summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2013-07-10 14:46:40 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2013-07-10 14:46:40 -0700
commit6664565681a1c0c95607ae2e30070352d9a563d0 (patch)
treefdd60bf602e1c26e87ab25ffd2cc370e0ab51eac
parent496fd15bee6f2fd673ab992e5211c5f3c5bd6779 (diff)
parent01ce784acfa69a171afe6ec3f85a959546f2d18a (diff)
Merge tag 'iommu-updates-v3.11' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu
Pull IOMMU updates from Joerg Roedel: "A few updates this time, most important and exiciting (to me) is: - The new ARM SMMU driver. This is a common IOMMU driver that will hopefully be used in a lot of upcoming ARM chips. So the mess in the past where every SOC had its own IOMMU will be over. Besides that: - Some important fixes in the IOMMU unmap path. There are fixes in the common code and also in the AMD IOMMU driver. - Other random fixes" * tag 'iommu-updates-v3.11' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: MAINTAINERS: add entry for ARM system MMU driver iommu/arm: Add support for ARM Ltd. System MMU architecture documentation/iommu: Add description of ARM System MMU binding iommu: Use %pa and %zx instead of casting iommu/amd: Only unmap large pages from the first pte iommu: Fix compiler warning on pr_debug iommu/amd: Fix memory leak in free_pagetable iommu: Split iommu_unmaps iommu/{vt-d,amd}: Remove multifunction assumption around grouping iommu/omap: fix checkpatch warnings in omap iommu code iommu/omap: fix printk formats for dma_addr_t iommu/vt-d: DMAR reporting table needs at least one DRHD iommu/vt-d: Downgrade the warning if enabling irq remapping fails
-rw-r--r--Documentation/devicetree/bindings/iommu/arm,smmu.txt70
-rw-r--r--MAINTAINERS6
-rw-r--r--drivers/iommu/Kconfig13
-rw-r--r--drivers/iommu/Makefile1
-rw-r--r--drivers/iommu/amd_iommu.c104
-rw-r--r--drivers/iommu/arm-smmu.c1969
-rw-r--r--drivers/iommu/dmar.c4
-rw-r--r--drivers/iommu/intel-iommu.c25
-rw-r--r--drivers/iommu/intel_irq_remapping.c3
-rw-r--r--drivers/iommu/iommu.c86
-rw-r--r--drivers/iommu/omap-iommu.c15
-rw-r--r--drivers/iommu/omap-iopgtable.h2
-rw-r--r--drivers/iommu/omap-iovmm.c4
13 files changed, 2212 insertions, 90 deletions
diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.txt b/Documentation/devicetree/bindings/iommu/arm,smmu.txt
new file mode 100644
index 000000000000..e34c6cdd8ba8
--- /dev/null
+++ b/Documentation/devicetree/bindings/iommu/arm,smmu.txt
@@ -0,0 +1,70 @@
+* ARM System MMU Architecture Implementation
+
+ARM SoCs may contain an implementation of the ARM System Memory
+Management Unit Architecture, which can be used to provide 1 or 2 stages
+of address translation to bus masters external to the CPU.
+
+The SMMU may also raise interrupts in response to various fault
+conditions.
+
+** System MMU required properties:
+
+- compatible : Should be one of:
+
+ "arm,smmu-v1"
+ "arm,smmu-v2"
+ "arm,mmu-400"
+ "arm,mmu-500"
+
+ depending on the particular implementation and/or the
+ version of the architecture implemented.
+
+- reg : Base address and size of the SMMU.
+
+- #global-interrupts : The number of global interrupts exposed by the
+ device.
+
+- interrupts : Interrupt list, with the first #global-irqs entries
+ corresponding to the global interrupts and any
+ following entries corresponding to context interrupts,
+ specified in order of their indexing by the SMMU.
+
+ For SMMUv2 implementations, there must be exactly one
+ interrupt per context bank. In the case of a single,
+ combined interrupt, it must be listed multiple times.
+
+- mmu-masters : A list of phandles to device nodes representing bus
+ masters for which the SMMU can provide a translation
+ and their corresponding StreamIDs (see example below).
+ Each device node linked from this list must have a
+ "#stream-id-cells" property, indicating the number of
+ StreamIDs associated with it.
+
+** System MMU optional properties:
+
+- smmu-parent : When multiple SMMUs are chained together, this
+ property can be used to provide a phandle to the
+ parent SMMU (that is the next SMMU on the path going
+ from the mmu-masters towards memory) node for this
+ SMMU.
+
+Example:
+
+ smmu {
+ compatible = "arm,smmu-v1";
+ reg = <0xba5e0000 0x10000>;
+ #global-interrupts = <2>;
+ interrupts = <0 32 4>,
+ <0 33 4>,
+ <0 34 4>, /* This is the first context interrupt */
+ <0 35 4>,
+ <0 36 4>,
+ <0 37 4>;
+
+ /*
+ * Two DMA controllers, the first with two StreamIDs (0xd01d
+ * and 0xd01e) and the second with only one (0xd11c).
+ */
+ mmu-masters = <&dma0 0xd01d 0xd01e>,
+ <&dma1 0xd11c>;
+ };
diff --git a/MAINTAINERS b/MAINTAINERS
index 37f9a71c744f..af4c3be44ac3 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1333,6 +1333,12 @@ S: Supported
F: arch/arm/mach-zynq/
F: drivers/cpuidle/cpuidle-zynq.c
+ARM SMMU DRIVER
+M: Will Deacon <will.deacon@arm.com>
+L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S: Maintained
+F: drivers/iommu/arm-smmu.c
+
ARM64 PORT (AARCH64 ARCHITECTURE)
M: Catalin Marinas <catalin.marinas@arm.com>
M: Will Deacon <will.deacon@arm.com>
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 01730b2b9954..820d85c4a4a0 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -269,4 +269,17 @@ config SPAPR_TCE_IOMMU
Enables bits of IOMMU API required by VFIO. The iommu_ops
is not implemented as it is not necessary for VFIO.
+config ARM_SMMU
+ bool "ARM Ltd. System MMU (SMMU) Support"
+ depends on ARM64 || (ARM_LPAE && OF)
+ select IOMMU_API
+ select ARM_DMA_USE_IOMMU if ARM
+ help
+ Support for implementations of the ARM System MMU architecture
+ versions 1 and 2. The driver supports both v7l and v8l table
+ formats with 4k and 64k page sizes.
+
+ Say Y here if your SoC includes an IOMMU device implementing
+ the ARM SMMU architecture.
+
endif # IOMMU_SUPPORT
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index ef0e5207ad69..bbe7041212dd 100644
--- a/drivers/iommu/Makefile
+++ b/drivers/iommu/Makefile
@@ -3,6 +3,7 @@ obj-$(CONFIG_OF_IOMMU) += of_iommu.o
obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o msm_iommu_dev.o
obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o
obj-$(CONFIG_AMD_IOMMU_V2) += amd_iommu_v2.o
+obj-$(CONFIG_ARM_SMMU) += arm-smmu.o
obj-$(CONFIG_DMAR_TABLE) += dmar.o
obj-$(CONFIG_INTEL_IOMMU) += iova.o intel-iommu.o
obj-$(CONFIG_IRQ_REMAP) += intel_irq_remapping.o irq_remapping.o
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 21d02b0d907c..6dc659426a51 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -287,14 +287,27 @@ static struct pci_dev *get_isolation_root(struct pci_dev *pdev)
/*
* If it's a multifunction device that does not support our
- * required ACS flags, add to the same group as function 0.
+ * required ACS flags, add to the same group as lowest numbered
+ * function that also does not suport the required ACS flags.
*/
if (dma_pdev->multifunction &&
- !pci_acs_enabled(dma_pdev, REQ_ACS_FLAGS))
- swap_pci_ref(&dma_pdev,
- pci_get_slot(dma_pdev->bus,
- PCI_DEVFN(PCI_SLOT(dma_pdev->devfn),
- 0)));
+ !pci_acs_enabled(dma_pdev, REQ_ACS_FLAGS)) {
+ u8 i, slot = PCI_SLOT(dma_pdev->devfn);
+
+ for (i = 0; i < 8; i++) {
+ struct pci_dev *tmp;
+
+ tmp = pci_get_slot(dma_pdev->bus, PCI_DEVFN(slot, i));
+ if (!tmp)
+ continue;
+
+ if (!pci_acs_enabled(tmp, REQ_ACS_FLAGS)) {
+ swap_pci_ref(&dma_pdev, tmp);
+ break;
+ }
+ pci_dev_put(tmp);
+ }
+ }
/*
* Devices on the root bus go through the iommu. If that's not us,
@@ -1484,6 +1497,10 @@ static unsigned long iommu_unmap_page(struct protection_domain *dom,
/* Large PTE found which maps this address */
unmap_size = PTE_PAGE_SIZE(*pte);
+
+ /* Only unmap from the first pte in the page */
+ if ((unmap_size - 1) & bus_addr)
+ break;
count = PAGE_SIZE_PTE_COUNT(unmap_size);
for (i = 0; i < count; i++)
pte[i] = 0ULL;
@@ -1493,7 +1510,7 @@ static unsigned long iommu_unmap_page(struct protection_domain *dom,
unmapped += unmap_size;
}
- BUG_ON(!is_power_of_2(unmapped));
+ BUG_ON(unmapped && !is_power_of_2(unmapped));
return unmapped;
}
@@ -1893,34 +1910,59 @@ static void domain_id_free(int id)
write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
}
+#define DEFINE_FREE_PT_FN(LVL, FN) \
+static void free_pt_##LVL (unsigned long __pt) \
+{ \
+ unsigned long p; \
+ u64 *pt; \
+ int i; \
+ \
+ pt = (u64 *)__pt; \
+ \
+ for (i = 0; i < 512; ++i) { \
+ if (!IOMMU_PTE_PRESENT(pt[i])) \
+ continue; \
+ \
+ p = (unsigned long)IOMMU_PTE_PAGE(pt[i]); \
+ FN(p); \
+ } \
+ free_page((unsigned long)pt); \
+}
+
+DEFINE_FREE_PT_FN(l2, free_page)
+DEFINE_FREE_PT_FN(l3, free_pt_l2)
+DEFINE_FREE_PT_FN(l4, free_pt_l3)
+DEFINE_FREE_PT_FN(l5, free_pt_l4)
+DEFINE_FREE_PT_FN(l6, free_pt_l5)
+
static void free_pagetable(struct protection_domain *domain)
{
- int i, j;
- u64 *p1, *p2, *p3;
-
- p1 = domain->pt_root;
-
- if (!p1)
- return;
-
- for (i = 0; i < 512; ++i) {
- if (!IOMMU_PTE_PRESENT(p1[i]))
- continue;
-
- p2 = IOMMU_PTE_PAGE(p1[i]);
- for (j = 0; j < 512; ++j) {
- if (!IOMMU_PTE_PRESENT(p2[j]))
- continue;
- p3 = IOMMU_PTE_PAGE(p2[j]);
- free_page((unsigned long)p3);
- }
+ unsigned long root = (unsigned long)domain->pt_root;
- free_page((unsigned long)p2);
+ switch (domain->mode) {
+ case PAGE_MODE_NONE:
+ break;
+ case PAGE_MODE_1_LEVEL:
+ free_page(root);
+ break;
+ case PAGE_MODE_2_LEVEL:
+ free_pt_l2(root);
+ break;
+ case PAGE_MODE_3_LEVEL:
+ free_pt_l3(root);
+ break;
+ case PAGE_MODE_4_LEVEL:
+ free_pt_l4(root);
+ break;
+ case PAGE_MODE_5_LEVEL:
+ free_pt_l5(root);
+ break;
+ case PAGE_MODE_6_LEVEL:
+ free_pt_l6(root);
+ break;
+ default:
+ BUG();
}
-
- free_page((unsigned long)p1);
-
- domain->pt_root = NULL;
}
static void free_gcr3_tbl_level1(u64 *tbl)
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
new file mode 100644
index 000000000000..ebd0a4cff049
--- /dev/null
+++ b/drivers/iommu/arm-smmu.c
@@ -0,0 +1,1969 @@
+/*
+ * IOMMU API for ARM architected SMMU implementations.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) 2013 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ *
+ * This driver currently supports:
+ * - SMMUv1 and v2 implementations
+ * - Stream-matching and stream-indexing
+ * - v7/v8 long-descriptor format
+ * - Non-secure access to the SMMU
+ * - 4k and 64k pages, with contiguous pte hints.
