From bfed6708d6c97406d14420f3288ee775c284ff8a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 17 Oct 2020 16:15:21 -0700 Subject: drm/i915: use vmap in shmem_pin_map shmem_pin_map somewhat awkwardly reimplements vmap using alloc_vm_area and manual pte setup. The only practical difference is that alloc_vm_area prefeaults the vmalloc area PTEs, which doesn't seem to be required here (and could be added to vmap using a flag if actually required). Switch to use vmap, and use vfree to free both the vmalloc mapping and the page array, as well as dropping the references to each page. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Reviewed-by: Tvrtko Ursulin Cc: Boris Ostrovsky Cc: Chris Wilson Cc: Jani Nikula Cc: Joonas Lahtinen Cc: Juergen Gross Cc: Matthew Auld Cc: "Matthew Wilcox (Oracle)" Cc: Minchan Kim Cc: Nitin Gupta Cc: Peter Zijlstra Cc: Rodrigo Vivi Cc: Stefano Stabellini Cc: Uladzislau Rezki (Sony) Link: https://lkml.kernel.org/r/20201002122204.1534411-7-hch@lst.de Signed-off-by: Linus Torvalds --- drivers/gpu/drm/i915/gt/shmem_utils.c | 76 +++++++++-------------------------- 1 file changed, 18 insertions(+), 58 deletions(-) (limited to 'drivers') diff --git a/drivers/gpu/drm/i915/gt/shmem_utils.c b/drivers/gpu/drm/i915/gt/shmem_utils.c index 43c7acbdc79d..f011ea42487e 100644 --- a/drivers/gpu/drm/i915/gt/shmem_utils.c +++ b/drivers/gpu/drm/i915/gt/shmem_utils.c @@ -49,80 +49,40 @@ struct file *shmem_create_from_object(struct drm_i915_gem_object *obj) return file; } -static size_t shmem_npte(struct file *file) -{ - return file->f_mapping->host->i_size >> PAGE_SHIFT; -} - -static void __shmem_unpin_map(struct file *file, void *ptr, size_t n_pte) -{ - unsigned long pfn; - - vunmap(ptr); - - for (pfn = 0; pfn < n_pte; pfn++) { - struct page *page; - - page = shmem_read_mapping_page_gfp(file->f_mapping, pfn, - GFP_KERNEL); - if (!WARN_ON(IS_ERR(page))) { - put_page(page); - put_page(page); - } - } -} - void *shmem_pin_map(struct file *file) { - const size_t n_pte = shmem_npte(file); - pte_t *stack[32], **ptes, **mem; - struct vm_struct *area; - unsigned long pfn; - - mem = stack; - if (n_pte > ARRAY_SIZE(stack)) { - mem = kvmalloc_array(n_pte, sizeof(*mem), GFP_KERNEL); - if (!mem) - return NULL; - } + struct page **pages; + size_t n_pages, i; + void *vaddr; - area = alloc_vm_area(n_pte << PAGE_SHIFT, mem); - if (!area) { - if (mem != stack) - kvfree(mem); + n_pages = file->f_mapping->host->i_size >> PAGE_SHIFT; + pages = kvmalloc_array(n_pages, sizeof(*pages), GFP_KERNEL); + if (!pages) return NULL; - } - ptes = mem; - for (pfn = 0; pfn < n_pte; pfn++) { - struct page *page; - - page = shmem_read_mapping_page_gfp(file->f_mapping, pfn, - GFP_KERNEL); - if (IS_ERR(page)) + for (i = 0; i < n_pages; i++) { + pages[i] = shmem_read_mapping_page_gfp(file->f_mapping, i, + GFP_KERNEL); + if (IS_ERR(pages[i])) goto err_page; - - **ptes++ = mk_pte(page, PAGE_KERNEL); } - if (mem != stack) - kvfree(mem); - + vaddr = vmap(pages, n_pages, VM_MAP_PUT_PAGES, PAGE_KERNEL); + if (!vaddr) + goto err_page; mapping_set_unevictable(file->f_mapping); - return area->addr; - + return vaddr; err_page: - if (mem != stack) - kvfree(mem); - - __shmem_unpin_map(file, area->addr, pfn); + while (--i >= 0) + put_page(pages[i]); + kvfree(pages); return NULL; } void shmem_unpin_map(struct file *file, void *ptr) { mapping_clear_unevictable(file->f_mapping); - __shmem_unpin_map(file, ptr, shmem_npte(file)); + vfree(ptr); } static int __shmem_rw(struct file *file, loff_t off, -- cgit v1.2.3 From 46ce3a62b1461d6950c0c353f106761d90a45258 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 17 Oct 2020 16:15:25 -0700 Subject: drm/i915: stop using kmap in i915_gem_object_map kmap for !PageHighmem is just a convoluted way to say page_address, and kunmap is a no-op in that case. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Reviewed-by: Tvrtko Ursulin Cc: Boris Ostrovsky Cc: Chris Wilson Cc: Jani Nikula Cc: Joonas Lahtinen Cc: Juergen Gross Cc: Matthew Auld Cc: "Matthew Wilcox (Oracle)" Cc: Minchan Kim Cc: Nitin Gupta Cc: Peter Zijlstra Cc: Rodrigo Vivi Cc: Stefano Stabellini Cc: Uladzislau Rezki (Sony) Link: https://lkml.kernel.org/r/20201002122204.1534411-8-hch@lst.de Signed-off-by: Linus Torvalds --- drivers/gpu/drm/i915/gem/i915_gem_pages.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'drivers') diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index d6eeefab3d01..6550c0bc824e 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -162,8 +162,6 @@ static void unmap_object(struct drm_i915_gem_object *obj, void *ptr) { if (is_vmalloc_addr(ptr)) vunmap(ptr); - else - kunmap(kmap_to_page(ptr)); } struct sg_table * @@ -277,11 +275,10 @@ static void *i915_gem_object_map(struct drm_i915_gem_object *obj, * forever. * * So if the page is beyond the 32b boundary, make an explicit - * vmap. On 64b, this check will be optimised away as we can - * directly kmap any page on the system. + * vmap. */ if (!PageHighMem(page)) - return kmap(page); + return page_address(page); } mem = stack; -- cgit v1.2.3 From 534a6687aaccce56c4801b70c651da311b71d402 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 17 Oct 2020 16:15:28 -0700 Subject: drm/i915: use vmap in i915_gem_object_map i915_gem_object_map implements fairly low-level vmap functionality in a driver. Split it into two helpers, one for remapping kernel memory which can use vmap, and one for I/O memory that uses vmap_pfn. The only practical difference is that alloc_vm_area prefeaults the vmalloc area PTEs, which doesn't seem to be required here for the kernel memory case (and could be added to vmap using a flag if actually required). Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Reviewed-by: Tvrtko Ursulin Cc: Boris Ostrovsky Cc: Chris Wilson Cc: Jani Nikula Cc: Joonas Lahtinen Cc: Juergen Gross Cc: Matthew Auld Cc: "Matthew Wilcox (Oracle)" Cc: Minchan Kim Cc: Nitin Gupta Cc: Peter Zijlstra Cc: Rodrigo Vivi Cc: Stefano Stabellini Cc: Uladzislau Rezki (Sony) Link: https://lkml.kernel.org/r/20201002122204.1534411-9-hch@lst.de Signed-off-by: Linus Torvalds --- drivers/gpu/drm/i915/Kconfig | 1 + drivers/gpu/drm/i915/gem/i915_gem_pages.c | 127 ++++++++++++++---------------- 2 files changed, 60 insertions(+), 68 deletions(-) (limited to 'drivers') diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig index 9afa5c4a6bf0..1e1cb245fca7 100644 --- a/drivers/gpu/drm/i915/Kconfig +++ b/drivers/gpu/drm/i915/Kconfig @@ -25,6 +25,7 @@ config DRM_I915 select CRC32 select SND_HDA_I915 if SND_HDA_CORE select CEC_CORE if CEC_NOTIFIER + select VMAP_PFN help Choose this option if you have a system that has "Intel Graphics Media Accelerator" or "HD Graphics" integrated graphics, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index 6550c0bc824e..f60ca6dc911f 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -232,34 +232,21 @@ unlock: return err; } -static inline pte_t iomap_pte(resource_size_t base, - dma_addr_t offset, - pgprot_t prot) -{ - return pte_mkspecial(pfn_pte((base + offset) >> PAGE_SHIFT, prot)); -} - /* The 'mapping' part of