[PATCH AUTOSEL 5.5 051/542] iommu/vt-d: Fix off-by-one in PASID allocation

[PATCH AUTOSEL 5.5 051/542] iommu/vt-d: Fix off-by-one in PASID allocation

[Sasha Levin]

From: Jacob Pan <jacob.jun.pan@linux.intel.com>

[ Upstream commit 39d630e332144028f56abba83d94291978e72df1 ]

PASID allocator uses IDR which is exclusive for the end of the
allocation range. There is no need to decrement pasid_max.

Fixes: af39507305fb ("iommu/vt-d: Apply global PASID in SVA")
Reported-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/iommu/intel-svm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
index dca88f9fdf29a..ff7a3f9add325 100644
--- a/drivers/iommu/intel-svm.c
+++ b/drivers/iommu/intel-svm.c
@@ -317,7 +317,7 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
 		/* Do not use PASID 0 in caching mode (virtualised IOMMU) */
 		ret = intel_pasid_alloc_id(svm,
 					   !!cap_caching_mode(iommu->cap),
-					   pasid_max - 1, GFP_KERNEL);
+					   pasid_max, GFP_KERNEL);
 		if (ret < 0) {
 			kfree(svm);
 			kfree(sdev);
-- 
2.20.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH AUTOSEL 5.5 224/542] PCI: Add nr_devfns parameter to pci_add_dma_alias()

[Sasha Levin]

From: James Sewart <jamessewart@arista.com>

[ Upstream commit 09298542cd891b43778db1f65aa3613aa5a562eb ]

Add a "nr_devfns" parameter to pci_add_dma_alias() so it can be used to
create DMA aliases for a range of devfns.

[bhelgaas: incorporate nr_devfns fix from James, update
quirk_pex_vca_alias() and setup_aliases()]
Signed-off-by: James Sewart <jamessewart@arista.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/iommu/amd_iommu.c |  7 ++-----
 drivers/pci/pci.c         | 22 +++++++++++++++++-----
 drivers/pci/quirks.c      | 23 +++++++++--------------
 include/linux/pci.h       |  2 +-
 4 files changed, 29 insertions(+), 25 deletions(-)

diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index bd25674ee4dba..7a6c056b9b9cc 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -230,11 +230,8 @@ static struct pci_dev *setup_aliases(struct device *dev)
 	 */
 	ivrs_alias = amd_iommu_alias_table[pci_dev_id(pdev)];
 	if (ivrs_alias != pci_dev_id(pdev) &&
-	    PCI_BUS_NUM(ivrs_alias) == pdev->bus->number) {
-		pci_add_dma_alias(pdev, ivrs_alias & 0xff);
-		pci_info(pdev, "Added PCI DMA alias %02x.%d\n",
-			PCI_SLOT(ivrs_alias), PCI_FUNC(ivrs_alias));
-	}
+	    PCI_BUS_NUM(ivrs_alias) == pdev->bus->number)
+		pci_add_dma_alias(pdev, ivrs_alias & 0xff, 1);
 
 	clone_aliases(pdev);
 
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 7b5fa2eabe095..951099279192d 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -5998,7 +5998,8 @@ EXPORT_SYMBOL_GPL(pci_pr3_present);
 /**
  * pci_add_dma_alias - Add a DMA devfn alias for a device
  * @dev: the PCI device for which alias is added
- * @devfn: alias slot and function
+ * @devfn_from: alias slot and function
+ * @nr_devfns: number of subsequent devfns to alias
  *
  * This helper encodes an 8-bit devfn as a bit number in dma_alias_mask
  * which is used to program permissible bus-devfn source addresses for DMA
@@ -6014,8 +6015,13 @@ EXPORT_SYMBOL_GPL(pci_pr3_present);
  * cannot be left as a userspace activity).  DMA aliases should therefore
  * be configured via quirks, such as the PCI fixup header quirk.
  */
-void pci_add_dma_alias(struct pci_dev *dev, u8 devfn)
+void pci_add_dma_alias(struct pci_dev *dev, u8 devfn_from, unsigned nr_devfns)
 {
+	int devfn_to;
+
+	nr_devfns = min(nr_devfns, (unsigned) MAX_NR_DEVFNS - devfn_from);
+	devfn_to = devfn_from + nr_devfns - 1;
+
 	if (!dev->dma_alias_mask)
 		dev->dma_alias_mask = bitmap_zalloc(MAX_NR_DEVFNS, GFP_KERNEL);
 	if (!dev->dma_alias_mask) {
@@ -6023,9 +6029,15 @@ void pci_add_dma_alias(struct pci_dev *dev, u8 devfn)
 		return;
 	}
 