+ * - Up to 39-bit addressing
+ * - Context fault reporting
+ */
+
+#define pr_fmt(fmt) "arm-smmu: " fmt
+
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/iommu.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#include <linux/amba/bus.h>
+
+#include <asm/pgalloc.h>
+
+/* Maximum number of stream IDs assigned to a single device */
+#define MAX_MASTER_STREAMIDS 8
+
+/* Maximum number of context banks per SMMU */
+#define ARM_SMMU_MAX_CBS 128
+
+/* Maximum number of mapping groups per SMMU */
+#define ARM_SMMU_MAX_SMRS 128
+
+/* Number of VMIDs per SMMU */
+#define ARM_SMMU_NUM_VMIDS 256
+
+/* SMMU global address space */
+#define ARM_SMMU_GR0(smmu) ((smmu)->base)
+#define ARM_SMMU_GR1(smmu) ((smmu)->base + (smmu)->pagesize)
+
+/* Page table bits */
+#define ARM_SMMU_PTE_PAGE (((pteval_t)3) << 0)
+#define ARM_SMMU_PTE_CONT (((pteval_t)1) << 52)
+#define ARM_SMMU_PTE_AF (((pteval_t)1) << 10)
+#define ARM_SMMU_PTE_SH_NS (((pteval_t)0) << 8)
+#define ARM_SMMU_PTE_SH_OS (((pteval_t)2) << 8)
+#define ARM_SMMU_PTE_SH_IS (((pteval_t)3) << 8)
+
+#if PAGE_SIZE == SZ_4K
+#define ARM_SMMU_PTE_CONT_ENTRIES 16
+#elif PAGE_SIZE == SZ_64K
+#define ARM_SMMU_PTE_CONT_ENTRIES 32
+#else
+#define ARM_SMMU_PTE_CONT_ENTRIES 1
+#endif
+
+#define ARM_SMMU_PTE_CONT_SIZE (PAGE_SIZE * ARM_SMMU_PTE_CONT_ENTRIES)
+#define ARM_SMMU_PTE_CONT_MASK (~(ARM_SMMU_PTE_CONT_SIZE - 1))
+#define ARM_SMMU_PTE_HWTABLE_SIZE (PTRS_PER_PTE * sizeof(pte_t))
+
+/* Stage-1 PTE */
+#define ARM_SMMU_PTE_AP_UNPRIV (((pteval_t)1) << 6)
+#define ARM_SMMU_PTE_AP_RDONLY (((pteval_t)2) << 6)
+#define ARM_SMMU_PTE_ATTRINDX_SHIFT 2
+
+/* Stage-2 PTE */
+#define ARM_SMMU_PTE_HAP_FAULT (((pteval_t)0) << 6)
+#define ARM_SMMU_PTE_HAP_READ (((pteval_t)1) << 6)
+#define ARM_SMMU_PTE_HAP_WRITE (((pteval_t)2) << 6)
+#define ARM_SMMU_PTE_MEMATTR_OIWB (((pteval_t)0xf) << 2)
+#define ARM_SMMU_PTE_MEMATTR_NC (((pteval_t)0x5) << 2)
+#define ARM_SMMU_PTE_MEMATTR_DEV (((pteval_t)0x1) << 2)
+
+/* Configuration registers */
+#define ARM_SMMU_GR0_sCR0 0x0
+#define sCR0_CLIENTPD (1 << 0)
+#define sCR0_GFRE (1 << 1)
+#define sCR0_GFIE (1 << 2)
+#define sCR0_GCFGFRE (1 << 4)
+#define sCR0_GCFGFIE (1 << 5)
+#define sCR0_USFCFG (1 << 10)
+#define sCR0_VMIDPNE (1 << 11)
+#define sCR0_PTM (1 << 12)
+#define sCR0_FB (1 << 13)
+#define sCR0_BSU_SHIFT 14
+#define sCR0_BSU_MASK 0x3
+
+/* Identification registers */
+#define ARM_SMMU_GR0_ID0 0x20
+#define ARM_SMMU_GR0_ID1 0x24
+#define ARM_SMMU_GR0_ID2 0x28
+#define ARM_SMMU_GR0_ID3 0x2c
+#define ARM_SMMU_GR0_ID4 0x30
+#define ARM_SMMU_GR0_ID5 0x34
+#define ARM_SMMU_GR0_ID6 0x38
+#define ARM_SMMU_GR0_ID7 0x3c
+#define ARM_SMMU_GR0_sGFSR 0x48
+#define ARM_SMMU_GR0_sGFSYNR0 0x50
+#define ARM_SMMU_GR0_sGFSYNR1 0x54
+#define ARM_SMMU_GR0_sGFSYNR2 0x58
+#define ARM_SMMU_GR0_PIDR0 0xfe0
+#define ARM_SMMU_GR0_PIDR1 0xfe4
+#define ARM_SMMU_GR0_PIDR2 0xfe8
+
+#define ID0_S1TS (1 << 30)
+#define ID0_S2TS (1 << 29)
+#define ID0_NTS (1 << 28)
+#define ID0_SMS (1 << 27)
+#define ID0_PTFS_SHIFT 24
+#define ID0_PTFS_MASK 0x2
+#define ID0_PTFS_V8_ONLY 0x2
+#define ID0_CTTW (1 << 14)
+#define ID0_NUMIRPT_SHIFT 16
+#define ID0_NUMIRPT_MASK 0xff
+#define ID0_NUMSMRG_SHIFT 0
+#define ID0_NUMSMRG_MASK 0xff
+
+#define ID1_PAGESIZE (1 << 31)
+#define ID1_NUMPAGENDXB_SHIFT 28
+#define ID1_NUMPAGENDXB_MASK 7
+#define ID1_NUMS2CB_SHIFT 16
+#define ID1_NUMS2CB_MASK 0xff
+#define ID1_NUMCB_SHIFT 0
+#define ID1_NUMCB_MASK 0xff
+
+#define ID2_OAS_SHIFT 4
+#define ID2_OAS_MASK 0xf
+#define ID2_IAS_SHIFT 0
+#define ID2_IAS_MASK 0xf
+#define ID2_UBS_SHIFT 8
+#define ID2_UBS_MASK 0xf
+#define ID2_PTFS_4K (1 << 12)
+#define ID2_PTFS_16K (1 << 13)
+#define ID2_PTFS_64K (1 << 14)
+
+#define PIDR2_ARCH_SHIFT 4
+#define PIDR2_ARCH_MASK 0xf
+
+/* Global TLB invalidation */
+#define ARM_SMMU_GR0_STLBIALL 0x60
+#define ARM_SMMU_GR0_TLBIVMID 0x64
+#define ARM_SMMU_GR0_TLBIALLNSNH 0x68
+#define ARM_SMMU_GR0_TLBIALLH 0x6c
+#define ARM_SMMU_GR0_sTLBGSYNC 0x70
+#define ARM_SMMU_GR0_sTLBGSTATUS 0x74
+#define sTLBGSTATUS_GSACTIVE (1 << 0)
+#define TLB_LOOP_TIMEOUT 1000000 /* 1s! */
+
+/* Stream mapping registers */
+#define ARM_SMMU_GR0_SMR(n) (0x800 + ((n) << 2))
+#define SMR_VALID (1 << 31)
+#define SMR_MASK_SHIFT 16
+#define SMR_MASK_MASK 0x7fff
+#define SMR_ID_SHIFT 0
+#define SMR_ID_MASK 0x7fff
+
+#define ARM_SMMU_GR0_S2CR(n) (0xc00 + ((n) << 2))
+#define S2CR_CBNDX_SHIFT 0
+#define S2CR_CBNDX_MASK 0xff
+#define S2CR_TYPE_SHIFT 16
+#define S2CR_TYPE_MASK 0x3
+#define S2CR_TYPE_TRANS (0 << S2CR_TYPE_SHIFT)
+#define S2CR_TYPE_BYPASS (1 << S2CR_TYPE_SHIFT)
+#define S2CR_TYPE_FAULT (2 << S2CR_TYPE_SHIFT)
+
+/* Context bank attribute registers */
+#define ARM_SMMU_GR1_CBAR(n) (0x0 + ((n) << 2))
+#define CBAR_VMID_SHIFT 0
+#define CBAR_VMID_MASK 0xff
+#define CBAR_S1_MEMATTR_SHIFT 12
+#define CBAR_S1_MEMATTR_MASK 0xf
+#define CBAR_S1_MEMATTR_WB 0xf
+#define CBAR_TYPE_SHIFT 16
+#define CBAR_TYPE_MASK 0x3
+#define CBAR_TYPE_S2_TRANS (0 << CBAR_TYPE_SHIFT)
+#define CBAR_TYPE_S1_TRANS_S2_BYPASS (1 << CBAR_TYPE_SHIFT)
+#define CBAR_TYPE_S1_TRANS_S2_FAULT (2 << CBAR_TYPE_SHIFT)
+#define CBAR_TYPE_S1_TRANS_S2_TRANS (3 << CBAR_TYPE_SHIFT)
+#define CBAR_IRPTNDX_SHIFT 24
+#define CBAR_IRPTNDX_MASK 0xff
+
+#define ARM_SMMU_GR1_CBA2R(n) (0x800 + ((n) << 2))
+#define CBA2R_RW64_32BIT (0 << 0)
+#define CBA2R_RW64_64BIT (1 << 0)
+
+/* Translation context bank */
+#define ARM_SMMU_CB_BASE(smmu) ((smmu)->base + ((smmu)->size >> 1))
+#define ARM_SMMU_CB(smmu, n) ((n) * (smmu)->pagesize)
+
+#define ARM_SMMU_CB_SCTLR 0x0
+#define ARM_SMMU_CB_RESUME 0x8
+#define ARM_SMMU_CB_TTBCR2 0x10
+#define ARM_SMMU_CB_TTBR0_LO 0x20
+#define ARM_SMMU_CB_TTBR0_HI 0x24
+#define ARM_SMMU_CB_TTBCR 0x30
+#define ARM_SMMU_CB_S1_MAIR0 0x38
+#define ARM_SMMU_CB_FSR 0x58
+#define ARM_SMMU_CB_FAR_LO 0x60
+#define ARM_SMMU_CB_FAR_HI 0x64
+#define ARM_SMMU_CB_FSYNR0 0x68
+
+#define SCTLR_S1_ASIDPNE (1 << 12)
+#define SCTLR_CFCFG (1 << 7)
+#define SCTLR_CFIE (1 << 6)
+#define SCTLR_CFRE (1 << 5)
+#define SCTLR_E (1 << 4)
+#define SCTLR_AFE (1 << 2)
+#define SCTLR_TRE (1 << 1)
+#define SCTLR_M (1 << 0)
+#define SCTLR_EAE_SBOP (SCTLR_AFE | SCTLR_TRE)
+
+#define RESUME_RETRY (0 << 0)
+#define RESUME_TERMINATE (1 << 0)
+
+#define TTBCR_EAE (1 << 31)
+
+#define TTBCR_PASIZE_SHIFT 16
+#define TTBCR_PASIZE_MASK 0x7
+
+#define TTBCR_TG0_4K (0 << 14)
+#define TTBCR_TG0_64K (1 << 14)
+
+#define TTBCR_SH0_SHIFT 12
+#define TTBCR_SH0_MASK 0x3
+#define TTBCR_SH_NS 0
+#define TTBCR_SH_OS 2
+#define TTBCR_SH_IS 3
+
+#define TTBCR_ORGN0_SHIFT 10
+#define TTBCR_IRGN0_SHIFT 8
+#define TTBCR_RGN_MASK 0x3
+#define TTBCR_RGN_NC 0
+#define TTBCR_RGN_WBWA 1
+#define TTBCR_RGN_WT 2
+#define TTBCR_RGN_WB 3
+
+#define TTBCR_SL0_SHIFT 6
+#define TTBCR_SL0_MASK 0x3
+#define TTBCR_SL0_LVL_2 0
+#define TTBCR_SL0_LVL_1 1
+
+#define TTBCR_T1SZ_SHIFT 16
+#define TTBCR_T0SZ_SHIFT 0
+#define TTBCR_SZ_MASK 0xf
+
+#define TTBCR2_SEP_SHIFT 15
+#define TTBCR2_SEP_MASK 0x7
+
+#define TTBCR2_PASIZE_SHIFT 0
+#define TTBCR2_PASIZE_MASK 0x7
+
+/* Common definitions for PASize and SEP fields */
+#define TTBCR2_ADDR_32 0
+#define TTBCR2_ADDR_36 1
+#define TTBCR2_ADDR_40 2
+#define TTBCR2_ADDR_42 3
+#define TTBCR2_ADDR_44 4
+#define TTBCR2_ADDR_48 5
+
+#define MAIR_ATTR_SHIFT(n) ((n) << 3)
+#define MAIR_ATTR_MASK 0xff
+#define MAIR_ATTR_DEVICE 0x04
+#define MAIR_ATTR_NC 0x44
+#define MAIR_ATTR_WBRWA 0xff
+#define MAIR_ATTR_IDX_NC 0
+#define MAIR_ATTR_IDX_CACHE 1
+#define MAIR_ATTR_IDX_DEV 2
+
+#define FSR_MULTI (1 << 31)
+#define FSR_SS (1 << 30)
+#define FSR_UUT (1 << 8)
+#define FSR_ASF (1 << 7)
+#define FSR_TLBLKF (1 << 6)
+#define FSR_TLBMCF (1 << 5)
+#define FSR_EF (1 << 4)
+#define FSR_PF (1 << 3)
+#define FSR_AFF (1 << 2)
+#define FSR_TF (1 << 1)
+
+#define FSR_IGN (FSR_AFF | FSR_ASF | FSR_TLBMCF | \
+ FSR_TLBLKF)
+#define FSR_FAULT (FSR_MULTI | FSR_SS | FSR_UUT | \
+ FSR_EF | FSR_PF | FSR_TF)
+
+#define FSYNR0_WNR (1 << 4)
+
+struct arm_smmu_smr {
+ u8 idx;
+ u16 mask;
+ u16 id;
+};
+
+struct arm_smmu_master {
+ struct device_node *of_node;
+
+ /*
+ * The following is specific to the master's position in the
+ * SMMU chain.
