[PATCH v2 06/29] drm/xe/uapi: Add DRM_XE_VM_BIND_FLAG_SYSTEM_ALLOCATON flag

Add the DRM_XE_VM_BIND_FLAG_SYSTEM_ALLOCATOR flag, which is used to create unpopulated virtual memory areas (VMAs) without memory backing or GPU page tables. These VMAs are referred to as system allocator VMAs. The idea is that upon a page fault or prefetch, the memory backing and GPU page tables w

[PATCH v2 10/29] drm/gpuvm: Add DRM_GPUVA_OP_USER

Add DRM_GPUVA_OP_USER which allows driver to define their own gpuvm ops. Cc: Danilo Krummrich Signed-off-by: Matthew Brost --- include/drm/drm_gpuvm.h | 5 + 1 file changed, 5 insertions(+) diff --git a/include/drm/drm_gpuvm.h b/include/drm/drm_gpuvm.h index 00d4e43b76b6..cc3f8ed5113b 1006

[PATCH v2 19/29] drm/xe: Add GPUSVM devic memory copy vfunc functions

Add GPUSVM devic memory copy vfunc functions and connect to migration layer. v2: - Allow NULL device pages in xe_svm_copy - Use new drm_gpusvm_devmem_ops Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/xe_svm.c | 150 1 file changed, 150 insertions(+)

[PATCH v2 15/29] drm/xe: Enable system allocator uAPI

Support for system allocator bindings in SRAM fully in place, enable the implementation. Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/xe_vm.c | 6 -- 1 file changed, 6 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 158fbb1c3f28..8eed820079ba 1

[PATCH v2 16/29] drm/xe: Add migrate layer functions for SVM support

Add functions which migrate to / from VRAM accepting a single DPA argument (VRAM) and array of dma addresses (SRAM). v2: - Don't unlock job_mutex in error path of xe_migrate_vram Signed-off-by: Oak Zeng Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/xe_migrate.c | 149 +++

[PATCH v2 01/29] drm/xe: Retry BO allocation

TTM doesn't support fair eviction via WW locking, this mitigated in by using retry loops in exec and preempt rebind worker. Extend this retry loop to BO allocation. Once TTM supports fair eviction this patch can be reverted. Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/xe_bo.c | 8 +++

[PATCH v2 00/29] Introduce GPU SVM and Xe SVM implementation

Version 2 of GPU SVM has been promoted to the proper series from an RFC. Thanks to everyone (especially Sima and Thomas) for their numerous reviews on revision 1 and for helping to address many design issues. This version has been tested with IGT [1] on PVC, BMG, and LNL. Major changes in v2: - D

[PATCH v2 02/29] mm/migrate: Add migrate_device_prepopulated_range

Add migrate_device_prepoluated_range which prepares an array of pre-populated device pages for migration. v2: - s/migrate_device_vma_range/migrate_device_prepopulated_range - Drop extra mmu invalidation (Vetter) Cc: Andrew Morton Signed-off-by: Matthew Brost --- include/linux/migrate.h | 1

[PATCH v2 04/29] drm/pagemap: Add DRM pagemap

From: Thomas Hellström Introduce drm_pagemap ops to map and unmap dma to VRAM resources. In the local memory case it's a matter of merely providing an offset into the device's physical address. For future p2p the map and unmap functions may encode as needed. Similar to how dma-buf works, let the

[PATCH v2 22/29] drm/xe: Add Xe SVM devmem_release vfunc

Implement with a simple BO put. v2: - Use new drm_gpusvm_devmem_ops Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/xe_svm.c | 7 +++ 1 file changed, 7 insertions(+) diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c index 19fcb8f71791..976b4ce15db4 100644 --- a/dr

[PATCH v2 08/29] drm/xe: Add dma_addr res cursor

From: Thomas Hellström Useful for SVM ranges in SRAM and programing page tables. Signed-off-by: Matthew Brost Signed-off-by: Thomas Hellström --- drivers/gpu/drm/xe/xe_res_cursor.h | 116 - drivers/gpu/drm/xe/xe_svm.h| 4 + 2 files changed, 118 insertions