-	set_bit(devfn, dev->dma_alias_mask);
-	pci_info(dev, "Enabling fixed DMA alias to %02x.%d\n",
-		 PCI_SLOT(devfn), PCI_FUNC(devfn));
+	bitmap_set(dev->dma_alias_mask, devfn_from, nr_devfns);
+
+	if (nr_devfns == 1)
+		pci_info(dev, "Enabling fixed DMA alias to %02x.%d\n",
+				PCI_SLOT(devfn_from), PCI_FUNC(devfn_from));
+	else if (nr_devfns > 1)
+		pci_info(dev, "Enabling fixed DMA alias for devfn range from %02x.%d to %02x.%d\n",
+				PCI_SLOT(devfn_from), PCI_FUNC(devfn_from),
+				PCI_SLOT(devfn_to), PCI_FUNC(devfn_to));
 }
 
 bool pci_devs_are_dma_aliases(struct pci_dev *dev1, struct pci_dev *dev2)
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index c0b7aa4dc0f51..9aa590eb712fe 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -3927,7 +3927,7 @@ int pci_dev_specific_reset(struct pci_dev *dev, int probe)
 static void quirk_dma_func0_alias(struct pci_dev *dev)
 {
 	if (PCI_FUNC(dev->devfn) != 0)
-		pci_add_dma_alias(dev, PCI_DEVFN(PCI_SLOT(dev->devfn), 0));
+		pci_add_dma_alias(dev, PCI_DEVFN(PCI_SLOT(dev->devfn), 0), 1);
 }
 
 /*
@@ -3941,7 +3941,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_RICOH, 0xe476, quirk_dma_func0_alias);
 static void quirk_dma_func1_alias(struct pci_dev *dev)
 {
 	if (PCI_FUNC(dev->devfn) != 1)
-		pci_add_dma_alias(dev, PCI_DEVFN(PCI_SLOT(dev->devfn), 1));
+		pci_add_dma_alias(dev, PCI_DEVFN(PCI_SLOT(dev->devfn), 1), 1);
 }
 
 /*
@@ -4026,7 +4026,7 @@ static void quirk_fixed_dma_alias(struct pci_dev *dev)
 
 	id = pci_match_id(fixed_dma_alias_tbl, dev);
 	if (id)
-		pci_add_dma_alias(dev, id->driver_data);
+		pci_add_dma_alias(dev, id->driver_data, 1);
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ADAPTEC2, 0x0285, quirk_fixed_dma_alias);
 
@@ -4067,9 +4067,9 @@ DECLARE_PCI_FIXUP_HEADER(0x8086, 0x244e, quirk_use_pcie_bridge_dma_alias);
  */
 static void quirk_mic_x200_dma_alias(struct pci_dev *pdev)
 {
-	pci_add_dma_alias(pdev, PCI_DEVFN(0x10, 0x0));
-	pci_add_dma_alias(pdev, PCI_DEVFN(0x11, 0x0));
-	pci_add_dma_alias(pdev, PCI_DEVFN(0x12, 0x3));
+	pci_add_dma_alias(pdev, PCI_DEVFN(0x10, 0x0), 1);
+	pci_add_dma_alias(pdev, PCI_DEVFN(0x11, 0x0), 1);
+	pci_add_dma_alias(pdev, PCI_DEVFN(0x12, 0x3), 1);
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2260, quirk_mic_x200_dma_alias);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2264, quirk_mic_x200_dma_alias);
@@ -4093,13 +4093,8 @@ static void quirk_pex_vca_alias(struct pci_dev *pdev)
 	const unsigned int num_pci_slots = 0x20;
 	unsigned int slot;
 