+ */
+ struct rb_node node;
+ int num_streamids;
+ u16 streamids[MAX_MASTER_STREAMIDS];
+
+ /*
+ * We only need to allocate these on the root SMMU, as we
+ * configure unmatched streams to bypass translation.
+ */
+ struct arm_smmu_smr *smrs;
+};
+
+struct arm_smmu_device {
+ struct device *dev;
+ struct device_node *parent_of_node;
+
+ void __iomem *base;
+ unsigned long size;
+ unsigned long pagesize;
+
+#define ARM_SMMU_FEAT_COHERENT_WALK (1 << 0)
+#define ARM_SMMU_FEAT_STREAM_MATCH (1 << 1)
+#define ARM_SMMU_FEAT_TRANS_S1 (1 << 2)
+#define ARM_SMMU_FEAT_TRANS_S2 (1 << 3)
+#define ARM_SMMU_FEAT_TRANS_NESTED (1 << 4)
+ u32 features;
+ int version;
+
+ u32 num_context_banks;
+ u32 num_s2_context_banks;
+ DECLARE_BITMAP(context_map, ARM_SMMU_MAX_CBS);
+ atomic_t irptndx;
+
+ u32 num_mapping_groups;
+ DECLARE_BITMAP(smr_map, ARM_SMMU_MAX_SMRS);
+
+ unsigned long input_size;
+ unsigned long s1_output_size;
+ unsigned long s2_output_size;
+
+ u32 num_global_irqs;
+ u32 num_context_irqs;
+ unsigned int *irqs;
+
+ DECLARE_BITMAP(vmid_map, ARM_SMMU_NUM_VMIDS);
+
+ struct list_head list;
+ struct rb_root masters;
+};
+
+struct arm_smmu_cfg {
+ struct arm_smmu_device *smmu;
+ u8 vmid;
+ u8 cbndx;
+ u8 irptndx;
+ u32 cbar;
+ pgd_t *pgd;
+};
+
+struct arm_smmu_domain {
+ /*
+ * A domain can span across multiple, chained SMMUs and requires
+ * all devices within the domain to follow the same translation
+ * path.
+ */
+ struct arm_smmu_device *leaf_smmu;
+ struct arm_smmu_cfg root_cfg;
+ phys_addr_t output_mask;
+
+ spinlock_t lock;
+};
+
+static DEFINE_SPINLOCK(arm_smmu_devices_lock);
+static LIST_HEAD(arm_smmu_devices);
+
+static struct arm_smmu_master *find_smmu_master(struct arm_smmu_device *smmu,
+ struct device_node *dev_node)
+{
+ struct rb_node *node = smmu->masters.rb_node;
+
+ while (node) {
+ struct arm_smmu_master *master;
+ master = container_of(node, struct arm_smmu_master, node);
+
+ if (dev_node < master->of_node)
+ node = node->rb_left;
+ else if (dev_node > master->of_node)
+ node = node->rb_right;
+ else
+ return master;
+ }
+
+ return NULL;
+}
+
+static int insert_smmu_master(struct arm_smmu_device *smmu,
+ struct arm_smmu_master *master)
+{
+ struct rb_node **new, *parent;
+
+ new = &smmu->masters.rb_node;
+ parent = NULL;
+ while (*new) {
+ struct arm_smmu_master *this;
+ this = container_of(*new, struct arm_smmu_master, node);
+
+ parent = *new;
+ if (master->of_node < this->of_node)
+ new = &((*new)->rb_left);
+ else if (master->of_node > this->of_node)
+ new = &((*new)->rb_right);
+ else
+ return -EEXIST;
+ }
+
+ rb_link_node(&master->node, parent, new);
+ rb_insert_color(&master->node, &smmu->masters);
+ return 0;
+}
+
+static int register_smmu_master(struct arm_smmu_device *smmu,
+ struct device *dev,
+ struct of_phandle_args *masterspec)
+{
+ int i;
+ struct arm_smmu_master *master;
+
+ master = find_smmu_master(smmu, masterspec->np);
+ if (master) {
+ dev_err(dev,
+ "rejecting multiple registrations for master device %s\n",
+ masterspec->np->name);
+ return -EBUSY;
+ }
+
+ if (masterspec->args_count > MAX_MASTER_STREAMIDS) {
+ dev_err(dev,
+ "reached maximum number (%d) of stream IDs for master device %s\n",
+ MAX_MASTER_STREAMIDS, masterspec->np->name);
+ return -ENOSPC;
+ }
+
+ master = devm_kzalloc(dev, sizeof(*master), GFP_KERNEL);
+ if (!master)
+ return -ENOMEM;
+
+ master->of_node = masterspec->np;
+ master->num_streamids = masterspec->args_count;
+
+ for (i = 0; i < master->num_streamids; ++i)
+ master->streamids[i] = masterspec->args[i];
+
+ return insert_smmu_master(smmu, master);
+}
+
+static struct arm_smmu_device *find_parent_smmu(struct arm_smmu_device *smmu)
+{
+ struct arm_smmu_device *parent;
+
+ if (!smmu->parent_of_node)
+ return NULL;
+
+ spin_lock(&arm_smmu_devices_lock);
+ list_for_each_entry(parent, &arm_smmu_devices, list)
+ if (parent->dev->of_node == smmu->parent_of_node)
+ goto out_unlock;
+
+ parent = NULL;
+ dev_warn(smmu->dev,
+ "Failed to find SMMU parent despite parent in DT\n");
+out_unlock:
+ spin_unlock(&arm_smmu_devices_lock);
+ return parent;
+}
+
+static int __arm_smmu_alloc_bitmap(unsigned long *map, int start, int end)
+{
+ int idx;
+
+ do {
+ idx = find_next_zero_bit(map, end, start);
+ if (idx == end)
+ return -ENOSPC;
+ } while (test_and_set_bit(idx, map));
+
+ return idx;
+}
+
+static void __arm_smmu_free_bitmap(unsigned long *map, int idx)
+{
+ clear_bit(idx, map);
+}
+
+/* Wait for any pending TLB invalidations to complete */
+static void arm_smmu_tlb_sync(struct arm_smmu_device *smmu)
+{
+ int count = 0;
+ void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
+
+ writel_relaxed(0, gr0_base + ARM_SMMU_GR0_sTLBGSYNC);
+ while (readl_relaxed(gr0_base + ARM_SMMU_GR0_sTLBGSTATUS)
+ & sTLBGSTATUS_GSACTIVE) {
+ cpu_relax();
+ if (++count == TLB_LOOP_TIMEOUT) {
+ dev_err_ratelimited(smmu->dev,
+ "TLB sync timed out -- SMMU may be deadlocked\n");
+ return;
+ }
+ udelay(1);
+ }
+}
+
+static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
+{
+ int flags, ret;
+ u32 fsr, far, fsynr, resume;
+ unsigned long iova;
+ struct iommu_domain *domain = dev;
+ struct arm_smmu_domain *smmu_domain = domain->priv;
+ struct arm_smmu_cfg *root_cfg = &smmu_domain->root_cfg;
+ struct arm_smmu_device *smmu = root_cfg->smmu;
+ void __iomem *cb_base;
+
+ cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, root_cfg->cbndx);
+ fsr = readl_relaxed(cb_base + ARM_SMMU_CB_FSR);
+
+ if (!(fsr & FSR_FAULT))
+ return IRQ_NONE;
+
+ if (fsr & FSR_IGN)
+ dev_err_ratelimited(smmu->dev,
+ "Unexpected context fault (fsr 0x%u)\n",
+ fsr);
+
+ fsynr = readl_relaxed(cb_base + ARM_SMMU_CB_FSYNR0);
+ flags = fsynr & FSYNR0_WNR ? IOMMU_FAULT_WRITE : IOMMU_FAULT_READ;
+
+ far = readl_relaxed(cb_base + ARM_SMMU_CB_FAR_LO);
+ iova = far;
+#ifdef CONFIG_64BIT
+ far = readl_relaxed(cb_base + ARM_SMMU_CB_FAR_HI);
+ iova |= ((unsigned long)far << 32);
+#endif
+
+ if (!report_iommu_fault(domain, smmu->dev, iova, flags)) {
+ ret = IRQ_HANDLED;
+ resume = RESUME_RETRY;
+ } else {
+ ret = IRQ_NONE;
+ resume = RESUME_TERMINATE;
+ }
+
+ /* Clear the faulting FSR */
+ writel(fsr, cb_base + ARM_SMMU_CB_FSR);
+
+ /* Retry or terminate any stalled transactions */
+ if (fsr & FSR_SS)
+ writel_relaxed(resume, cb_base + ARM_SMMU_CB_RESUME);
+
+ return ret;
+}
+
+static irqreturn_t arm_smmu_global_fault(int irq, void *dev)
+{
+ u32 gfsr, gfsynr0, gfsynr1, gfsynr2;
+ struct arm_smmu_device *smmu = dev;
+ void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
+
+ gfsr = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSR);
+ gfsynr0 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSYNR0);
+ gfsynr1 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSYNR1);
+ gfsynr2 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSYNR2);
+
+ dev_err_ratelimited(smmu->dev,
+ "Unexpected global fault, this could be serious\n");
+ dev_err_ratelimited(smmu->dev,
+ "\tGFSR 0x%08x, GFSYNR0 0x%08x, GFSYNR1 0x%08x, GFSYNR2 0x%08x\n",
+ gfsr, gfsynr0, gfsynr1, gfsynr2);
+
+ writel(gfsr, gr0_base + ARM_SMMU_GR0_sGFSR);
+ return IRQ_NONE;
+}
+
+static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
+{
+ u32 reg;
+ bool stage1;
+ struct arm_smmu_cfg *root_cfg = &smmu_domain->root_cfg;
+ struct arm_smmu_device *smmu = root_cfg->smmu;
+ void __iomem *cb_base, *gr0_base, *gr1_base;
+
+ gr0_base = ARM_SMMU_GR0(smmu);
+ gr1_base = ARM_SMMU_GR1(smmu);
+ stage1 = root_cfg->cbar != CBAR_TYPE_S2_TRANS;
+ cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, root_cfg->cbndx);
+
+ /* CBAR */
+ reg = root_cfg->cbar |
+ (root_cfg->vmid << CBAR_VMID_SHIFT);
+ if (smmu->version == 1)
+ reg |= root_cfg->irptndx << CBAR_IRPTNDX_SHIFT;
+
+ /* Use the weakest memory type, so it is overridden by the pte */
+ if (stage1)
+ reg |= (CBAR_S1_MEMATTR_WB << CBAR_S1_MEMATTR_SHIFT);
+ writel_relaxed(reg, gr1_base + ARM_SMMU_GR1_CBAR(root_cfg->cbndx));
+
+ if (smmu->version > 1) {
+ /* CBA2R */
+#ifdef CONFIG_64BIT
+ reg = CBA2R_RW64_64BIT;
+#else
+ reg = CBA2R_RW64_32BIT;
+#endif
+ writel_relaxed(reg,
+ gr1_base + ARM_SMMU_GR1_CBA2R(root_cfg->cbndx));
+
+ /* TTBCR2 */
+ switch (smmu->input_size) {
+ case 32:
+ reg = (TTBCR2_ADDR_32 << TTBCR2_SEP_SHIFT);
+ break;
+ case 36:
+ reg = (TTBCR2_ADDR_36 << TTBCR2_SEP_SHIFT);
+ break;
+ case 39:
+ reg = (TTBCR2_ADDR_40 << TTBCR2_SEP_SHIFT);
+ break;
+ case 42:
+ reg = (TTBCR2_ADDR_42 << TTBCR2_SEP_SHIFT);
+ break;
+ case 44:
+ reg = (TTBCR2_ADDR_44 << TTBCR2_SEP_SHIFT);
+ break;
+ case 48:
+ reg = (TTBCR2_ADDR_48 << TTBCR2_SEP_SHIFT);
+ break;
+ }
+
+ switch (smmu->s1_output_size) {
+ case 32:
+ reg |= (TTBCR2_ADDR_32 << TTBCR2_PASIZE_SHIFT);
+ break;
+ case 36:
+ reg |= (TTBCR2_ADDR_36 << TTBCR2_PASIZE_SHIFT);
+ break;
+ case 39:
+ reg |= (TTBCR2_ADDR_40 << TTBCR2_PASIZE_SHIFT);
+ break;
+ case 42:
+ reg |= (TTBCR2_ADDR_42 << TTBCR2_PASIZE_SHIFT);
+ break;
+ case 44:
+ reg |= (TTBCR2_ADDR_44 << TTBCR2_PASIZE_SHIFT);
+ break;
+ case 48:
+ reg |= (TTBCR2_ADDR_48 << TTBCR2_PASIZE_SHIFT);
+ break;
+ }
+
+ if (stage1)
+ writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBCR2);
+ }
+
+ /* TTBR0 */
+ reg = __pa(root_cfg->pgd);
+#ifndef __BIG_ENDIAN
+ writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_LO);
+ reg = (phys_addr_t)__pa(root_cfg->pgd) >> 32;
+ writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_HI);
+#else
+ writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_HI);
+ reg = (phys_addr_t)__pa(root_cfg->pgd) >> 32;
+ writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_LO);
+#endif
+
+ /*
+ * TTBCR
+ * We use long descriptor, with inner-shareable WBWA tables in TTBR0.
