From 1897bdc4d33167e9036460631d1349e59d841f2d Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 13 Nov 2014 13:46:09 +1100 Subject: mmu_notifier: add mmu_notifier_invalidate_range() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This notifier closes an important gap in the current mmu_notifier implementation, the existing callbacks are called too early or too late to reliably manage a non-CPU TLB. Specifically, invalidate_range_start() is called when all pages are still mapped and invalidate_range_end() when all pages are unmapped and potentially freed. This is fine when the users of the mmu_notifiers manage their own SoftTLB, like KVM does. When the TLB is managed in software it is easy to wipe out entries for a given range and prevent new entries to be established until invalidate_range_end is called. But when the user of mmu_notifiers has to manage a hardware TLB it can still wipe out TLB entries in invalidate_range_start, but it can't make sure that no new TLB entries in the given range are established between invalidate_range_start and invalidate_range_end. To avoid silent data corruption the entries in the non-CPU TLB need to be flushed when the pages are unmapped (at this point in time no _new_ TLB entries can be established in the non-CPU TLB) but not yet freed (as the non-CPU TLB may still have _existing_ entries pointing to the pages about to be freed). To fix this problem we need to catch the moment when the Linux VMM flushes remote TLBs (as a non-CPU TLB is not very CPU TLB), as this is the point in time when the pages are unmapped but _not_ yet freed. The mmu_notifier_invalidate_range() function aims to catch that moment. IOMMU code will be one user of the notifier-callback. Currently this is only the AMD IOMMUv2 driver, but its code is about to be more generalized and converted to a generic IOMMU-API extension to fit the needs of similar functionality in other IOMMUs as well. The current attempt in the AMD IOMMUv2 driver to work around the invalidate_range_start/end() shortcoming is to assign an empty page table to the non-CPU TLB between any invalidata_range_start/end calls. With the empty page-table assigned, every page-table walk to re-fill the non-CPU TLB will cause a page-fault reported to the IOMMU driver via an interrupt, possibly causing interrupt storms. The page-fault handler in the AMD IOMMUv2 driver doesn't handle the fault if an invalidate_range_start/end pair is active, it just reports back SUCCESS to the device and let it refault the page. But existing hardware (newer Radeon GPUs) that makes use of this feature don't re-fault indefinitly, after a certain number of faults for the same address the device enters a failure state and needs to be resetted. To avoid the GPUs entering a failure state we need to get rid of the empty-page-table workaround and use the mmu_notifier_invalidate_range() function introduced with this patch. Signed-off-by: Joerg Roedel Reviewed-by: Andrea Arcangeli Reviewed-by: Jérôme Glisse Cc: Peter Zijlstra Cc: Rik van Riel Cc: Hugh Dickins Cc: Mel Gorman Cc: Johannes Weiner Cc: Jay Cornwall Cc: Oded Gabbay Cc: Suravee Suthikulpanit Cc: Jesse Barnes Cc: David Woodhouse Signed-off-by: Andrew Morton Signed-off-by: Oded Gabbay --- include/linux/mmu_notifier.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 88787bb4b3b9..17907908d1df 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -242,6 +242,11 @@ static inline void mmu_notifier_invalidate_range_end(struct mm_struct *mm, __mmu_notifier_invalidate_range_end(mm, start, end); } +static inline void mmu_notifier_invalidate_range(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ +} + static inline void mmu_notifier_mm_init(struct mm_struct *mm) { mm->mmu_notifier_mm = NULL; @@ -342,6 +347,11 @@ static inline void mmu_notifier_invalidate_range_end(struct mm_struct *mm, { } +static inline void mmu_notifier_invalidate_range(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ +} + static inline void mmu_notifier_mm_init(struct mm_struct *mm) { } -- cgit v1.2.3-71-gd317 From 34ee645e83b60ae3d5955f70ab9ab9a159136673 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 13 Nov 2014 13:46:09 +1100 Subject: mmu_notifier: call mmu_notifier_invalidate_range() from VMM MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add calls to the new mmu_notifier_invalidate_range() function to all places in the VMM that need it. Signed-off-by: Joerg Roedel Reviewed-by: Andrea Arcangeli Reviewed-by: Jérôme Glisse Cc: Peter Zijlstra Cc: Rik van Riel Cc: Hugh Dickins Cc: Mel Gorman Cc: Johannes Weiner Cc: Jay Cornwall Cc: Oded Gabbay Cc: Suravee Suthikulpanit Cc: Jesse Barnes Cc: David Woodhouse Signed-off-by: Andrew Morton Signed-off-by: Oded Gabbay --- include/linux/mmu_notifier.h | 41 +++++++++++++++++++++++++++++++++++++++++ kernel/events/uprobes.c | 2 +- mm/fremap.c | 2 +- mm/huge_memory.c | 9 +++++---- mm/hugetlb.c | 7 ++++++- mm/ksm.c | 4 ++-- mm/memory.c | 3 ++- mm/migrate.c | 3 ++- mm/rmap.c | 2 +- 9 files changed, 61 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 17907908d1df..966da2b4b803 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -284,6 +284,44 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) __young; \ }) +#define ptep_clear_flush_notify(__vma, __address, __ptep) \ +({ \ + unsigned long ___addr = __address & PAGE_MASK; \ + struct mm_struct *___mm = (__vma)->vm_mm; \ + pte_t ___pte; \ + \ + ___pte = ptep_clear_flush(__vma, __address, __ptep); \ + mmu_notifier_invalidate_range(___mm, ___addr, \ + ___addr + PAGE_SIZE); \ + \ + ___pte; \ +}) + +#define pmdp_clear_flush_notify(__vma, __haddr, __pmd) \ +({ \ + unsigned long ___haddr = __haddr & HPAGE_PMD_MASK; \ + struct mm_struct *___mm = (__vma)->vm_mm; \ + pmd_t ___pmd; \ + \ + ___pmd = pmdp_clear_flush(__vma, __haddr, __pmd); \ + mmu_notifier_invalidate_range(___mm, ___haddr, \ + ___haddr + HPAGE_PMD_SIZE); \ + \ + ___pmd; \ +}) + +#define pmdp_get_and_clear_notify(__mm, __haddr, __pmd) \ +({ \ + unsigned long ___haddr = __haddr & HPAGE_PMD_MASK; \ + pmd_t ___pmd; \ + \ + ___pmd = pmdp_get_and_clear(__mm, __haddr, __pmd); \ + mmu_notifier_invalidate_range(__mm, ___haddr, \ + ___haddr + HPAGE_PMD_SIZE); \ + \ + ___pmd; \ +}) + /* * set_pte_at_notify() sets the pte _after_ running the notifier. * This is safe to start by updating the secondary MMUs, because the primary MMU @@ -362,6 +400,9 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) #define ptep_clear_flush_young_notify ptep_clear_flush_young #define pmdp_clear_flush_young_notify pmdp_clear_flush_young +#define ptep_clear_flush_notify ptep_clear_flush +#define pmdp_clear_flush_notify pmdp_clear_flush +#define pmdp_get_and_clear_notify