Merge branches 'for-next/mte', 'for-next/misc' and 'for-next/kselftest', remote-tracking branch 'arm64/for-next/perf' into for-next/core

* arm64/for-next/perf:
  arm64/perf: Replace '0xf' instances with ID_AA64DFR0_PMUVER_IMP_DEF

* for-next/mte:
  : Miscellaneous MTE improvements.
  arm64/cpufeature: Optionally disable MTE via command-line
  arm64: kasan: mte: remove redundant mte_report_once logic
  arm64: kasan: mte: use a constant kernel GCR_EL1 value
  arm64: avoid double ISB on kernel entry
  arm64: mte: optimize GCR_EL1 modification on kernel entry/exit
  Documentation: document the preferred tag checking mode feature
  arm64: mte: introduce a per-CPU tag checking mode preference
  arm64: move preemption disablement to prctl handlers
  arm64: mte: change ASYNC and SYNC TCF settings into bitfields
  arm64: mte: rename gcr_user_excl to mte_ctrl
  arm64: mte: avoid TFSRE0_EL1 related operations unless in async mode

* for-next/misc:
  : Miscellaneous updates.
  arm64: Do not trap PMSNEVFR_EL1
  arm64: mm: fix comment typo of pud_offset_phys()
  arm64: signal32: Drop pointless call to sigdelsetmask()
  arm64/sve: Better handle failure to allocate SVE register storage
  arm64: Document the requirement for SCR_EL3.HCE
  arm64: head: avoid over-mapping in map_memory
  arm64/sve: Add a comment documenting the binutils needed for SVE asm
  arm64/sve: Add some comments for sve_save/load_state()
  arm64: replace in_irq() with in_hardirq()
  arm64: mm: Fix TLBI vs ASID rollover
  arm64: entry: Add SYM_CODE annotation for __bad_stack
  arm64: fix typo in a comment
  arm64: move the (z)install rules to arch/arm64/Makefile
  arm64/sve: Make fpsimd_bind_task_to_cpu() static
  arm64: unnecessary end 'return;' in void functions
  arm64/sme: Document boot requirements for SME
  arm64: use __func__ to get function name in pr_err
  arm64: SSBS/DIT: print SSBS and DIT bit when printing PSTATE
  arm64: cpufeature: Use defined macro instead of magic numbers
  arm64/kexec: Test page size support with new TGRAN range values

* for-next/kselftest:
  : Kselftest additions for arm64.
  kselftest/arm64: signal: Add a TODO list for signal handling tests
  kselftest/arm64: signal: Add test case for SVE register state in signals
  kselftest/arm64: signal: Verify that signals can't change the SVE vector length
  kselftest/arm64: signal: Check SVE signal frame shows expected vector length
  kselftest/arm64: signal: Support signal frames with SVE register data
  kselftest/arm64: signal: Add SVE to the set of features we can check for
  kselftest/arm64: pac: Fix skipping of tests on systems without PAC
  kselftest/arm64: mte: Fix misleading output when skipping tests
  kselftest/arm64: Add a TODO list for floating point tests
  kselftest/arm64: Add tests for SVE vector configuration
  kselftest/arm64: Validate vector lengths are set in sve-probe-vls
  kselftest/arm64: Provide a helper binary and "library" for SVE RDVL
  kselftest/arm64: Ignore check_gcr_el1_cswitch binary

Author: ctmarinas

Documentation/ABI/testing/sysfs-devices-system-cpu

@@ -640,3 +640,20 @@ Description:	SPURR ticks for cpuX when it was idle.
 
