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

Pull arm64 fixes from Will Deacon:
 "A bumper crop of arm64 fixes for -rc3.

  The largest change is fixing our parsing of the 'rodata=full' command
  line option, which kstrtobool() started treating as 'rodata=false'.
  The fix actually makes the parsing of that option much less fragile
  and updates the documentation at the same time.

  We still have a boot issue pending when KASLR is disabled at compile
  time, but there's a fresh fix on the list which I'll send next week if
  it holds up to testing.

  Summary:

   - Fix workaround for Cortex-A76 erratum #1286807

   - Add workaround for AMU erratum #2457168 on Cortex-A510

   - Drop reference to removed CONFIG_ARCH_RANDOM #define

   - Fix parsing of the "rodata=full" cmdline option

   - Fix a bunch of issues in the SME register state switching and sigframe code

   - Fix incorrect extraction of the CTR_EL0.CWG register field

   - Fix ACPI cache topology probing when the PPTT is not present

   - Trivial comment and whitespace fixes"

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64/sme: Don't flush SVE register state when handling SME traps
  arm64/sme: Don't flush SVE register state when allocating SME storage
  arm64/signal: Flush FPSIMD register state when disabling streaming mode
  arm64/signal: Raise limit on stack frames
  arm64/cache: Fix cache_type_cwg() for register generation
  arm64/sysreg: Guard SYS_FIELD_ macros for asm
  arm64/sysreg: Directly include bitfield.h
  arm64: cacheinfo: Fix incorrect assignment of signed error value to unsigned fw_level
  arm64: errata: add detection for AMEVCNTR01 incrementing incorrectly
  arm64: fix rodata=full
  arm64: Fix comment typo
  docs/arm64: elf_hwcaps: unify newlines in HWCAP lists
  arm64: adjust KASLR relocation after ARCH_RANDOM removal
  arm64: Fix match_list for erratum 1286807 on Arm Cortex-A76

Documentation/admin-guide/kernel-parameters.txt

@@ -5331,6 +5331,8 @@
 	rodata=		[KNL]
 		on	Mark read-only kernel memory as read-only (default).
 		off	Leave read-only kernel memory writable for debugging.
+		full	Mark read-only kernel memory and aliases as read-only
+		        [arm64]
 
 	rockchip.usb_uart
 			Enable the uart passthrough on the designated usb port

Documentation/arm64/elf_hwcaps.rst

@@ -242,44 +242,34 @@ HWCAP2_MTE3
     by Documentation/arm64/memory-tagging-extension.rst.
 
 HWCAP2_SME
-
     Functionality implied by ID_AA64PFR1_EL1.SME == 0b0001, as described
     by Documentation/arm64/sme.rst.
 
 HWCAP2_SME_I16I64
-
     Functionality implied by ID_AA64SMFR0_EL1.I16I64 == 0b1111.
 
 HWCAP2_SME_F64F64
-
     Functionality implied by ID_AA64SMFR0_EL1.F64F64 == 0b1.
 
 HWCAP2_SME_I8I32
-
     Functionality implied by ID_AA64SMFR0_EL1.I8I32 == 0b1111.
 
 HWCAP2_SME_F16F32
-
     Functionality implied by ID_AA64SMFR0_EL1.F16F32 == 0b1.
 
 HWCAP2_SME_B16F32
-
     Functionality implied by ID_AA64SMFR0_EL1.B16F32 == 0b1.
 
 HWCAP2_SME_F32F32
-
     Functionality implied by ID_AA64SMFR0_EL1.F32F32 == 0b1.
 
 HWCAP2_SME_FA64
-
     Functionality implied by ID_AA64SMFR0_EL1.FA64 == 0b1.
 
 HWCAP2_WFXT
-
     Functionality implied by ID_AA64ISAR2_EL1.WFXT == 0b0010.
 
 HWCAP2_EBF16
-
     Functionality implied by ID_AA64ISAR1_EL1.BF16 == 0b0010.
 