pmdp_get_and_clear #define set_pte_at_notify set_pte_at #endif /* CONFIG_MMU_NOTIFIER */ diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 1d0af8a2c646..bc143cf56cab 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -193,7 +193,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, } flush_cache_page(vma, addr, pte_pfn(*ptep)); - ptep_clear_flush(vma, addr, ptep); + ptep_clear_flush_notify(vma, addr, ptep); set_pte_at_notify(mm, addr, ptep, mk_pte(kpage, vma->vm_page_prot)); page_remove_rmap(page); diff --git a/mm/fremap.c b/mm/fremap.c index 72b8fa361433..9129013732d7 100644 --- a/mm/fremap.c +++ b/mm/fremap.c @@ -37,7 +37,7 @@ static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma, if (pte_present(pte)) { flush_cache_page(vma, addr, pte_pfn(pte)); - pte = ptep_clear_flush(vma, addr, ptep); + pte = ptep_clear_flush_notify(vma, addr, ptep); page = vm_normal_page(vma, addr, pte); if (page) { if (pte_dirty(pte)) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index de984159cf0b..1d89526ed531 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1036,7 +1036,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, goto out_free_pages; VM_BUG_ON_PAGE(!PageHead(page), page); - pmdp_clear_flush(vma, haddr, pmd); + pmdp_clear_flush_notify(vma, haddr, pmd); /* leave pmd empty until pte is filled */ pgtable = pgtable_trans_huge_withdraw(mm, pmd); @@ -1179,7 +1179,7 @@ alloc: pmd_t entry; entry = mk_huge_pmd(new_page, vma->vm_page_prot); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); - pmdp_clear_flush(vma, haddr, pmd); + pmdp_clear_flush_notify(vma, haddr, pmd); page_add_new_anon_rmap(new_page, vma, haddr); mem_cgroup_commit_charge(new_page, memcg, false); lru_cache_add_active_or_unevictable(new_page, vma); @@ -1512,7 +1512,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, pmd_t entry; ret = 1; if (!prot_numa) { - entry = pmdp_get_and_clear(mm, addr, pmd); + entry = pmdp_get_and_clear_notify(mm, addr, pmd); if (pmd_numa(entry)) entry = pmd_mknonnuma(entry); entry = pmd_modify(entry, newprot); @@ -1644,6 +1644,7 @@ static int __split_huge_page_splitting(struct page *page, * serialize against split_huge_page*. */ pmdp_splitting_flush(vma, address, pmd); + ret = 1; spin_unlock(ptl); } @@ -2834,7 +2835,7 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, pmd_t _pmd; int i; - pmdp_clear_flush(vma, haddr, pmd); + pmdp_clear_flush_notify(vma, haddr, pmd); /* leave pmd empty until pte is filled */ pgtable = pgtable_trans_huge_withdraw(mm, pmd); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 9fd722769927..2e6add04fa1b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2598,8 +2598,11 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, } set_huge_pte_at(dst, addr, dst_pte, entry); } else { - if (cow) + if (cow) { huge_ptep_set_wrprotect(src, addr, src_pte); + mmu_notifier_invalidate_range(src, mmun_start, + mmun_end); + } entry = huge_ptep_get(src_pte); ptepage = pte_page(entry); get_page(ptepage); @@ -2899,6 +2902,7 @@ retry_avoidcopy: /* Break COW */ huge_ptep_clear_flush(vma, address, ptep); + mmu_notifier_invalidate_range(mm, mmun_start, mmun_end); set_huge_pte_at(mm, address, ptep, make_huge_pte(vma, new_page, 1)); page_remove_rmap(old_page); @@ -3374,6 +3378,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, * and that page table be reused and filled with junk. */ flush_tlb_range(vma, start, end); + mmu_notifier_invalidate_range(mm, start, end); mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex); mmu_notifier_invalidate_range_end(mm, start, end); diff --git a/mm/ksm.c b/mm/ksm.c index 6b2e337bc03c..d247efab5073 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -892,7 +892,7 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page, * this assure us that no O_DIRECT can happen after the check * or in the middle of the check. */ - entry = ptep_clear_flush(vma, addr, ptep); + entry = ptep_clear_flush_notify(vma, addr, ptep); /* * Check that no O_DIRECT or similar I/O is in progress on the * page @@ -960,7 +960,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, page_add_anon_rmap(kpage, vma, addr); flush_cache_page(vma, addr, pte_pfn(*ptep)); - ptep_clear_flush(vma, addr, ptep); + ptep_clear_flush_notify(vma, addr, ptep); set_pte_at_notify(mm, addr, ptep, mk_pte(kpage, vma->vm_page_prot)); page_remove_rmap(page); diff --git a/mm/memory.c b/mm/memory.c index 3e503831e042..655fd3d34bb0 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -238,6 +238,7 @@ static void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) { tlb->need_flush = 0; tlb_flush(tlb); + mmu_notifier_invalidate_range(tlb->mm, tlb->start, tlb->end); #ifdef CONFIG_HAVE_RCU_TABLE_FREE tlb_table_flush(tlb); #endif @@ -2234,7 +2235,7 @@ gotten: * seen in the presence of one thread doing SMC and another * thread doing COW. */ - ptep_clear_flush(vma, address, page_table); + ptep_clear_flush_notify(vma, address, page_table); page_add_new_anon_rmap(new_page, vma, address); mem_cgroup_commit_charge(new_page, memcg, false); lru_cache_add_active_or_unevictable(new_page, vma); diff --git a/mm/migrate.c b/mm/migrate.c index 01439953abf5..41945cb0ca38 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1854,7 +1854,7 @@ fail_putback: */ flush_cache_range(vma, mmun_start, mmun_end); page_add_anon_rmap(new_page, vma, mmun_start); - pmdp_clear_flush(vma, mmun_start, pmd); + pmdp_clear_flush_notify(vma, mmun_start, pmd); set_pmd_at(mm, mmun_start, pmd, entry); flush_tlb_range(vma, mmun_start, mmun_end); update_mmu_cache_pmd(vma, address, &entry); @@ -1862,6 +1862,7 @@ fail_putback: if (page_count(page) != 2) { set_pmd_at(mm, mmun_start, pmd, orig_entry); flush_tlb_range(vma, mmun_start, mmun_end); + mmu_notifier_invalidate_range(mm, mmun_start, mmun_end); update_mmu_cache_pmd(vma, address, &entry); page_remove_rmap(new_page); goto fail_putback; diff --git a/mm/rmap.c b/mm/rmap.c index 19886fb2f13a..d3eb1e02d1c6 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1378,7 +1378,7 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount, /* Nuke the page table entry. */ flush_cache_page(vma, address, pte_pfn(*pte)); - pteval = ptep_clear_flush(vma, address, pte); + pteval = ptep_clear_flush_notify(vma, address, pte); /* If nonlinear, store the file page offset in the pte. */ if (page->index != linear_page_index(vma, address)) { -- cgit v1.2.3-71-gd317 From 0f0a327fa12cd55de5e7f8c05a70ac3d047f405e Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 13 Nov 2014 13:46:09 +1100 Subject: mmu_notifier: add the callback for mmu_notifier_invalidate_range() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Now that the mmu_notifier_invalidate_range() calls are in