search for: hmm_pfn_flags

...es changed, 33 insertions(+), 5 deletions(-) diff --git a/include/linux/hmm.h b/include/linux/hmm.h index f4a09ed223ac..e7a21a21f11f 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -37,16 +37,17 @@ * will fail. Must be combined with HMM_PFN_REQ_FAULT. */ enum hmm_pfn_flags { - /* Output flags */ + /* Output fields and flags */ HMM_PFN_VALID = 1UL << (BITS_PER_LONG - 1), HMM_PFN_WRITE = 1UL << (BITS_PER_LONG - 2), HMM_PFN_ERROR = 1UL << (BITS_PER_LONG - 3), + HMM_PFN_ORDER_SHIFT = (BITS_PER_LONG - 8), /* Input flags */ HMM_PFN_REQ_FAULT =...

...gt; --- include/linux/hmm.h | 4 +++- mm/hmm.c | 10 +++++++--- 2 files changed, 10 insertions(+), 4 deletions(-) diff --git a/include/linux/hmm.h b/include/linux/hmm.h index e912b9dc4633..f2d38af421e7 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -41,12 +41,14 @@ enum hmm_pfn_flags { HMM_PFN_VALID = 1UL << (BITS_PER_LONG - 1), HMM_PFN_WRITE = 1UL << (BITS_PER_LONG - 2), HMM_PFN_ERROR = 1UL << (BITS_PER_LONG - 3), + HMM_PFN_COMPOUND = 1UL << (BITS_PER_LONG - 4), /* Input flags */ HMM_PFN_REQ_FAULT = HMM_PFN_VALID, HMM_PFN_REQ_WRITE = HMM_P...

...gt; --- include/linux/hmm.h | 4 +++- mm/hmm.c | 10 +++++++--- 2 files changed, 10 insertions(+), 4 deletions(-) diff --git a/include/linux/hmm.h b/include/linux/hmm.h index f4a09ed223ac..d0db78025baa 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -41,12 +41,14 @@ enum hmm_pfn_flags { HMM_PFN_VALID = 1UL << (BITS_PER_LONG - 1), HMM_PFN_WRITE = 1UL << (BITS_PER_LONG - 2), HMM_PFN_ERROR = 1UL << (BITS_PER_LONG - 3), + HMM_PFN_COMPOUND = 1UL << (BITS_PER_LONG - 4), /* Input flags */ HMM_PFN_REQ_FAULT = HMM_PFN_VALID, HMM_PFN_REQ_WRITE = HMM_P...

...e page is at least of size + * PUD_SIZE and fully mapped by the CPU with consistent + * protection (e.g., all writeable if HMM_PFN_WRITE is set). * * On input: * 0 - Return the current state of the page, do not fault it. @@ -41,12 +47,15 @@ enum hmm_pfn_flags { HMM_PFN_VALID = 1UL << (BITS_PER_LONG - 1), HMM_PFN_WRITE = 1UL << (BITS_PER_LONG - 2), HMM_PFN_ERROR = 1UL << (BITS_PER_LONG - 3), + HMM_PFN_PMD = 1UL << (BITS_PER_LONG - 4), + HMM_PFN_PUD = 1UL << (BITS_PER_LONG - 5), /* Input flags */ HMM_PFN_REQ_FAULT...

...will fail > + * HMM_PFN_REQ_WRITE - The output must have HMM_PFN_WRITE or hmm_range_fault() > + * will fail. Must be combined with HMM_PFN_REQ_FAULT. > */ > -enum hmm_pfn_flag_e { > - HMM_PFN_VALID = 0, > - HMM_PFN_WRITE, > - HMM_PFN_FLAG_MAX > +enum hmm_pfn_flags { Let's add: /* Output flags: */ > + HMM_PFN_VALID = 1UL << (BITS_PER_LONG - 1), > + HMM_PFN_WRITE = 1UL << (BITS_PER_LONG - 2), > + HMM_PFN_ERROR = 1UL << (BITS_PER_LONG - 3), > + /* Input flags: */ ... > @@ -174,44 +162,44 @@ static int...

