Varide
- [PATCH 01/62] drm/i915/gt: Move intel_breadcrumbs_arm_irq earlier
Chris Wilson
- [PATCH 02/62] drm/i915/gt: Hold context/request reference while breadcrumbs are active
Chris Wilson
- [PATCH 03/62] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 04/62] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 05/62] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 06/62] drm/i915: Drop i915_request.lock serialisation around await_start
Chris Wilson
- [PATCH 07/62] drm/i915: Drop i915_request.lock requirement for intel_rps_boost()
Chris Wilson
- [PATCH 08/62] drm/i915/gem: Reduce ctx->engine_mutex for reading the clone source
Chris Wilson
- [PATCH 09/62] drm/i915/gem: Reduce ctx->engines_mutex for get_engines()
Chris Wilson
- [PATCH 10/62] drm/i915/gt: Decouple obj<->fence reference cycles on freeing the GT pool
Chris Wilson
- [PATCH 11/62] drm/i915/gem: Don't drop the timeline lock during execbuf
Chris Wilson
- [PATCH 12/62] drm/i915/gem: Rename execbuf.bind_link to unbound_link
Chris Wilson
- [PATCH 13/62] drm/i915/gem: Rename the list of relocations to reloc_list
Chris Wilson
- [PATCH 14/62] drm/i915/gem: Move the 'cached' info to i915_execbuffer
Chris Wilson
- [PATCH 15/62] drm/i915/gem: Break apart the early i915_vma_pin from execbuf object lookup
Chris Wilson
- [PATCH 16/62] drm/i915/gem: Remove the call for no-evict i915_vma_pin
Chris Wilson
- [PATCH 17/62] drm/i915: Serialise i915_vma_pin_inplace() with i915_vma_unbind()
Chris Wilson
- [PATCH 18/62] drm/i915: Add list_for_each_entry_safe_continue_reverse
Chris Wilson
- [PATCH 19/62] drm/i915: Always defer fenced work to the worker
Chris Wilson
- [PATCH 20/62] drm/i915/gem: Assign context id for async work
Chris Wilson
- [PATCH 21/62] drm/i915/gem: Separate the ww_mutex walker into its own list
Chris Wilson
- [PATCH 22/62] drm/i915/gem: Asynchronous GTT unbinding
Chris Wilson
- [PATCH 23/62] drm/i915/gem: Bind the fence async for execbuf
Chris Wilson
- [PATCH 24/62] drm/i915/gem: Include cmdparser in common execbuf pinning
Chris Wilson
- [PATCH 25/62] drm/i915/gem: Include secure batch in common execbuf pinning
Chris Wilson
- [PATCH 26/62] drm/i915/gem: Manage ppGTT placement bias (starting offset) explicitly
Chris Wilson
- [PATCH 27/62] drm/i915/gem: Reintroduce multiple passes for reloc processing
Chris Wilson
- [PATCH 28/62] drm/i915: Add an implementation for i915_gem_ww_ctx locking, v2.
Chris Wilson
- [PATCH 29/62] drm/i915/gem: Pull execbuf dma resv under a single critical section
Chris Wilson
- [PATCH 30/62] drm/i915/gem: Replace i915_gem_object.mm.mutex with reservation_ww_class
Chris Wilson
- [PATCH 31/62] drm/i915: Hold wakeref for the duration of the vma GGTT binding
Chris Wilson
- [PATCH 32/62] drm/i915: Specialise GGTT binding
Chris Wilson
- [PATCH 33/62] drm/i915/gt: Acquire backing storage for the context
Chris Wilson
- [PATCH 34/62] drm/i915/gt: Push the wait for the context to bound to the request
Chris Wilson
- [PATCH 35/62] drm/i915: Remove unused i915_gem_evict_vm()
Chris Wilson
- [PATCH 36/62] drm/i915/display: Drop object lock from intel_unpin_fb_vma
Chris Wilson
- [PATCH 37/62] drm/i915/gem: Delay attach mmu-notifier until we acquire the pinned userptr
Chris Wilson
- [PATCH 38/62] drm/i915: Reduce test_and_set_bit to set_bit in i915_request_submit()
Chris Wilson
- [PATCH 39/62] drm/i915/gt: Decouple completed requests on unwind
Chris Wilson
- [PATCH 40/62] drm/i915/gt: Check for a completed last request once
Chris Wilson
- [PATCH 41/62] drm/i915/gt: Refactor heartbeat request construction and submission
Chris Wilson
- [PATCH 42/62] drm/i915/gt: Replace direct submit with direct call to tasklet
Chris Wilson
- [PATCH 43/62] heart
Chris Wilson
- [PATCH 44/62] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 45/62] drm/i915/gt: Use virtual_engine during execlists_dequeue
Chris Wilson
- [PATCH 46/62] drm/i915/gt: Decouple inflight virtual engines
Chris Wilson
- [PATCH 47/62] drm/i915/gt: Defer schedule_out until after the next dequeue
Chris Wilson
- [PATCH 48/62] drm/i915/gt: Resubmit the virtual engine on schedule-out
Chris Wilson
- [PATCH 49/62] drm/i915/gt: Simplify virtual engine handling for execlists_hold()
Chris Wilson
- [PATCH 50/62] drm/i915/gt: ce->inflight updates are now serialised
Chris Wilson
- [PATCH 51/62] drm/i915/gt: Drop atomic for engine->fw_active tracking
Chris Wilson
- [PATCH 52/62] drm/i915/gt: Extract busy-stats for ring-scheduler
Chris Wilson
- [PATCH 53/62] drm/i915/gt: Convert stats.active to plain unsigned int
Chris Wilson
- [PATCH 54/62] drm/i915: Lift waiter/signaler iterators
Chris Wilson
- [PATCH 55/62] drm/i915: Strip out internal priorities
Chris Wilson
- [PATCH 56/62] drm/i915: Remove I915_USER_PRIORITY_SHIFT
Chris Wilson
- [PATCH 57/62] drm/i915: Replace engine->schedule() with a known request operation
Chris Wilson
- [PATCH 58/62] drm/i915/gt: Do not suspend bonded requests if one hangs
Chris Wilson
- [PATCH 59/62] drm/i915: Teach the i915_dependency to use a double-lock
Chris Wilson
- [PATCH 60/62] drm/i915: Restructure priority inheritance
Chris Wilson
- [PATCH 61/62] drm/i915/selftests: Measure set-priority duration
Chris Wilson
- [PATCH 62/62] drm/i915: Improve DFS for priority inheritance
Chris Wilson
- [PATCH 01/41] drm/i915/gem: Don't drop the timeline lock during execbuf
Chris Wilson
- [PATCH 02/41] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 03/41] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 04/41] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 05/41] drm/i915: Drop i915_request.lock serialisation around await_start
Chris Wilson
- [PATCH 06/41] drm/i915: Drop i915_request.lock requirement for intel_rps_boost()
Chris Wilson
- [PATCH 07/41] drm/i915/gem: Reduce ctx->engine_mutex for reading the clone source
Chris Wilson
- [PATCH 08/41] drm/i915/gem: Reduce ctx->engines_mutex for get_engines()
Chris Wilson
- [PATCH 09/41] drm/i915: Reduce test_and_set_bit to set_bit in i915_request_submit()
Chris Wilson
- [PATCH 10/41] drm/i915/gt: Decouple completed requests on unwind
Chris Wilson
- [PATCH 11/41] drm/i915/gt: Check for a completed last request once
Chris Wilson
- [PATCH 12/41] drm/i915/gt: Refactor heartbeat request construction and submission
Chris Wilson
- [PATCH 13/41] drm/i915/gt: Replace direct submit with direct call to tasklet
Chris Wilson
- [PATCH 14/41] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 15/41] drm/i915/gt: Use virtual_engine during execlists_dequeue
Chris Wilson
- [PATCH 16/41] drm/i915/gt: Decouple inflight virtual engines
Chris Wilson
- [PATCH 17/41] drm/i915/gt: Defer schedule_out until after the next dequeue
Chris Wilson
- [PATCH 18/41] drm/i915/gt: Resubmit the virtual engine on schedule-out
Chris Wilson
- [PATCH 19/41] drm/i915/gt: Simplify virtual engine handling for execlists_hold()
Chris Wilson
- [PATCH 20/41] drm/i915/gt: ce->inflight updates are now serialised
Chris Wilson
- [PATCH 21/41] drm/i915/gt: Drop atomic for engine->fw_active tracking
Chris Wilson
- [PATCH 22/41] drm/i915/gt: Extract busy-stats for ring-scheduler
Chris Wilson
- [PATCH 23/41] drm/i915/gt: Convert stats.active to plain unsigned int
Chris Wilson
- [PATCH 24/41] drm/i915: Lift waiter/signaler iterators
Chris Wilson
- [PATCH 25/41] drm/i915: Strip out internal priorities
Chris Wilson
- [PATCH 26/41] drm/i915: Remove I915_USER_PRIORITY_SHIFT
Chris Wilson
- [PATCH 27/41] drm/i915: Replace engine->schedule() with a known request operation
Chris Wilson
- [PATCH 28/41] drm/i915/gt: Do not suspend bonded requests if one hangs
Chris Wilson
- [PATCH 29/41] drm/i915: Teach the i915_dependency to use a double-lock
Chris Wilson
- [PATCH 30/41] drm/i915: Restructure priority inheritance
Chris Wilson
- [PATCH 31/41] drm/i915/selftests: Measure set-priority duration
Chris Wilson
- [PATCH 32/41] drm/i915: Improve DFS for priority inheritance
Chris Wilson
- [PATCH 33/41] drm/i915/gt: Remove timeslice suppression
Chris Wilson
- [PATCH 34/41] drm/i915: Fair low-latency scheduling
Chris Wilson
- [PATCH 35/41] drm/i915/gt: Specify a deadline for the heartbeat
Chris Wilson
- [PATCH 36/41] drm/i915: Replace the priority boosting for the display with a deadline
Chris Wilson
- [PATCH 37/41] drm/i915: Move saturated workload detection back to the context
Chris Wilson
- [PATCH 38/41] drm/i915/gt: Defer the kmem_cache_free() until after the HW submit
Chris Wilson
- [PATCH 39/41] drm/i915: Prune empty priolists
Chris Wilson
- [PATCH 40/41] drm/i915/gt: Support virtual engine queues
Chris Wilson
- [PATCH 41/41] drm/i915/gt: Another tweak for flushing the tasklets
Chris Wilson
- [PATCH] drm/i915/gem: Don't drop the timeline lock during execbuf
Chris Wilson
- [PATCH 01/41] drm/i915/gem: Don't drop the timeline lock during execbuf
Chris Wilson
- [PATCH 02/41] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 03/41] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 04/41] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 05/41] drm/i915: Drop i915_request.lock serialisation around await_start
Chris Wilson
- [PATCH 06/41] drm/i915: Drop i915_request.lock requirement for intel_rps_boost()
Chris Wilson
- [PATCH 07/41] drm/i915/gem: Reduce ctx->engine_mutex for reading the clone source
Chris Wilson
- [PATCH 08/41] drm/i915/gem: Reduce ctx->engines_mutex for get_engines()
Chris Wilson
- [PATCH 09/41] drm/i915: Reduce test_and_set_bit to set_bit in i915_request_submit()
Chris Wilson
- [PATCH 10/41] drm/i915/gt: Decouple completed requests on unwind
Chris Wilson
- [PATCH 11/41] drm/i915/gt: Check for a completed last request once
Chris Wilson
- [PATCH 12/41] drm/i915/gt: Refactor heartbeat request construction and submission
Chris Wilson
- [PATCH 13/41] drm/i915/gt: Replace direct submit with direct call to tasklet
Chris Wilson
- [PATCH 14/41] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 15/41] drm/i915/gt: Use virtual_engine during execlists_dequeue
Chris Wilson
- [PATCH 16/41] drm/i915/gt: Decouple inflight virtual engines
Chris Wilson
- [PATCH 17/41] drm/i915/gt: Defer schedule_out until after the next dequeue
Chris Wilson
- [PATCH 18/41] drm/i915/gt: Resubmit the virtual engine on schedule-out
Chris Wilson
- [PATCH 19/41] drm/i915/gt: Simplify virtual engine handling for execlists_hold()
Chris Wilson
- [PATCH 20/41] drm/i915/gt: ce->inflight updates are now serialised
Chris Wilson
- [PATCH 21/41] drm/i915/gt: Drop atomic for engine->fw_active tracking
Chris Wilson
- [PATCH 22/41] drm/i915/gt: Extract busy-stats for ring-scheduler
Chris Wilson
- [PATCH 23/41] drm/i915/gt: Convert stats.active to plain unsigned int
Chris Wilson
- [PATCH 24/41] drm/i915: Lift waiter/signaler iterators
Chris Wilson
- [PATCH 25/41] drm/i915: Strip out internal priorities
Chris Wilson
- [PATCH 26/41] drm/i915: Remove I915_USER_PRIORITY_SHIFT
Chris Wilson
- [PATCH 27/41] drm/i915: Replace engine->schedule() with a known request operation
Chris Wilson
- [PATCH 28/41] drm/i915/gt: Do not suspend bonded requests if one hangs
Chris Wilson
- [PATCH 29/41] drm/i915: Teach the i915_dependency to use a double-lock
Chris Wilson
- [PATCH 30/41] drm/i915: Restructure priority inheritance
Chris Wilson
- [PATCH 31/41] drm/i915/selftests: Measure set-priority duration
Chris Wilson
- [PATCH 32/41] drm/i915: Improve DFS for priority inheritance
Chris Wilson
- [PATCH 33/41] drm/i915/gt: Remove timeslice suppression
Chris Wilson
- [PATCH 34/41] drm/i915: Fair low-latency scheduling
Chris Wilson
- [PATCH 35/41] drm/i915/gt: Specify a deadline for the heartbeat
Chris Wilson
- [PATCH 36/41] drm/i915: Replace the priority boosting for the display with a deadline
Chris Wilson
- [PATCH 37/41] drm/i915: Move saturated workload detection back to the context
Chris Wilson
- [PATCH 38/41] drm/i915/gt: Defer the kmem_cache_free() until after the HW submit
Chris Wilson
- [PATCH 39/41] drm/i915: Prune empty priolists
Chris Wilson
- [PATCH 40/41] drm/i915/gt: Support virtual engine queues
Chris Wilson
- [PATCH 41/41] drm/i915/gt: Another tweak for flushing the tasklets
Chris Wilson
- [PATCH 01/39] drm/i915/gem: Don't drop the timeline lock during execbuf
Chris Wilson
- [PATCH 02/39] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 03/39] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 04/39] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 05/39] drm/i915: Drop i915_request.lock serialisation around await_start
Chris Wilson
- [PATCH 06/39] drm/i915: Drop i915_request.lock requirement for intel_rps_boost()
Chris Wilson
- [PATCH 07/39] drm/i915/gem: Reduce ctx->engine_mutex for reading the clone source
Chris Wilson
- [PATCH 08/39] drm/i915/gem: Reduce ctx->engines_mutex for get_engines()
Chris Wilson
- [PATCH 09/39] drm/i915: Reduce test_and_set_bit to set_bit in i915_request_submit()
Chris Wilson
- [PATCH 10/39] drm/i915/gt: Decouple completed requests on unwind
Chris Wilson
- [PATCH 11/39] drm/i915/gt: Check for a completed last request once
Chris Wilson
- [PATCH 12/39] drm/i915/gt: Refactor heartbeat request construction and submission
Chris Wilson
- [PATCH 13/39] drm/i915/gt: Replace direct submit with direct call to tasklet
Chris Wilson
- [PATCH 14/39] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 15/39] drm/i915/gt: Use virtual_engine during execlists_dequeue
Chris Wilson
- [PATCH 16/39] drm/i915/gt: Decouple inflight virtual engines
Chris Wilson
- [PATCH 17/39] drm/i915/gt: Defer schedule_out until after the next dequeue
Chris Wilson
- [PATCH 18/39] drm/i915/gt: Resubmit the virtual engine on schedule-out
Chris Wilson
- [PATCH 19/39] drm/i915/gt: Simplify virtual engine handling for execlists_hold()
Chris Wilson
- [PATCH 20/39] drm/i915/gt: ce->inflight updates are now serialised
Chris Wilson
- [PATCH 21/39] drm/i915/gt: Drop atomic for engine->fw_active tracking
Chris Wilson
- [PATCH 22/39] drm/i915/gt: Extract busy-stats for ring-scheduler
Chris Wilson
- [PATCH 23/39] drm/i915/gt: Convert stats.active to plain unsigned int
Chris Wilson
- [PATCH 24/39] drm/i915: Lift waiter/signaler iterators
Chris Wilson
- [PATCH 25/39] drm/i915: Strip out internal priorities
Chris Wilson
- [PATCH 26/39] drm/i915: Remove I915_USER_PRIORITY_SHIFT
Chris Wilson
- [PATCH 27/39] drm/i915: Replace engine->schedule() with a known request operation
Chris Wilson
- [PATCH 28/39] drm/i915/gt: Do not suspend bonded requests if one hangs
Chris Wilson
- [PATCH 29/39] drm/i915: Teach the i915_dependency to use a double-lock
Chris Wilson
- [PATCH 30/39] drm/i915: Restructure priority inheritance
Chris Wilson
- [PATCH 31/39] drm/i915/selftests: Measure set-priority duration
Chris Wilson
- [PATCH 32/39] drm/i915: Improve DFS for priority inheritance
Chris Wilson
- [PATCH 33/39] drm/i915/gt: Remove timeslice suppression
Chris Wilson
- [PATCH 34/39] drm/i915: Fair low-latency scheduling
Chris Wilson
- [PATCH 35/39] drm/i915/gt: Specify a deadline for the heartbeat
Chris Wilson
- [PATCH 36/39] drm/i915: Replace the priority boosting for the display with a deadline
Chris Wilson
- [PATCH 37/39] drm/i915: Move saturated workload detection back to the context
Chris Wilson
- [PATCH 38/39] drm/i915/gt: Defer the kmem_cache_free() until after the HW submit
Chris Wilson
- [PATCH 39/39] drm/i915: Prune empty priolists
Chris Wilson
- [PATCH 1/2] drm/i915/gem: Don't drop the timeline lock during execbuf
Chris Wilson
- [PATCH 2/2] drm/i915/gem: Reduce context termination list iteration guard to RCU
Chris Wilson
