linux-kernel - [PATCH v4 17/28] powerpc/pseries/lpar: Enable VFIO

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <1424081180-4494-18-git-send-email-aik@ozlabs.ru>
Date:	Mon, 16 Feb 2015 21:06:09 +1100
From:	Alexey Kardashevskiy <aik@...abs.ru>
To:	linuxppc-dev@...ts.ozlabs.org
Cc:	Alexey Kardashevskiy <aik@...abs.ru>,
	Benjamin Herrenschmidt <benh@...nel.crashing.org>,
	Paul Mackerras <paulus@...ba.org>,
	Alex Williamson <alex.williamson@...hat.com>,
	Gavin Shan <gwshan@...ux.vnet.ibm.com>,
	Alexander Graf <agraf@...e.de>, linux-kernel@...r.kernel.org
Subject: [PATCH v4 17/28] powerpc/pseries/lpar: Enable VFIO

The previous patch introduced iommu_table_ops::exchange() callback
which effectively disabled VFIO on pseries. This implements exchange()
for pseries/lpar so VFIO can work in nested guests.

Since exchange() callback returns an old TCE, it has to call H_GET_TCE
for every TCE being put to the table so VFIO performance in guests
running under PR KVM is expected to be slower than in guests running under
HV KVM or bare metal hosts.

Signed-off-by: Alexey Kardashevskiy <aik@...abs.ru>
---
Changes:
v5:
* added global lock for xchg operations
* added missing be64_to_cpu(oldtce)
---
 arch/powerpc/platforms/pseries/iommu.c | 44 ++++++++++++++++++++++++++++++++--
 1 file changed, 42 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index f537e6e..a903a27 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -137,14 +137,25 @@ static void tce_freemulti_pSeriesLP(struct iommu_table*, long, long);
 
 static int tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum,
 				long npages, unsigned long uaddr,
+				unsigned long *old_tces,
 				enum dma_data_direction direction,
 				struct dma_attrs *attrs)
 {
 	u64 rc = 0;
 	u64 proto_tce, tce;
 	u64 rpn;
-	int ret = 0;
+	int ret = 0, i = 0;
 	long tcenum_start = tcenum, npages_start = npages;
+	static spinlock_t get_tces_lock;
+	static bool get_tces_lock_initialized;
+
+	if (old_tces) {
+		if (!get_tces_lock_initialized) {
+			spin_lock_init(&get_tces_lock);
+			get_tces_lock_initialized = true;
+		}
+		spin_lock(&get_tces_lock);
+	}
 
 	rpn = __pa(uaddr) >> TCE_SHIFT;
 	proto_tce = TCE_PCI_READ;
@@ -153,6 +164,14 @@ static int tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum,
 
 	while (npages--) {
 		tce = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT;
+		if (old_tces) {
+			unsigned long oldtce = 0;
+
+			plpar_tce_get((u64)tbl->it_index, (u64)tcenum << 12,
+					&oldtce);
+			old_tces[i] = be64_to_cpu(oldtce);
+			i++;
+		}
 		rc = plpar_tce_put((u64)tbl->it_index, (u64)tcenum << 12, tce);
 
 		if (unlikely(rc == H_NOT_ENOUGH_RESOURCES)) {
@@ -173,13 +192,18 @@ static int tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		tcenum++;
 		rpn++;
 	}
+
+	if (old_tces)
+		spin_unlock(&get_tces_lock);
+
 	return ret;
 }
 
 static DEFINE_PER_CPU(__be64 *, tce_page);
 
-static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
+static int tce_xchg_pSeriesLP(struct iommu_table *tbl, long tcenum,
 				     long npages, unsigned long uaddr,
+				     unsigned long *old_tces,
 				     enum dma_data_direction direction,
 				     struct dma_attrs *attrs)
 {
@@ -194,6 +218,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 
 	if ((npages == 1) || !firmware_has_feature(FW_FEATURE_MULTITCE)) {
 		return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr,
+					   old_tces,
 		                           direction, attrs);
 	}
 
@@ -210,6 +235,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		if (!tcep) {
 			local_irq_restore(flags);
 			return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr,
+					    old_tces,
 					    direction, attrs);
 		}
 		__this_cpu_write(tce_page, tcep);
@@ -231,6 +257,10 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		for (l = 0; l < limit; l++) {
 			tcep[l] = cpu_to_be64(proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT);
 			rpn++;
+			if (old_tces)
+				plpar_tce_get((u64)tbl->it_index,
+						(u64)(tcenum + l) << 12,
+						&old_tces[tcenum + l]);
 		}
 
 		rc = plpar_tce_put_indirect((u64)tbl->it_index,
@@ -261,6 +291,15 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 	return ret;
 }
 
+static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
+				     long npages, unsigned long uaddr,
+				     enum dma_data_direction direction,
+				     struct dma_attrs *attrs)
+{
+	return tce_xchg_pSeriesLP(tbl, tcenum, npages, uaddr, NULL,
+			direction, attrs);
+}
+
 static void tce_free_pSeriesLP(struct iommu_table *tbl, long tcenum, long npages)
 {
 	u64 rc;
@@ -634,6 +673,7 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
 
 struct iommu_table_ops iommu_table_lpar_multi_ops = {
 	.set = tce_buildmulti_pSeriesLP,
+	.exchange = tce_xchg_pSeriesLP,
 	.clear = tce_freemulti_pSeriesLP,
 	.get = tce_get_pSeriesLP
 };
-- 
2.0.0

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/