From: Alexey Kardashevskiy <aik@ozlabs.ru>
To: linuxppc-dev@lists.ozlabs.org
Cc: Alexey Kardashevskiy <aik@ozlabs.ru>,
Robin Murphy <robin.murphy@arm.com>,
Michael Ellerman <mpe@ellerman.id.au>,
Lu Baolu <baolu.lu@linux.intel.com>,
Kevin Tian <kevin.tian@intel.com>, Joerg Roedel <jroedel@suse.de>,
Jason Gunthorpe <jgg@ziepe.ca>,
Fabiano Rosas <farosas@linux.ibm.com>,
Daniel Henrique Barboza <danielhb413@gmail.com>,
Murilo Opsfelder Araujo <muriloo@linux.ibm.com>,
Alex Williamson <alex.williamson@redhat.com>,
kvm-ppc@vger.kernel.org, kvm@vger.kernel.org,
iommu@lists.linux-foundation.org
Subject: [PATCH kernel] powerpc/iommu: Add simple iommu_ops to report capabilities
Date: Tue, 05 Jul 2022 06:22:35 +0000 [thread overview]
Message-ID: <20220705062235.2276125-1-aik@ozlabs.ru> (raw)
Historically PPC64 managed to avoid using iommu_ops. The VFIO driver
uses a SPAPR TCE sub-driver and all iommu_ops uses were kept in
the Type1 VFIO driver. Recent development though has added a coherency
capability check to the generic part of VFIO and essentially disabled
VFIO on PPC64.
This adds a simple iommu_ops stub which reports support for cache
coherency. Because bus_set_iommu() triggers IOMMU probing of PCI devices,
this provides minimum code for the probing to not crash.
The previous discussion is here:
https://patchwork.ozlabs.org/project/kvm-ppc/patch/20220701061751.1955857-1-aik@ozlabs.ru/
Fixes: e8ae0e140c05 ("vfio: Require that devices support DMA cache coherence")
Fixes: 70693f470848 ("vfio: Set DMA ownership for VFIO devices")
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
I have not looked into the domains for ages, what is missing here? With this
on top of 5.19-rc1 VFIO works again on my POWER9 box. Thanks,
---
arch/powerpc/include/asm/iommu.h | 2 +
arch/powerpc/kernel/iommu.c | 70 ++++++++++++++++++++++++++++++++
arch/powerpc/kernel/pci_64.c | 3 ++
3 files changed, 75 insertions(+)
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 7e29c73e3dd4..4bdae0ee29d0 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -215,6 +215,8 @@ extern long iommu_tce_xchg_no_kill(struct mm_struct *mm,
enum dma_data_direction *direction);
extern void iommu_tce_kill(struct iommu_table *tbl,
unsigned long entry, unsigned long pages);
+
+extern const struct iommu_ops spapr_tce_iommu_ops;
#else
static inline void iommu_register_group(struct iommu_table_group *table_group,
int pci_domain_number,
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 7e56ddb3e0b9..2205b448f7d5 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -1176,4 +1176,74 @@ void iommu_del_device(struct device *dev)
iommu_group_remove_device(dev);
}
EXPORT_SYMBOL_GPL(iommu_del_device);
+
+/*
+ * A simple iommu_ops to allow less cruft in generic VFIO code.
+ */
+static bool spapr_tce_iommu_capable(enum iommu_cap cap)
+{
+ switch (cap) {
+ case IOMMU_CAP_CACHE_COHERENCY:
+ return true;
+ default:
+ break;
+ }
+
+ return false;
+}
+
+static struct iommu_domain *spapr_tce_iommu_domain_alloc(unsigned int type)
+{
+ struct iommu_domain *domain = kzalloc(sizeof(*domain), GFP_KERNEL);
+
+ if (!domain)
+ return NULL;
+
+ domain->geometry.aperture_start = 0;
+ domain->geometry.aperture_end = ~0ULL;
+ domain->geometry.force_aperture = true;
+
+ return domain;
+}
+
+static struct iommu_device *spapr_tce_iommu_probe_device(struct device *dev)
+{
+ struct iommu_device *iommu_dev = kzalloc(sizeof(struct iommu_device), GFP_KERNEL);
+
+ iommu_dev->dev = dev;
+ iommu_dev->ops = &spapr_tce_iommu_ops;
+
+ return iommu_dev;
+}
+
+static void spapr_tce_iommu_release_device(struct device *dev)
+{
+}
+
+static int spapr_tce_iommu_attach_dev(struct iommu_domain *dom,
+ struct device *dev)
+{
+ return 0;
+}
+
+static struct iommu_group *spapr_tce_iommu_device_group(struct device *dev)
+{
+ struct iommu_group *grp = dev->iommu_group;
+
+ if (!grp)
+ grp = ERR_PTR(-ENODEV);
+ return grp;
+}
+
+const struct iommu_ops spapr_tce_iommu_ops = {
+ .capable = spapr_tce_iommu_capable,
+ .domain_alloc = spapr_tce_iommu_domain_alloc,
+ .probe_device = spapr_tce_iommu_probe_device,
+ .release_device = spapr_tce_iommu_release_device,
+ .device_group = spapr_tce_iommu_device_group,
+ .default_domain_ops = &(const struct iommu_domain_ops) {
+ .attach_dev = spapr_tce_iommu_attach_dev,
+ }
+};
+
#endif /* CONFIG_IOMMU_API */
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index 19b03ddf5631..04bc0c52e45c 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -20,6 +20,7 @@
#include <linux/irq.h>
#include <linux/vmalloc.h>
#include <linux/of.h>
+#include <linux/iommu.h>
#include <asm/processor.h>
#include <asm/io.h>
@@ -27,6 +28,7 @@
#include <asm/byteorder.h>
#include <asm/machdep.h>
#include <asm/ppc-pci.h>
+#include <asm/iommu.h>
/* pci_io_base -- the base address from which io bars are offsets.
* This is the lowest I/O base address (so bar values are always positive),
@@ -69,6 +71,7 @@ static int __init pcibios_init(void)
ppc_md.pcibios_fixup();
printk(KERN_DEBUG "PCI: Probing PCI hardware done\n");
+ bus_set_iommu(&pci_bus_type, &spapr_tce_iommu_ops);
return 0;
}
--
2.30.2
next reply other threads:[~2022-07-05 6:22 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-07-05 6:22 Alexey Kardashevskiy [this message]
2022-07-05 9:41 ` [PATCH kernel] powerpc/iommu: Add simple iommu_ops to report capabilities Robin Murphy
2022-07-05 11:57 ` Jason Gunthorpe
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=20220705062235.2276125-1-aik@ozlabs.ru \
--to=aik@ozlabs.ru \
--cc=alex.williamson@redhat.com \
--cc=baolu.lu@linux.intel.com \
--cc=danielhb413@gmail.com \
--cc=farosas@linux.ibm.com \
--cc=iommu@lists.linux-foundation.org \
--cc=jgg@ziepe.ca \
--cc=jroedel@suse.de \
--cc=kevin.tian@intel.com \
--cc=kvm-ppc@vger.kernel.org \
--cc=kvm@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=mpe@ellerman.id.au \
--cc=muriloo@linux.ibm.com \
--cc=robin.murphy@arm.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: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).