From: Alexey Kardashevskiy <aik@ozlabs.ru> To: Ram Pai <linuxram@us.ibm.com>, mpe@ellerman.id.au Cc: linuxppc-dev@lists.ozlabs.org, benh@kernel.crashing.org, david@gibson.dropbear.id.au, paulus@ozlabs.org, mdroth@linux.vnet.ibm.com, hch@lst.de, andmike@us.ibm.com, sukadev@linux.vnet.ibm.com, mst@redhat.com, ram.n.pai@gmail.com, cai@lca.pw, tglx@linutronix.de, bauerman@linux.ibm.com, linux-kernel@vger.kernel.org, leonardo@linux.ibm.com Subject: Re: [PATCH v5 2/2] powerpc/pseries/iommu: Use dma_iommu_ops for Secure VM. Date: Tue, 10 Dec 2019 14:08:52 +1100 [thread overview] Message-ID: <5ee813ba-8f83-efd1-074c-1d9b2cb24334@ozlabs.ru> (raw) In-Reply-To: <1575681159-30356-3-git-send-email-linuxram@us.ibm.com> On 07/12/2019 12:12, Ram Pai wrote: > Commit edea902c1c1e ("powerpc/pseries/iommu: Don't use dma_iommu_ops on > secure guests") > disabled dma_iommu_ops path, for secure VMs. Disabling dma_iommu_ops > path for secure VMs, helped enable dma_direct path. This enabled > support for bounce-buffering through SWIOTLB. However it fails to > operate when IOMMU is enabled, since I/O pages are not TCE mapped. > > Renable dma_iommu_ops path for pseries Secure VMs. It handles all > cases including, TCE mapping I/O pages, in the presence of a > IOMMU. > > Signed-off-by: Ram Pai <linuxram@us.ibm.com> Reviewed-by: Alexey Kardashevskiy <aik@ozlabs.ru> Although I still do not totally understand the mechanics of this (swiotlb on top of huge DDW at 0x800.0000.0000.0000), this change looks reasonable anyway. > --- > arch/powerpc/platforms/pseries/iommu.c | 11 +---------- > 1 file changed, 1 insertion(+), 10 deletions(-) > > diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c > index 67b5009..4e27d66 100644 > --- a/arch/powerpc/platforms/pseries/iommu.c > +++ b/arch/powerpc/platforms/pseries/iommu.c > @@ -36,7 +36,6 @@ > #include <asm/udbg.h> > #include <asm/mmzone.h> > #include <asm/plpar_wrappers.h> > -#include <asm/svm.h> > #include <asm/ultravisor.h> > > #include "pseries.h" > @@ -1346,15 +1345,7 @@ void iommu_init_early_pSeries(void) > of_reconfig_notifier_register(&iommu_reconfig_nb); > register_memory_notifier(&iommu_mem_nb); > > - /* > - * Secure guest memory is inacessible to devices so regular DMA isn't > - * possible. > - * > - * In that case keep devices' dma_map_ops as NULL so that the generic > - * DMA code path will use SWIOTLB to bounce buffers for DMA. > - */ > - if (!is_secure_guest()) > - set_pci_dma_ops(&dma_iommu_ops); > + set_pci_dma_ops(&dma_iommu_ops); > } > > static int __init disable_multitce(char *str) > -- Alexey
WARNING: multiple messages have this Message-ID (diff)
From: Alexey Kardashevskiy <aik@ozlabs.ru> To: Ram Pai <linuxram@us.ibm.com>, mpe@ellerman.id.au Cc: andmike@us.ibm.com, mst@redhat.com, mdroth@linux.vnet.ibm.com, linux-kernel@vger.kernel.org, ram.n.pai@gmail.com, leonardo@linux.ibm.com, cai@lca.pw, tglx@linutronix.de, sukadev@linux.vnet.ibm.com, linuxppc-dev@lists.ozlabs.org, hch@lst.de, bauerman@linux.ibm.com, david@gibson.dropbear.id.au Subject: Re: [PATCH v5 2/2] powerpc/pseries/iommu: Use dma_iommu_ops for Secure VM. Date: Tue, 10 Dec 2019 14:08:52 +1100 [thread overview] Message-ID: <5ee813ba-8f83-efd1-074c-1d9b2cb24334@ozlabs.ru> (raw) In-Reply-To: <1575681159-30356-3-git-send-email-linuxram@us.ibm.com> On 07/12/2019 12:12, Ram Pai wrote: > Commit edea902c1c1e ("powerpc/pseries/iommu: Don't use dma_iommu_ops on > secure guests") > disabled dma_iommu_ops path, for secure VMs. Disabling dma_iommu_ops > path for secure VMs, helped enable dma_direct path. This enabled > support for bounce-buffering through SWIOTLB. However it fails to > operate when IOMMU is enabled, since I/O pages are not TCE mapped. > > Renable dma_iommu_ops path for pseries Secure VMs. It handles all > cases including, TCE mapping I/O pages, in