diff for duplicates of <5731B7D8.8040304@arm.com> diff --git a/a/1.txt b/N1/1.txt index 41ccf21..0f9db54 100644 --- a/a/1.txt +++ b/N1/1.txt @@ -1,4 +1,4 @@ -On 09/05/16 09:00, honghui.zhang@mediatek.com wrote: +On 09/05/16 09:00, honghui.zhang at mediatek.com wrote: [...] > +static void *mtk_iommu_alloc_pgt(struct device *dev, size_t size, gfp_t gfp) > +{ @@ -147,7 +147,7 @@ you could either get rid of the loop here... > +}; ...or perhaps advertise .pgsize_bitmap = ~0UL << MTK_IOMMU_PAGE_SHIFT -here, so you actually can handle multiple entries at once for larger +here, so you actually can handle multiple entries@once for larger mappings - given how simple the page table format is that doesn't seem too unreasonable, especially since it should give you a big efficiency win in terms of TLB maintenance. diff --git a/a/content_digest b/N1/content_digest index c2e20bd..f7fc6a8 100644 --- a/a/content_digest +++ b/N1/content_digest @@ -1,37 +1,12 @@ "ref\01462780816-5288-1-git-send-email-honghui.zhang@mediatek.com\0" "ref\01462780816-5288-5-git-send-email-honghui.zhang@mediatek.com\0" - "From\0Robin Murphy <robin.murphy@arm.com>\0" - "Subject\0Re: [PATCH 4/5] iommu/mediatek: add support for mtk iommu generation one HW\0" + "From\0robin.murphy@arm.com (Robin Murphy)\0" + "Subject\0[PATCH 4/5] iommu/mediatek: add support for mtk iommu generation one HW\0" "Date\0Tue, 10 May 2016 11:28:40 +0100\0" - "To\0honghui.zhang@mediatek.com" - joro@8bytes.org - treding@nvidia.com - mark.rutland@arm.com - " matthias.bgg@gmail.com\0" - "Cc\0catalin.marinas@arm.com" - will.deacon@arm.com - youlin.pei@mediatek.com - yingjoe.chen@mediatek.com - devicetree@vger.kernel.org - kendrick.hsu@mediatek.com - kernel@pengutronix.de - arnd@arndb.de - tfiga@google.com - robh+dt@kernel.org - linux-mediatek@lists.infradead.org - eddie.huang@mediatek.com - linux-arm-kernel@lists.infradead.org - pebolle@tiscali.nl - srv_heupstream@mediatek.com - erin.lo@mediatek.com - linux-kernel@vger.kernel.org - iommu@lists.linux-foundation.org - djkurtz@google.com - p.zabel@pengutronix.de - " l.stach@pengutronix.de\0" + "To\0linux-arm-kernel@lists.infradead.org\0" "\00:1\0" "b\0" - "On 09/05/16 09:00, honghui.zhang@mediatek.com wrote:\n" + "On 09/05/16 09:00, honghui.zhang at mediatek.com wrote:\n" "[...]\n" "> +static void *mtk_iommu_alloc_pgt(struct device *dev, size_t size, gfp_t gfp)\n" "> +{\n" @@ -180,11 +155,11 @@ "> +};\n" "\n" "...or perhaps advertise .pgsize_bitmap = ~0UL << MTK_IOMMU_PAGE_SHIFT \n" - "here, so you actually can handle multiple entries at once for larger \n" + "here, so you actually can handle multiple entries@once for larger \n" "mappings - given how simple the page table format is that doesn't seem \n" "too unreasonable, especially since it should give you a big efficiency \n" "win in terms of TLB maintenance.\n" "\n" Robin. -f3af65b8dd5842c476f015bea3ec3de7ef8d460ea33d4524a833500dd1a882b6 +e3f27ef77e7c2e41815d26b9e79ab75a10d84900de6edb65fef218750edf21b9
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.