[PATCH v2 14/29] drm/xe: Do not allow system allocator VMA unbind if the GPU has bindings

uAPI is designed with the the use case that only mapping a BO to a malloc'd address will unbind a system allocator VMA. Thus it doesn't make tons of sense to allow a system allocator VMA unbind if the GPU has bindings in the range being unbound. Do not support this as it simplifies the code. Can al

[PATCH v2 23/29] drm/xe: Add BO flags required for SVM

Add XE_BO_FLAG_SYSTEM_ALLOC to indicate BO is tied to SVM range. Add XE_BO_FLAG_SKIP_CLEAR to indicate BO does not need to cleared. v2: - Take VM ref for system allocator BOs Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/xe_bo.c | 15 +-- drivers/gpu/drm/xe/xe_bo.h | 2 ++

[PATCH v2 05/29] drm/gpusvm: Add support for GPU Shared Virtual Memory

This patch introduces support for GPU Shared Virtual Memory (SVM) in the Direct Rendering Manager (DRM) subsystem. SVM allows for seamless sharing of memory between the CPU and GPU, enhancing performance and flexibility in GPU computing tasks. The patch adds the necessary infrastructure for SVM, i

[PATCH v2 25/29] drm/xe: Basic SVM BO eviction

Wire xe_bo_move to GPUSVM migration to SRAM with trylocking of mmap lock. v2: - Use xe_svm_bo_evict - Drop bo->range Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/xe_bo.c | 20 drivers/gpu/drm/xe/xe_svm.c | 5 + drivers/gpu/drm/xe/xe_svm.h | 3 +++ 3 files ch

[PATCH v2 20/29] drm/xe: Add drm_pagemap ops to SVM

From: Thomas Hellström Add support for mapping device pages to Xe SVM. Signed-off-by: Matthew Brost Signed-off-by: Thomas Hellström --- drivers/gpu/drm/xe/xe_device_types.h | 7 +++ drivers/gpu/drm/xe/xe_svm.c | 30 2 files changed, 37 insertions(+)

[PATCH v2 26/29] drm/xe: Add SVM debug

Add some useful SVM debug logging. v2: - Upadte logging with latest structure layout Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/xe_pt.c | 8 +++ drivers/gpu/drm/xe/xe_svm.c | 101 +++- drivers/gpu/drm/xe/xe_svm.h | 2 + 3 files changed, 99 insertio

[PATCH v2 18/29] drm/xe: Add drm_gpusvm_devmem to xe_bo

Add drm_gpusvm_devmem to xe_bo. Required to enable SVM migrations. Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/xe_bo_types.h | 5 + 1 file changed, 5 insertions(+) diff --git a/drivers/gpu/drm/xe/xe_bo_types.h b/drivers/gpu/drm/xe/xe_bo_types.h index 13c6d8a69e91..54d337004621 10064

[PATCH v2 11/29] drm/xe: Add (re)bind to SVM page fault handler

Add (re)bind to SVM page fault handler. To facilitate add support function to VM layer which (re)binds a SVM range. Also teach PT layer to understand (re)binds of SVM ranges. v2: - Don't assert BO lock held for range binds - Use xe_svm_notifier_lock/unlock helper in xe_svm_close - Use drm_pagem

[PATCH v2 27/29] drm/xe: Add modparam for SVM notifier size

Useful to experiment with notifier size and how it affects performance. Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/xe_module.h | 1 + drivers/gpu/drm/xe/xe_svm.c| 5 +++-- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_module.h b/drivers/gpu/drm

[PATCH v2 29/29] drm/doc: gpusvm: Add GPU SVM documentation

Add documentation for agree upon GPU SVM design principles, current status, and future plans. Signed-off-by: Matthew Brost --- Documentation/gpu/rfc/gpusvm.rst | 70 Documentation/gpu/rfc/index.rst | 4 ++ 2 files changed, 74 insertions(+) create mode 100644 D

