search for: dma_addr

The kcalloc() in nouveau_dmem_evict_chunk() will return null if the physical memory has run out. As a result, if we dereference src_pfns, dst_pfns or dma_addrs, the null pointer dereference bugs will happen. Moreover, the GPU is going away. If the kcalloc() fails, we could not evict all pages mapping a chunk. So this patch adds a __GFP_NOFAIL flag in kcalloc(). Finally, as there is no need to have physically contiguous memory, this patch switches kcall...

...if000c.h> #include <linux/sched/mm.h> #include <linux/hmm.h> @@ -560,11 +562,12 @@ nouveau_dmem_init(struct nouveau_drm *drm) } static unsigned long nouveau_dmem_migrate_copy_one(struct nouveau_drm *drm, - struct vm_area_struct *vma, unsigned long addr, - unsigned long src, dma_addr_t *dma_addr) + struct vm_area_struct *vma, unsigned long src, + dma_addr_t *dma_addr, u64 *pfn) { struct device *dev = drm->dev->dev; struct page *dpage, *spage; + unsigned long paddr; spage = migrate_pfn_to_page(src); if (!spage || !(src & MIGRATE_PFN_MIGRATE)) @@ -572,17 +5...

...@@ -86,15 +84,6 @@ static inline struct nouveau_dmem *page_to_dmem(struct page *page) return container_of(page->pgmap, struct nouveau_dmem, pagemap); } -struct nouveau_migrate { - struct vm_area_struct *vma; - struct nouveau_drm *drm; - struct nouveau_fence *fence; - unsigned long npages; - dma_addr_t *dma; - unsigned long dma_nr; -}; - static unsigned long nouveau_dmem_page_addr(struct page *page) { struct nouveau_dmem_chunk *chunk = page->zone_device_data; @@ -569,131 +558,67 @@ nouveau_dmem_init(struct nouveau_drm *drm) drm->dmem = NULL; } -static void -nouveau_dmem_migrate_a...

...| __GFP_ZERO) > + > + > +struct device *cio_get_dma_css_dev(void) > +{ > + return &channel_subsystems[0]->device; > +} > + > +struct gen_pool *cio_gp_dma_create(struct device *dma_dev, int nr_pages) > +{ > + struct gen_pool *gp_dma; > + void *cpu_addr; > + dma_addr_t dma_addr; > + int i; > + > + gp_dma = gen_pool_create(3, -1); > + if (!gp_dma) > + return NULL; > + for (i = 0; i < nr_pages; ++i) { > + cpu_addr = dma_alloc_coherent(dma_dev, PAGE_SIZE, &dma_addr, > + CIO_DMA_GFP); > + if (!cpu_addr) > + return...

...| __GFP_ZERO) > + > + > +struct device *cio_get_dma_css_dev(void) > +{ > + return &channel_subsystems[0]->device; > +} > + > +struct gen_pool *cio_gp_dma_create(struct device *dma_dev, int nr_pages) > +{ > + struct gen_pool *gp_dma; > + void *cpu_addr; > + dma_addr_t dma_addr; > + int i; > + > + gp_dma = gen_pool_create(3, -1); > + if (!gp_dma) > + return NULL; > + for (i = 0; i < nr_pages; ++i) { > + cpu_addr = dma_alloc_coherent(dma_dev, PAGE_SIZE, &dma_addr, > + CIO_DMA_GFP); > + if (!cpu_addr) > + return...

Hi all, Here''s a work in progress series whcih does a partial revert of the previous swiotlb changes, and does a partial replacement with Becky Bruce''s series. The most important difference is Becky''s use of phys_addr_t rather than page+offset to represent arbitrary pages. This turns out to be simpler. I didn''t replicate the map_single_page changes, since

On Fri, May 19, 2023 at 01:49:46PM +0100, Andrew Cooper wrote: > > The alternative would be to finally merge swiotlb-xen into swiotlb, in > > which case we might be able to do this later. Let me see what I can > > do there. > > If that is an option, it would be great to reduce the special-cashing. I think it's doable, and I've been wanting it for a while. I just

...sched/mm.h> > #include <linux/hmm.h> > @@ -560,11 +562,12 @@ nouveau_dmem_init(struct nouveau_drm *drm) > } > > static unsigned long nouveau_dmem_migrate_copy_one(struct nouveau_drm *drm, > - struct vm_area_struct *vma, unsigned long addr, > - unsigned long src, dma_addr_t *dma_addr) > + struct vm_area_struct *vma, unsigned long src, > + dma_addr_t *dma_addr, u64 *pfn) > { > struct device *dev = drm->dev->dev; > struct page *dpage, *spage; > + unsigned long paddr; > > spage = migrate_pfn_to_page(src); > if (!spage || !(...

