- 21 Dec, 2023 40 commits
-
-
Lucas De Marchi authored
This is useful to debug cache issues, to double check if the PAT indexes match what they were supposed to be set to from spec. v2: Add separate functions for XeHP, XeHPC and XeLPG so it correctly reads the index based on MCR/REG registers and also decodes the fields (Matt Roper) v3: Starting with XeHPC, do not translate values to human-readable formats as the main goal is to make it easy to compare the table with the spec. Also, share a single array for xelp/xehp str map (Matt Roper) Reviewed-by:Matt Roper <matthew.d.roper@intel.com> Link: https://lore.kernel.org/r/20231006182325.3617685-3-lucas.demarchi@intel.comSigned-off-by:
Lucas De Marchi <lucas.demarchi@intel.com> Signed-off-by:
Rodrigo Vivi <rodrigo.vivi@intel.com>
-
Lucas De Marchi authored
Xe2 adds one more bit to cover all the possible 32 entries. Although those entries are not used by internal kernel code paths, it's expected that userspace will make use of it. Bspec: 59510, 67095 Reviewed-by:
Pallavi Mishra <pallavi.mishra@intel.com> Reviewed-by:
-
Matt Roper authored
The PAT tables become significantly more complicated on Xe2 platforms. They now control L3, L4, and coherency settings, as well as additional characteristics such as compression. Aside from the main PAT table, there's an additional register that also needs to be programmed with PAT settings for PCI Address Translation Services. Bspec: 71582 Signed-off-by:
Balasubramani Vivekanandan <balasubramani.vivekanandan@intel.com> Link: https://lore.kernel.org/r/20231006182325.3617685-1-lucas.demarchi@intel.comSigned-off-by:
-
David Kershner authored
Add missing kunit test to migrate a bo from vram to vram Reviewed-by:
Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com> Reviewed-by:
"Michael J. Ruhl" <michael.j.ruhl@intel.com> Signed-off-by:
David Kershner <david.kershner@intel.com> Signed-off-by:
-
David Kershner authored
Device Physical Address (DPA) is the starting offset device memory. Update xe_migrate identity map base PTE entries to start at dpa_base instead of 0. The VM offset value should be 0 relative instead of DPA relative. Reviewed-by:
-
Lucas De Marchi authored
Register GUC_TLB_INV_CR is gone in xe2. When GuC submission is not yet enabled, make sure to follow the same path as XeHPC. Signed-off-by:
-
Lucas De Marchi authored
When xelp_pte_encode_addr() was added in commit 23c8495e ("drm/xe/migrate: Do not hand-encode pte"), there was no xe pointer for using xe_assert(). This is not the case anymore, so prefer it over XE_WARN_ON(). Signed-off-by:
-
Matt Atwood authored
Force indirect state sampler data to only be in the dynamic state pool, which is more convienent for the UMD. Behavior change mirrors similar change for i915 in commit 16fc9c08 ("drm/i915: disable sampler indirect state in bindless heap") v2: split out per engine tuning into separate patch, commit message (Lucas) v3: rebase v4: Change to match render only, g.ver 1200 to 1271 (MattR) Acked-by:
Lionel Landwerlin <lionel.g.landwerlin@intel.com> Reviewed-by:
Matt Atwood <matthew.s.atwood@intel.com> Signed-off-by:
-
Matt Atwood authored
Add the infrastructure for per engine tuning in preparation for disable indirect state. v3: Rebase v4: Fix rebasing issues Reviewed-by:
-
Matthew Auld authored
It doesn't look like you can mix and match devm_ and drmmm_ for a managed resource. For drmmm the resources are all tracked in drm with its own list, and there is only one devm_ resource for the entire list. If the driver itself also adds some of its own devm resources, then those will be released first. In the case of hwmon the devm_kzalloc will be freed before the drmmm_ action to destroy the mutex allocated within, leading to uaf. Since hwmon itself wants to use devm, rather use that for the mutex destroy. Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/766Signed-off-by:
Matthew Auld <matthew.auld@intel.com> Cc: Badal Nilawar <badal.nilawar@intel.com> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Reviewed-by:
-
Lucas De Marchi authored
Add index 4 so WB on both L3 and L4 can be used by userspace. Bspec: 71582 Link: https://lore.kernel.org/all/7oqovb356dx2hm5muop3xjqr4kv7m5fzjisch3vmsmxm33ygtv@eib4jielia35/Reviewed-by:
-
José Roberto de Souza authored
This register don't exist in gfx12+, so here dropping the readout and print in devcoredump. Reviewed-by:
José Roberto de Souza <jose.souza@intel.com> Signed-off-by:
-
José Roberto de Souza authored
It was reading (base) + 0x8c but that is not a valid register and instead it should read (base) + 0x68. So here reading the correct register and removing the wrong and duplicated. Reviewed-by:
-
José Roberto de Souza authored
Fix a typo in RING_MI_MODE label. Signed-off-by:
-
Paulo Zanoni authored
We're already using the half-open interval notation "[A, B)", that "- 1" there makes it wrong. Also, getting rid of the "-1" makes it much easier to grep for the logs when you're looking for an address that's the end of a vma and the start of another. Signed-off-by:
Paulo Zanoni <paulo.r.zanoni@intel.com> Reviewed-by:
-
Paulo Zanoni authored
I would imagine that it's more efficient to fetch ops_list->prev than to walk the whole list forward. Signed-off-by:
-
Paulo Zanoni authored
Unions are cool, until they aren't. Signed-off-by:
-
Badal Nilawar authored
Expose hwmon energy attribute to show device level energy usage v2: - %s/hwm_/hwmon_/ - Convert enums to upper case v3: - %s/hwmon_/xe_hwmon - Remove gt specific hwmon attributes v4: - %s/REG_PKG_ENERGY_STATUS/REG_ENERGY_STATUS_ALL (Riana) - %s/hwmon_energy_info/xe_hwmon_energy_info (Riana) Acked-by:
Riana Tauro <riana.tauro@intel.com> Signed-off-by:
Badal Nilawar <badal.nilawar@intel.com> Reviewed-by:
Andi Shyti <andi.shyti@linux.intel.com> Link: https://lore.kernel.org/r/20230925081842.3566834-5-badal.nilawar@intel.comSigned-off-by:
-
Badal Nilawar authored
Use Xe HWMON subsystem to display the input voltage. v2: - Rename hwm_get_vltg to hwm_get_voltage (Riana) - Use scale factor SF_VOLTAGE (Riana) v3: - %s/gt_perf_status/REG_GT_PERF_STATUS/ - Remove platform check from hwmon_get_voltage() v4: - Fix review comments (Andi) Acked-by:
-
Badal Nilawar authored
Expose the card reactive critical (I1) power. I1 is exposed as power1_crit in microwatts (typically for client products) or as curr1_crit in milliamperes (typically for server). v2: Move PCODE_MBOX macro to pcode file (Riana) v3: s/IS_DG2/(gt_to_xe(gt)->info.platform == XE_DG2) v4: Fix review comments (Andi) Acked-by:
-
Badal Nilawar authored
Expose Card reactive sustained (pl1) power limit as power_max and card default power limit (tdp) as power_rated_max. v2: - Fix review comments (Riana) v3: - Use drmm_mutex_init (Matt Brost) - Print error value (Matt Brost) - Convert enums to uppercase (Matt Brost) - Avoid extra reg read in hwmon_is_visible function (Riana) - Use xe_device_assert_mem_access when applicable (Matt Brost) - Add intel-xe@lists.freedesktop.org in Documentation (Matt Brost) v4: - Use prefix xe_hwmon prefix for all functions (Matt Brost/Andi) - %s/hwmon_reg/xe_hwmon_reg (Andi) - Fix review comments (Guenter/Andi) v5: - Fix review comments (Riana) v6: - Use drm_warn in default case (Rodrigo) - s/ENODEV/EOPNOTSUPP (Andi) Acked-by:
-
Matthew Brost authored
Passing in a NULL exec queue to __xe_pt_unbind_vma results in the migrate exec queue being used. This is not the intent from the VM bind IOCTL, rather a NULL exec queue should use default VM exec queue. Reviewed-by:
Matthew Brost <matthew.brost@intel.com> Signed-off-by:
-
Balasubramani Vivekanandan authored
On platforms that support read L3 caching, set the default mocs index in CCS RING_CMD_CTL to leverage the read caching in L3. Currently PVC and Xe2 platforms have the support. Bspec: 72161 Signed-off-by:
-
Haridhar Kalvala authored
Xe2 changes or adds bits for mocs in a few BLT instructions: XY_CTRL_SURF_COPY_BLT, XY_FAST_COLOR_BLT, XY_FAST_COPY_BLT, and MEM_SET. Modify the code to deal with the new location. Unlike Xe1, the MOCS field in those instructions is only the MOCS index and not the Structure_MEMORY_OBJECT_CONTROL_STATE anymore. The pxp bit is now explicitly documented separately. Bspec: 57567,57566,57565,57562 Cc: Matt Roper <matthew.d.roper@intel.com> Signed-off-by:
Haridhar Kalvala <haridhar.kalvala@intel.com> Reviewed-by:
-
Haridhar Kalvala authored
Set bits 30 and 31 of XY_FAST_COPY_BLT's dword1 for XeHP and above. Destination or source being Y-Major is selected on dword0 and there's nothing to set on dword1. According to the bspec for Xe2, "Behavior is undefined when programmed the value 0". Also for XeHP, the only value allowed in those bits is 0b11, not being possible to select "Legacy Tile-Y" anymore, only the newer Tile4. So, unconditionally set those bits for graphics IP 12.50 and above. v2: Reword commit message and extend it to graphics version >= 12.50 (Matt Roper) Bspec: 57567 Cc: Matt Roper <matthew.d.roper@intel.com> Signed-off-by: -
Haridhar Kalvala authored
PVC_MS_* doesn't reflect the real name of the instruction. Rename it to follow the name used in the bspec. Cc: Matt Roper <matthew.d.roper@intel.com> Signed-off-by:
-
Haridhar Kalvala authored
Instead of using xe_mocs_index_to_value(), simply define the bitmask with the shift left applied. This will make it easier to adapt to new platforms that simply use the index. This also fixes PVC bug in emit_clear_link_copy() where the MOCS was getting shifted both by PVC_MS_MOCS_INDEX_MASK definition and by the xe_moc_index_to_value function. Bspec: 44509 Cc: Matt Roper <matthew.d.roper@intel.com> Signed-off-by:
-
Lucas De Marchi authored
For xe2, besides the previous sizes, the reserved portion of stolen can also have 16MB and 32MB. Bspec: 53148 Reviewed-by:
-
Matt Roper authored
The LRC tuning settings we have today are modifying registers that are part of the RCS engine's context; they're not part of the general CSFE context that would apply to all engines. Add ENGINE_CLASS(RENDER) to the RTP rules to properly restrict these to the RCS. Bspec: 46255, 46261 Reviewed-by:
-
Fei Yang authored
In xe_wait_user_fence_ioctl, the timeout is currently defined as unsigned long. That could potentially pass a negative value to the schedule_timeout() call because nsecs_to_jiffies() returns an unsigned long which gets used as signed long. [ 187.732238] schedule_timeout: wrong timeout value fffffffffffffc18 [ 187.733180] CPU: 0 PID: 792 Comm: test_thread_dim Tainted: G U 6.4.0-xe #1 [ 187.734251] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2007 [ 187.735019] Call Trace: [ 187.735373] <TASK> [ 187.735687] dump_stack_lvl+0x92/0xb0 [ 187.736193] schedule_timeout+0x348/0x430 [ 187.736739] ? __might_fault+0x67/0xd0 [ 187.737255] ? check_chain_key+0x224/0x2d0 [ 187.737812] ? __pfx_schedule_timeout+0x10/0x10 [ 187.738429] ? __might_fault+0x6b/0xd0 [ 187.738946] ? __pfx_lock_release+0x10/0x10 [ 187.739512] ? __pfx_lock_release+0x10/0x10 [ 187.740080] wait_woken+0x86/0x100 [ 187.740556] xe_wait_user_fence_ioctl+0x34b/0xe00 [xe] [ 187.741281] ? __pfx_xe_wait_user_fence_ioctl+0x10/0x10 [xe] [ 187.742075] ? lock_acquire+0x169/0x3d0 [ 187.742601] ? check_chain_key+0x224/0x2d0 [ 187.743158] ? drm_dev_enter+0x9/0xe0 [drm] [ 187.743740] ? __pfx_woken_wake_function+0x10/0x10 [ 187.744388] ? drm_dev_exit+0x11/0x50 [drm] [ 187.744969] ? __pfx_lock_release+0x10/0x10 [ 187.745536] ? __might_fault+0x67/0xd0 [ 187.746052] ? check_chain_key+0x224/0x2d0 [ 187.746610] drm_ioctl_kernel+0x172/0x250 [drm] [ 187.747242] ? __pfx_xe_wait_user_fence_ioctl+0x10/0x10 [xe] [ 187.748037] ? __pfx_drm_ioctl_kernel+0x10/0x10 [drm] [ 187.748729] ? __pfx_xe_wait_user_fence_ioctl+0x10/0x10 [xe] [ 187.749524] ? __pfx_xe_wait_user_fence_ioctl+0x10/0x10 [xe] [ 187.750319] drm_ioctl+0x35e/0x620 [drm] [ 187.750871] ? __pfx_drm_ioctl+0x10/0x10 [drm] [ 187.751495] ? restore_fpregs_from_fpstate+0x99/0x140 [ 187.752172] ? __pfx_restore_fpregs_from_fpstate+0x10/0x10 [ 187.752901] ? mark_held_locks+0x24/0x90 [ 187.753438] __x64_sys_ioctl+0xb4/0xf0 [ 187.753954] do_syscall_64+0x3f/0x90 [ 187.754450] entry_SYSCALL_64_after_hwframe+0x72/0xdc [ 187.755127] RIP: 0033:0x7f4e6651aaff [ 187.755623] Code: 00 48 89 44 24 18 31 c0 48 8d 44 24 60 c7 04 24 10 00 00 00 48 89 44 24 08 48 8d 44 24 20 48 89 44 24 10 b8 10 00 00 00 0f 05 <41> 89 c0 3d 00 f0 ff ff 77 1f 48 8b 44 24 18 64 48 2b 04 25 28 00 [ 187.757995] RSP: 002b:00007fff05f37a50 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 [ 187.758995] RAX: ffffffffffffffda RBX: 000055eca47c8130 RCX: 00007f4e6651aaff [ 187.759935] RDX: 00007fff05f37b60 RSI: 00000000c050644b RDI: 0000000000000004 [ 187.760874] RBP: 0000000000000017 R08: 0000000000000017 R09: 7fffffffffffffff [ 187.761814] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 [ 187.762753] R13: 0000000000000000 R14: 0000000000000000 R15: 00007f4e65d19ce0 [ 187.763694] </TASK> Fixes: 5572a004 ("drm/xe: Use nanoseconds instead of jiffies in uapi for user fence") Signed-off-by:
Fei Yang <fei.yang@intel.com> Cc: Andi Shyti <andi.shyti@linux.intel.com> Cc: Zbigniew Kempczyński <zbigniew.kempczynski@intel.com> Reviewed-by:
-
Fei Yang authored
Atomic access is supported by PVC, and became a common feature for all platforms starting from Xe2. To enable that XE_VMA_ATOMIC_PTE_BIT needs to be set, then pte encode will eventually set PTE_AE for devmem. Signed-off-by:
-
Bommithi Sakeena authored
Ensure that the mutex is destroyed at fini function. Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com> Signed-off-by:
Bommithi Sakeena <bommithi.sakeena@intel.com> Reviewed-by:
-
Bommithi Sakeena authored
Add missing mutex_destroy calls to fini functions or convert to drmm_mutex_init where fini function is not available. Cc: Matthew Brost <matthew.brost@intel.com> Signed-off-by:
-
Ohad Sharabi authored
When working without GuC (i.e. working with execlists), the flow attempts to perform suspend operation which is failing due to a lack of support without GuC. If PM ops are not supported without GuC we may as well avoid PM registration rather than returning errors from various PM flows. Signed-off-by:
Ohad Sharabi <osharabi@habana.ai> Reviewed-by:
-
Lucas De Marchi authored
Use 2 different functions for encoding the ggtt's pte, assigning them during initialization. Main difference is that before Xe-LPG, the pte didn't have the cache bits. v2: Re-use xelp_ggtt_pte_encode_bo() for the common part with xelpg_ggtt_pte_encode_bo() (Matt Roper) Reviewed-by: -
Lucas De Marchi authored
Change the xelp_pte_encode() and xelp_pde_encode() functions to use the platform-dependent pat_index. The same function can be used for all platforms as they only need to encode the pat_index bits in the same pte/pde layout. For platforms that don't have the most significant bit, as long as they don't return a bogus index they should be fine. v2: Use the same logic to encode pde as it's compatible with previous logic, it's more future proof and also fixes the cache setting for PVC (Matt Roper) Reviewed-by: -
Lucas De Marchi authored
Some of the PAT entries are relevant for internal driver use, which varies per platform. Let the PAT early initialization set what they should point to so the rest of the driver can use them where needed. Reviewed-by:
-
Lucas De Marchi authored
Both DG2 and PVC are derived from XeHP, but DG2 should not really re-use something introduced by PVC, so it's odd to have DG2 re-using the PVC programming for PAT. Let's prefer using the architecture and/or IP names. Reviewed-by:
-
Lucas De Marchi authored
DG2 should use the MCR variant to program the PAT registers, like PVC, but shouldn't use the same table as PVC. Reviewed-by:
-
Lucas De Marchi authored
Split the PAT initialization between SW-only and HW. The _early() only sets up the ops and data structure that are used later to program the tables. This allows the PAT to be easily extended to other platforms. Reviewed-by:
-