[PATCH v2 13/29] drm/xe: Add unbind to SVM garbage collector

Add unbind to SVM garbage collector. To facilitate add unbind support function to VM layer which unbinds a SVM range. Also teach PY layer to understand unbinds of SVM ranges. Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/xe_pt.c | 84 ++-- drivers/gpu/drm/

[PATCH v2 07/29] drm/xe: Add SVM init / close / fini to faulting VMs

Add SVM init / close / fini to faulting VMs. Minimual implementation. v2: - Add close function Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/Makefile | 1 + drivers/gpu/drm/xe/xe_svm.c | 46 drivers/gpu/drm/xe/xe_svm.h | 15 +++ dr

[PATCH v2 24/29] drm/xe: Add SVM VRAM migration

Migration is implemented with range granularity, with VRAM backing being a VM private TTM BO (i.e., shares dma-resv with VM). The lifetime of the TTM BO is limited to when the SVM range is in VRAM (i.e., when a VRAM SVM range is migrated to SRAM, the TTM BO is destroyed). The design choice for usi

[PATCH v2 21/29] drm/xe: Add Xe SVM populate_devmem_pfn vfunc

Get VRAM pfns from BO's buddy blocks. v2: - Use new drm_gpusvm_devmem_ops Signed-off-by: Niranjana Vishwanathapura Signed-off-by: Oak Zeng Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/xe_svm.c | 40 + 1 file changed, 40 insertions(+) diff --git a/d

[PATCH v2 28/29] drm/xe: Add always_migrate_to_vram modparam

Used to show we can bounce memory multiple times. Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/xe_module.c | 7 +++ drivers/gpu/drm/xe/xe_module.h | 1 + drivers/gpu/drm/xe/xe_svm.c| 3 +++ 3 files changed, 11 insertions(+) diff --git a/drivers/gpu/drm/xe/xe_module.c b/drivers/gp

Re: [PATCH v1 05/10] media: platform: mediatek: add isp_7x camsys unit

Re: [PATCH] drm/i915/lspcon: do not hardcode settle timeout

On 10/14/2024 3:09 PM, Giedrius Statkevičius wrote: Avoid hardcoding the LSPCON settle timeout because it takes a longer time on certain chips made by certain vendors. Use the function that already exists to determine the timeout. Signed-off-by: Giedrius Statkevičius --- drivers/gpu/drm/dis

Re: [PATCH v1 1/4] mm/hmm: HMM API for P2P DMA to device zone pages

Yonatan Maman writes: > From: Yonatan Maman > > hmm_range_fault() natively triggers a page fault on device private > pages, migrating them to RAM. In some cases, such as with RDMA devices, > the migration overhead between the device (e.g., GPU) and the CPU, and > vice-versa, significantly dama

Re: [PATCH v2 03/29] mm/migrate: Trylock device page in do_swap_page

Matthew Brost writes: > Avoid multiple CPU page faults to the same device page racing by trying > to lock the page in do_swap_page before taking an extra reference to the > page. This prevents scenarios where multiple CPU page faults each take > an extra reference to a device page, which could

Re: [PATCH] video: fix inconsistent indentation warning

On 15/10/24 02:02, Helge Deller wrote: On 10/6/24 09:15, SurajSonawane2415 wrote: Fix the indentation to ensure consistent code style and improve readability, and to fix this warning: drivers/video/fbdev/nvidia/nv_hw.c:1512 NVLoadStateExt() warn: inconsistent indenting Signed-off-by: SurajSonaw

Re: [PATCH v2 02/29] mm/migrate: Add migrate_device_prepopulated_range

Matthew Brost writes: > Add migrate_device_prepoluated_range which prepares an array of > pre-populated device pages for migration. It would be nice if the commit message could also include an explanation of why the existing migrate_device_range() is inadequate for your needs. > v2: > - s/mi

