Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Catalin Marinas:
 "These are the arm64 updates for 6.19.

  The biggest part is the Arm MPAM driver under drivers/resctrl/.
  There's a patch touching mm/ to handle spurious faults for huge pmd
  (similar to the pte version). The corresponding arm64 part allows us
  to avoid the TLB maintenance if a (huge) page is reused after a write
  fault. There's EFI refactoring to allow runtime services with
  preemption enabled and the rest is the usual perf/PMU updates and
  several cleanups/typos.

  Summary:

  Core features:

   - Basic Arm MPAM (Memory system resource Partitioning And Monitoring)
     driver under drivers/resctrl/ which makes use of the fs/rectrl/ API

  Perf and PMU:

   - Avoid cycle counter on multi-threaded CPUs

   - Extend CSPMU device probing and add additional filtering support
     for NVIDIA implementations

   - Add support for the PMUs on the NoC S3 interconnect

   - Add additional compatible strings for new Cortex and C1 CPUs

   - Add support for data source filtering to the SPE driver

   - Add support for i.MX8QM and "DB" PMU in the imx PMU driver

  Memory managemennt:

   - Avoid broadcast TLBI if page reused in write fault

   - Elide TLB invalidation if the old PTE was not valid

   - Drop redundant cpu_set_*_tcr_t0sz() macros

   - Propagate pgtable_alloc() errors outside of __create_pgd_mapping()

   - Propagate return value from __change_memory_common()

  ACPI and EFI:

   - Call EFI runtime services without disabling preemption

   - Remove unused ACPI function

  Miscellaneous:

   - ptrace support to disable streaming on SME-only systems

   - Improve sysreg generation to include a 'Prefix' descriptor

   - Replace __ASSEMBLY__ with __ASSEMBLER__

   - Align register dumps in the kselftest zt-test

   - Remove some no longer used macros/functions

   - Various spelling corrections"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (94 commits)
  arm64/mm: Document why linear map split failure upon vm_reset_perms is not problematic
  arm64/pageattr: Propagate return value from __change_memory_common
  arm64/sysreg: Remove unused define ARM64_FEATURE_FIELD_BITS
  KVM: arm64: selftests: Consider all 7 possible levels of cache
  KVM: arm64: selftests: Remove ARM64_FEATURE_FIELD_BITS and its last user
  arm64: atomics: lse: Remove unused parameters from ATOMIC_FETCH_OP_AND macros
  Documentation/arm64: Fix the typo of register names
  ACPI: GTDT: Get rid of acpi_arch_timer_mem_init()
  perf: arm_spe: Add support for filtering on data source
  perf: Add perf_event_attr::config4
  perf/imx_ddr: Add support for PMU in DB (system interconnects)
  perf/imx_ddr: Get and enable optional clks
  perf/imx_ddr: Move ida_alloc() from ddr_perf_init() to ddr_perf_probe()
  dt-bindings: perf: fsl-imx-ddr: Add compatible string for i.MX8QM, i.MX8QXP and i.MX8DXL
  arm64: remove duplicate ARCH_HAS_MEM_ENCRYPT
  arm64: mm: use untagged address to calculate page index
  MAINTAINERS: new entry for MPAM Driver
  arm_mpam: Add kunit tests for props_mismatch()
  arm_mpam: Add kunit test for bitmap reset
  arm_mpam: Add helper to reset saved mbwu state
  ...

Author: torvalds

Documentation/arch/arm64/booting.rst

@@ -391,13 +391,13 @@ Before jumping into the kernel, the following conditions must be met:
     - SMCR_EL2.LEN must be initialised to the same value for all CPUs the
       kernel will execute on.
 
-    - HWFGRTR_EL2.nTPIDR2_EL0 (bit 55) must be initialised to 0b01.
+    - HFGRTR_EL2.nTPIDR2_EL0 (bit 55) must be initialised to 0b01.
 
-    - HWFGWTR_EL2.nTPIDR2_EL0 (bit 55) must be initialised to 0b01.
+    - HFGWTR_EL2.nTPIDR2_EL0 (bit 55) must be initialised to 0b01.
 
-    - HWFGRTR_EL2.nSMPRI_EL1 (bit 54) must be initialised to 0b01.
+    - HFGRTR_EL2.nSMPRI_EL1 (bit 54) must be initialised to 0b01.
 
-    - HWFGWTR_EL2.nSMPRI_EL1 (bit 54) must be initialised to 0b01.
+    - HFGWTR_EL2.nSMPRI_EL1 (bit 54) must be initialised to 0b01.
 
   For CPUs with the Scalable Matrix Extension FA64 feature (FEAT_SME_FA64):
 

Documentation/arch/arm64/sve.rst

@@ -402,6 +402,11 @@ The regset data starts with struct user_sve_header, containing:
   streaming mode and any SETREGSET of NT_ARM_SSVE will enter streaming mode
   if the target was not in streaming mode.
 