 4. Unused AT_HWCAP bits

Documentation/arm64/silicon-errata.rst

@@ -52,6 +52,8 @@ stable kernels.
 | Allwinner      | A64/R18         | UNKNOWN1        | SUN50I_ERRATUM_UNKNOWN1     |
 +----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Cortex-A510     | #2457168        | ARM64_ERRATUM_2457168       |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A510     | #2064142        | ARM64_ERRATUM_2064142       |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A510     | #2038923        | ARM64_ERRATUM_2038923       |

arch/arm64/Kconfig

@@ -917,6 +917,23 @@ config ARM64_ERRATUM_1902691
 
 	  If unsure, say Y.
 
+config ARM64_ERRATUM_2457168
+	bool "Cortex-A510: 2457168: workaround for AMEVCNTR01 incrementing incorrectly"
+	depends on ARM64_AMU_EXTN
+	default y
+	help
+	  This option adds the workaround for ARM Cortex-A510 erratum 2457168.
+
+	  The AMU counter AMEVCNTR01 (constant counter) should increment at the same rate
+	  as the system counter. On affected Cortex-A510 cores AMEVCNTR01 increments
+	  incorrectly giving a significantly higher output value.
+
+	  Work around this problem by returning 0 when reading the affected counter in
+	  key locations that results in disabling all users of this counter. This effect
+	  is the same to firmware disabling affected counters.
+
+	  If unsure, say Y.
+
 config CAVIUM_ERRATUM_22375
 	bool "Cavium erratum 22375, 24313"
 	default y

arch/arm64/include/asm/cache.h

@@ -71,7 +71,7 @@ static __always_inline int icache_is_vpipt(void)
 
 static inline u32 cache_type_cwg(void)
 {
-	return (read_cpuid_cachetype() >> CTR_EL0_CWG_SHIFT) & CTR_EL0_CWG_MASK;
+	return SYS_FIELD_GET(CTR_EL0, CWG, read_cpuid_cachetype());
 }
 
 #define __read_mostly __section(".data..read_mostly")

arch/arm64/include/asm/fpsimd.h

@@ -153,7 +153,7 @@ struct vl_info {
 
 #ifdef CONFIG_ARM64_SVE
 
-extern void sve_alloc(struct task_struct *task);
+extern void sve_alloc(struct task_struct *task, bool flush);
 extern void fpsimd_release_task(struct task_struct *task);
 extern void fpsimd_sync_to_sve(struct task_struct *task);
 extern void fpsimd_force_sync_to_sve(struct task_struct *task);
@@ -256,7 +256,7 @@ size_t sve_state_size(struct task_struct const *task);
 
 #else /* ! CONFIG_ARM64_SVE */
 
-static inline void sve_alloc(struct task_struct *task) { }
+static inline void sve_alloc(struct task_struct *task, bool flush) { }
 static inline void fpsimd_release_task(struct task_struct *task) { }
 static inline void sve_sync_to_fpsimd(struct task_struct *task) { }
 static inline void sve_sync_from_fpsimd_zeropad(struct task_struct *task) { }

arch/arm64/include/asm/setup.h

@@ -3,6 +3,8 @@
 #ifndef __ARM64_ASM_SETUP_H
 #define __ARM64_ASM_SETUP_H
 
+#include <linux/string.h>
+
 #include <uapi/asm/setup.h>
 
 void *get_early_fdt_ptr(void);
@@ -14,4 +16,19 @@ void early_fdt_map(u64 dt_phys);
 extern phys_addr_t __fdt_pointer __initdata;
 extern u64 __cacheline_aligned boot_args[4];
 