+ */
+ if (smmu->version > 1) {
+ if (PAGE_SIZE == SZ_4K)
+ reg = TTBCR_TG0_4K;
+ else
+ reg = TTBCR_TG0_64K;
+
+ if (!stage1) {
+ switch (smmu->s2_output_size) {
+ case 32:
+ reg |= (TTBCR2_ADDR_32 << TTBCR_PASIZE_SHIFT);
+ break;
+ case 36:
+ reg |= (TTBCR2_ADDR_36 << TTBCR_PASIZE_SHIFT);
+ break;
+ case 40:
+ reg |= (TTBCR2_ADDR_40 << TTBCR_PASIZE_SHIFT);
+ break;
+ case 42:
+ reg |= (TTBCR2_ADDR_42 << TTBCR_PASIZE_SHIFT);
+ break;
+ case 44:
+ reg |= (TTBCR2_ADDR_44 << TTBCR_PASIZE_SHIFT);
+ break;
+ case 48:
+ reg |= (TTBCR2_ADDR_48 << TTBCR_PASIZE_SHIFT);
+ break;
+ }
+ } else {
+ reg |= (64 - smmu->s1_output_size) << TTBCR_T0SZ_SHIFT;
+ }
+ } else {
+ reg = 0;
+ }
+
+ reg |= TTBCR_EAE |
+ (TTBCR_SH_IS << TTBCR_SH0_SHIFT) |
+ (TTBCR_RGN_WBWA << TTBCR_ORGN0_SHIFT) |
+ (TTBCR_RGN_WBWA << TTBCR_IRGN0_SHIFT) |
+ (TTBCR_SL0_LVL_1 << TTBCR_SL0_SHIFT);
+ writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBCR);
+
+ /* MAIR0 (stage-1 only) */
+ if (stage1) {
+ reg = (MAIR_ATTR_NC << MAIR_ATTR_SHIFT(MAIR_ATTR_IDX_NC)) |
+ (MAIR_ATTR_WBRWA << MAIR_ATTR_SHIFT(MAIR_ATTR_IDX_CACHE)) |
+ (MAIR_ATTR_DEVICE << MAIR_ATTR_SHIFT(MAIR_ATTR_IDX_DEV));
+ writel_relaxed(reg, cb_base + ARM_SMMU_CB_S1_MAIR0);
+ }
+
+ /* Nuke the TLB */
+ writel_relaxed(root_cfg->vmid, gr0_base + ARM_SMMU_GR0_TLBIVMID);
+ arm_smmu_tlb_sync(smmu);
+
+ /* SCTLR */
+ reg = SCTLR_CFCFG | SCTLR_CFIE | SCTLR_CFRE | SCTLR_M | SCTLR_EAE_SBOP;
+ if (stage1)
+ reg |= SCTLR_S1_ASIDPNE;
+#ifdef __BIG_ENDIAN
+ reg |= SCTLR_E;
+#endif
+ writel(reg, cb_base + ARM_SMMU_CB_SCTLR);
+}
+
+static int arm_smmu_init_domain_context(struct iommu_domain *domain,
+ struct device *dev)
+{
+ int irq, ret, start;
+ struct arm_smmu_domain *smmu_domain = domain->priv;
+ struct arm_smmu_cfg *root_cfg = &smmu_domain->root_cfg;
+ struct arm_smmu_device *smmu, *parent;
+
+ /*
+ * Walk the SMMU chain to find the root device for this chain.
+ * We assume that no masters have translations which terminate
+ * early, and therefore check that the root SMMU does indeed have
+ * a StreamID for the master in question.
+ */
+ parent = dev->archdata.iommu;
+ smmu_domain->output_mask = -1;
+ do {
+ smmu = parent;
+ smmu_domain->output_mask &= (1ULL << smmu->s2_output_size) - 1;
+ } while ((parent = find_parent_smmu(smmu)));
+
+ if (!find_smmu_master(smmu, dev->of_node)) {
+ dev_err(dev, "unable to find root SMMU for device\n");
+ return -ENODEV;
+ }
+
+ ret = __arm_smmu_alloc_bitmap(smmu->vmid_map, 0, ARM_SMMU_NUM_VMIDS);
+ if (IS_ERR_VALUE(ret))
+ return ret;
+
+ root_cfg->vmid = ret;
+ if (smmu->features & ARM_SMMU_FEAT_TRANS_NESTED) {
+ /*
+ * We will likely want to change this if/when KVM gets
+ * involved.
+ */
+ root_cfg->cbar = CBAR_TYPE_S1_TRANS_S2_BYPASS;
+ start = smmu->num_s2_context_banks;
+ } else if (smmu->features & ARM_SMMU_FEAT_TRANS_S2) {
+ root_cfg->cbar = CBAR_TYPE_S2_TRANS;
+ start = 0;
+ } else {
+ root_cfg->cbar = CBAR_TYPE_S1_TRANS_S2_BYPASS;
+ start = smmu->num_s2_context_banks;
+ }
+
+ ret = __arm_smmu_alloc_bitmap(smmu->context_map, start,
+ smmu->num_context_banks);
+ if (IS_ERR_VALUE(ret))
+ goto out_free_vmid;
+
+ root_cfg->cbndx = ret;
+
+ if (smmu->version == 1) {
+ root_cfg->irptndx = atomic_inc_return(&smmu->irptndx);
+ root_cfg->irptndx %= smmu->num_context_irqs;
+ } else {
+ root_cfg->irptndx = root_cfg->cbndx;
+ }
+
+ irq = smmu->irqs[smmu->num_global_irqs + root_cfg->irptndx];
+ ret = request_irq(irq, arm_smmu_context_fault, IRQF_SHARED,
+ "arm-smmu-context-fault", domain);
+ if (IS_ERR_VALUE(ret)) {
+ dev_err(smmu->dev, "failed to request context IRQ %d (%u)\n",
+ root_cfg->irptndx, irq);
+ root_cfg->irptndx = -1;
+ goto out_free_context;
+ }
+
+ root_cfg->smmu = smmu;
+ arm_smmu_init_context_bank(smmu_domain);
+ return ret;
+
+out_free_context:
+ __arm_smmu_free_bitmap(smmu->context_map, root_cfg->cbndx);
+out_free_vmid:
+ __arm_smmu_free_bitmap(smmu->vmid_map, root_cfg->vmid);
+ return ret;
+}
+
+static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
+{
+ struct arm_smmu_domain *smmu_domain = domain->priv;
+ struct arm_smmu_cfg *root_cfg = &smmu_domain->root_cfg;
+ struct arm_smmu_device *smmu = root_cfg->smmu;
+ int irq;
+
+ if (!smmu)
+ return;
+
+ if (root_cfg->irptndx != -1) {
+ irq = smmu->irqs[smmu->num_global_irqs + root_cfg->irptndx];
+ free_irq(irq, domain);
+ }
+
+ __arm_smmu_free_bitmap(smmu->vmid_map, root_cfg->vmid);
+ __arm_smmu_free_bitmap(smmu->context_map, root_cfg->cbndx);
+}
+
+static int arm_smmu_domain_init(struct iommu_domain *domain)
+{
+ struct arm_smmu_domain *smmu_domain;
+ pgd_t *pgd;
+
+ /*
+ * Allocate the domain and initialise some of its data structures.
+ * We can't really do anything meaningful until we've added a
+ * master.
+ */
+ smmu_domain = kzalloc(sizeof(*smmu_domain), GFP_KERNEL);
+ if (!smmu_domain)
+ return -ENOMEM;
+
+ pgd = kzalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL);
+ if (!pgd)
+ goto out_free_domain;
+ smmu_domain->root_cfg.pgd = pgd;
+
+ spin_lock_init(&smmu_domain->lock);
+ domain->priv = smmu_domain;
+ return 0;
+
+out_free_domain:
+ kfree(smmu_domain);
+ return -ENOMEM;
+}
+
+static void arm_smmu_free_ptes(pmd_t *pmd)
+{
+ pgtable_t table = pmd_pgtable(*pmd);
+ pgtable_page_dtor(table);
+ __free_page(table);
+}
+
+static void arm_smmu_free_pmds(pud_t *pud)
+{
+ int i;
+ pmd_t *pmd, *pmd_base = pmd_offset(pud, 0);
+
+ pmd = pmd_base;
+ for (i = 0; i < PTRS_PER_PMD; ++i) {
+ if (pmd_none(*pmd))
+ continue;
+
+ arm_smmu_free_ptes(pmd);
+ pmd++;
+ }
+
+ pmd_free(NULL, pmd_base);
+}
+
+static void arm_smmu_free_puds(pgd_t *pgd)
+{
+ int i;
+ pud_t *pud, *pud_base = pud_offset(pgd, 0);
+
+ pud = pud_base;
+ for (i = 0; i < PTRS_PER_PUD; ++i) {
+ if (pud_none(*pud))
+ continue;
+
+ arm_smmu_free_pmds(pud);
+ pud++;
+ }
+
+ pud_free(NULL, pud_base);
+}
+
+static void arm_smmu_free_pgtables(struct arm_smmu_domain *smmu_domain)
+{
+ int i;
+ struct arm_smmu_cfg *root_cfg = &smmu_domain->root_cfg;
+ pgd_t *pgd, *pgd_base = root_cfg->pgd;
+
+ /*
+ * Recursively free the page tables for this domain. We don't
+ * care about speculative TLB filling, because the TLB will be
+ * nuked next time this context bank is re-allocated and no devices
+ * currently map to these tables.