place, add the callback to allow subsystems to register against it. Signed-off-by: Joerg Roedel Reviewed-by: Andrea Arcangeli Reviewed-by: Jérôme Glisse Cc: Peter Zijlstra Cc: Rik van Riel Cc: Hugh Dickins Cc: Mel Gorman Cc: Johannes Weiner Cc: Jay Cornwall Cc: Oded Gabbay Cc: Suravee Suthikulpanit Cc: Jesse Barnes Cc: David Woodhouse Signed-off-by: Andrew Morton Signed-off-by: Oded Gabbay --- include/linux/mmu_notifier.h | 37 ++++++++++++++++++++++++++++++++----- mm/mmu_notifier.c | 25 +++++++++++++++++++++++++ 2 files changed, 57 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 966da2b4b803..94d19f64cecf 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -98,11 +98,11 @@ struct mmu_notifier_ops { /* * invalidate_range_start() and invalidate_range_end() must be * paired and are called only when the mmap_sem and/or the - * locks protecting the reverse maps are held. The subsystem - * must guarantee that no additional references are taken to - * the pages in the range established between the call to - * invalidate_range_start() and the matching call to - * invalidate_range_end(). + * locks protecting the reverse maps are held. If the subsystem + * can't guarantee that no additional references are taken to + * the pages in the range, it has to implement the + * invalidate_range() notifier to remove any references taken + * after invalidate_range_start(). * * Invalidation of multiple concurrent ranges may be * optionally permitted by the driver. Either way the @@ -144,6 +144,29 @@ struct mmu_notifier_ops { void (*invalidate_range_end)(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long start, unsigned long end); + + /* + * invalidate_range() is either called between + * invalidate_range_start() and invalidate_range_end() when the + * VM has to free pages that where unmapped, but before the + * pages are actually freed, or outside of _start()/_end() when + * a (remote) TLB is necessary. + * + * If invalidate_range() is used to manage a non-CPU TLB with + * shared page-tables, it not necessary to implement the + * invalidate_range_start()/end() notifiers, as + * invalidate_range() alread catches the points in time when an + * external TLB range needs to be flushed. + * + * The invalidate_range() function is called under the ptl + * spin-lock and not allowed to sleep. + * + * Note that this function might be called with just a sub-range + * of what was passed to invalidate_range_start()/end(), if + * called between those functions. + */ + void (*invalidate_range)(struct mmu_notifier *mn, struct mm_struct *mm, + unsigned long start, unsigned long end); }; /* @@ -190,6 +213,8 @@ extern void __mmu_notifier_invalidate_range_start(struct mm_struct *mm, unsigned long start, unsigned long end); extern void __mmu_notifier_invalidate_range_end(struct mm_struct *mm, unsigned long start, unsigned long end); +extern void __mmu_notifier_invalidate_range(struct mm_struct *mm, + unsigned long start, unsigned long end); static inline void mmu_notifier_release(struct mm_struct *mm) { @@ -245,6 +270,8 @@ static inline void mmu_notifier_invalidate_range_end(struct mm_struct *mm, static inline void mmu_notifier_invalidate_range(struct mm_struct *mm, unsigned long start, unsigned long end) { + if (mm_has_notifiers(mm)) + __mmu_notifier_invalidate_range(mm, start, end); } static inline void mmu_notifier_mm_init(struct mm_struct *mm) diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index 2c8da9825fe3..3b9b3d0741b2 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -193,6 +193,16 @@ void __mmu_notifier_invalidate_range_end(struct mm_struct *mm, id = srcu_read_lock(&srcu); hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) { + /* + * Call invalidate_range here too to avoid the need for the + * subsystem of having to register an invalidate_range_end + * call-back when there is invalidate_range already. Usually a + * subsystem registers either invalidate_range_start()/end() or + * invalidate_range(), so this will be no additional overhead + * (besides the pointer check). + */ + if (mn->ops->invalidate_range) + mn->ops->invalidate_range(mn, mm, start, end); if (mn->ops->invalidate_range_end) mn->ops->invalidate_range_end(mn, mm, start, end); } @@ -200,6 +210,21 @@ void __mmu_notifier_invalidate_range_end(struct mm_struct *mm, } EXPORT_SYMBOL_GPL(__mmu_notifier_invalidate_range_end); +void __mmu_notifier_invalidate_range(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ + struct mmu_notifier *mn; + int id; + + id = srcu_read_lock(&srcu); + hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) { + if (mn->ops->invalidate_range) + mn->ops->invalidate_range(mn, mm, start, end); + } + srcu_read_unlock(&srcu, id); +} +EXPORT_SYMBOL_GPL(__mmu_notifier_invalidate_range); + static int do_mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm, int take_mmap_sem) -- cgit v1.2.3-71-gd317 From b7facbaec75a20f34c2065121dc423971682f922 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Wed, 16 Jul 2014 15:55:29 +0300 Subject: amdkfd: Add IOCTL set definitions of amdkfd - KFD_IOC_GET_VERSION: Retrieves the interface version of amdkfd - KFD_IOC_CREATE_QUEUE: Creates a usermode queue that runs on a specific GPU device - KFD_IOC_DESTROY_QUEUE: Destroys an existing usermode queue - KFD_IOC_SET_MEMORY_POLICY: Sets the memory policy of the default and alternate aperture of the calling process - KFD_IOC_GET_CLOCK_COUNTERS: Retrieves counters (timestamps) of CPU and GPU - KFD_IOC_GET_PROCESS_APERTURES: Retrieves information about process apertures that were initialized during the open() call of the amdkfd device - KFD_IOC_UPDATE_QUEUE: Updates configuration of an existing usermode queue v3: Remove pragma pack and pmc ioctls. Added parameter for doorbell offset and a comment on counters v5: Add define for AQL queues. Fix arguments of Get Version IOCTL Make IOCTL's structures to be the same size on 32/64 bit v6: Change the version of the amdkfd-thunk interface Signed-off-by: Oded Gabbay --- include/uapi/linux/kfd_ioctl.h | 154 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 154 insertions(+) create mode 100644 include/uapi/linux/kfd_ioctl.h (limited to 'include') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h new file mode 100644 index 000000000000..7acef41fc209 --- /dev/null +++ b/include/uapi/linux/kfd_ioctl.h @@ -0,0 +1,154 @@ +/* + * Copyright 2014 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +#ifndef KFD_IOCTL_H_INCLUDED +#define KFD_IOCTL_H_INCLUDED + +#include +#include + +#define KFD_IOCTL_MAJOR_VERSION 1 +#define KFD_IOCTL_MINOR_VERSION 0 + +struct kfd_ioctl_get_version_args { + uint32_t major_version; /* from KFD */ + uint32_t minor_version; /* from KFD */ +}; + +/* For kfd_ioctl_create_queue_args.queue_type. */ +#define KFD_IOC_QUEUE_TYPE_COMPUTE 0 +#define KFD_IOC_QUEUE_TYPE_SDMA 1 +#define KFD_IOC_QUEUE_TYPE_COMPUTE_AQL 2 + +#define KFD_MAX_QUEUE_PERCENTAGE 100 +#define KFD_MAX_QUEUE_PRIORITY 15 + +struct kfd_ioctl_create_queue_args { + uint64_t ring_base_address; /* to KFD */ + uint64_t write_pointer_address; /* from KFD */ + uint64_t read_pointer_address; /* from KFD */ + uint64_t doorbell_offset; /* from KFD */ + + uint32_t ring_size; /* to KFD */ + uint32_t gpu_id; /* to KFD */ + uint32_t queue_type; /* to KFD */ + uint32_t queue_percentage; /* to KFD */ + uint32_t queue_priority; /* to KFD */ + uint32_t queue_id; /* from KFD */ + + uint64_t eop_buffer_address; /* to KFD */ + uint64_t eop_buffer_size; /* to KFD */ + uint64_t ctx_save_restore_address; /* to KFD */ + uint64_t ctx_save_restore_size; /* to KFD */ +}; + +struct kfd_ioctl_destroy_queue_args { + uint32_t queue_id; /* to KFD */ + uint32_t pad; +}; + +struct kfd_ioctl_update_queue_args { + uint64_t ring_base_address; /* to KFD */ + + uint32_t queue_id; /* to KFD */ + uint32_t ring_size; /* to KFD */ + uint32_t queue_percentage; /* to KFD */ + uint32_t queue_priority; /* to KFD */ +}; + +/* For kfd_ioctl_set_memory_policy_args.default_policy and alternate_policy */ +#define KFD_IOC_CACHE_POLICY_COHERENT 0 +#define KFD_IOC_CACHE_POLICY_NONCOHERENT 1 + +struct kfd_ioctl_set_memory_policy_args { + uint64_t alternate_aperture_base; /* to KFD */ + uint64_t alternate_aperture_size; /* to KFD */ + + uint32_t gpu_id; /* to KFD */ + uint32_t default_policy; /* to KFD */ + uint32_t alternate_policy; /* to KFD */ + uint32_t pad; +}; + +/* + * All counters are monotonic. They are used for profiling of compute jobs. + * The profiling is done by userspace. + * + * In case of GPU reset, the counter should not be affected. + */ + +struct kfd_ioctl_get_clock_counters_args { + uint64_t gpu_clock_counter; /* from KFD */ + uint64_t cpu_clock_counter; /* from KFD */ + uint64_t system_clock_counter; /* from KFD */ + uint64_t system_clock_freq; /* from KFD */ + + uint32_t gpu_id; /* to KFD */ + uint32_t pad; +}; + +#define NUM_OF_SUPPORTED_GPUS 7 + +struct kfd_process_device_apertures { + uint64_t lds_base; /* from KFD */ + uint64_t lds_limit; /* from KFD */ + uint64_t scratch_base; /* from KFD */ + uint64_t scratch_limit; /* from KFD */ + uint64_t gpuvm_base; /* from KFD */ + uint64_t gpuvm_limit; /* from KFD */ + uint32_t gpu_id; /* from KFD */ + uint32_t pad; +}; + +struct kfd_ioctl_get_process_apertures_args { + struct kfd_process_device_apertures + process_apertures[NUM_OF_SUPPORTED_GPUS];/* from KFD */ + + /* from KFD, should be in the range [1 - NUM_OF_SUPPORTED_GPUS] */ + uint32_t num_of_nodes; + uint32_t pad; +}; + +#define KFD_IOC_MAGIC 'K' + +#define KFD_IOC_GET_VERSION \ + _IOR(KFD_IOC_MAGIC, 1, struct kfd_ioctl_get_version_args) + +#define KFD_IOC_CREATE_QUEUE \ + _IOWR(KFD_IOC_MAGIC, 2, struct kfd_ioctl_create_queue_args) + +#define KFD_IOC_DESTROY_QUEUE \ + _IOWR(KFD_IOC_MAGIC, 3, struct kfd_ioctl_destroy_queue_args) + +#define KFD_IOC_SET_MEMORY_POLICY \ + _IOW(KFD_IOC_MAGIC, 4, struct kfd_ioctl_set_memory_policy_args) + +#define KFD_IOC_GET_CLOCK_COUNTERS \ + _IOWR(KFD_IOC_MAGIC, 5, struct kfd_ioctl_get_clock_counters_args) + +#define KFD_IOC_GET_PROCESS_APERTURES \ + _IOR(KFD_IOC_MAGIC, 6, struct kfd_ioctl_get_process_apertures_args) + +#define KFD_IOC_UPDATE_QUEUE \ + _IOW(KFD_IOC_MAGIC, 7, struct kfd_ioctl_update_queue_args) + +#endif -- cgit v1.2.3-71-gd317 From 72bbf0af0c76cbefe9cecbd2ed670b7555e03625 Mon Sep 17 00:00:00 2001 From: Damien Lespiau Date: Wed, 13 Feb 2013 15:27:37 +0000 Subject: drm/i915/skl: Add the Skylake PCI ids v2: Squash in 2nd patch from Damien for more ids (Daniel) v3: info->has*ring -> info->ring_mask conversion. Also add VEBOX support. v4: Fold in update from Damien v5: Rebase and add GEN_DEFAULT_PIPEOFFSETS v6: Add more PCI ID (Vandana) v7: Rebase and add IVB_CURSOR_OFFSETS v8: Renamed the macro from _PCI_IDS to _IDS for consistency Reviewed-by: Thomas Wood Signed-off-by: Damien Lespiau Signed-off-by: Vandana Kannan Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_drv.c | 14 +++++++++++++- include/drm/i915_pciids.h | 17 +++++++++++++++++ 2 files changed, 30 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 3870c7359a16..bec58e86bd49 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -356,6 +356,17 @@ static const struct intel_device_info intel_cherryview_info = { CURSOR_OFFSETS, }; +static const struct intel_device_info intel_skylake_info = { + .is_preliminary = 1, + .gen = 9, .num_pipes = 3, + .need_gfx_hws = 1, .has_hotplug = 1, + .ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING, + .has_llc = 1, + .has_ddi = 1, + GEN_DEFAULT_PIPEOFFSETS, + IVB_CURSOR_OFFSETS, +}; + /* * Make sure any device matches here are from most specific to most * general. For example, since the Quanta match is based on the subsystem @@ -392,7 +403,8 @@ static const struct intel_device_info intel_cherryview_info = { INTEL_BDW_GT12D_IDS(&intel_broadwell_d_info), \ INTEL_BDW_GT3M_IDS(&intel_broadwell_gt3m_info), \ INTEL_BDW_GT3D_IDS(&intel_broadwell_gt3d_info), \ - INTEL_CHV_IDS(&intel_cherryview_info) + INTEL_CHV_IDS(&intel_cherryview_info), \ + INTEL_SKL_IDS(&intel_skylake_info) static const struct pci_device_id pciidlist[] = { /* aka */ INTEL_PCI_IDS, diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h index a70d45647898..180ad0e6de21 100644 --- a/include/drm/i915_pciids.h +++ b/include/drm/i915_pciids.h @@ -259,4 +259,21 @@ INTEL_VGA_DEVICE(0x22b2, info), \ INTEL_VGA_DEVICE(0x22b3, info) +#define INTEL_SKL_IDS(info) \ + INTEL_VGA_DEVICE(0x1916, info), /* ULT GT2 */ \ + INTEL_VGA_DEVICE(0x1906, info), /* ULT GT1 */ \ + INTEL_VGA_DEVICE(0x1926, info), /* ULT GT3 */ \ + INTEL_VGA_DEVICE(0x1921, info), /* ULT GT2F */ \ + INTEL_VGA_DEVICE(0x190E, info), /* ULX GT1 */ \ + INTEL_VGA_DEVICE(0x191E, info), /* ULX GT2 */ \ + INTEL_VGA_DEVICE(0x1912, info), /* DT GT2 */ \ + INTEL_VGA_DEVICE(0x1902, info), /* DT GT1 */ \ + INTEL_VGA_DEVICE(0x191B, info), /* Halo GT2 */ \ + INTEL_VGA_DEVICE(0x192B, info), /* Halo GT3 */ \ + INTEL_VGA_DEVICE(0x190B, info), /* Halo GT1 */ \ + INTEL_VGA_DEVICE(0x191A, info), /* SRV GT2 */ \ + INTEL_VGA_DEVICE(0x192A, info), /* SRV GT3 */ \ + INTEL_VGA_DEVICE(0x190A, info), /* SRV GT1 */ \ + INTEL_VGA_DEVICE(0x191D, info) /* WKS GT2 */ + #endif /* _I915_PCIIDS_H */ -- cgit v1.2.3-71-gd317 From ad9dc91b6e21266bfc6f466db4b95e10211f31ee Mon Sep 17 00:00:00 2001 From: Rodrigo Vivi Date: Tue, 16 Sep 2014 19:18:12 -0400 Subject: drm/i915: Fix Sink CRC In some cases like when PSR just got enabled the panel need more vblank