summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2019-09-17 00:14:40 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2019-09-17 00:14:40 +0300
commit52a5525214d0d612160154d902956eca0558b7c0 (patch)
treea459e3fc3977531d9f1c389eda7b49aaa0f416d0
parentbbfe0d6b8b730af4954a0e0e741217eb3e1c58bc (diff)
parente95adb9add75affb98570a518c902f50e5fcce1b (diff)
downloadlinux-52a5525214d0d612160154d902956eca0558b7c0.tar.xz
Merge tag 'iommu-updates-v5.4' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu
Pull iommu updates from Joerg Roedel: - batched unmap support for the IOMMU-API - support for unlocked command queueing in the ARM-SMMU driver - rework the ATS support in the ARM-SMMU driver - more refactoring in the ARM-SMMU driver to support hardware implemention specific quirks and errata - bounce buffering DMA-API implementatation in the Intel VT-d driver for untrusted devices (like Thunderbolt devices) - fixes for runtime PM support in the OMAP iommu driver - MT8183 IOMMU support in the Mediatek IOMMU driver - rework of the way the IOMMU core sets the default domain type for groups. Changing the default domain type on x86 does not require two kernel parameters anymore. - more smaller fixes and cleanups * tag 'iommu-updates-v5.4' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (113 commits) iommu/vt-d: Declare Broadwell igfx dmar support snafu iommu/vt-d: Add Scalable Mode fault information iommu/vt-d: Use bounce buffer for untrusted devices iommu/vt-d: Add trace events for device dma map/unmap iommu/vt-d: Don't switch off swiotlb if bounce page is used iommu/vt-d: Check whether device requires bounce buffer swiotlb: Split size parameter to map/unmap APIs iommu/omap: Mark pm functions __maybe_unused iommu/ipmmu-vmsa: Disable cache snoop transactions on R-Car Gen3 iommu/ipmmu-vmsa: Move IMTTBCR_SL0_TWOBIT_* to restore sort order iommu: Don't use sme_active() in generic code iommu/arm-smmu-v3: Fix build error without CONFIG_PCI_ATS iommu/qcom: Use struct_size() helper iommu: Remove wrong default domain comments iommu/dma: Fix for dereferencing before null checking iommu/mediatek: Clean up struct mtk_smi_iommu memory: mtk-smi: Get rid of need_larbid iommu/mediatek: Fix VLD_PA_RNG register backup when suspend memory: mtk-smi: Add bus_sel for mt8183 memory: mtk-smi: Invoke pm runtime_callback to enable clocks ...
-rw-r--r--Documentation/admin-guide/kernel-parameters.txt7
-rw-r--r--Documentation/devicetree/bindings/iommu/mediatek,iommu.txt30
-rw-r--r--Documentation/devicetree/bindings/memory-controllers/mediatek,smi-common.txt12
-rw-r--r--Documentation/devicetree/bindings/memory-controllers/mediatek,smi-larb.txt4
-rw-r--r--MAINTAINERS3
-rw-r--r--arch/arm/mach-omap2/Makefile2
-rw-r--r--arch/arm/mach-omap2/omap-iommu.c43
-rw-r--r--arch/ia64/include/asm/iommu.h2
-rw-r--r--arch/ia64/kernel/pci-dma.c2
-rw-r--r--arch/x86/include/asm/iommu.h1
-rw-r--r--arch/x86/kernel/pci-dma.c20
-rw-r--r--drivers/gpu/drm/panfrost/panfrost_mmu.c24
-rw-r--r--drivers/iommu/Kconfig1
-rw-r--r--drivers/iommu/Makefile5
-rw-r--r--drivers/iommu/amd_iommu.c106
-rw-r--r--drivers/iommu/amd_iommu.h14
-rw-r--r--drivers/iommu/amd_iommu_init.c5
-rw-r--r--drivers/iommu/amd_iommu_quirks.c92
-rw-r--r--drivers/iommu/amd_iommu_types.h9
-rw-r--r--drivers/iommu/arm-smmu-impl.c174
-rw-r--r--drivers/iommu/arm-smmu-regs.h210
-rw-r--r--drivers/iommu/arm-smmu-v3.c980
-rw-r--r--drivers/iommu/arm-smmu.c662
-rw-r--r--drivers/iommu/arm-smmu.h402
-rw-r--r--drivers/iommu/dma-iommu.c13
-rw-r--r--drivers/iommu/dmar.c77
-rw-r--r--drivers/iommu/exynos-iommu.c9
-rw-r--r--drivers/iommu/intel-iommu.c359
-rw-r--r--drivers/iommu/intel-trace.c14
-rw-r--r--drivers/iommu/intel_irq_remapping.c6
-rw-r--r--drivers/iommu/io-pgtable-arm-v7s.c145
-rw-r--r--drivers/iommu/io-pgtable-arm.c48
-rw-r--r--drivers/iommu/iommu.c217
-rw-r--r--drivers/iommu/iova.c4
-rw-r--r--drivers/iommu/ipmmu-vmsa.c106
-rw-r--r--drivers/iommu/msm_iommu.c43
-rw-r--r--drivers/iommu/mtk_iommu.c213
-rw-r--r--drivers/iommu/mtk_iommu.h21
-rw-r--r--drivers/iommu/mtk_iommu_v1.c9
-rw-r--r--drivers/iommu/omap-iommu.c324
-rw-r--r--drivers/iommu/omap-iommu.h9
-rw-r--r--drivers/iommu/qcom_iommu.c72
-rw-r--r--drivers/iommu/rockchip-iommu.c2
-rw-r--r--drivers/iommu/s390-iommu.c3
-rw-r--r--drivers/iommu/tegra-gart.c12
-rw-r--r--drivers/iommu/tegra-smmu.c2
-rw-r--r--drivers/iommu/virtio-iommu.c5
-rw-r--r--drivers/memory/mtk-smi.c268
-rw-r--r--drivers/vfio/vfio_iommu_type1.c27
-rw-r--r--drivers/xen/swiotlb-xen.c8
-rw-r--r--include/dt-bindings/memory/mt8183-larb-port.h130
-rw-r--r--include/linux/amd-iommu.h12
-rw-r--r--include/linux/blk_types.h5
-rw-r--r--include/linux/intel-iommu.h2
-rw-r--r--include/linux/io-pgtable.h66
-rw-r--r--include/linux/iommu.h108
-rw-r--r--include/linux/omap-iommu.h15
-rw-r--r--include/linux/platform_data/iommu-omap.h4
-rw-r--r--include/linux/swiotlb.h8
-rw-r--r--include/soc/mediatek/smi.h5
-rw-r--r--include/trace/events/intel_iommu.h106
-rw-r--r--kernel/dma/direct.c2
-rw-r--r--kernel/dma/swiotlb.c34
63 files changed, 3851 insertions, 1472 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 4c1971960afa..d31ffa110461 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1732,6 +1732,11 @@
Note that using this option lowers the security
provided by tboot because it makes the system
vulnerable to DMA attacks.
+ nobounce [Default off]
+ Disable bounce buffer for unstrusted devices such as
+ the Thunderbolt devices. This will treat the untrusted
+ devices as the trusted ones, hence might expose security
+ risks of DMA attacks.
intel_idle.max_cstate= [KNL,HW,ACPI,X86]
0 disables intel_idle and fall back on acpi_idle.
@@ -1811,7 +1816,7 @@
synchronously.
iommu.passthrough=
- [ARM64] Configure DMA to bypass the IOMMU by default.
+ [ARM64, X86] Configure DMA to bypass the IOMMU by default.
Format: { "0" | "1" }
0 - Use IOMMU translation for DMA.
1 - Bypass the IOMMU for DMA.
diff --git a/Documentation/devicetree/bindings/iommu/mediatek,iommu.txt b/Documentation/devicetree/bindings/iommu/mediatek,iommu.txt
index 6922db598def..ce59a505f5a4 100644
--- a/Documentation/devicetree/bindings/iommu/mediatek,iommu.txt
+++ b/Documentation/devicetree/bindings/iommu/mediatek,iommu.txt
@@ -11,10 +11,23 @@ ARM Short-Descriptor translation table format for address translation.
|
m4u (Multimedia Memory Management Unit)
|
+ +--------+
+ | |
+ gals0-rx gals1-rx (Global Async Local Sync rx)
+ | |
+ | |
+ gals0-tx gals1-tx (Global Async Local Sync tx)
+ | | Some SoCs may have GALS.
+ +--------+
+ |
SMI Common(Smart Multimedia Interface Common)
|
+----------------+-------
| |
+ | gals-rx There may be GALS in some larbs.
+ | |
+ | |
+ | gals-tx
| |
SMI larb0 SMI larb1 ... SoCs have several SMI local arbiter(larb).
(display) (vdec)
@@ -36,6 +49,10 @@ each local arbiter.
like display, video decode, and camera. And there are different ports
in each larb. Take a example, There are many ports like MC, PP, VLD in the
video decode local arbiter, all these ports are according to the video HW.
+ In some SoCs, there may be a GALS(Global Async Local Sync) module between
+smi-common and m4u, and additional GALS module between smi-larb and
+smi-common. GALS can been seen as a "asynchronous fifo" which could help
+synchronize for the modules in different clock frequency.
Required properties:
- compatible : must be one of the following string:
@@ -44,18 +61,25 @@ Required properties:
"mediatek,mt7623-m4u", "mediatek,mt2701-m4u" for mt7623 which uses
generation one m4u HW.
"mediatek,mt8173-m4u" for mt8173 which uses generation two m4u HW.
+ "mediatek,mt8183-m4u" for mt8183 which uses generation two m4u HW.
- reg : m4u register base and size.
- interrupts : the interrupt of m4u.
- clocks : must contain one entry for each clock-names.
-- clock-names : must be "bclk", It is the block clock of m4u.
+- clock-names : Only 1 optional clock:
+ - "bclk": the block clock of m4u.
+ Here is the list which require this "bclk":
+ - mt2701, mt2712, mt7623 and mt8173.
+ Note that m4u use the EMI clock which always has been enabled before kernel
+ if there is no this "bclk".
- mediatek,larbs : List of phandle to the local arbiters in the current Socs.
Refer to bindings/memory-controllers/mediatek,smi-larb.txt. It must sort
according to the local arbiter index, like larb0, larb1, larb2...
- iommu-cells : must be 1. This is the mtk_m4u_id according to the HW.
Specifies the mtk_m4u_id as defined in
dt-binding/memory/mt2701-larb-port.h for mt2701, mt7623
- dt-binding/memory/mt2712-larb-port.h for mt2712, and
- dt-binding/memory/mt8173-larb-port.h for mt8173.
+ dt-binding/memory/mt2712-larb-port.h for mt2712,
+ dt-binding/memory/mt8173-larb-port.h for mt8173, and
+ dt-binding/memory/mt8183-larb-port.h for mt8183.
Example:
iommu: iommu@10205000 {
diff --git a/Documentation/devicetree/bindings/memory-controllers/mediatek,smi-common.txt b/Documentation/devicetree/bindings/memory-controllers/mediatek,smi-common.txt
index e937ddd871a6..b478ade4da65 100644
--- a/Documentation/devicetree/bindings/memory-controllers/mediatek,smi-common.txt
+++ b/Documentation/devicetree/bindings/memory-controllers/mediatek,smi-common.txt
@@ -2,9 +2,10 @@ SMI (Smart Multimedia Interface) Common
The hardware block diagram please check bindings/iommu/mediatek,iommu.txt
-Mediatek SMI have two generations of HW architecture, mt2712 and mt8173 use
-the second generation of SMI HW while mt2701 uses the first generation HW of
-SMI.
+Mediatek SMI have two generations of HW architecture, here is the list
+which generation the SoCs use:
+generation 1: mt2701 and mt7623.
+generation 2: mt2712, mt8173 and mt8183.
There's slight differences between the two SMI, for generation 2, the
register which control the iommu port is at each larb's register base. But
@@ -19,6 +20,7 @@ Required properties:
"mediatek,mt2712-smi-common"
"mediatek,mt7623-smi-common", "mediatek,mt2701-smi-common"
"mediatek,mt8173-smi-common"
+ "mediatek,mt8183-smi-common"
- reg : the register and size of the SMI block.
- power-domains : a phandle to the power domain of this local arbiter.
- clocks : Must contain an entry for each entry in clock-names.
@@ -30,6 +32,10 @@ Required properties:
They may be the same if both source clocks are the same.
- "async" : asynchronous clock, it help transform the smi clock into the emi
clock domain, this clock is only needed by generation 1 smi HW.
+ and these 2 option clocks for generation 2 smi HW:
+ - "gals0": the path0 clock of GALS(Global Async Local Sync).
+ - "gals1": the path1 clock of GALS(Global Async Local Sync).
+ Here is the list which has this GALS: mt8183.
Example:
smi_common: smi@14022000 {
diff --git a/Documentation/devicetree/bindings/memory-controllers/mediatek,smi-larb.txt b/Documentation/devicetree/bindings/memory-controllers/mediatek,smi-larb.txt
index 94eddcae77ab..4b369b3e1a69 100644
--- a/Documentation/devicetree/bindings/memory-controllers/mediatek,smi-larb.txt
+++ b/Documentation/devicetree/bindings/memory-controllers/mediatek,smi-larb.txt
@@ -8,6 +8,7 @@ Required properties:
"mediatek,mt2712-smi-larb"
"mediatek,mt7623-smi-larb", "mediatek,mt2701-smi-larb"
"mediatek,mt8173-smi-larb"
+ "mediatek,mt8183-smi-larb"
- reg : the register and size of this local arbiter.
- mediatek,smi : a phandle to the smi_common node.
- power-domains : a phandle to the power domain of this local arbiter.
@@ -16,6 +17,9 @@ Required properties:
- "apb" : Advanced Peripheral Bus clock, It's the clock for setting
the register.
- "smi" : It's the clock for transfer data and command.
+ and this optional clock name:
+ - "gals": the clock for GALS(Global Async Local Sync).
+ Here is the list which has this GALS: mt8183.
Required property for mt2701, mt2712 and mt7623:
- mediatek,larb-id :the hardware id of this larb.
diff --git a/MAINTAINERS b/MAINTAINERS
index 7fd34066b34a..59a8ec493d7a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1342,8 +1342,7 @@ M: Will Deacon <will@kernel.org>
R: Robin Murphy <robin.murphy@arm.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
-F: drivers/iommu/arm-smmu.c
-F: drivers/iommu/arm-smmu-v3.c
+F: drivers/iommu/arm-smmu*
F: drivers/iommu/io-pgtable-arm.c
F: drivers/iommu/io-pgtable-arm-v7s.c
diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile
index 600650551621..d4f11c5070ae 100644
--- a/arch/arm/mach-omap2/Makefile
+++ b/arch/arm/mach-omap2/Makefile
@@ -229,3 +229,5 @@ include/generated/ti-pm-asm-offsets.h: arch/arm/mach-omap2/pm-asm-offsets.s FORC
$(obj)/sleep33xx.o $(obj)/sleep43xx.o: include/generated/ti-pm-asm-offsets.h
targets += pm-asm-offsets.s
+
+obj-$(CONFIG_OMAP_IOMMU) += omap-iommu.o
diff --git a/arch/arm/mach-omap2/omap-iommu.c b/arch/arm/mach-omap2/omap-iommu.c
new file mode 100644
index 000000000000..f1a6ece8108e
--- /dev/null
+++ b/arch/arm/mach-omap2/omap-iommu.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * OMAP IOMMU quirks for various TI SoCs
+ *
+ * Copyright (C) 2015-2019 Texas Instruments Incorporated - http://www.ti.com/
+ * Suman Anna <s-anna@ti.com>
+ */
+
+#include <linux/platform_device.h>
+#include <linux/err.h>
+
+#include "omap_hwmod.h"
+#include "omap_device.h"
+#include "powerdomain.h"
+
+int omap_iommu_set_pwrdm_constraint(struct platform_device *pdev, bool request,
+ u8 *pwrst)
+{
+ struct powerdomain *pwrdm;
+ struct omap_device *od;
+ u8 next_pwrst;
+
+ od = to_omap_device(pdev);
+ if (!od)
+ return -ENODEV;
+
+ if (od->hwmods_cnt != 1)
+ return -EINVAL;
+
+ pwrdm = omap_hwmod_get_pwrdm(od->hwmods[0]);
+ if (!pwrdm)
+ return -EINVAL;
+
+ if (request)
+ *pwrst = pwrdm_read_next_pwrst(pwrdm);
+
+ if (*pwrst > PWRDM_POWER_RET)
+ return 0;
+
+ next_pwrst = request ? PWRDM_POWER_ON : *pwrst;
+
+ return pwrdm_set_next_pwrst(pwrdm, next_pwrst);
+}
diff --git a/arch/ia64/include/asm/iommu.h b/arch/ia64/include/asm/iommu.h
index 7429a72f3f92..92aceef63710 100644
--- a/arch/ia64/include/asm/iommu.h
+++ b/arch/ia64/include/asm/iommu.h
@@ -8,10 +8,8 @@
extern void no_iommu_init(void);
#ifdef CONFIG_INTEL_IOMMU
extern int force_iommu, no_iommu;
-extern int iommu_pass_through;
extern int iommu_detected;
#else
-#define iommu_pass_through (0)
#define no_iommu (1)
#define iommu_detected (0)
#endif
diff --git a/arch/ia64/kernel/pci-dma.c b/arch/ia64/kernel/pci-dma.c
index fe988c49f01c..f5d49cd3fbb0 100644
--- a/arch/ia64/kernel/pci-dma.c
+++ b/arch/ia64/kernel/pci-dma.c
@@ -22,8 +22,6 @@ int force_iommu __read_mostly = 1;
int force_iommu __read_mostly;
#endif
-int iommu_pass_through;
-
static int __init pci_iommu_init(void)
{
if (iommu_detected)
diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h
index baedab8ac538..b91623d521d9 100644
--- a/arch/x86/include/asm/iommu.h
+++ b/arch/x86/include/asm/iommu.h
@@ -4,7 +4,6 @@
extern int force_iommu, no_iommu;
extern int iommu_detected;
-extern int iommu_pass_through;
/* 10 seconds */
#define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000)
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index f62b498b18fb..fa4352dce491 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/dma-direct.h>
#include <linux/dma-debug.h>
+#include <linux/iommu.h>
#include <linux/dmar.h>
#include <linux/export.h>
#include <linux/memblock.h>
@@ -34,21 +35,6 @@ int no_iommu __read_mostly;
/* Set this to 1 if there is a HW IOMMU in the system */
int iommu_detected __read_mostly = 0;
-/*
- * This variable becomes 1 if iommu=pt is passed on the kernel command line.
- * If this variable is 1, IOMMU implementations do no DMA translation for
- * devices and allow every device to access to whole physical memory. This is
- * useful if a user wants to use an IOMMU only for KVM device assignment to
- * guests and not for driver dma translation.
- * It is also possible to disable by default in kernel config, and enable with
- * iommu=nopt at boot time.
- */
-#ifdef CONFIG_IOMMU_DEFAULT_PASSTHROUGH
-int iommu_pass_through __read_mostly = 1;
-#else
-int iommu_pass_through __read_mostly;
-#endif
-
extern struct iommu_table_entry __iommu_table[], __iommu_table_end[];
void __init pci_iommu_alloc(void)
@@ -120,9 +106,9 @@ static __init int iommu_setup(char *p)
swiotlb = 1;
#endif
if (!strncmp(p, "pt", 2))
- iommu_pass_through = 1;
+ iommu_set_default_passthrough(true);
if (!strncmp(p, "nopt", 4))
- iommu_pass_through = 0;
+ iommu_set_default_translated(true);
gart_parse_options(p);
diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index 92ac995dd9c6..6e8145c36e93 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -222,7 +222,7 @@ void panfrost_mmu_unmap(struct panfrost_gem_object *bo)
size_t unmapped_page;
size_t pgsize = get_pgsize(iova, len - unmapped_len);
- unmapped_page = ops->unmap(ops, iova, pgsize);
+ unmapped_page = ops->unmap(ops, iova, pgsize, NULL);
if (!unmapped_page)
break;
@@ -247,20 +247,28 @@ static void mmu_tlb_inv_context_s1(void *cookie)
mmu_hw_do_operation(pfdev, 0, 0, ~0UL, AS_COMMAND_FLUSH_MEM);
}
-static void mmu_tlb_inv_range_nosync(unsigned long iova, size_t size,
- size_t granule, bool leaf, void *cookie)
-{}
-
static void mmu_tlb_sync_context(void *cookie)
{
//struct panfrost_device *pfdev = cookie;
// TODO: Wait 1000 GPU cycles for HW_ISSUE_6367/T60X
}
-static const struct iommu_gather_ops mmu_tlb_ops = {
+static void mmu_tlb_flush_walk(unsigned long iova, size_t size, size_t granule,
+ void *cookie)
+{
+ mmu_tlb_sync_context(cookie);
+}
+
+static void mmu_tlb_flush_leaf(unsigned long iova, size_t size, size_t granule,
+ void *cookie)
+{
+ mmu_tlb_sync_context(cookie);
+}
+
+static const struct iommu_flush_ops mmu_tlb_ops = {
.tlb_flush_all = mmu_tlb_inv_context_s1,
- .tlb_add_flush = mmu_tlb_inv_range_nosync,
- .tlb_sync = mmu_tlb_sync_context,
+ .tlb_flush_walk = mmu_tlb_flush_walk,
+ .tlb_flush_leaf = mmu_tlb_flush_leaf,
};
static const char *access_type_name(struct panfrost_device *pfdev,
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index e15cdcd8cb3c..a4ddeade8ac4 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -182,6 +182,7 @@ config INTEL_IOMMU
select IOMMU_IOVA
select NEED_DMA_MAP_STATE
select DMAR_TABLE
+ select SWIOTLB
help
DMA remapping (DMAR) devices support enables independent address
translations for Direct Memory Access (DMA) from devices.
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index f13f36ae1af6..4f405f926e73 100644
--- a/drivers/iommu/Makefile
+++ b/drivers/iommu/Makefile
@@ -10,13 +10,14 @@ obj-$(CONFIG_IOMMU_IO_PGTABLE_LPAE) += io-pgtable-arm.o
obj-$(CONFIG_IOMMU_IOVA) += iova.o
obj-$(CONFIG_OF_IOMMU) += of_iommu.o
obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o
-obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o
+obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o amd_iommu_quirks.o
obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += amd_iommu_debugfs.o
obj-$(CONFIG_AMD_IOMMU_V2) += amd_iommu_v2.o
-obj-$(CONFIG_ARM_SMMU) += arm-smmu.o
+obj-$(CONFIG_ARM_SMMU) += arm-smmu.o arm-smmu-impl.o
obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o
obj-$(CONFIG_DMAR_TABLE) += dmar.o
obj-$(CONFIG_INTEL_IOMMU) += intel-iommu.o intel-pasid.o
+obj-$(CONFIG_INTEL_IOMMU) += intel-trace.o
obj-$(CONFIG_INTEL_IOMMU_DEBUGFS) += intel-iommu-debugfs.o
obj-$(CONFIG_INTEL_IOMMU_SVM) += intel-svm.o
obj-$(CONFIG_IPMMU_VMSA) += ipmmu-vmsa.o
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 61de81965c44..1ed3b98324ba 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -436,7 +436,7 @@ static int iommu_init_device(struct device *dev)
* invalid address), we ignore the capability for the device so
* it'll be forced to go into translation mode.
*/
- if ((iommu_pass_through || !amd_iommu_force_isolation) &&
+ if ((iommu_default_passthrough() || !amd_iommu_force_isolation) &&
dev_is_pci(dev) && pci_iommuv2_capable(to_pci_dev(dev))) {
struct amd_iommu *iommu;
@@ -2256,7 +2256,7 @@ static int amd_iommu_add_device(struct device *dev)
BUG_ON(!dev_data);
- if (iommu_pass_through || dev_data->iommu_v2)
+ if (dev_data->iommu_v2)
iommu_request_dm_for_dev(dev);
/* Domains are initialized for this device - have a look what we ended up with */
@@ -2577,7 +2577,9 @@ static int map_sg(struct device *dev, struct scatterlist *sglist,
bus_addr = address + s->dma_address + (j << PAGE_SHIFT);
phys_addr = (sg_phys(s) & PAGE_MASK) + (j << PAGE_SHIFT);
- ret = iommu_map_page(domain, bus_addr, phys_addr, PAGE_SIZE, prot, GFP_ATOMIC);
+ ret = iommu_map_page(domain, bus_addr, phys_addr,
+ PAGE_SIZE, prot,
+ GFP_ATOMIC | __GFP_NOWARN);
if (ret)
goto out_unmap;
@@ -2835,7 +2837,7 @@ int __init amd_iommu_init_api(void)
int __init amd_iommu_init_dma_ops(void)
{
- swiotlb = (iommu_pass_through || sme_me_mask) ? 1 : 0;
+ swiotlb = (iommu_default_passthrough() || sme_me_mask) ? 1 : 0;
iommu_detected = 1;
if (amd_iommu_unmap_flush)
@@ -3085,7 +3087,8 @@ static int amd_iommu_map(struct iommu_domain *dom, unsigned long iova,
}
static size_t amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova,
- size_t page_size)
+ size_t page_size,
+ struct iommu_iotlb_gather *gather)
{
struct protection_domain *domain = to_pdomain(dom);
size_t unmap_size;
@@ -3226,9 +3229,10 @@ static void amd_iommu_flush_iotlb_all(struct iommu_domain *domain)
domain_flush_complete(dom);
}
-static void amd_iommu_iotlb_range_add(struct iommu_domain *domain,
- unsigned long iova, size_t size)
+static void amd_iommu_iotlb_sync(struct iommu_domain *domain,
+ struct iommu_iotlb_gather *gather)
{
+ amd_iommu_flush_iotlb_all(domain);
}
const struct iommu_ops amd_iommu_ops = {
@@ -3249,8 +3253,7 @@ const struct iommu_ops amd_iommu_ops = {
.is_attach_deferred = amd_iommu_is_attach_deferred,
.pgsize_bitmap = AMD_IOMMU_PGSIZES,
.flush_iotlb_all = amd_iommu_flush_iotlb_all,
- .iotlb_range_add = amd_iommu_iotlb_range_add,
- .iotlb_sync = amd_iommu_flush_iotlb_all,
+ .iotlb_sync = amd_iommu_iotlb_sync,
};
/*****************************************************************************
@@ -4343,13 +4346,62 @@ static const struct irq_domain_ops amd_ir_domain_ops = {
.deactivate = irq_remapping_deactivate,
};
+int amd_iommu_activate_guest_mode(void *data)
+{
+ struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
+ struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
+
+ if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) ||
+ !entry || entry->lo.fields_vapic.guest_mode)
+ return 0;
+
+ entry->lo.val = 0;
+ entry->hi.val = 0;
+
+ entry->lo.fields_vapic.guest_mode = 1;
+ entry->lo.fields_vapic.ga_log_intr = 1;
+ entry->hi.fields.ga_root_ptr = ir_data->ga_root_ptr;
+ entry->hi.fields.vector = ir_data->ga_vector;
+ entry->lo.fields_vapic.ga_tag = ir_data->ga_tag;
+
+ return modify_irte_ga(ir_data->irq_2_irte.devid,
+ ir_data->irq_2_irte.index, entry, NULL);
+}
+EXPORT_SYMBOL(amd_iommu_activate_guest_mode);
+
+int amd_iommu_deactivate_guest_mode(void *data)
+{
+ struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
+ struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
+ struct irq_cfg *cfg = ir_data->cfg;
+
+ if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) ||
+ !entry || !entry->lo.fields_vapic.guest_mode)
+ return 0;
+
+ entry->lo.val = 0;
+ entry->hi.val = 0;
+
+ entry->lo.fields_remap.dm = apic->irq_dest_mode;
+ entry->lo.fields_remap.int_type = apic->irq_delivery_mode;
+ entry->hi.fields.vector = cfg->vector;
+ entry->lo.fields_remap.destination =
+ APICID_TO_IRTE_DEST_LO(cfg->dest_apicid);
+ entry->hi.fields.destination =
+ APICID_TO_IRTE_DEST_HI(cfg->dest_apicid);
+
+ return modify_irte_ga(ir_data->irq_2_irte.devid,
+ ir_data->irq_2_irte.index, entry, NULL);
+}
+EXPORT_SYMBOL(amd_iommu_deactivate_guest_mode);
+
static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
{
+ int ret;
struct amd_iommu *iommu;
struct amd_iommu_pi_data *pi_data = vcpu_info;
struct vcpu_data *vcpu_pi_info = pi_data->vcpu_data;
struct amd_ir_data *ir_data = data->chip_data;
- struct irte_ga *irte = (struct irte_ga *) ir_data->entry;
struct irq_2_irte *irte_info = &ir_data->irq_2_irte;
struct iommu_dev_data *dev_data = search_dev_data(irte_info->devid);
@@ -4360,6 +4412,7 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
if (!dev_data || !dev_data->use_vapic)
return 0;
+ ir_data->cfg = irqd_cfg(data);
pi_data->ir_data = ir_data;
/* Note:
@@ -4378,37 +4431,24 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
pi_data->prev_ga_tag = ir_data->cached_ga_tag;
if (pi_data->is_guest_mode) {
- /* Setting */
- irte->hi.fields.ga_root_ptr = (pi_data->base >> 12);
- irte->hi.fields.vector = vcpu_pi_info->vector;
- irte->lo.fields_vapic.ga_log_intr = 1;
- irte->lo.fields_vapic.guest_mode = 1;
- irte->lo.fields_vapic.ga_tag = pi_data->ga_tag;
-
- ir_data->cached_ga_tag = pi_data->ga_tag;
+ ir_data->ga_root_ptr = (pi_data->base >> 12);
+ ir_data->ga_vector = vcpu_pi_info->vector;
+ ir_data->ga_tag = pi_data->ga_tag;
+ ret = amd_iommu_activate_guest_mode(ir_data);
+ if (!ret)
+ ir_data->cached_ga_tag = pi_data->ga_tag;
} else {
- /* Un-Setting */
- struct irq_cfg *cfg = irqd_cfg(data);
-
- irte->hi.val = 0;
- irte->lo.val = 0;
- irte->hi.fields.vector = cfg->vector;
- irte->lo.fields_remap.guest_mode = 0;
- irte->lo.fields_remap.destination =
- APICID_TO_IRTE_DEST_LO(cfg->dest_apicid);
- irte->hi.fields.destination =
- APICID_TO_IRTE_DEST_HI(cfg->dest_apicid);
- irte->lo.fields_remap.int_type = apic->irq_delivery_mode;
- irte->lo.fields_remap.dm = apic->irq_dest_mode;
+ ret = amd_iommu_deactivate_guest_mode(ir_data);
/*
* This communicates the ga_tag back to the caller
* so that it can do all the necessary clean up.
*/
- ir_data->cached_ga_tag = 0;
+ if (!ret)
+ ir_data->cached_ga_tag = 0;
}
- return modify_irte_ga(irte_info->devid, irte_info->index, irte, ir_data);
+ return ret;
}
diff --git a/drivers/iommu/amd_iommu.h b/drivers/iommu/amd_iommu.h
new file mode 100644
index 000000000000..12d540d9b59b
--- /dev/null
+++ b/drivers/iommu/amd_iommu.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef AMD_IOMMU_H
+#define AMD_IOMMU_H
+
+int __init add_special_device(u8 type, u8 id, u16 *devid, bool cmd_line);
+
+#ifdef CONFIG_DMI
+void amd_iommu_apply_ivrs_quirks(void);
+#else
+static void amd_iommu_apply_ivrs_quirks(void) { }
+#endif
+
+#endif
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 4413aa67000e..568c52317757 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -32,6 +32,7 @@
#include <asm/irq_remapping.h>
#include <linux/crash_dump.h>
+#include "amd_iommu.h"
#include "amd_iommu_proto.h"
#include "amd_iommu_types.h"
#include "irq_remapping.h"
@@ -1002,7 +1003,7 @@ static void __init set_dev_entry_from_acpi(struct amd_iommu *iommu,
set_iommu_for_device(iommu, devid);
}
-static int __init add_special_device(u8 type, u8 id, u16 *devid, bool cmd_line)
+int __init add_special_device(u8 type, u8 id, u16 *devid, bool cmd_line)
{
struct devid_map *entry;
struct list_head *list;
@@ -1153,6 +1154,8 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu,
if (ret)
return ret;
+ amd_iommu_apply_ivrs_quirks();
+
/*
* First save the recommended feature enable bits from ACPI
*/
diff --git a/drivers/iommu/amd_iommu_quirks.c b/drivers/iommu/amd_iommu_quirks.c
new file mode 100644
index 000000000000..c235f79b7a20
--- /dev/null
+++ b/drivers/iommu/amd_iommu_quirks.c
@@ -0,0 +1,92 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+/*
+ * Quirks for AMD IOMMU
+ *
+ * Copyright (C) 2019 Kai-Heng Feng <kai.heng.feng@canonical.com>
+ */
+
+#ifdef CONFIG_DMI
+#include <linux/dmi.h>
+
+#include "amd_iommu.h"
+
+#define IVHD_SPECIAL_IOAPIC 1
+
+struct ivrs_quirk_entry {
+ u8 id;
+ u16 devid;
+};
+
+enum {
+ DELL_INSPIRON_7375 = 0,
+ DELL_LATITUDE_5495,
+ LENOVO_IDEAPAD_330S_15ARR,
+};
+
+static const struct ivrs_quirk_entry ivrs_ioapic_quirks[][3] __initconst = {
+ /* ivrs_ioapic[4]=00:14.0 ivrs_ioapic[5]=00:00.2 */
+ [DELL_INSPIRON_7375] = {
+ { .id = 4, .devid = 0xa0 },
+ { .id = 5, .devid = 0x2 },
+ {}
+ },
+ /* ivrs_ioapic[4]=00:14.0 */
+ [DELL_LATITUDE_5495] = {
+ { .id = 4, .devid = 0xa0 },
+ {}
+ },
+ /* ivrs_ioapic[32]=00:14.0 */
+ [LENOVO_IDEAPAD_330S_15ARR] = {
+ { .id = 32, .devid = 0xa0 },
+ {}
+ },
+ {}
+};
+
+static int __init ivrs_ioapic_quirk_cb(const struct dmi_system_id *d)
+{
+ const struct ivrs_quirk_entry *i;
+
+ for (i = d->driver_data; i->id != 0 && i->devid != 0; i++)
+ add_special_device(IVHD_SPECIAL_IOAPIC, i->id, (u16 *)&i->devid, 0);
+
+ return 0;
+}
+
+static const struct dmi_system_id ivrs_quirks[] __initconst = {
+ {
+ .callback = ivrs_ioapic_quirk_cb,
+ .ident = "Dell Inspiron 7375",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 7375"),
+ },
+ .driver_data = (void *)&ivrs_ioapic_quirks[DELL_INSPIRON_7375],
+ },
+ {
+ .callback = ivrs_ioapic_quirk_cb,
+ .ident = "Dell Latitude 5495",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Latitude 5495"),
+ },
+ .driver_data = (void *)&ivrs_ioapic_quirks[DELL_LATITUDE_5495],
+ },
+ {
+ .callback = ivrs_ioapic_quirk_cb,
+ .ident = "Lenovo ideapad 330S-15ARR",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "81FB"),
+ },
+ .driver_data = (void *)&ivrs_ioapic_quirks[LENOVO_IDEAPAD_330S_15ARR],
+ },
+ {}
+};
+
+void __init amd_iommu_apply_ivrs_quirks(void)
+{
+ dmi_check_system(ivrs_quirks);
+}
+#endif
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index 64edd5a9694c..9ac229e92b07 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -873,6 +873,15 @@ struct amd_ir_data {
struct msi_msg msi_entry;
void *entry; /* Pointer to union irte or struct irte_ga */
void *ref; /* Pointer to the actual irte */
+
+ /**
+ * Store information for activate/de-activate
+ * Guest virtual APIC mode during runtime.
+ */
+ struct irq_cfg *cfg;
+ int ga_vector;
+ int ga_root_ptr;
+ int ga_tag;
};
struct amd_irte_ops {
diff --git a/drivers/iommu/arm-smmu-impl.c b/drivers/iommu/arm-smmu-impl.c
new file mode 100644
index 000000000000..5c87a38620c4
--- /dev/null
+++ b/drivers/iommu/arm-smmu-impl.c
@@ -0,0 +1,174 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Miscellaneous Arm SMMU implementation and integration quirks
+// Copyright (C) 2019 Arm Limited
+
+#define pr_fmt(fmt) "arm-smmu: " fmt
+
+#include <linux/bitfield.h>
+#include <linux/of.h>
+
+#include "arm-smmu.h"
+
+
+static int arm_smmu_gr0_ns(int offset)
+{
+ switch(offset) {
+ case ARM_SMMU_GR0_sCR0:
+ case ARM_SMMU_GR0_sACR:
+ case ARM_SMMU_GR0_sGFSR:
+ case ARM_SMMU_GR0_sGFSYNR0:
+ case ARM_SMMU_GR0_sGFSYNR1:
+ case ARM_SMMU_GR0_sGFSYNR2:
+ return offset + 0x400;
+ default:
+ return offset;
+ }
+}
+
+static u32 arm_smmu_read_ns(struct arm_smmu_device *smmu, int page,
+ int offset)
+{
+ if (page == ARM_SMMU_GR0)
+ offset = arm_smmu_gr0_ns(offset);
+ return readl_relaxed(arm_smmu_page(smmu, page) + offset);
+}
+
+static void arm_smmu_write_ns(struct arm_smmu_device *smmu, int page,
+ int offset, u32 val)
+{
+ if (page == ARM_SMMU_GR0)
+ offset = arm_smmu_gr0_ns(offset);
+ writel_relaxed(val, arm_smmu_page(smmu, page) + offset);
+}
+
+/* Since we don't care for sGFAR, we can do without 64-bit accessors */
+static const struct arm_smmu_impl calxeda_impl = {
+ .read_reg = arm_smmu_read_ns,
+ .write_reg = arm_smmu_write_ns,
+};
+
+
+struct cavium_smmu {
+ struct arm_smmu_device smmu;
+ u32 id_base;
+};
+
+static int cavium_cfg_probe(struct arm_smmu_device *smmu)
+{
+ static atomic_t context_count = ATOMIC_INIT(0);
+ struct cavium_smmu *cs = container_of(smmu, struct cavium_smmu, smmu);
+ /*
+ * Cavium CN88xx erratum #27704.
+ * Ensure ASID and VMID allocation is unique across all SMMUs in
+ * the system.
+ */
+ cs->id_base = atomic_fetch_add(smmu->num_context_banks, &context_count);
+ dev_notice(smmu->dev, "\tenabling workaround for Cavium erratum 27704\n");
+
+ return 0;
+}
+
+static int cavium_init_context(struct arm_smmu_domain *smmu_domain)
+{
+ struct cavium_smmu *cs = container_of(smmu_domain->smmu,
+ struct cavium_smmu, smmu);
+
+ if (smmu_domain->stage == ARM_SMMU_DOMAIN_S2)
+ smmu_domain->cfg.vmid += cs->id_base;
+ else
+ smmu_domain->cfg.asid += cs->id_base;
+
+ return 0;
+}
+
+static const struct arm_smmu_impl cavium_impl = {
+ .cfg_probe = cavium_cfg_probe,
+ .init_context = cavium_init_context,
+};
+
+static struct arm_smmu_device *cavium_smmu_impl_init(struct arm_smmu_device *smmu)
+{
+ struct cavium_smmu *cs;
+
+ cs = devm_kzalloc(smmu->dev, sizeof(*cs), GFP_KERNEL);
+ if (!cs)
+ return ERR_PTR(-ENOMEM);
+
+ cs->smmu = *smmu;
+ cs->smmu.impl = &cavium_impl;
+
+ devm_kfree(smmu->dev, smmu);
+
+ return &cs->smmu;
+}
+
+
+#define ARM_MMU500_ACTLR_CPRE (1 << 1)
+
+#define ARM_MMU500_ACR_CACHE_LOCK (1 << 26)
+#define ARM_MMU500_ACR_S2CRB_TLBEN (1 << 10)
+#define ARM_MMU500_ACR_SMTNMB_TLBEN (1 << 8)
+
+static int arm_mmu500_reset(struct arm_smmu_device *smmu)
+{
+ u32 reg, major;
+ int i;
+ /*
+ * On MMU-500 r2p0 onwards we need to clear ACR.CACHE_LOCK before
+ * writes to the context bank ACTLRs will stick. And we just hope that
+ * Secure has also cleared SACR.CACHE_LOCK for this to take effect...
+ */
+ reg = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_ID7);
+ major = FIELD_GET(ID7_MAJOR, reg);
+ reg = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sACR);
+ if (major >= 2)
+ reg &= ~ARM_MMU500_ACR_CACHE_LOCK;
+ /*
+ * Allow unmatched Stream IDs to allocate bypass
+ * TLB entries for reduced latency.
+ */
+ reg |= ARM_MMU500_ACR_SMTNMB_TLBEN | ARM_MMU500_ACR_S2CRB_TLBEN;
+ arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sACR, reg);
+
+ /*
+ * Disable MMU-500's not-particularly-beneficial next-page
+ * prefetcher for the sake of errata #841119 and #826419.
+ */
+ for (i = 0; i < smmu->num_context_banks; ++i) {
+ reg = arm_smmu_cb_read(smmu, i, ARM_SMMU_CB_ACTLR);
+ reg &= ~ARM_MMU500_ACTLR_CPRE;
+ arm_smmu_cb_write(smmu, i, ARM_SMMU_CB_ACTLR, reg);
+ }
+
+ return 0;
+}
+
+static const struct arm_smmu_impl arm_mmu500_impl = {
+ .reset = arm_mmu500_reset,
+};
+
+
+struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu)
+{
+ /*
+ * We will inevitably have to combine model-specific implementation
+ * quirks with platform-specific integration quirks, but everything
+ * we currently support happens to work out as straightforward
+ * mutually-exclusive assignments.
+ */
+ switch (smmu->model) {
+ case ARM_MMU500:
+ smmu->impl = &arm_mmu500_impl;
+ break;
+ case CAVIUM_SMMUV2:
+ return cavium_smmu_impl_init(smmu);
+ default:
+ break;
+ }
+
+ if (of_property_read_bool(smmu->dev->of_node,
+ "calxeda,smmu-secure-config-access"))
+ smmu->impl = &calxeda_impl;
+
+ return smmu;
+}
diff --git a/drivers/iommu/arm-smmu-regs.h b/drivers/iommu/arm-smmu-regs.h
deleted file mode 100644
index 1c278f7ae888..000000000000
--- a/drivers/iommu/arm-smmu-regs.h
+++ /dev/null
@@ -1,210 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * IOMMU API for ARM architected SMMU implementations.