+static inline bool arch_parse_debug_rodata(char *arg)
+{
+	extern bool rodata_enabled;
+	extern bool rodata_full;
+
+	if (arg && !strcmp(arg, "full")) {
+		rodata_enabled = true;
+		rodata_full = true;
+		return true;
+	}
+
+	return false;
+}
+#define arch_parse_debug_rodata arch_parse_debug_rodata
+
 #endif

arch/arm64/include/asm/sysreg.h

@@ -1116,6 +1116,7 @@
 
 #else
 
+#include <linux/bitfield.h>
 #include <linux/build_bug.h>
 #include <linux/types.h>
 #include <asm/alternative.h>
@@ -1209,8 +1210,6 @@
 	par;								\
 })
 
-#endif
-
 #define SYS_FIELD_GET(reg, field, val)		\
 		 FIELD_GET(reg##_##field##_MASK, val)
 
@@ -1220,4 +1219,6 @@
 #define SYS_FIELD_PREP_ENUM(reg, field, val)		\
 		 FIELD_PREP(reg##_##field##_MASK, reg##_##field##_##val)
 
+#endif
+
 #endif	/* __ASM_SYSREG_H */

arch/arm64/kernel/cacheinfo.c

@@ -45,7 +45,8 @@ static void ci_leaf_init(struct cacheinfo *this_leaf,
 
 int init_cache_level(unsigned int cpu)
 {
-	unsigned int ctype, level, leaves, fw_level;
+	unsigned int ctype, level, leaves;
+	int fw_level;
 	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
 
 	for (level = 1, leaves = 0; level <= MAX_CACHE_LEVEL; level++) {
@@ -63,6 +64,9 @@ int init_cache_level(unsigned int cpu)
 	else
 		fw_level = acpi_find_last_cache_level(cpu);
 
+	if (fw_level < 0)
+		return fw_level;
+
 	if (level < fw_level) {
 		/*
 		 * some external caches not specified in CLIDR_EL1

arch/arm64/kernel/cpu_errata.c

@@ -208,6 +208,8 @@ static const struct arm64_cpu_capabilities arm64_repeat_tlbi_list[] = {
 #ifdef CONFIG_ARM64_ERRATUM_1286807
 	{
 		ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 0),
+	},
+	{
 		/* Kryo4xx Gold (rcpe to rfpe) => (r0p0 to r3p0) */
 		ERRATA_MIDR_RANGE(MIDR_QCOM_KRYO_4XX_GOLD, 0xc, 0xe, 0xf, 0xe),
 	},
@@ -654,6 +656,16 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A510, 0, 0, 2)
 	},
 #endif
+#ifdef CONFIG_ARM64_ERRATUM_2457168
+	{
+		.desc = "ARM erratum 2457168",
+		.capability = ARM64_WORKAROUND_2457168,
+		.type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE,
+
+		/* Cortex-A510 r0p0-r1p1 */
+		CAP_MIDR_RANGE(MIDR_CORTEX_A510, 0, 0, 1, 1)
+	},
+#endif
 #ifdef CONFIG_ARM64_ERRATUM_2038923
 	{
 		.desc = "ARM erratum 2038923",

arch/arm64/kernel/cpufeature.c

@@ -1870,6 +1870,9 @@ static void cpu_amu_enable(struct arm64_cpu_capabilities const *cap)
 		pr_info("detected CPU%d: Activity Monitors Unit (AMU)\n",
 			smp_processor_id());
 		cpumask_set_cpu(smp_processor_id(), &amu_cpus);
+
+		/* 0 reference values signal broken/disabled counters */
+		if (!this_cpu_has_cap(ARM64_WORKAROUND_2457168))
 			update_freq_counters_refs();
 	}
 }

arch/arm64/kernel/entry.S

@@ -502,7 +502,7 @@ tsk	.req	x28		// current thread_info
 SYM_CODE_START(vectors)
 	kernel_ventry	1, t, 64, sync		// Synchronous EL1t
 	kernel_ventry	1, t, 64, irq		// IRQ EL1t
-	kernel_ventry	1, t, 64, fiq		// FIQ EL1h
+	kernel_ventry	1, t, 64, fiq		// FIQ EL1t
 	kernel_ventry	1, t, 64, error		// Error EL1t
 