the presence of a > IOMMU. > > Signed-off-by: Ram Pai <linuxram@us.ibm.com> Reviewed-by: Alexey Kardashevskiy <aik@ozlabs.ru> Although I still do not totally understand the mechanics of this (swiotlb on top of huge DDW at 0x800.0000.0000.0000), this change looks reasonable anyway. > --- > arch/powerpc/platforms/pseries/iommu.c | 11 +---------- > 1 file changed, 1 insertion(+), 10 deletions(-) > > diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c > index 67b5009..4e27d66 100644 > --- a/arch/powerpc/platforms/pseries/iommu.c > +++ b/arch/powerpc/platforms/pseries/iommu.c > @@ -36,7 +36,6 @@ > #include <asm/udbg.h> > #include <asm/mmzone.h> > #include <asm/plpar_wrappers.h> > -#include <asm/svm.h> > #include <asm/ultravisor.h> > > #include "pseries.h" > @@ -1346,15 +1345,7 @@ void iommu_init_early_pSeries(void) > of_reconfig_notifier_register(&iommu_reconfig_nb); > register_memory_notifier(&iommu_mem_nb); > > - /* > - * Secure guest memory is inacessible to devices so regular DMA isn't > - * possible. > - * > - * In that case keep devices' dma_map_ops as NULL so that the generic > - * DMA code path will use SWIOTLB to bounce buffers for DMA. > - */ > - if (!is_secure_guest()) > - set_pci_dma_ops(&dma_iommu_ops); > + set_pci_dma_ops(&dma_iommu_ops); > } > > static int __init disable_multitce(char *str) > -- Alexey
next prev parent reply other threads:[~2019-12-10 3:09 UTC|newest] Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top 2019-12-07 1:12 [PATCH v5 0/2] Enable IOMMU support for pseries Secure VMs Ram Pai 2019-12-07 1:12 ` Ram Pai 2019-12-07 1:12 ` [PATCH v5 1/2] powerpc/pseries/iommu: Share the per-cpu TCE page with the hypervisor Ram Pai 2019-12-07 1:12 ` Ram Pai 2019-12-07 1:12 ` [PATCH v5 2/2] powerpc/pseries/iommu: Use dma_iommu_ops for Secure VM Ram Pai 2019-12-07 1:12 ` Ram Pai 2019-12-10 3:08 ` Alexey Kardashevskiy [this message] 2019-12-10 3:08 ` Alexey Kardashevskiy 2019-12-10 22:09 ` Thiago Jung Bauermann 2019-12-10 22:09 ` Thiago Jung Bauermann 2019-12-11 1:43 ` Michael Roth 2019-12-11 1:43 ` Michael Roth 2019-12-11 8:36 ` Alexey Kardashevskiy 2019-12-11 8:36 ` Alexey Kardashevskiy 2019-12-11 18:07 ` Michael Roth 2019-12-11 18:07 ` Michael Roth 2019-12-11 18:20 ` Christoph Hellwig 2019-12-11 18:20 ` Christoph Hellwig 2019-12-12 6:45 ` Ram Pai 2019-12-12 6:45 ` Ram Pai 2019-12-13 0:19 ` Michael Roth 2019-12-13 0:19 ` Michael Roth 2019-12-10 3:07 ` [PATCH v5 1/2] powerpc/pseries/iommu: Share the per-cpu TCE page with the hypervisor Alexey Kardashevskiy 2019-12-10 3:07 ` Alexey Kardashevskiy 2019-12-10 5:12 ` Ram Pai 2019-12-10 5:12 ` Ram Pai 2019-12-10 5:32 ` Alexey Kardashevskiy 2019-12-10 5:32 ` Alexey Kardashevskiy 2019-12-10 15:35 ` Ram Pai 2019-12-10 15:35 ` Ram Pai 2019-12-11 8:15 ` Alexey Kardashevskiy 2019-12-11 8:15 ` Alexey Kardashevskiy 2019-12-11 20:31 ` Michael Roth 2019-12-11 20:31 ` Michael Roth 2019-12-11 22:47 ` Alexey Kardashevskiy 2019-12-11 22:47 ` Alexey Kardashevskiy 2019-12-12 2:39 ` Alexey Kardashevskiy 2019-12-12 2:39 ` Alexey Kardashevskiy 2019-12-13 0:22 ` Michael Roth 2019-12-13 0:22 ` Michael Roth 2019-12-12 4:11 ` Ram Pai 2019-12-12 4:11 ` Ram Pai
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=5ee813ba-8f83-efd1-074c-1d9b2cb24334@ozlabs.ru \ --to=aik@ozlabs.ru \ --cc=andmike@us.ibm.com \ --cc=bauerman@linux.ibm.com \ --cc=benh@kernel.crashing.org \ --cc=cai@lca.pw \ --cc=david@gibson.dropbear.id.au \ --cc=hch@lst.de \ --cc=leonardo@linux.ibm.com \ --cc=linux-kernel@vger.kernel.org \ --cc=linuxppc-dev@lists.ozlabs.org \ --cc=linuxram@us.ibm.com \ --cc=mdroth@linux.vnet.ibm.com \ --cc=mpe@ellerman.id.au \ --cc=mst@redhat.com \ --cc=paulus@ozlabs.org \ --cc=ram.n.pai@gmail.com \ --cc=sukadev@linux.vnet.ibm.com \ --cc=tglx@linutronix.de \ /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.