-	for (slot = 0; slot < num_pci_slots; slot++) {
-		pci_add_dma_alias(pdev, PCI_DEVFN(slot, 0x0));
-		pci_add_dma_alias(pdev, PCI_DEVFN(slot, 0x1));
-		pci_add_dma_alias(pdev, PCI_DEVFN(slot, 0x2));
-		pci_add_dma_alias(pdev, PCI_DEVFN(slot, 0x3));
-		pci_add_dma_alias(pdev, PCI_DEVFN(slot, 0x4));
-	}
+	for (slot = 0; slot < num_pci_slots; slot++)
+		pci_add_dma_alias(pdev, PCI_DEVFN(slot, 0x0), 5);
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2954, quirk_pex_vca_alias);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2955, quirk_pex_vca_alias);
@@ -5334,7 +5329,7 @@ static void quirk_switchtec_ntb_dma_alias(struct pci_dev *pdev)
 			pci_dbg(pdev,
 				"Aliasing Partition %d Proxy ID %02x.%d\n",
 				pp, PCI_SLOT(devfn), PCI_FUNC(devfn));
-			pci_add_dma_alias(pdev, devfn);
+			pci_add_dma_alias(pdev, devfn, 1);
 		}
 	}
 
diff --git a/include/linux/pci.h b/include/linux/pci.h
index c393dff2d66f6..930fab2930736 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -2310,7 +2310,7 @@ static inline struct eeh_dev *pci_dev_to_eeh_dev(struct pci_dev *pdev)
 }
 #endif
 
-void pci_add_dma_alias(struct pci_dev *dev, u8 devfn);
+void pci_add_dma_alias(struct pci_dev *dev, u8 devfn_from, unsigned nr_devfns);
 bool pci_devs_are_dma_aliases(struct pci_dev *dev1, struct pci_dev *dev2);
 int pci_for_each_dma_alias(struct pci_dev *pdev,
 			   int (*fn)(struct pci_dev *pdev,
-- 
2.20.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH AUTOSEL 5.5 254/542] iommu/amd: Check feature support bit before accessing MSI capability registers

[Sasha Levin]

From: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>

[ Upstream commit 813071438e83d338ba5cfe98b3b26c890dc0a6c0 ]

The IOMMU MMIO access to MSI capability registers is available only if
the EFR[MsiCapMmioSup] is set. Current implementation assumes this bit
is set if the EFR[XtSup] is set, which might not be the case.

Fix by checking the EFR[MsiCapMmioSup] before accessing the MSI address
low/high and MSI data registers via the MMIO.

Fixes: 66929812955b ('iommu/amd: Add support for X2APIC IOMMU interrupts')
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/iommu/amd_iommu_init.c  | 17 ++++++++++++-----
 drivers/iommu/amd_iommu_types.h |  1 +
 2 files changed, 13 insertions(+), 5 deletions(-)

diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 483f7bc379fa8..61628c906ce11 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -147,7 +147,7 @@ bool amd_iommu_dump;
 bool amd_iommu_irq_remap __read_mostly;
 
 int amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_VAPIC;
-static int amd_iommu_xt_mode = IRQ_REMAP_X2APIC_MODE;
+static int amd_iommu_xt_mode = IRQ_REMAP_XAPIC_MODE;
 
 static bool amd_iommu_detected;
 static bool __initdata amd_iommu_disabled;
@@ -1534,8 +1534,15 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
 			iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET;
 		if (((h->efr_reg & (0x1 << IOMMU_EFR_GASUP_SHIFT)) == 0))
 			amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY;
-		if (((h->efr_reg & (0x1 << IOMMU_EFR_XTSUP_SHIFT)) == 0))
-			amd_iommu_xt_mode = IRQ_REMAP_XAPIC_MODE;
+		/*
+		 * Note: Since iommu_update_intcapxt() leverages
+		 * the IOMMU MMIO access to MSI capability block registers
+		 * for MSI address lo/hi/data, we need to check both
+		 * EFR[XtSup] and EFR[MsiCapMmioSup] for x2APIC support.
+		 */
+		if ((h->efr_reg & BIT(IOMMU_EFR_XTSUP_SHIFT)) &&
+		    (h->efr_reg & BIT(IOMMU_EFR_MSICAPMMIOSUP_SHIFT)))
+			amd_iommu_xt_mode = IRQ_REMAP_X2APIC_MODE;
 		break;
 	default:
 		return -EINVAL;
@@ -1996,8 +2003,8 @@ static int iommu_init_intcapxt(struct amd_iommu *iommu)
 	struct irq_affinity_notify *notify = &iommu->intcapxt_notify;
 
