search for: pfns

...- 1 file changed, 12 insertions(+), 8 deletions(-) diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 7b6d74f..476c0e3 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -75,7 +75,7 @@ struct virtio_balloon { /* The array of pfns we tell the Host about. */ unsigned int num_pfns; - u32 pfns[VIRTIO_BALLOON_ARRAY_PFNS_MAX]; + __virtio32 pfns[VIRTIO_BALLOON_ARRAY_PFNS_MAX]; /* Memory statistics */ struct virtio_balloon_stat stats[VIRTIO_BALLOON_S_NR]; @@ -127,14 +127,16 @@ static void tell_host(struct virtio_balloon *vb...

...- 1 file changed, 12 insertions(+), 8 deletions(-) diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 7b6d74f..476c0e3 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -75,7 +75,7 @@ struct virtio_balloon { /* The array of pfns we tell the Host about. */ unsigned int num_pfns; - u32 pfns[VIRTIO_BALLOON_ARRAY_PFNS_MAX]; + __virtio32 pfns[VIRTIO_BALLOON_ARRAY_PFNS_MAX]; /* Memory statistics */ struct virtio_balloon_stat stats[VIRTIO_BALLOON_S_NR]; @@ -127,14 +127,16 @@ static void tell_host(struct virtio_balloon *vb...

This series contains one cleanup and two bug fixes for the virtio balloon driver.

This series contains one cleanup and two bug fixes for the virtio balloon driver.

...eletions(-) > > diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c > index 7b6d74f..476c0e3 100644 > --- a/drivers/virtio/virtio_balloon.c > +++ b/drivers/virtio/virtio_balloon.c > @@ -75,7 +75,7 @@ struct virtio_balloon { > > /* The array of pfns we tell the Host about. */ > unsigned int num_pfns; > - u32 pfns[VIRTIO_BALLOON_ARRAY_PFNS_MAX]; > + __virtio32 pfns[VIRTIO_BALLOON_ARRAY_PFNS_MAX]; > > /* Memory statistics */ > struct virtio_balloon_stat stats[VIRTIO_BALLOON_S_NR]; > @@ -127,14 +127,16 @@ static void...

...'t clear how anything actually could do that as hmm_range_fault() provides CPU addresses which must be DMA mapped. Perhaps there is some special HW that does not need DMA mapping, but we don't have any examples of this, and the theoretical performance win of avoiding an extra scan over the pfns array doesn't seem worth the complexity. Plus pfns needs to be scanned anyhow to sort out any DEVICE_PRIVATE pages. This version replaces the uint64_t with an usigned long containing a pfn and fix flags. On input flags is filled with the HMM_PFN_REQ_* values, on successful output it is filled...

...-}; - /* * Data structure to track address ranges and register for mmu interval * notifier updates. @@ -175,7 +160,7 @@ static inline struct dmirror_device *dmirror_page_to_device(struct page *page) static int dmirror_do_fault(struct dmirror *dmirror, struct hmm_range *range) { - uint64_t *pfns = range->pfns; + unsigned long *pfns = range->hmm_pfns; unsigned long pfn; for (pfn = (range->start >> PAGE_SHIFT); @@ -188,15 +173,16 @@ static int dmirror_do_fault(struct dmirror *dmirror, struct hmm_range *range) * Since we asked for hmm_range_fault() to populate pages,...

...mory; oom_notify: release some inflated memory via leak_balloon(); leak_balloon: wait for balloon_lock to be released by fill_balloon. This patch breaks the lock into two fine-grained inflate_lock and deflate_lock, and eliminates the unnecessary use of the shared data (i.e. vb->pnfs, vb->num_pfns). This enables leak_balloon and fill_balloon to run concurrently and solves the deadlock issue. Reported-by: Tetsuo Handa <penguin-kernel at I-love.SAKURA.ne.jp> Signed-off-by: Wei Wang <wei.w.wang at intel.com> Cc: Michael S. Tsirkin <mst at redhat.com> Cc: Tetsuo Handa <peng...

...g actually could do that > as hmm_range_fault() provides CPU addresses which must be DMA mapped. > > Perhaps there is some special HW that does not need DMA mapping, but we > don't have any examples of this, and the theoretical performance win of > avoiding an extra scan over the pfns array doesn't seem worth the > complexity. Plus pfns needs to be scanned anyhow to sort out any > DEVICE_PRIVATE pages. > > This version replaces the uint64_t with an usigned long containing a pfn > and fix flags. On input flags is filled with the HMM_PFN_REQ_* values, on > su...

...'t clear how anything actually could do that as hmm_range_fault() provides CPU addresses which must be DMA mapped. Perhaps there is some special HW that does not need DMA mapping, but we don't have any examples of this, and the theoretical performance win of avoiding an extra scan over the pfns array doesn't seem worth the complexity. Plus pfns needs to be scanned anyhow to sort out any DEVICE_PRIVATE pages. This version replaces the uint64_t with an usigned long containing a pfn and fixed flags. On input flags is filled with the HMM_PFN_REQ_* values, on successful output it is fille...

...rm *drm, out_free_page: nouveau_dmem_page_free_locked(drm, dpage); out: + *pfn = NVIF_VMM_PFNMAP_V0_NONE; return 0; } static void nouveau_dmem_migrate_chunk(struct migrate_vma *args, - struct nouveau_drm *drm, dma_addr_t *dma_addrs) + struct nouveau_drm *drm, dma_addr_t *dma_addrs, u64 *pfns) { struct nouveau_fence *fence; unsigned long addr = args->start, nr_dma = 0, i; for (i = 0; addr < args->end; i++) { args->dst[i] = nouveau_dmem_migrate_copy_one(drm, args->vma, - addr, args->src[i], &dma_addrs[nr_dma]); + args->src[i], &dma_addrs[nr_...