 		This sysfs interface exposes the number of SPURR ticks
 		for cpuX when it was idle.
+
+What: 		/sys/devices/system/cpu/cpuX/mte_tcf_preferred
+Date:		July 2021
+Contact:	Linux ARM Kernel Mailing list <[email protected]>
+Description:	Preferred MTE tag checking mode
+
+		When a user program specifies more than one MTE tag checking
+		mode, this sysfs node is used to specify which mode should
+		be preferred when scheduling a task on that CPU. Possible
+		values:
+
+		================  ==============================================
+		"sync"	  	  Prefer synchronous mode
+		"async"	  	  Prefer asynchronous mode
+		================  ==============================================
+
+		See also: Documentation/arm64/memory-tagging-extension.rst

Documentation/admin-guide/kernel-parameters.txt

@@ -380,6 +380,9 @@
 	arm64.nopauth	[ARM64] Unconditionally disable Pointer Authentication
 			support
 
+	arm64.nomte	[ARM64] Unconditionally disable Memory Tagging Extension
+			support
+
 	ataflop=	[HW,M68k]
 
 	atarimouse=	[HW,MOUSE] Atari Mouse

Documentation/arm64/booting.rst

@@ -207,10 +207,17 @@ Before jumping into the kernel, the following conditions must be met:
   software at a higher exception level to prevent execution in an UNKNOWN
   state.
 
-  - SCR_EL3.FIQ must have the same value across all CPUs the kernel is
-    executing on.
-  - The value of SCR_EL3.FIQ must be the same as the one present at boot
-    time whenever the kernel is executing.
+  For all systems:
+  - If EL3 is present:
+
+    - SCR_EL3.FIQ must have the same value across all CPUs the kernel is
+      executing on.
+    - The value of SCR_EL3.FIQ must be the same as the one present at boot
+      time whenever the kernel is executing.
+
+  - If EL3 is present and the kernel is entered at EL2:
+
+    - SCR_EL3.HCE (bit 8) must be initialised to 0b1.
 
   For systems with a GICv3 interrupt controller to be used in v3 mode:
   - If EL3 is present:
@@ -311,6 +318,28 @@ Before jumping into the kernel, the following conditions must be met:
     - ZCR_EL2.LEN must be initialised to the same value for all CPUs the
       kernel will execute on.
 
+  For CPUs with the Scalable Matrix Extension (FEAT_SME):
+
+  - If EL3 is present:
+
+    - CPTR_EL3.ESM (bit 12) must be initialised to 0b1.
+
+    - SCR_EL3.EnTP2 (bit 41) must be initialised to 0b1.
+
+    - SMCR_EL3.LEN must be initialised to the same value for all CPUs the
+      kernel will execute on.
+
+ - If the kernel is entered at EL1 and EL2 is present:
+
+    - CPTR_EL2.TSM (bit 12) must be initialised to 0b0.
+
+    - CPTR_EL2.SMEN (bits 25:24) must be initialised to 0b11.
+
+    - SCTLR_EL2.EnTP2 (bit 60) must be initialised to 0b1.
+
+    - SMCR_EL2.LEN must be initialised to the same value for all CPUs the
+      kernel will execute on.
+
 The requirements described above for CPU mode, caches, MMUs, architected
 timers, coherency and system registers apply to all CPUs.  All CPUs must
 enter the kernel in the same exception level.  Where the values documented

Documentation/arm64/memory-tagging-extension.rst

@@ -77,14 +77,20 @@ configurable behaviours:
   address is unknown).
 
 The user can select the above modes, per thread, using the
-``prctl(PR_SET_TAGGED_ADDR_CTRL, flags, 0, 0, 0)`` system call where
-``flags`` contain one of the following values in the ``PR_MTE_TCF_MASK``
+``prctl(PR_SET_TAGGED_ADDR_CTRL, flags, 0, 0, 0)`` system call where ``flags``
+contains any number of the following values in the ``PR_MTE_TCF_MASK``
 bit-field:
 
-- ``PR_MTE_TCF_NONE``  - *Ignore* tag check faults
+- ``PR_MTE_TCF_NONE``  - *Ignore* tag check faults
+                         (ignored if combined with other options)
 - ``PR_MTE_TCF_SYNC``  - *Synchronous* tag check fault mode
 - ``PR_MTE_TCF_ASYNC`` - *Asynchronous* tag check fault mode
 
+If no modes are specified, tag check faults are ignored. If a single
+mode is specified, the program will run in that mode. If multiple
+modes are specified, the mode is selected as described in the "Per-CPU
+preferred tag checking modes" section below.
+
 The current tag check fault mode can be read using the
 ``prctl(PR_GET_TAGGED_ADDR_CTRL, 0, 0, 0, 0)`` system call.
 