 	/**
-	 * IntCapXT requires XTSup=1, which can be inferred
-	 * amd_iommu_xt_mode.
+	 * IntCapXT requires XTSup=1 and MsiCapMmioSup=1,
+	 * which can be inferred from amd_iommu_xt_mode.
 	 */
 	if (amd_iommu_xt_mode != IRQ_REMAP_X2APIC_MODE)
 		return 0;
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index f52f59d5c6bd4..f8a7945f3df90 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -383,6 +383,7 @@
 /* IOMMU Extended Feature Register (EFR) */
 #define IOMMU_EFR_XTSUP_SHIFT	2
 #define IOMMU_EFR_GASUP_SHIFT	7
+#define IOMMU_EFR_MSICAPMMIOSUP_SHIFT	46
 
 #define MAX_DOMAIN_ID 65536
 
-- 
2.20.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH AUTOSEL 5.5 255/542] iommu/amd: Only support x2APIC with IVHD type 11h/40h

[Sasha Levin]

From: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>

[ Upstream commit 966b753cf3969553ca50bacd2b8c4ddade5ecc9e ]

Current implementation for IOMMU x2APIC support makes use of
the MMIO access to MSI capability block registers, which requires
checking EFR[MsiCapMmioSup]. However, only IVHD type 11h/40h contain
the information, and not in the IVHD type 10h IOMMU feature reporting
field. Since the BIOS in newer systems, which supports x2APIC, would
normally contain IVHD type 11h/40h, remove the IOMMU_FEAT_XTSUP_SHIFT
check for IVHD type 10h, and only support x2APIC with IVHD type 11h/40h.

Fixes: 66929812955b ('iommu/amd: Add support for X2APIC IOMMU interrupts')
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/iommu/amd_iommu_init.c  | 2 --
 drivers/iommu/amd_iommu_types.h | 1 -
 2 files changed, 3 deletions(-)

diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 61628c906ce11..d7cbca8bf2cd4 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -1523,8 +1523,6 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
 			iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET;
 		if (((h->efr_attr & (0x1 << IOMMU_FEAT_GASUP_SHIFT)) == 0))
 			amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY;
-		if (((h->efr_attr & (0x1 << IOMMU_FEAT_XTSUP_SHIFT)) == 0))
-			amd_iommu_xt_mode = IRQ_REMAP_XAPIC_MODE;
 		break;
 	case 0x11:
 	case 0x40:
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index f8a7945f3df90..798e1533a1471 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -377,7 +377,6 @@
 #define IOMMU_CAP_EFR     27
 
 /* IOMMU Feature Reporting Field (for IVHD type 10h */
-#define IOMMU_FEAT_XTSUP_SHIFT	0
 #define IOMMU_FEAT_GASUP_SHIFT	6
 
 /* IOMMU Extended Feature Register (EFR) */
-- 
2.20.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH AUTOSEL 5.5 256/542] iommu/iova: Silence warnings under memory pressure

[Sasha Levin]

From: Qian Cai <cai@lca.pw>

[ Upstream commit 944c9175397476199d4dd1028d87ddc582c35ee8 ]

When running heavy memory pressure workloads, this 5+ old system is
throwing endless warnings below because disk IO is too slow to recover
from swapping. Since the volume from alloc_iova_fast() could be large,
once it calls printk(), it will trigger disk IO (writing to the log
files) and pending softirqs which could cause an infinite loop and make
no progress for days by the ongoimng memory reclaim. This is the counter
part for Intel where the AMD part has already been merged. See the
commit 3d708895325b ("iommu/amd: Silence warnings under memory
pressure"). Since the allocation failure will be reported in
intel_alloc_iova(), so just call dev_err_once() there because even the
"ratelimited" is too much, and silence the one in alloc_iova_mem() to
avoid the expensive warn_alloc().