+ */
+ pgd = pgd_base;
+ for (i = 0; i < PTRS_PER_PGD; ++i) {
+ if (pgd_none(*pgd))
+ continue;
+ arm_smmu_free_puds(pgd);
+ pgd++;
+ }
+
+ kfree(pgd_base);
+}
+
+static void arm_smmu_domain_destroy(struct iommu_domain *domain)
+{
+ struct arm_smmu_domain *smmu_domain = domain->priv;
+ arm_smmu_destroy_domain_context(domain);
+ arm_smmu_free_pgtables(smmu_domain);
+ kfree(smmu_domain);
+}
+
+static int arm_smmu_master_configure_smrs(struct arm_smmu_device *smmu,
+ struct arm_smmu_master *master)
+{
+ int i;
+ struct arm_smmu_smr *smrs;
+ void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
+
+ if (!(smmu->features & ARM_SMMU_FEAT_STREAM_MATCH))
+ return 0;
+
+ if (master->smrs)
+ return -EEXIST;
+
+ smrs = kmalloc(sizeof(*smrs) * master->num_streamids, GFP_KERNEL);
+ if (!smrs) {
+ dev_err(smmu->dev, "failed to allocate %d SMRs for master %s\n",
+ master->num_streamids, master->of_node->name);
+ return -ENOMEM;
+ }
+
+ /* Allocate the SMRs on the root SMMU */
+ for (i = 0; i < master->num_streamids; ++i) {
+ int idx = __arm_smmu_alloc_bitmap(smmu->smr_map, 0,
+ smmu->num_mapping_groups);
+ if (IS_ERR_VALUE(idx)) {
+ dev_err(smmu->dev, "failed to allocate free SMR\n");
+ goto err_free_smrs;
+ }
+
+ smrs[i] = (struct arm_smmu_smr) {
+ .idx = idx,
+ .mask = 0, /* We don't currently share SMRs */
+ .id = master->streamids[i],
+ };
+ }
+
+ /* It worked! Now, poke the actual hardware */
+ for (i = 0; i < master->num_streamids; ++i) {
+ u32 reg = SMR_VALID | smrs[i].id << SMR_ID_SHIFT |
+ smrs[i].mask << SMR_MASK_SHIFT;
+ writel_relaxed(reg, gr0_base + ARM_SMMU_GR0_SMR(smrs[i].idx));
+ }
+
+ master->smrs = smrs;
+ return 0;
+
+err_free_smrs:
+ while (--i >= 0)
+ __arm_smmu_free_bitmap(smmu->smr_map, smrs[i].idx);
+ kfree(smrs);
+ return -ENOSPC;
+}
+
+static void arm_smmu_master_free_smrs(struct arm_smmu_device *smmu,
+ struct arm_smmu_master *master)
+{
+ int i;
+ void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
+ struct arm_smmu_smr *smrs = master->smrs;
+
+ /* Invalidate the SMRs before freeing back to the allocator */
+ for (i = 0; i < master->num_streamids; ++i) {
+ u8 idx = smrs[i].idx;
+ writel_relaxed(~SMR_VALID, gr0_base + ARM_SMMU_GR0_SMR(idx));
+ __arm_smmu_free_bitmap(smmu->smr_map, idx);
+ }
+
+ master->smrs = NULL;
+ kfree(smrs);
+}
+
+static void arm_smmu_bypass_stream_mapping(struct arm_smmu_device *smmu,
+ struct arm_smmu_master *master)
+{
+ int i;
+ void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
+
+ for (i = 0; i < master->num_streamids; ++i) {
+ u16 sid = master->streamids[i];
+ writel_relaxed(S2CR_TYPE_BYPASS,
+ gr0_base + ARM_SMMU_GR0_S2CR(sid));
+ }
+}
+
+static int arm_smmu_domain_add_master(struct arm_smmu_domain *smmu_domain,
+ struct arm_smmu_master *master)
+{
+ int i, ret;
+ struct arm_smmu_device *parent, *smmu = smmu_domain->root_cfg.smmu;
+ void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
+
+ ret = arm_smmu_master_configure_smrs(smmu, master);
+ if (ret)
+ return ret;
+
+ /* Bypass the leaves */
+ smmu = smmu_domain->leaf_smmu;
+ while ((parent = find_parent_smmu(smmu))) {
+ /*
+ * We won't have a StreamID match for anything but the root
+ * smmu, so we only need to worry about StreamID indexing,
+ * where we must install bypass entries in the S2CRs.
+ */
+ if (smmu->features & ARM_SMMU_FEAT_STREAM_MATCH)
+ continue;
+
+ arm_smmu_bypass_stream_mapping(smmu, master);
+ smmu = parent;
+ }
+
+ /* Now we're at the root, time to point at our context bank */
+ for (i = 0; i < master->num_streamids; ++i) {
+ u32 idx, s2cr;
+ idx = master->smrs ? master->smrs[i].idx : master->streamids[i];
+ s2cr = (S2CR_TYPE_TRANS << S2CR_TYPE_SHIFT) |
+ (smmu_domain->root_cfg.cbndx << S2CR_CBNDX_SHIFT);
+ writel_relaxed(s2cr, gr0_base + ARM_SMMU_GR0_S2CR(idx));
+ }
+
+ return 0;
+}
+
+static void arm_smmu_domain_remove_master(struct arm_smmu_domain *smmu_domain,
+ struct arm_smmu_master *master)
+{
+ struct arm_smmu_device *smmu = smmu_domain->root_cfg.smmu;
+
+ /*
+ * We *must* clear the S2CR first, because freeing the SMR means
+ * that it can be re-allocated immediately.
+ */
+ arm_smmu_bypass_stream_mapping(smmu, master);
+ arm_smmu_master_free_smrs(smmu, master);
+}
+
+static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
+{
+ int ret = -EINVAL;
+ struct arm_smmu_domain *smmu_domain = domain->priv;
+ struct arm_smmu_device *device_smmu = dev->archdata.iommu;
+ struct arm_smmu_master *master;
+
+ if (!device_smmu) {
+ dev_err(dev, "cannot attach to SMMU, is it on the same bus?\n");
+ return -ENXIO;
+ }
+
+ /*
+ * Sanity check the domain. We don't currently support domains
+ * that cross between different SMMU chains.
+ */
+ spin_lock(&smmu_domain->lock);
+ if (!smmu_domain->leaf_smmu) {
+ /* Now that we have a master, we can finalise the domain */
+ ret = arm_smmu_init_domain_context(domain, dev);
+ if (IS_ERR_VALUE(ret))
+ goto err_unlock;
+
+ smmu_domain->leaf_smmu = device_smmu;
+ } else if (smmu_domain->leaf_smmu != device_smmu) {
+ dev_err(dev,
+ "cannot attach to SMMU %s whilst already attached to domain on SMMU %s\n",
+ dev_name(smmu_domain->leaf_smmu->dev),
+ dev_name(device_smmu->dev));
+ goto err_unlock;
+ }
+ spin_unlock(&smmu_domain->lock);
+
+ /* Looks ok, so add the device to the domain */
+ master = find_smmu_master(smmu_domain->leaf_smmu, dev->of_node);
+ if (!master)
+ return -ENODEV;
+
+ return arm_smmu_domain_add_master(smmu_domain, master);
+
+err_unlock:
+ spin_unlock(&smmu_domain->lock);
+ return ret;
+}
+
+static void arm_smmu_detach_dev(struct iommu_domain *domain, struct device *dev)
+{
+ struct arm_smmu_domain *smmu_domain = domain->priv;
+ struct arm_smmu_master *master;
+
+ master = find_smmu_master(smmu_domain->leaf_smmu, dev->of_node);
+ if (master)
+ arm_smmu_domain_remove_master(smmu_domain, master);
+}
+
+static void arm_smmu_flush_pgtable(struct arm_smmu_device *smmu, void *addr,
+ size_t size)
+{
+ unsigned long offset = (unsigned long)addr & ~PAGE_MASK;
+
+ /*
+ * If the SMMU can't walk tables in the CPU caches, treat them
+ * like non-coherent DMA since we need to flush the new entries
+ * all the way out to memory. There's no possibility of recursion
+ * here as the SMMU table walker will not be wired through another
+ * SMMU.
+ */
+ if (!(smmu->features & ARM_SMMU_FEAT_COHERENT_WALK))
+ dma_map_page(smmu->dev, virt_to_page(addr), offset, size,
+ DMA_TO_DEVICE);
+}
+
+static bool arm_smmu_pte_is_contiguous_range(unsigned long addr,
+ unsigned long end)
+{
+ return !(addr & ~ARM_SMMU_PTE_CONT_MASK) &&
+ (addr + ARM_SMMU_PTE_CONT_SIZE <= end);
+}
+
+static int arm_smmu_alloc_init_pte(struct arm_smmu_device *smmu, pmd_t *pmd,
+ unsigned long addr, unsigned long end,
+ unsigned long pfn, int flags, int stage)
+{
+ pte_t *pte, *start;
+ pteval_t pteval = ARM_SMMU_PTE_PAGE | ARM_SMMU_PTE_AF;
+
+ if (pmd_none(*pmd)) {
+ /* Allocate a new set of tables */
+ pgtable_t table = alloc_page(PGALLOC_GFP);
+ if (!table)
+ return -ENOMEM;
+
+ arm_smmu_flush_pgtable(smmu, page_address(table),
+ ARM_SMMU_PTE_HWTABLE_SIZE);
+ pgtable_page_ctor(table);
+ pmd_populate(NULL, pmd, table);
+ arm_smmu_flush_pgtable(smmu, pmd, sizeof(*pmd));
+ }
+
+ if (stage == 1) {
+ pteval |= ARM_SMMU_PTE_AP_UNPRIV;
+ if (!(flags & IOMMU_WRITE) && (flags & IOMMU_READ))
+ pteval |= ARM_SMMU_PTE_AP_RDONLY;
+
+ if (flags & IOMMU_CACHE)
+ pteval |= (MAIR_ATTR_IDX_CACHE <<
+ ARM_SMMU_PTE_ATTRINDX_SHIFT);
+ } else {
+ pteval |= ARM_SMMU_PTE_HAP_FAULT;
+ if (flags & IOMMU_READ)
+ pteval |= ARM_SMMU_PTE_HAP_READ;
+ if (flags & IOMMU_WRITE)
+ pteval |= ARM_SMMU_PTE_HAP_WRITE;
+ if (flags & IOMMU_CACHE)
+ pteval |= ARM_SMMU_PTE_MEMATTR_OIWB;
+ else
+ pteval |= ARM_SMMU_PTE_MEMATTR_NC;
+ }
+
+ /* If no access, create a faulting entry to avoid TLB fills */
+ if (!(flags & (IOMMU_READ | IOMMU_WRITE)))
+ pteval &= ~ARM_SMMU_PTE_PAGE;
+
+ pteval |= ARM_SMMU_PTE_SH_IS;
+ start = pmd_page_vaddr(*pmd) + pte_index(addr);
+ pte = start;
+
+ /*
+ * Install the page table entries. This is fairly complicated
+ * since we attempt to make use of the contiguous hint in the
+ * ptes where possible. The contiguous hint indicates a series
+ * of ARM_SMMU_PTE_CONT_ENTRIES ptes mapping a physically
+ * contiguous region with the following constraints:
+ *
+ * - The region start is aligned to ARM_SMMU_PTE_CONT_SIZE
+ * - Each pte in the region has the contiguous hint bit set
+ *
+ * This complicates unmapping (also handled by this code, when
+ * neither IOMMU_READ or IOMMU_WRITE are set) because it is
+ * possible, yet highly unlikely, that a client may unmap only
+ * part of a contiguous range. This requires clearing of the
+ * contiguous hint bits in the range before installing the new
+ * faulting entries.
+ *
+ * Note that re-mapping an address range without first unmapping
+ * it is not supported, so TLB invalidation is not required here
+ * and is instead performed at unmap and domain-init time.
