search for: required_fault

...ge_need_fault(const struct hmm_vma_walk *hmm_vma_walk, - const uint64_t *pfns, unsigned long npages, - uint64_t cpu_flags) + const unsigned long hmm_pfns[], unsigned long npages, + unsigned long cpu_flags) { struct hmm_range *range = hmm_vma_walk->range; unsigned int required_fault = 0; @@ -142,12 +129,12 @@ hmm_range_need_fault(const struct hmm_vma_walk *hmm_vma_walk, * hmm_pte_need_fault() will always return 0. */ if (!((range->default_flags | range->pfn_flags_mask) & - range->flags[HMM_PFN_VALID])) + HMM_PFN_REQ_FAULT)) return 0; for...

...ge_need_fault(const struct hmm_vma_walk *hmm_vma_walk, - const uint64_t *pfns, unsigned long npages, - uint64_t cpu_flags) + const unsigned long hmm_pfns[], unsigned long npages, + unsigned long cpu_flags) { struct hmm_range *range = hmm_vma_walk->range; unsigned int required_fault = 0; @@ -142,12 +129,12 @@ hmm_range_need_fault(const struct hmm_vma_walk *hmm_vma_walk, * hmm_pte_need_fault() will always return 0. */ if (!((range->default_flags | range->pfn_flags_mask) & - range->flags[HMM_PFN_VALID])) + HMM_PFN_REQ_FAULT)) return 0; for...

...walk *hmm_vma_walk, > - const uint64_t *pfns, unsigned long npages, > - uint64_t cpu_flags) > + const unsigned long hmm_pfns[], unsigned long npages, > + unsigned long cpu_flags) > { > struct hmm_range *range = hmm_vma_walk->range; > unsigned int required_fault = 0; > @@ -142,12 +129,12 @@ hmm_range_need_fault(const struct hmm_vma_walk *hmm_vma_walk, > * hmm_pte_need_fault() will always return 0. > */ > if (!((range->default_flags | range->pfn_flags_mask) & > - range->flags[HMM_PFN_VALID])) > + HMM_PFN_RE...

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

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

...e_t *pte, unsigned long hmask, i = (start - range->start) >> PAGE_SHIFT; pfn_req_flags = range->hmm_pfns[i]; cpu_flags = pte_to_hmm_pfn_flags(range, entry); + if (hshift >= PUD_SHIFT) + cpu_flags |= HMM_PFN_PUD; + else if (hshift >= PMD_SHIFT) + cpu_flags |= HMM_PFN_PMD; required_fault = hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, cpu_flags); if (required_fault) { -- 2.20.1

...ma(vma), walk->mm, pte); entry = huge_ptep_get(pte); i = (start - range->start) >> PAGE_SHIFT; pfn_req_flags = range->hmm_pfns[i]; - cpu_flags = pte_to_hmm_pfn_flags(range, entry); + cpu_flags = pte_to_hmm_pfn_flags(range, entry) | + (horder << HMM_PFN_ORDER_SHIFT); required_fault = hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, cpu_flags); if (required_fault) { -- 2.20.1

...e *range); /* * HMM_RANGE_DEFAULT_TIMEOUT - default timeout (ms) when waiting for a range diff --git a/mm/hmm.c b/mm/hmm.c index 280585833adfc1..4c7c396655b528 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -174,7 +174,6 @@ static int hmm_vma_walk_hole(unsigned long addr, unsigned long end, } if (required_fault) return hmm_vma_fault(addr, end, required_fault, walk); - hmm_vma_walk->last = addr; return hmm_pfns_fill(addr, end, range, HMM_PFN_NONE); } @@ -207,7 +206,6 @@ static int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr, pfn = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >>...

...e *range); /* * HMM_RANGE_DEFAULT_TIMEOUT - default timeout (ms) when waiting for a range diff --git a/mm/hmm.c b/mm/hmm.c index 280585833adfc1..f06bcac948a79b 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -174,7 +174,6 @@ static int hmm_vma_walk_hole(unsigned long addr, unsigned long end, } if (required_fault) return hmm_vma_fault(addr, end, required_fault, walk); - hmm_vma_walk->last = addr; return hmm_pfns_fill(addr, end, range, HMM_PFN_NONE); } @@ -207,7 +206,6 @@ static int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr, pfn = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >>...

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

...;< (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 hmm_vma_walk_hole(unsigned long addr, unsigned long end, > } > if (required_fault) > return hmm_vma_fault(addr, end, required_fault, walk); > - return hmm_pfns_fill(addr, end, range, HMM_PFN_NONE); > + return hmm_pfns_fill(addr, end, range, 0); > } > > -static inline uint64_t pmd_to_hmm_pfn_flags(struct hmm_range *range, pmd_t pmd) > +static inline...

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

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