...of the previous virtio-balloon is not very efficient, because the ballooned pages are transferred to the host one by one. Here is the breakdown of the time in percentage spent on each step of the balloon inflating process (inflating 7GB of an 8GB idle guest). 1) allocating pages (6.5%) 2) sending PFNs to host (68.3%) 3) address translation (6.1%) 4) madvise (19%) It takes about 4126ms for the inflating process to complete. The above profiling shows that the bottlenecks are stage 2) and stage 4). This patch optimizes step 2) by transferring pages to the host in chunks. A chunk consists of guest...

As reported by David Gibson, current code handles PAGE_SIZE != 4k completely wrong which can lead to guest memory corruption errors. - page_to_balloon_pfn is wrong: e.g. on system with 64K page size it gives the same pfn value for 16 different pages. - we also need to convert back to linux pfns when we free. - for each linux page we need to tell host about multiple balloon pages, but code only adds one pfn to the array. Signed-off-by: David Gibson <david at gibson.dropbear.id.au> Signed-off-by: Michael S. Tsirkin <mst at redhat.com> Signed-off-by: David Gibson <david at...

As reported by David Gibson, current code handles PAGE_SIZE != 4k completely wrong which can lead to guest memory corruption errors. - page_to_balloon_pfn is wrong: e.g. on system with 64K page size it gives the same pfn value for 16 different pages. - we also need to convert back to linux pfns when we free. - for each linux page we need to tell host about multiple balloon pages, but code only adds one pfn to the array. Signed-off-by: David Gibson <david at gibson.dropbear.id.au> Signed-off-by: Michael S. Tsirkin <mst at redhat.com> Signed-off-by: David Gibson <david at...

...setup.c +++ b/arch/x86/xen/setup.c @@ -157,50 +157,48 @@ static unsigned long __init xen_populate_chunk( unsigned long dest_pfn; for (i = 0, entry = list; i < map_size; i++, entry++) { - unsigned long credits = credits_left; unsigned long s_pfn; unsigned long e_pfn; unsigned long pfns; long capacity; - if (credits <= 0) + if (credits_left <= 0) break; if (entry->type != E820_RAM) continue; - e_pfn = PFN_UP(entry->addr + entry->size); + e_pfn = PFN_DOWN(entry->addr + entry->size); /* We only care about E820 after the xen_start_inf...

...setup.c +++ b/arch/x86/xen/setup.c @@ -157,50 +157,48 @@ static unsigned long __init xen_populate_chunk( unsigned long dest_pfn; for (i = 0, entry = list; i < map_size; i++, entry++) { - unsigned long credits = credits_left; unsigned long s_pfn; unsigned long e_pfn; unsigned long pfns; long capacity; - if (credits <= 0) + if (credits_left <= 0) break; if (entry->type != E820_RAM) continue; - e_pfn = PFN_UP(entry->addr + entry->size); + e_pfn = PFN_DOWN(entry->addr + entry->size); /* We only care about E820 after the xen_start_inf...

...m *drm, out_free_page: nouveau_dmem_page_free_locked(drm, dpage); out: + *pfn = NVIF_VMM_PFNMAP_V0_NONE; return 0; } static void nouveau_dmem_migrate_chunk(struct nouveau_drm *drm, - struct migrate_vma *args, dma_addr_t *dma_addrs) + struct migrate_vma *args, dma_addr_t *dma_addrs, u64 *pfns) { struct nouveau_fence *fence; unsigned long addr = args->start, nr_dma = 0, i; for (i = 0; addr < args->end; i++) { args->dst[i] = nouveau_dmem_migrate_copy_one(drm, args->src[i], - dma_addrs + nr_dma); + dma_addrs + nr_dma, pfns + i); if (args->dst[i])...

...n of the current virtio-balloon is not very efficient, because the ballooned pages are transferred to the host one by one. Here is the breakdown of the time in percentage spent on each step of the balloon inflating process (inflating 7GB of an 8GB idle guest). 1) allocating pages (6.5%) 2) sending PFNs to host (68.3%) 3) address translation (6.1%) 4) madvise (19%) It takes about 4126ms for the inflating process to complete. The above profiling shows that the bottlenecks are stage 2) and stage 4). This patch optimizes step 2) by transferring pages to the host in chunks. A chunk consists of guest...

...mpbell at nvidia.com> > Cc: Christoph Hellwig <hch at lst.de> > Cc: Jason Gunthorpe <jgg at mellanox.com> > Cc: "Jérôme Glisse" <jglisse at redhat.com> > Cc: Ben Skeggs <bskeggs at redhat.com> Sorry for delay i am swamp, couple issues: - nouveau_pfns_map() is never call, it should be call after the dma copy is done (iirc it is lacking proper fencing so that would need to be implemented first) - the migrate ioctl is disconnected from the svm part and thus we would need first to implement svm reference counting and ta...

...The thread servicing the balloon. */ - struct task_struct *thread; + /* The workqueue servicing the balloon. */ + struct workqueue_struct *wq; + struct work_struct wq_work; /* Waiting for host to ack the pages we released. */ wait_queue_head_t acked; @@ -125,12 +122,15 @@ static void set_page_pfns(u32 pfns[], struct page *page) pfns[i] = page_to_balloon_pfn(page) + i; } -static void fill_balloon(struct virtio_balloon *vb, size_t num) +static void fill_balloon(struct virtio_balloon *vb, size_t diff) { struct balloon_dev_info *vb_dev_info = vb->vb_dev_info; + size_t num; + bool don...