i915_gem_object_pin_map() below */ -static void *i915_gem_object_map(struct drm_i915_gem_object *obj, - enum i915_map_type type) +static void *i915_gem_object_map_page(struct drm_i915_gem_object *obj, + enum i915_map_type type) { - unsigned long n_pte = obj->base.size >> PAGE_SHIFT; - struct sg_table *sgt = obj->mm.pages; - pte_t *stack[32], **mem; - struct vm_struct *area; + unsigned long n_pages = obj->base.size >> PAGE_SHIFT, i; + struct page *stack[32], **pages = stack, *page; + struct sgt_iter iter; pgprot_t pgprot; + void *vaddr; - if (!i915_gem_object_has_struct_page(obj) && type != I915_MAP_WC) - return NULL; - - if (GEM_WARN_ON(type == I915_MAP_WC && - !static_cpu_has(X86_FEATURE_PAT))) - return NULL; - - /* A single page can always be kmapped */ - if (n_pte == 1 && type == I915_MAP_WB) { - struct page *page = sg_page(sgt->sgl); - + switch (type) { + default: + MISSING_CASE(type); + fallthrough; /* to use PAGE_KERNEL anyway */ + case I915_MAP_WB: /* * On 32b, highmem using a finite set of indirect PTE (i.e. * vmap) to provide virtual mappings of the high pages. @@ -277,30 +264,8 @@ static void *i915_gem_object_map(struct drm_i915_gem_object *obj, * So if the page is beyond the 32b boundary, make an explicit * vmap. */ - if (!PageHighMem(page)) - return page_address(page); - } - - mem = stack; - if (n_pte > ARRAY_SIZE(stack)) { - /* Too big for stack -- allocate temporary array instead */ - mem = kvmalloc_array(n_pte, sizeof(*mem), GFP_KERNEL); - if (!mem) - return NULL; - } - - area = alloc_vm_area(obj->base.size, mem); - if (!area) { - if (mem != stack) - kvfree(mem); - return NULL; - } - - switch (type) { - default: - MISSING_CASE(type); - fallthrough; /* to use PAGE_KERNEL anyway */ - case I915_MAP_WB: + if (n_pages == 1 && !PageHighMem(sg_page(obj->mm.pages->sgl))) + return page_address(sg_page(obj->mm.pages->sgl)); pgprot = PAGE_KERNEL; break; case I915_MAP_WC: @@ -308,30 +273,50 @@ static void *i915_gem_object_map(struct drm_i915_gem_object *obj, break; } - if (i915_gem_object_has_struct_page(obj)) { - struct sgt_iter iter; - struct page *page; - pte_t **ptes = mem; + if (n_pages > ARRAY_SIZE(stack)) { + /* Too big for stack -- allocate temporary array instead */ + pages = kvmalloc_array(n_pages, sizeof(*pages), GFP_KERNEL); + if (!pages) + return NULL; + } - for_each_sgt_page(page, iter, sgt) - **ptes++ = mk_pte(page, pgprot); - } else { - resource_size_t iomap; - struct sgt_iter iter; - pte_t **ptes = mem; - dma_addr_t addr; + i = 0; + for_each_sgt_page(page, iter, obj->mm.pages) + pages[i++] = page; + vaddr = vmap(pages, n_pages, 0, pgprot); + if (pages != stack) + kvfree(pages); + return vaddr; +} - iomap = obj->mm.region->iomap.base; - iomap -= obj->mm.region->region.start; +static void *i915_gem_object_map_pfn(struct drm_i915_gem_object *obj, + enum i915_map_type type) +{ + resource_size_t iomap = obj->mm.region->iomap.base - + obj->mm.region->region.start; + unsigned long n_pfn = obj->base.size >> PAGE_SHIFT; + unsigned long stack[32], *pfns = stack, i; + struct sgt_iter iter; + dma_addr_t addr; + void *vaddr; + + if (type != I915_MAP_WC) + return NULL; - for_each_sgt_daddr(addr, iter, sgt) - **ptes++ = iomap_pte(iomap, addr, pgprot); + if (n_pfn > ARRAY_SIZE(stack)) { + /* Too big for stack -- allocate temporary array instead */ + pfns = kvmalloc_array(n_pfn, sizeof(*pfns), GFP_KERNEL); + if (!pfns) + return NULL; } - if (mem != stack) - kvfree(mem); - - return area->addr; + i = 0; + for_each_sgt_daddr(addr, iter, obj->mm.pages) + pfns[i++] = (iomap + addr) >> PAGE_SHIFT; + vaddr = vmap_pfn(pfns, n_pfn, pgprot_writecombine(PAGE_KERNEL_IO)); + if (pfns != stack) + kvfree(pfns); + return vaddr; } /* get, pin, and map the pages of the object into kernel space */ @@ -383,7 +368,13 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj, } if (!ptr) { - ptr = i915_gem_object_map(obj, type); + if (GEM_WARN_ON(type == I915_MAP_WC && + !static_cpu_has(X86_FEATURE_PAT))) + ptr = NULL; + else if (i915_gem_object_has_struct_page(obj)) + ptr = i915_gem_object_map_page(obj, type); + else + ptr = i915_gem_object_map_pfn(obj, type); if (!ptr) { err = -ENOMEM; goto err_unpin; -- cgit v1.2.3 From b723caece361029fa4aec83b951db2888d611c2b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 17 Oct 2020 16:15:32 -0700 Subject: xen/xenbus: use apply_to_page_range directly in xenbus_map_ring_pv Replacing alloc_vm_area with get_vm_area_caller + apply_page_range allows to fill put the phys_addr values directly instead of doing another loop over all addresses. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Reviewed-by: Boris Ostrovsky Cc: Chris Wilson Cc: Jani Nikula Cc: Joonas Lahtinen Cc: Juergen Gross Cc: Matthew Auld Cc: "Matthew Wilcox (Oracle)" Cc: Minchan Kim Cc: Nitin Gupta Cc: Peter Zijlstra Cc: Rodrigo Vivi Cc: Stefano Stabellini Cc: Tvrtko Ursulin Cc: Uladzislau Rezki (Sony) Link: https://lkml.kernel.org/r/20201002122204.1534411-10-hch@lst.de Signed-off-by: Linus Torvalds --- drivers/xen/xenbus/xenbus_client.c | 30 ++++++++++++++++-------------- 1 file changed, 16 insertions(+), 14 deletions(-) (limited to 'drivers') diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c index 2690318ad50f..fd80e318b99c 100644 --- a/drivers/xen/xenbus/xenbus_client.c +++ b/drivers/xen/xenbus/xenbus_client.c @@ -73,16 +73,13 @@ struct map_ring_valloc { struct xenbus_map_node *node; /* Why do we need two arrays? See comment of __xenbus_map_ring */ - union { - unsigned long addrs[XENBUS_MAX_RING_GRANTS]; - pte_t *ptes[XENBUS_MAX_RING_GRANTS]; - }; + unsigned long addrs[XENBUS_MAX_RING_GRANTS]; phys_addr_t phys_addrs[XENBUS_MAX_RING_GRANTS]; struct gnttab_map_grant_ref map[XENBUS_MAX_RING_GRANTS]; struct gnttab_unmap_grant_ref unmap[XENBUS_MAX_RING_GRANTS]; - unsigned int idx; /* HVM only. */ + unsigned int idx; }; static DEFINE_SPINLOCK(xenbus_valloc_lock); @@ -686,6 +683,14 @@ int xenbus_unmap_ring_vfree(struct xenbus_device *dev, void *vaddr) EXPORT_SYMBOL_GPL(xenbus_unmap_ring_vfree); #ifdef CONFIG_XEN_PV +static int map_ring_apply(pte_t *pte, unsigned long addr, void *data) +{ + struct map_ring_valloc *info = data; + + info->phys_addrs[info->idx++] = arbitrary_virt_to_machine(pte).maddr; + return 0; +} + static int xenbus_map_ring_pv(struct xenbus_device *dev, struct map_ring_valloc *info, grant_ref_t *gnt_refs, @@ -694,18 +699,15 @@ static int xenbus_map_ring_pv(struct xenbus_device *dev, { struct xenbus_map_node *node = info->node; struct vm_struct *area; - int err = GNTST_okay; - int i; - bool leaked; + bool leaked = false; + int err = -ENOMEM; - area = alloc_vm_area(XEN_PAGE_SIZE * nr_grefs, info->ptes); + area = get_vm_area(XEN_PAGE_SIZE * nr_grefs, VM_IOREMAP); if (!area) return -ENOMEM; - - for (i = 0; i < nr_grefs; i++) - info->phys_addrs[i] = - arbitrary_virt_to_machine(info->ptes[i]).maddr; - + if (apply_to_page_range(&init_mm, (unsigned long)area->addr, + XEN_PAGE_SIZE * nr_grefs, map_ring_apply, info)) + goto failed; err = __xenbus_map_ring(dev, gnt_refs, nr_grefs, node->handles, info, GNTMAP_host_map | GNTMAP_contains_pte, &leaked); -- cgit v1.2.3