The goal for this series is to introduce the hmm_pfn_to_map_order() function. This allows a device driver to know that a given 4K PFN is actually mapped by the CPU using a larger sized CPU page table entry and therefore the device driver can safely map system memory using larger device MMU PTEs. The series is based on 5.8.0-rc3 and is intended for Jason Gunthorpe's hmm tree. These were

From: Yonatan Maman <Ymaman at Nvidia.com> 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 such as NICs, eliminating the need to traverse system RAM, which is the

The goal for this series is to introduce the hmm_range_fault() output array flags HMM_PFN_PMD and HMM_PFN_PUD. This allows a device driver to know that a given 4K PFN is actually mapped by the CPU using either a PMD sized or PUD sized CPU page table entry and therefore the device driver can safely map system memory using larger device MMU PTEs. The series is based on 5.8.0-rc3 and is intended for

...hmm_range_fault() + * will fail + * HMM_PFN_REQ_WRITE - The output must have HMM_PFN_WRITE or hmm_range_fault() + * will fail. Must be combined with HMM_PFN_REQ_FAULT. */ -enum hmm_pfn_flag_e { - HMM_PFN_VALID = 0, - HMM_PFN_WRITE, - HMM_PFN_FLAG_MAX +enum hmm_pfn_flags { + HMM_PFN_VALID = 1UL << (BITS_PER_LONG - 1), + HMM_PFN_WRITE = 1UL << (BITS_PER_LONG - 2), + HMM_PFN_ERROR = 1UL << (BITS_PER_LONG - 3), + + HMM_PFN_REQ_FAULT = HMM_PFN_VALID, + HMM_PFN_REQ_WRITE = HMM_PFN_WRITE, + + HMM_PFN_FLAGS = HMM_PFN_VALID | HMM_PFN_WRITE | HMM_PFN_ERROR...

...hmm_range_fault() + * will fail + * HMM_PFN_REQ_WRITE - The output must have HMM_PFN_WRITE or hmm_range_fault() + * will fail. Must be combined with HMM_PFN_REQ_FAULT. */ -enum hmm_pfn_flag_e { - HMM_PFN_VALID = 0, - HMM_PFN_WRITE, - HMM_PFN_FLAG_MAX +enum hmm_pfn_flags { + HMM_PFN_VALID = 1UL << (BITS_PER_LONG - 1), + HMM_PFN_WRITE = 1UL << (BITS_PER_LONG - 2), + HMM_PFN_ERROR = 1UL << (BITS_PER_LONG - 3), + + HMM_PFN_REQ_FAULT = HMM_PFN_VALID, + HMM_PFN_REQ_WRITE = HMM_PFN_WRITE, + + HMM_PFN_FLAGS = HMM_PFN_VALID | HMM_PFN_WRITE | HMM_PFN_ERROR...

...will fail > + * HMM_PFN_REQ_WRITE - The output must have HMM_PFN_WRITE or hmm_range_fault() > + * will fail. Must be combined with HMM_PFN_REQ_FAULT. > */ > -enum hmm_pfn_flag_e { > - HMM_PFN_VALID = 0, > - HMM_PFN_WRITE, > - HMM_PFN_FLAG_MAX > +enum hmm_pfn_flags { > + HMM_PFN_VALID = 1UL << (BITS_PER_LONG - 1), > + HMM_PFN_WRITE = 1UL << (BITS_PER_LONG - 2), > + HMM_PFN_ERROR = 1UL << (BITS_PER_LONG - 3), > + > + HMM_PFN_REQ_FAULT = HMM_PFN_VALID, > + HMM_PFN_REQ_WRITE = HMM_PFN_WRITE, > + > + HMM_PFN_FLAGS = HMM_P...

From: Jason Gunthorpe <jgg at mellanox.com> The API is a bit complicated for the uses we actually have, and disucssions for simplifying have come up a number of times. This small series removes the customizable pfn format and simplifies the return code of hmm_range_fault() All the drivers are adjusted to process in the simplified format. I would appreciated tested-by's for the two

hmm_range_fault() returns an array of page frame numbers and flags for how the pages are mapped in the requested process' page tables. The PFN can be used to get the struct page with hmm_pfn_to_page() and the page size order can be determined with compound_order(page) but if the page is larger than order 0 (PAGE_SIZE), there is no indication that the page is mapped using a larger page size. To

From: Jason Gunthorpe <jgg at mellanox.com> The API is a bit complicated for the uses we actually have, and disucssions for simplifying have come up a number of times. This small series removes the customizable pfn format and simplifies the return code of hmm_range_fault() All the drivers are adjusted to process in the simplified format. I would appreciated tested-by's for the two

These patches apply to linux-5.8.0-rc1. Patches 1-3 should probably go into 5.8, the others can be queued for 5.9. Patches 4-6 improve the HMM self tests. Patch 7-8 prepare nouveau for the meat of this series which adds support and testing for compound page mapping of system memory (patches 9-11) and compound page migration to device private memory (patches 12-16). Since these changes are split

From: Jérôme Glisse <jglisse at redhat.com> (mm is cced just to allow exposure of device driver work without ccing a long list of peoples. I do not think there is anything usefull to discuss from mm point of view but i might be wrong, so just for the curious :)). git://people.freedesktop.org/~glisse/linux branch: nouveau-hmm-v00