- *
- * Copyright (C) 2013 ARM Limited
- *
- * Author: Will Deacon <will.deacon@arm.com>
- */
-
-#ifndef _ARM_SMMU_REGS_H
-#define _ARM_SMMU_REGS_H
-
-/* 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_EXIDENABLE (1 << 3)
-#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_VMID16EN (1 << 31)
-#define sCR0_BSU_SHIFT 14
-#define sCR0_BSU_MASK 0x3
-
-/* Auxiliary Configuration register */
-#define ARM_SMMU_GR0_sACR 0x10
-
-/* 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 ID0_S1TS (1 << 30)
-#define ID0_S2TS (1 << 29)
-#define ID0_NTS (1 << 28)
-#define ID0_SMS (1 << 27)
-#define ID0_ATOSNS (1 << 26)
-#define ID0_PTFS_NO_AARCH32 (1 << 25)
-#define ID0_PTFS_NO_AARCH32S (1 << 24)
-#define ID0_CTTW (1 << 14)
-#define ID0_NUMIRPT_SHIFT 16
-#define ID0_NUMIRPT_MASK 0xff
-#define ID0_NUMSIDB_SHIFT 9
-#define ID0_NUMSIDB_MASK 0xf
-#define ID0_EXIDS (1 << 8)
-#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 ID2_VMID16 (1 << 15)
-
-#define ID7_MAJOR_SHIFT 4
-#define ID7_MAJOR_MASK 0xf
-
-/* Global TLB invalidation */
-#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)
-
-/* Stream mapping registers */
-#define ARM_SMMU_GR0_SMR(n) (0x800 + ((n) << 2))
-#define SMR_VALID (1 << 31)
-#define SMR_MASK_SHIFT 16
-#define SMR_ID_SHIFT 0
-
-#define ARM_SMMU_GR0_S2CR(n) (0xc00 + ((n) << 2))
-#define S2CR_CBNDX_SHIFT 0
-#define S2CR_CBNDX_MASK 0xff
-#define S2CR_EXIDVALID (1 << 10)
-#define S2CR_TYPE_SHIFT 16
-#define S2CR_TYPE_MASK 0x3
-enum arm_smmu_s2cr_type {
- S2CR_TYPE_TRANS,
- S2CR_TYPE_BYPASS,
- S2CR_TYPE_FAULT,
-};
-
-#define S2CR_PRIVCFG_SHIFT 24
-#define S2CR_PRIVCFG_MASK 0x3
-enum arm_smmu_s2cr_privcfg {
- S2CR_PRIVCFG_DEFAULT,
- S2CR_PRIVCFG_DIPAN,
- S2CR_PRIVCFG_UNPRIV,
- S2CR_PRIVCFG_PRIV,
-};
-
-/* 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_BPSHCFG_SHIFT 8
-#define CBAR_S1_BPSHCFG_MASK 3
-#define CBAR_S1_BPSHCFG_NSH 3
-#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_CBFRSYNRA(n) (0x400 + ((n) << 2))
-
-#define ARM_SMMU_GR1_CBA2R(n) (0x800 + ((n) << 2))
-#define CBA2R_RW64_32BIT (0 << 0)
-#define CBA2R_RW64_64BIT (1 << 0)
-#define CBA2R_VMID_SHIFT 16
-#define CBA2R_VMID_MASK 0xffff
-
-#define ARM_SMMU_CB_SCTLR 0x0
-#define ARM_SMMU_CB_ACTLR 0x4
-#define ARM_SMMU_CB_RESUME 0x8
-#define ARM_SMMU_CB_TTBCR2 0x10
-#define ARM_SMMU_CB_TTBR0 0x20
-#define ARM_SMMU_CB_TTBR1 0x28
-#define ARM_SMMU_CB_TTBCR 0x30
-#define ARM_SMMU_CB_CONTEXTIDR 0x34
-#define ARM_SMMU_CB_S1_MAIR0 0x38
-#define ARM_SMMU_CB_S1_MAIR1 0x3c
-#define ARM_SMMU_CB_PAR 0x50
-#define ARM_SMMU_CB_FSR 0x58
-#define ARM_SMMU_CB_FAR 0x60
-#define ARM_SMMU_CB_FSYNR0 0x68
-#define ARM_SMMU_CB_S1_TLBIVA 0x600
-#define ARM_SMMU_CB_S1_TLBIASID 0x610
-#define ARM_SMMU_CB_S1_TLBIVAL 0x620
-#define ARM_SMMU_CB_S2_TLBIIPAS2 0x630
-#define ARM_SMMU_CB_S2_TLBIIPAS2L 0x638
-#define ARM_SMMU_CB_TLBSYNC 0x7f0
-#define ARM_SMMU_CB_TLBSTATUS 0x7f4
-#define ARM_SMMU_CB_ATS1PR 0x800
-#define ARM_SMMU_CB_ATSR 0x8f0
-
-#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 CB_PAR_F (1 << 0)
-
-#define ATSR_ACTIVE (1 << 0)
-
-#define RESUME_RETRY (0 << 0)
-#define RESUME_TERMINATE (1 << 0)
-
-#define TTBCR2_SEP_SHIFT 15
-#define TTBCR2_SEP_UPSTREAM (0x7 << TTBCR2_SEP_SHIFT)
-#define TTBCR2_AS (1 << 4)
-
-#define TTBRn_ASID_SHIFT 48
-
-#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 | FSR_IGN)
-
-#define FSYNR0_WNR (1 << 4)
-
-#endif /* _ARM_SMMU_REGS_H */
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index c5c93e48b4db..4aa414843557 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -181,12 +181,13 @@
#define ARM_SMMU_MEMATTR_DEVICE_nGnRE 0x1
#define ARM_SMMU_MEMATTR_OIWB 0xf
-#define Q_IDX(q, p) ((p) & ((1 << (q)->max_n_shift) - 1))
-#define Q_WRP(q, p) ((p) & (1 << (q)->max_n_shift))
-#define Q_OVERFLOW_FLAG (1 << 31)
-#define Q_OVF(q, p) ((p) & Q_OVERFLOW_FLAG)
+#define Q_IDX(llq, p) ((p) & ((1 << (llq)->max_n_shift) - 1))
+#define Q_WRP(llq, p) ((p) & (1 << (llq)->max_n_shift))
+#define Q_OVERFLOW_FLAG (1U << 31)
+#define Q_OVF(p) ((p) & Q_OVERFLOW_FLAG)
#define Q_ENT(q, p) ((q)->base + \
- Q_IDX(q, p) * (q)->ent_dwords)
+ Q_IDX(&((q)->llq), p) * \
+ (q)->ent_dwords)
#define Q_BASE_RWA (1UL << 62)
#define Q_BASE_ADDR_MASK GENMASK_ULL(51, 5)
@@ -306,6 +307,15 @@
#define CMDQ_ERR_CERROR_ABT_IDX 2
#define CMDQ_ERR_CERROR_ATC_INV_IDX 3
+#define CMDQ_PROD_OWNED_FLAG Q_OVERFLOW_FLAG
+
+/*
+ * This is used to size the command queue and therefore must be at least
+ * BITS_PER_LONG so that the valid_map works correctly (it relies on the
+ * total number of queue entries being a multiple of BITS_PER_LONG).
+ */
+#define CMDQ_BATCH_ENTRIES BITS_PER_LONG
+
#define CMDQ_0_OP GENMASK_ULL(7, 0)
#define CMDQ_0_SSV (1UL << 11)
@@ -368,9 +378,8 @@
#define PRIQ_1_ADDR_MASK GENMASK_ULL(63, 12)
/* High-level queue structures */
-#define ARM_SMMU_POLL_TIMEOUT_US 100
-#define ARM_SMMU_CMDQ_SYNC_TIMEOUT_US 1000000 /* 1s! */
-#define ARM_SMMU_CMDQ_SYNC_SPIN_COUNT 10
+#define ARM_SMMU_POLL_TIMEOUT_US 1000000 /* 1s! */
+#define ARM_SMMU_POLL_SPIN_COUNT 10
#define MSI_IOVA_BASE 0x8000000
#define MSI_IOVA_LENGTH 0x100000
@@ -472,13 +481,29 @@ struct arm_smmu_cmdq_ent {
#define CMDQ_OP_CMD_SYNC 0x46
struct {
- u32 msidata;
u64 msiaddr;
} sync;
};
};
+struct arm_smmu_ll_queue {
+ union {
+ u64 val;
+ struct {
+ u32 prod;
+ u32 cons;
+ };
+ struct {
+ atomic_t prod;
+ atomic_t cons;
+ } atomic;
+ u8 __pad[SMP_CACHE_BYTES];
+ } ____cacheline_aligned_in_smp;
+ u32 max_n_shift;
+};
+
struct arm_smmu_queue {
+ struct arm_smmu_ll_queue llq;
int irq; /* Wired interrupt */
__le64 *base;
@@ -486,17 +511,23 @@ struct arm_smmu_queue {
u64 q_base;
size_t ent_dwords;
- u32 max_n_shift;
- u32 prod;
- u32 cons;
u32 __iomem *prod_reg;
u32 __iomem *cons_reg;
};
+struct arm_smmu_queue_poll {
+ ktime_t timeout;
+ unsigned int delay;
+ unsigned int spin_cnt;
+ bool wfe;
+};
+
struct arm_smmu_cmdq {
struct arm_smmu_queue q;
- spinlock_t lock;
+ atomic_long_t *valid_map;
+ atomic_t owner_prod;
+ atomic_t lock;
};
struct arm_smmu_evtq {
@@ -576,8 +607,6 @@ struct arm_smmu_device {
int gerr_irq;
int combined_irq;
- u32 sync_nr;
- u8 prev_cmd_opcode;
unsigned long ias; /* IPA */
unsigned long oas; /* PA */
@@ -596,12 +625,6 @@ struct arm_smmu_device {
struct arm_smmu_strtab_cfg strtab_cfg;
- /* Hi16xx adds an extra 32 bits of goodness to its MSI payload */
- union {
- u32 sync_count;
- u64 padding;
- };
-
/* IOMMU core code handle */
struct iommu_device iommu;
};
@@ -614,7 +637,7 @@ struct arm_smmu_master {
struct list_head domain_head;
u32 *sids;
unsigned int num_sids;
- bool ats_enabled :1;
+ bool ats_enabled;
};
/* SMMU private data for an IOMMU domain */
@@ -631,6 +654,7 @@ struct arm_smmu_domain {
struct io_pgtable_ops *pgtbl_ops;
bool non_strict;
+ atomic_t nr_ats_masters;
enum arm_smmu_domain_stage stage;
union {
@@ -685,85 +709,97 @@ static void parse_driver_options(struct arm_smmu_device *smmu)
}
/* Low-level queue manipulation functions */
-static bool queue_full(struct arm_smmu_queue *q)
+static bool queue_has_space(struct arm_smmu_ll_queue *q, u32 n)
+{
+ u32 space, prod, cons;
+
+ prod = Q_IDX(q, q->prod);
+ cons = Q_IDX(q, q->cons);
+
+ if (Q_WRP(q, q->prod) == Q_WRP(q, q->cons))
+ space = (1 << q->max_n_shift) - (prod - cons);
+ else
+ space = cons - prod;
+
+ return space >= n;
+}
+
+static bool queue_full(struct arm_smmu_ll_queue *q)
{
return Q_IDX(q, q->prod) == Q_IDX(q, q->cons) &&
Q_WRP(q, q->prod) != Q_WRP(q, q->cons);
}
-static bool queue_empty(struct arm_smmu_queue *q)
+static bool queue_empty(struct arm_smmu_ll_queue *q)
{
return Q_IDX(q, q->prod) == Q_IDX(q, q->cons) &&
Q_WRP(q, q->prod) == Q_WRP(q, q->cons);
}
-static void queue_sync_cons(struct arm_smmu_queue *q)
+static bool queue_consumed(struct arm_smmu_ll_queue *q, u32 prod)
{
- q->cons = readl_relaxed(q->cons_reg);
+ return ((Q_WRP(q, q->cons) == Q_WRP(q, prod)) &&
+ (Q_IDX(q, q->cons) > Q_IDX(q, prod))) ||
+ ((Q_WRP(q, q->cons) != Q_WRP(q, prod)) &&
+ (Q_IDX(q, q->cons) <= Q_IDX(q, prod)));
}
-static void queue_inc_cons(struct arm_smmu_queue *q)
+static void queue_sync_cons_out(struct arm_smmu_queue *q)
{
- u32 cons = (Q_WRP(q, q->cons) | Q_IDX(q, q->cons)) + 1;
-
- q->cons = Q_OVF(q, q->cons) | Q_WRP(q, cons) | Q_IDX(q, cons);
-
/*
* Ensure that all CPU accesses (reads and writes) to the queue
* are complete before we update the cons pointer.
*/
mb();
- writel_relaxed(q->cons, q->cons_reg);
+ writel_relaxed(q->llq.cons, q->cons_reg);
+}
+
+static void queue_inc_cons(struct arm_smmu_ll_queue *q)
+{
+ u32 cons = (Q_WRP(q, q->cons) | Q_IDX(q, q->cons)) + 1;
+ q->cons = Q_OVF(q->cons) | Q_WRP(q, cons) | Q_IDX(q, cons);
}
-static int queue_sync_prod(struct arm_smmu_queue *q)
+static int queue_sync_prod_in(struct arm_smmu_queue *q)
{
int ret = 0;
u32 prod = readl_relaxed(q->prod_reg);
- if (Q_OVF(q, prod) != Q_OVF(q, q->prod))
+ if (Q_OVF(prod) != Q_OVF(q->llq.prod))
ret = -EOVERFLOW;
- q->prod = prod;
+ q->llq.prod = prod;
return ret;
}
-static void queue_inc_prod(struct arm_smmu_queue *q)
+static u32 queue_inc_prod_n(struct arm_smmu_ll_queue *q, int n)
{
- u32 prod = (Q_WRP(q, q->prod) | Q_IDX(q, q->prod)) + 1;
-
- q->prod = Q_OVF(q, q->prod) | Q_WRP(q, prod) | Q_IDX(q, prod);
- writel(q->prod, q->prod_reg);
+ u32 prod = (Q_WRP(q, q->prod) | Q_IDX(q, q->prod)) + n;
+ return Q_OVF(q->prod) | Q_WRP(q, prod) | Q_IDX(q, prod);
}
-/*
- * Wait for the SMMU to consume items. If sync is true, wait until the queue
- * is empty. Otherwise, wait until there is at least one free slot.
- */
-static int queue_poll_cons(struct arm_smmu_queue *q, bool sync, bool wfe)
+static void queue_poll_init(struct arm_smmu_device *smmu,
+ struct arm_smmu_queue_poll *qp)
{
- ktime_t timeout;
- unsigned int delay = 1, spin_cnt = 0;
-
- /* Wait longer if it's a CMD_SYNC */
- timeout = ktime_add_us(ktime_get(), sync ?
- ARM_SMMU_CMDQ_SYNC_TIMEOUT_US :
- ARM_SMMU_POLL_TIMEOUT_US);
+ qp->delay = 1;
+ qp->spin_cnt = 0;
+ qp->wfe = !!(smmu->features & ARM_SMMU_FEAT_SEV);
+ qp->timeout = ktime_add_us(ktime_get(), ARM_SMMU_POLL_TIMEOUT_US);
+}
- while (queue_sync_cons(q), (sync ? !queue_empty(q) : queue_full(q))) {
- if (ktime_compare(ktime_get(), timeout) > 0)
- return -ETIMEDOUT;
+static int queue_poll(struct arm_smmu_queue_poll *qp)
+{
+ if (ktime_compare(ktime_get(), qp->timeout) > 0)
+ return -ETIMEDOUT;
- if (wfe) {
- wfe();
- } else if (++spin_cnt < ARM_SMMU_CMDQ_SYNC_SPIN_COUNT) {
- cpu_relax();
- continue;
- } else {
- udelay(delay);
- delay *= 2;
- spin_cnt = 0;
- }
+ if (qp->wfe) {
+ wfe();
+ } else if (++qp->spin_cnt < ARM_SMMU_POLL_SPIN_COUNT) {
+ cpu_relax();
+ } else {
+ udelay(qp->delay);
+ qp->delay *= 2;
+ qp->spin_cnt = 0;
}
return 0;
@@ -777,16 +813,6 @@ static void queue_write(__le64 *dst, u64 *src, size_t n_dwords)
*dst++ = cpu_to_le64(*src++);
}
-static int queue_insert_raw(struct arm_smmu_queue *q, u64 *ent)
-{
- if (queue_full(q))
- return -ENOSPC;
-
- queue_write(Q_ENT(q, q->prod), ent, q->ent_dwords);
- queue_inc_prod(q);
- return 0;
-}
-
static void queue_read(__le64 *dst, u64 *src, size_t n_dwords)
{
int i;
@@ -797,11 +823,12 @@ static void queue_read(__le64 *dst, u64 *src, size_t n_dwords)
static int queue_remove_raw(struct arm_smmu_queue *q, u64 *ent)
{
- if (queue_empty(q))
+ if (queue_empty(&q->llq))
return -EAGAIN;
- queue_read(ent, Q_ENT(q, q->cons), q->ent_dwords);
- queue_inc_cons(q);
+ queue_read(ent, Q_ENT(q, q->llq.cons), q->ent_dwords);
+ queue_inc_cons(&q->llq);
+ queue_sync_cons_out(q);
return 0;
}
@@ -868,20 +895,14 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
cmd[1] |= FIELD_PREP(CMDQ_PRI_1_RESP, ent->pri.resp);
break;
case CMDQ_OP_CMD_SYNC:
- if (ent->sync.msiaddr)
+ if (ent->sync.msiaddr) {
cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_CS, CMDQ_SYNC_0_CS_IRQ);
- else
+ cmd[1] |= ent->sync.msiaddr & CMDQ_SYNC_1_MSIADDR_MASK;
+ } else {
cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_CS, CMDQ_SYNC_0_CS_SEV);
+ }
cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_MSH, ARM_SMMU_SH_ISH);
cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_MSIATTR, ARM_SMMU_MEMATTR_OIWB);
- /*
- * Commands are written little-endian, but we want the SMMU to
- * receive MSIData, and thus write it back to memory, in CPU
- * byte order, so big-endian needs an extra byteswap here.
- */
- cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_MSIDATA,
- cpu_to_le32(ent->sync.msidata));
- cmd[1] |= ent->sync.msiaddr & CMDQ_SYNC_1_MSIADDR_MASK;
break;
default:
return -ENOENT;
@@ -890,6 +911,27 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
return 0;
}
+static void arm_smmu_cmdq_build_sync_cmd(u64 *cmd, struct arm_smmu_device *smmu,
+ u32 prod)
+{
+ struct arm_smmu_queue *q = &smmu->cmdq.q;
+ struct arm_smmu_cmdq_ent ent = {
+ .opcode = CMDQ_OP_CMD_SYNC,
+ };
+
+ /*
+ * Beware that Hi16xx adds an extra 32 bits of goodness to its MSI
+ * payload, so the write will zero the entire command on that platform.
+ */
+ if (smmu->features & ARM_SMMU_FEAT_MSI &&
+ smmu->features & ARM_SMMU_FEAT_COHERENCY) {
+ ent.sync.msiaddr = q->base_dma + Q_IDX(&q->llq, prod) *
+ q->ent_dwords * 8;
+ }
+
+ arm_smmu_cmdq_build_cmd(cmd, &ent);
+}
+
static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu)
{
static const char *cerror_str[] = {
@@ -948,109 +990,456 @@ static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu)
queue_write(Q_ENT(q, cons), cmd, q->ent_dwords);
}
-static void arm_smmu_cmdq_insert_cmd(struct arm_smmu_device *smmu, u64 *cmd)
+/*
+ * Command queue locking.
+ * This is a form of bastardised rwlock with the following major changes:
+ *
+ * - The only LOCK routines are exclusive_trylock() and shared_lock().
+ * Neither have barrier semantics, and instead provide only a control
+ * dependency.
+ *
+ * - The UNLOCK routines are supplemented with shared_tryunlock(), which
+ * fails if the caller appears to be the last lock holder (yes, this is
+ * racy). All successful UNLOCK routines have RELEASE semantics.
+ */
+static void arm_smmu_cmdq_shared_lock(struct arm_smmu_cmdq *cmdq)
{
- struct arm_smmu_queue *q = &smmu->cmdq.q;
- bool wfe = !!(smmu->features & ARM_SMMU_FEAT_SEV);
+ int val;
+
+ /*
+ * We can try to avoid the cmpxchg() loop by simply incrementing the
+ * lock counter. When held in exclusive state, the lock counter is set
+ * to INT_MIN so these increments won't hurt as the value will remain
+ * negative.
+ */
+ if (atomic_fetch_inc_relaxed(&cmdq->lock) >= 0)
+ return;
+
+ do {
+ val = atomic_cond_read_relaxed(&cmdq->lock, VAL >= 0);
+ } while (atomic_cmpxchg_relaxed(&cmdq->lock, val, val + 1) != val);
+}
+
+static void arm_smmu_cmdq_shared_unlock(struct arm_smmu_cmdq *cmdq)
+{
+ (void)atomic_dec_return_release(&cmdq->lock);
+}
+
+static bool arm_smmu_cmdq_shared_tryunlock(struct arm_smmu_cmdq *cmdq)
+{
+ if (atomic_read(&cmdq->lock) == 1)
+ return false;
+
+ arm_smmu_cmdq_shared_unlock(cmdq);
+ return true;
+}
+
+#define arm_smmu_cmdq_exclusive_trylock_irqsave(cmdq, flags) \
+({ \
+ bool __ret; \
+ local_irq_save(flags); \
+ __ret = !atomic_cmpxchg_relaxed(&cmdq->lock, 0, INT_MIN); \
+ if (!__ret) \
+ local_irq_restore(flags); \
+ __ret; \
+})
+
+#define arm_smmu_cmdq_exclusive_unlock_irqrestore(cmdq, flags) \
+({ \
+ atomic_set_release(&cmdq->lock, 0); \
+ local_irq_restore(flags); \
+})
+
+
+/*
+ * Command queue insertion.
+ * This is made fiddly by our attempts to achieve some sort of scalability
+ * since there is one queue shared amongst all of the CPUs in the system. If
+ * you like mixed-size concurrency, dependency ordering and relaxed atomics,
+ * then you'll *love* this monstrosity.
+ *
+ * The basic idea is to split the queue up into ranges of commands that are
+ * owned by a given CPU; the owner may not have written all of the commands
+ * itself, but is responsible for advancing the hardware prod pointer when
+ * the time comes. The algorithm is roughly:
+ *
+ * 1. Allocate some space in the queue. At this point we also discover
+ * whether the head of the queue is currently owned by another CPU,
+ * or whether we are the owner.
+ *
+ * 2. Write our commands into our allocated slots in the queue.
+ *
+ * 3. Mark our slots as valid in arm_smmu_cmdq.valid_map.
+ *
+ * 4. If we are an owner:
+ * a. Wait for the previous owner to finish.
+ * b. Mark the queue head as unowned, which tells us the range
+ * that we are responsible for publishing.
+ * c. Wait for all commands in our owned range to become valid.
+ * d. Advance the hardware prod pointer.
+ * e. Tell the next owner we've finished.
+ *
+ * 5. If we are inserting a CMD_SYNC (we may or may not have been an
+ * owner), then we need to stick around until it has completed:
+ * a. If we have MSIs, the SMMU can write back into the CMD_SYNC
+ * to clear the first 4 bytes.
+ * b. Otherwise, we spin waiting for the hardware cons pointer to
+ * advance past our command.
+ *
+ * The devil is in the details, particularly the use of locking for handling
+ * SYNC completion and freeing up space in the queue before we think that it is
+ * full.
+ */
+static void __arm_smmu_cmdq_poll_set_valid_map(struct arm_smmu_cmdq *cmdq,
+ u32 sprod, u32 eprod, bool set)
+{
+ u32 swidx, sbidx, ewidx, ebidx;
+ struct arm_smmu_ll_queue llq = {
+ .max_n_shift = cmdq->q.llq.max_n_shift,
+ .prod = sprod,
+ };
+
+ ewidx = BIT_WORD(Q_IDX(&llq, eprod));
+ ebidx = Q_IDX(&llq, eprod) % BITS_PER_LONG;
+
+ while (llq.prod != eprod) {
+ unsigned long mask;
+ atomic_long_t *ptr;
+ u32 limit = BITS_PER_LONG;
+
+ swidx = BIT_WORD(Q_IDX(&llq, llq.prod));
+ sbidx = Q_IDX(&llq, llq.prod) % BITS_PER_LONG;
- smmu->prev_cmd_opcode = FIELD_GET(CMDQ_0_OP, cmd[0]);
+ ptr = &cmdq->valid_map[swidx];
- while (queue_insert_raw(q, cmd) == -ENOSPC) {
- if (queue_poll_cons(q, false, wfe))
- dev_err_ratelimited(smmu->dev, "CMDQ timeout\n");
+ if ((swidx == ewidx) && (sbidx < ebidx))
+ limit = ebidx;
+
+ mask = GENMASK(limit - 1, sbidx);
+
+ /*
+ * The valid bit is the inverse of the wrap bit. This means
+ * that a zero-initialised queue is invalid and, after marking
+ * all entries as valid, they become invalid again when we
+ * wrap.
+ */
+ if (set) {
+ atomic_long_xor(mask, ptr);
+ } else { /* Poll */
+ unsigned long valid;
+
+ valid = (ULONG_MAX + !!Q_WRP(&llq, llq.prod)) & mask;
+ atomic_long_cond_read_relaxed(ptr, (VAL & mask) == valid);
+ }
+
+ llq.prod = queue_inc_prod_n(&llq, limit - sbidx);
}
}
-static void arm_smmu_cmdq_issue_cmd(struct arm_smmu_device *smmu,
- struct arm_smmu_cmdq_ent *ent)
+/* Mark all entries in the range [sprod, eprod) as valid */
+static void arm_smmu_cmdq_set_valid_map(struct arm_smmu_cmdq *cmdq,
+ u32 sprod, u32 eprod)
+{
+ __arm_smmu_cmdq_poll_set_valid_map(cmdq, sprod, eprod, true);
+}
+
+/* Wait for all entries in the range [sprod, eprod) to become valid */
+static void arm_smmu_cmdq_poll_valid_map(struct arm_smmu_cmdq *cmdq,
+ u32 sprod, u32 eprod)
+{
+ __arm_smmu_cmdq_poll_set_valid_map(cmdq, sprod, eprod, false);
+}
+
+/* Wait for the command queue to become non-full */
+static int arm_smmu_cmdq_poll_until_not_full(struct arm_smmu_device *smmu,
+ struct arm_smmu_ll_queue *llq)
{
- u64 cmd[CMDQ_ENT_DWORDS];
unsigned long flags;
+ struct arm_smmu_queue_poll qp;
+ struct arm_smmu_cmdq *cmdq = &smmu->cmdq;
+ int ret = 0;
- if (arm_smmu_cmdq_build_cmd(cmd, ent)) {
- dev_warn(smmu->dev, "ignoring unknown CMDQ opcode 0x%x\n",
- ent->opcode);
- return;
+ /*
+ * Try to update our copy of cons by grabbing exclusive cmdq access. If
+ * that fails, spin until somebody else updates it for us.
+ */
+ if (arm_smmu_cmdq_exclusive_trylock_irqsave(cmdq, flags)) {
+ WRITE_ONCE(cmdq->q.llq.cons, readl_relaxed(cmdq->q.cons_reg));
+ arm_smmu_cmdq_exclusive_unlock_irqrestore(cmdq, flags);
+ llq->val = READ_ONCE(cmdq->q.llq.val);
+ return 0;
}
- spin_lock_irqsave(&smmu->cmdq.lock, flags);
- arm_smmu_cmdq_insert_cmd(smmu, cmd);
- spin_unlock_irqrestore(&smmu->cmdq.lock, flags);
+ queue_poll_init(smmu, &qp);
+ do {
+ llq->val = READ_ONCE(smmu->cmdq.q.llq.val);
+ if (!queue_full(llq))
+ break;
+
+ ret = queue_poll(&qp);
+ } while (!ret);
+
+ return ret;
}
/*
- * The difference between val and sync_idx is bounded by the maximum size of
- * a queue at 2^20 entries, so 32 bits is plenty for wrap-safe arithmetic.
+ * Wait until the SMMU signals a CMD_SYNC completion MSI.
+ * Must be called with the cmdq lock held in some capacity.
*/
-static int __arm_smmu_sync_poll_msi(struct arm_smmu_device *smmu, u32 sync_idx)
+static int __arm_smmu_cmdq_poll_until_msi(struct arm_smmu_device *smmu,
+ struct arm_smmu_ll_queue *llq)
{
- ktime_t timeout;
- u32 val;
+ int ret = 0;
+ struct arm_smmu_queue_poll qp;
+ struct arm_smmu_cmdq *cmdq = &smmu->cmdq;
+ u32 *cmd = (u32 *)(Q_ENT(&cmdq->q, llq->prod));
- timeout = ktime_add_us(ktime_get(), ARM_SMMU_CMDQ_SYNC_TIMEOUT_US);
- val = smp_cond_load_acquire(&smmu->sync_count,
- (int)(VAL - sync_idx) >= 0 ||
- !ktime_before(ktime_get(), timeout));
+ queue_poll_init(smmu, &qp);
- return (int)(val - sync_idx) < 0 ? -ETIMEDOUT : 0;
+ /*
+ * The MSI won't generate an event, since it's being written back
+ * into the command queue.
+ */
+ qp.wfe = false;
+ smp_cond_load_relaxed(cmd, !VAL || (ret = queue_poll(&qp)));
+ llq->cons = ret ? llq->prod : queue_inc_prod_n(llq, 1);
+ return ret;
}
-static int __arm_smmu_cmdq_issue_sync_msi(struct arm_smmu_device *smmu)
+/*
+ * Wait until the SMMU cons index passes llq->prod.
+ * Must be called with the cmdq lock held in some capacity.
+ */
+static int __arm_smmu_cmdq_poll_until_consumed(struct arm_smmu_device *smmu,
+ struct arm_smmu_ll_queue *llq)
{
- u64 cmd[CMDQ_ENT_DWORDS];
- unsigned long flags;
- struct arm_smmu_cmdq_ent ent = {
- .opcode = CMDQ_OP_CMD_SYNC,
- .sync = {
- .msiaddr = virt_to_phys(&smmu->sync_count),
- },
- };
+ struct arm_smmu_queue_poll qp;
+ struct arm_smmu_cmdq *cmdq = &smmu->cmdq;
+ u32 prod = llq->prod;
+ int ret = 0;
- spin_lock_irqsave(&smmu->cmdq.lock, flags);
+ queue_poll_init(smmu, &qp);
+ llq->val = READ_ONCE(smmu->cmdq.q.llq.val);
+ do {
+ if (queue_consumed(llq, prod))
+ break;
- /* Piggy-back on the previous command if it's a SYNC */
- if (smmu->prev_cmd_opcode == CMDQ_OP_CMD_SYNC) {
- ent.sync.msidata = smmu->sync_nr;
- } else {
- ent.sync.msidata = ++smmu->sync_nr;
- arm_smmu_cmdq_build_cmd(cmd, &ent);
- arm_smmu_cmdq_insert_cmd(smmu, cmd);
- }
+ ret = queue_poll(&qp);
- spin_unlock_irqrestore(&smmu->cmdq.lock, flags);
+ /*
+ * This needs to be a readl() so that our subsequent call
+ * to arm_smmu_cmdq_shared_tryunlock() can fail accurately.
+ *
+ * Specifically, we need to ensure that we observe all
+ * shared_lock()s by other CMD_SYNCs that share our owner,
+ * so that a failing call to tryunlock() means that we're
+ * the last one out and therefore we can safely advance
+ * cmdq->q.llq.cons. Roughly speaking:
+ *
+ * CPU 0 CPU1 CPU2 (us)
+ *
+ * if (sync)
+ * shared_lock();
+ *
+ * dma_wmb();
+ * set_valid_map();
+ *
+ * if (owner) {
+ * poll_valid_map();
+ * <control dependency>
+ * writel(prod_reg);
+ *
+ * readl(cons_reg);
+ * tryunlock();
+ *
+ * Requires us to see CPU 0's shared_lock() acquisition.
+ */
+ llq->cons = readl(cmdq->q.cons_reg);
+ } while (!ret);
- return __arm_smmu_sync_poll_msi(smmu, ent.sync.msidata);
+ return ret;
}
-static int __arm_smmu_cmdq_issue_sync(struct arm_smmu_device *smmu)
+static int arm_smmu_cmdq_poll_until_sync(struct arm_smmu_device *smmu,
+ struct arm_smmu_ll_queue *llq)
{
- u64 cmd[CMDQ_ENT_DWORDS];
+ if (smmu->features & ARM_SMMU_FEAT_MSI &&
+ smmu->features & ARM_SMMU_FEAT_COHERENCY)
+ return __arm_smmu_cmdq_poll_until_msi(smmu, llq);
+
+ return __arm_smmu_cmdq_poll_until_consumed(smmu, llq);
+}
+
+static void arm_smmu_cmdq_write_entries(struct arm_smmu_cmdq *cmdq, u64 *cmds,
+ u32 prod, int n)
+{
+ int i;
+ struct arm_smmu_ll_queue llq = {
+ .max_n_shift = cmdq->q.llq.max_n_shift,
+ .prod = prod,
+ };
+
+ for (i = 0; i < n; ++i) {
+ u64 *cmd = &cmds[i * CMDQ_ENT_DWORDS];
+
+ prod = queue_inc_prod_n(&llq, i);
+ queue_write(Q_ENT(&cmdq->q, prod), cmd, CMDQ_ENT_DWORDS);
+ }
+}
+
+/*
+ * This is the actual insertion function, and provides the following
+ * ordering guarantees to callers:
+ *
+ * - There is a dma_wmb() before publishing any commands to the queue.
+ * This can be relied upon to order prior writes to data structures
+ * in memory (such as a CD or an STE) before the command.
+ *
+ * - On completion of a CMD_SYNC, there is a control dependency.
+ * This can be relied upon to order subsequent writes to memory (e.g.
+ * freeing an IOVA) after completion of the CMD_SYNC.
+ *
+ * - Command insertion is totally ordered, so if two CPUs each race to
+ * insert their own list of commands then all of the commands from one
+ * CPU will appear before any of the commands from the other CPU.
+ */
+static int arm_smmu_cmdq_issue_cmdlist(struct arm_smmu_device *smmu,
+ u64 *cmds, int n, bool sync)
+{
+ u64 cmd_sync[CMDQ_ENT_DWORDS];
+ u32 prod;
unsigned long flags;
- bool wfe = !!(smmu->features & ARM_SMMU_FEAT_SEV);
- struct arm_smmu_cmdq_ent ent = { .opcode = CMDQ_OP_CMD_SYNC };
- int ret;
+ bool owner;
+ struct arm_smmu_cmdq *cmdq = &smmu->cmdq;
+ struct arm_smmu_ll_queue llq = {
+ .max_n_shift = cmdq->q.llq.max_n_shift,
+ }, head = llq;
+ int ret = 0;
- arm_smmu_cmdq_build_cmd(cmd, &ent);
+ /* 1. Allocate some space in the queue */
+ local_irq_save(flags);
+ llq.val = READ_ONCE(cmdq->q.llq.val);
+ do {
+ u64 old;
+
+ while (!queue_has_space(&llq, n + sync)) {
+ local_irq_restore(flags);
+ if (arm_smmu_cmdq_poll_until_not_full(smmu, &llq))
+ dev_err_ratelimited(smmu->dev, "CMDQ timeout\n");
+ local_irq_save(flags);
+ }
- spin_lock_irqsave(&smmu->cmdq.lock, flags);
- arm_smmu_cmdq_insert_cmd(smmu, cmd);
- ret = queue_poll_cons(&smmu->cmdq.q, true, wfe);
- spin_unlock_irqrestore(&smmu->cmdq.lock, flags);
+ head.cons = llq.cons;
+ head.prod = queue_inc_prod_n(&llq, n + sync) |
+ CMDQ_PROD_OWNED_FLAG;
+ old = cmpxchg_relaxed(&cmdq->q.llq.val, llq.val, head.val);
+ if (old == llq.val)
+ break;
+
+ llq.val = old;
+ } while (1);
+ owner = !(llq.prod & CMDQ_PROD_OWNED_FLAG);
+ head.prod &= ~CMDQ_PROD_OWNED_FLAG;
+ llq.prod &= ~CMDQ_PROD_OWNED_FLAG;
+
+ /*
+ * 2. Write our commands into the queue
+ * Dependency ordering from the cmpxchg() loop above.
+ */
+ arm_smmu_cmdq_write_entries(cmdq, cmds, llq.prod, n);
+ if (sync) {
+ prod = queue_inc_prod_n(&llq, n);
+ arm_smmu_cmdq_build_sync_cmd(cmd_sync, smmu, prod);
+ queue_write(Q_ENT(&cmdq->q, prod), cmd_sync, CMDQ_ENT_DWORDS);
+
+ /*
+ * In order to determine completion of our CMD_SYNC, we must
+ * ensure that the queue can't wrap twice without us noticing.
+ * We achieve that by taking the cmdq lock as shared before
+ * marking our slot as valid.
+ */
+ arm_smmu_cmdq_shared_lock(cmdq);
+ }
+
+ /* 3. Mark our slots as valid, ensuring commands are visible first */
+ dma_wmb();
+ arm_smmu_cmdq_set_valid_map(cmdq, llq.prod, head.prod);
+
+ /* 4. If we are the owner, take control of the SMMU hardware */
+ if (owner) {
+ /* a. Wait for previous owner to finish */
+ atomic_cond_read_relaxed(&cmdq->owner_prod, VAL == llq.prod);
+
+ /* b. Stop gathering work by clearing the owned flag */
+ prod = atomic_fetch_andnot_relaxed(CMDQ_PROD_OWNED_FLAG,
+ &cmdq->q.llq.atomic.prod);
+ prod &= ~CMDQ_PROD_OWNED_FLAG;
+
+ /*
+ * c. Wait for any gathered work to be written to the queue.
+ * Note that we read our own entries so that we have the control
+ * dependency required by (d).
+ */
+ arm_smmu_cmdq_poll_valid_map(cmdq, llq.prod, prod);
+
+ /*
+ * d. Advance the hardware prod pointer
+ * Control dependency ordering from the entries becoming valid.
+ */
+ writel_relaxed(prod, cmdq->q.prod_reg);
+
+ /*
+ * e. Tell the next owner we're done
+ * Make sure we've updated the hardware first, so that we don't
+ * race to update prod and potentially move it backwards.
+ */
+ atomic_set_release(&cmdq->owner_prod, prod);
+ }
+
+ /* 5. If we are inserting a CMD_SYNC, we must wait for it to complete */
+ if (sync) {
+ llq.prod = queue_inc_prod_n(&llq, n);
+ ret = arm_smmu_cmdq_poll_until_sync(smmu, &llq);
+ if (ret) {
+ dev_err_ratelimited(smmu->dev,
+ "CMD_SYNC timeout at 0x%08x [hwprod 0x%08x, hwcons 0x%08x]\n",
+ llq.prod,
+ readl_relaxed(cmdq->q.prod_reg),
+ readl_relaxed(cmdq->q.cons_reg));
+ }
+
+ /*
+ * Try to unlock the cmq lock. This will fail if we're the last
+ * reader, in which case we can safely update cmdq->q.llq.cons
+ */
+ if (!arm_smmu_cmdq_shared_tryunlock(cmdq)) {
+ WRITE_ONCE(cmdq->q.llq.cons, llq.cons);
+ arm_smmu_cmdq_shared_unlock(cmdq);
+ }
+ }
+
+ local_irq_restore(flags);
return ret;
}
-static int arm_smmu_cmdq_issue_sync(struct arm_smmu_device *smmu)
+static int arm_smmu_cmdq_issue_cmd(struct arm_smmu_device *smmu,
+ struct arm_smmu_cmdq_ent *ent)
{
- int ret;
- bool msi = (smmu->features & ARM_SMMU_FEAT_MSI) &&
- (smmu->features & ARM_SMMU_FEAT_COHERENCY);
+ u64 cmd[CMDQ_ENT_DWORDS];
- ret = msi ? __arm_smmu_cmdq_issue_sync_msi(smmu)
- : __arm_smmu_cmdq_issue_sync(smmu);
- if (ret)
- dev_err_ratelimited(smmu->dev, "CMD_SYNC timeout\n");
- return ret;
+ if (arm_smmu_cmdq_build_cmd(cmd, ent)) {
+ dev_warn(smmu->dev, "ignoring unknown CMDQ opcode 0x%x\n",
+ ent->opcode);
+ return -EINVAL;
+ }
+
+ return arm_smmu_cmdq_issue_cmdlist(smmu, cmd, 1, false);
+}
+
+static int arm_smmu_cmdq_issue_sync(struct arm_smmu_device *smmu)
+{
+ return arm_smmu_cmdq_issue_cmdlist(smmu, NULL, 0, true);
}
/* Context descriptor manipulation functions */
@@ -1305,6 +1694,7 @@ static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev)
int i;
struct arm_smmu_device *smmu = dev;
struct arm_smmu_queue *q = &smmu->evtq.q;
+ struct arm_smmu_ll_queue *llq = &q->llq;
u64 evt[EVTQ_ENT_DWORDS];
do {
@@ -1322,12 +1712,13 @@ static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev)
* Not much we can do on overflow, so scream and pretend we're
* trying harder.
*/
- if (queue_sync_prod(q) == -EOVERFLOW)
+ if (queue_sync_prod_in(q) == -EOVERFLOW)
dev_err(smmu->dev, "EVTQ overflow detected -- events lost\n");
- } while (!queue_empty(q));
+ } while (!queue_empty(llq));
/* Sync our overflow flag, as we believe we're up to speed */
- q->cons = Q_OVF(q, q->prod) | Q_WRP(q, q->cons) | Q_IDX(q, q->cons);
+ llq->cons = Q_OVF(llq->prod) | Q_WRP(llq, llq->cons) |
+ Q_IDX(llq, llq->cons);
return IRQ_HANDLED;
}
@@ -1373,19 +1764,21 @@ static irqreturn_t arm_smmu_priq_thread(int irq, void *dev)
{
struct arm_smmu_device *smmu = dev;
struct arm_smmu_queue *q = &smmu->priq.q;
+ struct arm_smmu_ll_queue *llq = &q->llq;
u64 evt[PRIQ_ENT_DWORDS];
do {
while (!queue_remove_raw(q, evt))
arm_smmu_handle_ppr(smmu, evt);
- if (queue_sync_prod(q) == -EOVERFLOW)
+ if (queue_sync_prod_in(q) == -EOVERFLOW)
dev_err(smmu->dev, "PRIQ overflow detected -- requests lost\n");
- } while (!queue_empty(q));
+ } while (!queue_empty(llq));
/* Sync our overflow flag, as we believe we're up to speed */
- q->cons = Q_OVF(q, q->prod) | Q_WRP(q, q->cons) | Q_IDX(q, q->cons);
- writel(q->cons, q->cons_reg);
+ llq->cons = Q_OVF(llq->prod) | Q_WRP(llq, llq->cons) |
+ Q_IDX(llq, llq->cons);
+ queue_sync_cons_out(q);
return IRQ_HANDLED;
}
@@ -1534,6 +1927,23 @@ static int arm_smmu_atc_inv_domain(struct arm_smmu_domain *smmu_domain,
if (!(smmu_domain->smmu->features & ARM_SMMU_FEAT_ATS))
return 0;
+ /*
+ * Ensure that we've completed prior invalidation of the main TLBs
+ * before we read 'nr_ats_masters' in case of a concurrent call to
+ * arm_smmu_enable_ats():
+ *
+ * // unmap() // arm_smmu_enable_ats()
+ * TLBI+SYNC atomic_inc(&nr_ats_masters);
+ * smp_mb(); [...]
+ * atomic_read(&nr_ats_masters); pci_enable_ats() // writel()
+ *
+ * Ensures that we always see the incremented 'nr_ats_masters' count if
+ * ATS was enabled at the PCI device before completion of the TLBI.
+ */
+ smp_mb();
+ if (!atomic_read(&smmu_domain->nr_ats_masters))
+ return 0;
+
arm_smmu_atc_inv_to_cmd(ssid, iova, size, &cmd);
spin_lock_irqsave(&smmu_domain->devices_lock, flags);
@@ -1545,13 +1955,6 @@ static int arm_smmu_atc_inv_domain(struct arm_smmu_domain *smmu_domain,
}
/* IO_PGTABLE API */
-static void arm_smmu_tlb_sync(void *cookie)
-{
- struct arm_smmu_domain *smmu_domain = cookie;
-
- arm_smmu_cmdq_issue_sync(smmu_domain->smmu);
-}
-
static void arm_smmu_tlb_inv_context(void *cookie)
{
struct arm_smmu_domain *smmu_domain = cookie;
@@ -1570,25 +1973,32 @@ static void arm_smmu_tlb_inv_context(void *cookie)
/*
* NOTE: when io-pgtable is in non-strict mode, we may get here with
* PTEs previously cleared by unmaps on the current CPU not yet visible
- * to the SMMU. We are relying on the DSB implicit in queue_inc_prod()
- * to guarantee those are observed before the TLBI. Do be careful, 007.
+ * to the SMMU. We are relying on the dma_wmb() implicit during cmd
+ * insertion to guarantee those are observed before the TLBI. Do be
+ * careful, 007.
*/
arm_smmu_cmdq_issue_cmd(smmu, &cmd);
arm_smmu_cmdq_issue_sync(smmu);
+ arm_smmu_atc_inv_domain(smmu_domain, 0, 0, 0);
}
-static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size,
- size_t granule, bool leaf, void *cookie)
+static void arm_smmu_tlb_inv_range(unsigned long iova, size_t size,
+ size_t granule, bool leaf,
+ struct arm_smmu_domain *smmu_domain)
{
- struct arm_smmu_domain *smmu_domain = cookie;
+ u64 cmds[CMDQ_BATCH_ENTRIES * CMDQ_ENT_DWORDS];
struct arm_smmu_device *smmu = smmu_domain->smmu;
+ unsigned long start = iova, end = iova + size;
+ int i = 0;
struct arm_smmu_cmdq_ent cmd = {
.tlbi = {
.leaf = leaf,
- .addr = iova,
},
};
+ if (!size)
+ return;
+
if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
cmd.opcode = CMDQ_OP_TLBI_NH_VA;
cmd.tlbi.asid = smmu_domain->s1_cfg.cd.asid;
@@ -1597,16 +2007,54 @@ static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size,
cmd.tlbi.vmid = smmu_domain->s2_cfg.vmid;
}
- do {
- arm_smmu_cmdq_issue_cmd(smmu, &cmd);
- cmd.tlbi.addr += granule;
- } while (size -= granule);
+ while (iova < end) {
+ if (i == CMDQ_BATCH_ENTRIES) {
+ arm_smmu_cmdq_issue_cmdlist(smmu, cmds, i, false);
+ i = 0;
+ }
+
+ cmd.tlbi.addr = iova;
+ arm_smmu_cmdq_build_cmd(&cmds[i * CMDQ_ENT_DWORDS], &cmd);
+ iova += granule;
+ i++;
+ }
+
+ arm_smmu_cmdq_issue_cmdlist(smmu, cmds, i, true);
+
+ /*
+ * Unfortunately, this can't be leaf-only since we may have
+ * zapped an entire table.