+* On systems that do not support SVE it is permitted to use SETREGSET to
+  write SVE_PT_REGS_FPSIMD formatted data via NT_ARM_SVE, in this case the
+  vector length should be specified as 0. This allows streaming mode to be
+  disabled on systems with SME but not SVE.
+
 * If any register data is provided along with SVE_PT_VL_ONEXEC then the
   registers data will be interpreted with the current vector length, not
   the vector length configured for use on exec.

Documentation/devicetree/bindings/perf/fsl-imx-ddr.yaml

@@ -14,6 +14,7 @@ properties:
     oneOf:
       - enum:
           - fsl,imx8-ddr-pmu
+          - fsl,imx8dxl-db-pmu
           - fsl,imx8m-ddr-pmu
           - fsl,imx8mq-ddr-pmu
           - fsl,imx8mm-ddr-pmu
@@ -28,7 +29,10 @@ properties:
               - fsl,imx8mp-ddr-pmu
           - const: fsl,imx8m-ddr-pmu
       - items:
-          - const: fsl,imx8dxl-ddr-pmu
+          - enum:
+              - fsl,imx8dxl-ddr-pmu
+              - fsl,imx8qm-ddr-pmu
+              - fsl,imx8qxp-ddr-pmu
           - const: fsl,imx8-ddr-pmu
       - items:
           - enum:
@@ -43,13 +47,36 @@ properties:
   interrupts:
     maxItems: 1
 
+  clocks:
+    maxItems: 2
+
+  clock-names:
+    items:
+      - const: ipg
+      - const: cnt
+
 required:
   - compatible
   - reg
   - interrupts
 
 additionalProperties: false
 
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: fsl,imx8dxl-db-pmu
+    then:
+      required:
+        - clocks
+        - clock-names
+    else:
+      properties:
+        clocks: false
+        clock-names: false
+
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>

MAINTAINERS

@@ -17470,6 +17470,16 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/leds/backlight/mps,mp3309c.yaml
 F:	drivers/video/backlight/mp3309c.c
 
+MPAM DRIVER
+M:	James Morse <james.morse@arm.com>
+M:	Ben Horgan <ben.horgan@arm.com>
+R:	Reinette Chatre <reinette.chatre@intel.com>
+R:	Fenghua Yu <fenghuay@nvidia.com>
+S:	Maintained
+F:	drivers/resctrl/mpam_*
+F:	drivers/resctrl/test_mpam_*
+F:	include/linux/arm_mpam.h
+
 MPS MP2869 DRIVER
 M:	Wensheng Wang <wenswang@yeah.net>
 L:	linux-hwmon@vger.kernel.org

arch/arm64/Kconfig

@@ -47,7 +47,6 @@ config ARM64
 	select ARCH_HAS_SETUP_DMA_OPS
 	select ARCH_HAS_SET_DIRECT_MAP
 	select ARCH_HAS_SET_MEMORY
-	select ARCH_HAS_MEM_ENCRYPT
 	select ARCH_HAS_FORCE_DMA_UNENCRYPTED
 	select ARCH_STACKWALK
 	select ARCH_HAS_STRICT_KERNEL_RWX
@@ -2023,6 +2022,31 @@ config ARM64_TLB_RANGE
 	  ARMv8.4-TLBI provides TLBI invalidation instruction that apply to a
 	  range of input addresses.
 
+config ARM64_MPAM
+	bool "Enable support for MPAM"
+	select ARM64_MPAM_DRIVER if EXPERT	# does nothing yet
+	select ACPI_MPAM if ACPI
+	help
+	  Memory System Resource Partitioning and Monitoring (MPAM) is an
+	  optional extension to the Arm architecture that allows each
+	  transaction issued to the memory system to be labelled with a
+	  Partition identifier (PARTID) and Performance Monitoring Group
+	  identifier (PMG).
+
+	  Memory system components, such as the caches, can be configured with
+	  policies to control how much of various physical resources (such as
+	  memory bandwidth or cache memory) the transactions labelled with each
+	  PARTID can consume.  Depending on the capabilities of the hardware,
+	  the PARTID and PMG can also be used as filtering criteria to measure
+	  the memory system resource consumption of different parts of a
+	  workload.
+
+	  Use of this extension requires CPU support, support in the
+	  Memory System Components (MSC), and a description from firmware
+	  of where the MSCs are in the address space.
+
+	  MPAM is exposed to user-space via the resctrl pseudo filesystem.
+
 endmenu # "ARMv8.4 architectural features"
 
 menu "ARMv8.5 architectural features"

arch/arm64/include/asm/alternative-macros.h

@@ -19,7 +19,7 @@
 #error "cpucaps have overflown ARM64_CB_BIT"
 #endif
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/stringify.h>
 
@@ -207,7 +207,7 @@ alternative_endif
 #define _ALTERNATIVE_CFG(insn1, insn2, cap, cfg, ...)	\
 	alternative_insn insn1, insn2, cap, IS_ENABLED(cfg)
 