 hpsa 0000:03:00.0: DMAR: Allocating 1-page iova failed
 hpsa 0000:03:00.0: DMAR: Allocating 1-page iova failed
 hpsa 0000:03:00.0: DMAR: Allocating 1-page iova failed
 hpsa 0000:03:00.0: DMAR: Allocating 1-page iova failed
 hpsa 0000:03:00.0: DMAR: Allocating 1-page iova failed
 hpsa 0000:03:00.0: DMAR: Allocating 1-page iova failed
 hpsa 0000:03:00.0: DMAR: Allocating 1-page iova failed
 hpsa 0000:03:00.0: DMAR: Allocating 1-page iova failed
 slab_out_of_memory: 66 callbacks suppressed
 SLUB: Unable to allocate memory on node -1, gfp=0xa20(GFP_ATOMIC)
   cache: iommu_iova, object size: 40, buffer size: 448, default order:
0, min order: 0
   node 0: slabs: 1822, objs: 16398, free: 0
   node 1: slabs: 2051, objs: 18459, free: 31
 SLUB: Unable to allocate memory on node -1, gfp=0xa20(GFP_ATOMIC)
   cache: iommu_iova, object size: 40, buffer size: 448, default order:
0, min order: 0
   node 0: slabs: 1822, objs: 16398, free: 0
   node 1: slabs: 2051, objs: 18459, free: 31
 SLUB: Unable to allocate memory on node -1, gfp=0xa20(GFP_ATOMIC)
   cache: iommu_iova, object size: 40, buffer size: 448, default order:
0, min order: 0
 SLUB: Unable to allocate memory on node -1, gfp=0xa20(GFP_ATOMIC)
 SLUB: Unable to allocate memory on node -1, gfp=0xa20(GFP_ATOMIC)
 SLUB: Unable to allocate memory on node -1, gfp=0xa20(GFP_ATOMIC)
 SLUB: Unable to allocate memory on node -1, gfp=0xa20(GFP_ATOMIC)
 SLUB: Unable to allocate memory on node -1, gfp=0xa20(GFP_ATOMIC)
   cache: skbuff_head_cache, object size: 208, buffer size: 640, default
order: 0, min order: 0
   cache: skbuff_head_cache, object size: 208, buffer size: 640, default
order: 0, min order: 0
   cache: skbuff_head_cache, object size: 208, buffer size: 640, default
order: 0, min order: 0
   cache: skbuff_head_cache, object size: 208, buffer size: 640, default
order: 0, min order: 0
   node 0: slabs: 697, objs: 4182, free: 0
   node 0: slabs: 697, objs: 4182, free: 0
   node 0: slabs: 697, objs: 4182, free: 0
   node 0: slabs: 697, objs: 4182, free: 0
   node 1: slabs: 381, objs: 2286, free: 27
   node 1: slabs: 381, objs: 2286, free: 27
   node 1: slabs: 381, objs: 2286, free: 27
   node 1: slabs: 381, objs: 2286, free: 27
   node 0: slabs: 1822, objs: 16398, free: 0
   cache: skbuff_head_cache, object size: 208, buffer size: 640, default
order: 0, min order: 0
   node 1: slabs: 2051, objs: 18459, free: 31
   node 0: slabs: 697, objs: 4182, free: 0
 SLUB: Unable to allocate memory on node -1, gfp=0xa20(GFP_ATOMIC)
   node 1: slabs: 381, objs: 2286, free: 27
   cache: skbuff_head_cache, object size: 208, buffer size: 640, default
order: 0, min order: 0
   node 0: slabs: 697, objs: 4182, free: 0
   node 1: slabs: 381, objs: 2286, free: 27
 hpsa 0000:03:00.0: DMAR: Allocating 1-page iova failed
 warn_alloc: 96 callbacks suppressed
 kworker/11:1H: page allocation failure: order:0,
mode:0xa20(GFP_ATOMIC), nodemask=(null),cpuset=/,mems_allowed=0-1
 CPU: 11 PID: 1642 Comm: kworker/11:1H Tainted: G    B
 Hardware name: HP ProLiant XL420 Gen9/ProLiant XL420 Gen9, BIOS U19
12/27/2015
 Workqueue: kblockd blk_mq_run_work_fn
 Call Trace:
  dump_stack+0xa0/0xea
  warn_alloc.cold.94+0x8a/0x12d
  __alloc_pages_slowpath+0x1750/0x1870
  __alloc_pages_nodemask+0x58a/0x710
  alloc_pages_current+0x9c/0x110
  alloc_slab_page+0xc9/0x760
  allocate_slab+0x48f/0x5d0
  new_slab+0x46/0x70
  ___slab_alloc+0x4ab/0x7b0
  __slab_alloc+0x43/0x70
  kmem_cache_alloc+0x2dd/0x450
 SLUB: Unable to allocate memory on node -1, gfp=0xa20(GFP_ATOMIC)
  alloc_iova+0x33/0x210
   cache: skbuff_head_cache, object size: 208, buffer size: 640, default
order: 0, min order: 0
   node 0: slabs: 697, objs: 4182, free: 0
  alloc_iova_fast+0x62/0x3d1
   node 1: slabs: 381, objs: 2286, free: 27
  intel_alloc_iova+0xce/0xe0
  intel_map_sg+0xed/0x410
  scsi_dma_map+0xd7/0x160
  scsi_queue_rq+0xbf7/0x1310
  blk_mq_dispatch_rq_list+0x4d9/0xbc0
  blk_mq_sched_dispatch_requests+0x24a/0x300
  __blk_mq_run_hw_queue+0x156/0x230
  blk_mq_run_work_fn+0x3b/0x40
  process_one_work+0x579/0xb90
  worker_thread+0x63/0x5b0
  kthread+0x1e6/0x210
  ret_from_fork+0x3a/0x50
 Mem-Info:
 active_anon:2422723 inactive_anon:361971 isolated_anon:34403
  active_file:2285 inactive_file:1838 isolated_file:0
  unevictable:0 dirty:1 writeback:5 unstable:0
  slab_reclaimable:13972 slab_unreclaimable:453879
  mapped:2380 shmem:154 pagetables:6948 bounce:0
  free:19133 free_pcp:7363 free_cma:0