 	kernel_ventry	1, h, 64, sync		// Synchronous EL1h

arch/arm64/kernel/fpsimd.c

@@ -715,10 +715,12 @@ size_t sve_state_size(struct task_struct const *task)
  * do_sve_acc() case, there is no ABI requirement to hide stale data
  * written previously be task.
  */
-void sve_alloc(struct task_struct *task)
+void sve_alloc(struct task_struct *task, bool flush)
 {
 	if (task->thread.sve_state) {
-		memset(task->thread.sve_state, 0, sve_state_size(task));
+		if (flush)
+			memset(task->thread.sve_state, 0,
+			       sve_state_size(task));
 		return;
 	}
 
@@ -1388,7 +1390,7 @@ void do_sve_acc(unsigned long esr, struct pt_regs *regs)
 		return;
 	}
 
-	sve_alloc(current);
+	sve_alloc(current, true);
 	if (!current->thread.sve_state) {
 		force_sig(SIGKILL);
 		return;
@@ -1439,7 +1441,7 @@ void do_sme_acc(unsigned long esr, struct pt_regs *regs)
 		return;
 	}
 
-	sve_alloc(current);
+	sve_alloc(current, false);
 	sme_alloc(current);
 	if (!current->thread.sve_state || !current->thread.za_state) {
 		force_sig(SIGKILL);
@@ -1460,17 +1462,6 @@ void do_sme_acc(unsigned long esr, struct pt_regs *regs)
 		fpsimd_bind_task_to_cpu();
 	}
 
-	/*
-	 * If SVE was not already active initialise the SVE registers,
-	 * any non-shared state between the streaming and regular SVE
-	 * registers is architecturally guaranteed to be zeroed when
-	 * we enter streaming mode.  We do not need to initialize ZA
-	 * since ZA must be disabled at this point and enabling ZA is
-	 * architecturally defined to zero ZA.
-	 */
-	if (system_supports_sve() && !test_thread_flag(TIF_SVE))
-		sve_init_regs();
-
 	put_cpu_fpsimd_context();
 }
 

arch/arm64/kernel/pi/kaslr_early.c

@@ -94,10 +94,8 @@ asmlinkage u64 kaslr_early_init(void *fdt)
 
 	seed = get_kaslr_seed(fdt);
 	if (!seed) {
-#ifdef CONFIG_ARCH_RANDOM
 		if (!__early_cpu_has_rndr() ||
 		    !__arm64_rndr((unsigned long *)&seed))
-#endif
 			return 0;
 	}
 

arch/arm64/kernel/ptrace.c

@@ -882,7 +882,7 @@ static int sve_set_common(struct task_struct *target,
 		 * state and ensure there's storage.
 		 */
 		if (target->thread.svcr != old_svcr)
-			sve_alloc(target);
+			sve_alloc(target, true);
 	}
 
 	/* Registers: FPSIMD-only case */
@@ -912,7 +912,7 @@ static int sve_set_common(struct task_struct *target,
 		goto out;
 	}
 
-	sve_alloc(target);
+	sve_alloc(target, true);
 	if (!target->thread.sve_state) {
 		ret = -ENOMEM;
 		clear_tsk_thread_flag(target, TIF_SVE);
@@ -1082,7 +1082,7 @@ static int za_set(struct task_struct *target,
 
 	/* Ensure there is some SVE storage for streaming mode */
 	if (!target->thread.sve_state) {
-		sve_alloc(target);
+		sve_alloc(target, false);
 		if (!target->thread.sve_state) {
 			clear_thread_flag(TIF_SME);
 			ret = -ENOMEM;

arch/arm64/kernel/signal.c

@@ -91,7 +91,7 @@ static size_t sigframe_size(struct rt_sigframe_user_layout const *user)
  * not taken into account.  This limit is not a guarantee and is
  * NOT ABI.
  */
-#define SIGFRAME_MAXSZ SZ_64K
+#define SIGFRAME_MAXSZ SZ_256K
 
 static int __sigframe_alloc(struct rt_sigframe_user_layout *user,
 			    unsigned long *offset, size_t size, bool extend)
@@ -310,7 +310,7 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user)
 	fpsimd_flush_task_state(current);
 	/* From now, fpsimd_thread_switch() won't touch thread.sve_state */
 