-#endif  /*  __ASSEMBLY__  */
+#endif  /*  __ASSEMBLER__  */
 
 /*
  * Usage: asm(ALTERNATIVE(oldinstr, newinstr, cpucap));
@@ -219,7 +219,7 @@ alternative_endif
 #define ALTERNATIVE(oldinstr, newinstr, ...)   \
 	_ALTERNATIVE_CFG(oldinstr, newinstr, __VA_ARGS__, 1)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 
@@ -263,6 +263,6 @@ alternative_has_cap_unlikely(const unsigned long cpucap)
 	return true;
 }
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_ALTERNATIVE_MACROS_H */

arch/arm64/include/asm/alternative.h

@@ -4,7 +4,7 @@
 
 #include <asm/alternative-macros.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/init.h>
 #include <linux/types.h>
@@ -37,5 +37,5 @@ static inline int apply_alternatives_module(void *start, size_t length)
 void alt_cb_patch_nops(struct alt_instr *alt, __le32 *origptr,
 		       __le32 *updptr, int nr_inst);
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* __ASM_ALTERNATIVE_H */

arch/arm64/include/asm/arch_gicv3.h

@@ -9,7 +9,7 @@
 
 #include <asm/sysreg.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/irqchip/arm-gic-common.h>
 #include <linux/stringify.h>
@@ -188,5 +188,5 @@ static inline bool gic_has_relaxed_pmr_sync(void)
 	return cpus_have_cap(ARM64_HAS_GIC_PRIO_RELAXED_SYNC);
 }
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* __ASM_ARCH_GICV3_H */

arch/arm64/include/asm/asm-extable.h

@@ -27,7 +27,7 @@
 /* Data fields for EX_TYPE_UACCESS_CPY */
 #define EX_DATA_UACCESS_WRITE	BIT(0)
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 #define __ASM_EXTABLE_RAW(insn, fixup, type, data)	\
 	.pushsection	__ex_table, "a";		\
@@ -77,7 +77,7 @@
 	__ASM_EXTABLE_RAW(\insn, \fixup, EX_TYPE_UACCESS_CPY, \uaccess_is_write)
 	.endm
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 
 #include <linux/stringify.h>
 
@@ -132,6 +132,6 @@
 			    EX_DATA_REG(ADDR, addr)				\
 			  ")")
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_ASM_EXTABLE_H */

arch/arm64/include/asm/assembler.h

@@ -5,7 +5,7 @@
  * Copyright (C) 1996-2000 Russell King
  * Copyright (C) 2012 ARM Ltd.
  */
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #error "Only include this from assembly code"
 #endif
 
@@ -325,14 +325,14 @@ alternative_cb_end
  * tcr_set_t0sz - update TCR.T0SZ so that we can load the ID map
  */
 	.macro	tcr_set_t0sz, valreg, t0sz
-	bfi	\valreg, \t0sz, #TCR_T0SZ_OFFSET, #TCR_TxSZ_WIDTH
+	bfi	\valreg, \t0sz, #TCR_EL1_T0SZ_SHIFT, #TCR_EL1_T0SZ_WIDTH
 	.endm
 
 /*
  * tcr_set_t1sz - update TCR.T1SZ
  */
 	.macro	tcr_set_t1sz, valreg, t1sz
-	bfi	\valreg, \t1sz, #TCR_T1SZ_OFFSET, #TCR_TxSZ_WIDTH
+	bfi	\valreg, \t1sz, #TCR_EL1_T1SZ_SHIFT, #TCR_EL1_T1SZ_WIDTH
 	.endm
 
 /*
@@ -371,7 +371,7 @@ alternative_endif
  * [start, end) with dcache line size explicitly provided.
  *
  * 	op:		operation passed to dc instruction
- * 	domain:		domain used in dsb instruciton
+ * 	domain:		domain used in dsb instruction
  * 	start:          starting virtual address of the region
  * 	end:            end virtual address of the region
  *	linesz:		dcache line size
@@ -412,7 +412,7 @@ alternative_endif
  * [start, end)
  *
  * 	op:		operation passed to dc instruction
- * 	domain:		domain used in dsb instruciton
+ * 	domain:		domain used in dsb instruction
  * 	start:          starting virtual address of the region
  * 	end:            end virtual address of the region
  * 	fixup:		optional label to branch to on user fault
@@ -589,7 +589,7 @@ alternative_endif
 	.macro	offset_ttbr1, ttbr, tmp
 #if defined(CONFIG_ARM64_VA_BITS_52) && !defined(CONFIG_ARM64_LPA2)
 	mrs	\tmp, tcr_el1
-	and	\tmp, \tmp, #TCR_T1SZ_MASK
+	and	\tmp, \tmp, #TCR_EL1_T1SZ_MASK
 	cmp	\tmp, #TCR_T1SZ(VA_BITS_MIN)
 	orr	\tmp, \ttbr, #TTBR1_BADDR_4852_OFFSET
 	csel	\ttbr, \tmp, \ttbr, eq