- [PATCH 01/41] drm/i915/gem: Don't drop the timeline lock during execbuf
Chris Wilson
- [PATCH 02/41] drm/i915/gem: Reduce context termination list iteration guard to RCU
Chris Wilson
- [PATCH 03/41] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 04/41] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 05/41] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 06/41] drm/i915: Drop i915_request.lock serialisation around await_start
Chris Wilson
- [PATCH 07/41] drm/i915: Drop i915_request.lock requirement for intel_rps_boost()
Chris Wilson
- [PATCH 08/41] drm/i915/gem: Reduce ctx->engine_mutex for reading the clone source
Chris Wilson
- [PATCH 09/41] drm/i915/gem: Reduce ctx->engines_mutex for get_engines()
Chris Wilson
- [PATCH 10/41] drm/i915: Reduce test_and_set_bit to set_bit in i915_request_submit()
Chris Wilson
- [PATCH 11/41] drm/i915/gt: Decouple completed requests on unwind
Chris Wilson
- [PATCH 12/41] drm/i915/gt: Check for a completed last request once
Chris Wilson
- [PATCH 13/41] drm/i915/gt: Refactor heartbeat request construction and submission
Chris Wilson
- [PATCH 14/41] drm/i915/gt: Replace direct submit with direct call to tasklet
Chris Wilson
- [PATCH 15/41] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 16/41] drm/i915/gt: Use virtual_engine during execlists_dequeue
Chris Wilson
- [PATCH 17/41] drm/i915/gt: Decouple inflight virtual engines
Chris Wilson
- [PATCH 18/41] drm/i915/gt: Defer schedule_out until after the next dequeue
Chris Wilson
- [PATCH 19/41] drm/i915/gt: Resubmit the virtual engine on schedule-out
Chris Wilson
- [PATCH 20/41] drm/i915/gt: Simplify virtual engine handling for execlists_hold()
Chris Wilson
- [PATCH 21/41] drm/i915/gt: ce->inflight updates are now serialised
Chris Wilson
- [PATCH 22/41] drm/i915/gt: Drop atomic for engine->fw_active tracking
Chris Wilson
- [PATCH 23/41] drm/i915/gt: Extract busy-stats for ring-scheduler
Chris Wilson
- [PATCH 24/41] drm/i915/gt: Convert stats.active to plain unsigned int
Chris Wilson
- [PATCH 25/41] drm/i915: Lift waiter/signaler iterators
Chris Wilson
- [PATCH 26/41] drm/i915: Strip out internal priorities
Chris Wilson
- [PATCH 27/41] drm/i915: Remove I915_USER_PRIORITY_SHIFT
Chris Wilson
- [PATCH 28/41] drm/i915/gt: Defer the kmem_cache_free() until after the HW submit
Chris Wilson
- [PATCH 29/41] drm/i915: Prune empty priolists
Chris Wilson
- [PATCH 30/41] drm/i915: Replace engine->schedule() with a known request operation
Chris Wilson
- [PATCH 31/41] drm/i915/gt: Do not suspend bonded requests if one hangs
Chris Wilson
- [PATCH 32/41] drm/i915: Teach the i915_dependency to use a double-lock
Chris Wilson
- [PATCH 33/41] drm/i915: Restructure priority inheritance
Chris Wilson
- [PATCH 34/41] drm/i915/selftests: Measure set-priority duration
Chris Wilson
- [PATCH 35/41] drm/i915: Improve DFS for priority inheritance
Chris Wilson
- [PATCH 36/41] drm/i915/gt: Remove timeslice suppression
Chris Wilson
- [PATCH 37/41] drm/i915: Fair low-latency scheduling
Chris Wilson
- [PATCH 38/41] drm/i915/gt: Specify a deadline for the heartbeat
Chris Wilson
- [PATCH 39/41] drm/i915: Replace the priority boosting for the display with a deadline
Chris Wilson
- [PATCH 40/41] drm/i915: Move saturated workload detection back to the context
Chris Wilson
- [PATCH 41/41] drm/i915/gt: Another tweak for flushing the tasklets
Chris Wilson
- [PATCH 01/41] drm/i915/gem: Don't drop the timeline lock during execbuf
Chris Wilson
- [PATCH 02/41] drm/i915/gem: Reduce context termination list iteration guard to RCU
Chris Wilson
- [PATCH 03/41] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 04/41] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 05/41] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 06/41] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 07/41] drm/i915: Drop i915_request.lock serialisation around await_start
Chris Wilson
- [PATCH 08/41] drm/i915: Drop i915_request.lock requirement for intel_rps_boost()
Chris Wilson
- [PATCH 09/41] drm/i915/gem: Reduce ctx->engine_mutex for reading the clone source
Chris Wilson
- [PATCH 10/41] drm/i915/gem: Reduce ctx->engines_mutex for get_engines()
Chris Wilson
- [PATCH 11/41] drm/i915: Reduce test_and_set_bit to set_bit in i915_request_submit()
Chris Wilson
- [PATCH 12/41] drm/i915/gt: Decouple completed requests on unwind
Chris Wilson
- [PATCH 13/41] drm/i915/gt: Check for a completed last request once
Chris Wilson
- [PATCH 14/41] drm/i915/gt: Refactor heartbeat request construction and submission
Chris Wilson
- [PATCH 15/41] drm/i915/gt: Replace direct submit with direct call to tasklet
Chris Wilson
- [PATCH 16/41] drm/i915/gt: Use virtual_engine during execlists_dequeue
Chris Wilson
- [PATCH 17/41] drm/i915/gt: Decouple inflight virtual engines
Chris Wilson
- [PATCH 18/41] drm/i915/gt: Defer schedule_out until after the next dequeue
Chris Wilson
- [PATCH 19/41] drm/i915/gt: Resubmit the virtual engine on schedule-out
Chris Wilson
- [PATCH 20/41] drm/i915/gt: Simplify virtual engine handling for execlists_hold()
Chris Wilson
- [PATCH 21/41] drm/i915/gt: ce->inflight updates are now serialised
Chris Wilson
- [PATCH 22/41] drm/i915/gt: Drop atomic for engine->fw_active tracking
Chris Wilson
- [PATCH 23/41] drm/i915/gt: Extract busy-stats for ring-scheduler
Chris Wilson
- [PATCH 24/41] drm/i915/gt: Convert stats.active to plain unsigned int
Chris Wilson
- [PATCH 25/41] drm/i915: Lift waiter/signaler iterators
Chris Wilson
- [PATCH 26/41] drm/i915: Strip out internal priorities
Chris Wilson
- [PATCH 27/41] drm/i915: Remove I915_USER_PRIORITY_SHIFT
Chris Wilson
- [PATCH 28/41] drm/i915/gt: Defer the kmem_cache_free() until after the HW submit
Chris Wilson
- [PATCH 29/41] drm/i915: Prune empty priolists
Chris Wilson
- [PATCH 30/41] drm/i915: Replace engine->schedule() with a known request operation
Chris Wilson
- [PATCH 31/41] drm/i915/gt: Do not suspend bonded requests if one hangs
Chris Wilson
- [PATCH 32/41] drm/i915: Teach the i915_dependency to use a double-lock
Chris Wilson
- [PATCH 33/41] drm/i915: Restructure priority inheritance
Chris Wilson
- [PATCH 34/41] drm/i915/selftests: Measure set-priority duration
Chris Wilson
- [PATCH 35/41] drm/i915: Improve DFS for priority inheritance
Chris Wilson
- [PATCH 36/41] drm/i915/gt: Remove timeslice suppression
Chris Wilson
- [PATCH 37/41] drm/i915: Fair low-latency scheduling
Chris Wilson
- [PATCH 38/41] drm/i915/gt: Specify a deadline for the heartbeat
Chris Wilson
- [PATCH 39/41] drm/i915: Replace the priority boosting for the display with a deadline
Chris Wilson
- [PATCH 40/41] drm/i915: Move saturated workload detection back to the context
Chris Wilson
- [PATCH 41/41] drm/i915/gt: Another tweak for flushing the tasklets
Chris Wilson
- [PATCH] drm/i915: Encode fence specific waitqueue behaviour into the wait.flags
Chris Wilson
- [PATCH 1/7] drm/i915/gem: Reduce context termination list iteration guard to RCU
Chris Wilson
- [PATCH 2/7] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 3/7] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 4/7] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 5/7] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 6/7] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 7/7] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 01/36] drm/i915/gem: Reduce context termination list iteration guard to RCU
Chris Wilson
- [PATCH 02/36] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 03/36] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 04/36] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 05/36] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 06/36] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 07/36] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 08/36] drm/i915/gem: Don't drop the timeline lock during execbuf
Chris Wilson
- [PATCH 09/36] drm/i915/gem: Rename execbuf.bind_link to unbound_link
Chris Wilson
- [PATCH 10/36] drm/i915/gem: Rename the list of relocations to reloc_list
Chris Wilson
- [PATCH 11/36] drm/i915/gem: Move the 'cached' info to i915_execbuffer
Chris Wilson
- [PATCH 12/36] drm/i915/gem: Break apart the early i915_vma_pin from execbuf object lookup
Chris Wilson
- [PATCH 13/36] drm/i915/gem: Remove the call for no-evict i915_vma_pin
Chris Wilson
- [PATCH 14/36] drm/i915: Serialise i915_vma_pin_inplace() with i915_vma_unbind()
Chris Wilson
- [PATCH 15/36] drm/i915: Add list_for_each_entry_safe_continue_reverse
Chris Wilson
- [PATCH 16/36] drm/i915: Always defer fenced work to the worker
Chris Wilson
- [PATCH 17/36] drm/i915/gem: Assign context id for async work
Chris Wilson
- [PATCH 18/36] drm/i915/gem: Separate the ww_mutex walker into its own list
Chris Wilson
- [PATCH 19/36] drm/i915/gem: Asynchronous GTT unbinding
Chris Wilson
- [PATCH 20/36] drm/i915/gem: Bind the fence async for execbuf
Chris Wilson
- [PATCH 21/36] drm/i915/gem: Include cmdparser in common execbuf pinning
Chris Wilson
- [PATCH 22/36] drm/i915/gem: Include secure batch in common execbuf pinning
Chris Wilson
- [PATCH 23/36] drm/i915/gem: Manage ppGTT placement bias (starting offset) explicitly
Chris Wilson
- [PATCH 24/36] drm/i915/gem: Reintroduce multiple passes for reloc processing
Chris Wilson
- [PATCH 25/36] drm/i915: Add an implementation for i915_gem_ww_ctx locking, v2.
Chris Wilson
- [PATCH 26/36] drm/i915/gem: Pull execbuf dma resv under a single critical section
Chris Wilson
- [PATCH 27/36] drm/i915/gtt: map the PD up front
Chris Wilson
- [PATCH 28/36] drm/i915: Acquire the object lock around page directories
Chris Wilson
- [PATCH 29/36] drm/i915/gem: Replace i915_gem_object.mm.mutex with reservation_ww_class
Chris Wilson
- [PATCH 30/36] drm/i915: Hold wakeref for the duration of the vma GGTT binding
Chris Wilson
- [PATCH 31/36] drm/i915: Specialise GGTT binding
Chris Wilson
- [PATCH 32/36] drm/i915/gt: Acquire backing storage for the context
Chris Wilson
- [PATCH 33/36] drm/i915/gt: Push the wait for the context to bound to the request
Chris Wilson
- [PATCH 34/36] drm/i915: Remove unused i915_gem_evict_vm()
Chris Wilson
- [PATCH 35/36] drm/i915/display: Drop object lock from intel_unpin_fb_vma
Chris Wilson
- [PATCH 36/36] drm/i915/gem: Delay attach mmu-notifier until we acquire the pinned userptr
Chris Wilson
- [PATCH 01/38] drm/i915/gem: Reduce context termination list iteration guard to RCU
Chris Wilson
- [PATCH 02/38] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 03/38] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 04/38] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 05/38] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 06/38] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 07/38] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 08/38] drm/i915/gem: Don't drop the timeline lock during execbuf
Chris Wilson
- [PATCH 09/38] drm/i915/gem: Rename execbuf.bind_link to unbound_link
Chris Wilson
- [PATCH 10/38] drm/i915/gem: Rename the list of relocations to reloc_list
Chris Wilson
- [PATCH 11/38] drm/i915/gem: Move the 'cached' info to i915_execbuffer
Chris Wilson
- [PATCH 12/38] drm/i915/gem: Break apart the early i915_vma_pin from execbuf object lookup
Chris Wilson
- [PATCH 13/38] drm/i915/gem: Remove the call for no-evict i915_vma_pin
Chris Wilson
- [PATCH 14/38] drm/i915: Serialise i915_vma_pin_inplace() with i915_vma_unbind()
Chris Wilson
- [PATCH 15/38] drm/i915: Add list_for_each_entry_safe_continue_reverse
Chris Wilson
- [PATCH 16/38] drm/i915: Always defer fenced work to the worker
Chris Wilson
- [PATCH 17/38] drm/i915/gem: Assign context id for async work
Chris Wilson
- [PATCH 18/38] drm/i915/gem: Separate the ww_mutex walker into its own list
Chris Wilson
- [PATCH 19/38] drm/i915/gem: Asynchronous GTT unbinding
Chris Wilson
- [PATCH 20/38] drm/i915/gem: Bind the fence async for execbuf
Chris Wilson
- [PATCH 21/38] drm/i915/gem: Include cmdparser in common execbuf pinning
Chris Wilson
- [PATCH 22/38] drm/i915/gem: Include secure batch in common execbuf pinning
Chris Wilson
- [PATCH 23/38] drm/i915/gem: Manage ppGTT placement bias (starting offset) explicitly
Chris Wilson
- [PATCH 24/38] drm/i915/gem: Reintroduce multiple passes for reloc processing
Chris Wilson
- [PATCH 25/38] drm/i915: Add an implementation for i915_gem_ww_ctx locking, v2.
Chris Wilson
- [PATCH 26/38] drm/i915/gem: Pull execbuf dma resv under a single critical section
Chris Wilson
- [PATCH 27/38] drm/i915/gtt: map the PD up front
Chris Wilson
- [PATCH 28/38] drm/i915: Acquire the object lock around page directories
Chris Wilson
- [PATCH 29/38] drm/i915/gem: Replace i915_gem_object.mm.mutex with reservation_ww_class
Chris Wilson
- [PATCH 30/38] drm/i915: Hold wakeref for the duration of the vma GGTT binding
Chris Wilson
- [PATCH 31/38] drm/i915/gt: Refactor heartbeat request construction and submission
Chris Wilson
- [PATCH 32/38] drm/i915: Specialise GGTT binding
Chris Wilson
- [PATCH 33/38] heart
Chris Wilson
- [PATCH 34/38] drm/i915/gt: Acquire backing storage for the context
Chris Wilson
- [PATCH 35/38] drm/i915/gt: Push the wait for the context to bound to the request
Chris Wilson
- [PATCH 36/38] drm/i915: Remove unused i915_gem_evict_vm()
Chris Wilson
- [PATCH 37/38] drm/i915/display: Drop object lock from intel_unpin_fb_vma
Chris Wilson
- [PATCH 38/38] drm/i915/gem: Delay attach mmu-notifier until we acquire the pinned userptr
Chris Wilson
- [PATCH 01/38] drm/i915/gem: Reduce context termination list iteration guard to RCU
Chris Wilson
- [PATCH 02/38] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 03/38] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 04/38] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 05/38] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 06/38] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 07/38] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 08/38] drm/i915/gem: Don't drop the timeline lock during execbuf
Chris Wilson
- [PATCH 09/38] drm/i915/gem: Rename execbuf.bind_link to unbound_link
Chris Wilson
- [PATCH 10/38] drm/i915/gem: Rename the list of relocations to reloc_list
Chris Wilson
- [PATCH 11/38] drm/i915/gem: Move the 'cached' info to i915_execbuffer
Chris Wilson
- [PATCH 12/38] drm/i915/gem: Break apart the early i915_vma_pin from execbuf object lookup
Chris Wilson
- [PATCH 13/38] drm/i915/gem: Remove the call for no-evict i915_vma_pin
Chris Wilson
- [PATCH 14/38] drm/i915: Serialise i915_vma_pin_inplace() with i915_vma_unbind()
Chris Wilson
- [PATCH 15/38] drm/i915: Add list_for_each_entry_safe_continue_reverse
Chris Wilson
- [PATCH 16/38] drm/i915: Always defer fenced work to the worker
Chris Wilson
- [PATCH 17/38] drm/i915/gem: Assign context id for async work
Chris Wilson
- [PATCH 18/38] drm/i915/gem: Separate the ww_mutex walker into its own list
Chris Wilson
- [PATCH 19/38] drm/i915/gem: Asynchronous GTT unbinding
Chris Wilson
- [PATCH 20/38] drm/i915/gem: Bind the fence async for execbuf
Chris Wilson
- [PATCH 21/38] drm/i915/gem: Include cmdparser in common execbuf pinning
Chris Wilson
- [PATCH 22/38] drm/i915/gem: Include secure batch in common execbuf pinning
Chris Wilson
- [PATCH 23/38] drm/i915/gem: Manage ppGTT placement bias (starting offset) explicitly
Chris Wilson
- [PATCH 24/38] drm/i915/gem: Reintroduce multiple passes for reloc processing
Chris Wilson
- [PATCH 25/38] drm/i915: Add an implementation for i915_gem_ww_ctx locking, v2.
