similar to: [bug report] drm/nouveau/imem: convert to new-style nvkm_subdev

From: Thierry Reding <treding at nvidia.com> Commit 12c9b05da918 ("drm/nouveau/imem: support allocations not preserved across suspend") uses container_of() to cast from struct nvkm_memory to struct nvkm_instobj, assuming that all instance objects are derived from struct nvkm_instobj. For the gk20a family that's not the case and they are derived from struct nvkm_memory instead.

On 08/12/2023 10:46, Thierry Reding wrote: > From: Thierry Reding <treding at nvidia.com> > > Commit 12c9b05da918 ("drm/nouveau/imem: support allocations not > preserved across suspend") uses container_of() to cast from struct > nvkm_memory to struct nvkm_instobj, assuming that all instance objects > are derived from struct nvkm_instobj. For the gk20a family

Commit be55287aa5b ("drm/nouveau/imem/nv50: embed nvkm_instobj directly into nv04_instobj") introduced some new calls to the refcount api to the nv50 mapping code. In one particular instance, it does the following: if (!refcount_inc_not_zero(&iobj->maps)) { ... refcount_inc(&iobj->maps); } i.e., it calls refcount_inc() to increment the

Hey Ard, It seems that Ben already committed a similar patch to his tree (see [0]). I do not know whether he is planning to have it part of a pull request of fixes for 4.15. Best regards, Pierre [0]: https://github.com/skeggsb/nouveau/commit/9068f1df2394f0e4ab2b2a28cac06b462fe0a0aa On 2017-12-18 — 09:27, Ard Biesheuvel wrote: > On 8 December 2017 at 19:30, Ard Biesheuvel <ard.biesheuvel

From: Thierry Reding <treding at nvidia.com> The gk20a implementation of instance memory uses vmap()/vunmap() to map memory regions into the kernel's virtual address space. These functions may sleep, so protecting them by a spin lock is not safe. This triggers a warning if the DEBUG_ATOMIC_SLEEP Kconfig option is enabled. Fix this by using a mutex instead. Signed-off-by: Thierry Reding

On 02/24/2017 01:20 AM, Thierry Reding wrote: > * PGP Signed by an unknown key > > On Mon, Jan 30, 2017 at 09:03:07PM +0100, Thierry Reding wrote: >> From: Thierry Reding <treding at nvidia.com> >> >> The gk20a implementation of instance memory uses vmap()/vunmap() to map >> memory regions into the kernel's virtual address space. These functions >>

Although I would not have expected this to happen, we seem to run into race conditions if instobjs are accessed concurrently. Use a global lock for safety. Signed-off-by: Alexandre Courbot <acourbot at nvidia.com> --- drm/nouveau/nvkm/subdev/instmem/gk20a.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) diff --git a/drm/nouveau/nvkm/subdev/instmem/gk20a.c

The LRU list used for recycling CPU mappings was handling concurrency very poorly. For instance, if an instobj was acquired twice before being released once, it would end up into the LRU list even though there is still a client accessing it. This patch fixes this by properly counting how many clients are currently using a given instobj. While at it, we also raise errors when inconsistencies are

Commit 69c4938249fb ("drm/nouveau/instmem/gk20a: use direct CPU access") tried to be smart while using the DMA-API by managing the CPU mappings of buffers allocated with the DMA-API by itself. In doing so, it relied on dma_to_phys() which is an architecture-private function not available everywhere. This broke the build on several architectures. Since there is no reliable and portable

On Tue, Dec 23, 2014 at 5:40 AM, Vince Hsu <vinceh at nvidia.com> wrote: > This is a workaround to avoid the instmem backup/restore during the suspend > and resume process in nv50 instemem driver. > > Signed-off-by: Vince Hsu <vinceh at nvidia.com> > --- > drm/Kbuild | 1 + > nvkm/engine/device/nve0.c | 2 +- >

From: Joerg Roedel <jroedel at suse.de> The map and unmap functions of the IOMMU-API changed their semantics: They do no longer guarantee that the hardware TLBs are synchronized with the page-table updates they made. To make conversion easier, new synchronized functions have been introduced which give these guarantees again until the code is converted to use the new TLB-flush interface of

On 8 December 2017 at 19:30, Ard Biesheuvel <ard.biesheuvel at linaro.org> wrote: > Commit be55287aa5b ("drm/nouveau/imem/nv50: embed nvkm_instobj directly > into nv04_instobj") introduced some new calls to the refcount api to > the nv50 mapping code. In one particular instance, it does the > following: > > if (!refcount_inc_not_zero(&iobj->maps)) {

When resuming from ACPI S3, memory leak happens in nvkm_ram_get(). This is because *pmemory points to newly allocated memory without checking and freeing the old memory. Here is the log showing this issue. unreferenced object 0xffffa3b608c6d5c0 (size 64): comm "kworker/u32:30", pid 934, jiffies 4294823520 (age 5000.217s) hex dump (first 32 bytes): 00 fc 4a c0 ff ff ff ff 00 00

These 4 patches fix two issues that existed on Tegra regarding DMA: 1) The bit indicating whether to use an IOMMU or not was hardcoded ; make this a platform property and use it in instmem 2) The DMA mask was not set for platform devices. Fix this by converting more pci_dma* to the DMA API, and use that more generic code to set the DMA mask properly for all platforms. Tested on both x86

The INA3221 is usually found on mid and high end kepler+ gpus Marins Patch implements the new iccsense subdev and all needed bits for the INA3221 power sensor. My Patch implements the hwmon power1 interface to expose the current power consumption through hwmon (and can be read out via sysfs or the sensors tool) Please test these patches for Fermi+ GPUs, that nothing gets messed up and works as

This is a complete rework from the first version I sent out. Now the implementation is more centered around the power_rails we find in the SENSE table instead of extdev centered. This makes the implementation a lot easier and straightforward. I've added support for the INA219, INA209 and INA3221 sensors found on multiple Fermi and Kepler cards. The power consumption is also exported via

This is a complete rework from the last version I sent out. Now the implementation is more centered around the power_rails we find in the SENSE table instead of extdev centered. This makes the implementation a lot easier and straightforward. I've added support for the INA219, INA209 and INA3221 sensors found on multiple Fermi and Kepler cards, but only the INA3221 bits are tested so far.

Hi, This is fourth approach for replacing struct dma_attrs with unsigned long. The main patch (1/44) doing the change is split into many subpatches for easier review (2-42). They should be squashed together when applying. *Important:* Patchset is tested on my ARM platforms and *only* build tested on allyesconfigs: ARM, ARM64, i386, x86_64 and powerpc. Please kindly provide reviewes and tests

This is a complete rework from the first version I sent out. Now the implementation is more centered around the power_rails we find in the SENSE table instead of extdev centered. This makes the implementation a lot easier and straightforward. I've added support for the INA219, INA209 and INA3221 sensors found on multiple Fermi and Kepler cards. The power consumption is also exported via

Signed-off-by: Ilia Mirkin <imirkin at alum.mit.edu> --- This was helpful when debugging our earlier mpeg woes. May as well have it upstream. drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv31.c | 7 ++++++- drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv40.c | 7 ++++++- 2 files changed, 12 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv31.c