+ */
+ arm_smmu_atc_inv_domain(smmu_domain, 0, start, size);
+}
+
+static void arm_smmu_tlb_inv_page_nosync(struct iommu_iotlb_gather *gather,
+ unsigned long iova, size_t granule,
+ void *cookie)
+{
+ struct arm_smmu_domain *smmu_domain = cookie;
+ struct iommu_domain *domain = &smmu_domain->domain;
+
+ iommu_iotlb_gather_add_page(domain, gather, iova, granule);
}
-static const struct iommu_gather_ops arm_smmu_gather_ops = {
+static void arm_smmu_tlb_inv_walk(unsigned long iova, size_t size,
+ size_t granule, void *cookie)
+{
+ arm_smmu_tlb_inv_range(iova, size, granule, false, cookie);
+}
+
+static void arm_smmu_tlb_inv_leaf(unsigned long iova, size_t size,
+ size_t granule, void *cookie)
+{
+ arm_smmu_tlb_inv_range(iova, size, granule, true, cookie);
+}
+
+static const struct iommu_flush_ops arm_smmu_flush_ops = {
.tlb_flush_all = arm_smmu_tlb_inv_context,
- .tlb_add_flush = arm_smmu_tlb_inv_range_nosync,
- .tlb_sync = arm_smmu_tlb_sync,
+ .tlb_flush_walk = arm_smmu_tlb_inv_walk,
+ .tlb_flush_leaf = arm_smmu_tlb_inv_leaf,
+ .tlb_add_page = arm_smmu_tlb_inv_page_nosync,
};
/* IOMMU API */
@@ -1796,7 +2244,7 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain)
.ias = ias,
.oas = oas,
.coherent_walk = smmu->features & ARM_SMMU_FEAT_COHERENCY,
- .tlb = &arm_smmu_gather_ops,
+ .tlb = &arm_smmu_flush_ops,
.iommu_dev = smmu->dev,
};
@@ -1863,44 +2311,65 @@ static void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master)
}
}
-static int arm_smmu_enable_ats(struct arm_smmu_master *master)
+#ifdef CONFIG_PCI_ATS
+static bool arm_smmu_ats_supported(struct arm_smmu_master *master)
{
- int ret;
- size_t stu;
struct pci_dev *pdev;
struct arm_smmu_device *smmu = master->smmu;
struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(master->dev);
if (!(smmu->features & ARM_SMMU_FEAT_ATS) || !dev_is_pci(master->dev) ||
!(fwspec->flags & IOMMU_FWSPEC_PCI_RC_ATS) || pci_ats_disabled())
- return -ENXIO;
+ return false;
pdev = to_pci_dev(master->dev);
- if (pdev->untrusted)
- return -EPERM;
+ return !pdev->untrusted && pdev->ats_cap;
+}
+#else
+static bool arm_smmu_ats_supported(struct arm_smmu_master *master)
+{
+ return false;
+}
+#endif
+
+static void arm_smmu_enable_ats(struct arm_smmu_master *master)
+{
+ size_t stu;
+ struct pci_dev *pdev;
+ struct arm_smmu_device *smmu = master->smmu;
+ struct arm_smmu_domain *smmu_domain = master->domain;
+
+ /* Don't enable ATS at the endpoint if it's not enabled in the STE */
+ if (!master->ats_enabled)
+ return;
/* Smallest Translation Unit: log2 of the smallest supported granule */
stu = __ffs(smmu->pgsize_bitmap);
+ pdev = to_pci_dev(master->dev);
- ret = pci_enable_ats(pdev, stu);
- if (ret)
- return ret;
-
- master->ats_enabled = true;
- return 0;
+ atomic_inc(&smmu_domain->nr_ats_masters);
+ arm_smmu_atc_inv_domain(smmu_domain, 0, 0, 0);
+ if (pci_enable_ats(pdev, stu))
+ dev_err(master->dev, "Failed to enable ATS (STU %zu)\n", stu);
}
static void arm_smmu_disable_ats(struct arm_smmu_master *master)
{
struct arm_smmu_cmdq_ent cmd;
+ struct arm_smmu_domain *smmu_domain = master->domain;
- if (!master->ats_enabled || !dev_is_pci(master->dev))
+ if (!master->ats_enabled)
return;
+ pci_disable_ats(to_pci_dev(master->dev));
+ /*
+ * Ensure ATS is disabled at the endpoint before we issue the
+ * ATC invalidation via the SMMU.
+ */
+ wmb();
arm_smmu_atc_inv_to_cmd(0, 0, 0, &cmd);
arm_smmu_atc_inv_master(master, &cmd);
- pci_disable_ats(to_pci_dev(master->dev));
- master->ats_enabled = false;
+ atomic_dec(&smmu_domain->nr_ats_masters);
}
static void arm_smmu_detach_dev(struct arm_smmu_master *master)
@@ -1911,14 +2380,15 @@ static void arm_smmu_detach_dev(struct arm_smmu_master *master)
if (!smmu_domain)
return;
+ arm_smmu_disable_ats(master);
+
spin_lock_irqsave(&smmu_domain->devices_lock, flags);
list_del(&master->domain_head);
spin_unlock_irqrestore(&smmu_domain->devices_lock, flags);
master->domain = NULL;
+ master->ats_enabled = false;
arm_smmu_install_ste_for_dev(master);
-
- arm_smmu_disable_ats(master);
}
static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
@@ -1958,17 +2428,20 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
master->domain = smmu_domain;
- spin_lock_irqsave(&smmu_domain->devices_lock, flags);
- list_add(&master->domain_head, &smmu_domain->devices);
- spin_unlock_irqrestore(&smmu_domain->devices_lock, flags);
-
if (smmu_domain->stage != ARM_SMMU_DOMAIN_BYPASS)
- arm_smmu_enable_ats(master);
+ master->ats_enabled = arm_smmu_ats_supported(master);
if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1)
arm_smmu_write_ctx_desc(smmu, &smmu_domain->s1_cfg);
arm_smmu_install_ste_for_dev(master);
+
+ spin_lock_irqsave(&smmu_domain->devices_lock, flags);
+ list_add(&master->domain_head, &smmu_domain->devices);
+ spin_unlock_irqrestore(&smmu_domain->devices_lock, flags);
+
+ arm_smmu_enable_ats(master);
+
out_unlock:
mutex_unlock(&smmu_domain->init_mutex);
return ret;
@@ -1985,21 +2458,16 @@ static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova,
return ops->map(ops, iova, paddr, size, prot);
}
-static size_t
-arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size)
+static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
+ size_t size, struct iommu_iotlb_gather *gather)
{
- int ret;
struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
struct io_pgtable_ops *ops = smmu_domain->pgtbl_ops;
if (!ops)
return 0;
- ret = ops->unmap(ops, iova, size);
- if (ret && arm_smmu_atc_inv_domain(smmu_domain, 0, iova, size))
- return 0;
-
- return ret;
+ return ops->unmap(ops, iova, size, gather);
}
static void arm_smmu_flush_iotlb_all(struct iommu_domain *domain)
@@ -2010,12 +2478,13 @@ static void arm_smmu_flush_iotlb_all(struct iommu_domain *domain)
arm_smmu_tlb_inv_context(smmu_domain);
}
-static void arm_smmu_iotlb_sync(struct iommu_domain *domain)
+static void arm_smmu_iotlb_sync(struct iommu_domain *domain,
+ struct iommu_iotlb_gather *gather)
{
- struct arm_smmu_device *smmu = to_smmu_domain(domain)->smmu;
+ struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
- if (smmu)
- arm_smmu_cmdq_issue_sync(smmu);
+ arm_smmu_tlb_inv_range(gather->start, gather->end - gather->start,
+ gather->pgsize, true, smmu_domain);
}
static phys_addr_t
@@ -2286,13 +2755,13 @@ static int arm_smmu_init_one_queue(struct arm_smmu_device *smmu,
size_t qsz;
do {
- qsz = ((1 << q->max_n_shift) * dwords) << 3;
+ qsz = ((1 << q->llq.max_n_shift) * dwords) << 3;
q->base = dmam_alloc_coherent(smmu->dev, qsz, &q->base_dma,
GFP_KERNEL);
if (q->base || qsz < PAGE_SIZE)
break;
- q->max_n_shift--;
+ q->llq.max_n_shift--;
} while (1);
if (!q->base) {
@@ -2304,7 +2773,7 @@ static int arm_smmu_init_one_queue(struct arm_smmu_device *smmu,
if (!WARN_ON(q->base_dma & (qsz - 1))) {
dev_info(smmu->dev, "allocated %u entries for %s\n",
- 1 << q->max_n_shift, name);
+ 1 << q->llq.max_n_shift, name);
}
q->prod_reg = arm_smmu_page1_fixup(prod_off, smmu);
@@ -2313,24 +2782,55 @@ static int arm_smmu_init_one_queue(struct arm_smmu_device *smmu,
q->q_base = Q_BASE_RWA;
q->q_base |= q->base_dma & Q_BASE_ADDR_MASK;
- q->q_base |= FIELD_PREP(Q_BASE_LOG2SIZE, q->max_n_shift);
+ q->q_base |= FIELD_PREP(Q_BASE_LOG2SIZE, q->llq.max_n_shift);
- q->prod = q->cons = 0;
+ q->llq.prod = q->llq.cons = 0;
return 0;
}
+static void arm_smmu_cmdq_free_bitmap(void *data)
+{
+ unsigned long *bitmap = data;
+ bitmap_free(bitmap);
+}
+
+static int arm_smmu_cmdq_init(struct arm_smmu_device *smmu)
+{
+ int ret = 0;
+ struct arm_smmu_cmdq *cmdq = &smmu->cmdq;
+ unsigned int nents = 1 << cmdq->q.llq.max_n_shift;
+ atomic_long_t *bitmap;
+
+ atomic_set(&cmdq->owner_prod, 0);
+ atomic_set(&cmdq->lock, 0);
+
+ bitmap = (atomic_long_t *)bitmap_zalloc(nents, GFP_KERNEL);
+ if (!bitmap) {
+ dev_err(smmu->dev, "failed to allocate cmdq bitmap\n");
+ ret = -ENOMEM;
+ } else {
+ cmdq->valid_map = bitmap;
+ devm_add_action(smmu->dev, arm_smmu_cmdq_free_bitmap, bitmap);
+ }
+
+ return ret;
+}
+
static int arm_smmu_init_queues(struct arm_smmu_device *smmu)
{
int ret;
/* cmdq */
- spin_lock_init(&smmu->cmdq.lock);
ret = arm_smmu_init_one_queue(smmu, &smmu->cmdq.q, ARM_SMMU_CMDQ_PROD,
ARM_SMMU_CMDQ_CONS, CMDQ_ENT_DWORDS,
"cmdq");
if (ret)
return ret;
+ ret = arm_smmu_cmdq_init(smmu);
+ if (ret)
+ return ret;
+
/* evtq */
ret = arm_smmu_init_one_queue(smmu, &smmu->evtq.q, ARM_SMMU_EVTQ_PROD,
ARM_SMMU_EVTQ_CONS, EVTQ_ENT_DWORDS,
@@ -2708,8 +3208,8 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass)
/* Command queue */
writeq_relaxed(smmu->cmdq.q.q_base, smmu->base + ARM_SMMU_CMDQ_BASE);
- writel_relaxed(smmu->cmdq.q.prod, smmu->base + ARM_SMMU_CMDQ_PROD);
- writel_relaxed(smmu->cmdq.q.cons, smmu->base + ARM_SMMU_CMDQ_CONS);
+ writel_relaxed(smmu->cmdq.q.llq.prod, smmu->base + ARM_SMMU_CMDQ_PROD);
+ writel_relaxed(smmu->cmdq.q.llq.cons, smmu->base + ARM_SMMU_CMDQ_CONS);
enables = CR0_CMDQEN;
ret = arm_smmu_write_reg_sync(smmu, enables, ARM_SMMU_CR0,
@@ -2736,9 +3236,9 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass)
/* Event queue */
writeq_relaxed(smmu->evtq.q.q_base, smmu->base + ARM_SMMU_EVTQ_BASE);
- writel_relaxed(smmu->evtq.q.prod,
+ writel_relaxed(smmu->evtq.q.llq.prod,
arm_smmu_page1_fixup(ARM_SMMU_EVTQ_PROD, smmu));
- writel_relaxed(smmu->evtq.q.cons,
+ writel_relaxed(smmu->evtq.q.llq.cons,
arm_smmu_page1_fixup(ARM_SMMU_EVTQ_CONS, smmu));
enables |= CR0_EVTQEN;
@@ -2753,9 +3253,9 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass)
if (smmu->features & ARM_SMMU_FEAT_PRI) {
writeq_relaxed(smmu->priq.q.q_base,
smmu->base + ARM_SMMU_PRIQ_BASE);
- writel_relaxed(smmu->priq.q.prod,
+ writel_relaxed(smmu->priq.q.llq.prod,
arm_smmu_page1_fixup(ARM_SMMU_PRIQ_PROD, smmu));
- writel_relaxed(smmu->priq.q.cons,
+ writel_relaxed(smmu->priq.q.llq.cons,
arm_smmu_page1_fixup(ARM_SMMU_PRIQ_CONS, smmu));
enables |= CR0_PRIQEN;
@@ -2909,18 +3409,24 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
}
/* Queue sizes, capped to ensure natural alignment */
- smmu->cmdq.q.max_n_shift = min_t(u32, CMDQ_MAX_SZ_SHIFT,
- FIELD_GET(IDR1_CMDQS, reg));
- if (!smmu->cmdq.q.max_n_shift) {
- /* Odd alignment restrictions on the base, so ignore for now */
- dev_err(smmu->dev, "unit-length command queue not supported\n");
+ smmu->cmdq.q.llq.max_n_shift = min_t(u32, CMDQ_MAX_SZ_SHIFT,
+ FIELD_GET(IDR1_CMDQS, reg));
+ if (smmu->cmdq.q.llq.max_n_shift <= ilog2(CMDQ_BATCH_ENTRIES)) {
+ /*
+ * We don't support splitting up batches, so one batch of
+ * commands plus an extra sync needs to fit inside the command
+ * queue. There's also no way we can handle the weird alignment
+ * restrictions on the base pointer for a unit-length queue.
+ */
+ dev_err(smmu->dev, "command queue size <= %d entries not supported\n",
+ CMDQ_BATCH_ENTRIES);
return -ENXIO;
}
- smmu->evtq.q.max_n_shift = min_t(u32, EVTQ_MAX_SZ_SHIFT,
- FIELD_GET(IDR1_EVTQS, reg));
- smmu->priq.q.max_n_shift = min_t(u32, PRIQ_MAX_SZ_SHIFT,
- FIELD_GET(IDR1_PRIQS, reg));
+ smmu->evtq.q.llq.max_n_shift = min_t(u32, EVTQ_MAX_SZ_SHIFT,
+ FIELD_GET(IDR1_EVTQS, reg));
+ smmu->priq.q.llq.max_n_shift = min_t(u32, PRIQ_MAX_SZ_SHIFT,
+ FIELD_GET(IDR1_PRIQS, reg));
/* SID/SSID sizes */
smmu->ssid_bits = FIELD_GET(IDR1_SSIDSIZE, reg);
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 64977c131ee6..5b93c79371e9 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -19,16 +19,13 @@
#include <linux/acpi.h>
#include <linux/acpi_iort.h>
-#include <linux/atomic.h>
+#include <linux/bitfield.h>
#include <linux/delay.h>
#include <linux/dma-iommu.h>
#include <linux/dma-mapping.h>
#include <linux/err.h>
#include <linux/interrupt.h>
#include <linux/io.h>
-#include <linux/io-64-nonatomic-hi-lo.h>
-#include <linux/io-pgtable.h>
-#include <linux/iommu.h>
#include <linux/iopoll.h>
#include <linux/init.h>
#include <linux/moduleparam.h>
@@ -40,12 +37,11 @@
#include <linux/platform_device.h>
#include <linux/pm_runtime.h>
#include <linux/slab.h>
-#include <linux/spinlock.h>
#include <linux/amba/bus.h>
#include <linux/fsl/mc.h>
-#include "arm-smmu-regs.h"
+#include "arm-smmu.h"
/*
* Apparently, some Qualcomm arm64 platforms which appear to expose their SMMU
@@ -56,46 +52,9 @@
*/
#define QCOM_DUMMY_VAL -1
-#define ARM_MMU500_ACTLR_CPRE (1 << 1)
-
-#define ARM_MMU500_ACR_CACHE_LOCK (1 << 26)
-#define ARM_MMU500_ACR_S2CRB_TLBEN (1 << 10)
-#define ARM_MMU500_ACR_SMTNMB_TLBEN (1 << 8)
-
#define TLB_LOOP_TIMEOUT 1000000 /* 1s! */
#define TLB_SPIN_COUNT 10
-/* Maximum number of context banks per SMMU */
-#define ARM_SMMU_MAX_CBS 128
-
-/* SMMU global address space */
-#define ARM_SMMU_GR0(smmu) ((smmu)->base)
-#define ARM_SMMU_GR1(smmu) ((smmu)->base + (1 << (smmu)->pgshift))
-
-/*
- * SMMU global address space with conditional offset to access secure
- * aliases of non-secure registers (e.g. nsCR0: 0x400, nsGFSR: 0x448,
- * nsGFSYNR0: 0x450)
- */
-#define ARM_SMMU_GR0_NS(smmu) \
- ((smmu)->base + \
- ((smmu->options & ARM_SMMU_OPT_SECURE_CFG_ACCESS) \
- ? 0x400 : 0))
-
-/*
- * Some 64-bit registers only make sense to write atomically, but in such
- * cases all the data relevant to AArch32 formats lies within the lower word,
- * therefore this actually makes more sense than it might first appear.
- */
-#ifdef CONFIG_64BIT
-#define smmu_write_atomic_lq writeq_relaxed
-#else
-#define smmu_write_atomic_lq writel_relaxed
-#endif
-
-/* Translation context bank */
-#define ARM_SMMU_CB(smmu, n) ((smmu)->cb_base + ((n) << (smmu)->pgshift))
-
#define MSI_IOVA_BASE 0x8000000
#define MSI_IOVA_LENGTH 0x100000
@@ -113,19 +72,6 @@ module_param(disable_bypass, bool, S_IRUGO);
MODULE_PARM_DESC(disable_bypass,
"Disable bypass streams such that incoming transactions from devices that are not attached to an iommu domain will report an abort back to the device and will not be allowed to pass through the SMMU.");
-enum arm_smmu_arch_version {
- ARM_SMMU_V1,
- ARM_SMMU_V1_64K,
- ARM_SMMU_V2,
-};
-
-enum arm_smmu_implementation {
- GENERIC_SMMU,
- ARM_MMU500,
- CAVIUM_SMMUV2,
- QCOM_SMMUV2,
-};
-
struct arm_smmu_s2cr {
struct iommu_group *group;
int count;
@@ -163,117 +109,8 @@ struct arm_smmu_master_cfg {
#define for_each_cfg_sme(fw, i, idx) \
for (i = 0; idx = fwspec_smendx(fw, i), i < fw->num_ids; ++i)
-struct arm_smmu_device {
- struct device *dev;
-
- void __iomem *base;
- void __iomem *cb_base;
- unsigned long pgshift;
-
-#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)
-#define ARM_SMMU_FEAT_TRANS_OPS (1 << 5)
-#define ARM_SMMU_FEAT_VMID16 (1 << 6)
-#define ARM_SMMU_FEAT_FMT_AARCH64_4K (1 << 7)
-#define ARM_SMMU_FEAT_FMT_AARCH64_16K (1 << 8)
-#define ARM_SMMU_FEAT_FMT_AARCH64_64K (1 << 9)
-#define ARM_SMMU_FEAT_FMT_AARCH32_L (1 << 10)
-#define ARM_SMMU_FEAT_FMT_AARCH32_S (1 << 11)
-#define ARM_SMMU_FEAT_EXIDS (1 << 12)
- u32 features;
-
-#define ARM_SMMU_OPT_SECURE_CFG_ACCESS (1 << 0)
- u32 options;
- enum arm_smmu_arch_version version;
- enum arm_smmu_implementation model;
-
- u32 num_context_banks;
- u32 num_s2_context_banks;
- DECLARE_BITMAP(context_map, ARM_SMMU_MAX_CBS);
- struct arm_smmu_cb *cbs;
- atomic_t irptndx;
-
- u32 num_mapping_groups;
- u16 streamid_mask;
- u16 smr_mask_mask;
- struct arm_smmu_smr *smrs;
- struct arm_smmu_s2cr *s2crs;
- struct mutex stream_map_mutex;
-
- unsigned long va_size;
- unsigned long ipa_size;
- unsigned long pa_size;
- unsigned long pgsize_bitmap;
-
- u32 num_global_irqs;
- u32 num_context_irqs;
- unsigned int *irqs;
- struct clk_bulk_data *clks;
- int num_clks;
-
- u32 cavium_id_base; /* Specific to Cavium */
-
- spinlock_t global_sync_lock;
-
- /* IOMMU core code handle */
- struct iommu_device iommu;
-};
-
-enum arm_smmu_context_fmt {
- ARM_SMMU_CTX_FMT_NONE,
- ARM_SMMU_CTX_FMT_AARCH64,
- ARM_SMMU_CTX_FMT_AARCH32_L,
- ARM_SMMU_CTX_FMT_AARCH32_S,
-};
-
-struct arm_smmu_cfg {
- u8 cbndx;
- u8 irptndx;
- union {
- u16 asid;
- u16 vmid;
- };
- u32 cbar;
- enum arm_smmu_context_fmt fmt;
-};
-#define INVALID_IRPTNDX 0xff
-
-enum arm_smmu_domain_stage {
- ARM_SMMU_DOMAIN_S1 = 0,
- ARM_SMMU_DOMAIN_S2,
- ARM_SMMU_DOMAIN_NESTED,
- ARM_SMMU_DOMAIN_BYPASS,
-};
-
-struct arm_smmu_domain {
- struct arm_smmu_device *smmu;
- struct io_pgtable_ops *pgtbl_ops;
- const struct iommu_gather_ops *tlb_ops;
- struct arm_smmu_cfg cfg;
- enum arm_smmu_domain_stage stage;
- bool non_strict;
- struct mutex init_mutex; /* Protects smmu pointer */
- spinlock_t cb_lock; /* Serialises ATS1* ops and TLB syncs */
- struct iommu_domain domain;
-};
-
-struct arm_smmu_option_prop {
- u32 opt;
- const char *prop;
-};
-
-static atomic_t cavium_smmu_context_count = ATOMIC_INIT(0);
-
static bool using_legacy_binding, using_generic_binding;
-static struct arm_smmu_option_prop arm_smmu_options[] = {
- { ARM_SMMU_OPT_SECURE_CFG_ACCESS, "calxeda,smmu-secure-config-access" },
- { 0, NULL},
-};
-
static inline int arm_smmu_rpm_get(struct arm_smmu_device *smmu)
{
if (pm_runtime_enabled(smmu->dev))
@@ -293,20 +130,6 @@ static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
return container_of(dom, struct arm_smmu_domain, domain);
}
-static void parse_driver_options(struct arm_smmu_device *smmu)
-{
- int i = 0;
-
- do {
- if (of_property_read_bool(smmu->dev->of_node,
- arm_smmu_options[i].prop)) {
- smmu->options |= arm_smmu_options[i].opt;
- dev_notice(smmu->dev, "option %s\n",
- arm_smmu_options[i].prop);
- }
- } while (arm_smmu_options[++i].opt);
-}
-
static struct device_node *dev_get_dev_node(struct device *dev)
{
if (dev_is_pci(dev)) {
@@ -415,15 +238,17 @@ static void __arm_smmu_free_bitmap(unsigned long *map, int idx)
}
/* Wait for any pending TLB invalidations to complete */
-static void __arm_smmu_tlb_sync(struct arm_smmu_device *smmu,
- void __iomem *sync, void __iomem *status)
+static void __arm_smmu_tlb_sync(struct arm_smmu_device *smmu, int page,
+ int sync, int status)
{
unsigned int spin_cnt, delay;
+ u32 reg;
- writel_relaxed(QCOM_DUMMY_VAL, sync);
+ arm_smmu_writel(smmu, page, sync, QCOM_DUMMY_VAL);
for (delay = 1; delay < TLB_LOOP_TIMEOUT; delay *= 2) {
for (spin_cnt = TLB_SPIN_COUNT; spin_cnt > 0; spin_cnt--) {
- if (!(readl_relaxed(status) & sTLBGSTATUS_GSACTIVE))
+ reg = arm_smmu_readl(smmu, page, status);
+ if (!(reg & sTLBGSTATUS_GSACTIVE))
return;
cpu_relax();
}
@@ -435,12 +260,11 @@ static void __arm_smmu_tlb_sync(struct arm_smmu_device *smmu,
static void arm_smmu_tlb_sync_global(struct arm_smmu_device *smmu)
{
- void __iomem *base = ARM_SMMU_GR0(smmu);
unsigned long flags;
spin_lock_irqsave(&smmu->global_sync_lock, flags);
- __arm_smmu_tlb_sync(smmu, base + ARM_SMMU_GR0_sTLBGSYNC,
- base + ARM_SMMU_GR0_sTLBGSTATUS);
+ __arm_smmu_tlb_sync(smmu, ARM_SMMU_GR0, ARM_SMMU_GR0_sTLBGSYNC,
+ ARM_SMMU_GR0_sTLBGSTATUS);
spin_unlock_irqrestore(&smmu->global_sync_lock, flags);
}
@@ -448,12 +272,11 @@ static void arm_smmu_tlb_sync_context(void *cookie)
{
struct arm_smmu_domain *smmu_domain = cookie;
struct arm_smmu_device *smmu = smmu_domain->smmu;
- void __iomem *base = ARM_SMMU_CB(smmu, smmu_domain->cfg.cbndx);
unsigned long flags;
spin_lock_irqsave(&smmu_domain->cb_lock, flags);
- __arm_smmu_tlb_sync(smmu, base + ARM_SMMU_CB_TLBSYNC,
- base + ARM_SMMU_CB_TLBSTATUS);
+ __arm_smmu_tlb_sync(smmu, ARM_SMMU_CB(smmu, smmu_domain->cfg.cbndx),
+ ARM_SMMU_CB_TLBSYNC, ARM_SMMU_CB_TLBSTATUS);
spin_unlock_irqrestore(&smmu_domain->cb_lock, flags);
}
@@ -467,14 +290,13 @@ static void arm_smmu_tlb_sync_vmid(void *cookie)
static void arm_smmu_tlb_inv_context_s1(void *cookie)
{
struct arm_smmu_domain *smmu_domain = cookie;
- struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
- void __iomem *base = ARM_SMMU_CB(smmu_domain->smmu, cfg->cbndx);
-
/*
- * NOTE: this is not a relaxed write; it needs to guarantee that PTEs
- * cleared by the current CPU are visible to the SMMU before the TLBI.
+ * The TLBI write may be relaxed, so ensure that PTEs cleared by the
+ * current CPU are visible beforehand.
*/
- writel(cfg->asid, base + ARM_SMMU_CB_S1_TLBIASID);
+ wmb();
+ arm_smmu_cb_write(smmu_domain->smmu, smmu_domain->cfg.cbndx,
+ ARM_SMMU_CB_S1_TLBIASID, smmu_domain->cfg.asid);
arm_smmu_tlb_sync_context(cookie);
}
@@ -482,87 +304,143 @@ static void arm_smmu_tlb_inv_context_s2(void *cookie)
{
struct arm_smmu_domain *smmu_domain = cookie;
struct arm_smmu_device *smmu = smmu_domain->smmu;
- void __iomem *base = ARM_SMMU_GR0(smmu);
- /* NOTE: see above */
- writel(smmu_domain->cfg.vmid, base + ARM_SMMU_GR0_TLBIVMID);
+ /* See above */
+ wmb();
+ arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_TLBIVMID, smmu_domain->cfg.vmid);
arm_smmu_tlb_sync_global(smmu);
}
-static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size,
- size_t granule, bool leaf, void *cookie)
+static void arm_smmu_tlb_inv_range_s1(unsigned long iova, size_t size,
+ size_t granule, bool leaf, void *cookie)
{
struct arm_smmu_domain *smmu_domain = cookie;
+ struct arm_smmu_device *smmu = smmu_domain->smmu;
struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
- bool stage1 = cfg->cbar != CBAR_TYPE_S2_TRANS;
- void __iomem *reg = ARM_SMMU_CB(smmu_domain->smmu, cfg->cbndx);
+ int reg, idx = cfg->cbndx;
- if (smmu_domain->smmu->features & ARM_SMMU_FEAT_COHERENT_WALK)
+ if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK)
wmb();
- if (stage1) {
- reg += leaf ? ARM_SMMU_CB_S1_TLBIVAL : ARM_SMMU_CB_S1_TLBIVA;
-
- if (cfg->fmt != ARM_SMMU_CTX_FMT_AARCH64) {
- iova &= ~12UL;
- iova |= cfg->asid;
- do {
- writel_relaxed(iova, reg);
- iova += granule;
- } while (size -= granule);
- } else {
- iova >>= 12;
- iova |= (u64)cfg->asid << 48;
- do {
- writeq_relaxed(iova, reg);
- iova += granule >> 12;
- } while (size -= granule);
- }
+ reg = leaf ? ARM_SMMU_CB_S1_TLBIVAL : ARM_SMMU_CB_S1_TLBIVA;
+
+ if (cfg->fmt != ARM_SMMU_CTX_FMT_AARCH64) {
+ iova = (iova >> 12) << 12;
+ iova |= cfg->asid;
+ do {
+ arm_smmu_cb_write(smmu, idx, reg, iova);
+ iova += granule;
+ } while (size -= granule);
} else {
- reg += leaf ? ARM_SMMU_CB_S2_TLBIIPAS2L :
- ARM_SMMU_CB_S2_TLBIIPAS2;
iova >>= 12;
+ iova |= (u64)cfg->asid << 48;
do {
- smmu_write_atomic_lq(iova, reg);
+ arm_smmu_cb_writeq(smmu, idx, reg, iova);
iova += granule >> 12;
} while (size -= granule);
}
}
+static void arm_smmu_tlb_inv_range_s2(unsigned long iova, size_t size,
+ size_t granule, bool leaf, void *cookie)
+{
+ struct arm_smmu_domain *smmu_domain = cookie;
+ struct arm_smmu_device *smmu = smmu_domain->smmu;
+ int reg, idx = smmu_domain->cfg.cbndx;
+
+ if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK)
+ wmb();
+
+ reg = leaf ? ARM_SMMU_CB_S2_TLBIIPAS2L : ARM_SMMU_CB_S2_TLBIIPAS2;
+ iova >>= 12;
+ do {
+ if (smmu_domain->cfg.fmt == ARM_SMMU_CTX_FMT_AARCH64)
+ arm_smmu_cb_writeq(smmu, idx, reg, iova);
+ else
+ arm_smmu_cb_write(smmu, idx, reg, iova);
+ iova += granule >> 12;
+ } while (size -= granule);
+}
+
/*
* On MMU-401 at least, the cost of firing off multiple TLBIVMIDs appears
* almost negligible, but the benefit of getting the first one in as far ahead
* of the sync as possible is significant, hence we don't just make this a
- * no-op and set .tlb_sync to arm_smmu_inv_context_s2() as you might think.
+ * no-op and set .tlb_sync to arm_smmu_tlb_inv_context_s2() as you might think.
*/
static void arm_smmu_tlb_inv_vmid_nosync(unsigned long iova, size_t size,
size_t granule, bool leaf, void *cookie)
{
struct arm_smmu_domain *smmu_domain = cookie;
- void __iomem *base = ARM_SMMU_GR0(smmu_domain->smmu);
+ struct arm_smmu_device *smmu = smmu_domain->smmu;
- if (smmu_domain->smmu->features & ARM_SMMU_FEAT_COHERENT_WALK)
+ if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK)
wmb();
- writel_relaxed(smmu_domain->cfg.vmid, base + ARM_SMMU_GR0_TLBIVMID);
+ arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_TLBIVMID, smmu_domain->cfg.vmid);
+}
+
+static void arm_smmu_tlb_inv_walk(unsigned long iova, size_t size,
+ size_t granule, void *cookie)
+{
+ struct arm_smmu_domain *smmu_domain = cookie;
+ const struct arm_smmu_flush_ops *ops = smmu_domain->flush_ops;
+
+ ops->tlb_inv_range(iova, size, granule, false, cookie);
+ ops->tlb_sync(cookie);
+}
+
+static void arm_smmu_tlb_inv_leaf(unsigned long iova, size_t size,
+ size_t granule, void *cookie)
+{
+ struct arm_smmu_domain *smmu_domain = cookie;
+ const struct arm_smmu_flush_ops *ops = smmu_domain->flush_ops;
+
+ ops->tlb_inv_range(iova, size, granule, true, cookie);
+ ops->tlb_sync(cookie);
+}
+
+static void arm_smmu_tlb_add_page(struct iommu_iotlb_gather *gather,
+ unsigned long iova, size_t granule,
+ void *cookie)
+{
+ struct arm_smmu_domain *smmu_domain = cookie;
+ const struct arm_smmu_flush_ops *ops = smmu_domain->flush_ops;
+
+ ops->tlb_inv_range(iova, granule, granule, true, cookie);
}
-static const struct iommu_gather_ops arm_smmu_s1_tlb_ops = {
- .tlb_flush_all = arm_smmu_tlb_inv_context_s1,
- .tlb_add_flush = arm_smmu_tlb_inv_range_nosync,
- .tlb_sync = arm_smmu_tlb_sync_context,
+static const struct arm_smmu_flush_ops arm_smmu_s1_tlb_ops = {
+ .tlb = {
+ .tlb_flush_all = arm_smmu_tlb_inv_context_s1,
+ .tlb_flush_walk = arm_smmu_tlb_inv_walk,
+ .tlb_flush_leaf = arm_smmu_tlb_inv_leaf,
+ .tlb_add_page = arm_smmu_tlb_add_page,
+ },
+ .tlb_inv_range = arm_smmu_tlb_inv_range_s1,
+ .tlb_sync = arm_smmu_tlb_sync_context,
};
-static const struct iommu_gather_ops arm_smmu_s2_tlb_ops_v2 = {
- .tlb_flush_all = arm_smmu_tlb_inv_context_s2,
- .tlb_add_flush = arm_smmu_tlb_inv_range_nosync,
- .tlb_sync = arm_smmu_tlb_sync_context,
+static const struct arm_smmu_flush_ops arm_smmu_s2_tlb_ops_v2 = {
+ .tlb = {
+ .tlb_flush_all = arm_smmu_tlb_inv_context_s2,
+ .tlb_flush_walk = arm_smmu_tlb_inv_walk,
+ .tlb_flush_leaf = arm_smmu_tlb_inv_leaf,
+ .tlb_add_page = arm_smmu_tlb_add_page,
+ },
+ .tlb_inv_range = arm_smmu_tlb_inv_range_s2,
+ .tlb_sync = arm_smmu_tlb_sync_context,
};
-static const struct iommu_gather_ops arm_smmu_s2_tlb_ops_v1 = {
- .tlb_flush_all = arm_smmu_tlb_inv_context_s2,
- .tlb_add_flush = arm_smmu_tlb_inv_vmid_nosync,
- .tlb_sync = arm_smmu_tlb_sync_vmid,
+static const struct arm_smmu_flush_ops arm_smmu_s2_tlb_ops_v1 = {
+ .tlb = {
+ .tlb_flush_all = arm_smmu_tlb_inv_context_s2,
+ .tlb_flush_walk = arm_smmu_tlb_inv_walk,
+ .tlb_flush_leaf = arm_smmu_tlb_inv_leaf,
+ .tlb_add_page = arm_smmu_tlb_add_page,
+ },
+ .tlb_inv_range = arm_smmu_tlb_inv_vmid_nosync,
+ .tlb_sync = arm_smmu_tlb_sync_vmid,
};
static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
@@ -571,26 +449,22 @@ static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
unsigned long iova;
struct iommu_domain *domain = dev;
struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
- struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
struct arm_smmu_device *smmu = smmu_domain->smmu;
- void __iomem *gr1_base = ARM_SMMU_GR1(smmu);
- void __iomem *cb_base;
-
- cb_base = ARM_SMMU_CB(smmu, cfg->cbndx);
- fsr = readl_relaxed(cb_base + ARM_SMMU_CB_FSR);
+ int idx = smmu_domain->cfg.cbndx;
+ fsr = arm_smmu_cb_read(smmu, idx, ARM_SMMU_CB_FSR);
if (!(fsr & FSR_FAULT))
return IRQ_NONE;
- fsynr = readl_relaxed(cb_base + ARM_SMMU_CB_FSYNR0);
- iova = readq_relaxed(cb_base + ARM_SMMU_CB_FAR);
- cbfrsynra = readl_relaxed(gr1_base + ARM_SMMU_GR1_CBFRSYNRA(cfg->cbndx));
+ fsynr = arm_smmu_cb_read(smmu, idx, ARM_SMMU_CB_FSYNR0);
+ iova = arm_smmu_cb_readq(smmu, idx, ARM_SMMU_CB_FAR);
+ cbfrsynra = arm_smmu_gr1_read(smmu, ARM_SMMU_GR1_CBFRSYNRA(idx));
dev_err_ratelimited(smmu->dev,
"Unhandled context fault: fsr=0x%x, iova=0x%08lx, fsynr=0x%x, cbfrsynra=0x%x, cb=%d\n",
- fsr, iova, fsynr, cbfrsynra, cfg->cbndx);
+ fsr, iova, fsynr, cbfrsynra, idx);
- writel(fsr, cb_base + ARM_SMMU_CB_FSR);
+ arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_FSR, fsr);
return IRQ_HANDLED;
}
@@ -598,12 +472,11 @@ 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_NS(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);
+ gfsr = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sGFSR);
+ gfsynr0 = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sGFSYNR0);
+ gfsynr1 = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sGFSYNR1);
+ gfsynr2 = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sGFSYNR2);
if (!gfsr)
return IRQ_NONE;
@@ -614,7 +487,7 @@ static irqreturn_t arm_smmu_global_fault(int irq, void *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);
+ arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sGFSR, gfsr);
return IRQ_HANDLED;
}
@@ -627,16 +500,16 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain,
cb->cfg = cfg;
- /* TTBCR */
+ /* TCR */
if (stage1) {
if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH32_S) {
cb->tcr[0] = pgtbl_cfg->arm_v7s_cfg.tcr;
} else {
cb->tcr[0] = pgtbl_cfg->arm_lpae_s1_cfg.tcr;
cb->tcr[1] = pgtbl_cfg->arm_lpae_s1_cfg.tcr >> 32;
- cb->tcr[1] |= TTBCR2_SEP_UPSTREAM;
+ cb->tcr[1] |= FIELD_PREP(TCR2_SEP, TCR2_SEP_UPSTREAM);
if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH64)
- cb->tcr[1] |= TTBCR2_AS;
+ cb->tcr[1] |= TCR2_AS;
}
} else {
cb->tcr[0] = pgtbl_cfg->arm_lpae_s2_cfg.vtcr;
@@ -649,9 +522,9 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain,
cb->ttbr[1] = pgtbl_cfg->arm_v7s_cfg.ttbr[1];
} else {
cb->ttbr[0] = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0];
- cb->ttbr[0] |= (u64)cfg->asid << TTBRn_ASID_SHIFT;
+ cb->ttbr[0] |= FIELD_PREP(TTBRn_ASID, cfg->asid);
cb->ttbr[1] = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[1];
- cb->ttbr[1] |= (u64)cfg->asid << TTBRn_ASID_SHIFT;
+ cb->ttbr[1] |= FIELD_PREP(TTBRn_ASID, cfg->asid);
}
} else {
cb->ttbr[0] = pgtbl_cfg->arm_lpae_s2_cfg.vttbr;
@@ -675,74 +548,71 @@ static void arm_smmu_write_context_bank(struct arm_smmu_device *smmu, int idx)
bool stage1;
struct arm_smmu_cb *cb = &smmu->cbs[idx];
struct arm_smmu_cfg *cfg = cb->cfg;
- void __iomem *cb_base, *gr1_base;
-
- cb_base = ARM_SMMU_CB(smmu, idx);
/* Unassigned context banks only need disabling */
if (!cfg) {
- writel_relaxed(0, cb_base + ARM_SMMU_CB_SCTLR);
+ arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_SCTLR, 0);
return;
}
- gr1_base = ARM_SMMU_GR1(smmu);
stage1 = cfg->cbar != CBAR_TYPE_S2_TRANS;
/* CBA2R */
if (smmu->version > ARM_SMMU_V1) {
if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH64)
- reg = CBA2R_RW64_64BIT;
+ reg = CBA2R_VA64;
else
- reg = CBA2R_RW64_32BIT;
+ reg = 0;
/* 16-bit VMIDs live in CBA2R */
if (smmu->features & ARM_SMMU_FEAT_VMID16)
- reg |= cfg->vmid << CBA2R_VMID_SHIFT;
+ reg |= FIELD_PREP(CBA2R_VMID16, cfg->vmid);
- writel_relaxed(reg, gr1_base + ARM_SMMU_GR1_CBA2R(idx));
+ arm_smmu_gr1_write(smmu, ARM_SMMU_GR1_CBA2R(idx), reg);
}
/* CBAR */
- reg = cfg->cbar;
+ reg = FIELD_PREP(CBAR_TYPE, cfg->cbar);
if (smmu->version < ARM_SMMU_V2)
- reg |= cfg->irptndx << CBAR_IRPTNDX_SHIFT;
+ reg |= FIELD_PREP(CBAR_IRPTNDX, cfg->irptndx);
/*
* Use the weakest shareability/memory types, so they are
* overridden by the ttbcr/pte.
*/
if (stage1) {
- reg |= (CBAR_S1_BPSHCFG_NSH << CBAR_S1_BPSHCFG_SHIFT) |
- (CBAR_S1_MEMATTR_WB << CBAR_S1_MEMATTR_SHIFT);
+ reg |= FIELD_PREP(CBAR_S1_BPSHCFG, CBAR_S1_BPSHCFG_NSH) |
+ FIELD_PREP(CBAR_S1_MEMATTR, CBAR_S1_MEMATTR_WB);
} else if (!(smmu->features & ARM_SMMU_FEAT_VMID16)) {
/* 8-bit VMIDs live in CBAR */
- reg |= cfg->vmid << CBAR_VMID_SHIFT;
+ reg |= FIELD_PREP(CBAR_VMID, cfg->vmid);
}
- writel_relaxed(reg, gr1_base + ARM_SMMU_GR1_CBAR(idx));
+ arm_smmu_gr1_write(smmu, ARM_SMMU_GR1_CBAR(idx), reg);
/*
- * TTBCR
+ * TCR
* We must write this before the TTBRs, since it determines the
* access behaviour of some fields (in particular, ASID[15:8]).
*/
if (stage1 && smmu->version > ARM_SMMU_V1)
- writel_relaxed(cb->tcr[1], cb_base + ARM_SMMU_CB_TTBCR2);
- writel_relaxed(cb->tcr[0], cb_base + ARM_SMMU_CB_TTBCR);
+ arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_TCR2, cb->tcr[1]);
+ arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_TCR, cb->tcr[0]);
/* TTBRs */
if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH32_S) {
- writel_relaxed(cfg->asid, cb_base + ARM_SMMU_CB_CONTEXTIDR);
- writel_relaxed(cb->ttbr[0], cb_base + ARM_SMMU_CB_TTBR0);
- writel_relaxed(cb->ttbr[1], cb_base + ARM_SMMU_CB_TTBR1);
+ arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_CONTEXTIDR, cfg->asid);
+ arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_TTBR0, cb->ttbr[0]);
+ arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_TTBR1, cb->ttbr[1]);
} else {
- writeq_relaxed(cb->ttbr[0], cb_base + ARM_SMMU_CB_TTBR0);
+ arm_smmu_cb_writeq(smmu, idx, ARM_SMMU_CB_TTBR0, cb->ttbr[0]);
if (stage1)
- writeq_relaxed(cb->ttbr[1], cb_base + ARM_SMMU_CB_TTBR1);
+ arm_smmu_cb_writeq(smmu, idx, ARM_SMMU_CB_TTBR1,
+ cb->ttbr[1]);
}
/* MAIRs (stage-1 only) */
if (stage1) {
- writel_relaxed(cb->mair[0], cb_base + ARM_SMMU_CB_S1_MAIR0);
- writel_relaxed(cb->mair[1], cb_base + ARM_SMMU_CB_S1_MAIR1);
+ arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_S1_MAIR0, cb->mair[0]);
+ arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_S1_MAIR1, cb->mair[1]);
}
/* SCTLR */
@@ -752,7 +622,7 @@ static void arm_smmu_write_context_bank(struct arm_smmu_device *smmu, int idx)
if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
reg |= SCTLR_E;
- writel_relaxed(reg, cb_base + ARM_SMMU_CB_SCTLR);
+ arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_SCTLR, reg);
}
static int arm_smmu_init_domain_context(struct iommu_domain *domain,
@@ -842,7 +712,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
ias = min(ias, 32UL);
oas = min(oas, 32UL);
}
- smmu_domain->tlb_ops = &arm_smmu_s1_tlb_ops;
+ smmu_domain->flush_ops = &arm_smmu_s1_tlb_ops;
break;
case ARM_SMMU_DOMAIN_NESTED:
/*
@@ -862,9 +732,9 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
oas = min(oas, 40UL);
}
if (smmu->version == ARM_SMMU_V2)
- smmu_domain->tlb_ops = &arm_smmu_s2_tlb_ops_v2;
+ smmu_domain->flush_ops = &arm_smmu_s2_tlb_ops_v2;
else
- smmu_domain->tlb_ops = &arm_smmu_s2_tlb_ops_v1;
+ smmu_domain->flush_ops = &arm_smmu_s2_tlb_ops_v1;
break;
default:
ret = -EINVAL;
@@ -884,23 +754,29 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
}
if (smmu_domain->stage == ARM_SMMU_DOMAIN_S2)
- cfg->vmid = cfg->cbndx + 1 + smmu->cavium_id_base;
+ cfg->vmid = cfg->cbndx + 1;
else
- cfg->asid = cfg->cbndx + smmu->cavium_id_base;
+ cfg->asid = cfg->cbndx;
+
+ smmu_domain->smmu = smmu;
+ if (smmu->impl && smmu->impl->init_context) {
+ ret = smmu->impl->init_context(smmu_domain);
+ if (ret)
+ goto out_unlock;
+ }
pgtbl_cfg = (struct io_pgtable_cfg) {
.pgsize_bitmap = smmu->pgsize_bitmap,
.ias = ias,
.oas = oas,
.coherent_walk = smmu->features & ARM_SMMU_FEAT_COHERENT_WALK,
- .tlb = smmu_domain->tlb_ops,
+ .tlb = &smmu_domain->flush_ops->tlb,
.iommu_dev = smmu->dev,
};
if (smmu_domain->non_strict)
pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_NON_STRICT;
- smmu_domain->smmu = smmu;
pgtbl_ops = alloc_io_pgtable_ops(fmt, &pgtbl_cfg, smmu_domain);
if (!pgtbl_ops) {
ret = -ENOMEM;
@@ -1019,24 +895,24 @@ static void arm_smmu_domain_free(struct iommu_domain *domain)
static void arm_smmu_write_smr(struct arm_smmu_device *smmu, int idx)
{
struct arm_smmu_smr *smr = smmu->smrs + idx;
- u32 reg = smr->id << SMR_ID_SHIFT | smr->mask << SMR_MASK_SHIFT;
+ u32 reg = FIELD_PREP(SMR_ID, smr->id) | FIELD_PREP(SMR_MASK, smr->mask);
if (!(smmu->features & ARM_SMMU_FEAT_EXIDS) && smr->valid)
reg |= SMR_VALID;
- writel_relaxed(reg, ARM_SMMU_GR0(smmu) + ARM_SMMU_GR0_SMR(idx));
+ arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_SMR(idx), reg);
}
static void arm_smmu_write_s2cr(struct arm_smmu_device *smmu, int idx)
{
struct arm_smmu_s2cr *s2cr = smmu->s2crs + idx;
- u32 reg = (s2cr->type & S2CR_TYPE_MASK) << S2CR_TYPE_SHIFT |
- (s2cr->cbndx & S2CR_CBNDX_MASK) << S2CR_CBNDX_SHIFT |
- (s2cr->privcfg & S2CR_PRIVCFG_MASK) << S2CR_PRIVCFG_SHIFT;
+ u32 reg = FIELD_PREP(S2CR_TYPE, s2cr->type) |
+ FIELD_PREP(S2CR_CBNDX, s2cr->cbndx) |
+ FIELD_PREP(S2CR_PRIVCFG, s2cr->privcfg);
if (smmu->features & ARM_SMMU_FEAT_EXIDS && smmu->smrs &&
smmu->smrs[idx].valid)
reg |= S2CR_EXIDVALID;
- writel_relaxed(reg, ARM_SMMU_GR0(smmu) + ARM_SMMU_GR0_S2CR(idx));
+ arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_S2CR(idx), reg);
}
static void arm_smmu_write_sme(struct arm_smmu_device *smmu, int idx)
@@ -1052,7 +928,6 @@ static void arm_smmu_write_sme(struct arm_smmu_device *smmu, int idx)
*/
static void arm_smmu_test_smr_masks(struct arm_smmu_device *smmu)
{
- void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
u32 smr;
if (!smmu->smrs)
@@ -1063,15 +938,15 @@ static void arm_smmu_test_smr_masks(struct arm_smmu_device *smmu)
* bits are set, so check each one separately. We can reject
* masters later if they try to claim IDs outside these masks.