@@ -120,13 +126,39 @@ in the ``PR_MTE_TAG_MASK`` bit-field.
 interface provides an include mask. An include mask of ``0`` (exclusion
 mask ``0xffff``) results in the CPU always generating tag ``0``.
 
+Per-CPU preferred tag checking mode
+-----------------------------------
+
+On some CPUs the performance of MTE in stricter tag checking modes
+is similar to that of less strict tag checking modes. This makes it
+worthwhile to enable stricter checks on those CPUs when a less strict
+checking mode is requested, in order to gain the error detection
+benefits of the stricter checks without the performance downsides. To
+support this scenario, a privileged user may configure a stricter
+tag checking mode as the CPU's preferred tag checking mode.
+
+The preferred tag checking mode for each CPU is controlled by
+``/sys/devices/system/cpu/cpu<N>/mte_tcf_preferred``, to which a
+privileged user may write the value ``async`` or ``sync``.  The default
+preferred mode for each CPU is ``async``.
+
+To allow a program to potentially run in the CPU's preferred tag
+checking mode, the user program may set multiple tag check fault mode
+bits in the ``flags`` argument to the ``prctl(PR_SET_TAGGED_ADDR_CTRL,
+flags, 0, 0, 0)`` system call. If the CPU's preferred tag checking
+mode is in the task's set of provided tag checking modes (this will
+always be the case at present because the kernel only supports two
+tag checking modes, but future kernels may support more modes), that
+mode will be selected. Otherwise, one of the modes in the task's mode
+set will be selected in a currently unspecified manner.
+
 Initial process state
 ---------------------
 
 On ``execve()``, the new process has the following configuration:
 
 - ``PR_TAGGED_ADDR_ENABLE`` set to 0 (disabled)
-- Tag checking mode set to ``PR_MTE_TCF_NONE``
+- No tag checking modes are selected (tag check faults ignored)
 - ``PR_MTE_TAG_MASK`` set to 0 (all tags excluded)
 - ``PSTATE.TCO`` set to 0
 - ``PROT_MTE`` not set on any of the initial memory maps
@@ -251,11 +283,13 @@ Example of correct usage
                     return EXIT_FAILURE;
 
             /*
-             * Enable the tagged address ABI, synchronous MTE tag check faults and
-             * allow all non-zero tags in the randomly generated set.
+             * Enable the tagged address ABI, synchronous or asynchronous MTE
+             * tag check faults (based on per-CPU preference) and allow all
+             * non-zero tags in the randomly generated set.
              */
             if (prctl(PR_SET_TAGGED_ADDR_CTRL,
-                      PR_TAGGED_ADDR_ENABLE | PR_MTE_TCF_SYNC | (0xfffe << PR_MTE_TAG_SHIFT),
+                      PR_TAGGED_ADDR_ENABLE | PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC |
+                      (0xfffe << PR_MTE_TAG_SHIFT),
                       0, 0, 0)) {
                     perror("prctl() failed");
                     return EXIT_FAILURE;

arch/arm64/Makefile

@@ -165,8 +165,11 @@ Image: vmlinux
 Image.%: Image
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
-zinstall install:
-	$(Q)$(MAKE) $(build)=$(boot) $@
+install: install-image := Image
+zinstall: install-image := Image.gz
+install zinstall:
+	$(CONFIG_SHELL) $(srctree)/$(boot)/install.sh $(KERNELRELEASE) \
+	$(boot)/$(install-image) System.map "$(INSTALL_PATH)"
 