+ */
+ do {
+ int i = 1;
+ pteval &= ~ARM_SMMU_PTE_CONT;
+
+ if (arm_smmu_pte_is_contiguous_range(addr, end)) {
+ i = ARM_SMMU_PTE_CONT_ENTRIES;
+ pteval |= ARM_SMMU_PTE_CONT;
+ } else if (pte_val(*pte) &
+ (ARM_SMMU_PTE_CONT | ARM_SMMU_PTE_PAGE)) {
+ int j;
+ pte_t *cont_start;
+ unsigned long idx = pte_index(addr);
+
+ idx &= ~(ARM_SMMU_PTE_CONT_ENTRIES - 1);
+ cont_start = pmd_page_vaddr(*pmd) + idx;
+ for (j = 0; j < ARM_SMMU_PTE_CONT_ENTRIES; ++j)
+ pte_val(*(cont_start + j)) &= ~ARM_SMMU_PTE_CONT;
+
+ arm_smmu_flush_pgtable(smmu, cont_start,
+ sizeof(*pte) *
+ ARM_SMMU_PTE_CONT_ENTRIES);
+ }
+
+ do {
+ *pte = pfn_pte(pfn, __pgprot(pteval));
+ } while (pte++, pfn++, addr += PAGE_SIZE, --i);
+ } while (addr != end);
+
+ arm_smmu_flush_pgtable(smmu, start, sizeof(*pte) * (pte - start));
+ return 0;
+}
+
+static int arm_smmu_alloc_init_pmd(struct arm_smmu_device *smmu, pud_t *pud,
+ unsigned long addr, unsigned long end,
+ phys_addr_t phys, int flags, int stage)
+{
+ int ret;
+ pmd_t *pmd;
+ unsigned long next, pfn = __phys_to_pfn(phys);
+
+#ifndef __PAGETABLE_PMD_FOLDED
+ if (pud_none(*pud)) {
+ pmd = pmd_alloc_one(NULL, addr);
+ if (!pmd)
+ return -ENOMEM;
+ } else
+#endif
+ pmd = pmd_offset(pud, addr);
+
+ do {
+ next = pmd_addr_end(addr, end);
+ ret = arm_smmu_alloc_init_pte(smmu, pmd, addr, end, pfn,
+ flags, stage);
+ pud_populate(NULL, pud, pmd);
+ arm_smmu_flush_pgtable(smmu, pud, sizeof(*pud));
+ phys += next - addr;
+ } while (pmd++, addr = next, addr < end);
+
+ return ret;
+}
+
+static int arm_smmu_alloc_init_pud(struct arm_smmu_device *smmu, pgd_t *pgd,
+ unsigned long addr, unsigned long end,
+ phys_addr_t phys, int flags, int stage)
+{
+ int ret = 0;
+ pud_t *pud;
+ unsigned long next;
+
+#ifndef __PAGETABLE_PUD_FOLDED
+ if (pgd_none(*pgd)) {
+ pud = pud_alloc_one(NULL, addr);
+ if (!pud)
+ return -ENOMEM;
+ } else
+#endif
+ pud = pud_offset(pgd, addr);
+
+ do {
+ next = pud_addr_end(addr, end);
+ ret = arm_smmu_alloc_init_pmd(smmu, pud, addr, next, phys,
+ flags, stage);
+ pgd_populate(NULL, pud, pgd);
+ arm_smmu_flush_pgtable(smmu, pgd, sizeof(*pgd));
+ phys += next - addr;
+ } while (pud++, addr = next, addr < end);
+
+ return ret;
+}
+
+static int arm_smmu_handle_mapping(struct arm_smmu_domain *smmu_domain,
+ unsigned long iova, phys_addr_t paddr,
+ size_t size, int flags)
+{
+ int ret, stage;
+ unsigned long end;
+ phys_addr_t input_mask, output_mask;
+ struct arm_smmu_cfg *root_cfg = &smmu_domain->root_cfg;
+ pgd_t *pgd = root_cfg->pgd;
+ struct arm_smmu_device *smmu = root_cfg->smmu;
+
+ if (root_cfg->cbar == CBAR_TYPE_S2_TRANS) {
+ stage = 2;
+ output_mask = (1ULL << smmu->s2_output_size) - 1;
+ } else {
+ stage = 1;
+ output_mask = (1ULL << smmu->s1_output_size) - 1;
+ }
+
+ if (!pgd)
+ return -EINVAL;
+
+ if (size & ~PAGE_MASK)
+ return -EINVAL;
+
+ input_mask = (1ULL << smmu->input_size) - 1;
+ if ((phys_addr_t)iova & ~input_mask)
+ return -ERANGE;
+
+ if (paddr & ~output_mask)
+ return -ERANGE;
+
+ spin_lock(&smmu_domain->lock);
+ pgd += pgd_index(iova);
+ end = iova + size;
+ do {
+ unsigned long next = pgd_addr_end(iova, end);
+
+ ret = arm_smmu_alloc_init_pud(smmu, pgd, iova, next, paddr,
+ flags, stage);
+ if (ret)
+ goto out_unlock;
+
+ paddr += next - iova;
+ iova = next;
+ } while (pgd++, iova != end);
+
+out_unlock:
+ spin_unlock(&smmu_domain->lock);
+
+ /* Ensure new page tables are visible to the hardware walker */
+ if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK)
+ dsb();
+
+ return ret;
+}
+
+static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova,
+ phys_addr_t paddr, size_t size, int flags)
+{
+ struct arm_smmu_domain *smmu_domain = domain->priv;
+ struct arm_smmu_device *smmu = smmu_domain->leaf_smmu;
+
+ if (!smmu_domain || !smmu)
+ return -ENODEV;
+
+ /* Check for silent address truncation up the SMMU chain. */
+ if ((phys_addr_t)iova & ~smmu_domain->output_mask)
+ return -ERANGE;
+
+ return arm_smmu_handle_mapping(smmu_domain, iova, paddr, size, flags);
+}
+
+static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
+ size_t size)
+{
+ int ret;
+ struct arm_smmu_domain *smmu_domain = domain->priv;
+ struct arm_smmu_cfg *root_cfg = &smmu_domain->root_cfg;
+ struct arm_smmu_device *smmu = root_cfg->smmu;
+ void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
+
+ ret = arm_smmu_handle_mapping(smmu_domain, iova, 0, size, 0);
+ writel_relaxed(root_cfg->vmid, gr0_base + ARM_SMMU_GR0_TLBIVMID);
+ arm_smmu_tlb_sync(smmu);
+ return ret ? ret : size;
+}
+
+static phys_addr_t arm_smmu_iova_to_phys(struct iommu_domain *domain,
+ dma_addr_t iova)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+ struct arm_smmu_domain *smmu_domain = domain->priv;
+ struct arm_smmu_cfg *root_cfg = &smmu_domain->root_cfg;
+ struct arm_smmu_device *smmu = root_cfg->smmu;
+
+ spin_lock(&smmu_domain->lock);
+ pgd = root_cfg->pgd;
+ if (!pgd)
+ goto err_unlock;
+
+ pgd += pgd_index(iova);
+ if (pgd_none_or_clear_bad(pgd))
+ goto err_unlock;
+
+ pud = pud_offset(pgd, iova);
+ if (pud_none_or_clear_bad(pud))
+ goto err_unlock;
+
+ pmd = pmd_offset(pud, iova);
+ if (pmd_none_or_clear_bad(pmd))
+ goto err_unlock;
+
+ pte = pmd_page_vaddr(*pmd) + pte_index(iova);
+ if (pte_none(pte))
+ goto err_unlock;
+
+ spin_unlock(&smmu_domain->lock);
+ return __pfn_to_phys(pte_pfn(*pte)) | (iova & ~PAGE_MASK);
+
+err_unlock:
+ spin_unlock(&smmu_domain->lock);
+ dev_warn(smmu->dev,
+ "invalid (corrupt?) page tables detected for iova 0x%llx\n",
+ (unsigned long long)iova);
+ return -EINVAL;
+}
+
+static int arm_smmu_domain_has_cap(struct iommu_domain *domain,
+ unsigned long cap)
+{
+ unsigned long caps = 0;
+ struct arm_smmu_domain *smmu_domain = domain->priv;
+
+ if (smmu_domain->root_cfg.smmu->features & ARM_SMMU_FEAT_COHERENT_WALK)
+ caps |= IOMMU_CAP_CACHE_COHERENCY;
+
+ return !!(cap & caps);
+}
+
+static int arm_smmu_add_device(struct device *dev)
+{
+ struct arm_smmu_device *child, *parent, *smmu;
+ struct arm_smmu_master *master = NULL;
+
+ spin_lock(&arm_smmu_devices_lock);
+ list_for_each_entry(parent, &arm_smmu_devices, list) {
+ smmu = parent;
+
+ /* Try to find a child of the current SMMU. */
+ list_for_each_entry(child, &arm_smmu_devices, list) {
+ if (child->parent_of_node == parent->dev->of_node) {
+ /* Does the child sit above our master? */
+ master = find_smmu_master(child, dev->of_node);
+ if (master) {
+ smmu = NULL;
+ break;
+ }
+ }
+ }
+
+ /* We found some children, so keep searching. */
+ if (!smmu) {
+ master = NULL;
+ continue;
+ }
+
+ master = find_smmu_master(smmu, dev->of_node);
+ if (master)
+ break;
+ }
+ spin_unlock(&arm_smmu_devices_lock);
+
+ if (!master)
+ return -ENODEV;
+
+ dev->archdata.iommu = smmu;
+ return 0;
+}
+
+static void arm_smmu_remove_device(struct device *dev)
+{
+ dev->archdata.iommu = NULL;
+}
+
+static struct iommu_ops arm_smmu_ops = {
+ .domain_init = arm_smmu_domain_init,
+ .domain_destroy = arm_smmu_domain_destroy,
+ .attach_dev = arm_smmu_attach_dev,
+ .detach_dev = arm_smmu_detach_dev,
+ .map = arm_smmu_map,
+ .unmap = arm_smmu_unmap,
+ .iova_to_phys = arm_smmu_iova_to_phys,
+ .domain_has_cap = arm_smmu_domain_has_cap,
+ .add_device = arm_smmu_add_device,
+ .remove_device = arm_smmu_remove_device,
+ .pgsize_bitmap = (SECTION_SIZE |
+ ARM_SMMU_PTE_CONT_SIZE |
+ PAGE_SIZE),
+};
+
+static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
+{
+ void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
+ int i = 0;
+ u32 scr0 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sCR0);
+
+ /* Mark all SMRn as invalid and all S2CRn as bypass */
+ for (i = 0; i < smmu->num_mapping_groups; ++i) {
+ writel_relaxed(~SMR_VALID, gr0_base + ARM_SMMU_GR0_SMR(i));
+ writel_relaxed(S2CR_TYPE_BYPASS, gr0_base + ARM_SMMU_GR0_S2CR(i));
+ }
+
+ /* Invalidate the TLB, just in case */
+ writel_relaxed(0, gr0_base + ARM_SMMU_GR0_STLBIALL);
+ writel_relaxed(0, gr0_base + ARM_SMMU_GR0_TLBIALLH);
+ writel_relaxed(0, gr0_base + ARM_SMMU_GR0_TLBIALLNSNH);
+
+ /* Enable fault reporting */
+ scr0 |= (sCR0_GFRE | sCR0_GFIE | sCR0_GCFGFRE | sCR0_GCFGFIE);
+
+ /* Disable TLB broadcasting. */
+ scr0 |= (sCR0_VMIDPNE | sCR0_PTM);
+
+ /* Enable client access, but bypass when no mapping is found */
+ scr0 &= ~(sCR0_CLIENTPD | sCR0_USFCFG);
+
+ /* Disable forced broadcasting */
+ scr0 &= ~sCR0_FB;
+
+ /* Don't upgrade barriers */
+ scr0 &= ~(sCR0_BSU_MASK << sCR0_BSU_SHIFT);
+
+ /* Push the button */
+ arm_smmu_tlb_sync(smmu);
+ writel(scr0, gr0_base + ARM_SMMU_GR0_sCR0);
+}
+
+static int arm_smmu_id_size_to_bits(int size)
+{
+ switch (size) {
+ case 0:
+ return 32;
+ case 1:
+ return 36;
+ case 2:
+ return 40;
+ case 3:
+ return 42;
+ case 4:
+ return 44;
+ case 5:
+ default:
+ return 48;
+ }
+}
+
+static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
+{
+ unsigned long size;
+ void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
+ u32 id;
+
+ dev_notice(smmu->dev, "probing hardware configuration...\n");
+
+ /* Primecell ID */
+ id = readl_relaxed(gr0_base + ARM_SMMU_GR0_PIDR2);
+ smmu->version = ((id >> PIDR2_ARCH_SHIFT) & PIDR2_ARCH_MASK) + 1;
+ dev_notice(smmu->dev, "SMMUv%d with:\n", smmu->version);
+
+ /* ID0 */
+ id = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID0);
+#ifndef CONFIG_64BIT
+ if (((id >> ID0_PTFS_SHIFT) & ID0_PTFS_MASK) == ID0_PTFS_V8_ONLY) {
+ dev_err(smmu->dev, "\tno v7 descriptor support!\n");
+ return -ENODEV;
+ }
+#endif
+ if (id & ID0_S1TS) {
+ smmu->features |= ARM_SMMU_FEAT_TRANS_S1;
+ dev_notice(smmu->dev, "\tstage 1 translation\n");
+ }
+
+ if (id & ID0_S2TS) {
+ smmu->features |= ARM_SMMU_FEAT_TRANS_S2;
+ dev_notice(smmu->dev, "\tstage 2 translation\n");
+ }
+
+ if (id & ID0_NTS) {
+ smmu->features |= ARM_SMMU_FEAT_TRANS_NESTED;
+ dev_notice(smmu->dev, "\tnested translation\n");
+ }
+
+ if (!(smmu->features &
+ (ARM_SMMU_FEAT_TRANS_S1 | ARM_SMMU_FEAT_TRANS_S2 |