*/
- smr = smmu->streamid_mask << SMR_ID_SHIFT;
- writel_relaxed(smr, gr0_base + ARM_SMMU_GR0_SMR(0));
- smr = readl_relaxed(gr0_base + ARM_SMMU_GR0_SMR(0));
- smmu->streamid_mask = smr >> SMR_ID_SHIFT;
+ smr = FIELD_PREP(SMR_ID, smmu->streamid_mask);
+ arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_SMR(0), smr);
+ smr = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_SMR(0));
+ smmu->streamid_mask = FIELD_GET(SMR_ID, smr);
- smr = smmu->streamid_mask << SMR_MASK_SHIFT;
- writel_relaxed(smr, gr0_base + ARM_SMMU_GR0_SMR(0));
- smr = readl_relaxed(gr0_base + ARM_SMMU_GR0_SMR(0));
- smmu->smr_mask_mask = smr >> SMR_MASK_SHIFT;
+ smr = FIELD_PREP(SMR_MASK, smmu->streamid_mask);
+ arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_SMR(0), smr);
+ smr = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_SMR(0));
+ smmu->smr_mask_mask = FIELD_GET(SMR_MASK, smr);
}
static int arm_smmu_find_sme(struct arm_smmu_device *smmu, u16 id, u16 mask)
@@ -1140,8 +1015,8 @@ static int arm_smmu_master_alloc_smes(struct device *dev)
mutex_lock(&smmu->stream_map_mutex);
/* Figure out a viable stream map entry allocation */
for_each_cfg_sme(fwspec, i, idx) {
- u16 sid = fwspec->ids[i];
- u16 mask = fwspec->ids[i] >> SMR_MASK_SHIFT;
+ u16 sid = FIELD_GET(SMR_ID, fwspec->ids[i]);
+ u16 mask = FIELD_GET(SMR_MASK, fwspec->ids[i]);
if (idx != INVALID_SMENDX) {
ret = -EEXIST;
@@ -1301,7 +1176,7 @@ static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova,
}
static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
- size_t size)
+ size_t size, struct iommu_iotlb_gather *gather)
{
struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops;
struct arm_smmu_device *smmu = to_smmu_domain(domain)->smmu;
@@ -1311,7 +1186,7 @@ static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
return 0;
arm_smmu_rpm_get(smmu);
- ret = ops->unmap(ops, iova, size);
+ ret = ops->unmap(ops, iova, size, gather);
arm_smmu_rpm_put(smmu);
return ret;
@@ -1322,21 +1197,22 @@ static void arm_smmu_flush_iotlb_all(struct iommu_domain *domain)
struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
struct arm_smmu_device *smmu = smmu_domain->smmu;
- if (smmu_domain->tlb_ops) {
+ if (smmu_domain->flush_ops) {
arm_smmu_rpm_get(smmu);
- smmu_domain->tlb_ops->tlb_flush_all(smmu_domain);
+ smmu_domain->flush_ops->tlb.tlb_flush_all(smmu_domain);
arm_smmu_rpm_put(smmu);
}
}
-static void arm_smmu_iotlb_sync(struct iommu_domain *domain)
+static void arm_smmu_iotlb_sync(struct iommu_domain *domain,
+ struct iommu_iotlb_gather *gather)
{
struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
struct arm_smmu_device *smmu = smmu_domain->smmu;
- if (smmu_domain->tlb_ops) {
+ if (smmu_domain->flush_ops) {
arm_smmu_rpm_get(smmu);
- smmu_domain->tlb_ops->tlb_sync(smmu_domain);
+ smmu_domain->flush_ops->tlb_sync(smmu_domain);
arm_smmu_rpm_put(smmu);
}
}
@@ -1349,28 +1225,25 @@ static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain,
struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
struct io_pgtable_ops *ops= smmu_domain->pgtbl_ops;
struct device *dev = smmu->dev;
- void __iomem *cb_base;
+ void __iomem *reg;
u32 tmp;
u64 phys;
unsigned long va, flags;
- int ret;
+ int ret, idx = cfg->cbndx;
ret = arm_smmu_rpm_get(smmu);
if (ret < 0)
return 0;
- cb_base = ARM_SMMU_CB(smmu, cfg->cbndx);
-
spin_lock_irqsave(&smmu_domain->cb_lock, flags);
- /* ATS1 registers can only be written atomically */
va = iova & ~0xfffUL;
- if (smmu->version == ARM_SMMU_V2)
- smmu_write_atomic_lq(va, cb_base + ARM_SMMU_CB_ATS1PR);
- else /* Register is only 32-bit in v1 */
- writel_relaxed(va, cb_base + ARM_SMMU_CB_ATS1PR);
+ if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH64)
+ arm_smmu_cb_writeq(smmu, idx, ARM_SMMU_CB_ATS1PR, va);
+ else
+ arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_ATS1PR, va);
- if (readl_poll_timeout_atomic(cb_base + ARM_SMMU_CB_ATSR, tmp,
- !(tmp & ATSR_ACTIVE), 5, 50)) {
+ reg = arm_smmu_page(smmu, ARM_SMMU_CB(smmu, idx)) + ARM_SMMU_CB_ATSR;
+ if (readl_poll_timeout_atomic(reg, tmp, !(tmp & ATSR_ACTIVE), 5, 50)) {
spin_unlock_irqrestore(&smmu_domain->cb_lock, flags);
dev_err(dev,
"iova to phys timed out on %pad. Falling back to software table walk.\n",
@@ -1378,7 +1251,7 @@ static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain,
return ops->iova_to_phys(ops, iova);
}
- phys = readq_relaxed(cb_base + ARM_SMMU_CB_PAR);
+ phys = arm_smmu_cb_readq(smmu, idx, ARM_SMMU_CB_PAR);
spin_unlock_irqrestore(&smmu_domain->cb_lock, flags);
if (phys & CB_PAR_F) {
dev_err(dev, "translation fault!\n");
@@ -1466,8 +1339,8 @@ static int arm_smmu_add_device(struct device *dev)
ret = -EINVAL;
for (i = 0; i < fwspec->num_ids; i++) {
- u16 sid = fwspec->ids[i];
- u16 mask = fwspec->ids[i] >> SMR_MASK_SHIFT;
+ u16 sid = FIELD_GET(SMR_ID, fwspec->ids[i]);
+ u16 mask = FIELD_GET(SMR_MASK, fwspec->ids[i]);
if (sid & ~smmu->streamid_mask) {
dev_err(dev, "stream ID 0x%x out of range for SMMU (0x%x)\n",
@@ -1648,12 +1521,12 @@ static int arm_smmu_of_xlate(struct device *dev, struct of_phandle_args *args)
u32 mask, fwid = 0;
if (args->args_count > 0)
- fwid |= (u16)args->args[0];
+ fwid |= FIELD_PREP(SMR_ID, args->args[0]);
if (args->args_count > 1)
- fwid |= (u16)args->args[1] << SMR_MASK_SHIFT;
+ fwid |= FIELD_PREP(SMR_MASK, args->args[1]);
else if (!of_property_read_u32(args->np, "stream-match-mask", &mask))
- fwid |= (u16)mask << SMR_MASK_SHIFT;
+ fwid |= FIELD_PREP(SMR_MASK, mask);
return iommu_fwspec_add_ids(dev, &fwid, 1);
}
@@ -1706,13 +1579,12 @@ static struct iommu_ops arm_smmu_ops = {
static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
{
- void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
int i;
- u32 reg, major;
+ u32 reg;
/* clear global FSR */
- reg = readl_relaxed(ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sGFSR);
- writel(reg, ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sGFSR);
+ reg = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sGFSR);
+ arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sGFSR, reg);
/*
* Reset stream mapping groups: Initial values mark all SMRn as
@@ -1721,47 +1593,17 @@ static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
for (i = 0; i < smmu->num_mapping_groups; ++i)
arm_smmu_write_sme(smmu, i);
- if (smmu->model == ARM_MMU500) {
- /*
- * Before clearing ARM_MMU500_ACTLR_CPRE, need to
- * clear CACHE_LOCK bit of ACR first. And, CACHE_LOCK
- * bit is only present in MMU-500r2 onwards.
- */
- reg = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID7);
- major = (reg >> ID7_MAJOR_SHIFT) & ID7_MAJOR_MASK;
- reg = readl_relaxed(gr0_base + ARM_SMMU_GR0_sACR);
- if (major >= 2)
- reg &= ~ARM_MMU500_ACR_CACHE_LOCK;
- /*
- * Allow unmatched Stream IDs to allocate bypass
- * TLB entries for reduced latency.
- */
- reg |= ARM_MMU500_ACR_SMTNMB_TLBEN | ARM_MMU500_ACR_S2CRB_TLBEN;
- writel_relaxed(reg, gr0_base + ARM_SMMU_GR0_sACR);
- }
-
/* Make sure all context banks are disabled and clear CB_FSR */
for (i = 0; i < smmu->num_context_banks; ++i) {
- void __iomem *cb_base = ARM_SMMU_CB(smmu, i);
-
arm_smmu_write_context_bank(smmu, i);
- writel_relaxed(FSR_FAULT, cb_base + ARM_SMMU_CB_FSR);
- /*
- * Disable MMU-500's not-particularly-beneficial next-page
- * prefetcher for the sake of errata #841119 and #826419.
- */
- if (smmu->model == ARM_MMU500) {
- reg = readl_relaxed(cb_base + ARM_SMMU_CB_ACTLR);
- reg &= ~ARM_MMU500_ACTLR_CPRE;
- writel_relaxed(reg, cb_base + ARM_SMMU_CB_ACTLR);
- }
+ arm_smmu_cb_write(smmu, i, ARM_SMMU_CB_FSR, FSR_FAULT);
}
/* Invalidate the TLB, just in case */
- writel_relaxed(QCOM_DUMMY_VAL, gr0_base + ARM_SMMU_GR0_TLBIALLH);
- writel_relaxed(QCOM_DUMMY_VAL, gr0_base + ARM_SMMU_GR0_TLBIALLNSNH);
+ arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_TLBIALLH, QCOM_DUMMY_VAL);
+ arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_TLBIALLNSNH, QCOM_DUMMY_VAL);
- reg = readl_relaxed(ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sCR0);
+ reg = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sCR0);
/* Enable fault reporting */
reg |= (sCR0_GFRE | sCR0_GFIE | sCR0_GCFGFRE | sCR0_GCFGFIE);
@@ -1780,7 +1622,7 @@ static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
reg &= ~sCR0_FB;
/* Don't upgrade barriers */
- reg &= ~(sCR0_BSU_MASK << sCR0_BSU_SHIFT);
+ reg &= ~(sCR0_BSU);
if (smmu->features & ARM_SMMU_FEAT_VMID16)
reg |= sCR0_VMID16EN;
@@ -1788,9 +1630,12 @@ static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
if (smmu->features & ARM_SMMU_FEAT_EXIDS)
reg |= sCR0_EXIDENABLE;
+ if (smmu->impl && smmu->impl->reset)
+ smmu->impl->reset(smmu);
+
/* Push the button */
arm_smmu_tlb_sync_global(smmu);
- writel(reg, ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sCR0);
+ arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sCR0, reg);
}
static int arm_smmu_id_size_to_bits(int size)
@@ -1814,8 +1659,7 @@ static int arm_smmu_id_size_to_bits(int size)
static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
{
- unsigned long size;
- void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
+ unsigned int size;
u32 id;
bool cttw_reg, cttw_fw = smmu->features & ARM_SMMU_FEAT_COHERENT_WALK;
int i;
@@ -1825,7 +1669,7 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
smmu->version == ARM_SMMU_V2 ? 2 : 1);
/* ID0 */
- id = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID0);
+ id = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_ID0);
/* Restrict available stages based on module parameter */
if (force_stage == 1)
@@ -1879,12 +1723,12 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
smmu->features |= ARM_SMMU_FEAT_EXIDS;
size = 1 << 16;
} else {
- size = 1 << ((id >> ID0_NUMSIDB_SHIFT) & ID0_NUMSIDB_MASK);
+ size = 1 << FIELD_GET(ID0_NUMSIDB, id);
}
smmu->streamid_mask = size - 1;
if (id & ID0_SMS) {
smmu->features |= ARM_SMMU_FEAT_STREAM_MATCH;
- size = (id >> ID0_NUMSMRG_SHIFT) & ID0_NUMSMRG_MASK;
+ size = FIELD_GET(ID0_NUMSMRG, id);
if (size == 0) {
dev_err(smmu->dev,
"stream-matching supported, but no SMRs present!\n");
@@ -1898,7 +1742,7 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
return -ENOMEM;
dev_notice(smmu->dev,
- "\tstream matching with %lu register groups", size);
+ "\tstream matching with %u register groups", size);
}
/* s2cr->type == 0 means translation, so initialise explicitly */
smmu->s2crs = devm_kmalloc_array(smmu->dev, size, sizeof(*smmu->s2crs),
@@ -1919,49 +1763,38 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
}
/* ID1 */
- id = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID1);
+ id = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_ID1);
smmu->pgshift = (id & ID1_PAGESIZE) ? 16 : 12;
/* Check for size mismatch of SMMU address space from mapped region */
- size = 1 << (((id >> ID1_NUMPAGENDXB_SHIFT) & ID1_NUMPAGENDXB_MASK) + 1);
- size <<= smmu->pgshift;
- if (smmu->cb_base != gr0_base + size)
+ size = 1 << (FIELD_GET(ID1_NUMPAGENDXB, id) + 1);
+ if (smmu->numpage != 2 * size << smmu->pgshift)
dev_warn(smmu->dev,
- "SMMU address space size (0x%lx) differs from mapped region size (0x%tx)!\n",
- size * 2, (smmu->cb_base - gr0_base) * 2);
+ "SMMU address space size (0x%x) differs from mapped region size (0x%x)!\n",
+ 2 * size << smmu->pgshift, smmu->numpage);
+ /* Now properly encode NUMPAGE to subsequently derive SMMU_CB_BASE */
+ smmu->numpage = size;
- smmu->num_s2_context_banks = (id >> ID1_NUMS2CB_SHIFT) & ID1_NUMS2CB_MASK;
- smmu->num_context_banks = (id >> ID1_NUMCB_SHIFT) & ID1_NUMCB_MASK;
+ smmu->num_s2_context_banks = FIELD_GET(ID1_NUMS2CB, id);
+ smmu->num_context_banks = FIELD_GET(ID1_NUMCB, id);
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);
- /*
- * Cavium CN88xx erratum #27704.
- * Ensure ASID and VMID allocation is unique across all SMMUs in
- * the system.
- */
- if (smmu->model == CAVIUM_SMMUV2) {
- smmu->cavium_id_base =
- atomic_add_return(smmu->num_context_banks,
- &cavium_smmu_context_count);
- smmu->cavium_id_base -= smmu->num_context_banks;
- dev_notice(smmu->dev, "\tenabling workaround for Cavium erratum 27704\n");
- }
smmu->cbs = devm_kcalloc(smmu->dev, smmu->num_context_banks,
sizeof(*smmu->cbs), GFP_KERNEL);
if (!smmu->cbs)
return -ENOMEM;
/* ID2 */
- id = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID2);
- size = arm_smmu_id_size_to_bits((id >> ID2_IAS_SHIFT) & ID2_IAS_MASK);
+ id = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_ID2);
+ size = arm_smmu_id_size_to_bits(FIELD_GET(ID2_IAS, id));
smmu->ipa_size = size;
/* The output mask is also applied for bypass */
- size = arm_smmu_id_size_to_bits((id >> ID2_OAS_SHIFT) & ID2_OAS_MASK);
+ size = arm_smmu_id_size_to_bits(FIELD_GET(ID2_OAS, id));
smmu->pa_size = size;
if (id & ID2_VMID16)
@@ -1981,7 +1814,7 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
if (smmu->version == ARM_SMMU_V1_64K)
smmu->features |= ARM_SMMU_FEAT_FMT_AARCH64_64K;
} else {
- size = (id >> ID2_UBS_SHIFT) & ID2_UBS_MASK;
+ size = FIELD_GET(ID2_UBS, id);
smmu->va_size = arm_smmu_id_size_to_bits(size);
if (id & ID2_PTFS_4K)
smmu->features |= ARM_SMMU_FEAT_FMT_AARCH64_4K;
@@ -2018,6 +1851,9 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
dev_notice(smmu->dev, "\tStage-2: %lu-bit IPA -> %lu-bit PA\n",
smmu->ipa_size, smmu->pa_size);
+ if (smmu->impl && smmu->impl->cfg_probe)
+ return smmu->impl->cfg_probe(smmu);
+
return 0;
}
@@ -2130,8 +1966,6 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev,
smmu->version = data->version;
smmu->model = data->model;
- parse_driver_options(smmu);
-
legacy_binding = of_find_property(dev->of_node, "mmu-masters", NULL);
if (legacy_binding && !using_generic_binding) {
if (!using_legacy_binding)
@@ -2194,12 +2028,20 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
if (err)
return err;
+ smmu = arm_smmu_impl_init(smmu);
+ if (IS_ERR(smmu))
+ return PTR_ERR(smmu);
+
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
ioaddr = res->start;
smmu->base = devm_ioremap_resource(dev, res);
if (IS_ERR(smmu->base))
return PTR_ERR(smmu->base);
- smmu->cb_base = smmu->base + resource_size(res) / 2;
+ /*
+ * The resource size should effectively match the value of SMMU_TOP;
+ * stash that temporarily until we know PAGESIZE to validate it with.
+ */
+ smmu->numpage = resource_size(res);
num_irqs = 0;
while ((res = platform_get_resource(pdev, IORESOURCE_IRQ, num_irqs))) {
@@ -2339,7 +2181,7 @@ static void arm_smmu_device_shutdown(struct platform_device *pdev)
arm_smmu_rpm_get(smmu);
/* Turn the thing off */
- writel(sCR0_CLIENTPD, ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sCR0);
+ arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sCR0, sCR0_CLIENTPD);
arm_smmu_rpm_put(smmu);
if (pm_runtime_enabled(smmu->dev))
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
new file mode 100644
index 000000000000..b19b6cae9b5e
--- /dev/null
+++ b/drivers/iommu/arm-smmu.h
@@ -0,0 +1,402 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * IOMMU API for ARM architected SMMU implementations.
+ *
+ * Copyright (C) 2013 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#ifndef _ARM_SMMU_H
+#define _ARM_SMMU_H
+
+#include <linux/atomic.h>
+#include <linux/bits.h>
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/io-64-nonatomic-hi-lo.h>
+#include <linux/io-pgtable.h>
+#include <linux/iommu.h>
+#include <linux/mutex.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+
+/* Configuration registers */
+#define ARM_SMMU_GR0_sCR0 0x0
+#define sCR0_VMID16EN BIT(31)
+#define sCR0_BSU GENMASK(15, 14)
+#define sCR0_FB BIT(13)
+#define sCR0_PTM BIT(12)
+#define sCR0_VMIDPNE BIT(11)
+#define sCR0_USFCFG BIT(10)
+#define sCR0_GCFGFIE BIT(5)
+#define sCR0_GCFGFRE BIT(4)
+#define sCR0_EXIDENABLE BIT(3)
+#define sCR0_GFIE BIT(2)
+#define sCR0_GFRE BIT(1)
+#define sCR0_CLIENTPD BIT(0)
+
+/* Auxiliary Configuration register */
+#define ARM_SMMU_GR0_sACR 0x10
+
+/* Identification registers */
+#define ARM_SMMU_GR0_ID0 0x20
+#define ID0_S1TS BIT(30)
+#define ID0_S2TS BIT(29)
+#define ID0_NTS BIT(28)
+#define ID0_SMS BIT(27)
+#define ID0_ATOSNS BIT(26)
+#define ID0_PTFS_NO_AARCH32 BIT(25)
+#define ID0_PTFS_NO_AARCH32S BIT(24)
+#define ID0_NUMIRPT GENMASK(23, 16)
+#define ID0_CTTW BIT(14)
+#define ID0_NUMSIDB GENMASK(12, 9)
+#define ID0_EXIDS BIT(8)
+#define ID0_NUMSMRG GENMASK(7, 0)
+
+#define ARM_SMMU_GR0_ID1 0x24
+#define ID1_PAGESIZE BIT(31)
+#define ID1_NUMPAGENDXB GENMASK(30, 28)
+#define ID1_NUMS2CB GENMASK(23, 16)
+#define ID1_NUMCB GENMASK(7, 0)
+
+#define ARM_SMMU_GR0_ID2 0x28
+#define ID2_VMID16 BIT(15)
+#define ID2_PTFS_64K BIT(14)
+#define ID2_PTFS_16K BIT(13)
+#define ID2_PTFS_4K BIT(12)
+#define ID2_UBS GENMASK(11, 8)
+#define ID2_OAS GENMASK(7, 4)
+#define ID2_IAS GENMASK(3, 0)
+
+#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 ID7_MAJOR GENMASK(7, 4)
+#define ID7_MINOR GENMASK(3, 0)
+
+#define ARM_SMMU_GR0_sGFSR 0x48
+#define ARM_SMMU_GR0_sGFSYNR0 0x50
+#define ARM_SMMU_GR0_sGFSYNR1 0x54
+#define ARM_SMMU_GR0_sGFSYNR2 0x58
+
+/* Global TLB invalidation */
+#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 BIT(0)
+
+/* Stream mapping registers */
+#define ARM_SMMU_GR0_SMR(n) (0x800 + ((n) << 2))
+#define SMR_VALID BIT(31)
+#define SMR_MASK GENMASK(31, 16)
+#define SMR_ID GENMASK(15, 0)
+
+#define ARM_SMMU_GR0_S2CR(n) (0xc00 + ((n) << 2))
+#define S2CR_PRIVCFG GENMASK(25, 24)
+enum arm_smmu_s2cr_privcfg {
+ S2CR_PRIVCFG_DEFAULT,
+ S2CR_PRIVCFG_DIPAN,
+ S2CR_PRIVCFG_UNPRIV,
+ S2CR_PRIVCFG_PRIV,
+};
+#define S2CR_TYPE GENMASK(17, 16)
+enum arm_smmu_s2cr_type {
+ S2CR_TYPE_TRANS,
+ S2CR_TYPE_BYPASS,
+ S2CR_TYPE_FAULT,
+};
+#define S2CR_EXIDVALID BIT(10)
+#define S2CR_CBNDX GENMASK(7, 0)
+
+/* Context bank attribute registers */
+#define ARM_SMMU_GR1_CBAR(n) (0x0 + ((n) << 2))
+#define CBAR_IRPTNDX GENMASK(31, 24)
+#define CBAR_TYPE GENMASK(17, 16)
+enum arm_smmu_cbar_type {
+ CBAR_TYPE_S2_TRANS,
+ CBAR_TYPE_S1_TRANS_S2_BYPASS,
+ CBAR_TYPE_S1_TRANS_S2_FAULT,
+ CBAR_TYPE_S1_TRANS_S2_TRANS,
+};
+#define CBAR_S1_MEMATTR GENMASK(15, 12)
+#define CBAR_S1_MEMATTR_WB 0xf
+#define CBAR_S1_BPSHCFG GENMASK(9, 8)
+#define CBAR_S1_BPSHCFG_NSH 3
+#define CBAR_VMID GENMASK(7, 0)
+
+#define ARM_SMMU_GR1_CBFRSYNRA(n) (0x400 + ((n) << 2))
+
+#define ARM_SMMU_GR1_CBA2R(n) (0x800 + ((n) << 2))
+#define CBA2R_VMID16 GENMASK(31, 16)
+#define CBA2R_VA64 BIT(0)
+
+#define ARM_SMMU_CB_SCTLR 0x0
+#define SCTLR_S1_ASIDPNE BIT(12)
+#define SCTLR_CFCFG BIT(7)
+#define SCTLR_CFIE BIT(6)
+#define SCTLR_CFRE BIT(5)
+#define SCTLR_E BIT(4)
+#define SCTLR_AFE BIT(2)
+#define SCTLR_TRE BIT(1)
+#define SCTLR_M BIT(0)
+
+#define ARM_SMMU_CB_ACTLR 0x4
+
+#define ARM_SMMU_CB_RESUME 0x8
+#define RESUME_TERMINATE BIT(0)
+
+#define ARM_SMMU_CB_TCR2 0x10
+#define TCR2_SEP GENMASK(17, 15)
+#define TCR2_SEP_UPSTREAM 0x7
+#define TCR2_AS BIT(4)
+
+#define ARM_SMMU_CB_TTBR0 0x20
+#define ARM_SMMU_CB_TTBR1 0x28
+#define TTBRn_ASID GENMASK_ULL(63, 48)
+
+#define ARM_SMMU_CB_TCR 0x30
+#define ARM_SMMU_CB_CONTEXTIDR 0x34
+#define ARM_SMMU_CB_S1_MAIR0 0x38
+#define ARM_SMMU_CB_S1_MAIR1 0x3c
+
+#define ARM_SMMU_CB_PAR 0x50
+#define CB_PAR_F BIT(0)
+
+#define ARM_SMMU_CB_FSR 0x58
+#define FSR_MULTI BIT(31)
+#define FSR_SS BIT(30)
+#define FSR_UUT BIT(8)
+#define FSR_ASF BIT(7)
+#define FSR_TLBLKF BIT(6)
+#define FSR_TLBMCF BIT(5)
+#define FSR_EF BIT(4)
+#define FSR_PF BIT(3)
+#define FSR_AFF BIT(2)
+#define FSR_TF BIT(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 | FSR_IGN)
+
+#define ARM_SMMU_CB_FAR 0x60
+
+#define ARM_SMMU_CB_FSYNR0 0x68
+#define FSYNR0_WNR BIT(4)
+
+#define ARM_SMMU_CB_S1_TLBIVA 0x600
+#define ARM_SMMU_CB_S1_TLBIASID 0x610
+#define ARM_SMMU_CB_S1_TLBIVAL 0x620
+#define ARM_SMMU_CB_S2_TLBIIPAS2 0x630
+#define ARM_SMMU_CB_S2_TLBIIPAS2L 0x638
+#define ARM_SMMU_CB_TLBSYNC 0x7f0
+#define ARM_SMMU_CB_TLBSTATUS 0x7f4
+#define ARM_SMMU_CB_ATS1PR 0x800
+
+#define ARM_SMMU_CB_ATSR 0x8f0
+#define ATSR_ACTIVE BIT(0)
+
+
+/* Maximum number of context banks per SMMU */
+#define ARM_SMMU_MAX_CBS 128
+
+
+/* Shared driver definitions */
+enum arm_smmu_arch_version {
+ ARM_SMMU_V1,
+ ARM_SMMU_V1_64K,
+ ARM_SMMU_V2,
+};
+
+enum arm_smmu_implementation {
+ GENERIC_SMMU,
+ ARM_MMU500,
+ CAVIUM_SMMUV2,
+ QCOM_SMMUV2,
+};
+
+struct arm_smmu_device {
+ struct device *dev;
+
+ void __iomem *base;
+ unsigned int numpage;
+ unsigned int pgshift;
+
+#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)
+#define ARM_SMMU_FEAT_TRANS_OPS (1 << 5)
+#define ARM_SMMU_FEAT_VMID16 (1 << 6)
+#define ARM_SMMU_FEAT_FMT_AARCH64_4K (1 << 7)
+#define ARM_SMMU_FEAT_FMT_AARCH64_16K (1 << 8)
+#define ARM_SMMU_FEAT_FMT_AARCH64_64K (1 << 9)
+#define ARM_SMMU_FEAT_FMT_AARCH32_L (1 << 10)
+#define ARM_SMMU_FEAT_FMT_AARCH32_S (1 << 11)
+#define ARM_SMMU_FEAT_EXIDS (1 << 12)
+ u32 features;
+
+ enum arm_smmu_arch_version version;
+ enum arm_smmu_implementation model;
+ const struct arm_smmu_impl *impl;
+
+ u32 num_context_banks;
+ u32 num_s2_context_banks;
+ DECLARE_BITMAP(context_map, ARM_SMMU_MAX_CBS);
+ struct arm_smmu_cb *cbs;
+ atomic_t irptndx;
+
+ u32 num_mapping_groups;
+ u16 streamid_mask;
+ u16 smr_mask_mask;
+ struct arm_smmu_smr *smrs;
+ struct arm_smmu_s2cr *s2crs;
+ struct mutex stream_map_mutex;
+
+ unsigned long va_size;
+ unsigned long ipa_size;
+ unsigned long pa_size;
+ unsigned long pgsize_bitmap;
+
+ u32 num_global_irqs;
+ u32 num_context_irqs;
+ unsigned int *irqs;
+ struct clk_bulk_data *clks;
+ int num_clks;
+
+ spinlock_t global_sync_lock;
+
+ /* IOMMU core code handle */
+ struct iommu_device iommu;
+};
+
+enum arm_smmu_context_fmt {
+ ARM_SMMU_CTX_FMT_NONE,
+ ARM_SMMU_CTX_FMT_AARCH64,
+ ARM_SMMU_CTX_FMT_AARCH32_L,
+ ARM_SMMU_CTX_FMT_AARCH32_S,
+};
+
+struct arm_smmu_cfg {
+ u8 cbndx;
+ u8 irptndx;
+ union {
+ u16 asid;
+ u16 vmid;
+ };
+ enum arm_smmu_cbar_type cbar;
+ enum arm_smmu_context_fmt fmt;
+};
+#define INVALID_IRPTNDX 0xff
+
+enum arm_smmu_domain_stage {
+ ARM_SMMU_DOMAIN_S1 = 0,
+ ARM_SMMU_DOMAIN_S2,
+ ARM_SMMU_DOMAIN_NESTED,
+ ARM_SMMU_DOMAIN_BYPASS,
+};
+
+struct arm_smmu_flush_ops {
+ struct iommu_flush_ops tlb;
+ void (*tlb_inv_range)(unsigned long iova, size_t size, size_t granule,
+ bool leaf, void *cookie);
+ void (*tlb_sync)(void *cookie);
+};
+
+struct arm_smmu_domain {
+ struct arm_smmu_device *smmu;
+ struct io_pgtable_ops *pgtbl_ops;
+ const struct arm_smmu_flush_ops *flush_ops;
+ struct arm_smmu_cfg cfg;
+ enum arm_smmu_domain_stage stage;
+ bool non_strict;
+ struct mutex init_mutex; /* Protects smmu pointer */
+ spinlock_t cb_lock; /* Serialises ATS1* ops and TLB syncs */
+ struct iommu_domain domain;
+};
+
+
+/* Implementation details, yay! */
+struct arm_smmu_impl {
+ u32 (*read_reg)(struct arm_smmu_device *smmu, int page, int offset);
+ void (*write_reg)(struct arm_smmu_device *smmu, int page, int offset,
+ u32 val);
+ u64 (*read_reg64)(struct arm_smmu_device *smmu, int page, int offset);
+ void (*write_reg64)(struct arm_smmu_device *smmu, int page, int offset,
+ u64 val);
+ int (*cfg_probe)(struct arm_smmu_device *smmu);
+ int (*reset)(struct arm_smmu_device *smmu);
+ int (*init_context)(struct arm_smmu_domain *smmu_domain);
+};
+
+static inline void __iomem *arm_smmu_page(struct arm_smmu_device *smmu, int n)
+{
+ return smmu->base + (n << smmu->pgshift);
+}
+
+static inline u32 arm_smmu_readl(struct arm_smmu_device *smmu, int page, int offset)
+{
+ if (smmu->impl && unlikely(smmu->impl->read_reg))
+ return smmu->impl->read_reg(smmu, page, offset);
+ return readl_relaxed(arm_smmu_page(smmu, page) + offset);
+}
+
+static inline void arm_smmu_writel(struct arm_smmu_device *smmu, int page,
+ int offset, u32 val)
+{
+ if (smmu->impl && unlikely(smmu->impl->write_reg))
+ smmu->impl->write_reg(smmu, page, offset, val);
+ else
+ writel_relaxed(val, arm_smmu_page(smmu, page) + offset);
+}
+
+static inline u64 arm_smmu_readq(struct arm_smmu_device *smmu, int page, int offset)
+{
+ if (smmu->impl && unlikely(smmu->impl->read_reg64))
+ return smmu->impl->read_reg64(smmu, page, offset);
+ return readq_relaxed(arm_smmu_page(smmu, page) + offset);
+}
+
+static inline void arm_smmu_writeq(struct arm_smmu_device *smmu, int page,
+ int offset, u64 val)
+{
+ if (smmu->impl && unlikely(smmu->impl->write_reg64))
+ smmu->impl->write_reg64(smmu, page, offset, val);
+ else
+ writeq_relaxed(val, arm_smmu_page(smmu, page) + offset);
+}
+
+#define ARM_SMMU_GR0 0
+#define ARM_SMMU_GR1 1
+#define ARM_SMMU_CB(s, n) ((s)->numpage + (n))
+
+#define arm_smmu_gr0_read(s, o) \
+ arm_smmu_readl((s), ARM_SMMU_GR0, (o))
+#define arm_smmu_gr0_write(s, o, v) \
+ arm_smmu_writel((s), ARM_SMMU_GR0, (o), (v))
+
+#define arm_smmu_gr1_read(s, o) \
+ arm_smmu_readl((s), ARM_SMMU_GR1, (o))
+#define arm_smmu_gr1_write(s, o, v) \
+ arm_smmu_writel((s), ARM_SMMU_GR1, (o), (v))
+
+#define arm_smmu_cb_read(s, n, o) \
+ arm_smmu_readl((s), ARM_SMMU_CB((s), (n)), (o))
+#define arm_smmu_cb_write(s, n, o, v) \
+ arm_smmu_writel((s), ARM_SMMU_CB((s), (n)), (o), (v))
+#define arm_smmu_cb_readq(s, n, o) \
+ arm_smmu_readq((s), ARM_SMMU_CB((s), (n)), (o))
+#define arm_smmu_cb_writeq(s, n, o, v) \
+ arm_smmu_writeq((s), ARM_SMMU_CB((s), (n)), (o), (v))
+
+struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu);
+
+#endif /* _ARM_SMMU_H */
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index f68a62c3c32b..8f412af84247 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -303,13 +303,15 @@ static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
u64 size, struct device *dev)
{
struct iommu_dma_cookie *cookie = domain->iova_cookie;
- struct iova_domain *iovad = &cookie->iovad;
unsigned long order, base_pfn;
+ struct iova_domain *iovad;
int attr;
if (!cookie || cookie->type != IOMMU_DMA_IOVA_COOKIE)
return -EINVAL;
+ iovad = &cookie->iovad;
+
/* Use the smallest supported page size for IOVA granularity */
order = __ffs(domain->pgsize_bitmap);
base_pfn = max_t(unsigned long, 1, base >> order);
@@ -444,13 +446,18 @@ static void __iommu_dma_unmap(struct device *dev, dma_addr_t dma_addr,
struct iommu_dma_cookie *cookie = domain->iova_cookie;
struct iova_domain *iovad = &cookie->iovad;
size_t iova_off = iova_offset(iovad, dma_addr);
+ struct iommu_iotlb_gather iotlb_gather;
+ size_t unmapped;
dma_addr -= iova_off;
size = iova_align(iovad, size + iova_off);
+ iommu_iotlb_gather_init(&iotlb_gather);
+
+ unmapped = iommu_unmap_fast(domain, dma_addr, size, &iotlb_gather);
+ WARN_ON(unmapped != size);
- WARN_ON(iommu_unmap_fast(domain, dma_addr, size) != size);
if (!cookie->fq_domain)
- iommu_tlb_sync(domain);
+ iommu_tlb_sync(domain, &iotlb_gather);
iommu_dma_free_iova(cookie, dma_addr, size);
}
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 5d0754ed5fa0..eecd6a421667 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -1519,6 +1519,64 @@ static const char *dma_remap_fault_reasons[] =
"PCE for translation request specifies blocking",
};
+static const char * const dma_remap_sm_fault_reasons[] = {
+ "SM: Invalid Root Table Address",
+ "SM: TTM 0 for request with PASID",
+ "SM: TTM 0 for page group request",
+ "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x33-0x37 */
+ "SM: Error attempting to access Root Entry",
+ "SM: Present bit in Root Entry is clear",
+ "SM: Non-zero reserved field set in Root Entry",
+ "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x3B-0x3F */
+ "SM: Error attempting to access Context Entry",
+ "SM: Present bit in Context Entry is clear",
+ "SM: Non-zero reserved field set in the Context Entry",
+ "SM: Invalid Context Entry",
+ "SM: DTE field in Context Entry is clear",
+ "SM: PASID Enable field in Context Entry is clear",
+ "SM: PASID is larger than the max in Context Entry",
+ "SM: PRE field in Context-Entry is clear",
+ "SM: RID_PASID field error in Context-Entry",
+ "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x49-0x4F */
+ "SM: Error attempting to access the PASID Directory Entry",
+ "SM: Present bit in Directory Entry is clear",
+ "SM: Non-zero reserved field set in PASID Directory Entry",
+ "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x53-0x57 */
+ "SM: Error attempting to access PASID Table Entry",
+ "SM: Present bit in PASID Table Entry is clear",
+ "SM: Non-zero reserved field set in PASID Table Entry",
+ "SM: Invalid Scalable-Mode PASID Table Entry",
+ "SM: ERE field is clear in PASID Table Entry",
+ "SM: SRE field is clear in PASID Table Entry",
+ "Unknown", "Unknown",/* 0x5E-0x5F */
+ "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x60-0x67 */
+ "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x68-0x6F */
+ "SM: Error attempting to access first-level paging entry",
+ "SM: Present bit in first-level paging entry is clear",
+ "SM: Non-zero reserved field set in first-level paging entry",
+ "SM: Error attempting to access FL-PML4 entry",
+ "SM: First-level entry address beyond MGAW in Nested translation",
+ "SM: Read permission error in FL-PML4 entry in Nested translation",
+ "SM: Read permission error in first-level paging entry in Nested translation",
+ "SM: Write permission error in first-level paging entry in Nested translation",
+ "SM: Error attempting to access second-level paging entry",
+ "SM: Read/Write permission error in second-level paging entry",
+ "SM: Non-zero reserved field set in second-level paging entry",
+ "SM: Invalid second-level page table pointer",
+ "SM: A/D bit update needed in second-level entry when set up in no snoop",
+ "Unknown", "Unknown", "Unknown", /* 0x7D-0x7F */
+ "SM: Address in first-level translation is not canonical",
+ "SM: U/S set 0 for first-level translation with user privilege",
+ "SM: No execute permission for request with PASID and ER=1",
+ "SM: Address beyond the DMA hardware max",
+ "SM: Second-level entry address beyond the max",
+ "SM: No write permission for Write/AtomicOp request",
+ "SM: No read permission for Read/AtomicOp request",
+ "SM: Invalid address-interrupt address",
+ "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x88-0x8F */
+ "SM: A/D bit update needed in first-level entry when set up in no snoop",
+};
+
static const char *irq_remap_fault_reasons[] =
{
"Detected reserved fields in the decoded interrupt-remapped request",
@@ -1536,6 +1594,10 @@ static const char *dmar_get_fault_reason(u8 fault_reason, int *fault_type)
ARRAY_SIZE(irq_remap_fault_reasons))) {
*fault_type = INTR_REMAP;
return irq_remap_fault_reasons[fault_reason - 0x20];
+ } else if (fault_reason >= 0x30 && (fault_reason - 0x30 <
+ ARRAY_SIZE(dma_remap_sm_fault_reasons))) {
+ *fault_type = DMA_REMAP;
+ return dma_remap_sm_fault_reasons[fault_reason - 0x30];
} else if (fault_reason < ARRAY_SIZE(dma_remap_fault_reasons)) {
*fault_type = DMA_REMAP;
return dma_remap_fault_reasons[fault_reason];
@@ -1611,7 +1673,8 @@ void dmar_msi_read(int irq, struct msi_msg *msg)
}
static int dmar_fault_do_one(struct intel_iommu *iommu, int type,
- u8 fault_reason, u16 source_id, unsigned long long addr)
+ u8 fault_reason, int pasid, u16 source_id,
+ unsigned long long addr)
{
const char *reason;
int fault_type;
@@ -1624,10 +1687,11 @@ static int dmar_fault_do_one(struct intel_iommu *iommu, int type,
PCI_FUNC(source_id & 0xFF), addr >> 48,
fault_reason, reason);
else
- pr_err("[%s] Request device [%02x:%02x.%d] fault addr %llx [fault reason %02d] %s\n",
+ pr_err("[%s] Request device [%02x:%02x.%d] PASID %x fault addr %llx [fault reason %02d] %s\n",
type ? "DMA Read" : "DMA Write",
source_id >> 8, PCI_SLOT(source_id & 0xFF),
- PCI_FUNC(source_id & 0xFF), addr, fault_reason, reason);
+ PCI_FUNC(source_id & 0xFF), pasid, addr,
+ fault_reason, reason);
return 0;
}
@@ -1659,8 +1723,9 @@ irqreturn_t dmar_fault(int irq, void *dev_id)
u8 fault_reason;
u16 source_id;
u64 guest_addr;
- int type;
+ int type, pasid;
u32 data;
+ bool pasid_present;
/* highest 32 bits */
data = readl(iommu->reg + reg +
@@ -1672,10 +1737,12 @@ irqreturn_t dmar_fault(int irq, void *dev_id)
fault_reason = dma_frcd_fault_reason(data);
type = dma_frcd_type(data);
+ pasid = dma_frcd_pasid_value(data);
data = readl(iommu->reg + reg +
fault_index * PRIMARY_FAULT_REG_LEN + 8);
source_id = dma_frcd_source_id(data);
+ pasid_present = dma_frcd_pasid_present(data);
guest_addr = dmar_readq(iommu->reg + reg +
fault_index * PRIMARY_FAULT_REG_LEN);
guest_addr = dma_frcd_page_addr(guest_addr);
@@ -1688,7 +1755,9 @@ irqreturn_t dmar_fault(int irq, void *dev_id)
raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
if (!ratelimited)
+ /* Using pasid -1 if pasid is not present */
dmar_fault_do_one(iommu, type, fault_reason,
+ pasid_present ? pasid : -1,
source_id, guest_addr);
fault_index++;
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index b0c1e5f9daae..9c94e16fb127 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -566,7 +566,7 @@ static void sysmmu_tlb_invalidate_entry(struct sysmmu_drvdata *data,
static const struct iommu_ops exynos_iommu_ops;
-static int __init exynos_sysmmu_probe(struct platform_device *pdev)
+static int exynos_sysmmu_probe(struct platform_device *pdev)
{
int irq, ret;
struct device *dev = &pdev->dev;
@@ -583,10 +583,8 @@ static int __init exynos_sysmmu_probe(struct platform_device *pdev)
return PTR_ERR(data->sfrbase);
irq = platform_get_irq(pdev, 0);
- if (irq <= 0) {
- dev_err(dev, "Unable to find IRQ resource\n");
+ if (irq <= 0)
return irq;
- }
ret = devm_request_irq(dev, irq, exynos_sysmmu_irq, 0,
dev_name(dev), data);
@@ -1130,7 +1128,8 @@ static void exynos_iommu_tlb_invalidate_entry(struct exynos_iommu_domain *domain
}
static size_t exynos_iommu_unmap(struct iommu_domain *iommu_domain,
- unsigned long l_iova, size_t size)
+ unsigned long l_iova, size_t size,
+ struct iommu_iotlb_gather *gather)
{
struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain);
sysmmu_iova_t iova = (sysmmu_iova_t)l_iova;
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index c4e0e4a9ee9e..87de0b975672 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -41,9 +41,11 @@
#include <linux/dma-direct.h>
#include <linux/crash_dump.h>
#include <linux/numa.h>
+#include <linux/swiotlb.h>
#include <asm/irq_remapping.h>
#include <asm/cacheflush.h>
#include <asm/iommu.h>
+#include <trace/events/intel_iommu.h>
#include "irq_remapping.h"
#include "intel-pasid.h"
@@ -346,6 +348,8 @@ static int domain_detach_iommu(struct dmar_domain *domain,
static bool device_is_rmrr_locked(struct device *dev);
static int intel_iommu_attach_device(struct iommu_domain *domain,
struct device *dev);
+static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
+ dma_addr_t iova);
#ifdef CONFIG_INTEL_IOMMU_DEFAULT_ON
int dmar_disabled = 0;
@@ -362,6 +366,7 @@ static int dmar_forcedac;
static int intel_iommu_strict;
static int intel_iommu_superpage = 1;
static int iommu_identity_mapping;
+static int intel_no_bounce;
#define IDENTMAP_ALL 1
#define IDENTMAP_GFX 2
@@ -375,6 +380,9 @@ EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped);
static DEFINE_SPINLOCK(device_domain_lock);
static LIST_HEAD(device_domain_list);
+#define device_needs_bounce(d) (!intel_no_bounce && dev_is_pci(d) && \
+ to_pci_dev(d)->untrusted)
+
/*
* Iterate over elements in device_domain_list and call the specified
* callback @fn against each element.