Re: [linux-next:master] [fs] d91ea8195e: stress-ng.ring-pipe.ops_per_sec -5.1% regression (stress-ng.ring-pipe.pipe_read+write_calls_per_sec 7.3% improvement)

hi, Eric, On Tue, Oct 15, 2024 at 07:25:32PM -0700, Eric Biggers wrote: > On Wed, Oct 16, 2024 at 10:19:25AM +0800, kernel test robot wrote: > > kernel test robot noticed a -5.1% regression of > > stress-ng.ring-pipe.ops_per_sec > > These emails that talk about negative regressions keep confusin

RE: [PATCH v1 1/5] PCI/P2PDMA: Don't enforce ACS check for functions of same device

Hi Logan, > > On 2024-10-11 20:40, Vivek Kasireddy wrote: > > Functions of the same PCI device (such as a PF and a VF) share the > > same bus and have a common root port and typically, the PF provisions > > resources for the VF. Therefore, they can be considered compatible > > as far as P2P acces

Re: [PATCH v2] drm/panthor: Fix firmware initialization on systems with a page size > 4k

On Tue, 15 Oct 2024 22:29:45 +0100 Liviu Dudau wrote: > On Tue, Oct 15, 2024 at 09:03:51AM +0200, Boris Brezillon wrote: > > Hi Liviu, > > > > On Tue, 15 Oct 2024 02:08:46 +0100 > > Liviu Dudau wrote: > > > > > Hi Boris, > > > > > > I'm a bit confused, I thought the plan was to separate the

Re: [PATCH v2 02/29] mm/migrate: Add migrate_device_prepopulated_range

On Wed, Oct 16, 2024 at 03:04:06PM +1100, Alistair Popple wrote: > > Matthew Brost writes: > > > Add migrate_device_prepoluated_range which prepares an array of > > pre-populated device pages for migration. > > It would be nice if the commit message could also include an explanation > of why th

Re: [PATCH v1 1/5] dt-bindings: dmaengine: qcom: gpi: Add additional arg to dma-cell property

On 15-10-24, 17:37, Jyothi Kumar Seerapu wrote: > When high performance with multiple i2c messages in a single transfer > is required, employ Block Event Interrupt (BEI) to trigger interrupts > after specific messages transfer and the last message transfer, > thereby reducing interrupts. > > For e

[PATCH] drm/i915/display: plane property for async supported modifiers

Create a i915 private plane property for sharing the async supported modifiers to the user. UMD related discussion requesting the same https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29618#note_2487123 Signed-off-by: Arun R Murthy --- .../gpu/drm/i915/display/intel_atomic_plane.c | 6

RE: [PATCH v1 4/5] drm/xe/bo: Create a new sg for dmabuf BOs that are associated with a VF

Hi Matt, > > On Fri, Oct 11, 2024 at 07:40:26PM -0700, Vivek Kasireddy wrote: > > For BOs of type ttm_bo_type_sg, that are backed by PCI BAR addresses > > associated with a VF, we need to adjust and translate these addresses > > to LMEM addresses to make the BOs usable by the PF. Otherwise, the B

Re: [PATCH v2] locking/ww_mutex: Adjust to lockdep nest_lock requirements

On Tue, 2024-10-15 at 11:00 -0700, Boqun Feng wrote: > On Tue, Oct 15, 2024 at 05:27:28PM +0200, Thomas Hellström wrote: > [..] > > > diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c > > > index 6f6a5fc85b42..6750321e3e9a 100644 > > > --- a/lib/locking-selftest.c > > > +++ b/lib/locking

Re: [PATCH v4 3/7] drm/log: Introduce a new boot logger to draw the kmsg on the screen

Hi Jocelyn, kernel test robot noticed the following build errors: [auto build test ERROR on 33c255312660653cf54f8019896b5dca28e3c580] url: https://github.com/intel-lab-lkp/linux/commits/Jocelyn-Falempe/drm-client-squash-of-drm-client-pending-series/20241011-225715 base: 33c255312660653cf54