times to calculate CRC. I figured that out with the new PSR test cases facing some cases that I had a green screen but a blank CRC. Even with 2 vblank waits on kernel + 2 vblank waits on test case. So let's give up to 6 vblank wait time. However we now check for TEST_CRC_COUNT that shows when panel finished to calculate CRC and has it ready. v2: Jani pointed out attempts decrements was wrong and should never reach the error condition. And Daniel pointed out that EIO is more appropriated than EGAIN. Also I realized that I have to read test_crc_count after setting test_sink v3: Rebase and adding error message Cc: Todd Previte Cc: Daniel Vetter Cc: Jani Nikula Signed-off-by: Rodrigo Vivi Reviewed-by: Todd Previte Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/intel_dp.c | 23 +++++++++++++++++------ include/drm/drm_dp_helper.h | 5 +++-- 2 files changed, 20 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 6f42d9568049..3caac0f01265 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -3807,21 +3807,32 @@ int intel_dp_sink_crc(struct intel_dp *intel_dp, u8 *crc) struct drm_device *dev = intel_dig_port->base.base.dev; struct intel_crtc *intel_crtc = to_intel_crtc(intel_dig_port->base.base.crtc); - u8 buf[1]; + u8 buf; + int test_crc_count; + int attempts = 6; - if (drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_SINK_MISC, buf) < 0) + if (drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_SINK_MISC, &buf) < 0) return -EIO; - if (!(buf[0] & DP_TEST_CRC_SUPPORTED)) + if (!(buf & DP_TEST_CRC_SUPPORTED)) return -ENOTTY; if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_TEST_SINK, DP_TEST_SINK_START) < 0) return -EIO; - /* Wait 2 vblanks to be sure we will have the correct CRC value */ - intel_wait_for_vblank(dev, intel_crtc->pipe); - intel_wait_for_vblank(dev, intel_crtc->pipe); + drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_SINK_MISC, &buf); + test_crc_count = buf & DP_TEST_COUNT_MASK; + + do { + drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_SINK_MISC, &buf); + intel_wait_for_vblank(dev, intel_crtc->pipe); + } while (--attempts && (buf & DP_TEST_COUNT_MASK) == test_crc_count); + + if (attempts == 0) { + DRM_ERROR("Panel is unable to calculate CRC after 6 vblanks\n"); + return -EIO; + } if (drm_dp_dpcd_read(&intel_dp->aux, DP_TEST_CRC_R_CR, crc, 6) < 0) return -EIO; diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index 9305c718d789..8edeed00c082 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -303,7 +303,8 @@ #define DP_TEST_CRC_B_CB 0x244 #define DP_TEST_SINK_MISC 0x246 -#define DP_TEST_CRC_SUPPORTED (1 << 5) +# define DP_TEST_CRC_SUPPORTED (1 << 5) +# define DP_TEST_COUNT_MASK 0x7 #define DP_TEST_RESPONSE 0x260 # define DP_TEST_ACK (1 << 0) @@ -313,7 +314,7 @@ #define DP_TEST_EDID_CHECKSUM 0x261 #define DP_TEST_SINK 0x270 -#define DP_TEST_SINK_START (1 << 0) +# define DP_TEST_SINK_START (1 << 0) #define DP_PAYLOAD_TABLE_UPDATE_STATUS 0x2c0 /* 1.2 MST */ # define DP_PAYLOAD_TABLE_UPDATED (1 << 0) -- cgit v1.2.3-71-gd317 From a1f1a79c51fd493887bb66d932ee66a23f8b1527 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Sat, 11 Oct 2014 22:08:57 -0700 Subject: drm: drm_err: Remove unnecessary __func__ argument Removing the unnecessary drm_err __func__ argument by using the equivalent %pf and __builtin_return_address(0) makes the code smaller for every use of the DRM_ERROR macro. For instance: (allmodconfig) $ size drivers/gpu/drm/i915/i915.o* text data bss dec hex filename 922447 193257 296736 1412440 158d58 drivers/gpu/drm/i915/i915.o.new 928111 193257 296736 1418104 15a378 drivers/gpu/drm/i915/i915.o.old Signed-off-by: Joe Perches Signed-off-by: Daniel Vetter --- drivers/gpu/drm/drm_drv.c | 5 +++-- include/drm/drmP.h | 8 ++++---- 2 files changed, 7 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c index bc3da32d4585..2e5c7d941313 100644 --- a/drivers/gpu/drm/drm_drv.c +++ b/drivers/gpu/drm/drm_drv.c @@ -56,7 +56,7 @@ static struct idr drm_minors_idr; struct class *drm_class; static struct dentry *drm_debugfs_root; -void drm_err(const char *func, const char *format, ...) +void drm_err(const char *format, ...) { struct va_format vaf; va_list args; @@ -66,7 +66,8 @@ void drm_err(const char *func, const char *format, ...) vaf.fmt = format; vaf.va = &args; - printk(KERN_ERR "[" DRM_NAME ":%s] *ERROR* %pV", func, &vaf); + printk(KERN_ERR "[" DRM_NAME ":%pf] *ERROR* %pV", + __builtin_return_address(0), &vaf); va_end(args); } diff --git a/include/drm/drmP.h b/include/drm/drmP.h index 53ed87698a74..d7ebd7b207e3 100644 --- a/include/drm/drmP.h +++ b/include/drm/drmP.h @@ -125,8 +125,8 @@ struct dma_buf_attachment; extern __printf(2, 3) void drm_ut_debug_printk(const char *function_name, const char *format, ...); -extern __printf(2, 3) -void drm_err(const char *func, const char *format, ...); +extern __printf(1, 2) +void drm_err(const char *format, ...); /***********************************************************************/ /** \name DRM template customization defaults */ @@ -155,7 +155,7 @@ void drm_err(const char *func, const char *format, ...); * \param arg arguments */ #define DRM_ERROR(fmt, ...) \ - drm_err(__func__, fmt, ##__VA_ARGS__) + drm_err(fmt, ##__VA_ARGS__) /** * Rate limited error output. Like DRM_ERROR() but won't flood the log. @@ -170,7 +170,7 @@ void drm_err(const char *func, const char *format, ...); DEFAULT_RATELIMIT_BURST); \ \ if (__ratelimit(&_rs)) \ - drm_err(__func__, fmt, ##__VA_ARGS__); \ + drm_err(fmt, ##__VA_ARGS__); \ }) #define DRM_INFO(fmt, ...) \ -- cgit v1.2.3-71-gd317 From 32197aab0425dbecc38462a91bc5c8acf70b2036 Mon Sep 17 00:00:00 2001 From: Masanari Iida Date: Mon, 20 Oct 2014 23:53:13 +0900 Subject: gpu:drm: Fix typo in Documentation/DocBook/drm.xml This patch fix spelling typos found in drm.xml. It is because the file is generated from comments in source codes, I have to fix the typos within source files. Signed-off-by: Masanari Iida Acked-by: Randy Dunlap Signed-off-by: Daniel Vetter --- drivers/gpu/drm/drm_crtc.c | 2 +- drivers/gpu/drm/drm_irq.c | 4 ++-- drivers/gpu/drm/drm_modes.c | 2 +- drivers/gpu/drm/drm_prime.c | 4 ++-- drivers/gpu/drm/i915/i915_cmd_parser.c | 4 ++-- drivers/gpu/drm/i915/i915_reg.h | 2 +- drivers/gpu/drm/i915/intel_lrc.c | 2 +- include/drm/drm_dp_mst_helper.h | 2 +- 8 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index e79c8d3700d8..7f94989e6fc9 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -3611,7 +3611,7 @@ static struct drm_property *property_create_range(struct drm_device *dev, * object with drm_object_attach_property. The returned property object must be * freed with drm_property_destroy. * - * Userspace is allowed to set any interger value in the (min, max) range + * Userspace is allowed to set any integer value in the (min, max) range * inclusive. * * Returns: diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c index 5ef03c216a27..3e6b582f60dd 100644 --- a/drivers/gpu/drm/drm_irq.c +++ b/drivers/gpu/drm/drm_irq.c @@ -1190,7 +1190,7 @@ EXPORT_SYMBOL(drm_crtc_vblank_off); * * This functions restores the vblank interrupt state captured with * drm_vblank_off() again. Note that calls to drm_vblank_on() and - * drm_vblank_off() can be unbalanced and so can also be unconditionaly called + * drm_vblank_off() can be unbalanced and so can also be unconditionally called * in driver load code to reflect the current hardware state of the crtc. * * This is the legacy version of drm_crtc_vblank_on(). @@ -1237,7 +1237,7 @@ EXPORT_SYMBOL(drm_vblank_on); * * This functions restores the vblank interrupt state captured with * drm_vblank_off() again. Note that calls to drm_vblank_on() and - * drm_vblank_off() can be unbalanced and so can also be unconditionaly called + * drm_vblank_off() can be unbalanced and so can also be unconditionally called * in driver load code to reflect the current hardware state of the crtc. * * This is the native kms version of drm_vblank_on(). diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c index d1b7d2006529..6d8b941c8200 100644 --- a/drivers/gpu/drm/drm_modes.c +++ b/drivers/gpu/drm/drm_modes.c @@ -914,7 +914,7 @@ EXPORT_SYMBOL(drm_mode_equal_no_clocks_no_stereo); * * This function is a helper which can be used to validate modes against size * limitations of the DRM device/connector. If a mode is too big its status - * memeber is updated with the appropriate validation failure code. The list + * member is updated with the appropriate validation failure code. The list * itself is not changed. */ void drm_mode_validate_size(struct drm_device *dev, diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 78ca30808422..6872eca6555e 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -328,7 +328,7 @@ static const struct dma_buf_ops drm_gem_prime_dmabuf_ops = { */ /** - * drm_gem_prime_export - helper library implemention of the export callback + * drm_gem_prime_export - helper library implementation of the export callback * @dev: drm_device to export from * @obj: GEM object to export * @flags: flags like DRM_CLOEXEC @@ -483,7 +483,7 @@ out_unlock: EXPORT_SYMBOL(drm_gem_prime_handle_to_fd); /** - * drm_gem_prime_import - helper library implemention of the import callback + * drm_gem_prime_import - helper library implementation of the import callback * @dev: drm_device to import into * @dma_buf: dma-buf object to import * diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index c45856bcc8b9..5506242ee766 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -73,7 +73,7 @@ * those commands required by the parser. This generally works because command * opcode ranges have standard command length encodings. So for commands that * the parser does not need to check, it can easily skip them. This is - * implementated via a per-ring length decoding vfunc. + * implemented via a per-ring length decoding vfunc. * * Unfortunately, there are a number of commands that do not follow the standard * length encoding for their opcode range, primarily amongst the MI_* commands. @@ -836,7 +836,7 @@ finish: * @ring: the ring in question * * Only certain platforms require software batch buffer command parsing, and - * only when enabled via module paramter. + * only when enabled via module parameter. * * Return: true if the ring requires software command parsing */ diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index b65bdfc23ccb..65821bad3f6a 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -664,7 +664,7 @@ enum punit_power_well { * need to be accessed during AUX communication, * * Generally the common lane corresponds to the pipe and - * the spline (PCS/TX) correponds to the port. + * the spline (PCS/TX) corresponds to the port. * * For dual channel PHY (VLV/CHV): * diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index bd1b28d99920..b7b9a097c213 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -1639,7 +1639,7 @@ static uint32_t get_lr_context_size(struct intel_engine_cs *ring) * the creation is a deferred call: it's better to make sure first that we need to use * a given ring with the context. * - * Return: non-zero on eror. + * Return: non-zero on error. */ int intel_lr_context_deferred_create(struct intel_context *ctx, struct intel_engine_cs *ring) diff --git a/include/drm/drm_dp_mst_helper.h b/include/drm/drm_dp_mst_helper.h index 9b446ada2532..3ecfcc143bdd 100644 --- a/include/drm/drm_dp_mst_helper.h +++ b/include/drm/drm_dp_mst_helper.h @@ -28,7 +28,7 @@ struct drm_dp_mst_branch; /** - * struct drm_dp_vcpi - Virtual Channel Payload Identifer + * struct drm_dp_vcpi - Virtual Channel Payload Identifier * @vcpi: Virtual channel ID. * @pbn: Payload Bandwidth Number for this channel * @aligned_pbn: PBN aligned with slot size -- cgit v1.2.3-71-gd317 From e45708976aea3a3c3aa959e3cc2b703fefbd758a Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 22 Oct 2014 11:16:36 +0200 Subject: drm/dp-helper: Move the legacy helpers to gma500 Except for gma500 all drivers are converted to the new style helpers, which have much better abstraction of the underlying hw protocols and already much more helper functions (including the entire mst library) on top of them. Since no one seems to work on converting gma500 let's just move the code away so that new drivers don't end up accidentally using this. Cc: Patrik Jakobsson Reviewed-by: Patrik Jakobsson Reviewed-by: Alan Cox [danvet: Add __deprecated as requested by Alan. Also add a short FIXME comment and drop the EXPORT_SYMBOL which is no longer needed.] Signed-off-by: Daniel Vetter --- drivers/gpu/drm/drm_dp_helper.c | 192 --------------------------------- drivers/gpu/drm/gma500/cdv_intel_dp.c | 195 ++++++++++++++++++++++++++++++++++ include/drm/drm_dp_helper.h | 20 ---- 3 files changed, 195 insertions(+), 212 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c index 08e33b8b13a4..c088bad7e72f 100644 --- a/drivers/gpu/drm/drm_dp_helper.c +++ b/drivers/gpu/drm/drm_dp_helper.c @@ -39,198 +39,6 @@ * blocks, ... */ -/* Run a single AUX_CH I2C transaction, writing/reading data as necessary */ -static int -i2c_algo_dp_aux_transaction(struct i2c_adapter *adapter, int mode, - uint8_t write_byte, uint8_t *read_byte) -{ - struct i2c_algo_dp_aux_data *algo_data = adapter->algo_data; - int ret; - - ret = (*algo_data->aux_ch)(adapter, mode, - write_byte, read_byte); - return ret; -} - -/* - * I2C over AUX CH - */ - -/* - * Send the address. If the I2C link is running, this 'restarts' - * the connection with the new address, this is used for doing - * a write followed by a read (as needed for DDC) - */ -static int -i2c_algo_dp_aux_address(struct i2c_adapter *adapter, u16 address, bool reading) -{ - struct i2c_algo_dp_aux_data *algo_data = adapter->algo_data; - int mode = MODE_I2C_START; - int ret; - - if (reading) - mode |= MODE_I2C_READ; - else - mode |= MODE_I2C_WRITE; - algo_data->address = address; - algo_data->running = true; - ret = i2c_algo_dp_aux_transaction(adapter, mode, 0, NULL); - return ret; -} - -/* - * Stop the I2C transaction. This closes out the link, sending - * a bare address packet with the MOT bit turned off - */ -static void -i2c_algo_dp_aux_stop(struct i2c_adapter *adapter, bool reading) -{ - struct i2c_algo_dp_aux_data *algo_data = adapter->algo_data; - int mode = MODE_I2C_STOP; - - if (reading) - mode |= MODE_I2C_READ; - else - mode |= MODE_I2C_WRITE; - if (algo_data->running) { - (void) i2c_algo_dp_aux_transaction(adapter, mode, 0, NULL); - algo_data->running = false; - } -} - -/* - * Write a single byte to the current I2C address, the - * the I2C link must be running or this returns -EIO - */ -static int -i2c_algo_dp_aux_put_byte(struct i2c_adapter *adapter, u8 byte) -{ - struct i2c_algo_dp_aux_data *algo_data = adapter->algo_data; - int ret; - - if (!algo_data->running) - return -EIO; - - ret = i2c_algo_dp_aux_transaction(adapter, MODE_I2C_WRITE, byte, NULL); - return ret; -} - -/* - * Read a single byte from the current I2C address, the - * I2C link must be running or this returns -EIO - */ -static int -i2c_algo_dp_aux_get_byte(struct i2c_adapter *adapter, u8 *byte_ret) -{ - struct i2c_algo_dp_aux_data *algo_data = adapter->algo_data; - int ret; - - if (!algo_data->running) - return -EIO; - - ret = i2c_algo_dp_aux_transaction(adapter, MODE_I2C_READ, 0, byte_ret); - return ret; -} - -static int -i2c_algo_dp_aux_xfer(struct i2c_adapter *adapter, - struct i2c_msg *msgs, - int num) -{ - int ret = 0; - bool reading = false; - int m; - int b; - - for (m = 0; m < num; m++) { - u16 len = msgs[m].len; - u8 *buf = msgs[m].buf; - reading = (msgs[m].flags & I2C_M_RD) != 0; - ret = i2c_algo_dp_aux_address(adapter, msgs[m].addr, reading); - if (ret < 0) - break; - if (reading) { - for (b = 0; b < len; b++) { - ret = i2c_algo_dp_aux_get_byte(adapter, &buf[b]); - if (ret < 0) - break; - } - } else { - for (b = 0; b < len; b++) { - ret = i2c_algo_dp_aux_put_byte(adapter, buf[b]); - if (ret < 0) - break; - } - } - if (ret < 0) - break; - } - if (ret >= 0) - ret = num; - i2c_algo_dp_aux_stop(adapter, reading); - DRM_DEBUG_KMS("dp_aux_xfer return %d\n", ret); - return ret; -} - -static u32 -i2c_algo_dp_aux_functionality(struct i2c_adapter *adapter) -{ - return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL | - I2C_FUNC_SMBUS_READ_BLOCK_DATA | - I2C_FUNC_SMBUS_BLOCK_PROC_CALL | - I2C_FUNC_10BIT_ADDR; -} - -static const struct i2c_algorithm i2c_dp_aux_algo = { - .master_xfer = i2c_algo_dp_aux_xfer, - .functionality = i2c_algo_dp_aux_functionality, -}; - -static void -i2c_dp_aux_reset_bus(struct i2c_adapter *adapter) -{ - (void) i2c_algo_dp_aux_address(adapter, 0, false); - (void) i2c_algo_dp_aux_stop(adapter, false); -} - -static int -i2c_dp_aux_prepare_bus(struct i2c_adapter *adapter) -{ - adapter->algo = &i2c_dp_aux_algo; - adapter->retries = 3; - i2c_dp_aux_reset_bus(adapter); - return 0; -} - -/** - * i2c_dp_aux_add_bus() - register an i2c adapter using the aux ch helper - * @adapter: i2c adapter to register - * - * This registers an i2c adapter that uses dp aux channel as it's underlaying - * transport. The driver needs to fill out the &i2c_algo_dp_aux_data structure - * and store it in the algo_data member of the @adapter argument. This will be - * used by the i2c over dp aux algorithm to drive the hardware. - * - * RETURNS: - * 0 on success, -ERRNO on failure. - * - * IMPORTANT: - * This interface is deprecated, please switch to the new dp aux helpers and - * drm_dp_aux_register(). - */ -int -i2c_dp_aux_add_bus(struct i2c_adapter *adapter) -{ - int error; - - error = i2c_dp_aux_prepare_bus(adapter); - if (error) - return error; - error = i2c_add_adapter(adapter); - return error; -} -EXPORT_SYMBOL(i2c_dp_aux_add_bus); - /* Helpers for DP link training */ static u8 dp_link_status(const u8 link_status[DP_LINK_STATUS_SIZE], int r) { diff --git a/drivers/gpu/drm/gma500/cdv_intel_dp.c b/drivers/gpu/drm/gma500/cdv_intel_dp.c index 9f158eab517a..0fafb8e2483a 100644 --- a/drivers/gpu/drm/gma500/cdv_intel_dp.c +++ b/drivers/gpu/drm/gma500/cdv_intel_dp.c @@ -37,6 +37,201 @@ #include "gma_display.h" #include +/** + * struct i2c_algo_dp_aux_data - driver interface structure for i2c over dp + * aux algorithm + * @running: set by the algo indicating whether an i2c is ongoing or whether + * the i2c bus is quiescent + * @address: i2c target address for the currently ongoing transfer + * @aux_ch: driver callback to transfer a single byte of the i2c payload + */ +struct i2c_algo_dp_aux_data { + bool running; + u16 address; + int (*aux_ch) (struct i2c_adapter *adapter, + int mode, uint8_t write_byte, + uint8_t *read_byte); +}; + +/* Run a single AUX_CH I2C transaction, writing/reading data as necessary */ +static int +i2c_algo_dp_aux_transaction(struct i2c_adapter *adapter, int mode, + uint8_t write_byte, uint8_t *read_byte) +{ + struct i2c_algo_dp_aux_data *algo_data = adapter->algo_data; + int ret; + + ret = (*algo_data->aux_ch)(adapter, mode, + write_byte, read_byte); + return ret; +} + +/* + * I2C over AUX CH + */ + +/* + * Send the address. If the I2C link is running, this 'restarts' + * the connection with the new address, this is used for doing + * a write followed by a read (as needed for DDC) + */ +static int +i2c_algo_dp_aux_address(struct i2c_adapter *adapter, u16 address, bool reading) +{ + struct i2c_algo_dp_aux_data *algo_data = adapter->algo_data; + int mode = MODE_I2C_START; + int ret; + + if (reading) + mode |= MODE_I2C_READ; + else + mode |= MODE_I2C_WRITE; + algo_data->address = address; + algo_data->running = true; + ret = i2c_algo_dp_aux_transaction(adapter, mode, 0, NULL); + return ret; +} + +/* + * Stop the I2C transaction. This closes out the link, sending + * a bare address packet with the MOT bit turned off + */ +static void +i2c_algo_dp_aux_stop(struct i2c_adapter *adapter, bool reading) +{ + struct i2c_algo_dp_aux_data *algo_data = adapter->algo_data; + int mode = MODE_I2C_STOP; + + if (reading) + mode |= MODE_I2C_READ; + else + mode |= MODE_I2C_WRITE; + if (algo_data->running) { + (void) i2c_algo_dp_aux_transaction(adapter, mode, 0, NULL); + algo_data->running = false; + } +} + +/* + * Write a single byte to the current I2C address, the + * the I2C link must be running or this returns -EIO + */ +static int +i2c_algo_dp_aux_put_byte(struct i2c_adapter *adapter, u8 byte) +{ + struct i2c_algo_dp_aux_data *algo_data = adapter->algo_data; + int ret; + + if (!algo_data->running) + return -EIO; + + ret = i2c_algo_dp_aux_transaction(adapter, MODE_I2C_WRITE, byte, NULL); + return ret; +} + +/* + * Read a single byte from the current I2C address, the + * I2C link must be running or this returns -EIO + */ +static int +i2c_algo_dp_aux_get_byte(struct i2c_adapter *adapter, u8 *byte_ret) +{ + struct i2c_algo_dp_aux_data *algo_data = adapter->algo_data; + int ret; + + if (!algo_data->running) + return -EIO; + + ret = i2c_algo_dp_aux_transaction(adapter, MODE_I2C_READ, 0, byte_ret); + return ret; +} + +static int +i2c_algo_dp_aux_xfer(struct i2c_adapter *adapter, + struct i2c_msg *msgs, + int num) +{ + int ret = 0; + bool reading = false; + int m; + int b; + + for (m = 0; m < num; m++) { + u16 len = msgs[m].len; + u8 *buf = msgs[m].buf; + reading = (msgs[m].flags & I2C_M_RD) != 0; + ret = i2c_algo_dp_aux_address(adapter, msgs[m].addr, reading); + if (ret < 0) + break; + if (reading) { + for (b = 0; b < len; b++) { + ret = i2c_algo_dp_aux_get_byte(adapter, &buf[b]); + if (ret < 0) + break; + } + } else { + for (b = 0; b < len; b++) { + ret = i2c_algo_dp_aux_put_byte(adapter, buf[b]); + if (ret < 0) + break; + } + } + if (ret < 0) + break; + } + if (ret >= 0) + ret = num; + i2c_algo_dp_aux_stop(adapter, reading); + DRM_DEBUG_KMS("dp_aux_xfer return %d\n", ret); + return ret; +} + +static u32 +i2c_algo_dp_aux_functionality(struct i2c_adapter *adapter) +{ + return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL | + I2C_FUNC_SMBUS_READ_BLOCK_DATA | + I2C_FUNC_SMBUS_BLOCK_PROC_CALL | + I2C_FUNC_10BIT_ADDR; +} + +static const struct i2c_algorithm i2c_dp_aux_algo = { + .master_xfer = i2c_algo_dp_aux_xfer, + .functionality = i2c_algo_dp_aux_functionality, +}; + +static void +i2c_dp_aux_reset_bus(struct i2c_adapter *adapter) +{ + (void) i2c_algo_dp_aux_address(adapter, 0, false); + (void) i2c_algo_dp_aux_stop(adapter, false); +} + +static int +i2c_dp_aux_prepare_bus(struct i2c_adapter *adapter) +{ + adapter->algo = &i2c_dp_aux_algo; + adapter->retries = 3; + i2c_dp_aux_reset_bus(adapter); + return 0; +} + +/* + * FIXME: This is the old dp aux helper, gma500 is the last driver that needs to + * be ported over to the new helper code in drm_dp_helper.c like i915 or radeon. + */ +static int __deprecated +i2c_dp_aux_add_bus(struct i2c_adapter *adapter) +{ + int error; + + error = i2c_dp_aux_prepare_bus(adapter); + if (error) + return error; + error = i2c_add_adapter(adapter); + return error; +} + #define _wait_for(COND, MS, W) ({ \ unsigned long timeout__ = jiffies + msecs_to_jiffies(MS); \ int ret__ = 0; \ diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index 9305c718d789..afebb08eee3a 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -404,26 +404,6 @@ #define MODE_I2C_READ 4 #define MODE_I2C_STOP 8 -/** - * struct i2c_algo_dp_aux_data - driver interface structure for i2c over dp - * aux algorithm - * @running: set by the algo indicating whether an i2c is ongoing or whether - * the i2c bus is quiescent - * @address: i2c target address for the currently ongoing transfer - * @aux_ch: driver callback to transfer a single byte of the i2c payload - */ -struct i2c_algo_dp_aux_data { - bool running; - u16 address; - int (*aux_ch) (struct i2c_adapter *adapter, - int mode, uint8_t write_byte, - uint8_t *read_byte); -}; - -int -i2c_dp_aux_add_bus(struct i2c_adapter *adapter); - - #define DP_LINK_STATUS_SIZE 6 bool drm_dp_channel_eq_ok(const u8 link_status[DP_LINK_STATUS_SIZE], int lane_count); -- cgit v1.2.3-71-gd317 From 3cb9ae4fd82ebc9759bc59998c88c385d35496fe Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 29 Oct 2014 10:03:57 +0100 Subject: drm: Move drm_crtc_init from drm_crtc.h to drm_plane_helper.h Just a bit of OCD cleanup on headers - this function isn't the core interface any more but just a helper for drivers who haven't yet transitioned to universal planes. Put the declaration at the right spot and sprinkle necessary #includes over all drivers. Maybe this helps to encourage driver maintainers to do the switch. v2: Fix #include ordering for tegra, reported by 0-day builder. v3: Include required headers, reported by Thierry. Cc: Matt Roper Cc: Thierry Reding Reviewed-by: Matt Roper Reviewed-by: Sean Paul Signed-off-by: Daniel Vetter --- drivers/gpu/drm/armada/armada_crtc.c | 1 + drivers/gpu/drm/ast/ast_mode.c | 1 + drivers/gpu/drm/bochs/bochs_kms.c | 1 + drivers/gpu/drm/cirrus/cirrus_mode.c | 1 + drivers/gpu/drm/gma500/psb_intel_display.c | 1 + drivers/gpu/drm/mgag200/mgag200_mode.c | 1 + drivers/gpu/drm/nouveau/dispnv04/crtc.c | 1 + drivers/gpu/drm/nouveau/nv50_display.c | 1 + drivers/gpu/drm/omapdrm/omap_crtc.c | 1 + drivers/gpu/drm/qxl/qxl_display.c | 1 + drivers/gpu/drm/radeon/radeon_display.c | 1 + drivers/gpu/drm/rcar-du/rcar_du_crtc.c | 1 + drivers/gpu/drm/shmobile/shmob_drm_crtc.c | 1 + drivers/gpu/drm/sti/sti_drm_crtc.c | 1 + drivers/gpu/drm/tegra/dc.c | 2 ++ drivers/gpu/drm/tilcdc/tilcdc_crtc.c | 1 + drivers/gpu/drm/udl/udl_modeset.c | 1 + drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c | 1 + drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c | 1 + drivers/staging/imx-drm/imx-drm-core.c | 1 + include/drm/drm_crtc.h | 3 --- include/drm/drm_plane_helper.h | 5 +++++ 22 files changed, 26 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c index 9a0cc09e6653..0b164fb1c107 100644 --- a/drivers/gpu/drm/armada/armada_crtc.c +++ b/drivers/gpu/drm/armada/armada_crtc.c @@ -12,6 +12,7 @@ #include #include #include +#include #include "armada_crtc.h" #include "armada_drm.h" #include "armada_fb.h" diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c index 9dc0fd5c1ea4..b7ee2634e47c 100644 --- a/drivers/gpu/drm/ast/ast_mode.c +++ b/drivers/gpu/drm/ast/ast_mode.c @@ -31,6 +31,7 @@ #include #include #include +#include #include "ast_drv.h" #include "ast_tables.h" diff --git a/drivers/gpu/drm/bochs/bochs_kms.c b/drivers/gpu/drm/bochs/bochs_kms.c index 6b7efcf363d6..5ffd4895d040 100644 --- a/drivers/gpu/drm/bochs/bochs_kms.c +++ b/drivers/gpu/drm/bochs/bochs_kms.c @@ -6,6 +6,7 @@ */ #include "bochs.h" +#include static int defx = 1024; static int defy = 768; diff --git a/drivers/gpu/drm/cirrus/cirrus_mode.c b/drivers/gpu/drm/cirrus/cirrus_mode.c index c7c5a9d91fa0..99d4a74ffeaf 100644 --- a/drivers/gpu/drm/cirrus/cirrus_mode.c +++ b/drivers/gpu/drm/cirrus/cirrus_mode.c @@ -16,6 +16,7 @@ */ #include #include +#include #include