Signed-off-by: Qian Cai <cai@lca.pw>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/iommu/intel-iommu.c | 3 ++-
 drivers/iommu/iova.c        | 2 +-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 932267f49f9a8..541896ab3d086 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -3406,7 +3406,8 @@ static unsigned long intel_alloc_iova(struct device *dev,
 	iova_pfn = alloc_iova_fast(&domain->iovad, nrpages,
 				   IOVA_PFN(dma_mask), true);
 	if (unlikely(!iova_pfn)) {
-		dev_err(dev, "Allocating %ld-page iova failed", nrpages);
+		dev_err_once(dev, "Allocating %ld-page iova failed\n",
+			     nrpages);
 		return 0;
 	}
 
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index c7a914b9bbbc4..0e6a9536eca62 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -233,7 +233,7 @@ static DEFINE_MUTEX(iova_cache_mutex);
 
 struct iova *alloc_iova_mem(void)
 {
-	return kmem_cache_zalloc(iova_cache, GFP_ATOMIC);
+	return kmem_cache_zalloc(iova_cache, GFP_ATOMIC | __GFP_NOWARN);
 }
 EXPORT_SYMBOL(alloc_iova_mem);
 
-- 
2.20.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH AUTOSEL 5.5 291/542] iommu/vt-d: Match CPU and IOMMU paging mode

[Sasha Levin]

From: Jacob Pan <jacob.jun.pan@linux.intel.com>

[ Upstream commit 79db7e1b4cf2a006f556099c13de3b12970fc6e3 ]

When setting up first level page tables for sharing with CPU, we need
to ensure IOMMU can support no less than the levels supported by the
CPU.

It is not adequate, as in the current code, to set up 5-level paging
in PASID entry First Level Paging Mode(FLPM) solely based on CPU.