@@ -457,6 +465,9 @@ static int __init intel_iommu_setup(char *str)
printk(KERN_INFO
"Intel-IOMMU: not forcing on after tboot. This could expose security risk for tboot\n");
intel_iommu_tboot_noforce = 1;
+ } else if (!strncmp(str, "nobounce", 8)) {
+ pr_info("Intel-IOMMU: No bounce buffer. This could expose security risks of DMA attacks\n");
+ intel_no_bounce = 1;
}
str += strcspn(str, ",");
@@ -3296,7 +3307,7 @@ static int __init init_dmars(void)
iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
}
- if (iommu_pass_through)
+ if (iommu_default_passthrough())
iommu_identity_mapping |= IDENTMAP_ALL;
#ifdef CONFIG_INTEL_IOMMU_BROKEN_GFX_WA
@@ -3534,6 +3545,9 @@ static dma_addr_t __intel_map_single(struct device *dev, phys_addr_t paddr,
start_paddr = (phys_addr_t)iova_pfn << PAGE_SHIFT;
start_paddr += paddr & ~PAGE_MASK;
+
+ trace_map_single(dev, start_paddr, paddr, size << VTD_PAGE_SHIFT);
+
return start_paddr;
error:
@@ -3589,10 +3603,7 @@ static void intel_unmap(struct device *dev, dma_addr_t dev_addr, size_t size)
if (dev_is_pci(dev))
pdev = to_pci_dev(dev);
- dev_dbg(dev, "Device unmapping: pfn %lx-%lx\n", start_pfn, last_pfn);
-
freelist = domain_unmap(domain, start_pfn, last_pfn);
-
if (intel_iommu_strict || (pdev && pdev->untrusted) ||
!has_iova_flush_queue(&domain->iovad)) {
iommu_flush_iotlb_psi(iommu, domain, start_pfn,
@@ -3608,6 +3619,8 @@ static void intel_unmap(struct device *dev, dma_addr_t dev_addr, size_t size)
* cpu used up by the iotlb flush operation...
*/
}
+
+ trace_unmap_single(dev, dev_addr, size);
}
static void intel_unmap_page(struct device *dev, dma_addr_t dev_addr,
@@ -3698,6 +3711,8 @@ static void intel_unmap_sg(struct device *dev, struct scatterlist *sglist,
}
intel_unmap(dev, startaddr, nrpages << VTD_PAGE_SHIFT);
+
+ trace_unmap_sg(dev, startaddr, nrpages << VTD_PAGE_SHIFT);
}
static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nelems,
@@ -3754,6 +3769,9 @@ static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nele
return 0;
}
+ trace_map_sg(dev, iova_pfn << PAGE_SHIFT,
+ sg_phys(sglist), size << VTD_PAGE_SHIFT);
+
return nelems;
}
@@ -3769,6 +3787,252 @@ static const struct dma_map_ops intel_dma_ops = {
.dma_supported = dma_direct_supported,
};
+static void
+bounce_sync_single(struct device *dev, dma_addr_t addr, size_t size,
+ enum dma_data_direction dir, enum dma_sync_target target)
+{
+ struct dmar_domain *domain;
+ phys_addr_t tlb_addr;
+
+ domain = find_domain(dev);
+ if (WARN_ON(!domain))
+ return;
+
+ tlb_addr = intel_iommu_iova_to_phys(&domain->domain, addr);
+ if (is_swiotlb_buffer(tlb_addr))
+ swiotlb_tbl_sync_single(dev, tlb_addr, size, dir, target);
+}
+
+static dma_addr_t
+bounce_map_single(struct device *dev, phys_addr_t paddr, size_t size,
+ enum dma_data_direction dir, unsigned long attrs,
+ u64 dma_mask)
+{
+ size_t aligned_size = ALIGN(size, VTD_PAGE_SIZE);
+ struct dmar_domain *domain;
+ struct intel_iommu *iommu;
+ unsigned long iova_pfn;
+ unsigned long nrpages;
+ phys_addr_t tlb_addr;
+ int prot = 0;
+ int ret;
+
+ domain = find_domain(dev);
+ if (WARN_ON(dir == DMA_NONE || !domain))
+ return DMA_MAPPING_ERROR;
+
+ iommu = domain_get_iommu(domain);
+ if (WARN_ON(!iommu))
+ return DMA_MAPPING_ERROR;
+
+ nrpages = aligned_nrpages(0, size);
+ iova_pfn = intel_alloc_iova(dev, domain,
+ dma_to_mm_pfn(nrpages), dma_mask);
+ if (!iova_pfn)
+ return DMA_MAPPING_ERROR;
+
+ /*
+ * Check if DMAR supports zero-length reads on write only
+ * mappings..
+ */
+ if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL ||
+ !cap_zlr(iommu->cap))
+ prot |= DMA_PTE_READ;
+ if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)
+ prot |= DMA_PTE_WRITE;
+
+ /*
+ * If both the physical buffer start address and size are
+ * page aligned, we don't need to use a bounce page.
+ */
+ if (!IS_ALIGNED(paddr | size, VTD_PAGE_SIZE)) {
+ tlb_addr = swiotlb_tbl_map_single(dev,
+ __phys_to_dma(dev, io_tlb_start),
+ paddr, size, aligned_size, dir, attrs);
+ if (tlb_addr == DMA_MAPPING_ERROR) {
+ goto swiotlb_error;
+ } else {
+ /* Cleanup the padding area. */
+ void *padding_start = phys_to_virt(tlb_addr);
+ size_t padding_size = aligned_size;
+
+ if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
+ (dir == DMA_TO_DEVICE ||
+ dir == DMA_BIDIRECTIONAL)) {
+ padding_start += size;
+ padding_size -= size;
+ }
+
+ memset(padding_start, 0, padding_size);
+ }
+ } else {
+ tlb_addr = paddr;
+ }
+
+ ret = domain_pfn_mapping(domain, mm_to_dma_pfn(iova_pfn),
+ tlb_addr >> VTD_PAGE_SHIFT, nrpages, prot);
+ if (ret)
+ goto mapping_error;
+
+ trace_bounce_map_single(dev, iova_pfn << PAGE_SHIFT, paddr, size);
+
+ return (phys_addr_t)iova_pfn << PAGE_SHIFT;
+
+mapping_error:
+ if (is_swiotlb_buffer(tlb_addr))
+ swiotlb_tbl_unmap_single(dev, tlb_addr, size,
+ aligned_size, dir, attrs);
+swiotlb_error:
+ free_iova_fast(&domain->iovad, iova_pfn, dma_to_mm_pfn(nrpages));
+ dev_err(dev, "Device bounce map: %zx@%llx dir %d --- failed\n",
+ size, (unsigned long long)paddr, dir);
+
+ return DMA_MAPPING_ERROR;
+}
+
+static void
+bounce_unmap_single(struct device *dev, dma_addr_t dev_addr, size_t size,
+ enum dma_data_direction dir, unsigned long attrs)
+{
+ size_t aligned_size = ALIGN(size, VTD_PAGE_SIZE);
+ struct dmar_domain *domain;
+ phys_addr_t tlb_addr;
+
+ domain = find_domain(dev);
+ if (WARN_ON(!domain))
+ return;
+
+ tlb_addr = intel_iommu_iova_to_phys(&domain->domain, dev_addr);
+ if (WARN_ON(!tlb_addr))
+ return;
+
+ intel_unmap(dev, dev_addr, size);
+ if (is_swiotlb_buffer(tlb_addr))
+ swiotlb_tbl_unmap_single(dev, tlb_addr, size,
+ aligned_size, dir, attrs);
+
+ trace_bounce_unmap_single(dev, dev_addr, size);
+}
+
+static dma_addr_t
+bounce_map_page(struct device *dev, struct page *page, unsigned long offset,
+ size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+ return bounce_map_single(dev, page_to_phys(page) + offset,
+ size, dir, attrs, *dev->dma_mask);
+}
+
+static dma_addr_t
+bounce_map_resource(struct device *dev, phys_addr_t phys_addr, size_t size,
+ enum dma_data_direction dir, unsigned long attrs)
+{
+ return bounce_map_single(dev, phys_addr, size,
+ dir, attrs, *dev->dma_mask);
+}
+
+static void
+bounce_unmap_page(struct device *dev, dma_addr_t dev_addr, size_t size,
+ enum dma_data_direction dir, unsigned long attrs)
+{
+ bounce_unmap_single(dev, dev_addr, size, dir, attrs);
+}
+
+static void
+bounce_unmap_resource(struct device *dev, dma_addr_t dev_addr, size_t size,
+ enum dma_data_direction dir, unsigned long attrs)
+{
+ bounce_unmap_single(dev, dev_addr, size, dir, attrs);
+}
+
+static void
+bounce_unmap_sg(struct device *dev, struct scatterlist *sglist, int nelems,
+ enum dma_data_direction dir, unsigned long attrs)
+{
+ struct scatterlist *sg;
+ int i;
+
+ for_each_sg(sglist, sg, nelems, i)
+ bounce_unmap_page(dev, sg->dma_address,
+ sg_dma_len(sg), dir, attrs);
+}
+
+static int
+bounce_map_sg(struct device *dev, struct scatterlist *sglist, int nelems,
+ enum dma_data_direction dir, unsigned long attrs)
+{
+ int i;
+ struct scatterlist *sg;
+
+ for_each_sg(sglist, sg, nelems, i) {
+ sg->dma_address = bounce_map_page(dev, sg_page(sg),
+ sg->offset, sg->length,
+ dir, attrs);
+ if (sg->dma_address == DMA_MAPPING_ERROR)
+ goto out_unmap;
+ sg_dma_len(sg) = sg->length;
+ }
+
+ return nelems;
+
+out_unmap:
+ bounce_unmap_sg(dev, sglist, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC);
+ return 0;
+}
+
+static void
+bounce_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
+ size_t size, enum dma_data_direction dir)
+{
+ bounce_sync_single(dev, addr, size, dir, SYNC_FOR_CPU);
+}
+
+static void
+bounce_sync_single_for_device(struct device *dev, dma_addr_t addr,
+ size_t size, enum dma_data_direction dir)
+{
+ bounce_sync_single(dev, addr, size, dir, SYNC_FOR_DEVICE);
+}
+
+static void
+bounce_sync_sg_for_cpu(struct device *dev, struct scatterlist *sglist,
+ int nelems, enum dma_data_direction dir)
+{
+ struct scatterlist *sg;
+ int i;
+
+ for_each_sg(sglist, sg, nelems, i)
+ bounce_sync_single(dev, sg_dma_address(sg),
+ sg_dma_len(sg), dir, SYNC_FOR_CPU);
+}
+
+static void
+bounce_sync_sg_for_device(struct device *dev, struct scatterlist *sglist,
+ int nelems, enum dma_data_direction dir)
+{
+ struct scatterlist *sg;
+ int i;
+
+ for_each_sg(sglist, sg, nelems, i)
+ bounce_sync_single(dev, sg_dma_address(sg),
+ sg_dma_len(sg), dir, SYNC_FOR_DEVICE);
+}
+
+static const struct dma_map_ops bounce_dma_ops = {
+ .alloc = intel_alloc_coherent,
+ .free = intel_free_coherent,
+ .map_sg = bounce_map_sg,
+ .unmap_sg = bounce_unmap_sg,
+ .map_page = bounce_map_page,
+ .unmap_page = bounce_unmap_page,
+ .sync_single_for_cpu = bounce_sync_single_for_cpu,
+ .sync_single_for_device = bounce_sync_single_for_device,
+ .sync_sg_for_cpu = bounce_sync_sg_for_cpu,
+ .sync_sg_for_device = bounce_sync_sg_for_device,
+ .map_resource = bounce_map_resource,
+ .unmap_resource = bounce_unmap_resource,
+ .dma_supported = dma_direct_supported,
+};
+
static inline int iommu_domain_cache_init(void)
{
int ret = 0;
@@ -4569,22 +4833,20 @@ const struct attribute_group *intel_iommu_groups[] = {
NULL,
};
-static int __init platform_optin_force_iommu(void)
+static inline bool has_untrusted_dev(void)
{
struct pci_dev *pdev = NULL;
- bool has_untrusted_dev = false;
- if (!dmar_platform_optin() || no_platform_optin)
- return 0;
+ for_each_pci_dev(pdev)
+ if (pdev->untrusted)
+ return true;
- for_each_pci_dev(pdev) {
- if (pdev->untrusted) {
- has_untrusted_dev = true;
- break;
- }
- }
+ return false;
+}
- if (!has_untrusted_dev)
+static int __init platform_optin_force_iommu(void)
+{
+ if (!dmar_platform_optin() || no_platform_optin || !has_untrusted_dev())
return 0;
if (no_iommu || dmar_disabled)
@@ -4598,9 +4860,6 @@ static int __init platform_optin_force_iommu(void)
iommu_identity_mapping |= IDENTMAP_ALL;
dmar_disabled = 0;
-#if defined(CONFIG_X86) && defined(CONFIG_SWIOTLB)
- swiotlb = 0;
-#endif
no_iommu = 0;
return 1;
@@ -4740,7 +4999,14 @@ int __init intel_iommu_init(void)
up_write(&dmar_global_lock);
#if defined(CONFIG_X86) && defined(CONFIG_SWIOTLB)
- swiotlb = 0;
+ /*
+ * If the system has no untrusted device or the user has decided
+ * to disable the bounce page mechanisms, we don't need swiotlb.
+ * Mark this and the pre-allocated bounce pages will be released
+ * later.
+ */
+ if (!has_untrusted_dev() || intel_no_bounce)
+ swiotlb = 0;
#endif
dma_ops = &intel_dma_ops;
@@ -5204,7 +5470,8 @@ static int intel_iommu_map(struct iommu_domain *domain,
}
static size_t intel_iommu_unmap(struct iommu_domain *domain,
- unsigned long iova, size_t size)
+ unsigned long iova, size_t size,
+ struct iommu_iotlb_gather *gather)
{
struct dmar_domain *dmar_domain = to_dmar_domain(domain);
struct page *freelist = NULL;
@@ -5360,6 +5627,11 @@ static int intel_iommu_add_device(struct device *dev)
}
}
+ if (device_needs_bounce(dev)) {
+ dev_info(dev, "Use Intel IOMMU bounce page dma_ops\n");
+ set_dma_ops(dev, &bounce_dma_ops);
+ }
+
return 0;
}
@@ -5377,6 +5649,9 @@ static void intel_iommu_remove_device(struct device *dev)
iommu_group_remove_device(dev);
iommu_device_unlink(&iommu->iommu, dev);
+
+ if (device_needs_bounce(dev))
+ set_dma_ops(dev, NULL);
}
static void intel_iommu_get_resv_regions(struct device *device,
@@ -5690,20 +5965,46 @@ const struct iommu_ops intel_iommu_ops = {
.pgsize_bitmap = INTEL_IOMMU_PGSIZES,
};
-static void quirk_iommu_g4x_gfx(struct pci_dev *dev)
+static void quirk_iommu_igfx(struct pci_dev *dev)
{
- /* G4x/GM45 integrated gfx dmar support is totally busted. */
pci_info(dev, "Disabling IOMMU for graphics on this chipset\n");
dmar_map_gfx = 0;
}
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2a40, quirk_iommu_g4x_gfx);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e00, quirk_iommu_g4x_gfx);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e10, quirk_iommu_g4x_gfx);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e20, quirk_iommu_g4x_gfx);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e30, quirk_iommu_g4x_gfx);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e40, quirk_iommu_g4x_gfx);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e90, quirk_iommu_g4x_gfx);
+/* G4x/GM45 integrated gfx dmar support is totally busted. */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2a40, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e00, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e10, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e20, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e30, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e40, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e90, quirk_iommu_igfx);
+
+/* Broadwell igfx malfunctions with dmar */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1606, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x160B, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x160E, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1602, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x160A, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x160D, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1616, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x161B, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x161E, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1612, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x161A, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x161D, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1626, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x162B, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x162E, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1622, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x162A, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x162D, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1636, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x163B, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x163E, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1632, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x163A, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x163D, quirk_iommu_igfx);
static void quirk_iommu_rwbf(struct pci_dev *dev)
{
diff --git a/drivers/iommu/intel-trace.c b/drivers/iommu/intel-trace.c
new file mode 100644
index 000000000000..bfb6a6e37a88
--- /dev/null
+++ b/drivers/iommu/intel-trace.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel IOMMU trace support
+ *
+ * Copyright (C) 2019 Intel Corporation
+ *
+ * Author: Lu Baolu <baolu.lu@linux.intel.com>
+ */
+
+#include <linux/string.h>
+#include <linux/types.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/intel_iommu.h>
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
index 4786ca061e31..81e43c1df7ec 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -376,13 +376,13 @@ static int set_msi_sid_cb(struct pci_dev *pdev, u16 alias, void *opaque)
{
struct set_msi_sid_data *data = opaque;
+ if (data->count == 0 || PCI_BUS_NUM(alias) == PCI_BUS_NUM(data->alias))
+ data->busmatch_count++;
+
data->pdev = pdev;
data->alias = alias;
data->count++;
- if (PCI_BUS_NUM(alias) == pdev->bus->number)
- data->busmatch_count++;
-
return 0;
}
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 0fc8dfab2abf..4cb394937700 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -112,7 +112,9 @@
#define ARM_V7S_TEX_MASK 0x7
#define ARM_V7S_ATTR_TEX(val) (((val) & ARM_V7S_TEX_MASK) << ARM_V7S_TEX_SHIFT)
-#define ARM_V7S_ATTR_MTK_4GB BIT(9) /* MTK extend it for 4GB mode */
+/* MediaTek extend the two bits for PA 32bit/33bit */
+#define ARM_V7S_ATTR_MTK_PA_BIT32 BIT(9)
+#define ARM_V7S_ATTR_MTK_PA_BIT33 BIT(4)
/* *well, except for TEX on level 2 large pages, of course :( */
#define ARM_V7S_CONT_PAGE_TEX_SHIFT 6
@@ -169,18 +171,62 @@ struct arm_v7s_io_pgtable {
spinlock_t split_lock;
};
+static bool arm_v7s_pte_is_cont(arm_v7s_iopte pte, int lvl);
+
static dma_addr_t __arm_v7s_dma_addr(void *pages)
{
return (dma_addr_t)virt_to_phys(pages);
}
-static arm_v7s_iopte *iopte_deref(arm_v7s_iopte pte, int lvl)
+static bool arm_v7s_is_mtk_enabled(struct io_pgtable_cfg *cfg)
+{
+ return IS_ENABLED(CONFIG_PHYS_ADDR_T_64BIT) &&
+ (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_EXT);
+}
+
+static arm_v7s_iopte paddr_to_iopte(phys_addr_t paddr, int lvl,
+ struct io_pgtable_cfg *cfg)
+{
+ arm_v7s_iopte pte = paddr & ARM_V7S_LVL_MASK(lvl);
+
+ if (!arm_v7s_is_mtk_enabled(cfg))
+ return pte;
+
+ if (paddr & BIT_ULL(32))
+ pte |= ARM_V7S_ATTR_MTK_PA_BIT32;
+ if (paddr & BIT_ULL(33))
+ pte |= ARM_V7S_ATTR_MTK_PA_BIT33;
+ return pte;
+}
+
+static phys_addr_t iopte_to_paddr(arm_v7s_iopte pte, int lvl,
+ struct io_pgtable_cfg *cfg)
{
+ arm_v7s_iopte mask;
+ phys_addr_t paddr;
+
if (ARM_V7S_PTE_IS_TABLE(pte, lvl))
- pte &= ARM_V7S_TABLE_MASK;
+ mask = ARM_V7S_TABLE_MASK;
+ else if (arm_v7s_pte_is_cont(pte, lvl))
+ mask = ARM_V7S_LVL_MASK(lvl) * ARM_V7S_CONT_PAGES;
else
- pte &= ARM_V7S_LVL_MASK(lvl);
- return phys_to_virt(pte);
+ mask = ARM_V7S_LVL_MASK(lvl);
+
+ paddr = pte & mask;
+ if (!arm_v7s_is_mtk_enabled(cfg))
+ return paddr;
+
+ if (pte & ARM_V7S_ATTR_MTK_PA_BIT32)
+ paddr |= BIT_ULL(32);
+ if (pte & ARM_V7S_ATTR_MTK_PA_BIT33)
+ paddr |= BIT_ULL(33);
+ return paddr;
+}
+
+static arm_v7s_iopte *iopte_deref(arm_v7s_iopte pte, int lvl,
+ struct arm_v7s_io_pgtable *data)
+{
+ return phys_to_virt(iopte_to_paddr(pte, lvl, &data->iop.cfg));
}
static void *__arm_v7s_alloc_table(int lvl, gfp_t gfp,
@@ -295,9 +341,6 @@ static arm_v7s_iopte arm_v7s_prot_to_pte(int prot, int lvl,
if (lvl == 1 && (cfg->quirks & IO_PGTABLE_QUIRK_ARM_NS))
pte |= ARM_V7S_ATTR_NS_SECTION;
- if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_4GB)
- pte |= ARM_V7S_ATTR_MTK_4GB;
-
return pte;
}
@@ -362,7 +405,8 @@ static bool arm_v7s_pte_is_cont(arm_v7s_iopte pte, int lvl)
return false;
}
-static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *, unsigned long,
+static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *,
+ struct iommu_iotlb_gather *, unsigned long,
size_t, int, arm_v7s_iopte *);
static int arm_v7s_init_pte(struct arm_v7s_io_pgtable *data,
@@ -383,7 +427,7 @@ static int arm_v7s_init_pte(struct arm_v7s_io_pgtable *data,
size_t sz = ARM_V7S_BLOCK_SIZE(lvl);
tblp = ptep - ARM_V7S_LVL_IDX(iova, lvl);
- if (WARN_ON(__arm_v7s_unmap(data, iova + i * sz,
+ if (WARN_ON(__arm_v7s_unmap(data, NULL, iova + i * sz,
sz, lvl, tblp) != sz))
return -EINVAL;
} else if (ptep[i]) {
@@ -396,7 +440,7 @@ static int arm_v7s_init_pte(struct arm_v7s_io_pgtable *data,
if (num_entries > 1)
pte = arm_v7s_pte_to_cont(pte, lvl);
- pte |= paddr & ARM_V7S_LVL_MASK(lvl);
+ pte |= paddr_to_iopte(paddr, lvl, cfg);
__arm_v7s_set_pte(ptep, pte, num_entries, cfg);
return 0;
@@ -462,7 +506,7 @@ static int __arm_v7s_map(struct arm_v7s_io_pgtable *data, unsigned long iova,
}
if (ARM_V7S_PTE_IS_TABLE(pte, lvl)) {
- cptep = iopte_deref(pte, lvl);
+ cptep = iopte_deref(pte, lvl, data);
} else if (pte) {
/* We require an unmap first */
WARN_ON(!selftest_running);
@@ -484,7 +528,8 @@ static int arm_v7s_map(struct io_pgtable_ops *ops, unsigned long iova,
if (!(prot & (IOMMU_READ | IOMMU_WRITE)))
return 0;
- if (WARN_ON(upper_32_bits(iova) || upper_32_bits(paddr)))
+ if (WARN_ON(iova >= (1ULL << data->iop.cfg.ias) ||
+ paddr >= (1ULL << data->iop.cfg.oas)))
return -ERANGE;
ret = __arm_v7s_map(data, iova, paddr, size, prot, 1, data->pgd);
@@ -493,9 +538,8 @@ static int arm_v7s_map(struct io_pgtable_ops *ops, unsigned long iova,
* a chance for anything to kick off a table walk for the new iova.
*/
if (iop->cfg.quirks & IO_PGTABLE_QUIRK_TLBI_ON_MAP) {
- io_pgtable_tlb_add_flush(iop, iova, size,
- ARM_V7S_BLOCK_SIZE(2), false);
- io_pgtable_tlb_sync(iop);
+ io_pgtable_tlb_flush_walk(iop, iova, size,
+ ARM_V7S_BLOCK_SIZE(2));
} else {
wmb();
}
@@ -512,7 +556,8 @@ static void arm_v7s_free_pgtable(struct io_pgtable *iop)
arm_v7s_iopte pte = data->pgd[i];
if (ARM_V7S_PTE_IS_TABLE(pte, 1))
- __arm_v7s_free_table(iopte_deref(pte, 1), 2, data);
+ __arm_v7s_free_table(iopte_deref(pte, 1, data),
+ 2, data);
}
__arm_v7s_free_table(data->pgd, 1, data);
kmem_cache_destroy(data->l2_tables);
@@ -541,12 +586,12 @@ static arm_v7s_iopte arm_v7s_split_cont(struct arm_v7s_io_pgtable *data,
__arm_v7s_pte_sync(ptep, ARM_V7S_CONT_PAGES, &iop->cfg);
size *= ARM_V7S_CONT_PAGES;
- io_pgtable_tlb_add_flush(iop, iova, size, size, true);
- io_pgtable_tlb_sync(iop);
+ io_pgtable_tlb_flush_leaf(iop, iova, size, size);
return pte;
}
static size_t arm_v7s_split_blk_unmap(struct arm_v7s_io_pgtable *data,
+ struct iommu_iotlb_gather *gather,
unsigned long iova, size_t size,
arm_v7s_iopte blk_pte,
arm_v7s_iopte *ptep)
@@ -582,16 +627,16 @@ static size_t arm_v7s_split_blk_unmap(struct arm_v7s_io_pgtable *data,
if (!ARM_V7S_PTE_IS_TABLE(pte, 1))
return 0;
- tablep = iopte_deref(pte, 1);
- return __arm_v7s_unmap(data, iova, size, 2, tablep);
+ tablep = iopte_deref(pte, 1, data);
+ return __arm_v7s_unmap(data, gather, iova, size, 2, tablep);
}
- io_pgtable_tlb_add_flush(&data->iop, iova, size, size, true);
- io_pgtable_tlb_sync(&data->iop);
+ io_pgtable_tlb_add_page(&data->iop, gather, iova, size);
return size;
}
static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data,
+ struct iommu_iotlb_gather *gather,
unsigned long iova, size_t size, int lvl,
arm_v7s_iopte *ptep)
{
@@ -638,10 +683,9 @@ static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data,
for (i = 0; i < num_entries; i++) {
if (ARM_V7S_PTE_IS_TABLE(pte[i], lvl)) {
/* Also flush any partial walks */
- io_pgtable_tlb_add_flush(iop, iova, blk_size,
- ARM_V7S_BLOCK_SIZE(lvl + 1), false);
- io_pgtable_tlb_sync(iop);
- ptep = iopte_deref(pte[i], lvl);
+ io_pgtable_tlb_flush_walk(iop, iova, blk_size,
+ ARM_V7S_BLOCK_SIZE(lvl + 1));
+ ptep = iopte_deref(pte[i], lvl, data);
__arm_v7s_free_table(ptep, lvl + 1, data);
} else if (iop->cfg.quirks & IO_PGTABLE_QUIRK_NON_STRICT) {
/*
@@ -651,8 +695,7 @@ static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data,
*/
smp_wmb();
} else {
- io_pgtable_tlb_add_flush(iop, iova, blk_size,
- blk_size, true);
+ io_pgtable_tlb_add_page(iop, gather, iova, blk_size);
}
iova += blk_size;
}
@@ -662,23 +705,24 @@ static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data,
* Insert a table at the next level to map the old region,
* minus the part we want to unmap
*/
- return arm_v7s_split_blk_unmap(data, iova, size, pte[0], ptep);
+ return arm_v7s_split_blk_unmap(data, gather, iova, size, pte[0],
+ ptep);
}
/* Keep on walkin' */
- ptep = iopte_deref(pte[0], lvl);
- return __arm_v7s_unmap(data, iova, size, lvl + 1, ptep);
+ ptep = iopte_deref(pte[0], lvl, data);
+ return __arm_v7s_unmap(data, gather, iova, size, lvl + 1, ptep);
}
static size_t arm_v7s_unmap(struct io_pgtable_ops *ops, unsigned long iova,
- size_t size)
+ size_t size, struct iommu_iotlb_gather *gather)
{
struct arm_v7s_io_pgtable *data = io_pgtable_ops_to_data(ops);
if (WARN_ON(upper_32_bits(iova)))
return 0;
- return __arm_v7s_unmap(data, iova, size, 1, data->pgd);
+ return __arm_v7s_unmap(data, gather, iova, size, 1, data->pgd);
}
static phys_addr_t arm_v7s_iova_to_phys(struct io_pgtable_ops *ops,
@@ -692,7 +736,7 @@ static phys_addr_t arm_v7s_iova_to_phys(struct io_pgtable_ops *ops,
do {
ptep += ARM_V7S_LVL_IDX(iova, ++lvl);
pte = READ_ONCE(*ptep);
- ptep = iopte_deref(pte, lvl);
+ ptep = iopte_deref(pte, lvl, data);
} while (ARM_V7S_PTE_IS_TABLE(pte, lvl));
if (!ARM_V7S_PTE_IS_VALID(pte))
@@ -701,7 +745,7 @@ static phys_addr_t arm_v7s_iova_to_phys(struct io_pgtable_ops *ops,
mask = ARM_V7S_LVL_MASK(lvl);
if (arm_v7s_pte_is_cont(pte, lvl))
mask *= ARM_V7S_CONT_PAGES;
- return (pte & mask) | (iova & ~mask);
+ return iopte_to_paddr(pte, lvl, &data->iop.cfg) | (iova & ~mask);
}
static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
@@ -709,18 +753,21 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
{
struct arm_v7s_io_pgtable *data;
- if (cfg->ias > ARM_V7S_ADDR_BITS || cfg->oas > ARM_V7S_ADDR_BITS)
+ if (cfg->ias > ARM_V7S_ADDR_BITS)
+ return NULL;
+
+ if (cfg->oas > (arm_v7s_is_mtk_enabled(cfg) ? 34 : ARM_V7S_ADDR_BITS))
return NULL;
if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS |
IO_PGTABLE_QUIRK_NO_PERMS |
IO_PGTABLE_QUIRK_TLBI_ON_MAP |
- IO_PGTABLE_QUIRK_ARM_MTK_4GB |
+ IO_PGTABLE_QUIRK_ARM_MTK_EXT |
IO_PGTABLE_QUIRK_NON_STRICT))
return NULL;
/* If ARM_MTK_4GB is enabled, the NO_PERMS is also expected. */
- if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_4GB &&
+ if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_EXT &&
!(cfg->quirks & IO_PGTABLE_QUIRK_NO_PERMS))
return NULL;
@@ -806,22 +853,24 @@ static void dummy_tlb_flush_all(void *cookie)
WARN_ON(cookie != cfg_cookie);
}
-static void dummy_tlb_add_flush(unsigned long iova, size_t size,
- size_t granule, bool leaf, void *cookie)
+static void dummy_tlb_flush(unsigned long iova, size_t size, size_t granule,
+ void *cookie)
{
WARN_ON(cookie != cfg_cookie);
WARN_ON(!(size & cfg_cookie->pgsize_bitmap));
}
-static void dummy_tlb_sync(void *cookie)
+static void dummy_tlb_add_page(struct iommu_iotlb_gather *gather,
+ unsigned long iova, size_t granule, void *cookie)
{
- WARN_ON(cookie != cfg_cookie);
+ dummy_tlb_flush(iova, granule, granule, cookie);
}
-static const struct iommu_gather_ops dummy_tlb_ops = {
+static const struct iommu_flush_ops dummy_tlb_ops = {
.tlb_flush_all = dummy_tlb_flush_all,
- .tlb_add_flush = dummy_tlb_add_flush,
- .tlb_sync = dummy_tlb_sync,
+ .tlb_flush_walk = dummy_tlb_flush,
+ .tlb_flush_leaf = dummy_tlb_flush,
+ .tlb_add_page = dummy_tlb_add_page,
};
#define __FAIL(ops) ({ \
@@ -896,7 +945,7 @@ static int __init arm_v7s_do_selftests(void)
size = 1UL << __ffs(cfg.pgsize_bitmap);
while (i < loopnr) {
iova_start = i * SZ_16M;
- if (ops->unmap(ops, iova_start + size, size) != size)
+ if (ops->unmap(ops, iova_start + size, size, NULL) != size)
return __FAIL(ops);
/* Remap of partial unmap */
@@ -914,7 +963,7 @@ static int __init arm_v7s_do_selftests(void)
for_each_set_bit(i, &cfg.pgsize_bitmap, BITS_PER_LONG) {
size = 1UL << i;
- if (ops->unmap(ops, iova, size) != size)
+ if (ops->unmap(ops, iova, size, NULL) != size)
return __FAIL(ops);
if (ops->iova_to_phys(ops, iova + 42))
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 161a7d56264d..4c91359057c5 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -12,7 +12,6 @@
#include <linux/atomic.h>
#include <linux/bitops.h>
#include <linux/io-pgtable.h>
-#include <linux/iommu.h>
#include <linux/kernel.h>
#include <linux/sizes.h>
#include <linux/slab.h>
@@ -290,6 +289,7 @@ static void __arm_lpae_set_pte(arm_lpae_iopte *ptep, arm_lpae_iopte pte,
}
static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
+ struct iommu_iotlb_gather *gather,
unsigned long iova, size_t size, int lvl,
arm_lpae_iopte *ptep);
@@ -335,8 +335,10 @@ static int arm_lpae_init_pte(struct arm_lpae_io_pgtable *data,
size_t sz = ARM_LPAE_BLOCK_SIZE(lvl, data);
tblp = ptep - ARM_LPAE_LVL_IDX(iova, lvl, data);
- if (WARN_ON(__arm_lpae_unmap(data, iova, sz, lvl, tblp) != sz))
+ if (__arm_lpae_unmap(data, NULL, iova, sz, lvl, tblp) != sz) {
+ WARN_ON(1);
return -EINVAL;
+ }
}
__arm_lpae_init_pte(data, paddr, prot, lvl, ptep);
@@ -537,6 +539,7 @@ static void arm_lpae_free_pgtable(struct io_pgtable *iop)
}
static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
+ struct iommu_iotlb_gather *gather,
unsigned long iova, size_t size,
arm_lpae_iopte blk_pte, int lvl,
arm_lpae_iopte *ptep)
@@ -582,15 +585,15 @@ static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
tablep = iopte_deref(pte, data);
} else if (unmap_idx >= 0) {
- io_pgtable_tlb_add_flush(&data->iop, iova, size, size, true);
- io_pgtable_tlb_sync(&data->iop);
+ io_pgtable_tlb_add_page(&data->iop, gather, iova, size);
return size;
}
- return __arm_lpae_unmap(data, iova, size, lvl, tablep);
+ return __arm_lpae_unmap(data, gather, iova, size, lvl, tablep);
}
static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
+ struct iommu_iotlb_gather *gather,
unsigned long iova, size_t size, int lvl,
arm_lpae_iopte *ptep)
{
@@ -612,9 +615,8 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
if (!iopte_leaf(pte, lvl, iop->fmt)) {
/* Also flush any partial walks */
- io_pgtable_tlb_add_flush(iop, iova, size,
- ARM_LPAE_GRANULE(data), false);
- io_pgtable_tlb_sync(iop);
+ io_pgtable_tlb_flush_walk(iop, iova, size,
+ ARM_LPAE_GRANULE(data));
ptep = iopte_deref(pte, data);
__arm_lpae_free_pgtable(data, lvl + 1, ptep);
} else if (iop->cfg.quirks & IO_PGTABLE_QUIRK_NON_STRICT) {
@@ -625,7 +627,7 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
*/
smp_wmb();
} else {
- io_pgtable_tlb_add_flush(iop, iova, size, size, true);
+ io_pgtable_tlb_add_page(iop, gather, iova, size);
}
return size;
@@ -634,17 +636,17 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
* Insert a table at the next level to map the old region,
* minus the part we want to unmap
*/
- return arm_lpae_split_blk_unmap(data, iova, size, pte,
+ return arm_lpae_split_blk_unmap(data, gather, iova, size, pte,
lvl + 1, ptep);
}
/* Keep on walkin' */
ptep = iopte_deref(pte, data);
- return __arm_lpae_unmap(data, iova, size, lvl + 1, ptep);
+ return __arm_lpae_unmap(data, gather, iova, size, lvl + 1, ptep);
}
static size_t arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
- size_t size)
+ size_t size, struct iommu_iotlb_gather *gather)
{
struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
arm_lpae_iopte *ptep = data->pgd;
@@ -653,7 +655,7 @@ static size_t arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
if (WARN_ON(iova >= (1ULL << data->iop.cfg.ias)))
return 0;
- return __arm_lpae_unmap(data, iova, size, lvl, ptep);
+ return __arm_lpae_unmap(data, gather, iova, size, lvl, ptep);
}
static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops,
@@ -1070,22 +1072,24 @@ static void dummy_tlb_flush_all(void *cookie)
WARN_ON(cookie != cfg_cookie);
}
-static void dummy_tlb_add_flush(unsigned long iova, size_t size,
- size_t granule, bool leaf, void *cookie)
+static void dummy_tlb_flush(unsigned long iova, size_t size, size_t granule,
+ void *cookie)
{
WARN_ON(cookie != cfg_cookie);
WARN_ON(!(size & cfg_cookie->pgsize_bitmap));
}
-static void dummy_tlb_sync(void *cookie)
+static void dummy_tlb_add_page(struct iommu_iotlb_gather *gather,
+ unsigned long iova, size_t granule, void *cookie)
{
- WARN_ON(cookie != cfg_cookie);
+ dummy_tlb_flush(iova, granule, granule, cookie);
}
-static const struct iommu_gather_ops dummy_tlb_ops __initconst = {
+static const struct iommu_flush_ops dummy_tlb_ops __initconst = {
.tlb_flush_all = dummy_tlb_flush_all,
- .tlb_add_flush = dummy_tlb_add_flush,
- .tlb_sync = dummy_tlb_sync,
+ .tlb_flush_walk = dummy_tlb_flush,
+ .tlb_flush_leaf = dummy_tlb_flush,
+ .tlb_add_page = dummy_tlb_add_page,
};
static void __init arm_lpae_dump_ops(struct io_pgtable_ops *ops)
@@ -1168,7 +1172,7 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg)
/* Partial unmap */
size = 1UL << __ffs(cfg->pgsize_bitmap);
- if (ops->unmap(ops, SZ_1G + size, size) != size)
+ if (ops->unmap(ops, SZ_1G + size, size, NULL) != size)
return __FAIL(ops, i);
/* Remap of partial unmap */
@@ -1183,7 +1187,7 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg)
for_each_set_bit(j, &cfg->pgsize_bitmap, BITS_PER_LONG) {
size = 1UL << j;
- if (ops->unmap(ops, iova, size) != size)
+ if (ops->unmap(ops, iova, size, NULL) != size)
return __FAIL(ops, i);
if (ops->iova_to_phys(ops, iova + 42))
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 0c674d80c37f..d658c7c6a2ab 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -26,12 +26,10 @@
static struct kset *iommu_group_kset;
static DEFINE_IDA(iommu_group_ida);
-#ifdef CONFIG_IOMMU_DEFAULT_PASSTHROUGH
-static unsigned int iommu_def_domain_type = IOMMU_DOMAIN_IDENTITY;
-#else
-static unsigned int iommu_def_domain_type = IOMMU_DOMAIN_DMA;
-#endif
+
+static unsigned int iommu_def_domain_type __read_mostly;
static bool iommu_dma_strict __read_mostly = true;
+static u32 iommu_cmd_line __read_mostly;
struct iommu_group {
struct kobject kobj;
@@ -68,6 +66,18 @@ static const char * const iommu_group_resv_type_string[] = {
[IOMMU_RESV_SW_MSI] = "msi",
};
+#define IOMMU_CMD_LINE_DMA_API BIT(0)
+
+static void iommu_set_cmd_line_dma_api(void)
+{
+ iommu_cmd_line |= IOMMU_CMD_LINE_DMA_API;
+}
+
+static bool iommu_cmd_line_dma_api(void)
+{
+ return !!(iommu_cmd_line & IOMMU_CMD_LINE_DMA_API);
+}
+
#define IOMMU_GROUP_ATTR(_name, _mode, _show, _store) \
struct iommu_group_attribute iommu_group_attr_##_name = \
__ATTR(_name, _mode, _show, _store)
@@ -80,12 +90,55 @@ struct iommu_group_attribute iommu_group_attr_##_name = \
static LIST_HEAD(iommu_device_list);
static DEFINE_SPINLOCK(iommu_device_lock);
+/*
+ * Use a function instead of an array here because the domain-type is a
+ * bit-field, so an array would waste memory.
+ */
+static const char *iommu_domain_type_str(unsigned int t)
+{
+ switch (t) {
+ case IOMMU_DOMAIN_BLOCKED:
+ return "Blocked";
+ case IOMMU_DOMAIN_IDENTITY:
+ return "Passthrough";
+ case IOMMU_DOMAIN_UNMANAGED:
+ return "Unmanaged";
+ case IOMMU_DOMAIN_DMA:
+ return "Translated";
+ default:
+ return "Unknown";
+ }
+}
+
+static int __init iommu_subsys_init(void)
+{
+ bool cmd_line = iommu_cmd_line_dma_api();
+
+ if (!cmd_line) {
+ if (IS_ENABLED(CONFIG_IOMMU_DEFAULT_PASSTHROUGH))
+ iommu_set_default_passthrough(false);
+ else
+ iommu_set_default_translated(false);
+
+ if (iommu_default_passthrough() && mem_encrypt_active()) {
+ pr_info("Memory encryption detected - Disabling default IOMMU Passthrough\n");
+ iommu_set_default_translated(false);
+ }
+ }
+
+ pr_info("Default domain type: %s %s\n",
+ iommu_domain_type_str(iommu_def_domain_type),
+ cmd_line ? "(set via kernel command line)" : "");
+
+ return 0;
+}
+subsys_initcall(iommu_subsys_init);
+
int iommu_device_register(struct iommu_device *iommu)
{
spin_lock(&iommu_device_lock);
list_add_tail(&iommu->list, &iommu_device_list);
spin_unlock(&iommu_device_lock);
-
return 0;
}
@@ -165,7 +218,11 @@ static int __init iommu_set_def_domain_type(char *str)
if (ret)
return ret;
- iommu_def_domain_type = pt ? IOMMU_DOMAIN_IDENTITY : IOMMU_DOMAIN_DMA;
+ if (pt)
+ iommu_set_default_passthrough(true);
+ else
+ iommu_set_default_translated(true);
+
return 0;
}
early_param("iommu.passthrough", iommu_set_def_domain_type);
@@ -229,60 +286,58 @@ static ssize_t iommu_group_show_name(struct iommu_group *group, char *buf)
* @new: new region to insert
* @regions: list of regions
*
- * The new element is sorted by address with respect to the other
- * regions of the same type. In case it overlaps with another
- * region of the same type, regions are merged. In case it
- * overlaps with another region of different type, regions are
- * not merged.
+ * Elements are sorted by start address and overlapping segments
+ * of the same type are merged.