 PHONY += vdso_install
 vdso_install:

arch/arm64/boot/Makefile

@@ -35,11 +35,3 @@ $(obj)/Image.lzma: $(obj)/Image FORCE
 
 $(obj)/Image.lzo: $(obj)/Image FORCE
 	$(call if_changed,lzo)
-
-install:
-	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
-	$(obj)/Image System.map "$(INSTALL_PATH)"
-
-zinstall:
-	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
-	$(obj)/Image.gz System.map "$(INSTALL_PATH)"

arch/arm64/include/asm/cpufeature.h

@@ -657,7 +657,8 @@ static inline bool system_supports_4kb_granule(void)
 	val = cpuid_feature_extract_unsigned_field(mmfr0,
 						ID_AA64MMFR0_TGRAN4_SHIFT);
 
-	return val == ID_AA64MMFR0_TGRAN4_SUPPORTED;
+	return (val >= ID_AA64MMFR0_TGRAN4_SUPPORTED_MIN) &&
+	       (val <= ID_AA64MMFR0_TGRAN4_SUPPORTED_MAX);
 }
 
 static inline bool system_supports_64kb_granule(void)
@@ -669,7 +670,8 @@ static inline bool system_supports_64kb_granule(void)
 	val = cpuid_feature_extract_unsigned_field(mmfr0,
 						ID_AA64MMFR0_TGRAN64_SHIFT);
 
-	return val == ID_AA64MMFR0_TGRAN64_SUPPORTED;
+	return (val >= ID_AA64MMFR0_TGRAN64_SUPPORTED_MIN) &&
+	       (val <= ID_AA64MMFR0_TGRAN64_SUPPORTED_MAX);
 }
 
 static inline bool system_supports_16kb_granule(void)
@@ -681,7 +683,8 @@ static inline bool system_supports_16kb_granule(void)
 	val = cpuid_feature_extract_unsigned_field(mmfr0,
 						ID_AA64MMFR0_TGRAN16_SHIFT);
 
-	return val == ID_AA64MMFR0_TGRAN16_SUPPORTED;
+	return (val >= ID_AA64MMFR0_TGRAN16_SUPPORTED_MIN) &&
+	       (val <= ID_AA64MMFR0_TGRAN16_SUPPORTED_MAX);
 }
 
 static inline bool system_supports_mixed_endian_el0(void)

arch/arm64/include/asm/el2_setup.h

@@ -150,8 +150,17 @@
 	ubfx	x1, x1, #ID_AA64MMFR0_FGT_SHIFT, #4
 	cbz	x1, .Lskip_fgt_\@
 
-	msr_s	SYS_HDFGRTR_EL2, xzr
-	msr_s	SYS_HDFGWTR_EL2, xzr
+	mov	x0, xzr
+	mrs	x1, id_aa64dfr0_el1
+	ubfx	x1, x1, #ID_AA64DFR0_PMSVER_SHIFT, #4
+	cmp	x1, #3
+	b.lt	.Lset_fgt_\@
+	/* Disable PMSNEVFR_EL1 read and write traps */
+	orr	x0, x0, #(1 << 62)
+
+.Lset_fgt_\@:
+	msr_s	SYS_HDFGRTR_EL2, x0
+	msr_s	SYS_HDFGWTR_EL2, x0
 	msr_s	SYS_HFGRTR_EL2, xzr
 	msr_s	SYS_HFGWTR_EL2, xzr
 	msr_s	SYS_HFGITR_EL2, xzr

arch/arm64/include/asm/fpsimd.h

@@ -45,7 +45,6 @@ extern void fpsimd_preserve_current_state(void);
 extern void fpsimd_restore_current_state(void);
 extern void fpsimd_update_current_state(struct user_fpsimd_state const *state);
 
-extern void fpsimd_bind_task_to_cpu(void);
 extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state,
 				     void *sve_state, unsigned int sve_vl);
 

arch/arm64/include/asm/fpsimdmacros.h

@@ -94,6 +94,7 @@
 .endm
 
 /* SVE instruction encodings for non-SVE-capable assemblers */
+/* (pre binutils 2.28, all kernel capable clang versions support SVE) */
 
 /* STR (vector): STR Z\nz, [X\nxbase, #\offset, MUL VL] */
 .macro _sve_str_v nz, nxbase, offset=0