On 3/6/24 06:01, Duoming Zhou wrote: > The kcalloc() in nouveau_dmem_evict_chunk() will return null if > the physical memory has run out. As a result, if we dereference > src_pfns, dst_pfns or dma_addrs, the null pointer dereference bugs > will happen. > > Moreover, the GPU is going away. If the kcalloc() fails, we could not > evict all pages mapping a chunk. So this patch adds a __GFP_NOFAIL > flag in kcalloc(). > > Finally, as there is no need to have physically contiguou...

The kcalloc() in nouveau_dmem_evict_chunk() will return null if the physical memory has run out. As a result, if we dereference src_pfns, dst_pfns or dma_addrs, the null pointer dereference bugs will happen. This patch uses stack variables to replace the kcalloc(). Fixes: 249881232e14 ("nouveau/dmem: evict device private memory during release") Signed-off-by: Duoming Zhou <duoming at zju.edu.cn> --- drivers/gpu/drm/nouveau/nouveau_dmem...

...NOMEM; int i; if (!dev->irq) { @@ -186,12 +184,22 @@ lan_init_chip(struct parisc_device *dev) lp = netdev_priv(netdevice); lp->options = dev->id.sversion == 0x72 ? OPT_SWAP_PORT : 0; + lp->dma = dma_alloc_attrs(&dev->dev, sizeof(struct i596_dma), + &lp->dma_addr, GFP_KERNEL, + DMA_ATTR_NON_CONSISTENT); + if (!lp->dma) + goto out_free_netdev; retval = i82596_probe(netdevice); - if (retval) { - free_netdev(netdevice); - return -ENODEV; - } + if (retval) + goto out_free_dma; + return 0; + +out_free_dma: + dma_free_attrs(&dev->dev, si...

...MEM; int i; if (!dev->irq) { @@ -186,12 +184,22 @@ lan_init_chip(struct parisc_device *dev) lp = netdev_priv(netdevice); lp->options = dev->id.sversion == 0x72 ? OPT_SWAP_PORT : 0; + lp->dma = dma_alloc_attrs(dev->dev.parent, sizeof(struct i596_dma), + &lp->dma_addr, GFP_KERNEL, + DMA_ATTR_NON_CONSISTENT); + if (!lp->dma) + goto out_free_netdev; retval = i82596_probe(netdevice); - if (retval) { - free_netdev(netdevice); - return -ENODEV; - } + if (retval) + goto out_free_dma; + return 0; + +out_free_dma: + dma_free_attrs(dev->dev.parent,...

...insertions(+), 136 deletions(-) delete mode 100644 include/linux/dma-attrs.h diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt index 45ef3f279c3b..24f9688bb98a 100644 --- a/Documentation/DMA-API.txt +++ b/Documentation/DMA-API.txt @@ -369,35 +369,32 @@ See also dma_map_single(). dma_addr_t dma_map_single_attrs(struct device *dev, void *cpu_addr, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) void dma_unmap_single_attrs(struct device *dev, dma_addr_t dma_addr, size_t size, enum dma_data_direction dir, -...

...the flag. > > This looks useful. I've already dropped that patch for the pending > resend. Thanks. > >> static unsigned long nouveau_dmem_migrate_copy_one(struct nouveau_drm *drm, >> - struct vm_area_struct *vma, unsigned long addr, >> - unsigned long src, dma_addr_t *dma_addr) >> + struct vm_area_struct *vma, unsigned long src, >> + dma_addr_t *dma_addr, u64 *pfn) > > I'll pick up the removal of the not needed addr argument for the patch > introducing nouveau_dmem_migrate_copy_one, thanks, > >> static void nouveau_dmem...