Currently, intel_pasid_setup_first_level() is only used by native SVM
code which already checks paging mode matches. However, future use of
this helper function may not be limited to native SVM.
https://lkml.org/lkml/2019/11/18/1037

Fixes: 437f35e1cd4c8 ("iommu/vt-d: Add first level page table interface")
Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/iommu/intel-pasid.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/intel-pasid.c b/drivers/iommu/intel-pasid.c
index 040a445be3009..e7cb0b8a73327 100644
--- a/drivers/iommu/intel-pasid.c
+++ b/drivers/iommu/intel-pasid.c
@@ -499,8 +499,16 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu,
 	}
 
 #ifdef CONFIG_X86
-	if (cpu_feature_enabled(X86_FEATURE_LA57))
-		pasid_set_flpm(pte, 1);
+	/* Both CPU and IOMMU paging mode need to match */
+	if (cpu_feature_enabled(X86_FEATURE_LA57)) {
+		if (cap_5lp_support(iommu->cap)) {
+			pasid_set_flpm(pte, 1);
+		} else {
+			pr_err("VT-d has no 5-level paging support for CPU\n");
+			pasid_clear_entry(pte);
+			return -EINVAL;
+		}
+	}
 #endif /* CONFIG_X86 */
 
 	pasid_set_domain_id(pte, did);
-- 
2.20.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH AUTOSEL 5.5 292/542] iommu/vt-d: Avoid sending invalid page response

[Sasha Levin]

From: Jacob Pan <jacob.jun.pan@linux.intel.com>

[ Upstream commit 5f75585e19cc7018bf2016aa771632081ee2f313 ]

Page responses should only be sent when last page in group (LPIG) or
private data is present in the page request. This patch avoids sending
invalid descriptors.

Fixes: 5d308fc1ecf53 ("iommu/vt-d: Add 256-bit invalidation descriptor support")
Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/iommu/intel-svm.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
index ff7a3f9add325..518d0b2d12afd 100644
--- a/drivers/iommu/intel-svm.c
+++ b/drivers/iommu/intel-svm.c
@@ -654,11 +654,10 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 			if (req->priv_data_present)
 				memcpy(&resp.qw2, req->priv_data,
 				       sizeof(req->priv_data));
+			resp.qw2 = 0;
+			resp.qw3 = 0;
+			qi_submit_sync(&resp, iommu);
 		}
-		resp.qw2 = 0;
-		resp.qw3 = 0;
-		qi_submit_sync(&resp, iommu);
-
 		head = (head + sizeof(*req)) & PRQ_RING_MASK;
 	}
 
-- 
2.20.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH AUTOSEL 5.5 312/542] iommu/arm-smmu-v3: Populate VMID field for CMDQ_OP_TLBI_NH_VA

[Sasha Levin]

From: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>

[ Upstream commit 935d43ba272e0001f8ef446a3eff15d8175cb11b ]

CMDQ_OP_TLBI_NH_VA requires VMID and this was missing since
commit 1c27df1c0a82 ("iommu/arm-smmu: Use correct address mask
for CMD_TLBI_S2_IPA"). Add it back.

Fixes: 1c27df1c0a82 ("iommu/arm-smmu: Use correct address mask for CMD_TLBI_S2_IPA")
Signed-off-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/iommu/arm-smmu-v3.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index effe72eb89e7f..2f7680faba49e 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -856,6 +856,7 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
 		cmd[1] |= FIELD_PREP(CMDQ_CFGI_1_RANGE, 31);
 		break;
 	case CMDQ_OP_TLBI_NH_VA:
+		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid);
 		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_ASID, ent->tlbi.asid);
 		cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_LEAF, ent->tlbi.leaf);
 		cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_VA_MASK;
-- 
2.20.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH AUTOSEL 5.5 370/542] iommu/arm-smmu-v3: Use WRITE_ONCE() when changing validity of an STE

[Sasha Levin]

From: Will Deacon <will@kernel.org>

[ Upstream commit d71e01716b3606a6648df7e5646ae12c75babde4 ]

If, for some bizarre reason, the compiler decided to split up the write
of STE DWORD 0, we could end up making a partial structure valid.

Although this probably won't happen, follow the example of the
context-descriptor code and use WRITE_ONCE() to ensure atomicity of the
write.