*/
-static int iommu_insert_resv_region(struct iommu_resv_region *new,
- struct list_head *regions)
+int iommu_insert_resv_region(struct iommu_resv_region *new,
+ struct list_head *regions)
{
- struct iommu_resv_region *region;
- phys_addr_t start = new->start;
- phys_addr_t end = new->start + new->length - 1;
- struct list_head *pos = regions->next;
-
- while (pos != regions) {
- struct iommu_resv_region *entry =
- list_entry(pos, struct iommu_resv_region, list);
- phys_addr_t a = entry->start;
- phys_addr_t b = entry->start + entry->length - 1;
- int type = entry->type;
-
- if (end < a) {
- goto insert;
- } else if (start > b) {
- pos = pos->next;
- } else if ((start >= a) && (end <= b)) {
- if (new->type == type)
- return 0;
- else
- pos = pos->next;
+ struct iommu_resv_region *iter, *tmp, *nr, *top;
+ LIST_HEAD(stack);
+
+ nr = iommu_alloc_resv_region(new->start, new->length,
+ new->prot, new->type);
+ if (!nr)
+ return -ENOMEM;
+
+ /* First add the new element based on start address sorting */
+ list_for_each_entry(iter, regions, list) {
+ if (nr->start < iter->start ||
+ (nr->start == iter->start && nr->type <= iter->type))
+ break;
+ }
+ list_add_tail(&nr->list, &iter->list);
+
+ /* Merge overlapping segments of type nr->type in @regions, if any */
+ list_for_each_entry_safe(iter, tmp, regions, list) {
+ phys_addr_t top_end, iter_end = iter->start + iter->length - 1;
+
+ /* no merge needed on elements of different types than @nr */
+ if (iter->type != nr->type) {
+ list_move_tail(&iter->list, &stack);
+ continue;
+ }
+
+ /* look for the last stack element of same type as @iter */
+ list_for_each_entry_reverse(top, &stack, list)
+ if (top->type == iter->type)
+ goto check_overlap;
+
+ list_move_tail(&iter->list, &stack);
+ continue;
+
+check_overlap:
+ top_end = top->start + top->length - 1;
+
+ if (iter->start > top_end + 1) {
+ list_move_tail(&iter->list, &stack);
} else {
- if (new->type == type) {
- phys_addr_t new_start = min(a, start);
- phys_addr_t new_end = max(b, end);
- int ret;
-
- list_del(&entry->list);
- entry->start = new_start;
- entry->length = new_end - new_start + 1;
- ret = iommu_insert_resv_region(entry, regions);
- kfree(entry);
- return ret;
- } else {
- pos = pos->next;
- }
+ top->length = max(top_end, iter_end) - top->start + 1;
+ list_del(&iter->list);
+ kfree(iter);
}
}
-insert:
- region = iommu_alloc_resv_region(new->start, new->length,
- new->prot, new->type);
- if (!region)
- return -ENOMEM;
-
- list_add_tail(&region->list, pos);
+ list_splice(&stack, regions);
return 0;
}
@@ -1862,7 +1917,7 @@ EXPORT_SYMBOL_GPL(iommu_map);
static size_t __iommu_unmap(struct iommu_domain *domain,
unsigned long iova, size_t size,
- bool sync)
+ struct iommu_iotlb_gather *iotlb_gather)
{
const struct iommu_ops *ops = domain->ops;
size_t unmapped_page, unmapped = 0;
@@ -1899,13 +1954,10 @@ static size_t __iommu_unmap(struct iommu_domain *domain,
while (unmapped < size) {
size_t pgsize = iommu_pgsize(domain, iova, size - unmapped);
- unmapped_page = ops->unmap(domain, iova, pgsize);
+ unmapped_page = ops->unmap(domain, iova, pgsize, iotlb_gather);
if (!unmapped_page)
break;
- if (sync && ops->iotlb_range_add)
- ops->iotlb_range_add(domain, iova, pgsize);
-
pr_debug("unmapped: iova 0x%lx size 0x%zx\n",
iova, unmapped_page);
@@ -1913,9 +1965,6 @@ static size_t __iommu_unmap(struct iommu_domain *domain,
unmapped += unmapped_page;
}
- if (sync && ops->iotlb_sync)
- ops->iotlb_sync(domain);
-
trace_unmap(orig_iova, size, unmapped);
return unmapped;
}
@@ -1923,14 +1972,22 @@ static size_t __iommu_unmap(struct iommu_domain *domain,
size_t iommu_unmap(struct iommu_domain *domain,
unsigned long iova, size_t size)
{
- return __iommu_unmap(domain, iova, size, true);
+ struct iommu_iotlb_gather iotlb_gather;
+ size_t ret;
+
+ iommu_iotlb_gather_init(&iotlb_gather);
+ ret = __iommu_unmap(domain, iova, size, &iotlb_gather);
+ iommu_tlb_sync(domain, &iotlb_gather);
+
+ return ret;
}
EXPORT_SYMBOL_GPL(iommu_unmap);
size_t iommu_unmap_fast(struct iommu_domain *domain,
- unsigned long iova, size_t size)
+ unsigned long iova, size_t size,
+ struct iommu_iotlb_gather *iotlb_gather)
{
- return __iommu_unmap(domain, iova, size, false);
+ return __iommu_unmap(domain, iova, size, iotlb_gather);
}
EXPORT_SYMBOL_GPL(iommu_unmap_fast);
@@ -2143,7 +2200,6 @@ request_default_domain_for_dev(struct device *dev, unsigned long type)
mutex_lock(&group->mutex);
- /* Check if the default domain is already direct mapped */
ret = 0;
if (group->default_domain && group->default_domain->type == type)
goto out;
@@ -2153,7 +2209,6 @@ request_default_domain_for_dev(struct device *dev, unsigned long type)
if (iommu_group_device_count(group) != 1)
goto out;
- /* Allocate a direct mapped domain */
ret = -ENOMEM;
domain = __iommu_domain_alloc(dev->bus, type);
if (!domain)
@@ -2168,7 +2223,7 @@ request_default_domain_for_dev(struct device *dev, unsigned long type)
iommu_group_create_direct_mappings(group, dev);
- /* Make the direct mapped domain the default for this group */
+ /* Make the domain the default for this group */
if (group->default_domain)
iommu_domain_free(group->default_domain);
group->default_domain = domain;
@@ -2196,6 +2251,28 @@ int iommu_request_dma_domain_for_dev(struct device *dev)
return request_default_domain_for_dev(dev, IOMMU_DOMAIN_DMA);
}
+void iommu_set_default_passthrough(bool cmd_line)
+{
+ if (cmd_line)
+ iommu_set_cmd_line_dma_api();
+
+ iommu_def_domain_type = IOMMU_DOMAIN_IDENTITY;
+}
+
+void iommu_set_default_translated(bool cmd_line)
+{
+ if (cmd_line)
+ iommu_set_cmd_line_dma_api();
+
+ iommu_def_domain_type = IOMMU_DOMAIN_DMA;
+}
+
+bool iommu_default_passthrough(void)
+{
+ return iommu_def_domain_type == IOMMU_DOMAIN_IDENTITY;
+}
+EXPORT_SYMBOL_GPL(iommu_default_passthrough);
+
const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode)
{
const struct iommu_ops *ops = NULL;
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index 3e1a8a675572..41c605b0058f 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -577,7 +577,9 @@ void queue_iova(struct iova_domain *iovad,
spin_unlock_irqrestore(&fq->lock, flags);
- if (atomic_cmpxchg(&iovad->fq_timer_on, 0, 1) == 0)
+ /* Avoid false sharing as much as possible. */
+ if (!atomic_read(&iovad->fq_timer_on) &&
+ !atomic_cmpxchg(&iovad->fq_timer_on, 0, 1))
mod_timer(&iovad->fq_timer,
jiffies + msecs_to_jiffies(IOVA_FQ_TIMEOUT));
}
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index ad0098c0c87c..9da8309f7170 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -49,6 +49,7 @@ struct ipmmu_features {
bool setup_imbuscr;
bool twobit_imttbcr_sl0;
bool reserved_context;
+ bool cache_snoop;
};
struct ipmmu_vmsa_device {
@@ -115,45 +116,44 @@ static struct ipmmu_vmsa_device *to_ipmmu(struct device *dev)
#define IMTTBCR 0x0008
#define IMTTBCR_EAE (1 << 31)
#define IMTTBCR_PMB (1 << 30)
-#define IMTTBCR_SH1_NON_SHAREABLE (0 << 28)
-#define IMTTBCR_SH1_OUTER_SHAREABLE (2 << 28)
-#define IMTTBCR_SH1_INNER_SHAREABLE (3 << 28)
-#define IMTTBCR_SH1_MASK (3 << 28)
-#define IMTTBCR_ORGN1_NC (0 << 26)
-#define IMTTBCR_ORGN1_WB_WA (1 << 26)
-#define IMTTBCR_ORGN1_WT (2 << 26)
-#define IMTTBCR_ORGN1_WB (3 << 26)
-#define IMTTBCR_ORGN1_MASK (3 << 26)
-#define IMTTBCR_IRGN1_NC (0 << 24)
-#define IMTTBCR_IRGN1_WB_WA (1 << 24)
-#define IMTTBCR_IRGN1_WT (2 << 24)
-#define IMTTBCR_IRGN1_WB (3 << 24)
-#define IMTTBCR_IRGN1_MASK (3 << 24)
+#define IMTTBCR_SH1_NON_SHAREABLE (0 << 28) /* R-Car Gen2 only */
+#define IMTTBCR_SH1_OUTER_SHAREABLE (2 << 28) /* R-Car Gen2 only */
+#define IMTTBCR_SH1_INNER_SHAREABLE (3 << 28) /* R-Car Gen2 only */
+#define IMTTBCR_SH1_MASK (3 << 28) /* R-Car Gen2 only */
+#define IMTTBCR_ORGN1_NC (0 << 26) /* R-Car Gen2 only */
+#define IMTTBCR_ORGN1_WB_WA (1 << 26) /* R-Car Gen2 only */
+#define IMTTBCR_ORGN1_WT (2 << 26) /* R-Car Gen2 only */
+#define IMTTBCR_ORGN1_WB (3 << 26) /* R-Car Gen2 only */
+#define IMTTBCR_ORGN1_MASK (3 << 26) /* R-Car Gen2 only */
+#define IMTTBCR_IRGN1_NC (0 << 24) /* R-Car Gen2 only */
+#define IMTTBCR_IRGN1_WB_WA (1 << 24) /* R-Car Gen2 only */
+#define IMTTBCR_IRGN1_WT (2 << 24) /* R-Car Gen2 only */
+#define IMTTBCR_IRGN1_WB (3 << 24) /* R-Car Gen2 only */
+#define IMTTBCR_IRGN1_MASK (3 << 24) /* R-Car Gen2 only */
#define IMTTBCR_TSZ1_MASK (7 << 16)
#define IMTTBCR_TSZ1_SHIFT 16
-#define IMTTBCR_SH0_NON_SHAREABLE (0 << 12)
-#define IMTTBCR_SH0_OUTER_SHAREABLE (2 << 12)
-#define IMTTBCR_SH0_INNER_SHAREABLE (3 << 12)
-#define IMTTBCR_SH0_MASK (3 << 12)
-#define IMTTBCR_ORGN0_NC (0 << 10)
-#define IMTTBCR_ORGN0_WB_WA (1 << 10)
-#define IMTTBCR_ORGN0_WT (2 << 10)
-#define IMTTBCR_ORGN0_WB (3 << 10)
-#define IMTTBCR_ORGN0_MASK (3 << 10)
-#define IMTTBCR_IRGN0_NC (0 << 8)
-#define IMTTBCR_IRGN0_WB_WA (1 << 8)
-#define IMTTBCR_IRGN0_WT (2 << 8)
-#define IMTTBCR_IRGN0_WB (3 << 8)
-#define IMTTBCR_IRGN0_MASK (3 << 8)
+#define IMTTBCR_SH0_NON_SHAREABLE (0 << 12) /* R-Car Gen2 only */
+#define IMTTBCR_SH0_OUTER_SHAREABLE (2 << 12) /* R-Car Gen2 only */
+#define IMTTBCR_SH0_INNER_SHAREABLE (3 << 12) /* R-Car Gen2 only */
+#define IMTTBCR_SH0_MASK (3 << 12) /* R-Car Gen2 only */
+#define IMTTBCR_ORGN0_NC (0 << 10) /* R-Car Gen2 only */
+#define IMTTBCR_ORGN0_WB_WA (1 << 10) /* R-Car Gen2 only */
+#define IMTTBCR_ORGN0_WT (2 << 10) /* R-Car Gen2 only */
+#define IMTTBCR_ORGN0_WB (3 << 10) /* R-Car Gen2 only */
+#define IMTTBCR_ORGN0_MASK (3 << 10) /* R-Car Gen2 only */
+#define IMTTBCR_IRGN0_NC (0 << 8) /* R-Car Gen2 only */
+#define IMTTBCR_IRGN0_WB_WA (1 << 8) /* R-Car Gen2 only */
+#define IMTTBCR_IRGN0_WT (2 << 8) /* R-Car Gen2 only */
+#define IMTTBCR_IRGN0_WB (3 << 8) /* R-Car Gen2 only */
+#define IMTTBCR_IRGN0_MASK (3 << 8) /* R-Car Gen2 only */
+#define IMTTBCR_SL0_TWOBIT_LVL_3 (0 << 6) /* R-Car Gen3 only */
+#define IMTTBCR_SL0_TWOBIT_LVL_2 (1 << 6) /* R-Car Gen3 only */
+#define IMTTBCR_SL0_TWOBIT_LVL_1 (2 << 6) /* R-Car Gen3 only */
#define IMTTBCR_SL0_LVL_2 (0 << 4)
#define IMTTBCR_SL0_LVL_1 (1 << 4)
#define IMTTBCR_TSZ0_MASK (7 << 0)
#define IMTTBCR_TSZ0_SHIFT O
-#define IMTTBCR_SL0_TWOBIT_LVL_3 (0 << 6)
-#define IMTTBCR_SL0_TWOBIT_LVL_2 (1 << 6)
-#define IMTTBCR_SL0_TWOBIT_LVL_1 (2 << 6)
-
#define IMBUSCR 0x000c
#define IMBUSCR_DVM (1 << 2)
#define IMBUSCR_BUSSEL_SYS (0 << 0)
@@ -361,16 +361,16 @@ static void ipmmu_tlb_flush_all(void *cookie)
ipmmu_tlb_invalidate(domain);
}
-static void ipmmu_tlb_add_flush(unsigned long iova, size_t size,
- size_t granule, bool leaf, void *cookie)
+static void ipmmu_tlb_flush(unsigned long iova, size_t size,
+ size_t granule, void *cookie)
{
- /* The hardware doesn't support selective TLB flush. */
+ ipmmu_tlb_flush_all(cookie);
}
-static const struct iommu_gather_ops ipmmu_gather_ops = {
+static const struct iommu_flush_ops ipmmu_flush_ops = {
.tlb_flush_all = ipmmu_tlb_flush_all,
- .tlb_add_flush = ipmmu_tlb_add_flush,
- .tlb_sync = ipmmu_tlb_flush_all,
+ .tlb_flush_walk = ipmmu_tlb_flush,
+ .tlb_flush_leaf = ipmmu_tlb_flush,
};
/* -----------------------------------------------------------------------------
@@ -422,17 +422,19 @@ static void ipmmu_domain_setup_context(struct ipmmu_vmsa_domain *domain)
/*
* TTBCR
- * We use long descriptors with inner-shareable WBWA tables and allocate
- * the whole 32-bit VA space to TTBR0.
+ * We use long descriptors and allocate the whole 32-bit VA space to
+ * TTBR0.
*/
if (domain->mmu->features->twobit_imttbcr_sl0)
tmp = IMTTBCR_SL0_TWOBIT_LVL_1;
else
tmp = IMTTBCR_SL0_LVL_1;
- ipmmu_ctx_write_root(domain, IMTTBCR, IMTTBCR_EAE |
- IMTTBCR_SH0_INNER_SHAREABLE | IMTTBCR_ORGN0_WB_WA |
- IMTTBCR_IRGN0_WB_WA | tmp);
+ if (domain->mmu->features->cache_snoop)
+ tmp |= IMTTBCR_SH0_INNER_SHAREABLE | IMTTBCR_ORGN0_WB_WA |
+ IMTTBCR_IRGN0_WB_WA;
+
+ ipmmu_ctx_write_root(domain, IMTTBCR, IMTTBCR_EAE | tmp);
/* MAIR0 */
ipmmu_ctx_write_root(domain, IMMAIR0,
@@ -480,7 +482,7 @@ static int ipmmu_domain_init_context(struct ipmmu_vmsa_domain *domain)
domain->cfg.pgsize_bitmap = SZ_1G | SZ_2M | SZ_4K;
domain->cfg.ias = 32;
domain->cfg.oas = 40;
- domain->cfg.tlb = &ipmmu_gather_ops;
+ domain->cfg.tlb = &ipmmu_flush_ops;
domain->io_domain.geometry.aperture_end = DMA_BIT_MASK(32);
domain->io_domain.geometry.force_aperture = true;
/*
@@ -733,14 +735,14 @@ static int ipmmu_map(struct iommu_domain *io_domain, unsigned long iova,
}
static size_t ipmmu_unmap(struct iommu_domain *io_domain, unsigned long iova,
- size_t size)
+ size_t size, struct iommu_iotlb_gather *gather)
{
struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
- return domain->iop->unmap(domain->iop, iova, size);
+ return domain->iop->unmap(domain->iop, iova, size, gather);
}
-static void ipmmu_iotlb_sync(struct iommu_domain *io_domain)
+static void ipmmu_flush_iotlb_all(struct iommu_domain *io_domain)
{
struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
@@ -748,6 +750,12 @@ static void ipmmu_iotlb_sync(struct iommu_domain *io_domain)
ipmmu_tlb_flush_all(domain);
}
+static void ipmmu_iotlb_sync(struct iommu_domain *io_domain,
+ struct iommu_iotlb_gather *gather)
+{
+ ipmmu_flush_iotlb_all(io_domain);
+}
+
static phys_addr_t ipmmu_iova_to_phys(struct iommu_domain *io_domain,
dma_addr_t iova)
{
@@ -957,7 +965,7 @@ static const struct iommu_ops ipmmu_ops = {
.detach_dev = ipmmu_detach_device,
.map = ipmmu_map,
.unmap = ipmmu_unmap,
- .flush_iotlb_all = ipmmu_iotlb_sync,
+ .flush_iotlb_all = ipmmu_flush_iotlb_all,
.iotlb_sync = ipmmu_iotlb_sync,
.iova_to_phys = ipmmu_iova_to_phys,
.add_device = ipmmu_add_device,
@@ -988,6 +996,7 @@ static const struct ipmmu_features ipmmu_features_default = {
.setup_imbuscr = true,
.twobit_imttbcr_sl0 = false,
.reserved_context = false,
+ .cache_snoop = true,
};
static const struct ipmmu_features ipmmu_features_rcar_gen3 = {
@@ -998,6 +1007,7 @@ static const struct ipmmu_features ipmmu_features_rcar_gen3 = {
.setup_imbuscr = false,
.twobit_imttbcr_sl0 = true,
.reserved_context = true,
+ .cache_snoop = false,
};
static const struct of_device_id ipmmu_of_ids[] = {
diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c
index b25e2eb9e038..be99d408cf35 100644
--- a/drivers/iommu/msm_iommu.c
+++ b/drivers/iommu/msm_iommu.c
@@ -168,20 +168,29 @@ fail:
return;
}
-static void __flush_iotlb_sync(void *cookie)
+static void __flush_iotlb_walk(unsigned long iova, size_t size,
+ size_t granule, void *cookie)
{
- /*
- * Nothing is needed here, the barrier to guarantee
- * completion of the tlb sync operation is implicitly
- * taken care when the iommu client does a writel before
- * kick starting the other master.
- */
+ __flush_iotlb_range(iova, size, granule, false, cookie);
+}
+
+static void __flush_iotlb_leaf(unsigned long iova, size_t size,
+ size_t granule, void *cookie)
+{
+ __flush_iotlb_range(iova, size, granule, true, cookie);
}
-static const struct iommu_gather_ops msm_iommu_gather_ops = {
+static void __flush_iotlb_page(struct iommu_iotlb_gather *gather,
+ unsigned long iova, size_t granule, void *cookie)
+{
+ __flush_iotlb_range(iova, granule, granule, true, cookie);
+}
+
+static const struct iommu_flush_ops msm_iommu_flush_ops = {
.tlb_flush_all = __flush_iotlb,
- .tlb_add_flush = __flush_iotlb_range,
- .tlb_sync = __flush_iotlb_sync,
+ .tlb_flush_walk = __flush_iotlb_walk,
+ .tlb_flush_leaf = __flush_iotlb_leaf,
+ .tlb_add_page = __flush_iotlb_page,
};
static int msm_iommu_alloc_ctx(unsigned long *map, int start, int end)
@@ -345,7 +354,7 @@ static int msm_iommu_domain_config(struct msm_priv *priv)
.pgsize_bitmap = msm_iommu_ops.pgsize_bitmap,
.ias = 32,
.oas = 32,
- .tlb = &msm_iommu_gather_ops,
+ .tlb = &msm_iommu_flush_ops,
.iommu_dev = priv->dev,
};
@@ -509,13 +518,13 @@ static int msm_iommu_map(struct iommu_domain *domain, unsigned long iova,
}
static size_t msm_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
- size_t len)
+ size_t len, struct iommu_iotlb_gather *gather)
{
struct msm_priv *priv = to_msm_priv(domain);
unsigned long flags;
spin_lock_irqsave(&priv->pgtlock, flags);
- len = priv->iop->unmap(priv->iop, iova, len);
+ len = priv->iop->unmap(priv->iop, iova, len, gather);
spin_unlock_irqrestore(&priv->pgtlock, flags);
return len;
@@ -691,6 +700,13 @@ static struct iommu_ops msm_iommu_ops = {
.detach_dev = msm_iommu_detach_dev,
.map = msm_iommu_map,
.unmap = msm_iommu_unmap,
+ /*
+ * Nothing is needed here, the barrier to guarantee
+ * completion of the tlb sync operation is implicitly
+ * taken care when the iommu client does a writel before
+ * kick starting the other master.
+ */
+ .iotlb_sync = NULL,
.iova_to_phys = msm_iommu_iova_to_phys,
.add_device = msm_iommu_add_device,
.remove_device = msm_iommu_remove_device,
@@ -750,7 +766,6 @@ static int msm_iommu_probe(struct platform_device *pdev)
iommu->irq = platform_get_irq(pdev, 0);
if (iommu->irq < 0) {
- dev_err(iommu->dev, "could not get iommu irq\n");
ret = -ENODEV;
goto fail;
}
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 82e4be4dfdaf..67a483c1a935 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -28,6 +28,7 @@
#include "mtk_iommu.h"
#define REG_MMU_PT_BASE_ADDR 0x000
+#define MMU_PT_ADDR_MASK GENMASK(31, 7)
#define REG_MMU_INVALIDATE 0x020
#define F_ALL_INVLD 0x2
@@ -44,12 +45,9 @@
#define REG_MMU_DCM_DIS 0x050
#define REG_MMU_CTRL_REG 0x110
+#define F_MMU_TF_PROT_TO_PROGRAM_ADDR (2 << 4)
#define F_MMU_PREFETCH_RT_REPLACE_MOD BIT(4)
-#define F_MMU_TF_PROTECT_SEL_SHIFT(data) \
- ((data)->m4u_plat == M4U_MT2712 ? 4 : 5)
-/* It's named by F_MMU_TF_PROT_SEL in mt2712. */
-#define F_MMU_TF_PROTECT_SEL(prot, data) \
- (((prot) & 0x3) << F_MMU_TF_PROTECT_SEL_SHIFT(data))
+#define F_MMU_TF_PROT_TO_PROGRAM_ADDR_MT8173 (2 << 5)
#define REG_MMU_IVRP_PADDR 0x114
@@ -66,26 +64,32 @@
#define F_INT_CLR_BIT BIT(12)
#define REG_MMU_INT_MAIN_CONTROL 0x124
-#define F_INT_TRANSLATION_FAULT BIT(0)
-#define F_INT_MAIN_MULTI_HIT_FAULT BIT(1)
-#define F_INT_INVALID_PA_FAULT BIT(2)
-#define F_INT_ENTRY_REPLACEMENT_FAULT BIT(3)
-#define F_INT_TLB_MISS_FAULT BIT(4)
-#define F_INT_MISS_TRANSACTION_FIFO_FAULT BIT(5)
-#define F_INT_PRETETCH_TRANSATION_FIFO_FAULT BIT(6)
+ /* mmu0 | mmu1 */
+#define F_INT_TRANSLATION_FAULT (BIT(0) | BIT(7))
+#define F_INT_MAIN_MULTI_HIT_FAULT (BIT(1) | BIT(8))
+#define F_INT_INVALID_PA_FAULT (BIT(2) | BIT(9))
+#define F_INT_ENTRY_REPLACEMENT_FAULT (BIT(3) | BIT(10))
+#define F_INT_TLB_MISS_FAULT (BIT(4) | BIT(11))
+#define F_INT_MISS_TRANSACTION_FIFO_FAULT (BIT(5) | BIT(12))
+#define F_INT_PRETETCH_TRANSATION_FIFO_FAULT (BIT(6) | BIT(13))
#define REG_MMU_CPE_DONE 0x12C
#define REG_MMU_FAULT_ST1 0x134
+#define F_REG_MMU0_FAULT_MASK GENMASK(6, 0)
+#define F_REG_MMU1_FAULT_MASK GENMASK(13, 7)
-#define REG_MMU_FAULT_VA 0x13c
+#define REG_MMU0_FAULT_VA 0x13c
#define F_MMU_FAULT_VA_WRITE_BIT BIT(1)
#define F_MMU_FAULT_VA_LAYER_BIT BIT(0)
-#define REG_MMU_INVLD_PA 0x140
-#define REG_MMU_INT_ID 0x150
-#define F_MMU0_INT_ID_LARB_ID(a) (((a) >> 7) & 0x7)
-#define F_MMU0_INT_ID_PORT_ID(a) (((a) >> 2) & 0x1f)
+#define REG_MMU0_INVLD_PA 0x140
+#define REG_MMU1_FAULT_VA 0x144
+#define REG_MMU1_INVLD_PA 0x148
+#define REG_MMU0_INT_ID 0x150
+#define REG_MMU1_INT_ID 0x154
+#define F_MMU_INT_ID_LARB_ID(a) (((a) >> 7) & 0x7)
+#define F_MMU_INT_ID_PORT_ID(a) (((a) >> 2) & 0x1f)
#define MTK_PROTECT_PA_ALIGN 128
@@ -107,6 +111,30 @@ struct mtk_iommu_domain {
static const struct iommu_ops mtk_iommu_ops;
+/*
+ * In M4U 4GB mode, the physical address is remapped as below:
+ *
+ * CPU Physical address:
+ * ====================
+ *
+ * 0 1G 2G 3G 4G 5G
+ * |---A---|---B---|---C---|---D---|---E---|
+ * +--I/O--+------------Memory-------------+
+ *
+ * IOMMU output physical address:
+ * =============================
+ *
+ * 4G 5G 6G 7G 8G
+ * |---E---|---B---|---C---|---D---|
+ * +------------Memory-------------+
+ *
+ * The Region 'A'(I/O) can NOT be mapped by M4U; For Region 'B'/'C'/'D', the
+ * bit32 of the CPU physical address always is needed to set, and for Region
+ * 'E', the CPU physical address keep as is.
+ * Additionally, The iommu consumers always use the CPU phyiscal address.
+ */
+#define MTK_IOMMU_4GB_MODE_REMAP_BASE 0x140000000UL
+
static LIST_HEAD(m4ulist); /* List all the M4U HWs */
#define for_each_m4u(data) list_for_each_entry(data, &m4ulist, list)
@@ -188,10 +216,32 @@ static void mtk_iommu_tlb_sync(void *cookie)
}
}
-static const struct iommu_gather_ops mtk_iommu_gather_ops = {
+static void mtk_iommu_tlb_flush_walk(unsigned long iova, size_t size,
+ size_t granule, void *cookie)
+{
+ mtk_iommu_tlb_add_flush_nosync(iova, size, granule, false, cookie);
+ mtk_iommu_tlb_sync(cookie);
+}
+
+static void mtk_iommu_tlb_flush_leaf(unsigned long iova, size_t size,
+ size_t granule, void *cookie)
+{
+ mtk_iommu_tlb_add_flush_nosync(iova, size, granule, true, cookie);
+ mtk_iommu_tlb_sync(cookie);
+}
+
+static void mtk_iommu_tlb_flush_page_nosync(struct iommu_iotlb_gather *gather,
+ unsigned long iova, size_t granule,
+ void *cookie)
+{
+ mtk_iommu_tlb_add_flush_nosync(iova, granule, granule, true, cookie);
+}
+
+static const struct iommu_flush_ops mtk_iommu_flush_ops = {
.tlb_flush_all = mtk_iommu_tlb_flush_all,
- .tlb_add_flush = mtk_iommu_tlb_add_flush_nosync,
- .tlb_sync = mtk_iommu_tlb_sync,
+ .tlb_flush_walk = mtk_iommu_tlb_flush_walk,
+ .tlb_flush_leaf = mtk_iommu_tlb_flush_leaf,
+ .tlb_add_page = mtk_iommu_tlb_flush_page_nosync,
};
static irqreturn_t mtk_iommu_isr(int irq, void *dev_id)
@@ -204,13 +254,21 @@ static irqreturn_t mtk_iommu_isr(int irq, void *dev_id)
/* Read error info from registers */
int_state = readl_relaxed(data->base + REG_MMU_FAULT_ST1);
- fault_iova = readl_relaxed(data->base + REG_MMU_FAULT_VA);
+ if (int_state & F_REG_MMU0_FAULT_MASK) {
+ regval = readl_relaxed(data->base + REG_MMU0_INT_ID);
+ fault_iova = readl_relaxed(data->base + REG_MMU0_FAULT_VA);
+ fault_pa = readl_relaxed(data->base + REG_MMU0_INVLD_PA);
+ } else {
+ regval = readl_relaxed(data->base + REG_MMU1_INT_ID);
+ fault_iova = readl_relaxed(data->base + REG_MMU1_FAULT_VA);
+ fault_pa = readl_relaxed(data->base + REG_MMU1_INVLD_PA);
+ }
layer = fault_iova & F_MMU_FAULT_VA_LAYER_BIT;
write = fault_iova & F_MMU_FAULT_VA_WRITE_BIT;
- fault_pa = readl_relaxed(data->base + REG_MMU_INVLD_PA);
- regval = readl_relaxed(data->base + REG_MMU_INT_ID);
- fault_larb = F_MMU0_INT_ID_LARB_ID(regval);
- fault_port = F_MMU0_INT_ID_PORT_ID(regval);
+ fault_larb = F_MMU_INT_ID_LARB_ID(regval);
+ fault_port = F_MMU_INT_ID_PORT_ID(regval);
+
+ fault_larb = data->plat_data->larbid_remap[fault_larb];
if (report_iommu_fault(&dom->domain, data->dev, fault_iova,
write ? IOMMU_FAULT_WRITE : IOMMU_FAULT_READ)) {
@@ -242,7 +300,7 @@ static void mtk_iommu_config(struct mtk_iommu_data *data,
for (i = 0; i < fwspec->num_ids; ++i) {
larbid = MTK_M4U_TO_LARB(fwspec->ids[i]);
portid = MTK_M4U_TO_PORT(fwspec->ids[i]);
- larb_mmu = &data->smi_imu.larb_imu[larbid];
+ larb_mmu = &data->larb_imu[larbid];
dev_dbg(dev, "%s iommu port: %d\n",
enable ? "enable" : "disable", portid);
@@ -263,17 +321,15 @@ static int mtk_iommu_domain_finalise(struct mtk_iommu_domain *dom)
dom->cfg = (struct io_pgtable_cfg) {
.quirks = IO_PGTABLE_QUIRK_ARM_NS |
IO_PGTABLE_QUIRK_NO_PERMS |
- IO_PGTABLE_QUIRK_TLBI_ON_MAP,
+ IO_PGTABLE_QUIRK_TLBI_ON_MAP |
+ IO_PGTABLE_QUIRK_ARM_MTK_EXT,
.pgsize_bitmap = mtk_iommu_ops.pgsize_bitmap,
.ias = 32,
- .oas = 32,
- .tlb = &mtk_iommu_gather_ops,
+ .oas = 34,
+ .tlb = &mtk_iommu_flush_ops,
.iommu_dev = data->dev,
};
- if (data->enable_4GB)
- dom->cfg.quirks |= IO_PGTABLE_QUIRK_ARM_MTK_4GB;
-
dom->iop = alloc_io_pgtable_ops(ARM_V7S, &dom->cfg, data);
if (!dom->iop) {
dev_err(data->dev, "Failed to alloc io pgtable\n");
@@ -336,7 +392,7 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain,
/* Update the pgtable base address register of the M4U HW */
if (!data->m4u_dom) {
data->m4u_dom = dom;
- writel(dom->cfg.arm_v7s_cfg.ttbr[0],
+ writel(dom->cfg.arm_v7s_cfg.ttbr[0] & MMU_PT_ADDR_MASK,
data->base + REG_MMU_PT_BASE_ADDR);
}
@@ -359,32 +415,43 @@ static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova,
phys_addr_t paddr, size_t size, int prot)
{
struct mtk_iommu_domain *dom = to_mtk_domain(domain);
+ struct mtk_iommu_data *data = mtk_iommu_get_m4u_data();
unsigned long flags;
int ret;
+ /* The "4GB mode" M4U physically can not use the lower remap of Dram. */
+ if (data->enable_4GB)
+ paddr |= BIT_ULL(32);
+
spin_lock_irqsave(&dom->pgtlock, flags);
- ret = dom->iop->map(dom->iop, iova, paddr & DMA_BIT_MASK(32),
- size, prot);
+ ret = dom->iop->map(dom->iop, iova, paddr, size, prot);
spin_unlock_irqrestore(&dom->pgtlock, flags);
return ret;
}
static size_t mtk_iommu_unmap(struct iommu_domain *domain,
- unsigned long iova, size_t size)
+ unsigned long iova, size_t size,
+ struct iommu_iotlb_gather *gather)
{
struct mtk_iommu_domain *dom = to_mtk_domain(domain);
unsigned long flags;
size_t unmapsz;
spin_lock_irqsave(&dom->pgtlock, flags);
- unmapsz = dom->iop->unmap(dom->iop, iova, size);
+ unmapsz = dom->iop->unmap(dom->iop, iova, size, gather);
spin_unlock_irqrestore(&dom->pgtlock, flags);
return unmapsz;
}
-static void mtk_iommu_iotlb_sync(struct iommu_domain *domain)
+static void mtk_iommu_flush_iotlb_all(struct iommu_domain *domain)
+{
+ mtk_iommu_tlb_sync(mtk_iommu_get_m4u_data());
+}
+
+static void mtk_iommu_iotlb_sync(struct iommu_domain *domain,
+ struct iommu_iotlb_gather *gather)
{
mtk_iommu_tlb_sync(mtk_iommu_get_m4u_data());
}
@@ -401,8 +468,8 @@ static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
pa = dom->iop->iova_to_phys(dom->iop, iova);
spin_unlock_irqrestore(&dom->pgtlock, flags);
- if (data->enable_4GB)
- pa |= BIT_ULL(32);
+ if (data->enable_4GB && pa >= MTK_IOMMU_4GB_MODE_REMAP_BASE)
+ pa &= ~BIT_ULL(32);
return pa;
}
@@ -490,7 +557,7 @@ static const struct iommu_ops mtk_iommu_ops = {
.detach_dev = mtk_iommu_detach_device,
.map = mtk_iommu_map,
.unmap = mtk_iommu_unmap,
- .flush_iotlb_all = mtk_iommu_iotlb_sync,
+ .flush_iotlb_all = mtk_iommu_flush_iotlb_all,
.iotlb_sync = mtk_iommu_iotlb_sync,
.iova_to_phys = mtk_iommu_iova_to_phys,
.add_device = mtk_iommu_add_device,
@@ -511,9 +578,11 @@ static int mtk_iommu_hw_init(const struct mtk_iommu_data *data)
return ret;
}
- regval = F_MMU_TF_PROTECT_SEL(2, data);
- if (data->m4u_plat == M4U_MT8173)
- regval |= F_MMU_PREFETCH_RT_REPLACE_MOD;
+ if (data->plat_data->m4u_plat == M4U_MT8173)
+ regval = F_MMU_PREFETCH_RT_REPLACE_MOD |
+ F_MMU_TF_PROT_TO_PROGRAM_ADDR_MT8173;
+ else
+ regval = F_MMU_TF_PROT_TO_PROGRAM_ADDR;
writel_relaxed(regval, data->base + REG_MMU_CTRL_REG);
regval = F_L2_MULIT_HIT_EN |
@@ -533,14 +602,14 @@ static int mtk_iommu_hw_init(const struct mtk_iommu_data *data)
F_INT_PRETETCH_TRANSATION_FIFO_FAULT;
writel_relaxed(regval, data->base + REG_MMU_INT_MAIN_CONTROL);
- if (data->m4u_plat == M4U_MT8173)
+ if (data->plat_data->m4u_plat == M4U_MT8173)
regval = (data->protect_base >> 1) | (data->enable_4GB << 31);
else
regval = lower_32_bits(data->protect_base) |
upper_32_bits(data->protect_base);
writel_relaxed(regval, data->base + REG_MMU_IVRP_PADDR);
- if (data->enable_4GB && data->m4u_plat != M4U_MT8173) {
+ if (data->enable_4GB && data->plat_data->has_vld_pa_rng) {
/*
* If 4GB mode is enabled, the validate PA range is from
* 0x1_0000_0000 to 0x1_ffff_ffff. here record bit[32:30].
@@ -550,8 +619,7 @@ static int mtk_iommu_hw_init(const struct mtk_iommu_data *data)
}
writel_relaxed(0, data->base + REG_MMU_DCM_DIS);
- /* It's MISC control register whose default value is ok except mt8173.*/
- if (data->m4u_plat == M4U_MT8173)
+ if (data->plat_data->reset_axi)
writel_relaxed(0, data->base + REG_MMU_STANDARD_AXI_MODE);
if (devm_request_irq(data->dev, data->irq, mtk_iommu_isr, 0,
@@ -584,7 +652,7 @@ static int mtk_iommu_probe(struct platform_device *pdev)
if (!data)
return -ENOMEM;
data->dev = dev;
- data->m4u_plat = (enum mtk_iommu_plat)of_device_get_match_data(dev);
+ data->plat_data = of_device_get_match_data(dev);
/* Protect memory. HW will access here while translation fault.*/
protect = devm_kzalloc(dev, MTK_PROTECT_PA_ALIGN * 2, GFP_KERNEL);
@@ -594,6 +662,8 @@ static int mtk_iommu_probe(struct platform_device *pdev)
/* Whether the current dram is over 4GB */
data->enable_4GB = !!(max_pfn > (BIT_ULL(32) >> PAGE_SHIFT));
+ if (!data->plat_data->has_4gb_mode)
+ data->enable_4GB = false;
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
data->base = devm_ioremap_resource(dev, res);
@@ -605,15 +675,16 @@ static int mtk_iommu_probe(struct platform_device *pdev)
if (data->irq < 0)
return data->irq;
- data->bclk = devm_clk_get(dev, "bclk");
- if (IS_ERR(data->bclk))
- return PTR_ERR(data->bclk);
+ if (data->plat_data->has_bclk) {
+ data->bclk = devm_clk_get(dev, "bclk");
+ if (IS_ERR(data->bclk))
+ return PTR_ERR(data->bclk);
+ }
larb_nr = of_count_phandle_with_args(dev->of_node,
"mediatek,larbs", NULL);
if (larb_nr < 0)
return larb_nr;
- data->smi_imu.larb_nr = larb_nr;
for (i = 0; i < larb_nr; i++) {
struct device_node *larbnode;
@@ -638,7 +709,7 @@ static int mtk_iommu_probe(struct platform_device *pdev)
of_node_put(larbnode);
return -EPROBE_DEFER;
}
- data->smi_imu.larb_imu[id].dev = &plarbdev->dev;
+ data->larb_imu[id].dev = &plarbdev->dev;
component_match_add_release(dev, &match, release_of,
compare_of, larbnode);
@@ -699,6 +770,7 @@ static int __maybe_unused mtk_iommu_suspend(struct device *dev)
reg->int_control0 = readl_relaxed(base + REG_MMU_INT_CONTROL0);
reg->int_main_control = readl_relaxed(base + REG_MMU_INT_MAIN_CONTROL);
reg->ivrp_paddr = readl_relaxed(base + REG_MMU_IVRP_PADDR);
+ reg->vld_pa_rng = readl_relaxed(base + REG_MMU_VLD_PA_RNG);
clk_disable_unprepare(data->bclk);
return 0;
}
@@ -707,6 +779,7 @@ static int __maybe_unused mtk_iommu_resume(struct device *dev)
{
struct mtk_iommu_data *data = dev_get_drvdata(dev);
struct mtk_iommu_suspend_reg *reg = &data->reg;
+ struct mtk_iommu_domain *m4u_dom = data->m4u_dom;
void __iomem *base = data->base;
int ret;
@@ -722,8 +795,9 @@ static int __maybe_unused mtk_iommu_resume(struct device *dev)
writel_relaxed(reg->int_control0, base + REG_MMU_INT_CONTROL0);
writel_relaxed(reg->int_main_control, base + REG_MMU_INT_MAIN_CONTROL);
writel_relaxed(reg->ivrp_paddr, base + REG_MMU_IVRP_PADDR);
- if (data->m4u_dom)
- writel(data->m4u_dom->cfg.arm_v7s_cfg.ttbr[0],
+ writel_relaxed(reg->vld_pa_rng, base + REG_MMU_VLD_PA_RNG);
+ if (m4u_dom)
+ writel(m4u_dom->cfg.arm_v7s_cfg.ttbr[0] & MMU_PT_ADDR_MASK,
base + REG_MMU_PT_BASE_ADDR);
return 0;
}
@@ -732,9 +806,32 @@ static const struct dev_pm_ops mtk_iommu_pm_ops = {
SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(mtk_iommu_suspend, mtk_iommu_resume)
};
+static const struct mtk_iommu_plat_data mt2712_data = {
+ .m4u_plat = M4U_MT2712,
+ .has_4gb_mode = true,
+ .has_bclk = true,
+ .has_vld_pa_rng = true,
+ .larbid_remap = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9},
+};
+
+static const struct mtk_iommu_plat_data mt8173_data = {
+ .m4u_plat = M4U_MT8173,
+ .has_4gb_mode = true,
+ .has_bclk = true,
+ .reset_axi = true,
+ .larbid_remap = {0, 1, 2, 3, 4, 5}, /* Linear mapping. */
+};
+
+static const struct mtk_iommu_plat_data mt8183_data = {
+ .m4u_plat = M4U_MT8183,
+ .reset_axi = true,
+ .larbid_remap = {0, 4, 5, 6, 7, 2, 3, 1},
+};
+
static const struct of_device_id mtk_iommu_of_ids[] = {
- { .compatible = "mediatek,mt2712-m4u", .data = (void *)M4U_MT2712},
- { .compatible = "mediatek,mt8173-m4u", .data = (void *)M4U_MT8173},
+ { .compatible = "mediatek,mt2712-m4u", .data = &mt2712_data},
+ { .compatible = "mediatek,mt8173-m4u", .data = &mt8173_data},
+ { .compatible = "mediatek,mt8183-m4u", .data = &mt8183_data},
{}
};
diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h
index 59337323db58..fc0f16eabacd 100644
--- a/drivers/iommu/mtk_iommu.h
+++ b/drivers/iommu/mtk_iommu.h
@@ -24,12 +24,25 @@ struct mtk_iommu_suspend_reg {
u32 int_control0;
u32 int_main_control;
u32 ivrp_paddr;
+ u32 vld_pa_rng;
};
enum mtk_iommu_plat {
M4U_MT2701,
M4U_MT2712,
M4U_MT8173,
+ M4U_MT8183,
+};
+
+struct mtk_iommu_plat_data {
+ enum mtk_iommu_plat m4u_plat;
+ bool has_4gb_mode;
+
+ /* HW will use the EMI clock if there isn't the "bclk". */
+ bool has_bclk;
+ bool has_vld_pa_rng;
+ bool reset_axi;
+ unsigned char larbid_remap[MTK_LARB_NR_MAX];
};
struct mtk_iommu_domain;
@@ -43,14 +56,14 @@ struct mtk_iommu_data {
struct mtk_iommu_suspend_reg reg;
struct mtk_iommu_domain *m4u_dom;
struct iommu_group *m4u_group;
- struct mtk_smi_iommu smi_imu; /* SMI larb iommu info */
bool enable_4GB;
bool tlb_flush_active;
struct iommu_device iommu;
- enum mtk_iommu_plat m4u_plat;
+ const struct mtk_iommu_plat_data *plat_data;
struct list_head list;
+ struct mtk_smi_larb_iommu larb_imu[MTK_LARB_NR_MAX];
};
static inline int compare_of(struct device *dev, void *data)
@@ -67,14 +80,14 @@ static inline int mtk_iommu_bind(struct device *dev)
{
struct mtk_iommu_data *data = dev_get_drvdata(dev);
- return component_bind_all(dev, &data->smi_imu);
+ return component_bind_all(dev, &data->larb_imu);
}
static inline void mtk_iommu_unbind(struct device *dev)
{
struct mtk_iommu_data *data = dev_get_drvdata(dev);
- component_unbind_all(dev, &data->smi_imu);
+ component_unbind_all(dev, &data->larb_imu);
}
#endif
diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c
index abeeac488372..210b1c7c0bda 100644
--- a/drivers/iommu/mtk_iommu_v1.c
+++ b/drivers/iommu/mtk_iommu_v1.c
@@ -206,7 +206,7 @@ static void mtk_iommu_config(struct mtk_iommu_data *data,
for (i = 0; i < fwspec->num_ids; ++i) {
larbid = mt2701_m4u_to_larb(fwspec->ids[i]);
portid = mt2701_m4u_to_port(fwspec->ids[i]);
- larb_mmu = &data->smi_imu.larb_imu[larbid];
+ larb_mmu = &data->larb_imu[larbid];
dev_dbg(dev, "%s iommu port: %d\n",
enable ? "enable" : "disable", portid);
@@ -324,7 +324,8 @@ static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova,
}
static size_t mtk_iommu_unmap(struct iommu_domain *domain,
- unsigned long iova, size_t size)
+ unsigned long iova, size_t size,
+ struct iommu_iotlb_gather *gather)
{
struct mtk_iommu_domain *dom = to_mtk_domain(domain);
unsigned long flags;
@@ -610,14 +611,12 @@ static int mtk_iommu_probe(struct platform_device *pdev)
}
}
- data->smi_imu.larb_imu[larb_nr].dev = &plarbdev->dev;
+ data->larb_imu[larb_nr].dev = &plarbdev->dev;
component_match_add_release(dev, &match, release_of,
compare_of, larb_spec.np);
larb_nr++;
}
- data->smi_imu.larb_nr = larb_nr;
-
platform_set_drvdata(pdev, data);
ret = mtk_iommu_hw_init(data);
diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c
index dfb961d8c21b..09c6e1c680db 100644
--- a/drivers/iommu/omap-iommu.c
+++ b/drivers/iommu/omap-iommu.c
@@ -35,6 +35,15 @@
static const struct iommu_ops omap_iommu_ops;
+struct orphan_dev {
+ struct device *dev;
+ struct list_head node;
+};
+
+static LIST_HEAD(orphan_dev_list);
+
+static DEFINE_SPINLOCK(orphan_lock);
+
#define to_iommu(dev) ((struct omap_iommu *)dev_get_drvdata(dev))
/* bitmap of the page sizes currently supported */
@@ -53,6 +62,8 @@ static const struct iommu_ops omap_iommu_ops;
static struct platform_driver omap_iommu_driver;
static struct kmem_cache *iopte_cachep;
+static int _omap_iommu_add_device(struct device *dev);
+
/**
* to_omap_domain - Get struct omap_iommu_domain from generic iommu_domain
* @dom: generic iommu domain handle
@@ -65,6 +76,9 @@ static struct omap_iommu_domain *to_omap_domain(struct iommu_domain *dom)
/**
* omap_iommu_save_ctx - Save registers for pm off-mode support
* @dev: client device
+ *
+ * This should be treated as an deprecated API. It is preserved only
+ * to maintain existing functionality for OMAP3 ISP driver.
**/
void omap_iommu_save_ctx(struct device *dev)
{
@@ -92,6 +106,9 @@ EXPORT_SYMBOL_GPL(omap_iommu_save_ctx);
/**
* omap_iommu_restore_ctx - Restore registers for pm off-mode support
* @dev: client device
+ *
+ * This should be treated as an deprecated API. It is preserved only
+ * to maintain existing functionality for OMAP3 ISP driver.
**/
void omap_iommu_restore_ctx(struct device *dev)
{
@@ -186,36 +203,18 @@ static void omap2_iommu_disable(struct omap_iommu *obj)
static int iommu_enable(struct omap_iommu *obj)
{
- int err;
- struct platform_device *pdev = to_platform_device(obj->dev);
- struct iommu_platform_data *pdata = dev_get_platdata(&pdev->dev);
-
- if (pdata && pdata->deassert_reset) {
- err = pdata->deassert_reset(pdev, pdata->reset_name);
- if (err) {
- dev_err(obj->dev, "deassert_reset failed: %d\n", err);
- return err;
- }
- }
-
- pm_runtime_get_sync(obj->dev);
+ int ret;
- err = omap2_iommu_enable(obj);
+ ret = pm_runtime_get_sync(obj->dev);
+ if (ret < 0)
+ pm_runtime_put_noidle(obj->dev);
- return err;
+ return ret < 0 ? ret : 0;
}
static void iommu_disable(struct omap_iommu *obj)
{
- struct platform_device *pdev = to_platform_device(obj->dev);
- struct iommu_platform_data *pdata = dev_get_platdata(&pdev->dev);
-
- omap2_iommu_disable(obj);
-
pm_runtime_put_sync(obj->dev);
-
- if (pdata && pdata->assert_reset)
- pdata->assert_reset(pdev, pdata->reset_name);
}
/*
@@ -901,15 +900,219 @@ static void omap_iommu_detach(struct omap_iommu *obj)
dma_unmap_single(obj->dev, obj->pd_dma, IOPGD_TABLE_SIZE,
DMA_TO_DEVICE);
- iommu_disable(obj);
obj->pd_dma = 0;
obj->iopgd = NULL;
+ iommu_disable(obj);
spin_unlock(&obj->iommu_lock);
dev_dbg(obj->dev, "%s: %s\n", __func__, obj->name);
}
+static void omap_iommu_save_tlb_entries(struct omap_iommu *obj)
+{
+ struct iotlb_lock lock;
+ struct cr_regs cr;
+ struct cr_regs *tmp;
+ int i;
+
+ /* check if there are any locked tlbs to save */
+ iotlb_lock_get(obj, &lock);
+ obj->num_cr_ctx = lock.base;
+ if (!obj->num_cr_ctx)
+ return;
+
+ tmp = obj->cr_ctx;
+ for_each_iotlb_cr(obj, obj->num_cr_ctx, i, cr)
+ * tmp++ = cr;
+}
+
+static void omap_iommu_restore_tlb_entries(struct omap_iommu *obj)
+{
+ struct iotlb_lock l;
+ struct cr_regs *tmp;
+ int i;
+
+ /* no locked tlbs to restore */
+ if (!obj->num_cr_ctx)
+ return;
+
+ l.base = 0;
+ tmp = obj->cr_ctx;
+ for (i = 0; i < obj->num_cr_ctx; i++, tmp++) {
+ l.vict = i;
+ iotlb_lock_set(obj, &l);
+ iotlb_load_cr(obj, tmp);
+ }
+ l.base = obj->num_cr_ctx;
+ l.vict = i;
+ iotlb_lock_set(obj, &l);
+}
+
+/**
+ * omap_iommu_domain_deactivate - deactivate attached iommu devices
+ * @domain: iommu domain attached to the target iommu device
+ *
+ * This API allows the client devices of IOMMU devices to suspend
+ * the IOMMUs they control at runtime, after they are idled and
+ * suspended all activity. System Suspend will leverage the PM
+ * driver late callbacks.
+ **/
+int omap_iommu_domain_deactivate(struct iommu_domain *domain)
+{
+ struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
+ struct omap_iommu_device *iommu;
+ struct omap_iommu *oiommu;
+ int i;
+
+ if (!omap_domain->dev)
+ return 0;
+
+ iommu = omap_domain->iommus;
+ iommu += (omap_domain->num_iommus - 1);
+ for (i = 0; i < omap_domain->num_iommus; i++, iommu--) {
+ oiommu = iommu->iommu_dev;
+ pm_runtime_put_sync(oiommu->dev);
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(omap_iommu_domain_deactivate);
+
+/**
+ * omap_iommu_domain_activate - activate attached iommu devices
+ * @domain: iommu domain attached to the target iommu device
+ *
+ * This API allows the client devices of IOMMU devices to resume the
+ * IOMMUs they control at runtime, before they can resume operations.
+ * System Resume will leverage the PM driver late callbacks.
+ **/
+int omap_iommu_domain_activate(struct iommu_domain *domain)
+{
+ struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
+ struct omap_iommu_device *iommu;
+ struct omap_iommu *oiommu;
+ int i;
+
+ if (!omap_domain->dev)
+ return 0;
+
+ iommu = omap_domain->iommus;
+ for (i = 0; i < omap_domain->num_iommus; i++, iommu++) {
+ oiommu = iommu->iommu_dev;
+ pm_runtime_get_sync(oiommu->dev);
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(omap_iommu_domain_activate);
+
+/**
+ * omap_iommu_runtime_suspend - disable an iommu device
+ * @dev: iommu device
+ *
+ * This function performs all that is necessary to disable an
+ * IOMMU device, either during final detachment from a client
+ * device, or during system/runtime suspend of the device. This
+ * includes programming all the appropriate IOMMU registers, and
+ * managing the associated omap_hwmod's state and the device's
+ * reset line. This function also saves the context of any
+ * locked TLBs if suspending.
+ **/
+static __maybe_unused int omap_iommu_runtime_suspend(struct device *dev)
+{
+ struct platform_device *pdev = to_platform_device(dev);
+ struct iommu_platform_data *pdata = dev_get_platdata(dev);
+ struct omap_iommu *obj = to_iommu(dev);
+ int ret;
+
+ /* save the TLBs only during suspend, and not for power down */
+ if (obj->domain && obj->iopgd)
+ omap_iommu_save_tlb_entries(obj);
+
+ omap2_iommu_disable(obj);
+
+ if (pdata && pdata->device_idle)
+ pdata->device_idle(pdev);
+
+ if (pdata && pdata->assert_reset)
+ pdata->assert_reset(pdev, pdata->reset_name);
+
+ if (pdata && pdata->set_pwrdm_constraint) {
+ ret = pdata->set_pwrdm_constraint(pdev, false, &obj->pwrst);
+ if (ret) {
+ dev_warn(obj->dev, "pwrdm_constraint failed to be reset, status = %d\n",
+ ret);
+ }
+ }
+
+ return 0;
+}
+
+/**
+ * omap_iommu_runtime_resume - enable an iommu device
+ * @dev: iommu device
+ *
+ * This function performs all that is necessary to enable an
+ * IOMMU device, either during initial attachment to a client
+ * device, or during system/runtime resume of the device. This
+ * includes programming all the appropriate IOMMU registers, and
+ * managing the associated omap_hwmod's state and the device's
+ * reset line. The function also restores any locked TLBs if
+ * resuming after a suspend.
+ **/
+static __maybe_unused int omap_iommu_runtime_resume(struct device *dev)
+{
+ struct platform_device *pdev = to_platform_device(dev);
+ struct iommu_platform_data *pdata = dev_get_platdata(dev);
+ struct omap_iommu *obj = to_iommu(dev);
+ int ret = 0;
+
+ if (pdata && pdata->set_pwrdm_constraint) {
+ ret = pdata->set_pwrdm_constraint(pdev, true, &obj->pwrst);
+ if (ret) {
+ dev_warn(obj->dev, "pwrdm_constraint failed to be set, status = %d\n",
+ ret);
+ }
+ }
+
+ if (pdata && pdata->deassert_reset) {
+ ret = pdata->deassert_reset(pdev, pdata->reset_name);
+ if (ret) {
+ dev_err(dev, "deassert_reset failed: %d\n", ret);
+ return ret;
+ }
+ }
+
+ if (pdata && pdata->device_enable)
+ pdata->device_enable(pdev);
+
+ /* restore the TLBs only during resume, and not for power up */
+ if (obj->domain)
+ omap_iommu_restore_tlb_entries(obj);
+
+ ret = omap2_iommu_enable(obj);
+
+ return ret;
+}
+
+/**
+ * omap_iommu_suspend_prepare - prepare() dev_pm_ops implementation
+ * @dev: iommu device
+ *
+ * This function performs the necessary checks to determine if the IOMMU
+ * device needs suspending or not. The function checks if the runtime_pm
+ * status of the device is suspended, and returns 1 in that case. This
+ * results in the PM core to skip invoking any of the Sleep PM callbacks
+ * (suspend, suspend_late, resume, resume_early etc).
+ */
+static int omap_iommu_prepare(struct device *dev)
+{
+ if (pm_runtime_status_suspended(dev))
+ return 1;
+ return 0;
+}
+
static bool omap_iommu_can_register(struct platform_device *pdev)
{
struct device_node *np = pdev->dev.of_node;
@@ -974,6 +1177,7 @@ static int omap_iommu_probe(struct platform_device *pdev)
struct omap_iommu *obj;
struct resource *res;
struct device_node *of = pdev->dev.of_node;
+ struct orphan_dev *orphan_dev, *tmp;
if (!of) {
pr_err("%s: only DT-based devices are supported\n", __func__);
@@ -984,6 +1188,15 @@ static int omap_iommu_probe(struct platform_device *pdev)
if (!obj)
return -ENOMEM;
+ /*
+ * self-manage the ordering dependencies between omap_device_enable/idle
+ * and omap_device_assert/deassert_hardreset API
+ */
+ if (pdev->dev.pm_domain) {
+ dev_dbg(&pdev->dev, "device pm_domain is being reset\n");
+ pdev->dev.pm_domain = NULL;
+ }
+
obj->name = dev_name(&pdev->dev);
obj->nr_tlb_entries = 32;
err = of_property_read_u32(of, "ti,#tlb-entries", &obj->nr_tlb_entries);
@@ -996,6 +1209,11 @@ static int omap_iommu_probe(struct platform_device *pdev)
obj->dev = &pdev->dev;
obj->ctx = (void *)obj + sizeof(*obj);
+ obj->cr_ctx = devm_kzalloc(&pdev->dev,
+ sizeof(*obj->cr_ctx) * obj->nr_tlb_entries,
+ GFP_KERNEL);
+ if (!obj->cr_ctx)
+ return -ENOMEM;
spin_lock_init(&obj->iommu_lock);
spin_lock_init(&obj->page_table_lock);
@@ -1036,13 +1254,20 @@ static int omap_iommu_probe(struct platform_device *pdev)
goto out_sysfs;
}
- pm_runtime_irq_safe(obj->dev);
pm_runtime_enable(obj->dev);
omap_iommu_debugfs_add(obj);
dev_info(&pdev->dev, "%s registered\n", obj->name);
+ list_for_each_entry_safe(orphan_dev, tmp, &orphan_dev_list, node) {
+ err = _omap_iommu_add_device(orphan_dev->dev);
+ if (!err) {
+ list_del(&orphan_dev->node);
+ kfree(orphan_dev);
+ }
+ }
+
return 0;
out_sysfs:
@@ -1072,6 +1297,14 @@ static int omap_iommu_remove(struct platform_device *pdev)
return 0;
}
+static const struct dev_pm_ops omap_iommu_pm_ops = {
+ .prepare = omap_iommu_prepare,
+ SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+ pm_runtime_force_resume)
+ SET_RUNTIME_PM_OPS(omap_iommu_runtime_suspend,
+ omap_iommu_runtime_resume, NULL)
+};
+
static const struct of_device_id omap_iommu_of_match[] = {
{ .compatible = "ti,omap2-iommu" },
{ .compatible = "ti,omap4-iommu" },
@@ -1085,6 +1318,7 @@ static struct platform_driver omap_iommu_driver = {
.remove = omap_iommu_remove,
.driver = {
.name = "omap-iommu",
+ .pm = &omap_iommu_pm_ops,
.of_match_table = of_match_ptr(omap_iommu_of_match),
},
};
@@ -1149,7 +1383,7 @@ static int omap_iommu_map(struct iommu_domain *domain, unsigned long da,
}
static size_t omap_iommu_unmap(struct iommu_domain *domain, unsigned long da,
- size_t size)
+ size_t size, struct iommu_iotlb_gather *gather)
{
struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
struct device *dev = omap_domain->dev;
@@ -1423,7 +1657,7 @@ static phys_addr_t omap_iommu_iova_to_phys(struct iommu_domain *domain,
return ret;
}
-static int omap_iommu_add_device(struct device *dev)
+static int _omap_iommu_add_device(struct device *dev)
{
struct omap_iommu_arch_data *arch_data, *tmp;
struct omap_iommu *oiommu;
@@ -1432,6 +1666,8 @@ static int omap_iommu_add_device(struct device *dev)
struct platform_device *pdev;
int num_iommus, i;
int ret;
+ struct orphan_dev *orphan_dev;
+ unsigned long flags;
/*
* Allocate the archdata iommu structure for DT-based devices.
@@ -1463,10 +1699,26 @@ static int omap_iommu_add_device(struct device *dev)
}
pdev = of_find_device_by_node(np);
- if (WARN_ON(!pdev)) {
+ if (!pdev) {
of_node_put(np);
kfree(arch_data);
- return -EINVAL;
+ spin_lock_irqsave(&orphan_lock, flags);
+ list_for_each_entry(orphan_dev, &orphan_dev_list,
+ node) {
+ if (orphan_dev->dev == dev)
+ break;
+ }
+ spin_unlock_irqrestore(&orphan_lock, flags);
+
+ if (orphan_dev && orphan_dev->dev == dev)
+ return -EPROBE_DEFER;
+
+ orphan_dev = kzalloc(sizeof(*orphan_dev), GFP_KERNEL);
+ orphan_dev->dev = dev;
+ spin_lock_irqsave(&orphan_lock, flags);
+ list_add(&orphan_dev->node, &orphan_dev_list);
+ spin_unlock_irqrestore(&orphan_lock, flags);
+ return -EPROBE_DEFER;
}
oiommu = platform_get_drvdata(pdev);
@@ -1477,6 +1729,7 @@ static int omap_iommu_add_device(struct device *dev)
}
tmp->iommu_dev = oiommu;
+ tmp->dev = &pdev->dev;
of_node_put(np);
}
@@ -1511,6 +1764,17 @@ static int omap_iommu_add_device(struct device *dev)
return 0;
}
+static int omap_iommu_add_device(struct device *dev)
+{
+ int ret;
+
+ ret = _omap_iommu_add_device(dev);
+ if (ret == -EPROBE_DEFER)
+ return 0;
+
+ return ret;
+}
+
static void omap_iommu_remove_device(struct device *dev)
{
struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
@@ -1554,7 +1818,7 @@ static const struct iommu_ops omap_iommu_ops = {
static int __init omap_iommu_init(void)
{
struct kmem_cache *p;
- const unsigned long flags = SLAB_HWCACHE_ALIGN;
+ const slab_flags_t flags = SLAB_HWCACHE_ALIGN;
size_t align = 1 << 10; /* L2 pagetable alignement */
struct device_node *np;
int ret;
diff --git a/drivers/iommu/omap-iommu.h b/drivers/iommu/omap-iommu.h
index 09968a02d291..18ee713ede78 100644
--- a/drivers/iommu/omap-iommu.h
+++ b/drivers/iommu/omap-iommu.h
@@ -73,16 +73,22 @@ struct omap_iommu {
void *ctx; /* iommu context: registres saved area */
+ struct cr_regs *cr_ctx;
+ u32 num_cr_ctx;
+
int has_bus_err_back;
u32 id;
struct iommu_device iommu;
struct iommu_group *group;
+
+ u8 pwrst;
};
/**
* struct omap_iommu_arch_data - omap iommu private data
- * @iommu_dev: handle of the iommu device
+ * @iommu_dev: handle of the OMAP iommu device
+ * @dev: handle of the iommu device
*
* This is an omap iommu private data object, which binds an iommu user
* to its iommu device. This object should be placed at the iommu user's
@@ -91,6 +97,7 @@ struct omap_iommu {
*/
struct omap_iommu_arch_data {
struct omap_iommu *iommu_dev;
+ struct device *dev;
};
struct cr_regs {
diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c
index 34d0b9783b3e..c31e7bc4ccbe 100644
--- a/drivers/iommu/qcom_iommu.c
+++ b/drivers/iommu/qcom_iommu.c
@@ -7,6 +7,7 @@
*/
#include <linux/atomic.h>
+#include <linux/bitfield.h>
#include <linux/clk.h>
#include <linux/delay.h>
#include <linux/dma-iommu.h>
@@ -32,7 +33,7 @@
#include <linux/slab.h>
#include <linux/spinlock.h>
-#include "arm-smmu-regs.h"
+#include "arm-smmu.h"
#define SMMU_INTR_SEL_NS 0x2000
@@ -155,7 +156,7 @@ static void qcom_iommu_tlb_inv_range_nosync(unsigned long iova, size_t size,
struct qcom_iommu_ctx *ctx = to_ctx(fwspec, fwspec->ids[i]);
size_t s = size;
- iova &= ~12UL;
+ iova = (iova >> 12) << 12;
iova |= ctx->asid;
do {
iommu_writel(ctx, reg, iova);
@@ -164,10 +165,32 @@ static void qcom_iommu_tlb_inv_range_nosync(unsigned long iova, size_t size,
}
}
-static const struct iommu_gather_ops qcom_gather_ops = {
+static void qcom_iommu_tlb_flush_walk(unsigned long iova, size_t size,
+ size_t granule, void *cookie)
+{
+ qcom_iommu_tlb_inv_range_nosync(iova, size, granule, false, cookie);
+ qcom_iommu_tlb_sync(cookie);
+}
+
+static void qcom_iommu_tlb_flush_leaf(unsigned long iova, size_t size,
+ size_t granule, void *cookie)
+{
+ qcom_iommu_tlb_inv_range_nosync(iova, size, granule, true, cookie);
+ qcom_iommu_tlb_sync(cookie);
+}
+
+static void qcom_iommu_tlb_add_page(struct iommu_iotlb_gather *gather,
+ unsigned long iova, size_t granule,
+ void *cookie)
+{
+ qcom_iommu_tlb_inv_range_nosync(iova, granule, granule, true, cookie);
+}
+
+static const struct iommu_flush_ops qcom_flush_ops = {
.tlb_flush_all = qcom_iommu_tlb_inv_context,
- .tlb_add_flush = qcom_iommu_tlb_inv_range_nosync,
- .tlb_sync = qcom_iommu_tlb_sync,
+ .tlb_flush_walk = qcom_iommu_tlb_flush_walk,
+ .tlb_flush_leaf = qcom_iommu_tlb_flush_leaf,
+ .tlb_add_page = qcom_iommu_tlb_add_page,
};
static irqreturn_t qcom_iommu_fault(int irq, void *dev)
@@ -215,7 +238,7 @@ static int qcom_iommu_init_domain(struct iommu_domain *domain,
.pgsize_bitmap = qcom_iommu_ops.pgsize_bitmap,
.ias = 32,
.oas = 40,
- .tlb = &qcom_gather_ops,
+ .tlb = &qcom_flush_ops,
.iommu_dev = qcom_iommu->dev,
};
@@ -247,16 +270,16 @@ static int qcom_iommu_init_domain(struct iommu_domain *domain,
/* TTBRs */
iommu_writeq(ctx, ARM_SMMU_CB_TTBR0,
pgtbl_cfg.arm_lpae_s1_cfg.ttbr[0] |
- ((u64)ctx->asid << TTBRn_ASID_SHIFT));
+ FIELD_PREP(TTBRn_ASID, ctx->asid));
iommu_writeq(ctx, ARM_SMMU_CB_TTBR1,
pgtbl_cfg.arm_lpae_s1_cfg.ttbr[1] |
- ((u64)ctx->asid << TTBRn_ASID_SHIFT));
+ FIELD_PREP(TTBRn_ASID, ctx->asid));
- /* TTBCR */
- iommu_writel(ctx, ARM_SMMU_CB_TTBCR2,
+ /* TCR */
+ iommu_writel(ctx, ARM_SMMU_CB_TCR2,
(pgtbl_cfg.arm_lpae_s1_cfg.tcr >> 32) |
- TTBCR2_SEP_UPSTREAM);
- iommu_writel(ctx, ARM_SMMU_CB_TTBCR,
+ FIELD_PREP(TCR2_SEP, TCR2_SEP_UPSTREAM));
+ iommu_writel(ctx, ARM_SMMU_CB_TCR,
pgtbl_cfg.arm_lpae_s1_cfg.tcr);
/* MAIRs (stage-1 only) */
@@ -417,7 +440,7 @@ static int qcom_iommu_map(struct iommu_domain *domain, unsigned long iova,
}
static size_t qcom_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
- size_t size)
+ size_t size, struct iommu_iotlb_gather *gather)
{
size_t ret;
unsigned long flags;
@@ -434,14 +457,14 @@ static size_t qcom_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
*/
pm_runtime_get_sync(qcom_domain->iommu->dev);
spin_lock_irqsave(&qcom_domain->pgtbl_lock, flags);
- ret = ops->unmap(ops, iova, size);
+ ret = ops->unmap(ops, iova, size, gather);
spin_unlock_irqrestore(&qcom_domain->pgtbl_lock, flags);
pm_runtime_put_sync(qcom_domain->iommu->dev);
return ret;
}
-static void qcom_iommu_iotlb_sync(struct iommu_domain *domain)
+static void qcom_iommu_flush_iotlb_all(struct iommu_domain *domain)
{
struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
struct io_pgtable *pgtable = container_of(qcom_domain->pgtbl_ops,
@@ -454,6 +477,12 @@ static void qcom_iommu_iotlb_sync(struct iommu_domain *domain)
pm_runtime_put_sync(qcom_domain->iommu->dev);
}
+static void qcom_iommu_iotlb_sync(struct iommu_domain *domain,
+ struct iommu_iotlb_gather *gather)
+{
+ qcom_iommu_flush_iotlb_all(domain);
+}
+
static phys_addr_t qcom_iommu_iova_to_phys(struct iommu_domain *domain,
dma_addr_t iova)
{
@@ -581,7 +610,7 @@ static const struct iommu_ops qcom_iommu_ops = {
.detach_dev = qcom_iommu_detach_dev,
.map = qcom_iommu_map,
.unmap = qcom_iommu_unmap,
- .flush_iotlb_all = qcom_iommu_iotlb_sync,
+ .flush_iotlb_all = qcom_iommu_flush_iotlb_all,
.iotlb_sync = qcom_iommu_iotlb_sync,
.iova_to_phys = qcom_iommu_iova_to_phys,
.add_device = qcom_iommu_add_device,
@@ -696,10 +725,8 @@ static int qcom_iommu_ctx_probe(struct platform_device *pdev)
return PTR_ERR(ctx->base);
irq = platform_get_irq(pdev, 0);
- if (irq < 0) {
- dev_err(dev, "failed to get irq\n");
+ if (irq < 0)
return -ENODEV;
- }
/* clear IRQs before registering fault handler, just in case the
* boot-loader left us a surprise:
@@ -775,7 +802,7 @@ static int qcom_iommu_device_probe(struct platform_device *pdev)
struct qcom_iommu_dev *qcom_iommu;
struct device *dev = &pdev->dev;
struct resource *res;
- int ret, sz, max_asid = 0;
+ int ret, max_asid = 0;
/* find the max asid (which is 1:1 to ctx bank idx), so we know how
* many child ctx devices we have:
@@ -783,9 +810,8 @@ static int qcom_iommu_device_probe(struct platform_device *pdev)
for_each_child_of_node(dev->of_node, child)
max_asid = max(max_asid, get_asid(child));
- sz = sizeof(*qcom_iommu) + (max_asid * sizeof(qcom_iommu->ctxs[0]));
-
- qcom_iommu = devm_kzalloc(dev, sz, GFP_KERNEL);
+ qcom_iommu = devm_kzalloc(dev, struct_size(qcom_iommu, ctxs, max_asid),
+ GFP_KERNEL);
if (!qcom_iommu)
return -ENOMEM;
qcom_iommu->num_ctxs = max_asid;
diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c
index dc26d74d79c2..26290f310f90 100644
--- a/drivers/iommu/rockchip-iommu.c
+++ b/drivers/iommu/rockchip-iommu.c
@@ -794,7 +794,7 @@ static int rk_iommu_map(struct iommu_domain *domain, unsigned long _iova,
}
static size_t rk_iommu_unmap(struct iommu_domain *domain, unsigned long _iova,
- size_t size)
+ size_t size, struct iommu_iotlb_gather *gather)
{
struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
unsigned long flags;
diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c
index 22d4db302c1c..3b0b18e23187 100644
--- a/drivers/iommu/s390-iommu.c
+++ b/drivers/iommu/s390-iommu.c
@@ -314,7 +314,8 @@ static phys_addr_t s390_iommu_iova_to_phys(struct iommu_domain *domain,
}
static size_t s390_iommu_unmap(struct iommu_domain *domain,
- unsigned long iova, size_t size)
+ unsigned long iova, size_t size,
+ struct iommu_iotlb_gather *gather)
{
struct s390_domain *s390_domain = to_s390_domain(domain);
int flags = ZPCI_PTE_INVALID;
diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c
index 6d40bc1b38bf..3924f7c05544 100644
--- a/drivers/iommu/tegra-gart.c
+++ b/drivers/iommu/tegra-gart.c
@@ -207,7 +207,7 @@ static inline int __gart_iommu_unmap(struct gart_device *gart,
}
static size_t gart_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
- size_t bytes)
+ size_t bytes, struct iommu_iotlb_gather *gather)
{
struct gart_device *gart = gart_handle;
int err;
@@ -273,11 +273,17 @@ static int gart_iommu_of_xlate(struct device *dev,
return 0;
}
-static void gart_iommu_sync(struct iommu_domain *domain)
+static void gart_iommu_sync_map(struct iommu_domain *domain)
{
FLUSH_GART_REGS(gart_handle);
}
+static void gart_iommu_sync(struct iommu_domain *domain,
+ struct iommu_iotlb_gather *gather)
+{
+ gart_iommu_sync_map(domain);
+}
+
static const struct iommu_ops gart_iommu_ops = {
.capable = gart_iommu_capable,
.domain_alloc = gart_iommu_domain_alloc,
@@ -292,7 +298,7 @@ static const struct iommu_ops gart_iommu_ops = {
.iova_to_phys = gart_iommu_iova_to_phys,
.pgsize_bitmap = GART_IOMMU_PGSIZES,
.of_xlate = gart_iommu_of_xlate,
- .iotlb_sync_map = gart_iommu_sync,
+ .iotlb_sync_map = gart_iommu_sync_map,
.iotlb_sync = gart_iommu_sync,
};
diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c
index c4a652b227f8..7293fc3f796d 100644
--- a/drivers/iommu/tegra-smmu.c
+++ b/drivers/iommu/tegra-smmu.c
@@ -680,7 +680,7 @@ static int tegra_smmu_map(struct iommu_domain *domain, unsigned long iova,
}
static size_t tegra_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
- size_t size)
+ size_t size, struct iommu_iotlb_gather *gather)
{
struct tegra_smmu_as *as = to_smmu_as(domain);
dma_addr_t pte_dma;
diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c
index 80a740df0737..3ea9d7682999 100644
--- a/drivers/iommu/virtio-iommu.c
+++ b/drivers/iommu/virtio-iommu.c
@@ -751,7 +751,7 @@ static int viommu_map(struct iommu_domain *domain, unsigned long iova,
}
static size_t viommu_unmap(struct iommu_domain *domain, unsigned long iova,
- size_t size)
+ size_t size, struct iommu_iotlb_gather *gather)
{
int ret = 0;
size_t unmapped;
@@ -797,7 +797,8 @@ static phys_addr_t viommu_iova_to_phys(struct iommu_domain *domain,
return paddr;
}
-static void viommu_iotlb_sync(struct iommu_domain *domain)
+static void viommu_iotlb_sync(struct iommu_domain *domain,
+ struct iommu_iotlb_gather *gather)
{
struct viommu_domain *vdomain = to_viommu_domain(domain);
diff --git a/drivers/memory/mtk-smi.c b/drivers/memory/mtk-smi.c
index 42ab43affbff..439d7d886873 100644
--- a/drivers/memory/mtk-smi.c
+++ b/drivers/memory/mtk-smi.c
@@ -41,17 +41,40 @@
#define SMI_LARB_NONSEC_CON(id) (0x380 + ((id) * 4))
#define F_MMU_EN BIT(0)
+/* SMI COMMON */
+#define SMI_BUS_SEL 0x220
+#define SMI_BUS_LARB_SHIFT(larbid) ((larbid) << 1)
+/* All are MMU0 defaultly. Only specialize mmu1 here. */
+#define F_MMU1_LARB(larbid) (0x1 << SMI_BUS_LARB_SHIFT(larbid))
+
+enum mtk_smi_gen {
+ MTK_SMI_GEN1,
+ MTK_SMI_GEN2
+};
+
+struct mtk_smi_common_plat {
+ enum mtk_smi_gen gen;
+ bool has_gals;
+ u32 bus_sel; /* Balance some larbs to enter mmu0 or mmu1 */
+};
+
struct mtk_smi_larb_gen {
- bool need_larbid;
int port_in_larb[MTK_LARB_NR_MAX + 1];
void (*config_port)(struct device *);
+ unsigned int larb_direct_to_common_mask;
+ bool has_gals;
};
struct mtk_smi {
struct device *dev;
struct clk *clk_apb, *clk_smi;
+ struct clk *clk_gals0, *clk_gals1;
struct clk *clk_async; /*only needed by mt2701*/
- void __iomem *smi_ao_base;
+ union {
+ void __iomem *smi_ao_base; /* only for gen1 */
+ void __iomem *base; /* only for gen2 */
+ };
+ const struct mtk_smi_common_plat *plat;
};
struct mtk_smi_larb { /* larb: local arbiter */
@@ -63,82 +86,56 @@ struct mtk_smi_larb { /* larb: local arbiter */
u32 *mmu;
};
-enum mtk_smi_gen {
- MTK_SMI_GEN1,
- MTK_SMI_GEN2
-};
-
-static int mtk_smi_enable(const struct mtk_smi *smi)
+static int mtk_smi_clk_enable(const struct mtk_smi *smi)
{
int ret;
- ret = pm_runtime_get_sync(smi->dev);
- if (ret < 0)
- return ret;
-
ret = clk_prepare_enable(smi->clk_apb);
if (ret)
- goto err_put_pm;
+ return ret;
ret = clk_prepare_enable(smi->clk_smi);
if (ret)
goto err_disable_apb;
+ ret = clk_prepare_enable(smi->clk_gals0);
+ if (ret)
+ goto err_disable_smi;
+
+ ret = clk_prepare_enable(smi->clk_gals1);
+ if (ret)
+ goto err_disable_gals0;
+
return 0;
+err_disable_gals0:
+ clk_disable_unprepare(smi->clk_gals0);
+err_disable_smi:
+ clk_disable_unprepare(smi->clk_smi);
err_disable_apb:
clk_disable_unprepare(smi->clk_apb);
-err_put_pm:
- pm_runtime_put_sync(smi->dev);
return ret;
}
-static void mtk_smi_disable(const struct mtk_smi *smi)
+static void mtk_smi_clk_disable(const struct mtk_smi *smi)
{
+ clk_disable_unprepare(smi->clk_gals1);
+ clk_disable_unprepare(smi->clk_gals0);
clk_disable_unprepare(smi->clk_smi);
clk_disable_unprepare(smi->clk_apb);
- pm_runtime_put_sync(smi->dev);
}
int mtk_smi_larb_get(struct device *larbdev)
{
- struct mtk_smi_larb *larb = dev_get_drvdata(larbdev);
- const struct mtk_smi_larb_gen *larb_gen = larb->larb_gen;
- struct mtk_smi *common = dev_get_drvdata(larb->smi_common_dev);
- int ret;
-
- /* Enable the smi-common's power and clocks */
- ret = mtk_smi_enable(common);
- if (ret)
- return ret;
+ int ret = pm_runtime_get_sync(larbdev);
- /* Enable the larb's power and clocks */
- ret = mtk_smi_enable(&larb->smi);
- if (ret) {
- mtk_smi_disable(common);
- return ret;
- }
-
- /* Configure the iommu info for this larb */
- larb_gen->config_port(larbdev);
-
- return 0;
+ return (ret < 0) ? ret : 0;
}
EXPORT_SYMBOL_GPL(mtk_smi_larb_get);
void mtk_smi_larb_put(struct device *larbdev)
{
- struct mtk_smi_larb *larb = dev_get_drvdata(larbdev);
- struct mtk_smi *common = dev_get_drvdata(larb->smi_common_dev);
-
- /*
- * Don't de-configure the iommu info for this larb since there may be
- * several modules in this larb.
- * The iommu info will be reset after power off.
- */
-
- mtk_smi_disable(&larb->smi);
- mtk_smi_disable(common);
+ pm_runtime_put_sync(larbdev);
}
EXPORT_SYMBOL_GPL(mtk_smi_larb_put);
@@ -146,39 +143,26 @@ static int
mtk_smi_larb_bind(struct device *dev, struct device *master, void *data)
{
struct mtk_smi_larb *larb = dev_get_drvdata(dev);
- struct mtk_smi_iommu *smi_iommu = data;
+ struct mtk_smi_larb_iommu *larb_mmu = data;
unsigned int i;
- if (larb->larb_gen->need_larbid) {
- larb->mmu = &smi_iommu->larb_imu[larb->larbid].mmu;
- return 0;
- }
-
- /*
- * If there is no larbid property, Loop to find the corresponding
- * iommu information.
- */
- for (i = 0; i < smi_iommu->larb_nr; i++) {
- if (dev == smi_iommu->larb_imu[i].dev) {
- /* The 'mmu' may be updated in iommu-attach/detach. */
- larb->mmu = &smi_iommu->larb_imu[i].mmu;
+ for (i = 0; i < MTK_LARB_NR_MAX; i++) {
+ if (dev == larb_mmu[i].dev) {
+ larb->larbid = i;
+ larb->mmu = &larb_mmu[i].mmu;
return 0;
}
}
return -ENODEV;
}
-static void mtk_smi_larb_config_port_mt2712(struct device *dev)
+static void mtk_smi_larb_config_port_gen2_general(struct device *dev)
{
struct mtk_smi_larb *larb = dev_get_drvdata(dev);
u32 reg;
int i;
- /*
- * larb 8/9 is the bdpsys larb, the iommu_en is enabled defaultly.
- * Don't need to set it again.
- */
- if (larb->larbid == 8 || larb->larbid == 9)
+ if (BIT(larb->larbid) & larb->larb_gen->larb_direct_to_common_mask)
return;
for_each_set_bit(i, (unsigned long *)larb->mmu, 32) {
@@ -243,7 +227,6 @@ static const struct mtk_smi_larb_gen mtk_smi_larb_mt8173 = {
};
static const struct mtk_smi_larb_gen mtk_smi_larb_mt2701 = {
- .need_larbid = true,
.port_in_larb = {
LARB0_PORT_OFFSET, LARB1_PORT_OFFSET,
LARB2_PORT_OFFSET, LARB3_PORT_OFFSET
@@ -252,8 +235,15 @@ static const struct mtk_smi_larb_gen mtk_smi_larb_mt2701 = {
};
static const struct mtk_smi_larb_gen mtk_smi_larb_mt2712 = {
- .need_larbid = true,
- .config_port = mtk_smi_larb_config_port_mt2712,
+ .config_port = mtk_smi_larb_config_port_gen2_general,
+ .larb_direct_to_common_mask = BIT(8) | BIT(9), /* bdpsys */
+};
+
+static const struct mtk_smi_larb_gen mtk_smi_larb_mt8183 = {
+ .has_gals = true,
+ .config_port = mtk_smi_larb_config_port_gen2_general,
+ .larb_direct_to_common_mask = BIT(2) | BIT(3) | BIT(7),
+ /* IPU0 | IPU1 | CCU */
};
static const struct of_device_id mtk_smi_larb_of_ids[] = {
@@ -269,6 +259,10 @@ static const struct of_device_id mtk_smi_larb_of_ids[] = {
.compatible = "mediatek,mt2712-smi-larb",
.data = &mtk_smi_larb_mt2712
},
+ {
+ .compatible = "mediatek,mt8183-smi-larb",
+ .data = &mtk_smi_larb_mt8183
+ },
{}
};
@@ -279,7 +273,6 @@ static int mtk_smi_larb_probe(struct platform_device *pdev)
struct device *dev = &pdev->dev;
struct device_node *smi_node;
struct platform_device *smi_pdev;
- int err;
larb = devm_kzalloc(dev, sizeof(*larb), GFP_KERNEL);
if (!larb)
@@ -298,16 +291,16 @@ static int mtk_smi_larb_probe(struct platform_device *pdev)
larb->smi.clk_smi = devm_clk_get(dev, "smi");
if (IS_ERR(larb->smi.clk_smi))
return PTR_ERR(larb->smi.clk_smi);
- larb->smi.dev = dev;
- if (larb->larb_gen->need_larbid) {
- err = of_property_read_u32(dev->of_node, "mediatek,larb-id",
- &larb->larbid);
- if (err) {
- dev_err(dev, "missing larbid property\n");
- return err;
- }
+ if (larb->larb_gen->has_gals) {
+ /* The larbs may still haven't gals even if the SoC support.*/
+ larb->smi.clk_gals0 = devm_clk_get(dev, "gals");
+ if (PTR_ERR(larb->smi.clk_gals0) == -ENOENT)
+ larb->smi.clk_gals0 = NULL;
+ else if (IS_ERR(larb->smi.clk_gals0))
+ return PTR_ERR(larb->smi.clk_gals0);
}
+ larb->smi.dev = dev;
smi_node = of_parse_phandle(dev->of_node, "mediatek,smi", 0);
if (!smi_node)
@@ -336,27 +329,86 @@ static int mtk_smi_larb_remove(struct platform_device *pdev)
return 0;
}
+static int __maybe_unused mtk_smi_larb_resume(struct device *dev)
+{
+ struct mtk_smi_larb *larb = dev_get_drvdata(dev);
+ const struct mtk_smi_larb_gen *larb_gen = larb->larb_gen;
+ int ret;
+
+ /* Power on smi-common. */
+ ret = pm_runtime_get_sync(larb->smi_common_dev);
+ if (ret < 0) {
+ dev_err(dev, "Failed to pm get for smi-common(%d).\n", ret);
+ return ret;
+ }
+
+ ret = mtk_smi_clk_enable(&larb->smi);
+ if (ret < 0) {
+ dev_err(dev, "Failed to enable clock(%d).\n", ret);
+ pm_runtime_put_sync(larb->smi_common_dev);
+ return ret;
+ }
+
+ /* Configure the basic setting for this larb */
+ larb_gen->config_port(dev);
+
+ return 0;
+}
+
+static int __maybe_unused mtk_smi_larb_suspend(struct device *dev)
+{
+ struct mtk_smi_larb *larb = dev_get_drvdata(dev);
+
+ mtk_smi_clk_disable(&larb->smi);
+ pm_runtime_put_sync(larb->smi_common_dev);
+ return 0;
+}
+
+static const struct dev_pm_ops smi_larb_pm_ops = {
+ SET_RUNTIME_PM_OPS(mtk_smi_larb_suspend, mtk_smi_larb_resume, NULL)
+};
+
static struct platform_driver mtk_smi_larb_driver = {
.probe = mtk_smi_larb_probe,
.remove = mtk_smi_larb_remove,
.driver = {
.name = "mtk-smi-larb",
.of_match_table = mtk_smi_larb_of_ids,
+ .pm = &smi_larb_pm_ops,
}
};
+static const struct mtk_smi_common_plat mtk_smi_common_gen1 = {
+ .gen = MTK_SMI_GEN1,
+};
+
+static const struct mtk_smi_common_plat mtk_smi_common_gen2 = {
+ .gen = MTK_SMI_GEN2,
+};
+
+static const struct mtk_smi_common_plat mtk_smi_common_mt8183 = {
+ .gen = MTK_SMI_GEN2,
+ .has_gals = true,
+ .bus_sel = F_MMU1_LARB(1) | F_MMU1_LARB(2) | F_MMU1_LARB(5) |
+ F_MMU1_LARB(7),
+};
+
static const struct of_device_id mtk_smi_common_of_ids[] = {
{
.compatible = "mediatek,mt8173-smi-common",
- .data = (void *)MTK_SMI_GEN2
+ .data = &mtk_smi_common_gen2,
},
{
.compatible = "mediatek,mt2701-smi-common",
- .data = (void *)MTK_SMI_GEN1
+ .data = &mtk_smi_common_gen1,
},
{
.compatible = "mediatek,mt2712-smi-common",
- .data = (void *)MTK_SMI_GEN2
+ .data = &mtk_smi_common_gen2,
+ },
+ {
+ .compatible = "mediatek,mt8183-smi-common",
+ .data = &mtk_smi_common_mt8183,
},
{}
};
@@ -366,13 +418,13 @@ static int mtk_smi_common_probe(struct platform_device *pdev)
struct device *dev = &pdev->dev;
struct mtk_smi *common;
struct resource *res;
- enum mtk_smi_gen smi_gen;
int ret;
common = devm_kzalloc(dev, sizeof(*common), GFP_KERNEL);
if (!common)
return -ENOMEM;
common->dev = dev;
+ common->plat = of_device_get_match_data(dev);
common->clk_apb = devm_clk_get(dev, "apb");
if (IS_ERR(common->clk_apb))
@@ -382,14 +434,23 @@ static int mtk_smi_common_probe(struct platform_device *pdev)
if (IS_ERR(common->clk_smi))
return PTR_ERR(common->clk_smi);
+ if (common->plat->has_gals) {
+ common->clk_gals0 = devm_clk_get(dev, "gals0");
+ if (IS_ERR(common->clk_gals0))
+ return PTR_ERR(common->clk_gals0);
+
+ common->clk_gals1 = devm_clk_get(dev, "gals1");
+ if (IS_ERR(common->clk_gals1))
+ return PTR_ERR(common->clk_gals1);
+ }
+
/*
* for mtk smi gen 1, we need to get the ao(always on) base to config
* m4u port, and we need to enable the aync clock for transform the smi
* clock into emi clock domain, but for mtk smi gen2, there's no smi ao
* base.
