From: KyongHo Cho <pullip.cho@samsung.com> To: Ohad Ben-Cohen <ohad@wizery.com> Cc: Arnd Bergmann <arnd@arndb.de>, Joerg Roedel <Joerg.Roedel@amd.com>, Hiroshi DOYU <Hiroshi.DOYU@nokia.com>, linux-kernel@vger.kernel.org, iommu@lists.linux-foundation.org, Laurent Pinchart <laurent.pinchart@ideasonboard.com>, David Brown <davidb@codeaurora.org>, linux-omap@vger.kernel.org, David Woodhouse <dwmw2@infradead.org>, linux-arm-kernel@lists.infradead.org Subject: Re: [RFC 7/7] iommu/core: split mapping to page sizes as supported by the hardware Date: Thu, 8 Sep 2011 21:51:57 +0900 [thread overview] Message-ID: <CAHQjnONUvBtKSMxiDf5Mk+DLqfrTr09Us11rWoaR1mVZeiAmnA@mail.gmail.com> (raw) In-Reply-To: <CAK=WgbbFhmiC=PJfmyPOhbHGtiPFOcmqBx7nSpkuDX36hPYgbA@mail.gmail.com> Hi Ohad, On Wed, Sep 7, 2011 at 6:16 PM, Ohad Ben-Cohen <ohad@wizery.com> wrote: > Hmm this sounds a bit like a red herring to me; optimization of the :) I agree. sorry. > map function is not the main subject here. Especially not when we're > discussing mapping of large physically contiguous memory regions which > do not happen too often. > I've got your point but I thought that it is really needed. > Another advantage for migrating s5p_iommu_map() over to the subject > patch, is that s5p_iommu_map() doesn't support super sections yet. To > support it, you'd need to add more code (duplicate another while > loop). But if you migrated to the subject patch, then you would only > need to flip the 16MB bit when you advertise page size capabilities > and then that's it; you're done. I did not implement that. 16MB page is less practical in Linux because Linux kernel is unable to allocated larger physically contiguous memory than 4MB by default. But I also think that it is needed to support 16MB mapping for IO virtualization someday and it is just trivial job. And you pointed correctly that s5p_iommu_map() has duplicate similar codes. Actually, I think your idea is good and does not cause performance degradation. But I wondered if it is really useful. > > The caller of iommu_map() doesn't say anything about alignments. It > just gives it a memory region to map, and expect things to just work. > The caller of iommu_map() gives gfp_order that is the size of the physical memory to map. I thought that it also means alignment of the physical memory. Isn't it? Regards, KyongHo
WARNING: multiple messages have this Message-ID (diff)
From: pullip.cho@samsung.com (KyongHo Cho) To: linux-arm-kernel@lists.infradead.org Subject: [RFC 7/7] iommu/core: split mapping to page sizes as supported by the hardware Date: Thu, 8 Sep 2011 21:51:57 +0900 [thread overview] Message-ID: <CAHQjnONUvBtKSMxiDf5Mk+DLqfrTr09Us11rWoaR1mVZeiAmnA@mail.gmail.com> (raw) In-Reply-To: <CAK=WgbbFhmiC=PJfmyPOhbHGtiPFOcmqBx7nSpkuDX36hPYgbA@mail.gmail.com> Hi Ohad, On Wed, Sep 7, 2011 at 6:16 PM, Ohad Ben-Cohen <ohad@wizery.com> wrote: > Hmm this sounds a bit like a red herring to me; optimization of the :) I agree. sorry. > map function is not the main subject here. Especially not when we're > discussing mapping of large physically contiguous memory regions which > do not happen too often. > I've got your point but I thought that it is really needed. > Another advantage for migrating s5p_iommu_map() over to the subject > patch, is that s5p_iommu_map() doesn't support super sections yet. To > support it, you'd need to add more code (duplicate another while > loop). But if you migrated to the subject patch, then you would only > need to flip the 16MB bit when you advertise page size capabilities > and then that's it; you're done. I did not implement that. 16MB page is less practical in Linux because Linux kernel is unable to allocated larger physically contiguous memory than 4MB by default. But I also think that it is needed to support 16MB mapping for IO virtualization someday and it is just trivial job. And you pointed correctly that s5p_iommu_map() has duplicate similar codes. Actually, I think your idea is good and does not cause performance degradation. But I wondered if it is really useful. > > The caller of iommu_map() doesn't say anything about alignments. It > just gives it a memory region to map, and expect things to just work. > The caller of iommu_map() gives gfp_order that is the size of the physical memory to map. I thought that it also means alignment of the physical memory. Isn't it? Regards, KyongHo
next prev parent reply other threads:[~2011-09-08 12:52 UTC|newest] Thread overview: 53+ messages / expand[flat|nested] mbox.gz Atom feed top 2011-09-02 17:32 [PATCH/RFC 0/7] iommu: fixes & extensions Ohad Ben-Cohen 2011-09-02 17:32 ` Ohad Ben-Cohen 2011-09-02 17:32 ` Ohad Ben-Cohen 2011-09-02 17:32 ` [PATCH 1/7] iommu/omap-iovmm: support non page-aligned buffers in iommu_vmap Ohad Ben-Cohen 2011-09-02 17:32 ` Ohad Ben-Cohen 2011-09-02 17:32 ` Ohad Ben-Cohen 2011-09-02 17:32 ` [PATCH 2/7] iommu/omap: cleanup: remove a redundant statement Ohad Ben-Cohen 2011-09-02 17:32 ` Ohad Ben-Cohen 2011-09-02 17:32 ` Ohad Ben-Cohen 2011-09-02 17:32 ` [PATCH 3/7] iommu/core: use the existing IS_ALIGNED macro Ohad Ben-Cohen 2011-09-02 17:32 ` Ohad Ben-Cohen 2011-09-02 17:32 ` Ohad Ben-Cohen 2011-09-02 17:32 ` [PATCH 4/7] iommu/omap: ->unmap() should return order of unmapped page Ohad Ben-Cohen 2011-09-02 17:32 ` Ohad Ben-Cohen 2011-09-02 17:32 ` Ohad Ben-Cohen 2011-09-02 17:32 ` [PATCH 5/7] iommu/msm: " Ohad Ben-Cohen 2011-09-02 17:32 ` Ohad Ben-Cohen 2011-09-02 17:32 ` Ohad Ben-Cohen 2011-09-02 18:36 ` David Brown 2011-09-02 18:36 ` David Brown 2011-09-02 18:36 ` David Brown 2011-09-02 17:32 ` [RFC 6/7] iommu/core: add fault reporting Ohad Ben-Cohen 2011-09-02 17:32 ` Ohad Ben-Cohen 2011-09-02 17:32 ` Ohad Ben-Cohen 2011-09-05 10:00 ` Roedel, Joerg 2011-09-05 10:00 ` Roedel, Joerg 2011-09-05 10:00 ` Roedel, Joerg 2011-09-07 16:36 ` Ohad Ben-Cohen 2011-09-07 16:36 ` Ohad Ben-Cohen 2011-09-07 16:36 ` Ohad Ben-Cohen 2011-09-02 17:32 ` [RFC 7/7] iommu/core: split mapping to page sizes as supported by the hardware Ohad Ben-Cohen 2011-09-02 17:32 ` Ohad Ben-Cohen 2011-09-02 17:32 ` Ohad Ben-Cohen 2011-09-07 1:30 ` KyongHo Cho 2011-09-07 1:30 ` KyongHo Cho 2011-09-07 6:01 ` Ohad Ben-Cohen 2011-09-07 6:01 ` Ohad Ben-Cohen 2011-09-07 8:05 ` KyongHo Cho 2011-09-07 8:05 ` KyongHo Cho 2011-09-07 9:16 ` Ohad Ben-Cohen 2011-09-07 9:16 ` Ohad Ben-Cohen 2011-09-08 12:51 ` KyongHo Cho [this message] 2011-09-08 12:51 ` KyongHo Cho 2011-09-08 14:03 ` Ohad Ben-Cohen 2011-09-08 14:03 ` Ohad Ben-Cohen 2011-09-07 9:49 ` Ohad Ben-Cohen 2011-09-07 9:49 ` Ohad Ben-Cohen 2011-09-06 10:15 ` [PATCH/RFC 0/7] iommu: fixes & extensions Roedel, Joerg 2011-09-06 10:15 ` Roedel, Joerg 2011-09-06 10:15 ` Roedel, Joerg 2011-09-06 11:28 ` Ohad Ben-Cohen 2011-09-06 11:28 ` Ohad Ben-Cohen 2011-09-06 11:28 ` Ohad Ben-Cohen
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=CAHQjnONUvBtKSMxiDf5Mk+DLqfrTr09Us11rWoaR1mVZeiAmnA@mail.gmail.com \ --to=pullip.cho@samsung.com \ --cc=Hiroshi.DOYU@nokia.com \ --cc=Joerg.Roedel@amd.com \ --cc=arnd@arndb.de \ --cc=davidb@codeaurora.org \ --cc=dwmw2@infradead.org \ --cc=iommu@lists.linux-foundation.org \ --cc=laurent.pinchart@ideasonboard.com \ --cc=linux-arm-kernel@lists.infradead.org \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-omap@vger.kernel.org \ --cc=ohad@wizery.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
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.