diff for duplicates of <20150323231943.GC21966@oracle.com> diff --git a/a/1.txt b/N1/1.txt index bea17de..78a3019 100644 --- a/a/1.txt +++ b/N1/1.txt @@ -23,7 +23,7 @@ indirection can be passed as a function pointer, or via the table_ops. What I've tried to do is to have a bool large_pool arg passed to iommu_tbl_pool_init. In my observation (instrumented for scsi, ixgbe), we never allocate more than 4 pages at a time, so I pass in -large_pool == false for all the sparc platforms. +large_pool = false for all the sparc platforms. > Or we can decide that large allocs are rare (typically > pci_alloc_consistent, ie, driver init time), and thus always flush on diff --git a/a/content_digest b/N1/content_digest index 0f0f0da..dc8c288 100644 --- a/a/content_digest +++ b/N1/content_digest @@ -5,7 +5,7 @@ "ref\01427150202.4770.248.camel@kernel.crashing.org\0" "From\0Sowmini Varadhan <sowmini.varadhan@oracle.com>\0" "Subject\0Re: Generic IOMMU pooled allocator\0" - "Date\0Mon, 23 Mar 2015 19:19:43 -0400\0" + "Date\0Mon, 23 Mar 2015 23:19:43 +0000\0" "To\0Benjamin Herrenschmidt <benh@kernel.crashing.org>\0" "Cc\0aik@au1.ibm.com" aik@ozlabs.ru @@ -41,7 +41,7 @@ "What I've tried to do is to have a bool large_pool arg passed\n" "to iommu_tbl_pool_init. In my observation (instrumented for scsi, ixgbe), \n" "we never allocate more than 4 pages at a time, so I pass in \n" - "large_pool == false for all the sparc platforms. \n" + "large_pool = false for all the sparc platforms. \n" "\n" "> Or we can decide that large allocs are rare (typically\n" "> pci_alloc_consistent, ie, driver init time), and thus always flush on\n" @@ -53,4 +53,4 @@ "> flush to avoid more spurrious flushes, but here too the benefit might be\n" > in the noise. -cd3479c9a8d2e6271b7e6c90c0cdbe3c86936890941dcdb4e364b62e01a1772b +85f4c320244b07d6ae3037bb4ac5a3370d0a522228d5704d4d0b742aac3c2dc6
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.