Chris Wilson
- [PATCH 26/38] drm/i915/gem: Pull execbuf dma resv under a single critical section
Chris Wilson
- [PATCH 27/38] drm/i915/gtt: map the PD up front
Chris Wilson
- [PATCH 28/38] drm/i915: Acquire the object lock around page directories
Chris Wilson
- [PATCH 29/38] drm/i915/gem: Replace i915_gem_object.mm.mutex with reservation_ww_class
Chris Wilson
- [PATCH 30/38] drm/i915: Hold wakeref for the duration of the vma GGTT binding
Chris Wilson
- [PATCH 31/38] drm/i915/gt: Refactor heartbeat request construction and submission
Chris Wilson
- [PATCH 32/38] drm/i915: Specialise GGTT binding
Chris Wilson
- [PATCH 33/38] heart
Chris Wilson
- [PATCH 34/38] drm/i915/gt: Acquire backing storage for the context
Chris Wilson
- [PATCH 35/38] drm/i915/gt: Push the wait for the context to bound to the request
Chris Wilson
- [PATCH 36/38] drm/i915: Remove unused i915_gem_evict_vm()
Chris Wilson
- [PATCH 37/38] drm/i915/display: Drop object lock from intel_unpin_fb_vma
Chris Wilson
- [PATCH 38/38] drm/i915/gem: Delay attach mmu-notifier until we acquire the pinned userptr
Chris Wilson
- [PATCH 01/44] drm/i915/gem: Reduce context termination list iteration guard to RCU
Chris Wilson
- [PATCH 02/44] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 03/44] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 04/44] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 05/44] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 06/44] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 07/44] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 08/44] drm/i915/gem: Don't drop the timeline lock during execbuf
Chris Wilson
- [PATCH 09/44] drm/i915: Drop i915_request.lock serialisation around await_start
Chris Wilson
- [PATCH 10/44] drm/i915: Drop i915_request.lock requirement for intel_rps_boost()
Chris Wilson
- [PATCH 11/44] drm/i915/gem: Reduce ctx->engine_mutex for reading the clone source
Chris Wilson
- [PATCH 12/44] drm/i915/gem: Reduce ctx->engines_mutex for get_engines()
Chris Wilson
- [PATCH 13/44] drm/i915: Reduce test_and_set_bit to set_bit in i915_request_submit()
Chris Wilson
- [PATCH 14/44] drm/i915/gt: Decouple completed requests on unwind
Chris Wilson
- [PATCH 15/44] drm/i915/gt: Check for a completed last request once
Chris Wilson
- [PATCH 16/44] drm/i915/gt: Refactor heartbeat request construction and submission
Chris Wilson
- [PATCH 17/44] drm/i915/gt: Replace direct submit with direct call to tasklet
Chris Wilson
- [PATCH 18/44] drm/i915/gt: Use virtual_engine during execlists_dequeue
Chris Wilson
- [PATCH 19/44] drm/i915/gt: Decouple inflight virtual engines
Chris Wilson
- [PATCH 20/44] drm/i915/gt: Defer schedule_out until after the next dequeue
Chris Wilson
- [PATCH 21/44] drm/i915/gt: Resubmit the virtual engine on schedule-out
Chris Wilson
- [PATCH 22/44] drm/i915/gt: Simplify virtual engine handling for execlists_hold()
Chris Wilson
- [PATCH 23/44] drm/i915/gt: ce->inflight updates are now serialised
Chris Wilson
- [PATCH 24/44] drm/i915/gt: Drop atomic for engine->fw_active tracking
Chris Wilson
- [PATCH 25/44] drm/i915/gt: Extract busy-stats for ring-scheduler
Chris Wilson
- [PATCH 26/44] drm/i915/gt: Convert stats.active to plain unsigned int
Chris Wilson
- [PATCH 27/44] drm/i915: Lift waiter/signaler iterators
Chris Wilson
- [PATCH 28/44] drm/i915: Strip out internal priorities
Chris Wilson
- [PATCH 29/44] drm/i915: Remove I915_USER_PRIORITY_SHIFT
Chris Wilson
- [PATCH 30/44] drm/i915/gt: Defer the kmem_cache_free() until after the HW submit
Chris Wilson
- [PATCH 31/44] drm/i915: Prune empty priolists
Chris Wilson
- [PATCH 32/44] drm/i915: Replace engine->schedule() with a known request operation
Chris Wilson
- [PATCH 33/44] drm/i915/gt: Do not suspend bonded requests if one hangs
Chris Wilson
- [PATCH 34/44] drm/i915: Teach the i915_dependency to use a double-lock
Chris Wilson
- [PATCH 35/44] drm/i915: Restructure priority inheritance
Chris Wilson
- [PATCH 36/44] drm/i915/selftests: Measure set-priority duration
Chris Wilson
- [PATCH 37/44] drm/i915/selftests: Exercise priority inheritance around an engine loop
Chris Wilson
- [PATCH 38/44] drm/i915: Improve DFS for priority inheritance
Chris Wilson
- [PATCH 39/44] drm/i915/gt: Remove timeslice suppression
Chris Wilson
- [PATCH 40/44] drm/i915: Fair low-latency scheduling
Chris Wilson
- [PATCH 41/44] drm/i915/gt: Specify a deadline for the heartbeat
Chris Wilson
- [PATCH 42/44] drm/i915: Replace the priority boosting for the display with a deadline
Chris Wilson
- [PATCH 43/44] drm/i915: Move saturated workload detection back to the context
Chris Wilson
- [PATCH 44/44] drm/i915/gt: Another tweak for flushing the tasklets
Chris Wilson
- [PATCH 01/44] drm/i915/gem: Reduce context termination list iteration guard to RCU
Chris Wilson
- [PATCH 02/44] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 03/44] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 04/44] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 05/44] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 06/44] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 07/44] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 08/44] drm/i915/gem: Don't drop the timeline lock during execbuf
Chris Wilson
- [PATCH 09/44] drm/i915: Drop i915_request.lock serialisation around await_start
Chris Wilson
- [PATCH 10/44] drm/i915: Drop i915_request.lock requirement for intel_rps_boost()
Chris Wilson
- [PATCH 11/44] drm/i915/gem: Reduce ctx->engine_mutex for reading the clone source
Chris Wilson
- [PATCH 12/44] drm/i915/gem: Reduce ctx->engines_mutex for get_engines()
Chris Wilson
- [PATCH 13/44] drm/i915: Reduce test_and_set_bit to set_bit in i915_request_submit()
Chris Wilson
- [PATCH 14/44] drm/i915/gt: Decouple completed requests on unwind
Chris Wilson
- [PATCH 15/44] drm/i915/gt: Check for a completed last request once
Chris Wilson
- [PATCH 16/44] drm/i915/gt: Refactor heartbeat request construction and submission
Chris Wilson
- [PATCH 17/44] drm/i915/gt: Replace direct submit with direct call to tasklet
Chris Wilson
- [PATCH 18/44] drm/i915/gt: Use virtual_engine during execlists_dequeue
Chris Wilson
- [PATCH 19/44] drm/i915/gt: Decouple inflight virtual engines
Chris Wilson
- [PATCH 20/44] drm/i915/gt: Defer schedule_out until after the next dequeue
Chris Wilson
- [PATCH 21/44] drm/i915/gt: Resubmit the virtual engine on schedule-out
Chris Wilson
- [PATCH 22/44] drm/i915/gt: Simplify virtual engine handling for execlists_hold()
Chris Wilson
- [PATCH 23/44] drm/i915/gt: ce->inflight updates are now serialised
Chris Wilson
- [PATCH 24/44] drm/i915/gt: Drop atomic for engine->fw_active tracking
Chris Wilson
- [PATCH 25/44] drm/i915/gt: Extract busy-stats for ring-scheduler
Chris Wilson
- [PATCH 26/44] drm/i915/gt: Convert stats.active to plain unsigned int
Chris Wilson
- [PATCH 27/44] drm/i915: Lift waiter/signaler iterators
Chris Wilson
- [PATCH 28/44] drm/i915: Strip out internal priorities
Chris Wilson
- [PATCH 29/44] drm/i915: Remove I915_USER_PRIORITY_SHIFT
Chris Wilson
- [PATCH 30/44] drm/i915/gt: Defer the kmem_cache_free() until after the HW submit
Chris Wilson
- [PATCH 31/44] drm/i915: Prune empty priolists
Chris Wilson
- [PATCH 32/44] drm/i915: Replace engine->schedule() with a known request operation
Chris Wilson
- [PATCH 33/44] drm/i915/gt: Do not suspend bonded requests if one hangs
Chris Wilson
- [PATCH 34/44] drm/i915: Teach the i915_dependency to use a double-lock
Chris Wilson
- [PATCH 35/44] drm/i915: Restructure priority inheritance
Chris Wilson
- [PATCH 36/44] drm/i915/selftests: Measure set-priority duration
Chris Wilson
- [PATCH 37/44] drm/i915/selftests: Exercise priority inheritance around an engine loop
Chris Wilson
- [PATCH 38/44] drm/i915: Improve DFS for priority inheritance
Chris Wilson
- [PATCH 39/44] drm/i915/gt: Remove timeslice suppression
Chris Wilson
- [PATCH 40/44] drm/i915: Fair low-latency scheduling
Chris Wilson
- [PATCH 41/44] drm/i915/gt: Specify a deadline for the heartbeat
Chris Wilson
- [PATCH 42/44] drm/i915: Replace the priority boosting for the display with a deadline
Chris Wilson
- [PATCH 43/44] drm/i915: Move saturated workload detection back to the context
Chris Wilson
- [PATCH 44/44] drm/i915/gt: Another tweak for flushing the tasklets
Chris Wilson
- [PATCH 01/44] drm/i915/gem: Reduce context termination list iteration guard to RCU
Chris Wilson
- [PATCH 02/44] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 03/44] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 04/44] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 05/44] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 06/44] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 07/44] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 08/44] drm/i915/gem: Don't drop the timeline lock during execbuf
Chris Wilson
- [PATCH 09/44] drm/i915: Drop i915_request.lock serialisation around await_start
Chris Wilson
- [PATCH 10/44] drm/i915: Drop i915_request.lock requirement for intel_rps_boost()
Chris Wilson
- [PATCH 11/44] drm/i915/gem: Reduce ctx->engine_mutex for reading the clone source
Chris Wilson
- [PATCH 12/44] drm/i915/gem: Reduce ctx->engines_mutex for get_engines()
Chris Wilson
- [PATCH 13/44] drm/i915: Reduce test_and_set_bit to set_bit in i915_request_submit()
Chris Wilson
- [PATCH 14/44] drm/i915/gt: Decouple completed requests on unwind
Chris Wilson
- [PATCH 15/44] drm/i915/gt: Check for a completed last request once
Chris Wilson
- [PATCH 16/44] drm/i915/gt: Refactor heartbeat request construction and submission
Chris Wilson
- [PATCH 17/44] drm/i915/gt: Replace direct submit with direct call to tasklet
Chris Wilson
- [PATCH 18/44] drm/i915/gt: Use virtual_engine during execlists_dequeue
Chris Wilson
- [PATCH 19/44] drm/i915/gt: Decouple inflight virtual engines
Chris Wilson
- [PATCH 20/44] drm/i915/gt: Defer schedule_out until after the next dequeue
Chris Wilson
- [PATCH 21/44] drm/i915/gt: Resubmit the virtual engine on schedule-out
Chris Wilson
- [PATCH 22/44] drm/i915/gt: Simplify virtual engine handling for execlists_hold()
Chris Wilson
- [PATCH 23/44] drm/i915/gt: ce->inflight updates are now serialised
Chris Wilson
- [PATCH 24/44] drm/i915/gt: Drop atomic for engine->fw_active tracking
Chris Wilson
- [PATCH 25/44] drm/i915/gt: Extract busy-stats for ring-scheduler
Chris Wilson
- [PATCH 26/44] drm/i915/gt: Convert stats.active to plain unsigned int
Chris Wilson
- [PATCH 27/44] drm/i915: Lift waiter/signaler iterators
Chris Wilson
- [PATCH 28/44] drm/i915: Strip out internal priorities
Chris Wilson
- [PATCH 29/44] drm/i915: Remove I915_USER_PRIORITY_SHIFT
Chris Wilson
- [PATCH 30/44] drm/i915/gt: Defer the kmem_cache_free() until after the HW submit
Chris Wilson
- [PATCH 31/44] drm/i915: Prune empty priolists
Chris Wilson
- [PATCH 32/44] drm/i915: Replace engine->schedule() with a known request operation
Chris Wilson
- [PATCH 33/44] drm/i915/gt: Do not suspend bonded requests if one hangs
Chris Wilson
- [PATCH 34/44] drm/i915: Teach the i915_dependency to use a double-lock
Chris Wilson
- [PATCH 35/44] drm/i915: Restructure priority inheritance
Chris Wilson
- [PATCH 36/44] drm/i915/selftests: Measure set-priority duration
Chris Wilson
- [PATCH 37/44] drm/i915/selftests: Exercise priority inheritance around an engine loop
Chris Wilson
- [PATCH 38/44] drm/i915: Improve DFS for priority inheritance
Chris Wilson
- [PATCH 39/44] drm/i915/gt: Remove timeslice suppression
Chris Wilson
- [PATCH 40/44] drm/i915: Fair low-latency scheduling
Chris Wilson
- [PATCH 41/44] drm/i915/gt: Specify a deadline for the heartbeat
Chris Wilson
- [PATCH 42/44] drm/i915: Replace the priority boosting for the display with a deadline
Chris Wilson
- [PATCH 43/44] drm/i915: Move saturated workload detection back to the context
Chris Wilson
- [PATCH 44/44] drm/i915/gt: Another tweak for flushing the tasklets
Chris Wilson
- [PATCH 01/37] drm/i915/gem: Reduce context termination list iteration guard to RCU
Chris Wilson
- [PATCH 02/37] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 03/37] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 04/37] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 05/37] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 06/37] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 07/37] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 08/37] drm/i915/gem: Don't drop the timeline lock during execbuf
Chris Wilson
- [PATCH 09/37] drm/i915/gem: Rename execbuf.bind_link to unbound_link
Chris Wilson
- [PATCH 10/37] drm/i915/gem: Rename the list of relocations to reloc_list
Chris Wilson
- [PATCH 11/37] drm/i915/gem: Move the 'cached' info to i915_execbuffer
Chris Wilson
- [PATCH 12/37] drm/i915/gem: Break apart the early i915_vma_pin from execbuf object lookup
Chris Wilson
- [PATCH 13/37] drm/i915/gem: Remove the call for no-evict i915_vma_pin
Chris Wilson
- [PATCH 14/37] drm/i915: Serialise i915_vma_pin_inplace() with i915_vma_unbind()
Chris Wilson
- [PATCH 15/37] drm/i915: Add list_for_each_entry_safe_continue_reverse
Chris Wilson
- [PATCH 16/37] drm/i915: Always defer fenced work to the worker
Chris Wilson
- [PATCH 17/37] drm/i915/gem: Assign context id for async work
Chris Wilson
- [PATCH 18/37] drm/i915/gem: Separate the ww_mutex walker into its own list
Chris Wilson
- [PATCH 19/37] drm/i915/gem: Asynchronous GTT unbinding
Chris Wilson
- [PATCH 20/37] drm/i915/gem: Bind the fence async for execbuf
Chris Wilson
- [PATCH 21/37] drm/i915/gem: Include cmdparser in common execbuf pinning
Chris Wilson
- [PATCH 22/37] drm/i915/gem: Include secure batch in common execbuf pinning
Chris Wilson
- [PATCH 23/37] drm/i915/gem: Manage ppGTT placement bias (starting offset) explicitly
Chris Wilson
- [PATCH 24/37] drm/i915/gem: Reintroduce multiple passes for reloc processing
Chris Wilson
- [PATCH 25/37] drm/i915: Add an implementation for common reservation_ww_class locking
Chris Wilson
- [PATCH 26/37] drm/i915/gem: Pull execbuf dma resv under a single critical section
Chris Wilson
- [PATCH 27/37] drm/i915/gtt: map the PD up front
Chris Wilson
- [PATCH 28/37] drm/i915: Acquire the object lock around page directories
Chris Wilson
- [PATCH 29/37] drm/i915/gem: Replace i915_gem_object.mm.mutex with reservation_ww_class
Chris Wilson
- [PATCH 30/37] drm/i915: Hold wakeref for the duration of the vma GGTT binding
Chris Wilson
- [PATCH 31/37] drm/i915/gt: Refactor heartbeat request construction and submission
Chris Wilson
- [PATCH 32/37] drm/i915: Specialise GGTT binding
Chris Wilson
- [PATCH 33/37] drm/i915/gt: Acquire backing storage for the context
Chris Wilson
- [PATCH 34/37] drm/i915/gt: Push the wait for the context to bound to the request
Chris Wilson
- [PATCH 35/37] drm/i915: Remove unused i915_gem_evict_vm()
Chris Wilson
- [PATCH 36/37] drm/i915/display: Drop object lock from intel_unpin_fb_vma
Chris Wilson
- [PATCH 37/37] drm/i915/gem: Delay attach mmu-notifier until we acquire the pinned userptr
Chris Wilson
- [PATCH 01/37] drm/i915/gem: Reduce context termination list iteration guard to RCU
Chris Wilson
- [PATCH 02/37] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 03/37] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 04/37] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 05/37] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 06/37] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 07/37] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 08/37] drm/i915/gem: Don't drop the timeline lock during execbuf
Chris Wilson
- [PATCH 09/37] drm/i915/gem: Rename execbuf.bind_link to unbound_link
Chris Wilson
- [PATCH 10/37] drm/i915/gem: Rename the list of relocations to reloc_list
Chris Wilson
- [PATCH 11/37] drm/i915/gem: Move the 'cached' info to i915_execbuffer
Chris Wilson
- [PATCH 12/37] drm/i915/gem: Break apart the early i915_vma_pin from execbuf object lookup
Chris Wilson
- [PATCH 13/37] drm/i915/gem: Remove the call for no-evict i915_vma_pin
Chris Wilson
- [PATCH 14/37] drm/i915: Serialise i915_vma_pin_inplace() with i915_vma_unbind()
Chris Wilson
- [PATCH 15/37] drm/i915: Add list_for_each_entry_safe_continue_reverse
Chris Wilson
- [PATCH 16/37] drm/i915: Always defer fenced work to the worker
Chris Wilson
- [PATCH 17/37] drm/i915/gem: Assign context id for async work
Chris Wilson
- [PATCH 18/37] drm/i915/gem: Separate the ww_mutex walker into its own list
Chris Wilson
- [PATCH 19/37] drm/i915/gem: Asynchronous GTT unbinding
Chris Wilson
- [PATCH 20/37] drm/i915/gem: Bind the fence async for execbuf
Chris Wilson
- [PATCH 21/37] drm/i915/gem: Include cmdparser in common execbuf pinning
Chris Wilson
- [PATCH 22/37] drm/i915/gem: Include secure batch in common execbuf pinning
Chris Wilson
- [PATCH 23/37] drm/i915/gem: Manage GTT placement bias (starting offset) explicitly
Chris Wilson
- [PATCH 24/37] drm/i915/gem: Reintroduce multiple passes for reloc processing
Chris Wilson
- [PATCH 25/37] drm/i915: Add an implementation for common reservation_ww_class locking
Chris Wilson
- [PATCH 26/37] drm/i915/gem: Pull execbuf dma resv under a single critical section
Chris Wilson
- [PATCH 27/37] drm/i915/gtt: map the PD up front
Chris Wilson
- [PATCH 28/37] drm/i915: Acquire the object lock around page directories
Chris Wilson
- [PATCH 29/37] drm/i915/gem: Replace i915_gem_object.mm.mutex with reservation_ww_class
Chris Wilson
- [PATCH 30/37] drm/i915: Hold wakeref for the duration of the vma GGTT binding
Chris Wilson
- [PATCH 31/37] drm/i915/gt: Refactor heartbeat request construction and submission
Chris Wilson
- [PATCH 32/37] drm/i915: Specialise GGTT binding
Chris Wilson
- [PATCH 33/37] drm/i915/gt: Acquire backing storage for the context
Chris Wilson
- [PATCH 34/37] drm/i915/gt: Push the wait for the context to bound to the request
Chris Wilson
- [PATCH 35/37] drm/i915: Remove unused i915_gem_evict_vm()
Chris Wilson
- [PATCH 36/37] drm/i915/display: Drop object lock from intel_unpin_fb_vma
Chris Wilson
- [PATCH 37/37] drm/i915/gem: Delay attach mmu-notifier until we acquire the pinned userptr
Chris Wilson
- [PATCH 01/49] cyclic-ids
Chris Wilson
- [PATCH 02/49] drm/i915/gem: Reduce context termination list iteration guard to RCU
Chris Wilson
- [PATCH 03/49] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 04/49] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 05/49] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 06/49] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 07/49] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 08/49] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 09/49] drm/i915/gem: Don't drop the timeline lock during execbuf
Chris Wilson
- [PATCH 10/49] drm/i915: Drop i915_request.lock serialisation around await_start
Chris Wilson
- [PATCH 11/49] drm/i915: Drop i915_request.lock requirement for intel_rps_boost()
Chris Wilson
- [PATCH 12/49] drm/i915/gem: Reduce ctx->engine_mutex for reading the clone source
Chris Wilson
- [PATCH 13/49] drm/i915/gem: Reduce ctx->engines_mutex for get_engines()
Chris Wilson
- [PATCH 14/49] drm/i915: Reduce test_and_set_bit to set_bit in i915_request_submit()