+ ARM_SMMU_FEAT_TRANS_NESTED))) {
+ dev_err(smmu->dev, "\tno translation support!\n");
+ return -ENODEV;
+ }
+
+ if (id & ID0_CTTW) {
+ smmu->features |= ARM_SMMU_FEAT_COHERENT_WALK;
+ dev_notice(smmu->dev, "\tcoherent table walk\n");
+ }
+
+ if (id & ID0_SMS) {
+ u32 smr, sid, mask;
+
+ smmu->features |= ARM_SMMU_FEAT_STREAM_MATCH;
+ smmu->num_mapping_groups = (id >> ID0_NUMSMRG_SHIFT) &
+ ID0_NUMSMRG_MASK;
+ if (smmu->num_mapping_groups == 0) {
+ dev_err(smmu->dev,
+ "stream-matching supported, but no SMRs present!\n");
+ return -ENODEV;
+ }
+
+ smr = SMR_MASK_MASK << SMR_MASK_SHIFT;
+ smr |= (SMR_ID_MASK << SMR_ID_SHIFT);
+ writel_relaxed(smr, gr0_base + ARM_SMMU_GR0_SMR(0));
+ smr = readl_relaxed(gr0_base + ARM_SMMU_GR0_SMR(0));
+
+ mask = (smr >> SMR_MASK_SHIFT) & SMR_MASK_MASK;
+ sid = (smr >> SMR_ID_SHIFT) & SMR_ID_MASK;
+ if ((mask & sid) != sid) {
+ dev_err(smmu->dev,
+ "SMR mask bits (0x%x) insufficient for ID field (0x%x)\n",
+ mask, sid);
+ return -ENODEV;
+ }
+
+ dev_notice(smmu->dev,
+ "\tstream matching with %u register groups, mask 0x%x",
+ smmu->num_mapping_groups, mask);
+ }
+
+ /* ID1 */
+ id = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID1);
+ smmu->pagesize = (id & ID1_PAGESIZE) ? SZ_64K : SZ_4K;
+
+ /* Check that we ioremapped enough */
+ size = 1 << (((id >> ID1_NUMPAGENDXB_SHIFT) & ID1_NUMPAGENDXB_MASK) + 1);
+ size *= (smmu->pagesize << 1);
+ if (smmu->size < size)
+ dev_warn(smmu->dev,
+ "device is 0x%lx bytes but only mapped 0x%lx!\n",
+ size, smmu->size);
+
+ smmu->num_s2_context_banks = (id >> ID1_NUMS2CB_SHIFT) &
+ ID1_NUMS2CB_MASK;
+ smmu->num_context_banks = (id >> ID1_NUMCB_SHIFT) & ID1_NUMCB_MASK;
+ if (smmu->num_s2_context_banks > smmu->num_context_banks) {
+ dev_err(smmu->dev, "impossible number of S2 context banks!\n");
+ return -ENODEV;
+ }
+ dev_notice(smmu->dev, "\t%u context banks (%u stage-2 only)\n",
+ smmu->num_context_banks, smmu->num_s2_context_banks);
+
+ /* ID2 */
+ id = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID2);
+ size = arm_smmu_id_size_to_bits((id >> ID2_IAS_SHIFT) & ID2_IAS_MASK);
+
+ /*
+ * Stage-1 output limited by stage-2 input size due to pgd
+ * allocation (PTRS_PER_PGD).
+ */
+#ifdef CONFIG_64BIT
+ /* Current maximum output size of 39 bits */
+ smmu->s1_output_size = min(39UL, size);
+#else
+ smmu->s1_output_size = min(32UL, size);
+#endif
+
+ /* The stage-2 output mask is also applied for bypass */
+ size = arm_smmu_id_size_to_bits((id >> ID2_OAS_SHIFT) & ID2_OAS_MASK);
+ smmu->s2_output_size = min((unsigned long)PHYS_MASK_SHIFT, size);
+
+ if (smmu->version == 1) {
+ smmu->input_size = 32;
+ } else {
+#ifdef CONFIG_64BIT
+ size = (id >> ID2_UBS_SHIFT) & ID2_UBS_MASK;
+ size = min(39, arm_smmu_id_size_to_bits(size));
+#else
+ size = 32;
+#endif
+ smmu->input_size = size;
+
+ if ((PAGE_SIZE == SZ_4K && !(id & ID2_PTFS_4K)) ||
+ (PAGE_SIZE == SZ_64K && !(id & ID2_PTFS_64K)) ||
+ (PAGE_SIZE != SZ_4K && PAGE_SIZE != SZ_64K)) {
+ dev_err(smmu->dev, "CPU page size 0x%lx unsupported\n",
+ PAGE_SIZE);
+ return -ENODEV;
+ }
+ }
+
+ dev_notice(smmu->dev,
+ "\t%lu-bit VA, %lu-bit IPA, %lu-bit PA\n",
+ smmu->input_size, smmu->s1_output_size, smmu->s2_output_size);
+ return 0;
+}
+
+static int arm_smmu_device_dt_probe(struct platform_device *pdev)
+{
+ struct resource *res;
+ struct arm_smmu_device *smmu;
+ struct device_node *dev_node;
+ struct device *dev = &pdev->dev;
+ struct rb_node *node;
+ struct of_phandle_args masterspec;
+ int num_irqs, i, err;
+
+ smmu = devm_kzalloc(dev, sizeof(*smmu), GFP_KERNEL);
+ if (!smmu) {
+ dev_err(dev, "failed to allocate arm_smmu_device\n");
+ return -ENOMEM;
+ }
+ smmu->dev = dev;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res) {
+ dev_err(dev, "missing base address/size\n");
+ return -ENODEV;
+ }
+
+ smmu->size = resource_size(res);
+ smmu->base = devm_request_and_ioremap(dev, res);
+ if (!smmu->base)
+ return -EADDRNOTAVAIL;
+
+ if (of_property_read_u32(dev->of_node, "#global-interrupts",
+ &smmu->num_global_irqs)) {
+ dev_err(dev, "missing #global-interrupts property\n");
+ return -ENODEV;
+ }
+
+ num_irqs = 0;
+ while ((res = platform_get_resource(pdev, IORESOURCE_IRQ, num_irqs))) {
+ num_irqs++;
+ if (num_irqs > smmu->num_global_irqs)
+ smmu->num_context_irqs++;
+ }
+
+ if (num_irqs < smmu->num_global_irqs) {
+ dev_warn(dev, "found %d interrupts but expected at least %d\n",
+ num_irqs, smmu->num_global_irqs);
+ smmu->num_global_irqs = num_irqs;
+ }
+ smmu->num_context_irqs = num_irqs - smmu->num_global_irqs;
+
+ smmu->irqs = devm_kzalloc(dev, sizeof(*smmu->irqs) * num_irqs,
+ GFP_KERNEL);
+ if (!smmu->irqs) {
+ dev_err(dev, "failed to allocate %d irqs\n", num_irqs);
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < num_irqs; ++i) {
+ int irq = platform_get_irq(pdev, i);
+ if (irq < 0) {
+ dev_err(dev, "failed to get irq index %d\n", i);
+ return -ENODEV;
+ }
+ smmu->irqs[i] = irq;
+ }
+
+ i = 0;
+ smmu->masters = RB_ROOT;
+ while (!of_parse_phandle_with_args(dev->of_node, "mmu-masters",
+ "#stream-id-cells", i,
+ &masterspec)) {
+ err = register_smmu_master(smmu, dev, &masterspec);
+ if (err) {
+ dev_err(dev, "failed to add master %s\n",
+ masterspec.np->name);
+ goto out_put_masters;
+ }
+
+ i++;
+ }
+ dev_notice(dev, "registered %d master devices\n", i);
+
+ if ((dev_node = of_parse_phandle(dev->of_node, "smmu-parent", 0)))
+ smmu->parent_of_node = dev_node;
+
+ err = arm_smmu_device_cfg_probe(smmu);
+ if (err)
+ goto out_put_parent;
+
+ if (smmu->version > 1 &&
+ smmu->num_context_banks != smmu->num_context_irqs) {
+ dev_err(dev,
+ "found only %d context interrupt(s) but %d required\n",
+ smmu->num_context_irqs, smmu->num_context_banks);
+ goto out_put_parent;
+ }
+
+ arm_smmu_device_reset(smmu);
+
+ for (i = 0; i < smmu->num_global_irqs; ++i) {
+ err = request_irq(smmu->irqs[i],
+ arm_smmu_global_fault,
+ IRQF_SHARED,
+ "arm-smmu global fault",
+ smmu);
+ if (err) {
+ dev_err(dev, "failed to request global IRQ %d (%u)\n",
+ i, smmu->irqs[i]);
+ goto out_free_irqs;
+ }
+ }
+
+ INIT_LIST_HEAD(&smmu->list);
+ spin_lock(&arm_smmu_devices_lock);
+ list_add(&smmu->list, &arm_smmu_devices);
+ spin_unlock(&arm_smmu_devices_lock);
+ return 0;
+
+out_free_irqs:
+ while (i--)
+ free_irq(smmu->irqs[i], smmu);
+
+out_put_parent:
+ if (smmu->parent_of_node)
+ of_node_put(smmu->parent_of_node);
+
+out_put_masters:
+ for (node = rb_first(&smmu->masters); node; node = rb_next(node)) {
+ struct arm_smmu_master *master;
+ master = container_of(node, struct arm_smmu_master, node);
+ of_node_put(master->of_node);
+ }
+
+ return err;
+}
+
+static int arm_smmu_device_remove(struct platform_device *pdev)
+{
+ int i;
+ struct device *dev = &pdev->dev;
+ struct arm_smmu_device *curr, *smmu = NULL;
+ struct rb_node *node;
+
+ spin_lock(&arm_smmu_devices_lock);
+ list_for_each_entry(curr, &arm_smmu_devices, list) {
+ if (curr->dev == dev) {
+ smmu = curr;
+ list_del(&smmu->list);
+ break;
+ }
+ }
+ spin_unlock(&arm_smmu_devices_lock);
+
+ if (!smmu)
+ return -ENODEV;
+
+ if (smmu->parent_of_node)
+ of_node_put(smmu->parent_of_node);
+
+ for (node = rb_first(&smmu->masters); node; node = rb_next(node)) {
+ struct arm_smmu_master *master;
+ master = container_of(node, struct arm_smmu_master, node);
+ of_node_put(master->of_node);
+ }
+
+ if (!bitmap_empty(smmu->vmid_map, ARM_SMMU_NUM_VMIDS))
+ dev_err(dev, "removing device with active domains!\n");
+
+ for (i = 0; i < smmu->num_global_irqs; ++i)
+ free_irq(smmu->irqs[i], smmu);
+
+ /* Turn the thing off */
+ writel(sCR0_CLIENTPD, ARM_SMMU_GR0(smmu) + ARM_SMMU_GR0_sCR0);
+ return 0;
+}
+
+#ifdef CONFIG_OF
+static struct of_device_id arm_smmu_of_match[] = {
+ { .compatible = "arm,smmu-v1", },
+ { .compatible = "arm,smmu-v2", },
+ { .compatible = "arm,mmu-400", },
+ { .compatible = "arm,mmu-500", },
+ { },
+};
+MODULE_DEVICE_TABLE(of, arm_smmu_of_match);
+#endif
+
+static struct platform_driver arm_smmu_driver = {
+ .driver = {
+ .owner = THIS_MODULE,
+ .name = "arm-smmu",
+ .of_match_table = of_match_ptr(arm_smmu_of_match),
+ },
+ .probe = arm_smmu_device_dt_probe,
+ .remove = arm_smmu_device_remove,
+};
+
+static int __init arm_smmu_init(void)
+{
+ int ret;
+
+ ret = platform_driver_register(&arm_smmu_driver);
+ if (ret)
+ return ret;
+
+ /* Oh, for a proper bus abstraction */
+ if (!iommu_present(&platform_bus_type));
+ bus_set_iommu(&platform_bus_type, &arm_smmu_ops);
+
+ if (!iommu_present(&amba_bustype));
+ bus_set_iommu(&amba_bustype, &arm_smmu_ops);
+
+ return 0;
+}
+
+static void __exit arm_smmu_exit(void)
+{
+ return platform_driver_unregister(&arm_smmu_driver);
+}
+
+module_init(arm_smmu_init);
+module_exit(arm_smmu_exit);
+
+MODULE_DESCRIPTION("IOMMU API for ARM architected SMMU implementations");
+MODULE_AUTHOR("Will Deacon <will.deacon@arm.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index a7967ceb79e6..785675a56a10 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -309,6 +309,7 @@ parse_dmar_table(void)
struct acpi_table_dmar *dmar;
struct acpi_dmar_header *entry_header;
int ret = 0;
+ int drhd_count = 0;
/*
* Do it again, earlier dmar_tbl mapping could be mapped with
@@ -347,6 +348,7 @@ parse_dmar_table(void)
switch (entry_header->type) {
case ACPI_DMAR_TYPE_HARDWARE_UNIT:
+ drhd_count++;
ret = dmar_parse_one_drhd(entry_header);
break;
case ACPI_DMAR_TYPE_RESERVED_MEMORY:
@@ -371,6 +373,8 @@ parse_dmar_table(void)
entry_header = ((void *)entry_header + entry_header->length);
}
+ if (drhd_count == 0)
+ pr_warn(FW_BUG "No DRHD structure found in DMAR table\n");
return ret;
}
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index b4f0e28dfa41..eec0d3e04bf5 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -4182,14 +4182,27 @@ static int intel_iommu_add_device(struct device *dev)
/*
* If it's a multifunction device that does not support our
- * required ACS flags, add to the same group as function 0.
