Message ID | 20191118234240.191075-1-adisuresh@google.com |
---|---|
State | Not Applicable |
Delegated to: | David Miller |
Headers | show |
Series | [net,v2] gve: fix dma sync bug where not all pages synced | expand |
From: Adi Suresh <adisuresh@google.com> Date: Mon, 18 Nov 2019 15:42:40 -0800 > The previous commit had a bug where the last page in the memory range > could not be synced. This change fixes the behavior so that all the > required pages are synced. > > Fixes: 9cfeeb5 ("gve: Fixes DMA synchronization") 12 digits of SHA1 hash signifigance in Fixes: tags please. Thank you.
Addressed in v3 On Mon, Nov 18, 2019 at 6:03 PM David Miller <davem@davemloft.net> wrote: > > From: Adi Suresh <adisuresh@google.com> > Date: Mon, 18 Nov 2019 15:42:40 -0800 > > > The previous commit had a bug where the last page in the memory range > > could not be synced. This change fixes the behavior so that all the > > required pages are synced. > > > > Fixes: 9cfeeb5 ("gve: Fixes DMA synchronization") > > 12 digits of SHA1 hash signifigance in Fixes: tags please. > > Thank you. >
diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c index 0a9a7ee2a866..f4889431f9b7 100644 --- a/drivers/net/ethernet/google/gve/gve_tx.c +++ b/drivers/net/ethernet/google/gve/gve_tx.c @@ -393,12 +393,13 @@ static void gve_tx_fill_seg_desc(union gve_tx_desc *seg_desc, static void gve_dma_sync_for_device(struct device *dev, dma_addr_t *page_buses, u64 iov_offset, u64 iov_len) { + u64 last_page = (iov_offset + iov_len - 1) / PAGE_SIZE; + u64 first_page = iov_offset / PAGE_SIZE; dma_addr_t dma; - u64 addr; + u64 page; - for (addr = iov_offset; addr < iov_offset + iov_len; - addr += PAGE_SIZE) { - dma = page_buses[addr / PAGE_SIZE]; + for (page = first_page; page <= last_page; page++) { + dma = page_buses[page]; dma_sync_single_for_device(dev, dma, PAGE_SIZE, DMA_TO_DEVICE); } }