Chris Wilson
- [PATCH 15/49] drm/i915/gt: Decouple completed requests on unwind
Chris Wilson
- [PATCH 16/49] drm/i915/gt: Check for a completed last request once
Chris Wilson
- [PATCH 17/49] drm/i915/gt: Refactor heartbeat request construction and submission
Chris Wilson
- [PATCH 18/49] drm/i915/gt: Replace direct submit with direct call to tasklet
Chris Wilson
- [PATCH 19/49] drm/i915/gt: Use virtual_engine during execlists_dequeue
Chris Wilson
- [PATCH 20/49] drm/i915/gt: Decouple inflight virtual engines
Chris Wilson
- [PATCH] cyclic-ids
Chris Wilson
- [PATCH 21/49] drm/i915/gt: Defer schedule_out until after the next dequeue
Chris Wilson
- [PATCH 22/49] drm/i915/gt: Resubmit the virtual engine on schedule-out
Chris Wilson
- [PATCH 23/49] drm/i915/gt: Simplify virtual engine handling for execlists_hold()
Chris Wilson
- [PATCH 24/49] drm/i915/gt: ce->inflight updates are now serialised
Chris Wilson
- [PATCH 25/49] drm/i915/gt: Drop atomic for engine->fw_active tracking
Chris Wilson
- [PATCH 26/49] drm/i915/gt: Extract busy-stats for ring-scheduler
Chris Wilson
- [PATCH 27/49] drm/i915/gt: Convert stats.active to plain unsigned int
Chris Wilson
- [PATCH 28/49] drm/i915: Lift waiter/signaler iterators
Chris Wilson
- [PATCH 29/49] drm/i915: Strip out internal priorities
Chris Wilson
- [PATCH 30/49] drm/i915: Remove I915_USER_PRIORITY_SHIFT
Chris Wilson
- [PATCH 31/49] drm/i915/gt: Defer the kmem_cache_free() until after the HW submit
Chris Wilson
- [PATCH 32/49] drm/i915: Prune empty priolists
Chris Wilson
- [PATCH 33/49] drm/i915: Replace engine->schedule() with a known request operation
Chris Wilson
- [PATCH 34/49] drm/i915/gt: Do not suspend bonded requests if one hangs
Chris Wilson
- [PATCH 35/49] drm/i915: Teach the i915_dependency to use a double-lock
Chris Wilson
- [PATCH 36/49] drm/i915: Restructure priority inheritance
Chris Wilson
- [PATCH 37/49] drm/i915/selftests: Measure set-priority duration
Chris Wilson
- [PATCH 38/49] drm/i915/selftests: Exercise priority inheritance around an engine loop
Chris Wilson
- [PATCH 39/49] drm/i915: Improve DFS for priority inheritance
Chris Wilson
- [PATCH 40/49] drm/i915/gt: Remove timeslice suppression
Chris Wilson
- [PATCH 41/49] enqueue
Chris Wilson
- [PATCH 42/49] onhold
Chris Wilson
- [PATCH 43/49] defer
Chris Wilson
- [PATCH 44/49] dfs-defer
Chris Wilson
- [PATCH 45/49] drm/i915: Fair low-latency scheduling
Chris Wilson
- [PATCH 46/49] drm/i915/gt: Specify a deadline for the heartbeat
Chris Wilson
- [PATCH 47/49] drm/i915: Replace the priority boosting for the display with a deadline
Chris Wilson
- [PATCH 48/49] drm/i915: Move saturated workload detection back to the context
Chris Wilson
- [PATCH 49/49] drm/i915/gt: Another tweak for flushing the tasklets
Chris Wilson
- [PATCH] cyclic-ids
Chris Wilson
- [PATCH] cyclic-ids
Chris Wilson
- [PATCH] cyclic-ids
Chris Wilson
- [PATCH] cyclic-ids
Chris Wilson
- [PATCH] cyclic-ids
Chris Wilson
- [PATCH] cyclic-ids
Chris Wilson
- [PATCH 1/8] drm/i915/gem: Reduce context termination list iteration guard to RCU
Chris Wilson
- [PATCH 2/8] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 3/8] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 4/8] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 5/8] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 6/8] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 7/8] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 8/8] bread
Chris Wilson
- [PATCH 01/39] drm/i915/gem: Reduce context termination list iteration guard to RCU
Chris Wilson
- [PATCH 02/39] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 03/39] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 04/39] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 05/39] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 06/39] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 07/39] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 08/39] bread
Chris Wilson
- [PATCH 09/39] drm/i915/gem: Don't drop the timeline lock during execbuf
Chris Wilson
- [PATCH 10/39] drm/i915/gem: Rename execbuf.bind_link to unbound_link
Chris Wilson
- [PATCH 11/39] drm/i915/gem: Rename the list of relocations to reloc_list
Chris Wilson
- [PATCH 12/39] drm/i915/gem: Move the 'cached' info to i915_execbuffer
Chris Wilson
- [PATCH 13/39] drm/i915/gem: Break apart the early i915_vma_pin from execbuf object lookup
Chris Wilson
- [PATCH 14/39] drm/i915/gem: Remove the call for no-evict i915_vma_pin
Chris Wilson
- [PATCH 15/39] drm/i915: Serialise i915_vma_pin_inplace() with i915_vma_unbind()
Chris Wilson
- [PATCH 16/39] drm/i915: Add list_for_each_entry_safe_continue_reverse
Chris Wilson
- [PATCH 17/39] drm/i915: Always defer fenced work to the worker
Chris Wilson
- [PATCH 18/39] drm/i915/gem: Assign context id for async work
Chris Wilson
- [PATCH 19/39] drm/i915/gem: Separate the ww_mutex walker into its own list
Chris Wilson
- [PATCH 20/39] drm/i915/gem: Asynchronous GTT unbinding
Chris Wilson
- [PATCH 21/39] drm/i915/gem: Bind the fence async for execbuf
Chris Wilson
- [PATCH 22/39] drm/i915/gem: Include cmdparser in common execbuf pinning
Chris Wilson
- [PATCH 23/39] drm/i915/gem: Include secure batch in common execbuf pinning
Chris Wilson
- [PATCH 24/39] drm/i915/gem: Manage GTT placement bias (starting offset) explicitly
Chris Wilson
- [PATCH 25/39] drm/i915/gem: Reintroduce multiple passes for reloc processing
Chris Wilson
- [PATCH 26/39] drm/i915: Add an implementation for common reservation_ww_class locking
Chris Wilson
- [PATCH 27/39] drm/i915/gem: Pull execbuf dma resv under a single critical section
Chris Wilson
- [PATCH 28/39] drm/i915/gtt: map the PD up front
Chris Wilson
- [PATCH 29/39] drm/i915: Acquire the object lock around page directories
Chris Wilson
- [PATCH 30/39] drm/i915/gem: Replace i915_gem_object.mm.mutex with reservation_ww_class
Chris Wilson
- [PATCH 31/39] drm/i915: Hold wakeref for the duration of the vma GGTT binding
Chris Wilson
- [PATCH 32/39] drm/i915/gt: Refactor heartbeat request construction and submission
Chris Wilson
- [PATCH 33/39] drm/i915: Specialise GGTT binding
Chris Wilson
- [PATCH 34/39] drm/i915/gt: Acquire backing storage for the context
Chris Wilson
- [PATCH 35/39] drm/i915/gt: Push the wait for the context to bound to the request
Chris Wilson
- [PATCH 36/39] drm/i915: Remove unused i915_gem_evict_vm()
Chris Wilson
- [PATCH 37/39] drm/i915/display: Drop object lock from intel_unpin_fb_vma
Chris Wilson
- [PATCH 38/39] drm/i915/gem: Delay attach mmu-notifier until we acquire the pinned userptr
Chris Wilson
- [PATCH 39/39] seres
Chris Wilson
- [PATCH 1/8] drm/i915/gem: Reduce context termination list iteration guard to RCU
Chris Wilson
- [PATCH 2/8] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 3/8] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 4/8] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 5/8] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 6/8] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 7/8] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 8/8] bread
Chris Wilson
- [PATCH 01/38] drm/i915/gem: Reduce context termination list iteration guard to RCU
Chris Wilson
- [PATCH 02/38] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 03/38] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 04/38] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 05/38] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 06/38] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 07/38] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 08/38] bread
Chris Wilson
- [PATCH 09/38] drm/i915/gem: Don't drop the timeline lock during execbuf
Chris Wilson
- [PATCH 10/38] drm/i915/gem: Rename execbuf.bind_link to unbound_link
Chris Wilson
- [PATCH 11/38] drm/i915/gem: Rename the list of relocations to reloc_list
Chris Wilson
- [PATCH 12/38] drm/i915/gem: Move the 'cached' info to i915_execbuffer
Chris Wilson
- [PATCH 13/38] drm/i915/gem: Break apart the early i915_vma_pin from execbuf object lookup
Chris Wilson
- [PATCH 14/38] drm/i915/gem: Remove the call for no-evict i915_vma_pin
Chris Wilson
- [PATCH 15/38] drm/i915: Serialise i915_vma_pin_inplace() with i915_vma_unbind()
Chris Wilson
- [PATCH 16/38] drm/i915: Add list_for_each_entry_safe_continue_reverse
Chris Wilson
- [PATCH 17/38] drm/i915: Always defer fenced work to the worker
Chris Wilson
- [PATCH 18/38] drm/i915/gem: Assign context id for async work
Chris Wilson
- [PATCH 19/38] drm/i915/gem: Separate the ww_mutex walker into its own list
Chris Wilson
- [PATCH 20/38] drm/i915/gem: Asynchronous GTT unbinding
Chris Wilson
- [PATCH 21/38] drm/i915/gem: Bind the fence async for execbuf
Chris Wilson
- [PATCH 22/38] drm/i915/gem: Include cmdparser in common execbuf pinning
Chris Wilson
- [PATCH 23/38] drm/i915/gem: Include secure batch in common execbuf pinning
Chris Wilson
- [PATCH 24/38] drm/i915/gem: Manage GTT placement bias (starting offset) explicitly
Chris Wilson
- [PATCH 25/38] drm/i915/gem: Reintroduce multiple passes for reloc processing
Chris Wilson
- [PATCH 26/38] drm/i915: Add an implementation for common reservation_ww_class locking
Chris Wilson
- [PATCH 27/38] drm/i915/gem: Pull execbuf dma resv under a single critical section
Chris Wilson
- [PATCH 28/38] drm/i915/gtt: map the PD up front
Chris Wilson
- [PATCH 29/38] drm/i915: Acquire the object lock around page directories
Chris Wilson
- [PATCH 30/38] drm/i915/gem: Replace i915_gem_object.mm.mutex with reservation_ww_class
Chris Wilson
- [PATCH 31/38] drm/i915: Hold wakeref for the duration of the vma GGTT binding
Chris Wilson
- [PATCH 32/38] drm/i915/gt: Refactor heartbeat request construction and submission
Chris Wilson
- [PATCH 33/38] drm/i915: Specialise GGTT binding
Chris Wilson
- [PATCH 34/38] drm/i915/gt: Acquire backing storage for the context
Chris Wilson
- [PATCH 35/38] drm/i915/gt: Push the wait for the context to bound to the request
Chris Wilson
- [PATCH 36/38] drm/i915: Remove unused i915_gem_evict_vm()
Chris Wilson
- [PATCH 37/38] drm/i915/display: Drop object lock from intel_unpin_fb_vma
Chris Wilson
- [PATCH 38/38] drm/i915/gem: Delay attach mmu-notifier until we acquire the pinned userptr
Chris Wilson
- [PATCH 1/4] drm/i915/gem: Reduce context termination list iteration guard to RCU
Chris Wilson
- [PATCH 2/4] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 3/4] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 4/4] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 1/7] drm/i915/gem: Reduce context termination list iteration guard to RCU
Chris Wilson
- [PATCH 2/7] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 3/7] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 4/7] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 5/7] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 6/7] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 7/7] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 1/4] drm/i915/gem: Reduce context termination list iteration guard to RCU
Chris Wilson
- [PATCH 2/4] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 3/4] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 4/4] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 1/4] drm/i915/gem: Reduce context termination list iteration guard to RCU
Chris Wilson
- [PATCH 2/4] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 3/4] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 4/4] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 1/4] drm/i915/gem: Reduce context termination list iteration guard to RCU
Chris Wilson
- [PATCH 2/4] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 3/4] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 4/4] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 1/7] drm/i915/gem: Reduce context termination list iteration guard to RCU
Chris Wilson
- [PATCH 2/7] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 3/7] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 4/7] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 5/7] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 6/7] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 7/7] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 1/3] drm/i915/gem: Reduce context termination list iteration guard to RCU
Chris Wilson
- [PATCH 2/3] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 3/3] ve2
Chris Wilson
- [PATCH 1/6] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 2/6] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 3/6] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 4/6] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 5/6] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 6/6] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 1/7] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 2/7] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 3/7] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 4/7] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 5/7] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 6/7] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 7/7] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 1/4] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 2/4] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 3/4] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 4/4] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH] drm/i915: Encode fence specific waitqueue behaviour into the wait.flags
Chris Wilson
- [PATCH] drm/i915/gt: Rejig "Forcibly evict stable csb entries" for Tigerlake
Chris Wilson
- [PATCH] bruce
Chris Wilson
- [PATCH 01/80] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 02/80] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 03/80] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 04/80] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 05/80] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 06/80] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 07/80] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 08/80] drm/i915/gem: Don't drop the timeline lock during execbuf
Chris Wilson
- [PATCH 09/80] drm/i915/gem: Rename execbuf.bind_link to unbound_link
Chris Wilson
- [PATCH 10/80] drm/i915/gem: Rename the list of relocations to reloc_list
Chris Wilson
- [PATCH 11/80] drm/i915/gem: Move the 'cached' info to i915_execbuffer
Chris Wilson
- [PATCH 12/80] drm/i915/gem: Break apart the early i915_vma_pin from execbuf object lookup
Chris Wilson
- [PATCH 13/80] drm/i915/gem: Remove the call for no-evict i915_vma_pin
Chris Wilson
- [PATCH 14/80] drm/i915: Serialise i915_vma_pin_inplace() with i915_vma_unbind()
Chris Wilson
- [PATCH 15/80] drm/i915: Add list_for_each_entry_safe_continue_reverse
Chris Wilson
- [PATCH 16/80] drm/i915: Always defer fenced work to the worker
Chris Wilson
- [PATCH 17/80] drm/i915/gem: Assign context id for async work
Chris Wilson
- [PATCH 18/80] drm/i915/gem: Separate the ww_mutex walker into its own list
Chris Wilson
- [PATCH 19/80] drm/i915/gem: Asynchronous GTT unbinding
Chris Wilson
- [PATCH 20/80] drm/i915/gem: Bind the fence async for execbuf
Chris Wilson
- [PATCH 21/80] drm/i915/gem: Include cmdparser in common execbuf pinning
Chris Wilson
- [PATCH 22/80] drm/i915/gem: Include secure batch in common execbuf pinning
Chris Wilson
- [PATCH 23/80] drm/i915/gem: Manage GTT placement bias (starting offset) explicitly
Chris Wilson
- [PATCH 24/80] drm/i915/gem: Reintroduce multiple passes for reloc processing
Chris Wilson
- [PATCH 25/80] drm/i915: Add an implementation for common reservation_ww_class locking
Chris Wilson
- [PATCH 26/80] drm/i915/gem: Pull execbuf dma resv under a single critical section
Chris Wilson
- [PATCH 27/80] drm/i915/gtt: map the PD up front
Chris Wilson
- [PATCH 28/80] drm/i915: Acquire the object lock around page directories
Chris Wilson
- [PATCH 29/80] drm/i915/gem: Replace i915_gem_object.mm.mutex with reservation_ww_class
Chris Wilson
- [PATCH 30/80] drm/i915: Hold wakeref for the duration of the vma GGTT binding
Chris Wilson
- [PATCH 31/80] drm/i915/gt: Refactor heartbeat request construction and submission
Chris Wilson
- [PATCH 32/80] drm/i915: Specialise GGTT binding
Chris Wilson
- [PATCH 33/80] drm/i915/gt: Acquire backing storage for the context
Chris Wilson
- [PATCH 34/80] drm/i915/gt: Push the wait for the context to bound to the request
Chris Wilson
- [PATCH 35/80] drm/i915: Remove unused i915_gem_evict_vm()
Chris Wilson
- [PATCH 36/80] drm/i915/display: Drop object lock from intel_unpin_fb_vma
Chris Wilson
- [PATCH 37/80] drm/i915/gem: Delay attach mmu-notifier until we acquire the pinned userptr
Chris Wilson
- [PATCH 38/80] drm/i915: Drop i915_request.lock serialisation around await_start
Chris Wilson
- [PATCH 39/80] drm/i915: Drop i915_request.lock requirement for intel_rps_boost()
Chris Wilson
- [PATCH 40/80] drm/i915/gem: Reduce ctx->engine_mutex for reading the clone source
Chris Wilson
- [PATCH 41/80] drm/i915/gem: Reduce ctx->engines_mutex for get_engines()
Chris Wilson
- [PATCH 42/80] drm/i915: Reduce test_and_set_bit to set_bit in i915_request_submit()
Chris Wilson
- [PATCH 43/80] drm/i915/gt: Decouple completed requests on unwind
Chris Wilson
- [PATCH 44/80] drm/i915/gt: Check for a completed last request once
Chris Wilson
- [PATCH 45/80] drm/i915/gt: Replace direct submit with direct call to tasklet
Chris Wilson
- [PATCH 46/80] drm/i915/gt: Use virtual_engine during execlists_dequeue
Chris Wilson
- [PATCH 47/80] drm/i915/gt: Decouple inflight virtual engines
Chris Wilson
- [PATCH 48/80] drm/i915/gt: Defer schedule_out until after the next dequeue
Chris Wilson
- [PATCH 49/80] drm/i915/gt: Resubmit the virtual engine on schedule-out
Chris Wilson
- [PATCH 50/80] drm/i915/gt: Simplify virtual engine handling for execlists_hold()
Chris Wilson
- [PATCH 51/80] drm/i915/gt: ce->inflight updates are now serialised
Chris Wilson
- [PATCH 52/80] drm/i915/gt: Drop atomic for engine->fw_active tracking
Chris Wilson
- [PATCH 53/80] drm/i915/gt: Extract busy-stats for ring-scheduler
Chris Wilson
- [PATCH 54/80] drm/i915/gt: Convert stats.active to plain unsigned int
Chris Wilson
- [PATCH 55/80] drm/i915: Lift waiter/signaler iterators
Chris Wilson
- [PATCH 56/80] drm/i915: Strip out internal priorities
Chris Wilson
- [PATCH 57/80] drm/i915: Remove I915_USER_PRIORITY_SHIFT
Chris Wilson
- [PATCH 58/80] drm/i915/gt: Defer the kmem_cache_free() until after the HW submit
Chris Wilson
- [PATCH 59/80] drm/i915: Prune empty priolists
Chris Wilson
- [PATCH 60/80] drm/i915: Replace engine->schedule() with a known request operation
Chris Wilson
- [PATCH 61/80] drm/i915/gt: Do not suspend bonded requests if one hangs
Chris Wilson
- [PATCH 62/80] drm/i915: Teach the i915_dependency to use a double-lock
Chris Wilson
- [PATCH 63/80] drm/i915: Restructure priority inheritance
Chris Wilson
- [PATCH 64/80] drm/i915/selftests: Measure set-priority duration
Chris Wilson
- [PATCH 65/80] drm/i915/selftests: Exercise priority inheritance around an engine loop
Chris Wilson
- [PATCH 66/80] drm/i915: Improve DFS for priority inheritance