[PATCH v5 1/1] drm/i915/pxp: Add missing tag for Wa_14019159160

Add missing tag for "Wa_14019159160 - Case 2" (for existing PXP code that ensures run alone mode bit is set to allow PxP-decryption. v5: - remove the max IP_VER check since new platforms that i915 supports needs this fix and tag the caller too (John Harrison). v4: - Include IP_VER

Re: [PATCH v1 08/10] media: platform: mediatek: add isp_7x state ctrl

Re: [PATCH v1 09/10] media: platform: mediatek: add isp_7x build config

Re:Re:Re:[PATCH v5] rockchip/drm: vop2: add support for gamma LUT

Hi Piotr, At 2024-10-16 04:13:40, "Piotr Zalewski" wrote: >Hi Andy > >On Tuesday, October 15th, 2024 at 2:22 PM, Andy Yan wrote: > >> > > > + struct vop2_video_port *vp, >> > > > + struct drm_crtc *crtc, >> > > > + struct drm_crtc_state *crtc_state) >> > > > +{ >> > > > + >> > > > + if (vop2->l

Re:[PATCH v5] rockchip/drm: vop2: add support for gamma LUT

Hi Piotr, At 2024-10-15 06:30:27, "Piotr Zalewski" wrote: >Add support for gamma LUT in VOP2 driver. The implementation was inspired >by one found in VOP1 driver. Blue and red channels in gamma LUT register >write were swapped with respect to how gamma LUT values are written in >VOP1. Gamma LUT p

[linux-next:master] [fs] d91ea8195e: stress-ng.ring-pipe.ops_per_sec -5.1% regression (stress-ng.ring-pipe.pipe_read+write_calls_per_sec 7.3% improvement)

a27-oliver.s...@intel.com/ Details are as below: --> The kernel config and materials to reproduce are available at: https://download.01.org/0day-ci/archive/20241015/202410151611.f4cd71f2-oliver.s...@intel.com ==

Re: [linux-next:master] [fs] d91ea8195e: stress-ng.ring-pipe.ops_per_sec -5.1% regression (stress-ng.ring-pipe.pipe_read+write_calls_per_sec 7.3% improvement)

On Wed, Oct 16, 2024 at 10:19:25AM +0800, kernel test robot wrote: > kernel test robot noticed a -5.1% regression of > stress-ng.ring-pipe.ops_per_sec These emails that talk about negative regressions keep confusing me. A negative regression would be an improvement. But that is not actually wha

[PATCH v11 2/2] drm/tiny: Add driver for Sharp Memory LCD

Add support for the monochrome Sharp Memory LCDs. Co-developed-by: Mehdi Djait Signed-off-by: Mehdi Djait Signed-off-by: Alex Lanzano Reviewed-by: Dmitry Baryshkov Acked-by: Uwe Kleine-König --- MAINTAINERS | 6 + drivers/gpu/drm/tiny/Kconfig| 21 + drivers

[PATCH v11 1/2] dt-bindings: display: Add Sharp Memory LCD bindings

Add device tree bindings for the monochrome Sharp Memory LCD Co-developed-by: Mehdi Djait Signed-off-by: Mehdi Djait Signed-off-by: Alex Lanzano Reviewed-by: Krzysztof Kozlowski --- .../bindings/display/sharp,ls010b7dh04.yaml | 92 +++ 1 file changed, 92 insertions(+) creat

[PATCH v11 0/2] Add driver for Sharp Memory LCD

This patch series add support for the monochrome Sharp Memory LCD panels. This series is based off of the work done by Mehdi Djait. References: https://lore.kernel.org/dri-devel/71a9dbf4609dbba46026a31f60261830163a0b99.1701267411.git.mehdi.dj...@bootlin.com/ https://www.sharpsde.com/fileadmin/prod

Re: vc4: HDMI Sink doesn't support RGB, something's wrong.

Hi Dave, Am 15.10.24 um 11:32 schrieb Dave Stevenson: On Mon, 14 Oct 2024 at 22:16, Stefan Wahren wrote: Am 14.10.24 um 12:54 schrieb Dave Stevenson: On Mon, 14 Oct 2024 at 10:04, Maxime Ripard wrote: Hi, On Sun, Oct 13, 2024 at 09:57:58PM GMT, Stefan Wahren wrote: Am 13.10.24 um 21:11 s

Re: [PATCH v1 1/3] proc_pid_fdinfo.5: Reduce indent for most of the page

On Tue, Oct 15, 2024 at 1:32 PM G. Branden Robinson wrote: > > At 2024-10-15T11:38:22-0700, Ian Rogers wrote: > > When /proc/pid/fdinfo was part of proc.5 man page the indentation made > > sense. As a standalone man page the indentation doesn't need to be so > > far over to the right. > > > > Sign

[PATCH v2 3/3] proc_pid_fdinfo.5: Add DRM subsection

Add description of DRM fdinfo information based on the Linux kernel's `Documentation/gpu/drm-usage-stats.rst`: https://docs.kernel.org/gpu/drm-usage-stats.html Signed-off-by: Ian Rogers --- man/man5/proc_pid_fdinfo.5 | 94 ++ 1 file changed, 94 insertions(+)

[PATCH v2 1/3] proc_pid_fdinfo.5: Reduce indent for most of the page

When /proc/pid/fdinfo was part of proc.5 man page the indentation made sense. As a standalone man page the indentation doesn't need to be so far over to the right. Remove the initial tagged pragraph and move the styling to the initial summary description. Suggested-by: G. Branden Robinson Signed-

[PATCH v2 2/3] proc_pid_fdinfo.5: Add subsection headers for different fd types

Make the sections about eventfd, epoll, signalfd, inotify, fanotify, timerfd better separated with a clearer subsection header. Signed-off-by: Ian Rogers --- man/man5/proc_pid_fdinfo.5 | 6 ++ 1 file changed, 6 insertions(+) diff --git a/man/man5/proc_pid_fdinfo.5 b/man/man5/proc_pid_fdinfo

Re:Re:[PATCH v5] rockchip/drm: vop2: add support for gamma LUT

Hi Andy On Tuesday, October 15th, 2024 at 2:22 PM, Andy Yan wrote: > > > > + struct vop2_video_port *vp, > > > > + struct drm_crtc *crtc, > > > > + struct drm_crtc_state *crtc_state) > > > > +{ > > > > + > > > > + if (vop2->lut_regs && crtc_state->color_mgmt_changed) { > > > > + if (!crtc_state-

Re: [PATCH RFC 3/3] arm64: dts: qcom: x1e80100: Add ACD levels for GPU

On Mon, Oct 14, 2024 at 09:40:13AM +0200, Krzysztof Kozlowski wrote: > On Sat, Oct 12, 2024 at 01:59:30AM +0530, Akhil P Oommen wrote: > > Update GPU node to include acd level values. > > > > Signed-off-by: Akhil P Oommen > > --- > > arch/arm64/boot/dts/qcom/x1e80100.dtsi | 11 ++- > > 1

[PATCH v1 4/5] dmaengine: qcom: gpi: Add GPI Block event interrupt support

GSI hardware generates an interrupt for each transfer completion. For multiple messages within a single transfer, this results in receiving N interrupts for N messages, which can introduce significant software interrupt latency. To mitigate this latency, utilize Block Event Interrupt (BEI) only whe

[PATCH v1 3/5] dmaengine: qcom: gpi: Add provision to support TRE size as the fourth argument of dma-cells property

The current GPI driver hardcodes the channel TRE (Transfer Ring Element) size to 64. For scenarios requiring high performance with multiple messages in a transfer, use Block Event Interrupt (BEI). This method triggers interrupt after specific message transfers and the last message transfer, effecti