Reported-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/iommu/arm-smmu-v3.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 2f7680faba49e..6bd6a3f3f4710 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -1643,7 +1643,8 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 						 STRTAB_STE_1_EATS_TRANS));
 
 	arm_smmu_sync_ste_for_sid(smmu, sid);
-	dst[0] = cpu_to_le64(val);
+	/* See comment in arm_smmu_write_ctx_desc() */
+	WRITE_ONCE(dst[0], cpu_to_le64(val));
 	arm_smmu_sync_ste_for_sid(smmu, sid);
 
 	/* It's likely that we'll want to use the new STE soon */
-- 
2.20.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH AUTOSEL 5.5 458/542] iommu/vt-d: Mark firmware tainted if RMRR fails sanity check

[Sasha Levin]

From: Barret Rhoden <brho@google.com>

[ Upstream commit f5a68bb0752e0cf77c06f53f72258e7beb41381b ]

RMRR entries describe memory regions that are DMA targets for devices
outside the kernel's control.

RMRR entries that fail the sanity check are pointing to regions of
memory that the firmware did not tell the kernel are reserved or
otherwise should not be used.

Instead of aborting DMAR processing, this commit marks the firmware
as tainted. These RMRRs will still be identity mapped, otherwise,
some devices, e.x. graphic devices, will not work during boot.

Signed-off-by: Barret Rhoden <brho@google.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Fixes: f036c7fa0ab60 ("iommu/vt-d: Check VT-d RMRR region in BIOS is reported as reserved")
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/iommu/intel-iommu.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 541896ab3d086..dfedbb04f647d 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -4320,12 +4320,16 @@ int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg)
 {
 	struct acpi_dmar_reserved_memory *rmrr;
 	struct dmar_rmrr_unit *rmrru;
-	int ret;
 
 	rmrr = (struct acpi_dmar_reserved_memory *)header;
-	ret = arch_rmrr_sanity_check(rmrr);
-	if (ret)
-		return ret;
+	if (arch_rmrr_sanity_check(rmrr))
+		WARN_TAINT(1, TAINT_FIRMWARE_WORKAROUND,
+			   "Your BIOS is broken; bad RMRR [%#018Lx-%#018Lx]\n"
+			   "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
+			   rmrr->base_address, rmrr->end_address,
+			   dmi_get_system_info(DMI_BIOS_VENDOR),
+			   dmi_get_system_info(DMI_BIOS_VERSION),
+			   dmi_get_system_info(DMI_PRODUCT_VERSION));
 
 	rmrru = kzalloc(sizeof(*rmrru), GFP_KERNEL);
 	if (!rmrru)
-- 
2.20.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH AUTOSEL 5.5 459/542] iommu/vt-d: Remove unnecessary WARN_ON_ONCE()

[Sasha Levin]

From: Lu Baolu <baolu.lu@linux.intel.com>

[ Upstream commit 857f081426e5aa38313426c13373730f1345fe95 ]

Address field in device TLB invalidation descriptor is qualified
by the S field. If S field is zero, a single page at page address
specified by address [63:12] is requested to be invalidated. If S
field is set, the least significant bit in the address field with
value 0b (say bit N) indicates the invalidation address range. The
spec doesn't require the address [N - 1, 0] to be cleared, hence
remove the unnecessary WARN_ON_ONCE().

Otherwise, the caller might set "mask = MAX_AGAW_PFN_WIDTH" in order
to invalidating all the cached mappings on an endpoint, and below
overflow error will be triggered.

[...]
UBSAN: Undefined behaviour in drivers/iommu/dmar.c:1354:3
shift exponent 64 is too large for 64-bit type 'long long unsigned int'
[...]

Reported-and-tested-by: Frank <fgndev@posteo.de>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/iommu/dmar.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 3acfa6a25fa29..fb66f717127d2 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -1354,7 +1354,6 @@ void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid,
 	struct qi_desc desc;
 
 	if (mask) {
-		WARN_ON_ONCE(addr & ((1ULL << (VTD_PAGE_SHIFT + mask)) - 1));
 		addr |= (1ULL << (VTD_PAGE_SHIFT + mask - 1)) - 1;
 		desc.qw1 = QI_DEV_IOTLB_ADDR(addr) | QI_DEV_IOTLB_SIZE;
 	} else
-- 
2.20.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu