Merge branches 'for-next/misc', 'for-next/vmcoreinfo', 'for-next/cpufeature',...

Merge branches 'for-next/misc', 'for-next/vmcoreinfo', 'for-next/cpufeature', 'for-next/acpi', 'for-next/perf', 'for-next/timens', 'for-next/msi-iommu' and 'for-next/trivial' into for-next/core

* for-next/misc:
  : Miscellaneous fixes and cleanups
  arm64: use IRQ_STACK_SIZE instead of THREAD_SIZE for irq stack
  arm64/mm: save memory access in check_and_switch_context() fast switch path
  recordmcount: only record relocation of type R_AARCH64_CALL26 on arm64.
  arm64: Reserve HWCAP2_MTE as (1 << 18)
  arm64/entry: deduplicate SW PAN entry/exit routines
  arm64: s/AMEVTYPE/AMEVTYPER
  arm64/hugetlb: Reserve CMA areas for gigantic pages on 16K and 64K configs
  arm64: stacktrace: Move export for save_stack_trace_tsk()
  smccc: Make constants available to assembly
  arm64/mm: Redefine CONT_{PTE, PMD}_SHIFT
  arm64/defconfig: Enable CONFIG_KEXEC_FILE
  arm64: Document sysctls for emulated deprecated instructions
  arm64/panic: Unify all three existing notifier blocks
  arm64/module: Optimize module load time by optimizing PLT counting

* for-next/vmcoreinfo:
  : Export the virtual and physical address sizes in vmcoreinfo
  arm64/crash_core: Export TCR_EL1.T1SZ in vmcoreinfo
  crash_core, vmcoreinfo: Append 'MAX_PHYSMEM_BITS' to vmcoreinfo

* for-next/cpufeature:
  : CPU feature handling cleanups
  arm64/cpufeature: Validate feature bits spacing in arm64_ftr_regs[]
  arm64/cpufeature: Replace all open bits shift encodings with macros
  arm64/cpufeature: Add remaining feature bits in ID_AA64MMFR2 register
  arm64/cpufeature: Add remaining feature bits in ID_AA64MMFR1 register
  arm64/cpufeature: Add remaining feature bits in ID_AA64MMFR0 register

* for-next/acpi:
  : ACPI updates for arm64
  arm64/acpi: disallow writeable AML opregion mapping for EFI code regions
  arm64/acpi: disallow AML memory opregions to access kernel memory

* for-next/perf:
  : perf updates for arm64
  arm64: perf: Expose some new events via sysfs
  tools headers UAPI: Update tools's copy of linux/perf_event.h
  arm64: perf: Add cap_user_time_short
  perf: Add perf_event_mmap_page::cap_user_time_short ABI
  arm64: perf: Only advertise cap_user_time for arch_timer
  arm64: perf: Implement correct cap_user_time
  time/sched_clock: Use raw_read_seqcount_latch()
  sched_clock: Expose struct clock_read_data
  arm64: perf: Correct the event index in sysfs
  perf/smmuv3: To simplify code for ioremap page in pmcg

* for-next/timens:
  : Time namespace support for arm64
  arm64: enable time namespace support
  arm64/vdso: Restrict splitting VVAR VMA
  arm64/vdso: Handle faults on timens page
  arm64/vdso: Add time namespace page
  arm64/vdso: Zap vvar pages when switching to a time namespace
  arm64/vdso: use the fault callback to map vvar pages

* for-next/msi-iommu:
  : Make the MSI/IOMMU input/output ID translation PCI agnostic, augment the
  : MSI/IOMMU ACPI/OF ID mapping APIs to accept an input ID bus-specific parameter
  : and apply the resulting changes to the device ID space provided by the
  : Freescale FSL bus
  bus: fsl-mc: Add ACPI support for fsl-mc
  bus/fsl-mc: Refactor the MSI domain creation in the DPRC driver
  of/irq: Make of_msi_map_rid() PCI bus agnostic
  of/irq: make of_msi_map_get_device_domain() bus agnostic
  dt-bindings: arm: fsl: Add msi-map device-tree binding for fsl-mc bus
  of/device: Add input id to of_dma_configure()
  of/iommu: Make of_map_rid() PCI agnostic
  ACPI/IORT: Add an input ID to acpi_dma_configure()
  ACPI/IORT: Remove useless PCI bus walk
  ACPI/IORT: Make iort_msi_map_rid() PCI agnostic
  ACPI/IORT: Make iort_get_device_domain IRQ domain agnostic
  ACPI/IORT: Make iort_match_node_callback walk the ACPI namespace for NC

* for-next/trivial:
  : Trivial fixes
  arm64: sigcontext.h: delete duplicated word
  arm64: ptrace.h: delete duplicated word
  arm64: pgtable-hwdef.h: delete duplicated words

Documentation/admin-guide/kdump/vmcoreinfo.rst

@@ -93,6 +93,11 @@ It exists in the sparse memory mapping model, and it is also somewhat
 similar to the mem_map variable, both of them are used to translate an
 address.
 
+MAX_PHYSMEM_BITS
+----------------
+
+Defines the maximum supported physical address space memory.
+
 page
 ----
 
@@ -399,6 +404,17 @@ KERNELPACMASK
 The mask to extract the Pointer Authentication Code from a kernel virtual
 address.
 
+TCR_EL1.T1SZ
+------------
+
+Indicates the size offset of the memory region addressed by TTBR1_EL1.
+The region size is 2^(64-T1SZ) bytes.
+
+TTBR1_EL1 is the table base address register specified by ARMv8-A
+architecture which is used to lookup the page-tables for the Virtual
+addresses in the higher VA range (refer to ARMv8 ARM document for
+more details).
+
 arm
 ===
 

Documentation/devicetree/bindings/misc/fsl,qoriq-mc.txt

@@ -28,6 +28,16 @@ Documentation/devicetree/bindings/iommu/iommu.txt.
 For arm-smmu binding, see:
 Documentation/devicetree/bindings/iommu/arm,smmu.yaml.
 
+The MSI writes are accompanied by sideband data which is derived from the ICID.
+The msi-map property is used to associate the devices with both the ITS
+controller and the sideband data which accompanies the writes.
+
+For generic MSI bindings, see
+Documentation/devicetree/bindings/interrupt-controller/msi.txt.
+
+For GICv3 and GIC ITS bindings, see:
+Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml.
+
 Required properties:
 
     - compatible
@@ -49,11 +59,6 @@ Required properties:
                         region may not be present in some scenarios, such
                         as in the device tree presented to a virtual machine.
 
-    - msi-parent
-        Value type: <phandle>
-        Definition: Must be present and point to the MSI controller node
-                    handling message interrupts for the MC.
-
     - ranges
         Value type: <prop-encoded-array>
         Definition: A standard property.  Defines the mapping between the child
@@ -119,6 +124,28 @@ Optional properties:
   associated with the listed IOMMU, with the iommu-specifier
   (i - icid-base + iommu-base).
 
+- msi-map: Maps an ICID to a GIC ITS and associated msi-specifier
+  data.
+
+  The property is an arbitrary number of tuples of
+  (icid-base,gic-its,msi-base,length).
+
+  Any ICID in the interval [icid-base, icid-base + length) is
+  associated with the listed GIC ITS, with the msi-specifier
+  (i - icid-base + msi-base).
+
+Deprecated properties:
+
+    - msi-parent
+        Value type: <phandle>
+        Definition: Describes the MSI controller node handling message
+                    interrupts for the MC. When there is no translation
+                    between the ICID and deviceID this property can be used
+                    to describe the MSI controller used by the devices on the
+                    mc-bus.
+                    The use of this property for mc-bus is deprecated. Please
+                    use msi-map.
+
 Example:
 
         smmu: iommu@5000000 {
@@ -128,13 +155,24 @@ Example:
                ...
         };
 
+        gic: interrupt-controller@6000000 {
+               compatible = "arm,gic-v3";
+               ...
+        }
+        its: gic-its@6020000 {
+               compatible = "arm,gic-v3-its";
+               msi-controller;
+               ...
+        };
+
         fsl_mc: fsl-mc@80c000000 {
                 compatible = "fsl,qoriq-mc";
                 reg = <0x00000008 0x0c000000 0 0x40>,    /* MC portal base */
                       <0x00000000 0x08340000 0 0x40000>; /* MC control reg */
-                msi-parent = <&its>;
                 /* define map for ICIDs 23-64 */
                 iommu-map = <23 &smmu 23 41>;
+                /* define msi map for ICIDs 23-64 */
+                msi-map = <23 &its 23 41>;
                 #address-cells = <3>;
                 #size-cells = <1>;
 

arch/arm64/Kconfig

@@ -118,6 +118,7 @@ config ARM64
 	select GENERIC_STRNLEN_USER
 	select GENERIC_TIME_VSYSCALL
 	select GENERIC_GETTIMEOFDAY
+	select GENERIC_VDSO_TIME_NS
 	select HANDLE_DOMAIN_IRQ
 	select HARDIRQS_SW_RESEND
 	select HAVE_PCI

arch/arm64/include/asm/acpi.h

@@ -47,20 +47,7 @@
 pgprot_t __acpi_get_mem_attribute(phys_addr_t addr);
 
 /* ACPI table mapping after acpi_permanent_mmap is set */
-static inline void __iomem *acpi_os_ioremap(acpi_physical_address phys,
-					    acpi_size size)
-{
-	/* For normal memory we already have a cacheable mapping. */
-	if (memblock_is_map_memory(phys))
-		return (void __iomem *)__phys_to_virt(phys);
-
-	/*
-	 * We should still honor the memory's attribute here because
-	 * crash dump kernel possibly excludes some ACPI (reclaim)
-	 * regions from memblock list.
-	 */
-	return __ioremap(phys, size, __acpi_get_mem_attribute(phys));
-}
+void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size);
 #define acpi_os_ioremap acpi_os_ioremap
 
 typedef u64 phys_cpuid_t;

arch/arm64/include/asm/perf_event.h

@@ -72,6 +72,13 @@
 #define ARMV8_PMUV3_PERFCTR_LL_CACHE_RD				0x36
 #define ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD			0x37
 #define ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD			0x38
+#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_LMISS_RD			0x39
+#define ARMV8_PMUV3_PERFCTR_OP_RETIRED				0x3A
+#define ARMV8_PMUV3_PERFCTR_OP_SPEC				0x3B
+#define ARMV8_PMUV3_PERFCTR_STALL				0x3C
+#define ARMV8_PMUV3_PERFCTR_STALL_SLOT_BACKEND			0x3D
+#define ARMV8_PMUV3_PERFCTR_STALL_SLOT_FRONTEND			0x3E
+#define ARMV8_PMUV3_PERFCTR_STALL_SLOT				0x3F
 
 /* Statistical profiling extension microarchitectural events */
 #define	ARMV8_SPE_PERFCTR_SAMPLE_POP				0x4000
@@ -79,6 +86,26 @@
 #define	ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE			0x4002
 #define	ARMV8_SPE_PERFCTR_SAMPLE_COLLISION			0x4003
 
+/* AMUv1 architecture events */
+#define	ARMV8_AMU_PERFCTR_CNT_CYCLES				0x4004
+#define	ARMV8_AMU_PERFCTR_STALL_BACKEND_MEM			0x4005
+
+/* long-latency read miss events */
+#define	ARMV8_PMUV3_PERFCTR_L1I_CACHE_LMISS			0x4006
+#define	ARMV8_PMUV3_PERFCTR_L2D_CACHE_LMISS_RD			0x4009
+#define	ARMV8_PMUV3_PERFCTR_L2I_CACHE_LMISS			0x400A
+#define	ARMV8_PMUV3_PERFCTR_L3D_CACHE_LMISS_RD			0x400B
+
+/* additional latency from alignment events */
+#define	ARMV8_PMUV3_PERFCTR_LDST_ALIGN_LAT			0x4020
+#define	ARMV8_PMUV3_PERFCTR_LD_ALIGN_LAT			0x4021
+#define	ARMV8_PMUV3_PERFCTR_ST_ALIGN_LAT			0x4022
+
+/* Armv8.5 Memory Tagging Extension events */
+#define	ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED			0x4024
+#define	ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_RD			0x4025
+#define	ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_WR			0x4026
+
 /* ARMv8 recommended implementation defined event types */
 #define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_RD			0x40
 #define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR			0x41

arch/arm64/include/asm/pgtable-hwdef.h

@@ -29,7 +29,7 @@
  * Size mapped by an entry at level n ( 0 <= n <= 3)
  * We map (PAGE_SHIFT - 3) at all translation levels and PAGE_SHIFT bits
  * in the final page. The maximum number of translation levels supported by
- * the architecture is 4. Hence, starting at at level n, we have further
+ * the architecture is 4. Hence, starting at level n, we have further
  * ((4 - n) - 1) levels of translation excluding the offset within the page.
  * So, the total number of bits mapped by an entry at level n is :
  *
@@ -98,7 +98,7 @@
 #define CONT_PMDS		(1 << (CONT_PMD_SHIFT - PMD_SHIFT))
 #define CONT_PMD_SIZE		(CONT_PMDS * PMD_SIZE)
 #define CONT_PMD_MASK		(~(CONT_PMD_SIZE - 1))
-/* the the numerical offset of the PTE within a range of CONT_PTES */
+/* the numerical offset of the PTE within a range of CONT_PTES */
 #define CONT_RANGE_OFFSET(addr) (((addr)>>PAGE_SHIFT)&(CONT_PTES-1))
 
 /*
@@ -216,6 +216,7 @@
 #define TCR_TxSZ(x)		(TCR_T0SZ(x) | TCR_T1SZ(x))
 #define TCR_TxSZ_WIDTH		6
 #define TCR_T0SZ_MASK		(((UL(1) << TCR_TxSZ_WIDTH) - 1) << TCR_T0SZ_OFFSET)
+#define TCR_T1SZ_MASK		(((UL(1) << TCR_TxSZ_WIDTH) - 1) << TCR_T1SZ_OFFSET)
 
 #define TCR_EPD0_SHIFT		7
 #define TCR_EPD0_MASK		(UL(1) << TCR_EPD0_SHIFT)

arch/arm64/include/asm/ptrace.h

@@ -27,7 +27,7 @@
  *
  * Some code sections either automatically switch back to PSR.I or explicitly
  * require to not use priority masking. If bit GIC_PRIO_PSR_I_SET is included
- * in the  the priority mask, it indicates that PSR.I should be set and
+ * in the priority mask, it indicates that PSR.I should be set and
  * interrupt disabling temporarily does not rely on IRQ priorities.
  */
 #define GIC_PRIO_IRQON			0xe0

arch/arm64/include/asm/sysreg.h

@@ -706,6 +706,9 @@
 #define ID_AA64ZFR0_SVEVER_SVE2		0x1
 
 /* id_aa64mmfr0 */
+#define ID_AA64MMFR0_ECV_SHIFT		60
+#define ID_AA64MMFR0_FGT_SHIFT		56
+#define ID_AA64MMFR0_EXS_SHIFT		44
 #define ID_AA64MMFR0_TGRAN4_2_SHIFT	40
 #define ID_AA64MMFR0_TGRAN64_2_SHIFT	36
 #define ID_AA64MMFR0_TGRAN16_2_SHIFT	32
@@ -734,6 +737,10 @@
 #endif
 
 /* id_aa64mmfr1 */
+#define ID_AA64MMFR1_ETS_SHIFT		36
+#define ID_AA64MMFR1_TWED_SHIFT		32
+#define ID_AA64MMFR1_XNX_SHIFT		28
+#define ID_AA64MMFR1_SPECSEI_SHIFT	24
 #define ID_AA64MMFR1_PAN_SHIFT		20
 #define ID_AA64MMFR1_LOR_SHIFT		16
 #define ID_AA64MMFR1_HPD_SHIFT		12
@@ -746,8 +753,15 @@
 
 /* id_aa64mmfr2 */
 #define ID_AA64MMFR2_E0PD_SHIFT		60
+#define ID_AA64MMFR2_EVT_SHIFT		56
+#define ID_AA64MMFR2_BBM_SHIFT		52
+#define ID_AA64MMFR2_TTL_SHIFT		48
 #define ID_AA64MMFR2_FWB_SHIFT		40
+#define ID_AA64MMFR2_IDS_SHIFT		36
 #define ID_AA64MMFR2_AT_SHIFT		32
+#define ID_AA64MMFR2_ST_SHIFT		28
+#define ID_AA64MMFR2_NV_SHIFT		24
+#define ID_AA64MMFR2_CCIDX_SHIFT	20
 #define ID_AA64MMFR2_LVA_SHIFT		16
 #define ID_AA64MMFR2_IESB_SHIFT		12
 #define ID_AA64MMFR2_LSM_SHIFT		8
@@ -755,6 +769,7 @@
 #define ID_AA64MMFR2_CNP_SHIFT		0
 
 /* id_aa64dfr0 */
+#define ID_AA64DFR0_DOUBLELOCK_SHIFT	36
 #define ID_AA64DFR0_PMSVER_SHIFT	32
 #define ID_AA64DFR0_CTX_CMPS_SHIFT	28
 #define ID_AA64DFR0_WRPS_SHIFT		20
@@ -807,18 +822,40 @@
 #define ID_ISAR6_DP_SHIFT		4
 #define ID_ISAR6_JSCVT_SHIFT		0
 
+#define ID_MMFR0_INNERSHR_SHIFT		28
+#define ID_MMFR0_FCSE_SHIFT		24
+#define ID_MMFR0_AUXREG_SHIFT		20
+#define ID_MMFR0_TCM_SHIFT		16
+#define ID_MMFR0_SHARELVL_SHIFT		12
+#define ID_MMFR0_OUTERSHR_SHIFT		8
+#define ID_MMFR0_PMSA_SHIFT		4
+#define ID_MMFR0_VMSA_SHIFT		0
+
 #define ID_MMFR4_EVT_SHIFT		28
 #define ID_MMFR4_CCIDX_SHIFT		24
 #define ID_MMFR4_LSM_SHIFT		20
 #define ID_MMFR4_HPDS_SHIFT		16
 #define ID_MMFR4_CNP_SHIFT		12
 #define ID_MMFR4_XNX_SHIFT		8
+#define ID_MMFR4_AC2_SHIFT		4
 #define ID_MMFR4_SPECSEI_SHIFT		0
 
 #define ID_MMFR5_ETS_SHIFT		0
 
 #define ID_PFR0_DIT_SHIFT		24
 #define ID_PFR0_CSV2_SHIFT		16
+#define ID_PFR0_STATE3_SHIFT		12
+#define ID_PFR0_STATE2_SHIFT		8
+#define ID_PFR0_STATE1_SHIFT		4
+#define ID_PFR0_STATE0_SHIFT		0
+
+#define ID_DFR0_PERFMON_SHIFT		24
+#define ID_DFR0_MPROFDBG_SHIFT		20
+#define ID_DFR0_MMAPTRC_SHIFT		16
+#define ID_DFR0_COPTRC_SHIFT		12
+#define ID_DFR0_MMAPDBG_SHIFT		8
+#define ID_DFR0_COPSDBG_SHIFT		4
+#define ID_DFR0_COPDBG_SHIFT		0
 
 #define ID_PFR2_SSBS_SHIFT		4
 #define ID_PFR2_CSV3_SHIFT		0
@@ -861,6 +898,11 @@
 #define ID_AA64MMFR0_TGRAN_SUPPORTED	ID_AA64MMFR0_TGRAN64_SUPPORTED
 #endif
 
+#define MVFR2_FPMISC_SHIFT		4
+#define MVFR2_SIMDMISC_SHIFT		0
+
+#define DCZID_DZP_SHIFT			4
+#define DCZID_BS_SHIFT			0
 
 /*
  * The ZCR_ELx_LEN_* definitions intentionally include bits [8:4] which

arch/arm64/include/asm/vdso.h

@@ -12,6 +12,8 @@
  */
 #define VDSO_LBASE	0x0
 
+#define __VVAR_PAGES    2
+
 #ifndef __ASSEMBLY__
 
 #include <generated/vdso-offsets.h>

arch/arm64/include/asm/vdso/compat_gettimeofday.h

@@ -152,6 +152,18 @@ static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
 	return ret;
 }
 
+#ifdef CONFIG_TIME_NS
+static __always_inline const struct vdso_data *__arch_get_timens_vdso_data(void)
+{
+	const struct vdso_data *ret;
+
+	/* See __arch_get_vdso_data(). */
+	asm volatile("mov %0, %1" : "=r"(ret) : "r"(_timens_data));
+
+	return ret;
+}
+#endif
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_VDSO_GETTIMEOFDAY_H */

arch/arm64/include/asm/vdso/gettimeofday.h

@@ -96,6 +96,14 @@ const struct vdso_data *__arch_get_vdso_data(void)
 	return _vdso_data;
 }
 
+#ifdef CONFIG_TIME_NS
+static __always_inline
+const struct vdso_data *__arch_get_timens_vdso_data(void)
+{
+	return _timens_data;
+}
+#endif
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_VDSO_GETTIMEOFDAY_H */

arch/arm64/include/uapi/asm/sigcontext.h

@@ -179,7 +179,7 @@ struct sve_context {
  * The same convention applies when returning from a signal: a caller
  * will need to remove or resize the sve_context block if it wants to
  * make the SVE registers live when they were previously non-live or
- * vice-versa.  This may require the the caller to allocate fresh
+ * vice-versa.  This may require the caller to allocate fresh
  * memory and/or move other context blocks in the signal frame.
  *
  * Changing the vector length during signal return is not permitted:

arch/arm64/kernel/acpi.c

@@ -261,6 +261,81 @@ pgprot_t __acpi_get_mem_attribute(phys_addr_t addr)
 	return __pgprot(PROT_DEVICE_nGnRnE);
 }
 
+void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size)
+{
+	efi_memory_desc_t *md, *region = NULL;
+	pgprot_t prot;
+
+	if (WARN_ON_ONCE(!efi_enabled(EFI_MEMMAP)))
+		return NULL;
+
+	for_each_efi_memory_desc(md) {
+		u64 end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT);
+
+		if (phys < md->phys_addr || phys >= end)
+			continue;
+
+		if (phys + size > end) {
+			pr_warn(FW_BUG "requested region covers multiple EFI memory regions\n");
+			return NULL;
+		}
+		region = md;
+		break;
+	}
+
+	/*
+	 * It is fine for AML to remap regions that are not represented in the
+	 * EFI memory map at all, as it only describes normal memory, and MMIO
+	 * regions that require a virtual mapping to make them accessible to
+	 * the EFI runtime services.
+	 */
+	prot = __pgprot(PROT_DEVICE_nGnRnE);
+	if (region) {
+		switch (region->type) {
+		case EFI_LOADER_CODE:
+		case EFI_LOADER_DATA:
+		case EFI_BOOT_SERVICES_CODE:
+		case EFI_BOOT_SERVICES_DATA:
+		case EFI_CONVENTIONAL_MEMORY:
+		case EFI_PERSISTENT_MEMORY:
+			pr_warn(FW_BUG "requested region covers kernel memory @ %pa\n", &phys);
+			return NULL;
+
+		case EFI_RUNTIME_SERVICES_CODE:
+			/*
+			 * This would be unusual, but not problematic per se,
+			 * as long as we take care not to create a writable
+			 * mapping for executable code.
+			 */
+			prot = PAGE_KERNEL_RO;
+			break;
+
+		case EFI_ACPI_RECLAIM_MEMORY:
+			/*
+			 * ACPI reclaim memory is used to pass firmware tables
+			 * and other data that is intended for consumption by
+			 * the OS only, which may decide it wants to reclaim
+			 * that memory and use it for something else. We never
+			 * do that, but we usually add it to the linear map
+			 * anyway, in which case we should use the existing
+			 * mapping.
+			 */
+			if (memblock_is_map_memory(phys))
+				return (void __iomem *)__phys_to_virt(phys);
+			/* fall through */
+
+		default:
+			if (region->attribute & EFI_MEMORY_WB)
+				prot = PAGE_KERNEL;
+			else if (region->attribute & EFI_MEMORY_WT)
+				prot = __pgprot(PROT_NORMAL_WT);
+			else if (region->attribute & EFI_MEMORY_WC)
+				prot = __pgprot(PROT_NORMAL_NC);
+		}
+	}
+	return __ioremap(phys, size, prot);
+}
+
 /*
  * Claim Synchronous External Aborts as a firmware first notification.
  *

arch/arm64/kernel/crash_core.c

@@ -7,6 +7,14 @@
 #include <linux/crash_core.h>
 #include <asm/cpufeature.h>
 #include <asm/memory.h>
+#include <asm/pgtable-hwdef.h>
+
+static inline u64 get_tcr_el1_t1sz(void);
+
+static inline u64 get_tcr_el1_t1sz(void)
+{
+	return (read_sysreg(tcr_el1) & TCR_T1SZ_MASK) >> TCR_T1SZ_OFFSET;
+}
 
 void arch_crash_save_vmcoreinfo(void)
 {
@@ -16,6 +24,8 @@ void arch_crash_save_vmcoreinfo(void)
 						kimage_voffset);
 	vmcoreinfo_append_str("NUMBER(PHYS_OFFSET)=0x%llx\n",
 						PHYS_OFFSET);
+	vmcoreinfo_append_str("NUMBER(TCR_EL1_T1SZ)=0x%llx\n",
+						get_tcr_el1_t1sz());
 	vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
 	vmcoreinfo_append_str("NUMBER(KERNELPACMASK)=0x%llx\n",
 						system_supports_address_auth() ?

arch/arm64/kernel/perf_event.c

@@ -13,12 +13,15 @@
 #include <asm/sysreg.h>
 #include <asm/virt.h>
 
+#include <clocksource/arm_arch_timer.h>
+
 #include <linux/acpi.h>
 #include <linux/clocksource.h>
 #include <linux/kvm_host.h>
 #include <linux/of.h>
 #include <linux/perf/arm_pmu.h>
 #include <linux/platform_device.h>
+#include <linux/sched_clock.h>
 #include <linux/smp.h>
 
 /* ARMv8 Cortex-A53 specific event types. */
@@ -155,7 +158,7 @@ armv8pmu_events_sysfs_show(struct device *dev,
 
 	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
 
-	return sprintf(page, "event=0x%03llx\n", pmu_attr->id);
+	return sprintf(page, "event=0x%04llx\n", pmu_attr->id);
 }
 
 #define ARMV8_EVENT_ATTR(name, config)						\
@@ -222,10 +225,29 @@ static struct attribute *armv8_pmuv3_event_attrs[] = {
 	ARMV8_EVENT_ATTR(ll_cache_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_RD),
 	ARMV8_EVENT_ATTR(ll_cache_miss_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD),
 	ARMV8_EVENT_ATTR(remote_access_rd, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD),
+	ARMV8_EVENT_ATTR(l1d_cache_lmiss_rd, ARMV8_PMUV3_PERFCTR_L1D_CACHE_LMISS_RD),
+	ARMV8_EVENT_ATTR(op_retired, ARMV8_PMUV3_PERFCTR_OP_RETIRED),
+	ARMV8_EVENT_ATTR(op_spec, ARMV8_PMUV3_PERFCTR_OP_SPEC),
+	ARMV8_EVENT_ATTR(stall, ARMV8_PMUV3_PERFCTR_STALL),
+	ARMV8_EVENT_ATTR(stall_slot_backend, ARMV8_PMUV3_PERFCTR_STALL_SLOT_BACKEND),
+	ARMV8_EVENT_ATTR(stall_slot_frontend, ARMV8_PMUV3_PERFCTR_STALL_SLOT_FRONTEND),
+	ARMV8_EVENT_ATTR(stall_slot, ARMV8_PMUV3_PERFCTR_STALL_SLOT),
 	ARMV8_EVENT_ATTR(sample_pop, ARMV8_SPE_PERFCTR_SAMPLE_POP),
 	ARMV8_EVENT_ATTR(sample_feed, ARMV8_SPE_PERFCTR_SAMPLE_FEED),
 	ARMV8_EVENT_ATTR(sample_filtrate, ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE),
 	ARMV8_EVENT_ATTR(sample_collision, ARMV8_SPE_PERFCTR_SAMPLE_COLLISION),
+	ARMV8_EVENT_ATTR(cnt_cycles, ARMV8_AMU_PERFCTR_CNT_CYCLES),
+	ARMV8_EVENT_ATTR(stall_backend_mem, ARMV8_AMU_PERFCTR_STALL_BACKEND_MEM),
+	ARMV8_EVENT_ATTR(l1i_cache_lmiss, ARMV8_PMUV3_PERFCTR_L1I_CACHE_LMISS),
+	ARMV8_EVENT_ATTR(l2d_cache_lmiss_rd, ARMV8_PMUV3_PERFCTR_L2D_CACHE_LMISS_RD),
+	ARMV8_EVENT_ATTR(l2i_cache_lmiss, ARMV8_PMUV3_PERFCTR_L2I_CACHE_LMISS),
+	ARMV8_EVENT_ATTR(l3d_cache_lmiss_rd, ARMV8_PMUV3_PERFCTR_L3D_CACHE_LMISS_RD),
+	ARMV8_EVENT_ATTR(ldst_align_lat, ARMV8_PMUV3_PERFCTR_LDST_ALIGN_LAT),
+	ARMV8_EVENT_ATTR(ld_align_lat, ARMV8_PMUV3_PERFCTR_LD_ALIGN_LAT),
+	ARMV8_EVENT_ATTR(st_align_lat, ARMV8_PMUV3_PERFCTR_ST_ALIGN_LAT),
+	ARMV8_EVENT_ATTR(mem_access_checked, ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED),
+	ARMV8_EVENT_ATTR(mem_access_checked_rd, ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_RD),
+	ARMV8_EVENT_ATTR(mem_access_checked_wr, ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_WR),
 	NULL,
 };
 
@@ -244,10 +266,13 @@ armv8pmu_event_attr_is_visible(struct kobject *kobj,
 	    test_bit(pmu_attr->id, cpu_pmu->pmceid_bitmap))
 		return attr->mode;
 
-	pmu_attr->id -= ARMV8_PMUV3_EXT_COMMON_EVENT_BASE;
-	if (pmu_attr->id < ARMV8_PMUV3_MAX_COMMON_EVENTS &&
-	    test_bit(pmu_attr->id, cpu_pmu->pmceid_ext_bitmap))
+	if (pmu_attr->id >= ARMV8_PMUV3_EXT_COMMON_EVENT_BASE) {
+		u64 id = pmu_attr->id - ARMV8_PMUV3_EXT_COMMON_EVENT_BASE;
+
+		if (id < ARMV8_PMUV3_MAX_COMMON_EVENTS &&
+		    test_bit(id, cpu_pmu->pmceid_ext_bitmap))
 			return attr->mode;
+	}
 
 	return 0;
 }
@@ -1165,28 +1190,54 @@ device_initcall(armv8_pmu_driver_init)
 void arch_perf_update_userpage(struct perf_event *event,
 			       struct perf_event_mmap_page *userpg, u64 now)
 {
-	u32 freq;
-	u32 shift;
+	struct clock_read_data *rd;
+	unsigned int seq;
+	u64 ns;
+
+	userpg->cap_user_time = 0;
+	userpg->cap_user_time_zero = 0;
+	userpg->cap_user_time_short = 0;
+
+	do {
+		rd = sched_clock_read_begin(&seq);
+
+		if (rd->read_sched_clock != arch_timer_read_counter)
+			return;
+
+		userpg->time_mult = rd->mult;
+		userpg->time_shift = rd->shift;
+		userpg->time_zero = rd->epoch_ns;
+		userpg->time_cycles = rd->epoch_cyc;
+		userpg->time_mask = rd->sched_clock_mask;
 
 		/*
-	 * Internal timekeeping for enabled/running/stopped times
-	 * is always computed with the sched_clock.
+		 * Subtract the cycle base, such that software that
+		 * doesn't know about cap_user_time_short still 'works'
+		 * assuming no wraps.
 		 */
-	freq = arch_timer_get_rate();
-	userpg->cap_user_time = 1;
+		ns = mul_u64_u32_shr(rd->epoch_cyc, rd->mult, rd->shift);
+		userpg->time_zero -= ns;
+
+	} while (sched_clock_read_retry(seq));
+
+	userpg->time_offset = userpg->time_zero - now;
 
-	clocks_calc_mult_shift(&userpg->time_mult, &shift, freq,
-			NSEC_PER_SEC, 0);
 	/*
 	 * time_shift is not expected to be greater than 31 due to
 	 * the original published conversion algorithm shifting a
 	 * 32-bit value (now specifies a 64-bit value) - refer
 	 * perf_event_mmap_page documentation in perf_event.h.
 	 */
-	if (shift == 32) {
-		shift = 31;
+	if (userpg->time_shift == 32) {
+		userpg->time_shift = 31;
 		userpg->time_mult >>= 1;
 	}
-	userpg->time_shift = (u16)shift;
-	userpg->time_offset = -now;
+
+	/*
+	 * Internal timekeeping for enabled/running/stopped times
+	 * is always computed with the sched_clock.
+	 */
+	userpg->cap_user_time = 1;
+	userpg->cap_user_time_zero = 1;
+	userpg->cap_user_time_short = 1;
 }

arch/arm64/kernel/vdso.c

@@ -18,6 +18,7 @@
 #include <linux/sched.h>
 #include <linux/signal.h>
 #include <linux/slab.h>
+#include <linux/time_namespace.h>
 #include <linux/timekeeper_internal.h>
 #include <linux/vmalloc.h>
 #include <vdso/datapage.h>
@@ -40,6 +41,12 @@ enum vdso_abi {
 #endif /* CONFIG_COMPAT_VDSO */
 };
 
+enum vvar_pages {
+	VVAR_DATA_PAGE_OFFSET,
+	VVAR_TIMENS_PAGE_OFFSET,
+	VVAR_NR_PAGES,
+};
+
 struct vdso_abi_info {
 	const char *name;
 	const char *vdso_code_start;
@@ -107,25 +114,122 @@ static int __vdso_init(enum vdso_abi abi)
 			vdso_info[abi].vdso_code_start) >>
 			PAGE_SHIFT;
 
-	/* Allocate the vDSO pagelist, plus a page for the data. */
-	vdso_pagelist = kcalloc(vdso_info[abi].vdso_pages + 1,
+	vdso_pagelist = kcalloc(vdso_info[abi].vdso_pages,
 				sizeof(struct page *),
 				GFP_KERNEL);
 	if (vdso_pagelist == NULL)
 		return -ENOMEM;
 
-	/* Grab the vDSO data page. */
-	vdso_pagelist[0] = phys_to_page(__pa_symbol(vdso_data));
-
-
 	/* Grab the vDSO code pages. */
 	pfn = sym_to_pfn(vdso_info[abi].vdso_code_start);
 
 	for (i = 0; i < vdso_info[abi].vdso_pages; i++)
-		vdso_pagelist[i + 1] = pfn_to_page(pfn + i);
+		vdso_pagelist[i] = pfn_to_page(pfn + i);
+
+	vdso_info[abi].cm->pages = vdso_pagelist;
+
+	return 0;
+}
+
+#ifdef CONFIG_TIME_NS
+struct vdso_data *arch_get_vdso_data(void *vvar_page)
+{
+	return (struct vdso_data *)(vvar_page);
+}
+
+/*
+ * The vvar mapping contains data for a specific time namespace, so when a task
+ * changes namespace we must unmap its vvar data for the old namespace.
+ * Subsequent faults will map in data for the new namespace.
+ *
+ * For more details see timens_setup_vdso_data().
+ */
+int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
+{
+	struct mm_struct *mm = task->mm;
+	struct vm_area_struct *vma;
+
+	mmap_read_lock(mm);
+
+	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+		unsigned long size = vma->vm_end - vma->vm_start;
+
+		if (vma_is_special_mapping(vma, vdso_info[VDSO_ABI_AA64].dm))
+			zap_page_range(vma, vma->vm_start, size);
+#ifdef CONFIG_COMPAT_VDSO
+		if (vma_is_special_mapping(vma, vdso_info[VDSO_ABI_AA32].dm))
+			zap_page_range(vma, vma->vm_start, size);
+#endif
+	}
+
+	mmap_read_unlock(mm);
+	return 0;
+}
 
-	vdso_info[abi].dm->pages = &vdso_pagelist[0];
-	vdso_info[abi].cm->pages = &vdso_pagelist[1];
+static struct page *find_timens_vvar_page(struct vm_area_struct *vma)
+{
+	if (likely(vma->vm_mm == current->mm))
+		return current->nsproxy->time_ns->vvar_page;
+
+	/*
+	 * VM_PFNMAP | VM_IO protect .fault() handler from being called
+	 * through interfaces like /proc/$pid/mem or
+	 * process_vm_{readv,writev}() as long as there's no .access()
+	 * in special_mapping_vmops.
+	 * For more details check_vma_flags() and __access_remote_vm()
+	 */
+	WARN(1, "vvar_page accessed remotely");
+
+	return NULL;
+}
+#else
+static struct page *find_timens_vvar_page(struct vm_area_struct *vma)
+{
+	return NULL;
+}
+#endif
+
+static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
+			     struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct page *timens_page = find_timens_vvar_page(vma);
+	unsigned long pfn;
+
+	switch (vmf->pgoff) {
+	case VVAR_DATA_PAGE_OFFSET:
+		if (timens_page)
+			pfn = page_to_pfn(timens_page);
+		else
+			pfn = sym_to_pfn(vdso_data);
+		break;
+#ifdef CONFIG_TIME_NS
+	case VVAR_TIMENS_PAGE_OFFSET:
+		/*
+		 * If a task belongs to a time namespace then a namespace
+		 * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and
+		 * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET
+		 * offset.
+		 * See also the comment near timens_setup_vdso_data().
+		 */
+		if (!timens_page)
+			return VM_FAULT_SIGBUS;
+		pfn = sym_to_pfn(vdso_data);
+		break;
+#endif /* CONFIG_TIME_NS */
+	default:
+		return VM_FAULT_SIGBUS;
+	}
+
+	return vmf_insert_pfn(vma, vmf->address, pfn);
+}
+
+static int vvar_mremap(const struct vm_special_mapping *sm,
+		       struct vm_area_struct *new_vma)
+{
+	unsigned long new_size = new_vma->vm_end - new_vma->vm_start;
+
+	if (new_size != VVAR_NR_PAGES * PAGE_SIZE)
+		return -EINVAL;
 
 	return 0;
 }
@@ -139,9 +243,11 @@ static int __setup_additional_pages(enum vdso_abi abi,
 	unsigned long gp_flags = 0;
 	void *ret;
 
+	BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES);
+
 	vdso_text_len = vdso_info[abi].vdso_pages << PAGE_SHIFT;
 	/* Be sure to map the data page */
-	vdso_mapping_len = vdso_text_len + PAGE_SIZE;
+	vdso_mapping_len = vdso_text_len + VVAR_NR_PAGES * PAGE_SIZE;
 
 	vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0);
 	if (IS_ERR_VALUE(vdso_base)) {
@@ -149,8 +255,8 @@ static int __setup_additional_pages(enum vdso_abi abi,
 		goto up_fail;
 	}
 
-	ret = _install_special_mapping(mm, vdso_base, PAGE_SIZE,
-				       VM_READ|VM_MAYREAD,
+	ret = _install_special_mapping(mm, vdso_base, VVAR_NR_PAGES * PAGE_SIZE,
+				       VM_READ|VM_MAYREAD|VM_PFNMAP,
 				       vdso_info[abi].dm);
 	if (IS_ERR(ret))
 		goto up_fail;
@@ -158,7 +264,7 @@ static int __setup_additional_pages(enum vdso_abi abi,
 	if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) && system_supports_bti())
 		gp_flags = VM_ARM64_BTI;
 
-	vdso_base += PAGE_SIZE;
+	vdso_base += VVAR_NR_PAGES * PAGE_SIZE;
 	mm->context.vdso = (void *)vdso_base;
 	ret = _install_special_mapping(mm, vdso_base, vdso_text_len,
 				       VM_READ|VM_EXEC|gp_flags|
@@ -206,6 +312,8 @@ static struct vm_special_mapping aarch32_vdso_maps[] = {
 #ifdef CONFIG_COMPAT_VDSO
 	[AA32_MAP_VVAR] = {
 		.name = "[vvar]",
+		.fault = vvar_fault,
+		.mremap = vvar_mremap,
 	},
 	[AA32_MAP_VDSO] = {
 		.name = "[vdso]",
@@ -371,6 +479,8 @@ enum aarch64_map {
 static struct vm_special_mapping aarch64_vdso_maps[] __ro_after_init = {
 	[AA64_MAP_VVAR] = {
 		.name	= "[vvar]",
+		.fault = vvar_fault,
+		.mremap = vvar_mremap,
 	},
 	[AA64_MAP_VDSO] = {
 		.name	= "[vdso]",

arch/arm64/kernel/vdso/vdso.lds.S

@@ -17,7 +17,10 @@ OUTPUT_ARCH(aarch64)
 
 SECTIONS
 {
-	PROVIDE(_vdso_data = . - PAGE_SIZE);
+	PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE);
+#ifdef CONFIG_TIME_NS
+	PROVIDE(_timens_data = _vdso_data + PAGE_SIZE);
+#endif
 	. = VDSO_LBASE + SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text

arch/arm64/kernel/vdso32/vdso.lds.S

@@ -17,7 +17,10 @@ OUTPUT_ARCH(arm)
 
 SECTIONS
 {
-	PROVIDE_HIDDEN(_vdso_data = . - PAGE_SIZE);
+	PROVIDE_HIDDEN(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE);
+#ifdef CONFIG_TIME_NS
+	PROVIDE_HIDDEN(_timens_data = _vdso_data + PAGE_SIZE);
+#endif
 	. = VDSO_LBASE + SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text

drivers/acpi/arm64/iort.c

@@ -264,15 +264,31 @@ static acpi_status iort_match_node_callback(struct acpi_iort_node *node,
 
 	if (node->type == ACPI_IORT_NODE_NAMED_COMPONENT) {
 		struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER, NULL };
-		struct acpi_device *adev = to_acpi_device_node(dev->fwnode);
+		struct acpi_device *adev;
 		struct acpi_iort_named_component *ncomp;
+		struct device *nc_dev = dev;
+
+		/*
+		 * Walk the device tree to find a device with an
+		 * ACPI companion; there is no point in scanning
+		 * IORT for a device matching a named component if
+		 * the device does not have an ACPI companion to
+		 * start with.
+		 */
+		do {
+			adev = ACPI_COMPANION(nc_dev);
+			if (adev)
+				break;
+
+			nc_dev = nc_dev->parent;
+		} while (nc_dev);
 
 		if (!adev)
 			goto out;
 
 		status = acpi_get_name(adev->handle, ACPI_FULL_PATHNAME, &buf);
 		if (ACPI_FAILURE(status)) {
-			dev_warn(dev, "Can't get device full path name\n");
+			dev_warn(nc_dev, "Can't get device full path name\n");
 			goto out;
 		}
 
@@ -534,7 +550,6 @@ static struct acpi_iort_node *iort_find_dev_node(struct device *dev)
 		node = iort_get_iort_node(dev->fwnode);
 		if (node)
 			return node;
-
 		/*
 		 * if not, then it should be a platform device defined in
 		 * DSDT/SSDT (with Named Component node in IORT)
@@ -543,32 +558,29 @@ static struct acpi_iort_node *iort_find_dev_node(struct device *dev)
 				      iort_match_node_callback, dev);
 	}
 
-	/* Find a PCI root bus */
 	pbus = to_pci_dev(dev)->bus;
-	while (!pci_is_root_bus(pbus))
-		pbus = pbus->parent;
 
 	return iort_scan_node(ACPI_IORT_NODE_PCI_ROOT_COMPLEX,
 			      iort_match_node_callback, &pbus->dev);
 }
 
 /**
- * iort_msi_map_rid() - Map a MSI requester ID for a device
+ * iort_msi_map_id() - Map a MSI input ID for a device
  * @dev: The device for which the mapping is to be done.
- * @req_id: The device requester ID.
+ * @input_id: The device input ID.
  *
- * Returns: mapped MSI RID on success, input requester ID otherwise
+ * Returns: mapped MSI ID on success, input ID otherwise
  */
-u32 iort_msi_map_rid(struct device *dev, u32 req_id)
+u32 iort_msi_map_id(struct device *dev, u32 input_id)
 {
 	struct acpi_iort_node *node;
 	u32 dev_id;
 
 	node = iort_find_dev_node(dev);
 	if (!node)
-		return req_id;
+		return input_id;
 
-	iort_node_map_id(node, req_id, &dev_id, IORT_MSI_TYPE);
+	iort_node_map_id(node, input_id, &dev_id, IORT_MSI_TYPE);
 	return dev_id;
 }
 
@@ -625,13 +637,13 @@ static int __maybe_unused iort_find_its_base(u32 its_id, phys_addr_t *base)
 /**
  * iort_dev_find_its_id() - Find the ITS identifier for a device
  * @dev: The device.
- * @req_id: Device's requester ID
+ * @id: Device's ID
  * @idx: Index of the ITS identifier list.
  * @its_id: ITS identifier.
  *
  * Returns: 0 on success, appropriate error value otherwise
  */
-static int iort_dev_find_its_id(struct device *dev, u32 req_id,
+static int iort_dev_find_its_id(struct device *dev, u32 id,
 				unsigned int idx, int *its_id)
 {
 	struct acpi_iort_its_group *its;
@@ -641,7 +653,7 @@ static int iort_dev_find_its_id(struct device *dev, u32 req_id,
 	if (!node)
 		return -ENXIO;
 
-	node = iort_node_map_id(node, req_id, NULL, IORT_MSI_TYPE);
+	node = iort_node_map_id(node, id, NULL, IORT_MSI_TYPE);
 	if (!node)
 		return -ENXIO;
 
@@ -664,19 +676,20 @@ static int iort_dev_find_its_id(struct device *dev, u32 req_id,
  *
  * Returns: the MSI domain for this device, NULL otherwise
  */
-struct irq_domain *iort_get_device_domain(struct device *dev, u32 req_id)
+struct irq_domain *iort_get_device_domain(struct device *dev, u32 id,
+					  enum irq_domain_bus_token bus_token)
 {
 	struct fwnode_handle *handle;
 	int its_id;
 
-	if (iort_dev_find_its_id(dev, req_id, 0, &its_id))
+	if (iort_dev_find_its_id(dev, id, 0, &its_id))
 		return NULL;
 
 	handle = iort_find_domain_token(its_id);
 	if (!handle)
 		return NULL;
 
-	return irq_find_matching_fwnode(handle, DOMAIN_BUS_PCI_MSI);
+	return irq_find_matching_fwnode(handle, bus_token);
 }
 
 static void iort_set_device_domain(struct device *dev,
@@ -965,19 +978,54 @@ static void iort_named_component_init(struct device *dev,
 					   nc->node_flags);
 }
 
+static int iort_nc_iommu_map(struct device *dev, struct acpi_iort_node *node)
+{
+	struct acpi_iort_node *parent;
+	int err = -ENODEV, i = 0;
+	u32 streamid = 0;
+
+	do {
+
+		parent = iort_node_map_platform_id(node, &streamid,
+						   IORT_IOMMU_TYPE,
+						   i++);
+
+		if (parent)
+			err = iort_iommu_xlate(dev, parent, streamid);
+	} while (parent && !err);
+
+	return err;
+}
+
+static int iort_nc_iommu_map_id(struct device *dev,
+				struct acpi_iort_node *node,
+				const u32 *in_id)
+{
+	struct acpi_iort_node *parent;
+	u32 streamid;
+
+	parent = iort_node_map_id(node, *in_id, &streamid, IORT_IOMMU_TYPE);
+	if (parent)
+		return iort_iommu_xlate(dev, parent, streamid);
+
+	return -ENODEV;
+}
+
+
 /**
- * iort_iommu_configure - Set-up IOMMU configuration for a device.
+ * iort_iommu_configure_id - Set-up IOMMU configuration for a device.
  *
  * @dev: device to configure
+ * @id_in: optional input id const value pointer
  *
  * Returns: iommu_ops pointer on configuration success
  *          NULL on configuration failure
  */
-const struct iommu_ops *iort_iommu_configure(struct device *dev)
+const struct iommu_ops *iort_iommu_configure_id(struct device *dev,
+						const u32 *id_in)
 {
-	struct acpi_iort_node *node, *parent;
+	struct acpi_iort_node *node;
 	const struct iommu_ops *ops;
-	u32 streamid = 0;
 	int err = -ENODEV;
 
 	/*
@@ -1006,21 +1054,13 @@ const struct iommu_ops *iort_iommu_configure(struct device *dev)
 		if (fwspec && iort_pci_rc_supports_ats(node))
 			fwspec->flags |= IOMMU_FWSPEC_PCI_RC_ATS;
 	} else {
-		int i = 0;
-
 		node = iort_scan_node(ACPI_IORT_NODE_NAMED_COMPONENT,
 				      iort_match_node_callback, dev);
 		if (!node)
 			return NULL;
 
-		do {
-			parent = iort_node_map_platform_id(node, &streamid,
-							   IORT_IOMMU_TYPE,
-							   i++);
-
-			if (parent)
-				err = iort_iommu_xlate(dev, parent, streamid);
-		} while (parent && !err);
+		err = id_in ? iort_nc_iommu_map_id(dev, node, id_in) :
+			      iort_nc_iommu_map(dev, node);
 
 		if (!err)
 			iort_named_component_init(dev, node);
@@ -1045,6 +1085,7 @@ const struct iommu_ops *iort_iommu_configure(struct device *dev)
 
 	return ops;
 }
+
 #else
 static inline const struct iommu_ops *iort_fwspec_iommu_ops(struct device *dev)
 { return NULL; }
@@ -1053,7 +1094,8 @@ static inline int iort_add_device_replay(const struct iommu_ops *ops,
 { return 0; }
 int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head)
 { return 0; }
-const struct iommu_ops *iort_iommu_configure(struct device *dev)
+const struct iommu_ops *iort_iommu_configure_id(struct device *dev,
+						const u32 *input_id)
 { return NULL; }
 #endif
 

drivers/acpi/scan.c

@@ -1457,8 +1457,10 @@ int acpi_dma_get_range(struct device *dev, u64 *dma_addr, u64 *offset,
  * acpi_dma_configure - Set-up DMA configuration for the device.
  * @dev: The pointer to the device
  * @attr: device dma attributes
+ * @input_id: input device id const value pointer
  */
-int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr)
+int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr,
+			  const u32 *input_id)
 {
 	const struct iommu_ops *iommu;
 	u64 dma_addr = 0, size = 0;
@@ -1470,7 +1472,7 @@ int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr)
 
 	iort_dma_setup(dev, &dma_addr, &size);
 
-	iommu = iort_iommu_configure(dev);
+	iommu = iort_iommu_configure_id(dev, input_id);
 	if (PTR_ERR(iommu) == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
 
@@ -1479,7 +1481,7 @@ int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(acpi_dma_configure);
+EXPORT_SYMBOL_GPL(acpi_dma_configure_id);
 
 static void acpi_init_coherency(struct acpi_device *adev)
 {

drivers/bus/fsl-mc/dprc-driver.c

@@ -592,6 +592,7 @@ static int dprc_probe(struct fsl_mc_device *mc_dev)
 	bool mc_io_created = false;
 	bool msi_domain_set = false;
 	u16 major_ver, minor_ver;
+	struct irq_domain *mc_msi_domain;
 
 	if (!is_fsl_mc_bus_dprc(mc_dev))
 		return -EINVAL;
@@ -621,32 +622,16 @@ static int dprc_probe(struct fsl_mc_device *mc_dev)
 			return error;
 
 		mc_io_created = true;
+	}
 
-		/*
-		 * Inherit parent MSI domain:
-		 */
-		dev_set_msi_domain(&mc_dev->dev,
-				   dev_get_msi_domain(parent_dev));
-		msi_domain_set = true;
-	} else {
-		/*
-		 * This is a root DPRC
-		 */
-		struct irq_domain *mc_msi_domain;
-
-		if (dev_is_fsl_mc(parent_dev))
-			return -EINVAL;
-
-		error = fsl_mc_find_msi_domain(parent_dev,
-					       &mc_msi_domain);
-		if (error < 0) {
+	mc_msi_domain = fsl_mc_find_msi_domain(&mc_dev->dev);
+	if (!mc_msi_domain) {
 		dev_warn(&mc_dev->dev,
 			 "WARNING: MC bus without interrupt support\n");
 	} else {
 		dev_set_msi_domain(&mc_dev->dev, mc_msi_domain);
 		msi_domain_set = true;
 	}
-	}
 
 	error = dprc_open(mc_dev->mc_io, 0, mc_dev->obj_desc.id,
 			  &mc_dev->mc_handle);

drivers/bus/fsl-mc/fsl-mc-bus.c

@@ -18,6 +18,8 @@
 #include <linux/bitops.h>
 #include <linux/msi.h>
 #include <linux/dma-mapping.h>
+#include <linux/acpi.h>
+#include <linux/iommu.h>
 
 #include "fsl-mc-private.h"
 
@@ -38,6 +40,7 @@ struct fsl_mc {
 	struct fsl_mc_device *root_mc_bus_dev;
 	u8 num_translation_ranges;
 	struct fsl_mc_addr_translation_range *translation_ranges;
+	void *fsl_mc_regs;
 };
 
 /**
@@ -56,6 +59,10 @@ struct fsl_mc_addr_translation_range {
 	phys_addr_t start_phys_addr;
 };
 
+#define FSL_MC_FAPR	0x28
+#define MC_FAPR_PL	BIT(18)
+#define MC_FAPR_BMT	BIT(17)
+
 /**
  * fsl_mc_bus_match - device to driver matching callback
  * @dev: the fsl-mc device to match against
@@ -118,11 +125,16 @@ static int fsl_mc_bus_uevent(struct device *dev, struct kobj_uevent_env *env)
 static int fsl_mc_dma_configure(struct device *dev)
 {
 	struct device *dma_dev = dev;
+	struct fsl_mc_device *mc_dev = to_fsl_mc_device(dev);
+	u32 input_id = mc_dev->icid;
 
 	while (dev_is_fsl_mc(dma_dev))
 		dma_dev = dma_dev->parent;
 
-	return of_dma_configure(dev, dma_dev->of_node, 0);
+	if (dev_of_node(dma_dev))
+		return of_dma_configure_id(dev, dma_dev->of_node, 0, &input_id);
+
+	return acpi_dma_configure_id(dev, DEV_DMA_COHERENT, &input_id);
 }
 
 static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
@@ -368,7 +380,7 @@ EXPORT_SYMBOL_GPL(fsl_mc_get_version);
 /**
  * fsl_mc_get_root_dprc - function to traverse to the root dprc
  */
-static void fsl_mc_get_root_dprc(struct device *dev,
+void fsl_mc_get_root_dprc(struct device *dev,
 			 struct device **root_dprc_dev)
 {
 	if (!dev) {
@@ -863,8 +875,11 @@ static int fsl_mc_bus_probe(struct platform_device *pdev)
 	struct fsl_mc_io *mc_io = NULL;
 	int container_id;
 	phys_addr_t mc_portal_phys_addr;
-	u32 mc_portal_size;
-	struct resource res;
+	u32 mc_portal_size, mc_stream_id;
+	struct resource *plat_res;
+
+	if (!iommu_present(&fsl_mc_bus_type))
+		return -EPROBE_DEFER;
 
 	mc = devm_kzalloc(&pdev->dev, sizeof(*mc), GFP_KERNEL);
 	if (!mc)
@@ -872,19 +887,33 @@ static int fsl_mc_bus_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, mc);
 
+	plat_res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	mc->fsl_mc_regs = devm_ioremap_resource(&pdev->dev, plat_res);
+	if (IS_ERR(mc->fsl_mc_regs))
+		return PTR_ERR(mc->fsl_mc_regs);
+
+	if (IS_ENABLED(CONFIG_ACPI) && !dev_of_node(&pdev->dev)) {
+		mc_stream_id = readl(mc->fsl_mc_regs + FSL_MC_FAPR);
 		/*
-	 * Get physical address of MC portal for the root DPRC:
+		 * HW ORs the PL and BMT bit, places the result in bit 15 of
+		 * the StreamID and ORs in the ICID. Calculate it accordingly.
 		 */
-	error = of_address_to_resource(pdev->dev.of_node, 0, &res);
-	if (error < 0) {
-		dev_err(&pdev->dev,
-			"of_address_to_resource() failed for %pOF\n",
-			pdev->dev.of_node);
-		return error;
+		mc_stream_id = (mc_stream_id & 0xffff) |
+				((mc_stream_id & (MC_FAPR_PL | MC_FAPR_BMT)) ?
+					0x4000 : 0);
+		error = acpi_dma_configure_id(&pdev->dev, DEV_DMA_COHERENT,
+					      &mc_stream_id);
+		if (error)
+			dev_warn(&pdev->dev, "failed to configure dma: %d.\n",
+				 error);
 	}
 
-	mc_portal_phys_addr = res.start;
-	mc_portal_size = resource_size(&res);
+	/*
+	 * Get physical address of MC portal for the root DPRC:
+	 */
+	plat_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	mc_portal_phys_addr = plat_res->start;
+	mc_portal_size = resource_size(plat_res);
 	error = fsl_create_mc_io(&pdev->dev, mc_portal_phys_addr,
 				 mc_portal_size, NULL,
 				 FSL_MC_IO_ATOMIC_CONTEXT_PORTAL, &mc_io);
@@ -901,11 +930,13 @@ static int fsl_mc_bus_probe(struct platform_device *pdev)
 	dev_info(&pdev->dev, "MC firmware version: %u.%u.%u\n",
 		 mc_version.major, mc_version.minor, mc_version.revision);
 
+	if (dev_of_node(&pdev->dev)) {
 		error = get_mc_addr_translation_ranges(&pdev->dev,
 						&mc->translation_ranges,
 						&mc->num_translation_ranges);
 		if (error < 0)
 			goto error_cleanup_mc_io;
+	}
 
 	error = dprc_get_container_id(mc_io, 0, &container_id);
 	if (error < 0) {
@@ -932,6 +963,7 @@ static int fsl_mc_bus_probe(struct platform_device *pdev)
 		goto error_cleanup_mc_io;
 
 	mc->root_mc_bus_dev = mc_bus_dev;
+	mc_bus_dev->dev.fwnode = pdev->dev.fwnode;
 	return 0;
 
 error_cleanup_mc_io:
@@ -965,11 +997,18 @@ static const struct of_device_id fsl_mc_bus_match_table[] = {
 
 MODULE_DEVICE_TABLE(of, fsl_mc_bus_match_table);
 
+static const struct acpi_device_id fsl_mc_bus_acpi_match_table[] = {
+	{"NXP0008", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(acpi, fsl_mc_bus_acpi_match_table);
+
 static struct platform_driver fsl_mc_bus_driver = {
 	.driver = {
 		   .name = "fsl_mc_bus",
 		   .pm = NULL,
 		   .of_match_table = fsl_mc_bus_match_table,
+		   .acpi_match_table = fsl_mc_bus_acpi_match_table,
 		   },
 	.probe = fsl_mc_bus_probe,
 	.remove = fsl_mc_bus_remove,

drivers/bus/fsl-mc/fsl-mc-msi.c

@@ -13,6 +13,7 @@
 #include <linux/irq.h>
 #include <linux/irqdomain.h>
 #include <linux/msi.h>
+#include <linux/acpi_iort.h>
 
 #include "fsl-mc-private.h"
 
@@ -177,23 +178,36 @@ struct irq_domain *fsl_mc_msi_create_irq_domain(struct fwnode_handle *fwnode,
 	return domain;
 }
 
-int fsl_mc_find_msi_domain(struct device *mc_platform_dev,
-			   struct irq_domain **mc_msi_domain)
+struct irq_domain *fsl_mc_find_msi_domain(struct device *dev)
 {
+	struct device *root_dprc_dev;
+	struct device *bus_dev;
 	struct irq_domain *msi_domain;
-	struct device_node *mc_of_node = mc_platform_dev->of_node;
+	struct fsl_mc_device *mc_dev = to_fsl_mc_device(dev);
 
-	msi_domain = of_msi_get_domain(mc_platform_dev, mc_of_node,
+	fsl_mc_get_root_dprc(dev, &root_dprc_dev);
+	bus_dev = root_dprc_dev->parent;
+
+	if (bus_dev->of_node) {
+		msi_domain = of_msi_map_get_device_domain(dev,
+						  mc_dev->icid,
 						  DOMAIN_BUS_FSL_MC_MSI);
-	if (!msi_domain) {
-		pr_err("Unable to find fsl-mc MSI domain for %pOF\n",
-		       mc_of_node);
 
-		return -ENOENT;
+		/*
+		 * if the msi-map property is missing assume that all the
+		 * child containers inherit the domain from the parent
+		 */
+		if (!msi_domain)
+
+			msi_domain = of_msi_get_domain(bus_dev,
+						bus_dev->of_node,
+						DOMAIN_BUS_FSL_MC_MSI);
+	} else {
+		msi_domain = iort_get_device_domain(dev, mc_dev->icid,
+						    DOMAIN_BUS_FSL_MC_MSI);
 	}
 
-	*mc_msi_domain = msi_domain;
-	return 0;
+	return msi_domain;
 }
 
 static void fsl_mc_msi_free_descs(struct device *dev)

drivers/bus/fsl-mc/fsl-mc-private.h

@@ -595,8 +595,7 @@ int fsl_mc_msi_domain_alloc_irqs(struct device *dev,
 
 void fsl_mc_msi_domain_free_irqs(struct device *dev);
 
-int fsl_mc_find_msi_domain(struct device *mc_platform_dev,
-			   struct irq_domain **mc_msi_domain);
+struct irq_domain *fsl_mc_find_msi_domain(struct device *dev);
 
 int fsl_mc_populate_irq_pool(struct fsl_mc_bus *mc_bus,
 			     unsigned int irq_count);
@@ -613,6 +612,9 @@ void fsl_destroy_mc_io(struct fsl_mc_io *mc_io);
 
 bool fsl_mc_is_root_dprc(struct device *dev);
 
+void fsl_mc_get_root_dprc(struct device *dev,
+			 struct device **root_dprc_dev);
+
 struct fsl_mc_device *fsl_mc_device_lookup(struct fsl_mc_obj_desc *obj_desc,
 					   struct fsl_mc_device *mc_bus_dev);
 

drivers/iommu/of_iommu.c

@@ -118,46 +118,66 @@ static int of_iommu_xlate(struct device *dev,
 	return ret;
 }
 
-struct of_pci_iommu_alias_info {
-	struct device *dev;
-	struct device_node *np;
-};
-
-static int of_pci_iommu_init(struct pci_dev *pdev, u16 alias, void *data)
+static int of_iommu_configure_dev_id(struct device_node *master_np,
+				     struct device *dev,
+				     const u32 *id)
 {
-	struct of_pci_iommu_alias_info *info = data;
 	struct of_phandle_args iommu_spec = { .args_count = 1 };
 	int err;
 
-	err = of_map_rid(info->np, alias, "iommu-map", "iommu-map-mask",
-			 &iommu_spec.np, iommu_spec.args);
+	err = of_map_id(master_np, *id, "iommu-map",
+			 "iommu-map-mask", &iommu_spec.np,
+			 iommu_spec.args);
 	if (err)
 		return err == -ENODEV ? NO_IOMMU : err;
 
-	err = of_iommu_xlate(info->dev, &iommu_spec);
+	err = of_iommu_xlate(dev, &iommu_spec);
 	of_node_put(iommu_spec.np);
 	return err;
 }
 
-static int of_fsl_mc_iommu_init(struct fsl_mc_device *mc_dev,
-				struct device_node *master_np)
+static int of_iommu_configure_dev(struct device_node *master_np,
+				  struct device *dev)
 {
-	struct of_phandle_args iommu_spec = { .args_count = 1 };
-	int err;
+	struct of_phandle_args iommu_spec;
+	int err = NO_IOMMU, idx = 0;
 
-	err = of_map_rid(master_np, mc_dev->icid, "iommu-map",
-			 "iommu-map-mask", &iommu_spec.np,
-			 iommu_spec.args);
+	while (!of_parse_phandle_with_args(master_np, "iommus",
+					   "#iommu-cells",
+					   idx, &iommu_spec)) {
+		err = of_iommu_xlate(dev, &iommu_spec);
+		of_node_put(iommu_spec.np);
+		idx++;
 		if (err)
-		return err == -ENODEV ? NO_IOMMU : err;
+			break;
+	}
 
-	err = of_iommu_xlate(&mc_dev->dev, &iommu_spec);
-	of_node_put(iommu_spec.np);
 	return err;
 }
 
+struct of_pci_iommu_alias_info {
+	struct device *dev;
+	struct device_node *np;
+};
+
+static int of_pci_iommu_init(struct pci_dev *pdev, u16 alias, void *data)
+{
+	struct of_pci_iommu_alias_info *info = data;
+	u32 input_id = alias;
+
+	return of_iommu_configure_dev_id(info->np, info->dev, &input_id);
+}
+
+static int of_iommu_configure_device(struct device_node *master_np,
+				     struct device *dev, const u32 *id)
+{
+	return (id) ? of_iommu_configure_dev_id(master_np, dev, id) :
+		      of_iommu_configure_dev(master_np, dev);
+}
+
 const struct iommu_ops *of_iommu_configure(struct device *dev,
-					   struct device_node *master_np)
+					   struct device_node *master_np,
+					   const u32 *id)
 {
 	const struct iommu_ops *ops = NULL;
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
@@ -188,21 +208,8 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
 		pci_request_acs();
 		err = pci_for_each_dma_alias(to_pci_dev(dev),
 					     of_pci_iommu_init, &info);
-	} else if (dev_is_fsl_mc(dev)) {
-		err = of_fsl_mc_iommu_init(to_fsl_mc_device(dev), master_np);
 	} else {
-		struct of_phandle_args iommu_spec;
-		int idx = 0;
-
-		while (!of_parse_phandle_with_args(master_np, "iommus",
-						   "#iommu-cells",
-						   idx, &iommu_spec)) {
-			err = of_iommu_xlate(dev, &iommu_spec);
-			of_node_put(iommu_spec.np);
-			idx++;
-			if (err)
-				break;
-		}
+		err = of_iommu_configure_device(master_np, dev, id);
 
 		fwspec = dev_iommu_fwspec_get(dev);
 		if (!err && fwspec)

drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c

@@ -7,6 +7,8 @@
  *
  */
 
+#include <linux/acpi.h>
+#include <linux/acpi_iort.h>
 #include <linux/of_device.h>
 #include <linux/of_address.h>
 #include <linux/irq.h>
@@ -23,6 +25,19 @@ static struct irq_chip its_msi_irq_chip = {
 	.irq_set_affinity = msi_domain_set_affinity
 };
 
+static u32 fsl_mc_msi_domain_get_msi_id(struct irq_domain *domain,
+					struct fsl_mc_device *mc_dev)
+{
+	struct device_node *of_node;
+	u32 out_id;
+
+	of_node = irq_domain_get_of_node(domain);
+	out_id = of_node ? of_msi_map_id(&mc_dev->dev, of_node, mc_dev->icid) :
+			iort_msi_map_id(&mc_dev->dev, mc_dev->icid);
+
+	return out_id;
+}
+
 static int its_fsl_mc_msi_prepare(struct irq_domain *msi_domain,
 				  struct device *dev,
 				  int nvec, msi_alloc_info_t *info)
@@ -43,7 +58,8 @@ static int its_fsl_mc_msi_prepare(struct irq_domain *msi_domain,
 	 * NOTE: This device id corresponds to the IOMMU stream ID
 	 * associated with the DPRC object (ICID).
 	 */
-	info->scratchpad[0].ul = mc_bus_dev->icid;
+	info->scratchpad[0].ul = fsl_mc_msi_domain_get_msi_id(msi_domain,
+							      mc_bus_dev);
 	msi_info = msi_get_domain_info(msi_domain->parent);
 
 	/* Allocate at least 32 MSIs, and always as a power of 2 */
@@ -66,36 +82,87 @@ static const struct of_device_id its_device_id[] = {
 	{},
 };
 
-static int __init its_fsl_mc_msi_init(void)
+static void __init its_fsl_mc_msi_init_one(struct fwnode_handle *handle,
+					  const char *name)
 {
-	struct device_node *np;
 	struct irq_domain *parent;
 	struct irq_domain *mc_msi_domain;
 
-	for (np = of_find_matching_node(NULL, its_device_id); np;
-	     np = of_find_matching_node(np, its_device_id)) {
-		if (!of_device_is_available(np))
-			continue;
-		if (!of_property_read_bool(np, "msi-controller"))
-			continue;
-
-		parent = irq_find_matching_host(np, DOMAIN_BUS_NEXUS);
+	parent = irq_find_matching_fwnode(handle, DOMAIN_BUS_NEXUS);
 	if (!parent || !msi_get_domain_info(parent)) {
-			pr_err("%pOF: unable to locate ITS domain\n", np);
-			continue;
+		pr_err("%s: unable to locate ITS domain\n", name);
+		return;
 	}
 
-		mc_msi_domain = fsl_mc_msi_create_irq_domain(
-						 of_node_to_fwnode(np),
+	mc_msi_domain = fsl_mc_msi_create_irq_domain(handle,
 						&its_fsl_mc_msi_domain_info,
 						parent);
 	if (!mc_msi_domain) {
-			pr_err("%pOF: unable to create fsl-mc domain\n", np);
-			continue;
+		pr_err("%s: unable to create fsl-mc domain\n", name);
+		return;
+	}
+
+	pr_info("fsl-mc MSI: %s domain created\n", name);
+}
+
+#ifdef CONFIG_ACPI
+static int __init
+its_fsl_mc_msi_parse_madt(union acpi_subtable_headers *header,
+			  const unsigned long end)
+{
+	struct acpi_madt_generic_translator *its_entry;
+	struct fwnode_handle *dom_handle;
+	const char *node_name;
+	int err = 0;
+
+	its_entry = (struct acpi_madt_generic_translator *)header;
+	node_name = kasprintf(GFP_KERNEL, "ITS@0x%lx",
+			      (long)its_entry->base_address);
+
+	dom_handle = iort_find_domain_token(its_entry->translation_id);
+	if (!dom_handle) {
+		pr_err("%s: Unable to locate ITS domain handle\n", node_name);
+		err = -ENXIO;
+		goto out;
 	}
 
-		pr_info("fsl-mc MSI: %pOF domain created\n", np);
+	its_fsl_mc_msi_init_one(dom_handle, node_name);
+
+out:
+	kfree(node_name);
+	return err;
+}
+
+
+static void __init its_fsl_mc_acpi_msi_init(void)
+{
+	acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_TRANSLATOR,
+			      its_fsl_mc_msi_parse_madt, 0);
+}
+#else
+static inline void its_fsl_mc_acpi_msi_init(void) { }
+#endif
+
+static void __init its_fsl_mc_of_msi_init(void)
+{
+	struct device_node *np;
+
+	for (np = of_find_matching_node(NULL, its_device_id); np;
+	     np = of_find_matching_node(np, its_device_id)) {
+		if (!of_device_is_available(np))
+			continue;
+		if (!of_property_read_bool(np, "msi-controller"))
+			continue;
+
+		its_fsl_mc_msi_init_one(of_node_to_fwnode(np),
+					np->full_name);
 	}
+}
+
+static int __init its_fsl_mc_msi_init(void)
+{
+	its_fsl_mc_of_msi_init();
+	its_fsl_mc_acpi_msi_init();
 
 	return 0;
 }

drivers/of/base.c

@@ -2201,15 +2201,15 @@ int of_find_last_cache_level(unsigned int cpu)
 }
 
 /**
- * of_map_rid - Translate a requester ID through a downstream mapping.
+ * of_map_id - Translate an ID through a downstream mapping.
  * @np: root complex device node.
- * @rid: device requester ID to map.
+ * @id: device ID to map.
  * @map_name: property name of the map to use.
  * @map_mask_name: optional property name of the mask to use.
  * @target: optional pointer to a target device node.
  * @id_out: optional pointer to receive the translated ID.
  *
- * Given a device requester ID, look up the appropriate implementation-defined
+ * Given a device ID, look up the appropriate implementation-defined
  * platform ID and/or the target device which receives transactions on that
  * ID, as per the "iommu-map" and "msi-map" bindings. Either of @target or
  * @id_out may be NULL if only the other is required. If @target points to
@@ -2219,11 +2219,11 @@ int of_find_last_cache_level(unsigned int cpu)
  *
  * Return: 0 on success or a standard error code on failure.
  */
-int of_map_rid(struct device_node *np, u32 rid,
+int of_map_id(struct device_node *np, u32 id,
 	       const char *map_name, const char *map_mask_name,
 	       struct device_node **target, u32 *id_out)
 {
-	u32 map_mask, masked_rid;
+	u32 map_mask, masked_id;
 	int map_len;
 	const __be32 *map = NULL;
 
@@ -2235,7 +2235,7 @@ int of_map_rid(struct device_node *np, u32 rid,
 		if (target)
 			return -ENODEV;
 		/* Otherwise, no map implies no translation */
-		*id_out = rid;
+		*id_out = id;
 		return 0;
 	}
 
@@ -2255,22 +2255,22 @@ int of_map_rid(struct device_node *np, u32 rid,
 	if (map_mask_name)
 		of_property_read_u32(np, map_mask_name, &map_mask);
 
-	masked_rid = map_mask & rid;
+	masked_id = map_mask & id;
 	for ( ; map_len > 0; map_len -= 4 * sizeof(*map), map += 4) {
 		struct device_node *phandle_node;
-		u32 rid_base = be32_to_cpup(map + 0);
+		u32 id_base = be32_to_cpup(map + 0);
 		u32 phandle = be32_to_cpup(map + 1);
 		u32 out_base = be32_to_cpup(map + 2);
-		u32 rid_len = be32_to_cpup(map + 3);
+		u32 id_len = be32_to_cpup(map + 3);
 
-		if (rid_base & ~map_mask) {
-			pr_err("%pOF: Invalid %s translation - %s-mask (0x%x) ignores rid-base (0x%x)\n",
+		if (id_base & ~map_mask) {
+			pr_err("%pOF: Invalid %s translation - %s-mask (0x%x) ignores id-base (0x%x)\n",
 				np, map_name, map_name,
-				map_mask, rid_base);
+				map_mask, id_base);
 			return -EFAULT;
 		}
 
-		if (masked_rid < rid_base || masked_rid >= rid_base + rid_len)
+		if (masked_id < id_base || masked_id >= id_base + id_len)
 			continue;
 
 		phandle_node = of_find_node_by_phandle(phandle);
@@ -2288,20 +2288,20 @@ int of_map_rid(struct device_node *np, u32 rid,
 		}
 
 		if (id_out)
-			*id_out = masked_rid - rid_base + out_base;
+			*id_out = masked_id - id_base + out_base;
 
-		pr_debug("%pOF: %s, using mask %08x, rid-base: %08x, out-base: %08x, length: %08x, rid: %08x -> %08x\n",
-			np, map_name, map_mask, rid_base, out_base,
-			rid_len, rid, masked_rid - rid_base + out_base);
+		pr_debug("%pOF: %s, using mask %08x, id-base: %08x, out-base: %08x, length: %08x, id: %08x -> %08x\n",
+			np, map_name, map_mask, id_base, out_base,
+			id_len, id, masked_id - id_base + out_base);
 		return 0;
 	}
 
-	pr_info("%pOF: no %s translation for rid 0x%x on %pOF\n", np, map_name,
-		rid, target && *target ? *target : NULL);
+	pr_info("%pOF: no %s translation for id 0x%x on %pOF\n", np, map_name,
+		id, target && *target ? *target : NULL);
 
 	/* Bypasses translation */
 	if (id_out)
-		*id_out = rid;
+		*id_out = id;
 	return 0;
 }
-EXPORT_SYMBOL_GPL(of_map_rid);
+EXPORT_SYMBOL_GPL(of_map_id);

drivers/of/device.c

@@ -78,6 +78,7 @@ int of_device_add(struct platform_device *ofdev)
  * @np:		Pointer to OF node having DMA configuration
  * @force_dma:  Whether device is to be set up by of_dma_configure() even if
  *		DMA capability is not explicitly described by firmware.
+ * @id:		Optional const pointer value input id
  *
  * Try to get devices's DMA configuration from DT and update it
  * accordingly.
@@ -86,7 +87,8 @@ int of_device_add(struct platform_device *ofdev)
  * can use a platform bus notifier and handle BUS_NOTIFY_ADD_DEVICE events
  * to fix up DMA configuration.
  */
-int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma)
+int of_dma_configure_id(struct device *dev, struct device_node *np,
+			bool force_dma, const u32 *id)
 {
 	u64 dma_addr, paddr, size = 0;
 	int ret;
@@ -160,7 +162,7 @@ int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma)
 	dev_dbg(dev, "device is%sdma coherent\n",
 		coherent ? " " : " not ");
 
-	iommu = of_iommu_configure(dev, np);
+	iommu = of_iommu_configure(dev, np, id);
 	if (PTR_ERR(iommu) == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
 
@@ -171,7 +173,7 @@ int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(of_dma_configure);
+EXPORT_SYMBOL_GPL(of_dma_configure_id);
 
 int of_device_register(struct platform_device *pdev)
 {

drivers/of/irq.c

@@ -576,55 +576,57 @@ void __init of_irq_init(const struct of_device_id *matches)
 	}
 }
 
-static u32 __of_msi_map_rid(struct device *dev, struct device_node **np,
-			    u32 rid_in)
+static u32 __of_msi_map_id(struct device *dev, struct device_node **np,
+			    u32 id_in)
 {
 	struct device *parent_dev;
-	u32 rid_out = rid_in;
+	u32 id_out = id_in;
 
 	/*
 	 * Walk up the device parent links looking for one with a
 	 * "msi-map" property.
 	 */
 	for (parent_dev = dev; parent_dev; parent_dev = parent_dev->parent)
-		if (!of_map_rid(parent_dev->of_node, rid_in, "msi-map",
-				"msi-map-mask", np, &rid_out))
+		if (!of_map_id(parent_dev->of_node, id_in, "msi-map",
+				"msi-map-mask", np, &id_out))
 			break;
-	return rid_out;
+	return id_out;
 }
 
 /**
- * of_msi_map_rid - Map a MSI requester ID for a device.
+ * of_msi_map_id - Map a MSI ID for a device.
  * @dev: device for which the mapping is to be done.
  * @msi_np: device node of the expected msi controller.
- * @rid_in: unmapped MSI requester ID for the device.
+ * @id_in: unmapped MSI ID for the device.
  *
  * Walk up the device hierarchy looking for devices with a "msi-map"
- * property.  If found, apply the mapping to @rid_in.
+ * property.  If found, apply the mapping to @id_in.
  *
- * Returns the mapped MSI requester ID.
+ * Returns the mapped MSI ID.
  */
-u32 of_msi_map_rid(struct device *dev, struct device_node *msi_np, u32 rid_in)
+u32 of_msi_map_id(struct device *dev, struct device_node *msi_np, u32 id_in)
 {
-	return __of_msi_map_rid(dev, &msi_np, rid_in);
+	return __of_msi_map_id(dev, &msi_np, id_in);
 }
 
 /**
  * of_msi_map_get_device_domain - Use msi-map to find the relevant MSI domain
  * @dev: device for which the mapping is to be done.
- * @rid: Requester ID for the device.
+ * @id: Device ID.
+ * @bus_token: Bus token
  *
  * Walk up the device hierarchy looking for devices with a "msi-map"
  * property.
  *
  * Returns: the MSI domain for this device (or NULL on failure)
  */
-struct irq_domain *of_msi_map_get_device_domain(struct device *dev, u32 rid)
+struct irq_domain *of_msi_map_get_device_domain(struct device *dev, u32 id,
+						u32 bus_token)
 {
 	struct device_node *np = NULL;
 
-	__of_msi_map_rid(dev, &np, rid);
-	return irq_find_matching_host(np, DOMAIN_BUS_PCI_MSI);
+	__of_msi_map_id(dev, &np, id);
+	return irq_find_matching_host(np, bus_token);
 }
 
 /**

drivers/pci/msi.c

@@ -1535,8 +1535,8 @@ u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev)
 	pci_for_each_dma_alias(pdev, get_msi_id_cb, &rid);
 
 	of_node = irq_domain_get_of_node(domain);
-	rid = of_node ? of_msi_map_rid(&pdev->dev, of_node, rid) :
-			iort_msi_map_rid(&pdev->dev, rid);
+	rid = of_node ? of_msi_map_id(&pdev->dev, of_node, rid) :
+			iort_msi_map_id(&pdev->dev, rid);
 
 	return rid;
 }
@@ -1556,9 +1556,10 @@ struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev)
 	u32 rid = pci_dev_id(pdev);
 
 	pci_for_each_dma_alias(pdev, get_msi_id_cb, &rid);
-	dom = of_msi_map_get_device_domain(&pdev->dev, rid);
+	dom = of_msi_map_get_device_domain(&pdev->dev, rid, DOMAIN_BUS_PCI_MSI);
 	if (!dom)
-		dom = iort_get_device_domain(&pdev->dev, rid);
+		dom = iort_get_device_domain(&pdev->dev, rid,
+					     DOMAIN_BUS_PCI_MSI);
 	return dom;
 }
 #endif /* CONFIG_PCI_MSI_IRQ_DOMAIN */

drivers/perf/arm_smmuv3_pmu.c

@@ -755,8 +755,7 @@ static int smmu_pmu_probe(struct platform_device *pdev)
 		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 	};
 
-	res_0 = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	smmu_pmu->reg_base = devm_ioremap_resource(dev, res_0);
+	smmu_pmu->reg_base = devm_platform_get_and_ioremap_resource(pdev, 0, &res_0);
 	if (IS_ERR(smmu_pmu->reg_base))
 		return PTR_ERR(smmu_pmu->reg_base);
 

include/acpi/acpi_bus.h

@@ -588,8 +588,13 @@ bool acpi_dma_supported(struct acpi_device *adev);
 enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev);
 int acpi_dma_get_range(struct device *dev, u64 *dma_addr, u64 *offset,
 		       u64 *size);
-int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr);
-
+int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr,
+			   const u32 *input_id);
+static inline int acpi_dma_configure(struct device *dev,
+				     enum dev_dma_attr attr)
+{
+	return acpi_dma_configure_id(dev, attr, NULL);
+}
 struct acpi_device *acpi_find_child_device(struct acpi_device *parent,
 					   u64 address, bool check_children);
 int acpi_is_root_bridge(acpi_handle);

include/linux/acpi.h

@@ -905,6 +905,13 @@ static inline int acpi_dma_configure(struct device *dev,
 	return 0;
 }
 
+static inline int acpi_dma_configure_id(struct device *dev,
+					enum dev_dma_attr attr,
+					const u32 *input_id)
+{
+	return 0;
+}
+
 #define ACPI_PTR(_ptr)	(NULL)
 
 static inline void acpi_device_set_enumerated(struct acpi_device *adev)

include/linux/acpi_iort.h

@@ -28,27 +28,29 @@ void iort_deregister_domain_token(int trans_id);
 struct fwnode_handle *iort_find_domain_token(int trans_id);
 #ifdef CONFIG_ACPI_IORT
 void acpi_iort_init(void);
-u32 iort_msi_map_rid(struct device *dev, u32 req_id);
-struct irq_domain *iort_get_device_domain(struct device *dev, u32 req_id);
+u32 iort_msi_map_id(struct device *dev, u32 id);
+struct irq_domain *iort_get_device_domain(struct device *dev, u32 id,
+					  enum irq_domain_bus_token bus_token);
 void acpi_configure_pmsi_domain(struct device *dev);
 int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id);
 /* IOMMU interface */
 void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *size);
-const struct iommu_ops *iort_iommu_configure(struct device *dev);
+const struct iommu_ops *iort_iommu_configure_id(struct device *dev,
+						const u32 *id_in);
 int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head);
 #else
 static inline void acpi_iort_init(void) { }
-static inline u32 iort_msi_map_rid(struct device *dev, u32 req_id)
-{ return req_id; }
-static inline struct irq_domain *iort_get_device_domain(struct device *dev,
-							u32 req_id)
+static inline u32 iort_msi_map_id(struct device *dev, u32 id)
+{ return id; }
+static inline struct irq_domain *iort_get_device_domain(
+	struct device *dev, u32 id, enum irq_domain_bus_token bus_token)
 { return NULL; }
 static inline void acpi_configure_pmsi_domain(struct device *dev) { }
 /* IOMMU interface */
 static inline void iort_dma_setup(struct device *dev, u64 *dma_addr,
 				  u64 *size) { }
-static inline const struct iommu_ops *iort_iommu_configure(
-				      struct device *dev)
+static inline const struct iommu_ops *iort_iommu_configure_id(
+				      struct device *dev, const u32 *id_in)
 { return NULL; }
 static inline
 int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head)

include/linux/of.h

@@ -554,7 +554,7 @@ bool of_console_check(struct device_node *dn, char *name, int index);
 
 extern int of_cpu_node_to_id(struct device_node *np);
 
-int of_map_rid(struct device_node *np, u32 rid,
+int of_map_id(struct device_node *np, u32 id,
 	       const char *map_name, const char *map_mask_name,
 	       struct device_node **target, u32 *id_out);
 
@@ -978,7 +978,7 @@ static inline int of_cpu_node_to_id(struct device_node *np)
 	return -ENODEV;
 }
 
-static inline int of_map_rid(struct device_node *np, u32 rid,
+static inline int of_map_id(struct device_node *np, u32 id,
 			     const char *map_name, const char *map_mask_name,
 			     struct device_node **target, u32 *id_out)
 {

include/linux/of_device.h

@@ -55,9 +55,15 @@ static inline struct device_node *of_cpu_device_node_get(int cpu)
 	return of_node_get(cpu_dev->of_node);
 }
 
-int of_dma_configure(struct device *dev,
+int of_dma_configure_id(struct device *dev,
 		     struct device_node *np,
-		     bool force_dma);
+		     bool force_dma, const u32 *id);
+static inline int of_dma_configure(struct device *dev,
+				   struct device_node *np,
+				   bool force_dma)
+{
+	return of_dma_configure_id(dev, np, force_dma, NULL);
+}
 #else /* CONFIG_OF */
 
 static inline int of_driver_match_device(struct device *dev,
@@ -106,6 +112,12 @@ static inline struct device_node *of_cpu_device_node_get(int cpu)
 	return NULL;
 }
 
+static inline int of_dma_configure_id(struct device *dev,
+				   struct device_node *np,
+				   bool force_dma)
+{
+	return 0;
+}
 static inline int of_dma_configure(struct device *dev,
 				   struct device_node *np,
 				   bool force_dma)

include/linux/of_iommu.h

@@ -13,7 +13,8 @@ extern int of_get_dma_window(struct device_node *dn, const char *prefix,
 			     size_t *size);
 
 extern const struct iommu_ops *of_iommu_configure(struct device *dev,
-					struct device_node *master_np);
+					struct device_node *master_np,
+					const u32 *id);
 
 #else
 
@@ -25,7 +26,8 @@ static inline int of_get_dma_window(struct device_node *dn, const char *prefix,
 }
 
 static inline const struct iommu_ops *of_iommu_configure(struct device *dev,
-					 struct device_node *master_np)
+					 struct device_node *master_np,
+					 const u32 *id)
 {
 	return NULL;
 }

include/linux/of_irq.h

@@ -52,9 +52,10 @@ extern struct irq_domain *of_msi_get_domain(struct device *dev,
 					    struct device_node *np,
 					    enum irq_domain_bus_token token);
 extern struct irq_domain *of_msi_map_get_device_domain(struct device *dev,
-						       u32 rid);
+							u32 id,
+							u32 bus_token);
 extern void of_msi_configure(struct device *dev, struct device_node *np);
-u32 of_msi_map_rid(struct device *dev, struct device_node *msi_np, u32 rid_in);
+u32 of_msi_map_id(struct device *dev, struct device_node *msi_np, u32 id_in);
 #else
 static inline int of_irq_count(struct device_node *dev)
 {
@@ -85,17 +86,17 @@ static inline struct irq_domain *of_msi_get_domain(struct device *dev,
 	return NULL;
 }
 static inline struct irq_domain *of_msi_map_get_device_domain(struct device *dev,
-							      u32 rid)
+						u32 id, u32 bus_token)
 {
 	return NULL;
 }
 static inline void of_msi_configure(struct device *dev, struct device_node *np)
 {
 }
-static inline u32 of_msi_map_rid(struct device *dev,
-				 struct device_node *msi_np, u32 rid_in)
+static inline u32 of_msi_map_id(struct device *dev,
+				 struct device_node *msi_np, u32 id_in)
 {
-	return rid_in;
+	return id_in;
 }
 #endif
 

include/linux/sched_clock.h

@@ -6,6 +6,34 @@
 #define LINUX_SCHED_CLOCK
 
 #ifdef CONFIG_GENERIC_SCHED_CLOCK
+/**
+ * struct clock_read_data - data required to read from sched_clock()
+ *
+ * @epoch_ns:		sched_clock() value at last update
+ * @epoch_cyc:		Clock cycle value at last update.
+ * @sched_clock_mask:   Bitmask for two's complement subtraction of non 64bit
+ *			clocks.
+ * @read_sched_clock:	Current clock source (or dummy source when suspended).
+ * @mult:		Multipler for scaled math conversion.
+ * @shift:		Shift value for scaled math conversion.
+ *
+ * Care must be taken when updating this structure; it is read by
+ * some very hot code paths. It occupies <=40 bytes and, when combined
+ * with the seqcount used to synchronize access, comfortably fits into
+ * a 64 byte cache line.
+ */
+struct clock_read_data {
+	u64 epoch_ns;
+	u64 epoch_cyc;
+	u64 sched_clock_mask;
+	u64 (*read_sched_clock)(void);
+	u32 mult;
+	u32 shift;
+};
+
+extern struct clock_read_data *sched_clock_read_begin(unsigned int *seq);
+extern int sched_clock_read_retry(unsigned int seq);
+
 extern void generic_sched_clock_init(void);
 
 extern void sched_clock_register(u64 (*read)(void), int bits,

include/uapi/linux/perf_event.h

@@ -532,9 +532,10 @@ struct perf_event_mmap_page {
 				cap_bit0_is_deprecated	: 1, /* Always 1, signals that bit 0 is zero */
 
 				cap_user_rdpmc		: 1, /* The RDPMC instruction can be used to read counts */
-				cap_user_time		: 1, /* The time_* fields are used */
+				cap_user_time		: 1, /* The time_{shift,mult,offset} fields are used */
 				cap_user_time_zero	: 1, /* The time_zero field is used */
-				cap_____res		: 59;
+				cap_user_time_short	: 1, /* the time_{cycle,mask} fields are used */
+				cap_____res		: 58;
 		};
 	};
 
@@ -593,13 +594,29 @@ struct perf_event_mmap_page {
 	 *               ((rem * time_mult) >> time_shift);
 	 */
 	__u64	time_zero;
+
 	__u32	size;			/* Header size up to __reserved[] fields. */
+	__u32	__reserved_1;
+
+	/*
+	 * If cap_usr_time_short, the hardware clock is less than 64bit wide
+	 * and we must compute the 'cyc' value, as used by cap_usr_time, as:
+	 *
+	 *   cyc = time_cycles + ((cyc - time_cycles) & time_mask)
+	 *
+	 * NOTE: this form is explicitly chosen such that cap_usr_time_short
+	 *       is a correction on top of cap_usr_time, and code that doesn't
+	 *       know about cap_usr_time_short still works under the assumption
+	 *       the counter doesn't wrap.
+	 */
+	__u64	time_cycles;
+	__u64	time_mask;
 
 		/*
 		 * Hole for extension of the self monitor capabilities
 		 */
 
-	__u8	__reserved[118*8+4];	/* align to 1k. */
+	__u8	__reserved[116*8];	/* align to 1k. */
 
 	/*
 	 * Control data for the mmap() data buffer.

include/vdso/datapage.h

@@ -109,6 +109,7 @@ struct vdso_data {
  * relocation, and this is what we need.
  */
 extern struct vdso_data _vdso_data[CS_BASES] __attribute__((visibility("hidden")));
+extern struct vdso_data _timens_data[CS_BASES] __attribute__((visibility("hidden")));
 
 /*
  * The generic vDSO implementation requires that gettimeofday.h

kernel/crash_core.c

@@ -413,6 +413,7 @@ static int __init crash_save_vmcoreinfo_init(void)
 	VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS);
 	VMCOREINFO_STRUCT_SIZE(mem_section);
 	VMCOREINFO_OFFSET(mem_section, section_mem_map);
+	VMCOREINFO_NUMBER(MAX_PHYSMEM_BITS);
 #endif
 	VMCOREINFO_STRUCT_SIZE(page);
 	VMCOREINFO_STRUCT_SIZE(pglist_data);

kernel/time/sched_clock.c

@@ -19,31 +19,6 @@
 
 #include "timekeeping.h"
 
-/**
- * struct clock_read_data - data required to read from sched_clock()
- *
- * @epoch_ns:		sched_clock() value at last update
- * @epoch_cyc:		Clock cycle value at last update.
- * @sched_clock_mask:   Bitmask for two's complement subtraction of non 64bit
- *			clocks.
- * @read_sched_clock:	Current clock source (or dummy source when suspended).
- * @mult:		Multipler for scaled math conversion.
- * @shift:		Shift value for scaled math conversion.
- *
- * Care must be taken when updating this structure; it is read by
- * some very hot code paths. It occupies <=40 bytes and, when combined
- * with the seqcount used to synchronize access, comfortably fits into
- * a 64 byte cache line.
- */
-struct clock_read_data {
-	u64 epoch_ns;
-	u64 epoch_cyc;
-	u64 sched_clock_mask;
-	u64 (*read_sched_clock)(void);
-	u32 mult;
-	u32 shift;
-};
-
 /**
  * struct clock_data - all data needed for sched_clock() (including
  *                     registration of a new clock source)
@@ -93,6 +68,17 @@ static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift)
 	return (cyc * mult) >> shift;
 }
 
+struct clock_read_data *sched_clock_read_begin(unsigned int *seq)
+{
+	*seq = raw_read_seqcount_latch(&cd.seq);
+	return cd.read_data + (*seq & 1);
+}
+
+int sched_clock_read_retry(unsigned int seq)
+{
+	return read_seqcount_retry(&cd.seq, seq);
+}
+
 unsigned long long notrace sched_clock(void)
 {
 	u64 cyc, res;
@@ -100,13 +86,12 @@ unsigned long long notrace sched_clock(void)
 	struct clock_read_data *rd;
 
 	do {
-		seq = raw_read_seqcount(&cd.seq);
-		rd = cd.read_data + (seq & 1);
+		rd = sched_clock_read_begin(&seq);
 
 		cyc = (rd->read_sched_clock() - rd->epoch_cyc) &
 		      rd->sched_clock_mask;
 		res = rd->epoch_ns + cyc_to_ns(cyc, rd->mult, rd->shift);
-	} while (read_seqcount_retry(&cd.seq, seq));
+	} while (sched_clock_read_retry(seq));
 
 	return res;
 }

tools/include/uapi/linux/perf_event.h

@@ -532,9 +532,10 @@ struct perf_event_mmap_page {
 				cap_bit0_is_deprecated	: 1, /* Always 1, signals that bit 0 is zero */
 
 				cap_user_rdpmc		: 1, /* The RDPMC instruction can be used to read counts */
-				cap_user_time		: 1, /* The time_* fields are used */
+				cap_user_time		: 1, /* The time_{shift,mult,offset} fields are used */
 				cap_user_time_zero	: 1, /* The time_zero field is used */
-				cap_____res		: 59;
+				cap_user_time_short	: 1, /* the time_{cycle,mask} fields are used */
+				cap_____res		: 58;
 		};
 	};
 
@@ -593,13 +594,29 @@ struct perf_event_mmap_page {
 	 *               ((rem * time_mult) >> time_shift);
 	 */
 	__u64	time_zero;
+
 	__u32	size;			/* Header size up to __reserved[] fields. */
+	__u32	__reserved_1;
+
+	/*
+	 * If cap_usr_time_short, the hardware clock is less than 64bit wide
+	 * and we must compute the 'cyc' value, as used by cap_usr_time, as:
+	 *
+	 *   cyc = time_cycles + ((cyc - time_cycles) & time_mask)
+	 *
+	 * NOTE: this form is explicitly chosen such that cap_usr_time_short
+	 *       is a correction on top of cap_usr_time, and code that doesn't
+	 *       know about cap_usr_time_short still works under the assumption
+	 *       the counter doesn't wrap.
+	 */
+	__u64	time_cycles;
+	__u64	time_mask;
 
 		/*
 		 * Hole for extension of the self monitor capabilities
 		 */
 
-	__u8	__reserved[118*8+4];	/* align to 1k. */
+	__u8	__reserved[116*8];	/* align to 1k. */
 
 	/*
 	 * Control data for the mmap() data buffer.