[PATCH v1 2/4] nouveau/dmem: HMM P2P DMA for private dev pages

From: Yonatan Maman Enabling Peer-to-Peer DMA (P2P DMA) access in GPU-centric applications is crucial for minimizing data transfer overhead (e.g., for RDMA use- case). This change aims to enable that capability for Nouveau over HMM device private pages. P2P DMA for private device pages allows th

[PATCH v1 0/5] Add Block event interrupt support for I2C protocol

The I2C driver gets an interrupt upon transfer completion. For multiple messages in a single transfer, N interrupts will be received for N messages, leading to significant software interrupt latency. To mitigate this latency, utilize Block Event Interrupt (BEI) only when an interrupt is necessary.

[PATCH v1 5/5] i2c: i2c-qcom-geni: Add Block event interrupt support

The I2C driver gets an interrupt upon transfer completion. For multiple messages in a single transfer, N interrupts will be received for N messages, leading to significant software interrupt latency. To mitigate this latency, utilize Block Event Interrupt (BEI) only when an interrupt is necessary.

[PATCH v1 3/4] IB/core: P2P DMA for device private pages

From: Yonatan Maman Add Peer-to-Peer (P2P) DMA request for hmm_range_fault calling, utilizing capabilities introduced in mm/hmm. By setting range.default_flags to HMM_PFN_REQ_FAULT | HMM_PFN_REQ_TRY_P2P, HMM attempts to initiate P2P DMA connections for device private pages (instead of page fault

[PATCH v1 4/4] RDMA/mlx5: Enabling ATS for ODP memory

From: Yonatan Maman ATS (Address Translation Services) mainly utilized to optimize PCI Peer-to-Peer transfers and prevent bus failures. This change employed ATS usage for ODP memory, to optimize DMA P2P for ODP memory. (e.g DMA P2P for private device pages - ODP memory). Signed-off-by: Yonatan M

[PATCH v1 1/5] dt-bindings: dmaengine: qcom: gpi: Add additional arg to dma-cell property

When high performance with multiple i2c messages in a single transfer is required, employ Block Event Interrupt (BEI) to trigger interrupts after specific messages transfer and the last message transfer, thereby reducing interrupts. For each i2c message transfer, a series of Transfer Request Eleme

[PATCH v1 1/4] mm/hmm: HMM API for P2P DMA to device zone pages

From: Yonatan Maman hmm_range_fault() natively triggers a page fault on device private pages, migrating them to RAM. In some cases, such as with RDMA devices, the migration overhead between the device (e.g., GPU) and the CPU, and vice-versa, significantly damages performance. Thus, enabling Peer-

[PATCH v1 2/5] arm64: dts: qcom: Add support for configuring channel TRE size

When high performance with multiple i2c messages in a single transfer is required, employ Block Event Interrupt (BEI) to trigger interrupts after specific messages transfer and the last message transfer, thereby reducing interrupts. For each i2c message transfer, a series of Transfer Request Elemen

[PATCH v1 0/4] GPU Direct RDMA (P2P DMA) for Device Private Pages

From: Yonatan Maman This patch series aims to enable Peer-to-Peer (P2P) DMA access in GPU-centric applications that utilize RDMA and private device pages. This enhancement is crucial for minimizing data transfer overhead by allowing the GPU to directly expose device private page data to devices s

Re: [PATCH v2] drm/panthor: Fix firmware initialization on systems with a page size > 4k

On Tue, Oct 15, 2024 at 09:03:51AM +0200, Boris Brezillon wrote: > Hi Liviu, > > On Tue, 15 Oct 2024 02:08:46 +0100 > Liviu Dudau wrote: > > > Hi Boris, > > > > I'm a bit confused, I thought the plan was to separate the FW_PAGE_SIZE > > from the rest of Panthor's PAGE_SIZE. > > > > On Mon, Oct

<    1   2