+ * required ACS flags, add to the same group as lowest numbered
+ * function that also does not suport the required ACS flags.
*/
if (dma_pdev->multifunction &&
- !pci_acs_enabled(dma_pdev, REQ_ACS_FLAGS))
- swap_pci_ref(&dma_pdev,
- pci_get_slot(dma_pdev->bus,
- PCI_DEVFN(PCI_SLOT(dma_pdev->devfn),
- 0)));
+ !pci_acs_enabled(dma_pdev, REQ_ACS_FLAGS)) {
+ u8 i, slot = PCI_SLOT(dma_pdev->devfn);
+
+ for (i = 0; i < 8; i++) {
+ struct pci_dev *tmp;
+
+ tmp = pci_get_slot(dma_pdev->bus, PCI_DEVFN(slot, i));
+ if (!tmp)
+ continue;
+
+ if (!pci_acs_enabled(tmp, REQ_ACS_FLAGS)) {
+ swap_pci_ref(&dma_pdev, tmp);
+ break;
+ }
+ pci_dev_put(tmp);
+ }
+ }
/*
* Devices on the root bus go through the iommu. If that's not us,
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
index 5b19b2d6ec2d..f71673dbb23d 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -664,8 +664,7 @@ error:
*/
if (x2apic_present)
- WARN(1, KERN_WARNING
- "Failed to enable irq remapping. You are vulnerable to irq-injection attacks.\n");
+ pr_warn("Failed to enable irq remapping. You are vulnerable to irq-injection attacks.\n");
return -1;
}
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index d8f98b14e2fe..fbe9ca734f8f 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -754,6 +754,38 @@ int iommu_domain_has_cap(struct iommu_domain *domain,
}
EXPORT_SYMBOL_GPL(iommu_domain_has_cap);
+static size_t iommu_pgsize(struct iommu_domain *domain,
+ unsigned long addr_merge, size_t size)
+{
+ unsigned int pgsize_idx;
+ size_t pgsize;
+
+ /* Max page size that still fits into 'size' */
+ pgsize_idx = __fls(size);
+
+ /* need to consider alignment requirements ? */
+ if (likely(addr_merge)) {
+ /* Max page size allowed by address */
+ unsigned int align_pgsize_idx = __ffs(addr_merge);
+ pgsize_idx = min(pgsize_idx, align_pgsize_idx);
+ }
+
+ /* build a mask of acceptable page sizes */
+ pgsize = (1UL << (pgsize_idx + 1)) - 1;
+
+ /* throw away page sizes not supported by the hardware */
+ pgsize &= domain->ops->pgsize_bitmap;
+
+ /* make sure we're still sane */
+ BUG_ON(!pgsize);
+
+ /* pick the biggest page */
+ pgsize_idx = __fls(pgsize);
+ pgsize = 1UL << pgsize_idx;
+
+ return pgsize;
+}
+
int iommu_map(struct iommu_domain *domain, unsigned long iova,
phys_addr_t paddr, size_t size, int prot)
{
@@ -775,45 +807,18 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova,
* size of the smallest page supported by the hardware
*/
if (!IS_ALIGNED(iova | paddr | size, min_pagesz)) {
- pr_err("unaligned: iova 0x%lx pa 0x%lx size 0x%lx min_pagesz "
- "0x%x\n", iova, (unsigned long)paddr,
- (unsigned long)size, min_pagesz);
+ pr_err("unaligned: iova 0x%lx pa 0x%pa size 0x%zx min_pagesz 0x%x\n",
+ iova, &paddr, size, min_pagesz);
return -EINVAL;
}
- pr_debug("map: iova 0x%lx pa 0x%lx size 0x%lx\n", iova,
- (unsigned long)paddr, (unsigned long)size);
+ pr_debug("map: iova 0x%lx pa 0x%pa size 0x%zx\n", iova, &paddr, size);
while (size) {
- unsigned long pgsize, addr_merge = iova | paddr;
- unsigned int pgsize_idx;
-
- /* Max page size that still fits into 'size' */
- pgsize_idx = __fls(size);
-
- /* need to consider alignment requirements ? */
- if (likely(addr_merge)) {
- /* Max page size allowed by both iova and paddr */
- unsigned int align_pgsize_idx = __ffs(addr_merge);
-
- pgsize_idx = min(pgsize_idx, align_pgsize_idx);
- }
-
- /* build a mask of acceptable page sizes */
- pgsize = (1UL << (pgsize_idx + 1)) - 1;
-
- /* throw away page sizes not supported by the hardware */
- pgsize &= domain->ops->pgsize_bitmap;
-
- /* make sure we're still sane */
- BUG_ON(!pgsize);
-
- /* pick the biggest page */
- pgsize_idx = __fls(pgsize);
- pgsize = 1UL << pgsize_idx;
+ size_t pgsize = iommu_pgsize(domain, iova | paddr, size);
- pr_debug("mapping: iova 0x%lx pa 0x%lx pgsize %lu\n", iova,
- (unsigned long)paddr, pgsize);
+ pr_debug("mapping: iova 0x%lx pa 0x%pa pgsize 0x%zx\n",
+ iova, &paddr, pgsize);
ret = domain->ops->map(domain, iova, paddr, pgsize, prot);
if (ret)
@@ -850,27 +855,26 @@ size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size)
* by the hardware
*/
if (!IS_ALIGNED(iova | size, min_pagesz)) {
- pr_err("unaligned: iova 0x%lx size 0x%lx min_pagesz 0x%x\n",
- iova, (unsigned long)size, min_pagesz);
+ pr_err("unaligned: iova 0x%lx size 0x%zx min_pagesz 0x%x\n",
+ iova, size, min_pagesz);
return -EINVAL;
}
- pr_debug("unmap this: iova 0x%lx size 0x%lx\n", iova,
- (unsigned long)size);
+ pr_debug("unmap this: iova 0x%lx size 0x%zx\n", iova, size);
/*
* Keep iterating until we either unmap 'size' bytes (or more)
* or we hit an area that isn't mapped.
*/
while (unmapped < size) {
- size_t left = size - unmapped;
+ size_t pgsize = iommu_pgsize(domain, iova, size - unmapped);
- unmapped_page = domain->ops->unmap(domain, iova, left);
+ unmapped_page = domain->ops->unmap(domain, iova, pgsize);
if (!unmapped_page)
break;
- pr_debug("unmapped: iova 0x%lx size %lx\n", iova,
- (unsigned long)unmapped_page);
+ pr_debug("unmapped: iova 0x%lx size 0x%zx\n",
+ iova, unmapped_page);
iova += unmapped_page;
unmapped += unmapped_page;
diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c
index e02e5d71745b..0ba3766240d5 100644
--- a/drivers/iommu/omap-iommu.c
+++ b/drivers/iommu/omap-iommu.c
@@ -833,16 +833,15 @@ static irqreturn_t iommu_fault_handler(int irq, void *data)
iopgd = iopgd_offset(obj, da);
if (!iopgd_is_table(*iopgd)) {
- dev_err(obj->dev, "%s: errs:0x%08x da:0x%08x pgd:0x%p "
- "*pgd:px%08x\n", obj->name, errs, da, iopgd, *iopgd);
+ dev_err(obj->dev, "%s: errs:0x%08x da:0x%08x pgd:0x%p *pgd:px%08x\n",
+ obj->name, errs, da, iopgd, *iopgd);
return IRQ_NONE;
}
iopte = iopte_offset(iopgd, da);
- dev_err(obj->dev, "%s: errs:0x%08x da:0x%08x pgd:0x%p *pgd:0x%08x "
- "pte:0x%p *pte:0x%08x\n", obj->name, errs, da, iopgd, *iopgd,
- iopte, *iopte);
+ dev_err(obj->dev, "%s: errs:0x%08x da:0x%08x pgd:0x%p *pgd:0x%08x pte:0x%p *pte:0x%08x\n",
+ obj->name, errs, da, iopgd, *iopgd, iopte, *iopte);
return IRQ_NONE;
}
@@ -1235,14 +1234,16 @@ static phys_addr_t omap_iommu_iova_to_phys(struct iommu_domain *domain,
else if (iopte_is_large(*pte))
ret = omap_iommu_translate(*pte, da, IOLARGE_MASK);
else
- dev_err(dev, "bogus pte 0x%x, da 0x%lx", *pte, da);
+ dev_err(dev, "bogus pte 0x%x, da 0x%llx", *pte,
+ (unsigned long long)da);
} else {
if (iopgd_is_section(*pgd))
ret = omap_iommu_translate(*pgd, da, IOSECTION_MASK);
else if (iopgd_is_super(*pgd))
ret = omap_iommu_translate(*pgd, da, IOSUPER_MASK);
else
- dev_err(dev, "bogus pgd 0x%x, da 0x%lx", *pgd, da);
+ dev_err(dev, "bogus pgd 0x%x, da 0x%llx", *pgd,
+ (unsigned long long)da);
}
return ret;
diff --git a/drivers/iommu/omap-iopgtable.h b/drivers/iommu/omap-iopgtable.h
index cd4ae9e5b0c6..f4003d568a92 100644
--- a/drivers/iommu/omap-iopgtable.h
+++ b/drivers/iommu/omap-iopgtable.h
@@ -95,4 +95,4 @@ static inline phys_addr_t omap_iommu_translate(u32 d, u32 va, u32 mask)
#define iopte_offset(iopgd, da) (iopgd_page_vaddr(iopgd) + iopte_index(da))
#define to_iommu(dev) \
- (struct omap_iommu *)platform_get_drvdata(to_platform_device(dev))
+ ((struct omap_iommu *)platform_get_drvdata(to_platform_device(dev)))
diff --git a/drivers/iommu/omap-iovmm.c b/drivers/iommu/omap-iovmm.c
index 46d875690739..d14725984153 100644
--- a/drivers/iommu/omap-iovmm.c
+++ b/drivers/iommu/omap-iovmm.c
@@ -102,8 +102,8 @@ static size_t sgtable_len(const struct sg_table *sgt)
}
if (i && sg->offset) {
- pr_err("%s: sg[%d] offset not allowed in internal "
- "entries\n", __func__, i);
+ pr_err("%s: sg[%d] offset not allowed in internal entries\n",
+ __func__, i);
return 0;
}