Chris Wilson
- [PATCH 67/80] drm/i915/gt: Remove timeslice suppression
Chris Wilson
- [PATCH 68/80] enqueue
Chris Wilson
- [PATCH 69/80] onhold
Chris Wilson
- [PATCH 70/80] defer
Chris Wilson
- [PATCH 71/80] dfs-defer
Chris Wilson
- [PATCH 72/80] drm/i915: Fair low-latency scheduling
Chris Wilson
- [PATCH 73/80] drm/i915/gt: Specify a deadline for the heartbeat
Chris Wilson
- [PATCH 74/80] drm/i915: Replace the priority boosting for the display with a deadline
Chris Wilson
- [PATCH 75/80] drm/i915: Move saturated workload detection back to the context
Chris Wilson
- [PATCH 76/80] drm/i915/gt: Another tweak for flushing the tasklets
Chris Wilson
- [PATCH 77/80] drm/i915/gt: Support virtual engine queues
Chris Wilson
- [PATCH 78/80] drm/i915/gt: Stall around xcs invalidations on tgl
Chris Wilson
- [PATCH 79/80] drm/i915/gt: Prevent immediate reuse of the last context tag
Chris Wilson
- [PATCH 80/80] irq
Chris Wilson
- [PATCH 1/2] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 2/2] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 1/4] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 2/4] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 3/4] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 4/4] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 1/2] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 2/2] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 1/3] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 2/3] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 3/3] gtpm
Chris Wilson
- [PATCH 1/9] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 2/9] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 3/9] gtpm
Chris Wilson
- [PATCH 4/9] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 5/9] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 6/9] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 7/9] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 8/9] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 9/9] rcu-signal
Chris Wilson
- [PATCH 1/8] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 2/8] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 3/8] gtpm
Chris Wilson
- [PATCH 4/8] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 5/8] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 6/8] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 7/8] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 8/8] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH] drm/i915/gt: Signal cancelled requests upon wedging
Chris Wilson
- [PATCH] drm/i915/gt: Signal cancelled requests upon wedging
Chris Wilson
- [PATCH] drm/i915: Encode fence specific waitqueue behaviour into the wait.flags
Chris Wilson
- [PATCH 1/8] drm/i915/gt: Signal cancelled requests upon wedging
Chris Wilson
- [PATCH 2/8] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 3/8] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 4/8] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 5/8] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 6/8] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 7/8] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 8/8] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 01/78] drm/i915/gt: Signal cancelled requests upon wedging
Chris Wilson
- [PATCH 02/78] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 03/78] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 04/78] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 05/78] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 06/78] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 07/78] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 08/78] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 09/78] drm/i915/gt: Prefer recycling an idle fence
Chris Wilson
- [PATCH 10/78] drm/i915/gem: Don't drop the timeline lock during execbuf
Chris Wilson
- [PATCH 11/78] drm/i915/gem: Rename execbuf.bind_link to unbound_link
Chris Wilson
- [PATCH 12/78] drm/i915/gem: Rename the list of relocations to reloc_list
Chris Wilson
- [PATCH 13/78] drm/i915/gem: Move the 'cached' info to i915_execbuffer
Chris Wilson
- [PATCH 14/78] drm/i915/gem: Break apart the early i915_vma_pin from execbuf object lookup
Chris Wilson
- [PATCH 15/78] drm/i915/gem: Remove the call for no-evict i915_vma_pin
Chris Wilson
- [PATCH 16/78] drm/i915: Serialise i915_vma_pin_inplace() with i915_vma_unbind()
Chris Wilson
- [PATCH 17/78] drm/i915: Add list_for_each_entry_safe_continue_reverse
Chris Wilson
- [PATCH 18/78] drm/i915: Always defer fenced work to the worker
Chris Wilson
- [PATCH 19/78] drm/i915/gem: Assign context id for async work
Chris Wilson
- [PATCH 20/78] drm/i915/gem: Separate the ww_mutex walker into its own list
Chris Wilson
- [PATCH 21/78] drm/i915/gem: Asynchronous GTT unbinding
Chris Wilson
- [PATCH 22/78] drm/i915/gem: Bind the fence async for execbuf
Chris Wilson
- [PATCH 23/78] drm/i915/gem: Include cmdparser in common execbuf pinning
Chris Wilson
- [PATCH 24/78] drm/i915/gem: Include secure batch in common execbuf pinning
Chris Wilson
- [PATCH 25/78] drm/i915/gem: Manage GTT placement bias (starting offset) explicitly
Chris Wilson
- [PATCH 26/78] drm/i915/gem: Reintroduce multiple passes for reloc processing
Chris Wilson
- [PATCH 27/78] drm/i915: Add an implementation for common reservation_ww_class locking
Chris Wilson
- [PATCH 28/78] drm/i915/gem: Pull execbuf dma resv under a single critical section
Chris Wilson
- [PATCH 29/78] drm/i915/gtt: map the PD up front
Chris Wilson
- [PATCH 30/78] drm/i915: Acquire the object lock around page directories
Chris Wilson
- [PATCH 31/78] drm/i915/gem: Replace i915_gem_object.mm.mutex with reservation_ww_class
Chris Wilson
- [PATCH 32/78] drm/i915: Hold wakeref for the duration of the vma GGTT binding
Chris Wilson
- [PATCH 33/78] drm/i915/gt: Refactor heartbeat request construction and submission
Chris Wilson
- [PATCH 34/78] drm/i915: Specialise GGTT binding
Chris Wilson
- [PATCH 35/78] drm/i915/gt: Acquire backing storage for the context
Chris Wilson
- [PATCH 36/78] drm/i915/gt: Push the wait for the context to bound to the request
Chris Wilson
- [PATCH 37/78] drm/i915: Remove unused i915_gem_evict_vm()
Chris Wilson
- [PATCH 38/78] drm/i915/display: Drop object lock from intel_unpin_fb_vma
Chris Wilson
- [PATCH 39/78] drm/i915/gem: Delay attach mmu-notifier until we acquire the pinned userptr
Chris Wilson
- [PATCH 40/78] drm/i915: Drop i915_request.lock serialisation around await_start
Chris Wilson
- [PATCH 41/78] drm/i915: Drop i915_request.lock requirement for intel_rps_boost()
Chris Wilson
- [PATCH 42/78] drm/i915/gem: Reduce ctx->engine_mutex for reading the clone source
Chris Wilson
- [PATCH 43/78] drm/i915/gem: Reduce ctx->engines_mutex for get_engines()
Chris Wilson
- [PATCH 44/78] drm/i915: Reduce test_and_set_bit to set_bit in i915_request_submit()
Chris Wilson
- [PATCH 45/78] drm/i915/gt: Decouple completed requests on unwind
Chris Wilson
- [PATCH 46/78] drm/i915/gt: Check for a completed last request once
Chris Wilson
- [PATCH 47/78] drm/i915/gt: Replace direct submit with direct call to tasklet
Chris Wilson
- [PATCH 48/78] drm/i915/gt: Use virtual_engine during execlists_dequeue
Chris Wilson
- [PATCH 49/78] drm/i915/gt: Decouple inflight virtual engines
Chris Wilson
- [PATCH 50/78] drm/i915/gt: Defer schedule_out until after the next dequeue
Chris Wilson
- [PATCH 51/78] drm/i915/gt: Resubmit the virtual engine on schedule-out
Chris Wilson
- [PATCH 52/78] drm/i915/gt: Simplify virtual engine handling for execlists_hold()
Chris Wilson
- [PATCH 53/78] drm/i915/gt: ce->inflight updates are now serialised
Chris Wilson
- [PATCH 54/78] drm/i915/gt: Drop atomic for engine->fw_active tracking
Chris Wilson
- [PATCH 55/78] drm/i915/gt: Extract busy-stats for ring-scheduler
Chris Wilson
- [PATCH 56/78] drm/i915/gt: Convert stats.active to plain unsigned int
Chris Wilson
- [PATCH 57/78] drm/i915: Lift waiter/signaler iterators
Chris Wilson
- [PATCH 58/78] drm/i915: Strip out internal priorities
Chris Wilson
- [PATCH 59/78] drm/i915: Remove I915_USER_PRIORITY_SHIFT
Chris Wilson
- [PATCH 60/78] drm/i915/gt: Defer the kmem_cache_free() until after the HW submit
Chris Wilson
- [PATCH 61/78] drm/i915: Prune empty priolists
Chris Wilson
- [PATCH 62/78] drm/i915: Replace engine->schedule() with a known request operation
Chris Wilson
- [PATCH 63/78] drm/i915/gt: Do not suspend bonded requests if one hangs
Chris Wilson
- [PATCH 64/78] drm/i915: Teach the i915_dependency to use a double-lock
Chris Wilson
- [PATCH 65/78] drm/i915: Restructure priority inheritance
Chris Wilson
- [PATCH 66/78] drm/i915/selftests: Measure set-priority duration
Chris Wilson
- [PATCH 67/78] drm/i915/selftests: Exercise priority inheritance around an engine loop
Chris Wilson
- [PATCH 68/78] drm/i915: Improve DFS for priority inheritance
Chris Wilson
- [PATCH 69/78] drm/i915/gt: Remove timeslice suppression
Chris Wilson
- [PATCH 70/78] enqueue
Chris Wilson
- [PATCH 71/78] onhold
Chris Wilson
- [PATCH 72/78] defer
Chris Wilson
- [PATCH 73/78] dfs-defer
Chris Wilson
- [PATCH 74/78] drm/i915: Fair low-latency scheduling
Chris Wilson
- [PATCH 75/78] drm/i915/gt: Specify a deadline for the heartbeat
Chris Wilson
- [PATCH 76/78] drm/i915: Replace the priority boosting for the display with a deadline
Chris Wilson
- [PATCH 77/78] drm/i915: Move saturated workload detection back to the context
Chris Wilson
- [PATCH 78/78] drm/i915/gt: Another tweak for flushing the tasklets
Chris Wilson
- [PATCH 1/9] drm/i915/gt: Signal cancelled requests upon wedging
Chris Wilson
- [PATCH 2/9] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 3/9] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 4/9] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 5/9] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 6/9] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 7/9] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 8/9] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 9/9] drm/i915/gt: Prefer recycling an idle fence
Chris Wilson
- [PATCH 01/39] drm/i915/gt: Signal cancelled requests upon wedging
Chris Wilson
- [PATCH 02/39] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 03/39] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 04/39] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 05/39] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 06/39] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 07/39] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 08/39] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 09/39] drm/i915/gt: Prefer recycling an idle fence
Chris Wilson
- [PATCH 10/39] drm/i915/gem: Don't drop the timeline lock during execbuf
Chris Wilson
- [PATCH 11/39] drm/i915/gem: Rename execbuf.bind_link to unbound_link
Chris Wilson
- [PATCH 12/39] drm/i915/gem: Rename the list of relocations to reloc_list
Chris Wilson
- [PATCH 13/39] drm/i915/gem: Move the 'cached' info to i915_execbuffer
Chris Wilson
- [PATCH 14/39] drm/i915/gem: Break apart the early i915_vma_pin from execbuf object lookup
Chris Wilson
- [PATCH 15/39] drm/i915/gem: Remove the call for no-evict i915_vma_pin
Chris Wilson
- [PATCH 16/39] drm/i915: Serialise i915_vma_pin_inplace() with i915_vma_unbind()
Chris Wilson
- [PATCH 17/39] drm/i915: Add list_for_each_entry_safe_continue_reverse
Chris Wilson
- [PATCH 18/39] drm/i915: Always defer fenced work to the worker
Chris Wilson
- [PATCH 19/39] drm/i915/gem: Assign context id for async work
Chris Wilson
- [PATCH 20/39] drm/i915/gem: Separate the ww_mutex walker into its own list
Chris Wilson
- [PATCH 21/39] drm/i915/gem: Asynchronous GTT unbinding
Chris Wilson
- [PATCH 22/39] drm/i915/gem: Bind the fence async for execbuf
Chris Wilson
- [PATCH 23/39] drm/i915/gem: Include cmdparser in common execbuf pinning
Chris Wilson
- [PATCH 24/39] drm/i915/gem: Include secure batch in common execbuf pinning
Chris Wilson
- [PATCH 25/39] drm/i915/gem: Manage GTT placement bias (starting offset) explicitly
Chris Wilson
- [PATCH 26/39] drm/i915/gem: Reintroduce multiple passes for reloc processing
Chris Wilson
- [PATCH 27/39] drm/i915: Add an implementation for common reservation_ww_class locking
Chris Wilson
- [PATCH 28/39] drm/i915/gem: Pull execbuf dma resv under a single critical section
Chris Wilson
- [PATCH 29/39] drm/i915/gtt: map the PD up front
Chris Wilson
- [PATCH 30/39] drm/i915: Acquire the object lock around page directories
Chris Wilson
- [PATCH 31/39] drm/i915/gem: Replace i915_gem_object.mm.mutex with reservation_ww_class
Chris Wilson
- [PATCH 32/39] drm/i915: Hold wakeref for the duration of the vma GGTT binding
Chris Wilson
- [PATCH 33/39] drm/i915/gt: Refactor heartbeat request construction and submission
Chris Wilson
- [PATCH 34/39] drm/i915: Specialise GGTT binding
Chris Wilson
- [PATCH 35/39] drm/i915/gt: Acquire backing storage for the context
Chris Wilson
- [PATCH 36/39] drm/i915/gt: Push the wait for the context to bound to the request
Chris Wilson
- [PATCH 37/39] drm/i915: Remove unused i915_gem_evict_vm()
Chris Wilson
- [PATCH 38/39] drm/i915/display: Drop object lock from intel_unpin_fb_vma
Chris Wilson
- [PATCH 39/39] drm/i915/gem: Delay attach mmu-notifier until we acquire the pinned userptr
Chris Wilson
- [PATCH 01/28] drm/i915/gt: Signal cancelled requests upon wedging
Chris Wilson
- [PATCH 02/28] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 03/28] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 04/28] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 05/28] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 06/28] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 07/28] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 08/28] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 09/28] drm/i915/gt: Prefer recycling an idle fence
Chris Wilson
- [PATCH 10/28] drm/i915/gem: Don't drop the timeline lock during execbuf
Chris Wilson
- [PATCH 11/28] drm/i915/gem: Rename execbuf.bind_link to unbound_link
Chris Wilson
- [PATCH 12/28] drm/i915/gem: Rename the list of relocations to reloc_list
Chris Wilson
- [PATCH 13/28] drm/i915/gem: Move the 'cached' info to i915_execbuffer
Chris Wilson
- [PATCH 14/28] drm/i915/gem: Break apart the early i915_vma_pin from execbuf object lookup
Chris Wilson
- [PATCH 15/28] drm/i915/gem: Remove the call for no-evict i915_vma_pin
Chris Wilson
- [PATCH 16/28] drm/i915: Serialise i915_vma_pin_inplace() with i915_vma_unbind()
Chris Wilson
- [PATCH 17/28] drm/i915: Add list_for_each_entry_safe_continue_reverse
Chris Wilson
- [PATCH 18/28] drm/i915: Always defer fenced work to the worker
Chris Wilson
- [PATCH 19/28] drm/i915/gem: Assign context id for async work
Chris Wilson
- [PATCH 20/28] drm/i915/gem: Separate the ww_mutex walker into its own list
Chris Wilson
- [PATCH 21/28] drm/i915/gem: Asynchronous GTT unbinding
Chris Wilson
- [PATCH 22/28] drm/i915/gem: Bind the fence async for execbuf
Chris Wilson
- [PATCH 23/28] drm/i915/gem: Include cmdparser in common execbuf pinning
Chris Wilson
- [PATCH 24/28] drm/i915/gem: Include secure batch in common execbuf pinning
Chris Wilson
- [PATCH 25/28] drm/i915/gem: Manage GTT placement bias (starting offset) explicitly
Chris Wilson
- [PATCH 26/28] drm/i915/gem: Reintroduce multiple passes for reloc processing
Chris Wilson
- [PATCH 27/28] drm/i915: Add an implementation for common reservation_ww_class locking
Chris Wilson
- [PATCH 28/28] drm/i915/gem: Pull execbuf dma resv under a single critical section
Chris Wilson
- [PATCH 01/16] drm/i915/gt: Signal cancelled requests upon wedging
Chris Wilson
- [PATCH 02/16] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 03/16] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 04/16] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 05/16] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 06/16] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 07/16] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 08/16] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 09/16] drm/i915/gt: Prefer recycling an idle fence
Chris Wilson
- [PATCH 10/16] drm/i915/gem: Don't drop the timeline lock during execbuf
Chris Wilson
- [PATCH 11/16] drm/i915/gem: Rename execbuf.bind_link to unbound_link
Chris Wilson
- [PATCH 12/16] drm/i915/gem: Rename the list of relocations to reloc_list
Chris Wilson
- [PATCH 13/16] drm/i915/gem: Move the 'cached' info to i915_execbuffer
Chris Wilson
- [PATCH 14/16] drm/i915/gem: Break apart the early i915_vma_pin from execbuf object lookup
Chris Wilson
- [PATCH 15/16] drm/i915/gem: Remove the call for no-evict i915_vma_pin
Chris Wilson
- [PATCH 16/16] drm/i915: Serialise i915_vma_pin_inplace() with i915_vma_unbind()
Chris Wilson
- [PATCH 01/16] drm/i915/gt: Signal cancelled requests upon wedging
Chris Wilson
- [PATCH 02/16] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 03/16] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 04/16] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 05/16] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 06/16] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 07/16] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 08/16] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 09/16] drm/i915/gt: Prefer recycling an idle fence
Chris Wilson
- [PATCH 10/16] drm/i915/gem: Don't drop the timeline lock during execbuf
Chris Wilson
- [PATCH 11/16] drm/i915/gem: Rename execbuf.bind_link to unbound_link
Chris Wilson
- [PATCH 12/16] drm/i915/gem: Rename the list of relocations to reloc_list
Chris Wilson
- [PATCH 13/16] drm/i915/gem: Move the 'cached' info to i915_execbuffer
Chris Wilson
- [PATCH 14/16] drm/i915/gem: Break apart the early i915_vma_pin from execbuf object lookup
Chris Wilson
- [PATCH 15/16] drm/i915/gem: Remove the call for no-evict i915_vma_pin
Chris Wilson
- [PATCH 16/16] drm/i915: Serialise i915_vma_pin_inplace() with i915_vma_unbind()
Chris Wilson
- [PATCH 1/8] drm/i915/gt: Signal cancelled requests upon wedging
Chris Wilson
- [PATCH 2/8] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 3/8] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 4/8] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 5/8] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 6/8] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 7/8] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 8/8] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH] retire-request-onfini
Chris Wilson
- [PATCH 1/8] retire-request-onfini
Chris Wilson
- [PATCH 2/8] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 3/8] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 4/8] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 5/8] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 6/8] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 7/8] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 8/8] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 01/10] drm/i915/gt: Signal cancelled requests
Chris Wilson
- [PATCH 02/10] drm/i915/selftests: Finish pending mock requests on cancellation.
Chris Wilson
- [PATCH 03/10] drm/i915/gt: Retire cancelled requests on unload
Chris Wilson
- [PATCH 04/10] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 05/10] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 06/10] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 07/10] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 08/10] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 09/10] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 10/10] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 1/2] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Chris Wilson
- [PATCH 2/2] icl-fixup?
Chris Wilson
- [PATCH 1/2] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Chris Wilson
- [PATCH 2/2] icl-fixup?
Chris Wilson
- [PATCH 1/2] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Chris Wilson
- [PATCH 2/2] icl-fixup?
Chris Wilson
- [PATCH 1/2] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Chris Wilson
- [PATCH 2/2] consolidate-gt-clock
Chris Wilson
- [PATCH 1/2] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Chris Wilson
- [PATCH 2/2] drm/i915/gt: Consolidate the CS timestamp clocks
Chris Wilson
- [PATCH 1/2] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Chris Wilson
- [PATCH 2/2] drm/i915/gt: Consolidate the CS timestamp clocks
Chris Wilson
- [PATCH 1/2] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Chris Wilson
- [PATCH 2/2] drm/i915/gt: Consolidate the CS timestamp clocks
Chris Wilson
- [PATCH] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Chris Wilson
- [PATCH] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Chris Wilson
- [PATCH 1/2] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Chris Wilson
- [PATCH 2/2] drm/i915/gt: Wait for CSB entries on Tigerlake
Chris Wilson
- [PATCH 1/3] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Chris Wilson
- [PATCH 2/3] drm/i915/gt: Wait for CSB entries on Tigerlake
Chris Wilson
- [PATCH 3/3] drm/i915/gt: Apply the CSB w/a for all
Chris Wilson
- [PATCH 1/3] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Chris Wilson
- [PATCH 2/3] drm/i915/gt: Wait for CSB entries on Tigerlake
Chris Wilson
- [PATCH 3/3] drm/i915/gt: Apply the CSB w/a for all
Chris Wilson
- [PATCH 01/19] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Chris Wilson
- [PATCH 02/19] drm/i915/gt: Wait for CSB entries on Tigerlake
Chris Wilson
- [PATCH 03/19] drm/i915/gt: Apply the CSB w/a for all
Chris Wilson
- [PATCH 04/19] drm/i915: Cancel outstanding work after disabling heartbeats on an engine
Chris Wilson
- [PATCH 05/19] drm/i915/gt: Always send a pulse down the engine after disabling heartbeat
Chris Wilson
- [PATCH 06/19] drm/i915/gem: Always test execution status on closing the context
Chris Wilson
- [PATCH 07/19] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Chris Wilson
- [PATCH 08/19] drm/i915/gt: Consolidate the CS timestamp clocks
Chris Wilson
- [PATCH 09/19] drm/i915: Drop runtime-pm assert from vgpu io accessors
Chris Wilson
- [PATCH 10/19] drm/i915/gt: Signal cancelled requests
Chris Wilson
- [PATCH 11/19] drm/i915/selftests: Finish pending mock requests on cancellation.
Chris Wilson
- [PATCH 12/19] drm/i915/gt: Retire cancelled requests on unload
Chris Wilson
- [PATCH 13/19] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 14/19] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 15/19] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 16/19] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 17/19] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 18/19] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 19/19] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 01/18] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Chris Wilson
- [PATCH 02/18] drm/i915/gt: Wait for CSB entries on Tigerlake
Chris Wilson
- [PATCH 03/18] drm/i915/gt: Apply the CSB w/a for all
Chris Wilson
- [PATCH 04/18] drm/i915: Cancel outstanding work after disabling heartbeats on an engine
Chris Wilson
- [PATCH 05/18] drm/i915/gt: Always send a pulse down the engine after disabling heartbeat
Chris Wilson
- [PATCH 06/18] drm/i915/gem: Always test execution status on closing the context
Chris Wilson
- [PATCH 07/18] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Chris Wilson
- [PATCH 08/18] drm/i915: Drop runtime-pm assert from vgpu io accessors
Chris Wilson
- [PATCH 09/18] drm/i915/gt: Signal cancelled requests
Chris Wilson
- [PATCH 10/18] drm/i915/selftests: Finish pending mock requests on cancellation.
Chris Wilson
- [PATCH 11/18] drm/i915/gt: Retire cancelled requests on unload
Chris Wilson
- [PATCH 12/18] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 13/18] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 14/18] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 15/18] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 16/18] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 17/18] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 18/18] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 1/8] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Chris Wilson
- [PATCH 2/8] drm/i915/gt: Wait for CSB entries on Tigerlake
Chris Wilson
- [PATCH 3/8] drm/i915/gt: Apply the CSB w/a for all
Chris Wilson
- [PATCH 4/8] drm/i915: Cancel outstanding work after disabling heartbeats on an engine
Chris Wilson
- [PATCH 5/8] drm/i915/gt: Always send a pulse down the engine after disabling heartbeat
Chris Wilson
- [PATCH 6/8] drm/i915/gem: Always test execution status on closing the context
Chris Wilson
- [PATCH 7/8] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Chris Wilson
- [PATCH 8/8] drm/i915/gt: Consolidate the CS timestamp clocks
Chris Wilson
- [PATCH 01/17] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Chris Wilson
- [PATCH 02/17] drm/i915/gt: Wait for CSB entries on Tigerlake
Chris Wilson
- [PATCH 03/17] drm/i915/gt: Apply the CSB w/a for all
Chris Wilson
- [PATCH 04/17] drm/i915: Cancel outstanding work after disabling heartbeats on an engine
Chris Wilson
- [PATCH 05/17] drm/i915/gt: Always send a pulse down the engine after disabling heartbeat
Chris Wilson
- [PATCH 06/17] drm/i915/gem: Always test execution status on closing the context
Chris Wilson
- [PATCH 07/17] drm/i915: Drop runtime-pm assert from vgpu io accessors
Chris Wilson
- [PATCH 08/17] drm/i915/gt: Signal cancelled requests
Chris Wilson
- [PATCH 09/17] drm/i915/selftests: Finish pending mock requests on cancellation.
Chris Wilson
- [PATCH 10/17] drm/i915/gt: Retire cancelled requests on unload
Chris Wilson
- [PATCH 11/17] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 12/17] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 13/17] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 14/17] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 15/17] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 16/17] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 17/17] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 2/4] drm/i915/perf: Whitelist OA report trigger registers
Chris Wilson
- [PATCH 01/19] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Chris Wilson
- [PATCH 02/19] drm/i915/gt: Wait for CSB entries on Tigerlake
Chris Wilson
- [PATCH 03/19] drm/i915/gt: Apply the CSB w/a for all
Chris Wilson
- [PATCH 04/19] drm/i915: Cancel outstanding work after disabling heartbeats on an engine
Chris Wilson
- [PATCH 05/19] drm/i915/gt: Always send a pulse down the engine after disabling heartbeat
Chris Wilson
- [PATCH 06/19] drm/i915/gem: Always test execution status on closing the context
Chris Wilson
- [PATCH 07/19] drm/i915: Drop runtime-pm assert from vgpu io accessors
Chris Wilson
- [PATCH 08/19] drm/i915/gt: Signal cancelled requests
Chris Wilson
- [PATCH 09/19] drm/i915/selftests: Finish pending mock requests on cancellation.
Chris Wilson
- [PATCH 10/19] drm/i915/gt: Retire cancelled requests on unload
Chris Wilson
- [PATCH 11/19] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 12/19] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 13/19] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 14/19] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 15/19] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 16/19] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 17/19] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 18/19] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Chris Wilson
- [PATCH 19/19] drm/i915/gt: Consolidate the CS timestamp clocks
Chris Wilson
- [PATCH 01/20] drm/i915/selftests: Push the fake iommu device from the stack to data
Chris Wilson
- [PATCH 02/20] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Chris Wilson
- [PATCH 03/20] drm/i915/gt: Wait for CSB entries on Tigerlake
Chris Wilson
- [PATCH 04/20] drm/i915/gt: Apply the CSB w/a for all
Chris Wilson
- [PATCH 05/20] drm/i915: Cancel outstanding work after disabling heartbeats on an engine
Chris Wilson
- [PATCH 06/20] drm/i915/gt: Always send a pulse down the engine after disabling heartbeat
Chris Wilson
- [PATCH 07/20] drm/i915/gem: Always test execution status on closing the context
Chris Wilson
- [PATCH 08/20] drm/i915: Drop runtime-pm assert from vgpu io accessors
Chris Wilson
- [PATCH 09/20] drm/i915/gt: Signal cancelled requests
Chris Wilson
- [PATCH 10/20] drm/i915/selftests: Finish pending mock requests on cancellation.
Chris Wilson
- [PATCH 11/20] drm/i915/gt: Retire cancelled requests on unload
Chris Wilson
- [PATCH 12/20] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 13/20] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 14/20] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 15/20] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 16/20] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 17/20] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 18/20] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 19/20] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Chris Wilson
- [PATCH 20/20] drm/i915/gt: Consolidate the CS timestamp clocks
Chris Wilson
- [PATCH 01/27] drm/i915/selftests: Push the fake iommu device from the stack to data
Chris Wilson
- [PATCH 02/27] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Chris Wilson
- [PATCH 03/27] drm/i915/gt: Wait for CSB entries on Tigerlake
Chris Wilson
- [PATCH 04/27] drm/i915/gt: Apply the CSB w/a for all
Chris Wilson
- [PATCH 05/27] drm/i915: Cancel outstanding work after disabling heartbeats on an engine
Chris Wilson
- [PATCH 06/27] drm/i915/gt: Always send a pulse down the engine after disabling heartbeat
Chris Wilson
- [PATCH 07/27] drm/i915/gem: Always test execution status on closing the context
Chris Wilson
- [PATCH 08/27] drm/i915: Drop runtime-pm assert from vgpu io accessors
Chris Wilson
- [PATCH 09/27] drm/i915/gt: Signal cancelled requests
Chris Wilson
- [PATCH 10/27] drm/i915/selftests: Finish pending mock requests on cancellation.
Chris Wilson
- [PATCH 11/27] drm/i915/gt: Retire cancelled requests on unload
Chris Wilson
- [PATCH 12/27] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 13/27] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 14/27] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 15/27] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 16/27] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 17/27] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 18/27] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 19/27] drm/i915/gt: Decouple completed requests on unwind
Chris Wilson
- [PATCH 20/27] drm/i915/gt: Check for a completed last request once
Chris Wilson
- [PATCH 21/27] drm/i915/gt: Replace direct submit with direct call to tasklet
Chris Wilson
- [PATCH 22/27] drm/i915/gt: Use virtual_engine during execlists_dequeue
Chris Wilson
- [PATCH 23/27] drm/i915/gt: Decouple inflight virtual engines
Chris Wilson
- [PATCH 24/27] drm/i915/gt: Defer schedule_out until after the next dequeue
Chris Wilson
- [PATCH 25/27] drm/i915/gt: Resubmit the virtual engine on schedule-out
Chris Wilson
- [PATCH 26/27] drm/i915/gt: Simplify virtual engine handling for execlists_hold()
Chris Wilson
- [PATCH 27/27] irq-ve
Chris Wilson
- [PATCH 01/27] drm/i915/selftests: Push the fake iommu device from the stack to data
Chris Wilson
- [PATCH 02/27] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Chris Wilson
- [PATCH 03/27] drm/i915/gt: Wait for CSB entries on Tigerlake
Chris Wilson
- [PATCH 04/27] drm/i915/gt: Apply the CSB w/a for all
Chris Wilson
- [PATCH 05/27] drm/i915: Cancel outstanding work after disabling heartbeats on an engine
Chris Wilson
- [PATCH 06/27] drm/i915/gt: Always send a pulse down the engine after disabling heartbeat
Chris Wilson
- [PATCH 07/27] drm/i915/gem: Always test execution status on closing the context
Chris Wilson
- [PATCH 08/27] drm/i915: Drop runtime-pm assert from vgpu io accessors
Chris Wilson
- [PATCH 09/27] drm/i915/gt: Signal cancelled requests
Chris Wilson
- [PATCH 10/27] drm/i915/selftests: Finish pending mock requests on cancellation.
Chris Wilson
- [PATCH 11/27] drm/i915/gt: Retire cancelled requests on unload
Chris Wilson
- [PATCH 12/27] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 13/27] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 14/27] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 15/27] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 16/27] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 17/27] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 18/27] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 19/27] drm/i915/gt: Decouple completed requests on unwind
Chris Wilson
- [PATCH 20/27] drm/i915/gt: Check for a completed last request once
Chris Wilson
- [PATCH 21/27] drm/i915/gt: Replace direct submit with direct call to tasklet
Chris Wilson
- [PATCH 22/27] drm/i915/gt: ce->inflight updates are now serialised
Chris Wilson
- [PATCH 23/27] drm/i915/gt: Use virtual_engine during execlists_dequeue
Chris Wilson
- [PATCH 24/27] drm/i915/gt: Decouple inflight virtual engines
Chris Wilson
- [PATCH 25/27] drm/i915/gt: Defer schedule_out until after the next dequeue
Chris Wilson
- [PATCH 26/27] drm/i915/gt: Resubmit the virtual engine on schedule-out
Chris Wilson
- [PATCH 27/27] drm/i915/gt: Simplify virtual engine handling for execlists_hold()
Chris Wilson
- [PATCH 01/30] drm/i915/selftests: Push the fake iommu device from the stack to data
Chris Wilson
- [PATCH 02/30] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Chris Wilson
- [PATCH 03/30] drm/i915/gt: Wait for CSB entries on Tigerlake
Chris Wilson
- [PATCH 04/30] drm/i915/gt: Apply the CSB w/a for all
Chris Wilson
- [PATCH 05/30] drm/i915: Cancel outstanding work after disabling heartbeats on an engine
Chris Wilson
- [PATCH 06/30] drm/i915/gt: Always send a pulse down the engine after disabling heartbeat
Chris Wilson
- [PATCH 07/30] drm/i915/gem: Always test execution status on closing the context
Chris Wilson
- [PATCH 08/30] drm/i915: Drop runtime-pm assert from vgpu io accessors
Chris Wilson
- [PATCH 09/30] drm/i915/gt: Signal cancelled requests
Chris Wilson
- [PATCH 10/30] drm/i915/selftests: Finish pending mock requests on cancellation.
Chris Wilson
- [PATCH 11/30] drm/i915/gt: Retire cancelled requests on unload
Chris Wilson
- [PATCH 12/30] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 13/30] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 14/30] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 15/30] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 16/30] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 17/30] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 18/30] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 19/30] drm/i915/gt: Decouple completed requests on unwind
Chris Wilson
- [PATCH 20/30] drm/i915/gt: Check for a completed last request once
Chris Wilson
- [PATCH 21/30] drm/i915/gt: Replace direct submit with direct call to tasklet
Chris Wilson
- [PATCH 22/30] drm/i915/gt: ce->inflight updates are now serialised
Chris Wilson
- [PATCH 23/30] drm/i915/gt: Use virtual_engine during execlists_dequeue
Chris Wilson
- [PATCH 24/30] drm/i915/gt: Decouple inflight virtual engines
Chris Wilson
- [PATCH 25/30] drm/i915/gt: Defer schedule_out until after the next dequeue
Chris Wilson
- [PATCH 26/30] drm/i915/gt: Resubmit the virtual engine on schedule-out
Chris Wilson
- [PATCH 27/30] drm/i915/gt: Simplify virtual engine handling for execlists_hold()
Chris Wilson
- [PATCH 28/30] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Chris Wilson
- [PATCH 29/30] drm/i915/gt: Consolidate the CS timestamp clocks
Chris Wilson
- [PATCH 30/30] drm/i915: Encode fence specific waitqueue behaviour into the wait.flags
Chris Wilson
- [PATCH 01/35] drm/i915/gem: Replace reloc chain with terminator on error unwind
Chris Wilson
- [PATCH 02/35] drm/i915/gem: Fallback to using a plain kmap if reloc address space is limited
Chris Wilson
- [PATCH 03/35] drm/i915: Initialise outparam for error return from wait_for_register
Chris Wilson
- [PATCH 04/35] drm/i915/selftests: Push the fake iommu device from the stack to data
Chris Wilson
- [PATCH 05/35] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Chris Wilson
- [PATCH 06/35] drm/i915/gt: Wait for CSB entries on Tigerlake
Chris Wilson
- [PATCH 07/35] drm/i915/gt: Apply the CSB w/a for all
Chris Wilson
- [PATCH 08/35] drm/i915: Cancel outstanding work after disabling heartbeats on an engine
Chris Wilson
- [PATCH 09/35] drm/i915/gt: Always send a pulse down the engine after disabling heartbeat
Chris Wilson
- [PATCH 10/35] drm/i915/gem: Always test execution status on closing the context
Chris Wilson
- [PATCH 11/35] drm/i915: Drop runtime-pm assert from vgpu io accessors
Chris Wilson
- [PATCH 12/35] drm/i915/gt: Signal cancelled requests
Chris Wilson
- [PATCH 13/35] drm/i915/selftests: Finish pending mock requests on cancellation.
Chris Wilson
- [PATCH 14/35] drm/i915/gt: Retire cancelled requests on unload
Chris Wilson
- [PATCH 15/35] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 16/35] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 17/35] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 18/35] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 19/35] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 20/35] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 21/35] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 22/35] irq-cancel
Chris Wilson
- [PATCH 23/35] drm/i915/gt: Decouple completed requests on unwind
Chris Wilson
- [PATCH 24/35] drm/i915/gt: Check for a completed last request once
Chris Wilson
- [PATCH 25/35] drm/i915/gt: Replace direct submit with direct call to tasklet
Chris Wilson
- [PATCH 26/35] drm/i915/gt: ce->inflight updates are now serialised
Chris Wilson
- [PATCH 27/35] drm/i915/gt: Use virtual_engine during execlists_dequeue
Chris Wilson
- [PATCH 28/35] drm/i915/gt: Decouple inflight virtual engines
Chris Wilson
- [PATCH 29/35] drm/i915/gt: Defer schedule_out until after the next dequeue
Chris Wilson
- [PATCH 30/35] drm/i915/gt: Resubmit the virtual engine on schedule-out
Chris Wilson
- [PATCH 31/35] shrink-active
Chris Wilson
- [PATCH 32/35] drm/i915/gt: Simplify virtual engine handling for execlists_hold()
Chris Wilson
- [PATCH 33/35] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Chris Wilson
- [PATCH 34/35] drm/i915/gt: Consolidate the CS timestamp clocks
Chris Wilson
- [PATCH 35/35] drm/i915: Encode fence specific waitqueue behaviour into the wait.flags
Chris Wilson
- [PATCH 01/36] drm/i915/gem: Replace reloc chain with terminator on error unwind
Chris Wilson
- [PATCH 02/36] drm/i915/gem: Fallback to using a plain kmap if reloc address space is limited
Chris Wilson
- [PATCH 03/36] drm/i915: Initialise outparam for error return from wait_for_register
Chris Wilson
- [PATCH 04/36] drm/i915/selftests: Push the fake iommu device from the stack to data
Chris Wilson
- [PATCH 05/36] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Chris Wilson
- [PATCH 06/36] drm/i915/gt: Wait for CSB entries on Tigerlake
Chris Wilson
- [PATCH 07/36] drm/i915/gt: Apply the CSB w/a for all
Chris Wilson
- [PATCH 08/36] drm/i915: Cancel outstanding work after disabling heartbeats on an engine
Chris Wilson
- [PATCH 09/36] drm/i915/gt: Always send a pulse down the engine after disabling heartbeat
Chris Wilson
- [PATCH 10/36] drm/i915/gem: Always test execution status on closing the context
Chris Wilson
- [PATCH 11/36] drm/i915: Drop runtime-pm assert from vgpu io accessors
Chris Wilson
- [PATCH 12/36] drm/i915/gt: Signal cancelled requests
Chris Wilson
- [PATCH 13/36] drm/i915/selftests: Finish pending mock requests on cancellation.
Chris Wilson
- [PATCH 14/36] drm/i915/gt: Retire cancelled requests on unload
Chris Wilson
- [PATCH 15/36] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 16/36] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 17/36] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 18/36] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 19/36] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 20/36] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 21/36] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 22/36] irq-cancel
Chris Wilson
- [PATCH 23/36] drm/i915/gt: Decouple completed requests on unwind
Chris Wilson
- [PATCH 24/36] drm/i915/gt: Check for a completed last request once
Chris Wilson
- [PATCH 25/36] drm/i915/gt: Replace direct submit with direct call to tasklet
Chris Wilson
- [PATCH 26/36] drm/i915/gt: ce->inflight updates are now serialised
Chris Wilson
- [PATCH 27/36] drm/i915/gt: Use virtual_engine during execlists_dequeue
Chris Wilson
- [PATCH 28/36] drm/i915/gt: Decouple inflight virtual engines
Chris Wilson
- [PATCH 29/36] drm/i915/gt: Defer schedule_out until after the next dequeue
Chris Wilson
- [PATCH 30/36] cancel-virtual
Chris Wilson
- [PATCH 31/36] shrink-active
Chris Wilson
- [PATCH 32/36] drm/i915/gt: Resubmit the virtual engine on schedule-out
Chris Wilson
- [PATCH 33/36] drm/i915/gt: Simplify virtual engine handling for execlists_hold()
Chris Wilson
- [PATCH 34/36] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Chris Wilson
- [PATCH 35/36] drm/i915/gt: Consolidate the CS timestamp clocks
Chris Wilson
- [PATCH 36/36] drm/i915: Encode fence specific waitqueue behaviour into the wait.flags
Chris Wilson
- [PATCH 01/38] drm/i915/gem: Replace reloc chain with terminator on error unwind
Chris Wilson
- [PATCH 02/38] drm/i915/gem: Fallback to using a plain kmap if reloc address space is limited
Chris Wilson
- [PATCH 03/38] drm/i915/gem: Prevent using pgprot_writecombine() if PAT is not supported
Chris Wilson
- [PATCH 04/38] drm/i915: Initialise outparam for error return from wait_for_register
Chris Wilson
- [PATCH 05/38] drm/i915/selftests: Push the fake iommu device from the stack to data
Chris Wilson
- [PATCH 06/38] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Chris Wilson
- [PATCH 07/38] drm/i915/gt: Wait for CSB entries on Tigerlake
Chris Wilson
- [PATCH 08/38] drm/i915/gt: Apply the CSB w/a for all
Chris Wilson
- [PATCH 09/38] drm/i915/gem: Hold request reference for canceling an active context
Chris Wilson
- [PATCH 10/38] drm/i915: Cancel outstanding work after disabling heartbeats on an engine
Chris Wilson
- [PATCH 11/38] drm/i915/gt: Always send a pulse down the engine after disabling heartbeat
Chris Wilson
- [PATCH 12/38] drm/i915/gem: Always test execution status on closing the context
Chris Wilson
- [PATCH 13/38] drm/i915: Drop runtime-pm assert from vgpu io accessors
Chris Wilson
- [PATCH 14/38] drm/i915/gt: Signal cancelled requests
Chris Wilson
- [PATCH 15/38] drm/i915/selftests: Finish pending mock requests on cancellation.
Chris Wilson
- [PATCH 16/38] drm/i915/gt: Retire cancelled requests on unload
Chris Wilson
- [PATCH 17/38] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 18/38] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 19/38] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 20/38] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 21/38] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 22/38] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 23/38] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 24/38] drm/i915/gt: Move the breadcrumb to the signaler if completed upon cancel
Chris Wilson
- [PATCH 25/38] drm/i915/gt: Decouple completed requests on unwind
Chris Wilson
- [PATCH 26/38] drm/i915/gt: Check for a completed last request once
Chris Wilson
- [PATCH 27/38] drm/i915/gt: Replace direct submit with direct call to tasklet
Chris Wilson
- [PATCH 28/38] drm/i915/gt: ce->inflight updates are now serialised
Chris Wilson
- [PATCH 29/38] drm/i915/gt: Use virtual_engine during execlists_dequeue
Chris Wilson
- [PATCH 30/38] drm/i915/gt: Decouple inflight virtual engines
Chris Wilson
- [PATCH 31/38] drm/i915/gt: Defer schedule_out until after the next dequeue
Chris Wilson
- [PATCH 32/38] drm/i915/gt: Remove virtual breadcrumb before transfer
Chris Wilson
- [PATCH 33/38] drm/i915/gt: Shrink the critical section for irq signaling
Chris Wilson
- [PATCH 34/38] drm/i915/gt: Resubmit the virtual engine on schedule-out
Chris Wilson
- [PATCH 35/38] drm/i915/gt: Simplify virtual engine handling for execlists_hold()
Chris Wilson
- [PATCH 36/38] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Chris Wilson
- [PATCH 37/38] drm/i915/gt: Consolidate the CS timestamp clocks
Chris Wilson
- [PATCH 38/38] drm/i915: Encode fence specific waitqueue behaviour into the wait.flags
Chris Wilson
- [PATCH 01/38] drm/i915/gem: Replace reloc chain with terminator on error unwind
Chris Wilson
- [PATCH 02/38] drm/i915/gem: Fallback to using a plain kmap if reloc address space is limited
Chris Wilson
- [PATCH 03/38] drm/i915/gem: Prevent using pgprot_writecombine() if PAT is not supported
Chris Wilson
- [PATCH 04/38] drm/i915: Initialise outparam for error return from wait_for_register
Chris Wilson
- [PATCH 05/38] drm/i915/selftests: Push the fake iommu device from the stack to data
Chris Wilson
- [PATCH 06/38] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Chris Wilson
- [PATCH 07/38] drm/i915/gt: Wait for CSB entries on Tigerlake
Chris Wilson
- [PATCH 08/38] drm/i915/gt: Apply the CSB w/a for all
Chris Wilson
- [PATCH 09/38] drm/i915/gem: Hold request reference for canceling an active context
Chris Wilson
- [PATCH 10/38] drm/i915: Cancel outstanding work after disabling heartbeats on an engine
Chris Wilson
- [PATCH 11/38] drm/i915/gt: Always send a pulse down the engine after disabling heartbeat
Chris Wilson
- [PATCH 12/38] drm/i915/gem: Always test execution status on closing the context
Chris Wilson
- [PATCH 13/38] drm/i915: Drop runtime-pm assert from vgpu io accessors
Chris Wilson
- [PATCH 14/38] drm/i915/gt: Signal cancelled requests
Chris Wilson
- [PATCH 15/38] drm/i915/selftests: Finish pending mock requests on cancellation.
Chris Wilson
- [PATCH 16/38] drm/i915/gt: Retire cancelled requests on unload
Chris Wilson
- [PATCH 17/38] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 18/38] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 19/38] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 20/38] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 21/38] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 22/38] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 23/38] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 24/38] drm/i915/gt: Move the breadcrumb to the signaler if completed upon cancel
Chris Wilson
- [PATCH 25/38] drm/i915/gt: Decouple completed requests on unwind
Chris Wilson
- [PATCH 26/38] drm/i915/gt: Check for a completed last request once
Chris Wilson
- [PATCH 27/38] drm/i915/gt: Replace direct submit with direct call to tasklet
Chris Wilson
- [PATCH 28/38] drm/i915/gt: ce->inflight updates are now serialised
Chris Wilson
- [PATCH 29/38] drm/i915/gt: Use virtual_engine during execlists_dequeue
Chris Wilson
- [PATCH 30/38] drm/i915/gt: Decouple inflight virtual engines
Chris Wilson
- [PATCH 31/38] drm/i915/gt: Defer schedule_out until after the next dequeue
Chris Wilson
- [PATCH 32/38] drm/i915/gt: Remove virtual breadcrumb before transfer
Chris Wilson
- [PATCH 33/38] drm/i915/gt: Shrink the critical section for irq signaling
Chris Wilson
- [PATCH 34/38] drm/i915/gt: Resubmit the virtual engine on schedule-out
Chris Wilson
- [PATCH 35/38] drm/i915/gt: Simplify virtual engine handling for execlists_hold()
Chris Wilson
- [PATCH 36/38] drm/i915: Encode fence specific waitqueue behaviour into the wait.flags
Chris Wilson
- [PATCH 37/38] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Chris Wilson
- [PATCH 38/38] drm/i915/gt: Consolidate the CS timestamp clocks
Chris Wilson
- [PATCH i-g-t] i915/gem_softpin: Active rebinds
Chris Wilson
- [PATCH 1/4] mm: Export flush_vm_area() to sync the PTEs upon construction
Chris Wilson
- [PATCH 2/4] drm/i915/gem: Sync the vmap PTEs upon construction
Chris Wilson
- [PATCH 3/4] drm/i915/gem: Use set_pte_at() for assigning the vmapped PTE
Chris Wilson
- [PATCH 4/4] drm/i915/gem: Replace reloc chain with terminator on error unwind
Chris Wilson
- [PATCH 01/41] drm/i915/gem: Use set_pte_at() for assigning the vmapped PTE
Chris Wilson
- [PATCH 02/41] drm/i915/gem: Replace reloc chain with terminator on error unwind
Chris Wilson
- [PATCH 03/41] drm/i915/gem: Avoid implicit vmap for highmem on x86-32
Chris Wilson
- [PATCH 04/41] drm/i915/gem: Prevent using pgprot_writecombine() if PAT is not supported
Chris Wilson
- [PATCH 05/41] drm/i915/gt: Clear the buffer pool age before use
Chris Wilson
- [PATCH 06/41] drm/i915: Break up error capture compression loops with cond_resched()
Chris Wilson
- [PATCH 07/41] drm/i915: Initialise outparam for error return from wait_for_register
Chris Wilson
- [PATCH 08/41] drm/i915/selftests: Push the fake iommu device from the stack to data
Chris Wilson
- [PATCH 09/41] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Chris Wilson
- [PATCH 10/41] drm/i915/gt: Wait for CSB entries on Tigerlake
Chris Wilson
- [PATCH 11/41] drm/i915/gt: Apply the CSB w/a for all
Chris Wilson
- [PATCH 12/41] drm/i915/gem: Hold request reference for canceling an active context
Chris Wilson
- [PATCH 13/41] drm/i915: Cancel outstanding work after disabling heartbeats on an engine
Chris Wilson
- [PATCH 14/41] drm/i915/gt: Always send a pulse down the engine after disabling heartbeat
Chris Wilson
- [PATCH 15/41] drm/i915/gem: Always test execution status on closing the context
Chris Wilson
- [PATCH 16/41] drm/i915: Drop runtime-pm assert from vgpu io accessors
Chris Wilson
- [PATCH 17/41] drm/i915/gt: Signal cancelled requests
Chris Wilson
- [PATCH 18/41] drm/i915/selftests: Finish pending mock requests on cancellation.
Chris Wilson
- [PATCH 19/41] drm/i915/gt: Retire cancelled requests on unload
Chris Wilson
- [PATCH 20/41] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 21/41] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 22/41] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 23/41] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 24/41] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 25/41] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 26/41] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 27/41] drm/i915/gt: Move the breadcrumb to the signaler if completed upon cancel
Chris Wilson
- [PATCH 28/41] drm/i915/gt: Decouple completed requests on unwind
Chris Wilson
- [PATCH 29/41] drm/i915/gt: Check for a completed last request once
Chris Wilson
- [PATCH 30/41] drm/i915/gt: Replace direct submit with direct call to tasklet
Chris Wilson
- [PATCH 31/41] drm/i915/gt: ce->inflight updates are now serialised
Chris Wilson
- [PATCH 32/41] drm/i915/gt: Use virtual_engine during execlists_dequeue
Chris Wilson
- [PATCH 33/41] drm/i915/gt: Decouple inflight virtual engines
Chris Wilson
- [PATCH 34/41] drm/i915/gt: Defer schedule_out until after the next dequeue
Chris Wilson
- [PATCH 35/41] drm/i915/gt: Remove virtual breadcrumb before transfer
Chris Wilson
- [PATCH 36/41] drm/i915/gt: Shrink the critical section for irq signaling
Chris Wilson
- [PATCH 37/41] drm/i915/gt: Resubmit the virtual engine on schedule-out
Chris Wilson
- [PATCH 38/41] drm/i915/gt: Simplify virtual engine handling for execlists_hold()
Chris Wilson
- [PATCH 39/41] drm/i915: Encode fence specific waitqueue behaviour into the wait.flags
Chris Wilson
- [PATCH 40/41] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Chris Wilson
- [PATCH 41/41] drm/i915/gt: Consolidate the CS timestamp clocks
Chris Wilson
- [PATCH 01/42] drm/i915/gem: Use set_pte_at() for assigning the vmapped PTE
Chris Wilson
- [PATCH 02/42] drm/i915/gem: Replace reloc chain with terminator on error unwind
Chris Wilson
- [PATCH 03/42] drm/i915/gem: Avoid implicit vmap for highmem on x86-32
Chris Wilson
- [PATCH 04/42] drm/i915/gem: Prevent using pgprot_writecombine() if PAT is not supported
Chris Wilson
- [PATCH 05/42] drm/i915/gt: Clear the buffer pool age before use
Chris Wilson
- [PATCH 06/42] drm/i915: Break up error capture compression loops with cond_resched()
Chris Wilson
- [PATCH 07/42] drm/i915: Reduce GPU error capture mutex hold time
Chris Wilson
- [PATCH 08/42] drm/i915: Initialise outparam for error return from wait_for_register
Chris Wilson
- [PATCH 09/42] drm/i915/selftests: Push the fake iommu device from the stack to data
Chris Wilson
- [PATCH 10/42] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Chris Wilson
- [PATCH 11/42] drm/i915/gt: Wait for CSB entries on Tigerlake
Chris Wilson
- [PATCH 12/42] drm/i915/gt: Apply the CSB w/a for all
Chris Wilson
- [PATCH 13/42] drm/i915/gem: Hold request reference for canceling an active context
Chris Wilson
- [PATCH 14/42] drm/i915: Cancel outstanding work after disabling heartbeats on an engine
Chris Wilson
- [PATCH 15/42] drm/i915/gt: Always send a pulse down the engine after disabling heartbeat
Chris Wilson
- [PATCH 16/42] drm/i915/gem: Always test execution status on closing the context
Chris Wilson
- [PATCH 17/42] drm/i915: Drop runtime-pm assert from vgpu io accessors
Chris Wilson
- [PATCH 18/42] drm/i915/gt: Signal cancelled requests
Chris Wilson
- [PATCH 19/42] drm/i915/selftests: Finish pending mock requests on cancellation.
Chris Wilson
- [PATCH 20/42] drm/i915/gt: Retire cancelled requests on unload
Chris Wilson
- [PATCH 21/42] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 22/42] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 23/42] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 24/42] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 25/42] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 26/42] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 27/42] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 28/42] drm/i915/gt: Move the breadcrumb to the signaler if completed upon cancel
Chris Wilson
- [PATCH 29/42] drm/i915/gt: Decouple completed requests on unwind
Chris Wilson
- [PATCH 30/42] drm/i915/gt: Check for a completed last request once
Chris Wilson
- [PATCH 31/42] drm/i915/gt: Replace direct submit with direct call to tasklet
Chris Wilson
- [PATCH 32/42] drm/i915/gt: ce->inflight updates are now serialised
Chris Wilson
- [PATCH 33/42] drm/i915/gt: Use virtual_engine during execlists_dequeue
Chris Wilson
- [PATCH 34/42] drm/i915/gt: Decouple inflight virtual engines
Chris Wilson
- [PATCH 35/42] drm/i915/gt: Defer schedule_out until after the next dequeue
Chris Wilson
- [PATCH 36/42] drm/i915/gt: Remove virtual breadcrumb before transfer
Chris Wilson
- [PATCH 37/42] drm/i915/gt: Shrink the critical section for irq signaling
Chris Wilson
- [PATCH 38/42] drm/i915/gt: Resubmit the virtual engine on schedule-out
Chris Wilson
- [PATCH 39/42] drm/i915/gt: Simplify virtual engine handling for execlists_hold()
Chris Wilson
- [PATCH 40/42] drm/i915: Encode fence specific waitqueue behaviour into the wait.flags
Chris Wilson
- [PATCH 41/42] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Chris Wilson
- [PATCH 42/42] drm/i915/gt: Consolidate the CS timestamp clocks
Chris Wilson
- [PATCH 01/40] drm/i915/gem: Use set_pte_at() for assigning the vmapped PTE
Chris Wilson
- [PATCH 02/40] drm/i915/gem: Replace reloc chain with terminator on error unwind
Chris Wilson
- [PATCH 03/40] drm/i915/gem: Avoid implicit vmap for highmem on x86-32
Chris Wilson
- [PATCH 04/40] drm/i915/gem: Prevent using pgprot_writecombine() if PAT is not supported
Chris Wilson
- [PATCH 05/40] drm/i915/gt: Clear the buffer pool age before use
Chris Wilson
- [PATCH 06/40] drm/i915: Break up error capture compression loops with cond_resched()
Chris Wilson
- [PATCH 07/40] drm/i915: Reduce GPU error capture mutex hold time
Chris Wilson
- [PATCH 08/40] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Chris Wilson
- [PATCH 09/40] drm/i915/gt: Wait for CSB entries on Tigerlake
Chris Wilson
- [PATCH 10/40] drm/i915/gt: Apply the CSB w/a for all
Chris Wilson
- [PATCH 11/40] drm/i915/gt: Show engine properties in the pretty printer
Chris Wilson
- [PATCH 12/40] drm/i915/gem: Hold request reference for canceling an active context
Chris Wilson
- [PATCH 13/40] drm/i915: Cancel outstanding work after disabling heartbeats on an engine
Chris Wilson
- [PATCH 14/40] drm/i915/gt: Always send a pulse down the engine after disabling heartbeat
Chris Wilson
- [PATCH 15/40] drm/i915/gem: Always test execution status on closing the context
Chris Wilson
- [PATCH 16/40] drm/i915/gt: Signal cancelled requests
Chris Wilson
- [PATCH 17/40] drm/i915/selftests: Finish pending mock requests on cancellation.
Chris Wilson
- [PATCH 18/40] drm/i915/gt: Retire cancelled requests on unload
Chris Wilson
- [PATCH 19/40] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 20/40] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 21/40] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 22/40] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 23/40] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 24/40] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 25/40] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 26/40] drm/i915/gt: Move the breadcrumb to the signaler if completed upon cancel
Chris Wilson
- [PATCH 27/40] drm/i915/gt: Decouple completed requests on unwind
Chris Wilson
- [PATCH 28/40] drm/i915/gt: Check for a completed last request once
Chris Wilson
- [PATCH 29/40] drm/i915/gt: Replace direct submit with direct call to tasklet
Chris Wilson
- [PATCH 30/40] drm/i915/gt: ce->inflight updates are now serialised
Chris Wilson
- [PATCH 31/40] drm/i915/gt: Use virtual_engine during execlists_dequeue
Chris Wilson
- [PATCH 32/40] drm/i915/gt: Decouple inflight virtual engines
Chris Wilson
- [PATCH 33/40] drm/i915/gt: Defer schedule_out until after the next dequeue
Chris Wilson
- [PATCH 34/40] drm/i915/gt: Remove virtual breadcrumb before transfer
Chris Wilson
- [PATCH 35/40] drm/i915/gt: Shrink the critical section for irq signaling
Chris Wilson
- [PATCH 36/40] drm/i915/gt: Resubmit the virtual engine on schedule-out
Chris Wilson
- [PATCH 37/40] drm/i915/gt: Simplify virtual engine handling for execlists_hold()
Chris Wilson
- [PATCH 38/40] drm/i915: Encode fence specific waitqueue behaviour into the wait.flags
Chris Wilson
- [PATCH 39/40] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Chris Wilson
- [PATCH 40/40] drm/i915/gt: Consolidate the CS timestamp clocks
Chris Wilson
- [PATCH 01/28] drm/i915/gem: Use set_pte_at() for assigning the vmapped PTE
Chris Wilson
- [PATCH 02/28] drm/i915/gem: Avoid implicit vmap for highmem on x86-32
Chris Wilson
- [PATCH 03/28] drm/i915/gem: Prevent using pgprot_writecombine() if PAT is not supported
Chris Wilson
- [PATCH 04/28] drm/i915/gt: Clear the buffer pool age before use
Chris Wilson
- [PATCH 05/28] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Chris Wilson
- [PATCH 06/28] drm/i915/gt: Wait for CSB entries on Tigerlake
Chris Wilson
- [PATCH 07/28] drm/i915/gt: Apply the CSB w/a for all
Chris Wilson
- [PATCH 08/28] drm/i915/gt: Show engine properties in the pretty printer
Chris Wilson
- [PATCH 09/28] drm/i915/gem: Hold request reference for canceling an active context
Chris Wilson
- [PATCH 10/28] drm/i915: Cancel outstanding work after disabling heartbeats on an engine
Chris Wilson
- [PATCH 11/28] drm/i915/gt: Always send a pulse down the engine after disabling heartbeat
Chris Wilson
- [PATCH 12/28] drm/i915/gem: Always test execution status on closing the context
Chris Wilson
- [PATCH 13/28] drm/i915/gt: Signal cancelled requests
Chris Wilson
- [PATCH 14/28] drm/i915/selftests: Finish pending mock requests on cancellation.
Chris Wilson
- [PATCH 15/28] drm/i915/gt: Retire cancelled requests on unload
Chris Wilson
- [PATCH 16/28] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 17/28] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 18/28] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 19/28] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 20/28] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 21/28] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 22/28] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 23/28] drm/i915/gt: Move the breadcrumb to the signaler if completed upon cancel
Chris Wilson
- [PATCH 24/28] drm/i915/gt: Decouple completed requests on unwind
Chris Wilson
- [PATCH 25/28] drm/i915/gt: Check for a completed last request once
Chris Wilson
- [PATCH 26/28] drm/i915/gt: Replace direct submit with direct call to tasklet
Chris Wilson
- [PATCH 27/28] drm/i915/gt: ce->inflight updates are now serialised
Chris Wilson
- [PATCH 28/28] drm/i915/gt: Use virtual_engine during execlists_dequeue
Chris Wilson
- [PATCH 01/39] drm/i915/gem: Use set_pte_at() for assigning the vmapped PTE
Chris Wilson
- [PATCH 02/39] drm/i915/gem: Avoid implicit vmap for highmem on x86-32
Chris Wilson
- [PATCH 03/39] drm/i915/gem: Prevent using pgprot_writecombine() if PAT is not supported
Chris Wilson
- [PATCH 04/39] drm/i915/gt: Clear the buffer pool age before use
Chris Wilson
- [PATCH 05/39] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Chris Wilson
- [PATCH 06/39] drm/i915/gt: Wait for CSB entries on Tigerlake
Chris Wilson
- [PATCH 07/39] drm/i915/gt: Apply the CSB w/a for all
Chris Wilson
- [PATCH 08/39] drm/i915/gt: Show engine properties in the pretty printer
Chris Wilson
- [PATCH 09/39] drm/i915/gem: Hold request reference for canceling an active context
Chris Wilson
- [PATCH 10/39] drm/i915: Cancel outstanding work after disabling heartbeats on an engine
Chris Wilson
- [PATCH 11/39] drm/i915/gt: Always send a pulse down the engine after disabling heartbeat
Chris Wilson
- [PATCH 12/39] drm/i915/gem: Always test execution status on closing the context
Chris Wilson
- [PATCH 13/39] drm/i915/gt: Signal cancelled requests
Chris Wilson
- [PATCH 14/39] drm/i915/selftests: Finish pending mock requests on cancellation.
Chris Wilson
- [PATCH 15/39] drm/i915/gt: Retire cancelled requests on unload
Chris Wilson
- [PATCH 16/39] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 17/39] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 18/39] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 19/39] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 20/39] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 21/39] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 22/39] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 23/39] drm/i915/gt: Move the breadcrumb to the signaler if completed upon cancel
Chris Wilson
- [PATCH 24/39] drm/i915/gt: Decouple completed requests on unwind
Chris Wilson
- [PATCH 25/39] drm/i915/gt: Check for a completed last request once
Chris Wilson
- [PATCH 26/39] drm/i915/gt: Replace direct submit with direct call to tasklet
Chris Wilson
- [PATCH 27/39] drm/i915/gt: ce->inflight updates are now serialised
Chris Wilson
- [PATCH 28/39] drm/i915/gt: Use virtual_engine during execlists_dequeue
Chris Wilson
- [PATCH 29/39] drm/i915/gt: Decouple inflight virtual engines
Chris Wilson
- [PATCH 30/39] drm/i915/gt: Defer schedule_out until after the next dequeue
Chris Wilson
- [PATCH 31/39] drm/i915/gt: Remove virtual breadcrumb before transfer
Chris Wilson
- [PATCH 32/39] drm/i915/gt: Shrink the critical section for irq signaling
Chris Wilson
- [PATCH 33/39] drm/i915/gt: Resubmit the virtual engine on schedule-out
Chris Wilson
- [PATCH 34/39] drm/i915/gt: Simplify virtual engine handling for execlists_hold()
Chris Wilson
- [PATCH 35/39] drm/i915: Encode fence specific waitqueue behaviour into the wait.flags
Chris Wilson
- [PATCH 36/39] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Chris Wilson
- [PATCH 37/39] drm/i915/gt: Consolidate the CS timestamp clocks
Chris Wilson
- [PATCH 38/39] drm/i915: Break up error capture compression loops with cond_resched()
Chris Wilson
- [PATCH 39/39] drm/i915: Reduce GPU error capture mutex hold time
Chris Wilson
- [PATCH 01/39] drm/i915/gem: Use set_pte_at() for assigning the vmapped PTE
Chris Wilson
- [PATCH 02/39] drm/i915/gem: Avoid implicit vmap for highmem on x86-32
Chris Wilson
- [PATCH 03/39] drm/i915/gem: Prevent using pgprot_writecombine() if PAT is not supported
Chris Wilson
- [PATCH 04/39] drm/i915/gt: Clear the buffer pool age before use
Chris Wilson
- [PATCH 05/39] drm/i915/gt: Widen CSB pointer to u64 for the parsers
Chris Wilson
- [PATCH 06/39] drm/i915/gt: Wait for CSB entries on Tigerlake
Chris Wilson
- [PATCH 07/39] drm/i915/gt: Apply the CSB w/a for all
Chris Wilson
- [PATCH 08/39] drm/i915/gt: Show engine properties in the pretty printer
Chris Wilson
- [PATCH 09/39] drm/i915/gem: Hold request reference for canceling an active context
Chris Wilson
- [PATCH 10/39] drm/i915: Cancel outstanding work after disabling heartbeats on an engine
Chris Wilson
- [PATCH 11/39] drm/i915/gt: Always send a pulse down the engine after disabling heartbeat
Chris Wilson
- [PATCH 12/39] drm/i915/gem: Always test execution status on closing the context
Chris Wilson
- [PATCH 13/39] drm/i915/gt: Signal cancelled requests
Chris Wilson
- [PATCH 14/39] drm/i915/selftests: Finish pending mock requests on cancellation.
Chris Wilson
- [PATCH 15/39] drm/i915/gt: Retire cancelled requests on unload
Chris Wilson
- [PATCH 16/39] drm/i915/gt: Remove defunct intel_virtual_engine_get_sibling()
Chris Wilson
- [PATCH 17/39] drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission
Chris Wilson
- [PATCH 18/39] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Chris Wilson
- [PATCH 19/39] drm/i915/gt: Don't cancel the interrupt shadow too early
Chris Wilson
- [PATCH 20/39] drm/i915/gt: Free stale request on destroying the virtual engine
Chris Wilson
- [PATCH 21/39] drm/i915/gt: Protect context lifetime with RCU
Chris Wilson
- [PATCH 22/39] drm/i915/gt: Split the breadcrumb spinlock between global and contexts
Chris Wilson
- [PATCH 23/39] drm/i915/gt: Move the breadcrumb to the signaler if completed upon cancel
Chris Wilson
- [PATCH 24/39] drm/i915/gt: Decouple completed requests on unwind
Chris Wilson
- [PATCH 25/39] drm/i915/gt: Check for a completed last request once
Chris Wilson
- [PATCH 26/39] drm/i915/gt: Replace direct submit with direct call to tasklet
Chris Wilson
- [PATCH 27/39] drm/i915/gt: ce->inflight updates are now serialised
Chris Wilson
- [PATCH 28/39] drm/i915/gt: Use virtual_engine during execlists_dequeue
Chris Wilson
- [PATCH 29/39] drm/i915/gt: Decouple inflight virtual engines
Chris Wilson
- [PATCH 30/39] drm/i915/gt: Defer schedule_out until after the next dequeue
Chris Wilson
- [PATCH 31/39] drm/i915/gt: Remove virtual breadcrumb before transfer
Chris Wilson
- [PATCH 32/39] drm/i915/gt: Shrink the critical section for irq signaling
Chris Wilson
- [PATCH 33/39] drm/i915/gt: Resubmit the virtual engine on schedule-out
Chris Wilson
- [PATCH 34/39] drm/i915/gt: Simplify virtual engine handling for execlists_hold()
Chris Wilson
- [PATCH 35/39] drm/i915: Encode fence specific waitqueue behaviour into the wait.flags
Chris Wilson
- [PATCH 36/39] drm/i915/selftests: Confirm RING_TIMESTAMP / CTX_TIMESTAMP share a clock
Chris Wilson
- [PATCH 37/39] drm/i915/gt: Consolidate the CS timestamp clocks
Chris Wilson
- [PATCH 38/39] drm/i915: Break up error capture compression loops with cond_resched()
Chris Wilson
- [PATCH 39/39] drm/i915: Reduce GPU error capture mutex hold time
Chris Wilson
Last message date:
Mon Aug 31 11:13:03 UTC 2020
Archived on: Mon Aug 31 11:13:03 UTC 2020
This archive was generated by
Pipermail 0.09 (Mailman edition).