*/
- smi_gen = (enum mtk_smi_gen)of_device_get_match_data(dev);
- if (smi_gen == MTK_SMI_GEN1) {
+ if (common->plat->gen == MTK_SMI_GEN1) {
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
common->smi_ao_base = devm_ioremap_resource(dev, res);
if (IS_ERR(common->smi_ao_base))
@@ -402,6 +463,11 @@ static int mtk_smi_common_probe(struct platform_device *pdev)
ret = clk_prepare_enable(common->clk_async);
if (ret)
return ret;
+ } else {
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ common->base = devm_ioremap_resource(dev, res);
+ if (IS_ERR(common->base))
+ return PTR_ERR(common->base);
}
pm_runtime_enable(dev);
platform_set_drvdata(pdev, common);
@@ -414,12 +480,42 @@ static int mtk_smi_common_remove(struct platform_device *pdev)
return 0;
}
+static int __maybe_unused mtk_smi_common_resume(struct device *dev)
+{
+ struct mtk_smi *common = dev_get_drvdata(dev);
+ u32 bus_sel = common->plat->bus_sel;
+ int ret;
+
+ ret = mtk_smi_clk_enable(common);
+ if (ret) {
+ dev_err(common->dev, "Failed to enable clock(%d).\n", ret);
+ return ret;
+ }
+
+ if (common->plat->gen == MTK_SMI_GEN2 && bus_sel)
+ writel(bus_sel, common->base + SMI_BUS_SEL);
+ return 0;
+}
+
+static int __maybe_unused mtk_smi_common_suspend(struct device *dev)
+{
+ struct mtk_smi *common = dev_get_drvdata(dev);
+
+ mtk_smi_clk_disable(common);
+ return 0;
+}
+
+static const struct dev_pm_ops smi_common_pm_ops = {
+ SET_RUNTIME_PM_OPS(mtk_smi_common_suspend, mtk_smi_common_resume, NULL)
+};
+
static struct platform_driver mtk_smi_common_driver = {
.probe = mtk_smi_common_probe,
.remove = mtk_smi_common_remove,
.driver = {
.name = "mtk-smi-common",
.of_match_table = mtk_smi_common_of_ids,
+ .pm = &smi_common_pm_ops,
}
};
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 054391f30fa8..ad830abe1021 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -650,12 +650,13 @@ unpin_exit:
}
static long vfio_sync_unpin(struct vfio_dma *dma, struct vfio_domain *domain,
- struct list_head *regions)
+ struct list_head *regions,
+ struct iommu_iotlb_gather *iotlb_gather)
{
long unlocked = 0;
struct vfio_regions *entry, *next;
- iommu_tlb_sync(domain->domain);
+ iommu_tlb_sync(domain->domain, iotlb_gather);
list_for_each_entry_safe(entry, next, regions, list) {
unlocked += vfio_unpin_pages_remote(dma,
@@ -685,18 +686,19 @@ static size_t unmap_unpin_fast(struct vfio_domain *domain,
struct vfio_dma *dma, dma_addr_t *iova,
size_t len, phys_addr_t phys, long *unlocked,
struct list_head *unmapped_list,
- int *unmapped_cnt)
+ int *unmapped_cnt,
+ struct iommu_iotlb_gather *iotlb_gather)
{
size_t unmapped = 0;
struct vfio_regions *entry = kzalloc(sizeof(*entry), GFP_KERNEL);
if (entry) {
- unmapped = iommu_unmap_fast(domain->domain, *iova, len);
+ unmapped = iommu_unmap_fast(domain->domain, *iova, len,
+ iotlb_gather);
if (!unmapped) {
kfree(entry);
} else {
- iommu_tlb_range_add(domain->domain, *iova, unmapped);
entry->iova = *iova;
entry->phys = phys;
entry->len = unmapped;
@@ -712,8 +714,8 @@ static size_t unmap_unpin_fast(struct vfio_domain *domain,
* or in case of errors.
*/
if (*unmapped_cnt >= VFIO_IOMMU_TLB_SYNC_MAX || !unmapped) {
- *unlocked += vfio_sync_unpin(dma, domain,
- unmapped_list);
+ *unlocked += vfio_sync_unpin(dma, domain, unmapped_list,
+ iotlb_gather);
*unmapped_cnt = 0;
}
@@ -744,6 +746,7 @@ static long vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma,
dma_addr_t iova = dma->iova, end = dma->iova + dma->size;
struct vfio_domain *domain, *d;
LIST_HEAD(unmapped_region_list);
+ struct iommu_iotlb_gather iotlb_gather;
int unmapped_region_cnt = 0;
long unlocked = 0;
@@ -768,6 +771,7 @@ static long vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma,
cond_resched();
}
+ iommu_iotlb_gather_init(&iotlb_gather);
while (iova < end) {
size_t unmapped, len;
phys_addr_t phys, next;
@@ -796,7 +800,8 @@ static long vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma,
*/
unmapped = unmap_unpin_fast(domain, dma, &iova, len, phys,
&unlocked, &unmapped_region_list,
- &unmapped_region_cnt);
+ &unmapped_region_cnt,
+ &iotlb_gather);
if (!unmapped) {
unmapped = unmap_unpin_slow(domain, dma, &iova, len,
phys, &unlocked);
@@ -807,8 +812,10 @@ static long vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma,
dma->iommu_mapped = false;
- if (unmapped_region_cnt)
- unlocked += vfio_sync_unpin(dma, domain, &unmapped_region_list);
+ if (unmapped_region_cnt) {
+ unlocked += vfio_sync_unpin(dma, domain, &unmapped_region_list,
+ &iotlb_gather);
+ }
if (do_accounting) {
vfio_lock_acct(dma, -unlocked, true);
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index ae1df496bf38..adcabd9473eb 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -386,8 +386,8 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
*/
trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
- map = swiotlb_tbl_map_single(dev, start_dma_addr, phys, size, dir,
- attrs);
+ map = swiotlb_tbl_map_single(dev, start_dma_addr, phys,
+ size, size, dir, attrs);
if (map == (phys_addr_t)DMA_MAPPING_ERROR)
return DMA_MAPPING_ERROR;
@@ -397,7 +397,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
* Ensure that the address returned is DMA'ble
*/
if (unlikely(!dma_capable(dev, dev_addr, size))) {
- swiotlb_tbl_unmap_single(dev, map, size, dir,
+ swiotlb_tbl_unmap_single(dev, map, size, size, dir,
attrs | DMA_ATTR_SKIP_CPU_SYNC);
return DMA_MAPPING_ERROR;
}
@@ -433,7 +433,7 @@ static void xen_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
/* NOTE: We use dev_addr here, not paddr! */
if (is_xen_swiotlb_buffer(dev_addr))
- swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, attrs);
+ swiotlb_tbl_unmap_single(hwdev, paddr, size, size, dir, attrs);
}
static void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
diff --git a/include/dt-bindings/memory/mt8183-larb-port.h b/include/dt-bindings/memory/mt8183-larb-port.h
new file mode 100644
index 000000000000..2c579f305162
--- /dev/null
+++ b/include/dt-bindings/memory/mt8183-larb-port.h
@@ -0,0 +1,130 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2018 MediaTek Inc.
+ * Author: Yong Wu <yong.wu@mediatek.com>
+ */
+#ifndef __DTS_IOMMU_PORT_MT8183_H
+#define __DTS_IOMMU_PORT_MT8183_H
+
+#define MTK_M4U_ID(larb, port) (((larb) << 5) | (port))
+
+#define M4U_LARB0_ID 0
+#define M4U_LARB1_ID 1
+#define M4U_LARB2_ID 2
+#define M4U_LARB3_ID 3
+#define M4U_LARB4_ID 4
+#define M4U_LARB5_ID 5
+#define M4U_LARB6_ID 6
+#define M4U_LARB7_ID 7
+
+/* larb0 */
+#define M4U_PORT_DISP_OVL0 MTK_M4U_ID(M4U_LARB0_ID, 0)
+#define M4U_PORT_DISP_2L_OVL0_LARB0 MTK_M4U_ID(M4U_LARB0_ID, 1)
+#define M4U_PORT_DISP_2L_OVL1_LARB0 MTK_M4U_ID(M4U_LARB0_ID, 2)
+#define M4U_PORT_DISP_RDMA0 MTK_M4U_ID(M4U_LARB0_ID, 3)
+#define M4U_PORT_DISP_RDMA1 MTK_M4U_ID(M4U_LARB0_ID, 4)
+#define M4U_PORT_DISP_WDMA0 MTK_M4U_ID(M4U_LARB0_ID, 5)
+#define M4U_PORT_MDP_RDMA0 MTK_M4U_ID(M4U_LARB0_ID, 6)
+#define M4U_PORT_MDP_WROT0 MTK_M4U_ID(M4U_LARB0_ID, 7)
+#define M4U_PORT_MDP_WDMA0 MTK_M4U_ID(M4U_LARB0_ID, 8)
+#define M4U_PORT_DISP_FAKE0 MTK_M4U_ID(M4U_LARB0_ID, 9)
+
+/* larb1 */
+#define M4U_PORT_HW_VDEC_MC_EXT MTK_M4U_ID(M4U_LARB1_ID, 0)
+#define M4U_PORT_HW_VDEC_PP_EXT MTK_M4U_ID(M4U_LARB1_ID, 1)
+#define M4U_PORT_HW_VDEC_VLD_EXT MTK_M4U_ID(M4U_LARB1_ID, 2)
+#define M4U_PORT_HW_VDEC_AVC_MV_EXT MTK_M4U_ID(M4U_LARB1_ID, 3)
+#define M4U_PORT_HW_VDEC_PRED_RD_EXT MTK_M4U_ID(M4U_LARB1_ID, 4)
+#define M4U_PORT_HW_VDEC_PRED_WR_EXT MTK_M4U_ID(M4U_LARB1_ID, 5)
+#define M4U_PORT_HW_VDEC_PPWRAP_EXT MTK_M4U_ID(M4U_LARB1_ID, 6)
+
+/* larb2 VPU0 */
+#define M4U_PORT_IMG_IPUO MTK_M4U_ID(M4U_LARB2_ID, 0)
+#define M4U_PORT_IMG_IPU3O MTK_M4U_ID(M4U_LARB2_ID, 1)
+#define M4U_PORT_IMG_IPUI MTK_M4U_ID(M4U_LARB2_ID, 2)
+
+/* larb3 VPU1 */
+#define M4U_PORT_CAM_IPUO MTK_M4U_ID(M4U_LARB3_ID, 0)
+#define M4U_PORT_CAM_IPU2O MTK_M4U_ID(M4U_LARB3_ID, 1)
+#define M4U_PORT_CAM_IPU3O MTK_M4U_ID(M4U_LARB3_ID, 2)
+#define M4U_PORT_CAM_IPUI MTK_M4U_ID(M4U_LARB3_ID, 3)
+#define M4U_PORT_CAM_IPU2I MTK_M4U_ID(M4U_LARB3_ID, 4)
+
+/* larb4 */
+#define M4U_PORT_VENC_RCPU MTK_M4U_ID(M4U_LARB4_ID, 0)
+#define M4U_PORT_VENC_REC MTK_M4U_ID(M4U_LARB4_ID, 1)
+#define M4U_PORT_VENC_BSDMA MTK_M4U_ID(M4U_LARB4_ID, 2)
+#define M4U_PORT_VENC_SV_COMV MTK_M4U_ID(M4U_LARB4_ID, 3)
+#define M4U_PORT_VENC_RD_COMV MTK_M4U_ID(M4U_LARB4_ID, 4)
+#define M4U_PORT_JPGENC_RDMA MTK_M4U_ID(M4U_LARB4_ID, 5)
+#define M4U_PORT_JPGENC_BSDMA MTK_M4U_ID(M4U_LARB4_ID, 6)
+#define M4U_PORT_VENC_CUR_LUMA MTK_M4U_ID(M4U_LARB4_ID, 7)
+#define M4U_PORT_VENC_CUR_CHROMA MTK_M4U_ID(M4U_LARB4_ID, 8)
+#define M4U_PORT_VENC_REF_LUMA MTK_M4U_ID(M4U_LARB4_ID, 9)
+#define M4U_PORT_VENC_REF_CHROMA MTK_M4U_ID(M4U_LARB4_ID, 10)
+
+/* larb5 */
+#define M4U_PORT_CAM_IMGI MTK_M4U_ID(M4U_LARB5_ID, 0)
+#define M4U_PORT_CAM_IMG2O MTK_M4U_ID(M4U_LARB5_ID, 1)
+#define M4U_PORT_CAM_IMG3O MTK_M4U_ID(M4U_LARB5_ID, 2)
+#define M4U_PORT_CAM_VIPI MTK_M4U_ID(M4U_LARB5_ID, 3)
+#define M4U_PORT_CAM_LCEI MTK_M4U_ID(M4U_LARB5_ID, 4)
+#define M4U_PORT_CAM_SMXI MTK_M4U_ID(M4U_LARB5_ID, 5)
+#define M4U_PORT_CAM_SMXO MTK_M4U_ID(M4U_LARB5_ID, 6)
+#define M4U_PORT_CAM_WPE0_RDMA1 MTK_M4U_ID(M4U_LARB5_ID, 7)
+#define M4U_PORT_CAM_WPE0_RDMA0 MTK_M4U_ID(M4U_LARB5_ID, 8)
+#define M4U_PORT_CAM_WPE0_WDMA MTK_M4U_ID(M4U_LARB5_ID, 9)
+#define M4U_PORT_CAM_FDVT_RP MTK_M4U_ID(M4U_LARB5_ID, 10)
+#define M4U_PORT_CAM_FDVT_WR MTK_M4U_ID(M4U_LARB5_ID, 11)
+#define M4U_PORT_CAM_FDVT_RB MTK_M4U_ID(M4U_LARB5_ID, 12)
+#define M4U_PORT_CAM_WPE1_RDMA0 MTK_M4U_ID(M4U_LARB5_ID, 13)
+#define M4U_PORT_CAM_WPE1_RDMA1 MTK_M4U_ID(M4U_LARB5_ID, 14)
+#define M4U_PORT_CAM_WPE1_WDMA MTK_M4U_ID(M4U_LARB5_ID, 15)
+#define M4U_PORT_CAM_DPE_RDMA MTK_M4U_ID(M4U_LARB5_ID, 16)
+#define M4U_PORT_CAM_DPE_WDMA MTK_M4U_ID(M4U_LARB5_ID, 17)
+#define M4U_PORT_CAM_MFB_RDMA0 MTK_M4U_ID(M4U_LARB5_ID, 18)
+#define M4U_PORT_CAM_MFB_RDMA1 MTK_M4U_ID(M4U_LARB5_ID, 19)
+#define M4U_PORT_CAM_MFB_WDMA MTK_M4U_ID(M4U_LARB5_ID, 20)
+#define M4U_PORT_CAM_RSC_RDMA0 MTK_M4U_ID(M4U_LARB5_ID, 21)
+#define M4U_PORT_CAM_RSC_WDMA MTK_M4U_ID(M4U_LARB5_ID, 22)
+#define M4U_PORT_CAM_OWE_RDMA MTK_M4U_ID(M4U_LARB5_ID, 23)
+#define M4U_PORT_CAM_OWE_WDMA MTK_M4U_ID(M4U_LARB5_ID, 24)
+
+/* larb6 */
+#define M4U_PORT_CAM_IMGO MTK_M4U_ID(M4U_LARB6_ID, 0)
+#define M4U_PORT_CAM_RRZO MTK_M4U_ID(M4U_LARB6_ID, 1)
+#define M4U_PORT_CAM_AAO MTK_M4U_ID(M4U_LARB6_ID, 2)
+#define M4U_PORT_CAM_AFO MTK_M4U_ID(M4U_LARB6_ID, 3)
+#define M4U_PORT_CAM_LSCI0 MTK_M4U_ID(M4U_LARB6_ID, 4)
+#define M4U_PORT_CAM_LSCI1 MTK_M4U_ID(M4U_LARB6_ID, 5)
+#define M4U_PORT_CAM_PDO MTK_M4U_ID(M4U_LARB6_ID, 6)
+#define M4U_PORT_CAM_BPCI MTK_M4U_ID(M4U_LARB6_ID, 7)
+#define M4U_PORT_CAM_LCSO MTK_M4U_ID(M4U_LARB6_ID, 8)
+#define M4U_PORT_CAM_CAM_RSSO_A MTK_M4U_ID(M4U_LARB6_ID, 9)
+#define M4U_PORT_CAM_UFEO MTK_M4U_ID(M4U_LARB6_ID, 10)
+#define M4U_PORT_CAM_SOCO MTK_M4U_ID(M4U_LARB6_ID, 11)
+#define M4U_PORT_CAM_SOC1 MTK_M4U_ID(M4U_LARB6_ID, 12)
+#define M4U_PORT_CAM_SOC2 MTK_M4U_ID(M4U_LARB6_ID, 13)
+#define M4U_PORT_CAM_CCUI MTK_M4U_ID(M4U_LARB6_ID, 14)
+#define M4U_PORT_CAM_CCUO MTK_M4U_ID(M4U_LARB6_ID, 15)
+#define M4U_PORT_CAM_RAWI_A MTK_M4U_ID(M4U_LARB6_ID, 16)
+#define M4U_PORT_CAM_CCUG MTK_M4U_ID(M4U_LARB6_ID, 17)
+#define M4U_PORT_CAM_PSO MTK_M4U_ID(M4U_LARB6_ID, 18)
+#define M4U_PORT_CAM_AFO_1 MTK_M4U_ID(M4U_LARB6_ID, 19)
+#define M4U_PORT_CAM_LSCI_2 MTK_M4U_ID(M4U_LARB6_ID, 20)
+#define M4U_PORT_CAM_PDI MTK_M4U_ID(M4U_LARB6_ID, 21)
+#define M4U_PORT_CAM_FLKO MTK_M4U_ID(M4U_LARB6_ID, 22)
+#define M4U_PORT_CAM_LMVO MTK_M4U_ID(M4U_LARB6_ID, 23)
+#define M4U_PORT_CAM_UFGO MTK_M4U_ID(M4U_LARB6_ID, 24)
+#define M4U_PORT_CAM_SPARE MTK_M4U_ID(M4U_LARB6_ID, 25)
+#define M4U_PORT_CAM_SPARE_2 MTK_M4U_ID(M4U_LARB6_ID, 26)
+#define M4U_PORT_CAM_SPARE_3 MTK_M4U_ID(M4U_LARB6_ID, 27)
+#define M4U_PORT_CAM_SPARE_4 MTK_M4U_ID(M4U_LARB6_ID, 28)
+#define M4U_PORT_CAM_SPARE_5 MTK_M4U_ID(M4U_LARB6_ID, 29)
+#define M4U_PORT_CAM_SPARE_6 MTK_M4U_ID(M4U_LARB6_ID, 30)
+
+/* CCU */
+#define M4U_PORT_CCU0 MTK_M4U_ID(M4U_LARB7_ID, 0)
+#define M4U_PORT_CCU1 MTK_M4U_ID(M4U_LARB7_ID, 1)
+
+#endif
diff --git a/include/linux/amd-iommu.h b/include/linux/amd-iommu.h
index 4a4d00646040..21e950e4ab62 100644
--- a/include/linux/amd-iommu.h
+++ b/include/linux/amd-iommu.h
@@ -184,6 +184,9 @@ extern int amd_iommu_register_ga_log_notifier(int (*notifier)(u32));
extern int
amd_iommu_update_ga(int cpu, bool is_run, void *data);
+extern int amd_iommu_activate_guest_mode(void *data);
+extern int amd_iommu_deactivate_guest_mode(void *data);
+
#else /* defined(CONFIG_AMD_IOMMU) && defined(CONFIG_IRQ_REMAP) */
static inline int
@@ -198,6 +201,15 @@ amd_iommu_update_ga(int cpu, bool is_run, void *data)
return 0;
}
+static inline int amd_iommu_activate_guest_mode(void *data)
+{
+ return 0;
+}
+
+static inline int amd_iommu_deactivate_guest_mode(void *data)
+{
+ return 0;
+}
#endif /* defined(CONFIG_AMD_IOMMU) && defined(CONFIG_IRQ_REMAP) */
#endif /* _ASM_X86_AMD_IOMMU_H */
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index feff3fe4467e..1b1fa1557e68 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -311,6 +311,7 @@ enum req_flag_bits {
__REQ_RAHEAD, /* read ahead, can fail anytime */
__REQ_BACKGROUND, /* background IO */
__REQ_NOWAIT, /* Don't wait if request will block */
+ __REQ_NOWAIT_INLINE, /* Return would-block error inline */
/*
* When a shared kthread needs to issue a bio for a cgroup, doing
* so synchronously can lead to priority inversions as the kthread
@@ -345,6 +346,7 @@ enum req_flag_bits {
#define REQ_RAHEAD (1ULL << __REQ_RAHEAD)
#define REQ_BACKGROUND (1ULL << __REQ_BACKGROUND)
#define REQ_NOWAIT (1ULL << __REQ_NOWAIT)
+#define REQ_NOWAIT_INLINE (1ULL << __REQ_NOWAIT_INLINE)
#define REQ_CGROUP_PUNT (1ULL << __REQ_CGROUP_PUNT)
#define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP)
@@ -418,12 +420,13 @@ static inline int op_stat_group(unsigned int op)
typedef unsigned int blk_qc_t;
#define BLK_QC_T_NONE -1U
+#define BLK_QC_T_EAGAIN -2U
#define BLK_QC_T_SHIFT 16
#define BLK_QC_T_INTERNAL (1U << 31)
static inline bool blk_qc_t_valid(blk_qc_t cookie)
{
- return cookie != BLK_QC_T_NONE;
+ return cookie != BLK_QC_T_NONE && cookie != BLK_QC_T_EAGAIN;
}
static inline unsigned int blk_qc_t_to_queue_num(blk_qc_t cookie)
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 4fc6454f7ebb..ed11ef594378 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -272,6 +272,8 @@
#define dma_frcd_type(d) ((d >> 30) & 1)
#define dma_frcd_fault_reason(c) (c & 0xff)
#define dma_frcd_source_id(c) (c & 0xffff)
+#define dma_frcd_pasid_value(c) (((c) >> 8) & 0xfffff)
+#define dma_frcd_pasid_present(c) (((c) >> 31) & 1)
/* low 64 bit */
#define dma_frcd_page_addr(d) (d & (((u64)-1) << PAGE_SHIFT))
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index b5a450a3bb47..ec7a13405f10 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -1,7 +1,9 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __IO_PGTABLE_H
#define __IO_PGTABLE_H
+
#include <linux/bitops.h>
+#include <linux/iommu.h>
/*
* Public API for use by IOMMU drivers
@@ -17,22 +19,31 @@ enum io_pgtable_fmt {
};
/**
- * struct iommu_gather_ops - IOMMU callbacks for TLB and page table management.
+ * struct iommu_flush_ops - IOMMU callbacks for TLB and page table management.
*
- * @tlb_flush_all: Synchronously invalidate the entire TLB context.
- * @tlb_add_flush: Queue up a TLB invalidation for a virtual address range.
- * @tlb_sync: Ensure any queued TLB invalidation has taken effect, and
- * any corresponding page table updates are visible to the
- * IOMMU.
+ * @tlb_flush_all: Synchronously invalidate the entire TLB context.
+ * @tlb_flush_walk: Synchronously invalidate all intermediate TLB state
+ * (sometimes referred to as the "walk cache") for a virtual
+ * address range.
+ * @tlb_flush_leaf: Synchronously invalidate all leaf TLB state for a virtual
+ * address range.
+ * @tlb_add_page: Optional callback to queue up leaf TLB invalidation for a
+ * single page. IOMMUs that cannot batch TLB invalidation
+ * operations efficiently will typically issue them here, but
+ * others may decide to update the iommu_iotlb_gather structure
+ * and defer the invalidation until iommu_tlb_sync() instead.
*
* Note that these can all be called in atomic context and must therefore
* not block.
*/
-struct iommu_gather_ops {
+struct iommu_flush_ops {
void (*tlb_flush_all)(void *cookie);
- void (*tlb_add_flush)(unsigned long iova, size_t size, size_t granule,
- bool leaf, void *cookie);
- void (*tlb_sync)(void *cookie);
+ void (*tlb_flush_walk)(unsigned long iova, size_t size, size_t granule,
+ void *cookie);
+ void (*tlb_flush_leaf)(unsigned long iova, size_t size, size_t granule,
+ void *cookie);
+ void (*tlb_add_page)(struct iommu_iotlb_gather *gather,
+ unsigned long iova, size_t granule, void *cookie);
};
/**
@@ -65,10 +76,9 @@ struct io_pgtable_cfg {
* (unmapped) entries but the hardware might do so anyway, perform
* TLB maintenance when mapping as well as when unmapping.
*
- * IO_PGTABLE_QUIRK_ARM_MTK_4GB: (ARM v7s format) Set bit 9 in all
- * PTEs, for Mediatek IOMMUs which treat it as a 33rd address bit
- * when the SoC is in "4GB mode" and they can only access the high
- * remap of DRAM (0x1_00000000 to 0x1_ffffffff).
+ * IO_PGTABLE_QUIRK_ARM_MTK_EXT: (ARM v7s format) MediaTek IOMMUs extend
+ * to support up to 34 bits PA where the bit32 and bit33 are
+ * encoded in the bit9 and bit4 of the PTE respectively.
*
* IO_PGTABLE_QUIRK_NON_STRICT: Skip issuing synchronous leaf TLBIs
* on unmap, for DMA domains using the flush queue mechanism for
@@ -77,14 +87,14 @@ struct io_pgtable_cfg {
#define IO_PGTABLE_QUIRK_ARM_NS BIT(0)
#define IO_PGTABLE_QUIRK_NO_PERMS BIT(1)
#define IO_PGTABLE_QUIRK_TLBI_ON_MAP BIT(2)
- #define IO_PGTABLE_QUIRK_ARM_MTK_4GB BIT(3)
+ #define IO_PGTABLE_QUIRK_ARM_MTK_EXT BIT(3)
#define IO_PGTABLE_QUIRK_NON_STRICT BIT(4)
unsigned long quirks;
unsigned long pgsize_bitmap;
unsigned int ias;
unsigned int oas;
bool coherent_walk;
- const struct iommu_gather_ops *tlb;
+ const struct iommu_flush_ops *tlb;
struct device *iommu_dev;
/* Low-level data specific to the table format */
@@ -128,7 +138,7 @@ struct io_pgtable_ops {
int (*map)(struct io_pgtable_ops *ops, unsigned long iova,
phys_addr_t paddr, size_t size, int prot);
size_t (*unmap)(struct io_pgtable_ops *ops, unsigned long iova,
- size_t size);
+ size_t size, struct iommu_iotlb_gather *gather);
phys_addr_t (*iova_to_phys)(struct io_pgtable_ops *ops,
unsigned long iova);
};
@@ -184,15 +194,27 @@ static inline void io_pgtable_tlb_flush_all(struct io_pgtable *iop)
iop->cfg.tlb->tlb_flush_all(iop->cookie);
}
-static inline void io_pgtable_tlb_add_flush(struct io_pgtable *iop,
- unsigned long iova, size_t size, size_t granule, bool leaf)
+static inline void
+io_pgtable_tlb_flush_walk(struct io_pgtable *iop, unsigned long iova,
+ size_t size, size_t granule)
+{
+ iop->cfg.tlb->tlb_flush_walk(iova, size, granule, iop->cookie);
+}
+
+static inline void
+io_pgtable_tlb_flush_leaf(struct io_pgtable *iop, unsigned long iova,
+ size_t size, size_t granule)
{
- iop->cfg.tlb->tlb_add_flush(iova, size, granule, leaf, iop->cookie);
+ iop->cfg.tlb->tlb_flush_leaf(iova, size, granule, iop->cookie);
}
-static inline void io_pgtable_tlb_sync(struct io_pgtable *iop)
+static inline void
+io_pgtable_tlb_add_page(struct io_pgtable *iop,
+ struct iommu_iotlb_gather * gather, unsigned long iova,
+ size_t granule)
{
- iop->cfg.tlb->tlb_sync(iop->cookie);
+ if (iop->cfg.tlb->tlb_add_page)
+ iop->cfg.tlb->tlb_add_page(gather, iova, granule, iop->cookie);
}
/**
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index fdc355ccc570..29bac5345563 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -192,6 +192,23 @@ struct iommu_sva_ops {
#ifdef CONFIG_IOMMU_API
/**
+ * struct iommu_iotlb_gather - Range information for a pending IOTLB flush
+ *
+ * @start: IOVA representing the start of the range to be flushed
+ * @end: IOVA representing the end of the range to be flushed (exclusive)
+ * @pgsize: The interval at which to perform the flush
+ *
+ * This structure is intended to be updated by multiple calls to the
+ * ->unmap() function in struct iommu_ops before eventually being passed
+ * into ->iotlb_sync().
+ */
+struct iommu_iotlb_gather {
+ unsigned long start;
+ unsigned long end;
+ size_t pgsize;
+};
+
+/**
* struct iommu_ops - iommu ops and capabilities
* @capable: check capability
* @domain_alloc: allocate iommu domain
@@ -201,7 +218,6 @@ struct iommu_sva_ops {
* @map: map a physically contiguous memory region to an iommu domain
* @unmap: unmap a physically contiguous memory region from an iommu domain
* @flush_iotlb_all: Synchronously flush all hardware TLBs for this domain
- * @iotlb_range_add: Add a given iova range to the flush queue for this domain
* @iotlb_sync_map: Sync mappings created recently using @map to the hardware
* @iotlb_sync: Flush all queued ranges from the hardware TLBs and empty flush
* queue
@@ -242,12 +258,11 @@ struct iommu_ops {
int (*map)(struct iommu_domain *domain, unsigned long iova,
phys_addr_t paddr, size_t size, int prot);
size_t (*unmap)(struct iommu_domain *domain, unsigned long iova,
- size_t size);
+ size_t size, struct iommu_iotlb_gather *iotlb_gather);
void (*flush_iotlb_all)(struct iommu_domain *domain);
- void (*iotlb_range_add)(struct iommu_domain *domain,
- unsigned long iova, size_t size);
void (*iotlb_sync_map)(struct iommu_domain *domain);
- void (*iotlb_sync)(struct iommu_domain *domain);
+ void (*iotlb_sync)(struct iommu_domain *domain,
+ struct iommu_iotlb_gather *iotlb_gather);
phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova);
int (*add_device)(struct device *dev);
void (*remove_device)(struct device *dev);
@@ -378,6 +393,13 @@ static inline struct iommu_device *dev_to_iommu_device(struct device *dev)
return (struct iommu_device *)dev_get_drvdata(dev);
}
+static inline void iommu_iotlb_gather_init(struct iommu_iotlb_gather *gather)
+{
+ *gather = (struct iommu_iotlb_gather) {
+ .start = ULONG_MAX,
+ };
+}
+
#define IOMMU_GROUP_NOTIFY_ADD_DEVICE 1 /* Device added */
#define IOMMU_GROUP_NOTIFY_DEL_DEVICE 2 /* Pre Device removed */
#define IOMMU_GROUP_NOTIFY_BIND_DRIVER 3 /* Pre Driver bind */
@@ -402,7 +424,8 @@ extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova,
size_t size);
extern size_t iommu_unmap_fast(struct iommu_domain *domain,
- unsigned long iova, size_t size);
+ unsigned long iova, size_t size,
+ struct iommu_iotlb_gather *iotlb_gather);
extern size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
struct scatterlist *sg,unsigned int nents, int prot);
extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova);
@@ -413,6 +436,9 @@ extern void iommu_get_resv_regions(struct device *dev, struct list_head *list);
extern void iommu_put_resv_regions(struct device *dev, struct list_head *list);
extern int iommu_request_dm_for_dev(struct device *dev);
extern int iommu_request_dma_domain_for_dev(struct device *dev);
+extern void iommu_set_default_passthrough(bool cmd_line);
+extern void iommu_set_default_translated(bool cmd_line);
+extern bool iommu_default_passthrough(void);
extern struct iommu_resv_region *
iommu_alloc_resv_region(phys_addr_t start, size_t length, int prot,
enum iommu_resv_type type);
@@ -476,17 +502,38 @@ static inline void iommu_flush_tlb_all(struct iommu_domain *domain)
domain->ops->flush_iotlb_all(domain);
}
-static inline void iommu_tlb_range_add(struct iommu_domain *domain,
- unsigned long iova, size_t size)
+static inline void iommu_tlb_sync(struct iommu_domain *domain,
+ struct iommu_iotlb_gather *iotlb_gather)
{
- if (domain->ops->iotlb_range_add)
- domain->ops->iotlb_range_add(domain, iova, size);
+ if (domain->ops->iotlb_sync)
+ domain->ops->iotlb_sync(domain, iotlb_gather);
+
+ iommu_iotlb_gather_init(iotlb_gather);
}
-static inline void iommu_tlb_sync(struct iommu_domain *domain)
+static inline void iommu_iotlb_gather_add_page(struct iommu_domain *domain,
+ struct iommu_iotlb_gather *gather,
+ unsigned long iova, size_t size)
{
- if (domain->ops->iotlb_sync)
- domain->ops->iotlb_sync(domain);
+ unsigned long start = iova, end = start + size;
+
+ /*
+ * If the new page is disjoint from the current range or is mapped at
+ * a different granularity, then sync the TLB so that the gather
+ * structure can be rewritten.
+ */
+ if (gather->pgsize != size ||
+ end < gather->start || start > gather->end) {
+ if (gather->pgsize)
+ iommu_tlb_sync(domain, gather);
+ gather->pgsize = size;
+ }
+
+ if (gather->end < end)
+ gather->end = end;
+
+ if (gather->start > start)
+ gather->start = start;
}
/* PCI device grouping function */
@@ -567,6 +614,7 @@ struct iommu_group {};
struct iommu_fwspec {};
struct iommu_device {};
struct iommu_fault_param {};
+struct iommu_iotlb_gather {};
static inline bool iommu_present(struct bus_type *bus)
{
@@ -621,7 +669,8 @@ static inline size_t iommu_unmap(struct iommu_domain *domain,
}
static inline size_t iommu_unmap_fast(struct iommu_domain *domain,
- unsigned long iova, int gfp_order)
+ unsigned long iova, int gfp_order,
+ struct iommu_iotlb_gather *iotlb_gather)
{
return 0;
}
@@ -637,12 +686,8 @@ static inline void iommu_flush_tlb_all(struct iommu_domain *domain)
{
}
-static inline void iommu_tlb_range_add(struct iommu_domain *domain,
- unsigned long iova, size_t size)
-{
-}
-
-static inline void iommu_tlb_sync(struct iommu_domain *domain)
+static inline void iommu_tlb_sync(struct iommu_domain *domain,
+ struct iommu_iotlb_gather *iotlb_gather)
{
}
@@ -694,6 +739,19 @@ static inline int iommu_request_dma_domain_for_dev(struct device *dev)
return -ENODEV;
}
+static inline void iommu_set_default_passthrough(bool cmd_line)
+{
+}
+
+static inline void iommu_set_default_translated(bool cmd_line)
+{
+}
+
+static inline bool iommu_default_passthrough(void)
+{
+ return true;
+}
+
static inline int iommu_attach_group(struct iommu_domain *domain,
struct iommu_group *group)
{
@@ -827,6 +885,16 @@ static inline struct iommu_device *dev_to_iommu_device(struct device *dev)
return NULL;
}
+static inline void iommu_iotlb_gather_init(struct iommu_iotlb_gather *gather)
+{
+}
+
+static inline void iommu_iotlb_gather_add_page(struct iommu_domain *domain,
+ struct iommu_iotlb_gather *gather,
+ unsigned long iova, size_t size)
+{
+}
+
static inline void iommu_device_unregister(struct iommu_device *iommu)
{
}
diff --git a/include/linux/omap-iommu.h b/include/linux/omap-iommu.h
index 153bf25b4df3..2c32ca09df02 100644
--- a/include/linux/omap-iommu.h
+++ b/include/linux/omap-iommu.h
@@ -10,12 +10,27 @@
#ifndef _OMAP_IOMMU_H_
#define _OMAP_IOMMU_H_
+struct iommu_domain;
+
#ifdef CONFIG_OMAP_IOMMU
extern void omap_iommu_save_ctx(struct device *dev);
extern void omap_iommu_restore_ctx(struct device *dev);
+
+int omap_iommu_domain_deactivate(struct iommu_domain *domain);
+int omap_iommu_domain_activate(struct iommu_domain *domain);
#else
static inline void omap_iommu_save_ctx(struct device *dev) {}
static inline void omap_iommu_restore_ctx(struct device *dev) {}
+
+static inline int omap_iommu_domain_deactivate(struct iommu_domain *domain)
+{
+ return -ENODEV;
+}
+
+static inline int omap_iommu_domain_activate(struct iommu_domain *domain)
+{
+ return -ENODEV;
+}
#endif
#endif
diff --git a/include/linux/platform_data/iommu-omap.h b/include/linux/platform_data/iommu-omap.h
index 44d913a7580c..8474a0208b34 100644
--- a/include/linux/platform_data/iommu-omap.h
+++ b/include/linux/platform_data/iommu-omap.h
@@ -13,4 +13,8 @@ struct iommu_platform_data {
const char *reset_name;
int (*assert_reset)(struct platform_device *pdev, const char *name);
int (*deassert_reset)(struct platform_device *pdev, const char *name);
+ int (*device_enable)(struct platform_device *pdev);
+ int (*device_idle)(struct platform_device *pdev);
+ int (*set_pwrdm_constraint)(struct platform_device *pdev, bool request,
+ u8 *pwrst);
};
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 361f62bb4a8e..cde3dc18e21a 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -46,13 +46,17 @@ enum dma_sync_target {
extern phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
dma_addr_t tbl_dma_addr,
- phys_addr_t phys, size_t size,
+ phys_addr_t phys,
+ size_t mapping_size,
+ size_t alloc_size,
enum dma_data_direction dir,
unsigned long attrs);
extern void swiotlb_tbl_unmap_single(struct device *hwdev,
phys_addr_t tlb_addr,
- size_t size, enum dma_data_direction dir,
+ size_t mapping_size,
+ size_t alloc_size,
+ enum dma_data_direction dir,
unsigned long attrs);
extern void swiotlb_tbl_sync_single(struct device *hwdev,
diff --git a/include/soc/mediatek/smi.h b/include/soc/mediatek/smi.h
index 79b74ced9d91..5a34b87d89e3 100644
--- a/include/soc/mediatek/smi.h
+++ b/include/soc/mediatek/smi.h
@@ -20,11 +20,6 @@ struct mtk_smi_larb_iommu {
unsigned int mmu;
};
-struct mtk_smi_iommu {
- unsigned int larb_nr;
- struct mtk_smi_larb_iommu larb_imu[MTK_LARB_NR_MAX];
-};
-
/*
* mtk_smi_larb_get: Enable the power domain and clocks for this local arbiter.
* It also initialize some basic setting(like iommu).
diff --git a/include/trace/events/intel_iommu.h b/include/trace/events/intel_iommu.h
new file mode 100644
index 000000000000..54e61d456cdf
--- /dev/null
+++ b/include/trace/events/intel_iommu.h
@@ -0,0 +1,106 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Intel IOMMU trace support
+ *
+ * Copyright (C) 2019 Intel Corporation
+ *
+ * Author: Lu Baolu <baolu.lu@linux.intel.com>
+ */
+#ifdef CONFIG_INTEL_IOMMU
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM intel_iommu
+
+#if !defined(_TRACE_INTEL_IOMMU_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_INTEL_IOMMU_H
+
+#include <linux/tracepoint.h>
+#include <linux/intel-iommu.h>
+
+DECLARE_EVENT_CLASS(dma_map,
+ TP_PROTO(struct device *dev, dma_addr_t dev_addr, phys_addr_t phys_addr,
+ size_t size),
+
+ TP_ARGS(dev, dev_addr, phys_addr, size),
+
+ TP_STRUCT__entry(
+ __string(dev_name, dev_name(dev))
+ __field(dma_addr_t, dev_addr)
+ __field(phys_addr_t, phys_addr)
+ __field(size_t, size)
+ ),
+
+ TP_fast_assign(
+ __assign_str(dev_name, dev_name(dev));
+ __entry->dev_addr = dev_addr;
+ __entry->phys_addr = phys_addr;
+ __entry->size = size;
+ ),
+
+ TP_printk("dev=%s dev_addr=0x%llx phys_addr=0x%llx size=%zu",
+ __get_str(dev_name),
+ (unsigned long long)__entry->dev_addr,
+ (unsigned long long)__entry->phys_addr,
+ __entry->size)
+);
+
+DEFINE_EVENT(dma_map, map_single,
+ TP_PROTO(struct device *dev, dma_addr_t dev_addr, phys_addr_t phys_addr,
+ size_t size),
+ TP_ARGS(dev, dev_addr, phys_addr, size)
+);
+
+DEFINE_EVENT(dma_map, map_sg,
+ TP_PROTO(struct device *dev, dma_addr_t dev_addr, phys_addr_t phys_addr,
+ size_t size),
+ TP_ARGS(dev, dev_addr, phys_addr, size)
+);
+
+DEFINE_EVENT(dma_map, bounce_map_single,
+ TP_PROTO(struct device *dev, dma_addr_t dev_addr, phys_addr_t phys_addr,
+ size_t size),
+ TP_ARGS(dev, dev_addr, phys_addr, size)
+);
+
+DECLARE_EVENT_CLASS(dma_unmap,
+ TP_PROTO(struct device *dev, dma_addr_t dev_addr, size_t size),
+
+ TP_ARGS(dev, dev_addr, size),
+
+ TP_STRUCT__entry(
+ __string(dev_name, dev_name(dev))
+ __field(dma_addr_t, dev_addr)
+ __field(size_t, size)
+ ),
+
+ TP_fast_assign(
+ __assign_str(dev_name, dev_name(dev));
+ __entry->dev_addr = dev_addr;
+ __entry->size = size;
+ ),
+
+ TP_printk("dev=%s dev_addr=0x%llx size=%zu",
+ __get_str(dev_name),
+ (unsigned long long)__entry->dev_addr,
+ __entry->size)
+);
+
+DEFINE_EVENT(dma_unmap, unmap_single,
+ TP_PROTO(struct device *dev, dma_addr_t dev_addr, size_t size),
+ TP_ARGS(dev, dev_addr, size)
+);
+
+DEFINE_EVENT(dma_unmap, unmap_sg,
+ TP_PROTO(struct device *dev, dma_addr_t dev_addr, size_t size),
+ TP_ARGS(dev, dev_addr, size)
+);
+
+DEFINE_EVENT(dma_unmap, bounce_unmap_single,
+ TP_PROTO(struct device *dev, dma_addr_t dev_addr, size_t size),
+ TP_ARGS(dev, dev_addr, size)
+);
+
+#endif /* _TRACE_INTEL_IOMMU_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
+#endif /* CONFIG_INTEL_IOMMU */
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 706113c6bebc..8402b29c280f 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -305,7 +305,7 @@ void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
dma_direct_sync_single_for_cpu(dev, addr, size, dir);
if (unlikely(is_swiotlb_buffer(phys)))
- swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs);
+ swiotlb_tbl_unmap_single(dev, phys, size, size, dir, attrs);
}
EXPORT_SYMBOL(dma_direct_unmap_page);
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 9de232229063..796a44f8ef5a 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -444,7 +444,9 @@ static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr,
phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
dma_addr_t tbl_dma_addr,
- phys_addr_t orig_addr, size_t size,
+ phys_addr_t orig_addr,
+ size_t mapping_size,
+ size_t alloc_size,
enum dma_data_direction dir,
unsigned long attrs)
{
@@ -464,6 +466,12 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
pr_warn_once("%s is active and system is using DMA bounce buffers\n",
sme_active() ? "SME" : "SEV");
+ if (mapping_size > alloc_size) {
+ dev_warn_once(hwdev, "Invalid sizes (mapping: %zd bytes, alloc: %zd bytes)",
+ mapping_size, alloc_size);
+ return (phys_addr_t)DMA_MAPPING_ERROR;
+ }
+
mask = dma_get_seg_boundary(hwdev);
tbl_dma_addr &= mask;
@@ -471,8 +479,8 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
offset_slots = ALIGN(tbl_dma_addr, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
/*
- * Carefully handle integer overflow which can occur when mask == ~0UL.
- */
+ * Carefully handle integer overflow which can occur when mask == ~0UL.
+ */
max_slots = mask + 1
? ALIGN(mask + 1, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT
: 1UL << (BITS_PER_LONG - IO_TLB_SHIFT);
@@ -481,8 +489,8 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
* For mappings greater than or equal to a page, we limit the stride
* (and hence alignment) to a page size.
*/
- nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
- if (size >= PAGE_SIZE)
+ nslots = ALIGN(alloc_size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
+ if (alloc_size >= PAGE_SIZE)
stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT));
else
stride = 1;
@@ -547,7 +555,7 @@ not_found:
spin_unlock_irqrestore(&io_tlb_lock, flags);
if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit())
dev_warn(hwdev, "swiotlb buffer is full (sz: %zd bytes), total %lu (slots), used %lu (slots)\n",
- size, io_tlb_nslabs, tmp_io_tlb_used);
+ alloc_size, io_tlb_nslabs, tmp_io_tlb_used);
return (phys_addr_t)DMA_MAPPING_ERROR;
found:
io_tlb_used += nslots;
@@ -562,7 +570,7 @@ found:
io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT);
if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
- swiotlb_bounce(orig_addr, tlb_addr, size, DMA_TO_DEVICE);
+ swiotlb_bounce(orig_addr, tlb_addr, mapping_size, DMA_TO_DEVICE);
return tlb_addr;
}
@@ -571,11 +579,11 @@ found:
* tlb_addr is the physical address of the bounce buffer to unmap.
*/
void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
- size_t size, enum dma_data_direction dir,
- unsigned long attrs)
+ size_t mapping_size, size_t alloc_size,
+ enum dma_data_direction dir, unsigned long attrs)
{
unsigned long flags;
- int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
+ int i, count, nslots = ALIGN(alloc_size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT;
phys_addr_t orig_addr = io_tlb_orig_addr[index];
@@ -585,7 +593,7 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
if (orig_addr != INVALID_PHYS_ADDR &&
!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
- swiotlb_bounce(orig_addr, tlb_addr, size, DMA_FROM_DEVICE);
+ swiotlb_bounce(orig_addr, tlb_addr, mapping_size, DMA_FROM_DEVICE);
/*
* Return the buffer to the free list by setting the corresponding
@@ -665,14 +673,14 @@ bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr,
/* Oh well, have to allocate and map a bounce buffer. */
*phys = swiotlb_tbl_map_single(dev, __phys_to_dma(dev, io_tlb_start),
- *phys, size, dir, attrs);
+ *phys, size, size, dir, attrs);
if (*phys == (phys_addr_t)DMA_MAPPING_ERROR)
return false;
/* Ensure that the address returned is DMA'ble */
*dma_addr = __phys_to_dma(dev, *phys);
if (unlikely(!dma_capable(dev, *dma_addr, size))) {
- swiotlb_tbl_unmap_single(dev, *phys, size, dir,
+ swiotlb_tbl_unmap_single(dev, *phys, size, size, dir,
attrs | DMA_ATTR_SKIP_CPU_SYNC);
return false;
}