...#include <nvif/if900b.h> +#include <nvif/if000c.h> #include <linux/sched/mm.h> #include <linux/hmm.h> @@ -558,10 +560,11 @@ nouveau_dmem_init(struct nouveau_drm *drm) } static unsigned long nouveau_dmem_migrate_copy_one(struct nouveau_drm *drm, - unsigned long src, dma_addr_t *dma_addr) + unsigned long src, dma_addr_t *dma_addr, u64 *pfn) { struct device *dev = drm->dev->dev; struct page *dpage, *spage; + unsigned long paddr; spage = migrate_pfn_to_page(src); if (!spage || !(src & MIGRATE_PFN_MIGRATE)) @@ -569,17 +572,21 @@ static unsigned long n...

...index 55a62ca..7e2788c 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -313,10 +313,10 @@ vmxnet3_unmap_tx_buf(struct vmxnet3_tx_buf_info *tbi, struct pci_dev *pdev) { if (tbi->map_type == VMXNET3_MAP_SINGLE) - pci_unmap_single(pdev, tbi->dma_addr, tbi->len, + dma_unmap_single(&pdev->dev, tbi->dma_addr, tbi->len, PCI_DMA_TODEVICE); else if (tbi->map_type == VMXNET3_MAP_PAGE) - pci_unmap_page(pdev, tbi->dma_addr, tbi->len, + dma_unmap_page(&pdev->dev, tbi->dma_addr, tbi->len, PCI_DMA...

...index 55a62ca..7e2788c 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -313,10 +313,10 @@ vmxnet3_unmap_tx_buf(struct vmxnet3_tx_buf_info *tbi, struct pci_dev *pdev) { if (tbi->map_type == VMXNET3_MAP_SINGLE) - pci_unmap_single(pdev, tbi->dma_addr, tbi->len, + dma_unmap_single(&pdev->dev, tbi->dma_addr, tbi->len, PCI_DMA_TODEVICE); else if (tbi->map_type == VMXNET3_MAP_PAGE) - pci_unmap_page(pdev, tbi->dma_addr, tbi->len, + dma_unmap_page(&pdev->dev, tbi->dma_addr, tbi->len, PCI_DMA...

...for (i = 0; i < VDPASIM_VQ_NUM; i++) vdpasim_vq_reset(&vdpasim->vqs[i]); + spin_lock(&vdpasim->iommu_lock); vhost_iotlb_reset(vdpasim->iommu); + spin_unlock(&vdpasim->iommu_lock); vdpasim->features = 0; vdpasim->status = 0; @@ -236,8 +240,10 @@ static dma_addr_t vdpasim_map_page(struct device *dev, struct page *page, /* For simplicity, use identical mapping to avoid e.g iova * allocator. */ + spin_lock(&vdpasim->iommu_lock); ret = vhost_iotlb_add_range(iommu, pa, pa + size - 1, pa, dir_to_perm(dir)); + spin_unlock(&vdpasim-&...

Originally patch 4 was targeted for Jason's rdma tree since other HMM related changes were queued there. Now that those have been merged, these patches just contain changes to nouveau so they could go through any tree. I guess Ben Skeggs' tree would be appropriate. Changes since v2: Added patches 1-3 to fix some minor issues. Eliminated nouveau_find_svmm() since it is easily found.

...;dev; struct page *dpage, *spage; + struct nouveau_svmm *svmm; spage = migrate_pfn_to_page(args->src[0]); if (!spage || !(args->src[0] & MIGRATE_PFN_MIGRATE)) @@ -154,14 +155,19 @@ static vm_fault_t nouveau_dmem_fault_copy_one(struct nouveau_drm *drm, if (dma_mapping_error(dev, *dma_addr)) goto error_free_page; + svmm = spage->zone_device_data; + mutex_lock(&svmm->mutex); + nouveau_svmm_invalidate(svmm, args->start, args->end); if (drm->dmem->migrate.copy_func(drm, 1, NOUVEAU_APER_HOST, *dma_addr, NOUVEAU_APER_VRAM, nouveau_dmem_page_addr(spage)))...