-	sve_alloc(current);
+	sve_alloc(current, true);
 	if (!current->thread.sve_state) {
 		clear_thread_flag(TIF_SVE);
 		return -ENOMEM;
@@ -926,6 +926,16 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka,
 
 	/* Signal handlers are invoked with ZA and streaming mode disabled */
 	if (system_supports_sme()) {
+		/*
+		 * If we were in streaming mode the saved register
+		 * state was SVE but we will exit SM and use the
+		 * FPSIMD register state - flush the saved FPSIMD
+		 * register state in case it gets loaded.
+		 */
+		if (current->thread.svcr & SVCR_SM_MASK)
+			memset(&current->thread.uw.fpsimd_state, 0,
+			       sizeof(current->thread.uw.fpsimd_state));
+
 		current->thread.svcr &= ~(SVCR_ZA_MASK |
 					  SVCR_SM_MASK);
 		sme_smstop();

arch/arm64/kernel/topology.c

@@ -296,12 +296,25 @@ core_initcall(init_amu_fie);
 
 static void cpu_read_corecnt(void *val)
 {
+	/*
+	 * A value of 0 can be returned if the current CPU does not support AMUs
+	 * or if the counter is disabled for this CPU. A return value of 0 at
+	 * counter read is properly handled as an error case by the users of the
+	 * counter.
+	 */
 	*(u64 *)val = read_corecnt();
 }
 
 static void cpu_read_constcnt(void *val)
 {
-	*(u64 *)val = read_constcnt();
+	/*
+	 * Return 0 if the current CPU is affected by erratum 2457168. A value
+	 * of 0 is also returned if the current CPU does not support AMUs or if
+	 * the counter is disabled. A return value of 0 at counter read is
+	 * properly handled as an error case by the users of the counter.
+	 */
+	*(u64 *)val = this_cpu_has_cap(ARM64_WORKAROUND_2457168) ?
+		      0UL : read_constcnt();
 }
 
 static inline
@@ -328,7 +341,22 @@ int counters_read_on_cpu(int cpu, smp_call_func_t func, u64 *val)
  */
 bool cpc_ffh_supported(void)
 {
-	return freq_counters_valid(get_cpu_with_amu_feat());
+	int cpu = get_cpu_with_amu_feat();
+
+	/*
+	 * FFH is considered supported if there is at least one present CPU that
+	 * supports AMUs. Using FFH to read core and reference counters for CPUs
+	 * that do not support AMUs, have counters disabled or that are affected
+	 * by errata, will result in a return value of 0.
+	 *
+	 * This is done to allow any enabled and valid counters to be read
+	 * through FFH, knowing that potentially returning 0 as counter value is
+	 * properly handled by the users of these counters.
+	 */
+	if ((cpu >= nr_cpu_ids) || !cpumask_test_cpu(cpu, cpu_present_mask))
+		return false;
+
+	return true;
 }
 
 int cpc_read_ffh(int cpu, struct cpc_reg *reg, u64 *val)

arch/arm64/mm/mmu.c

@@ -642,24 +642,6 @@ static void __init map_kernel_segment(pgd_t *pgdp, void *va_start, void *va_end,
 	vm_area_add_early(vma);
 }
 
-static int __init parse_rodata(char *arg)
-{
-	int ret = strtobool(arg, &rodata_enabled);
-	if (!ret) {
-		rodata_full = false;
-		return 0;
-	}
-
-	/* permit 'full' in addition to boolean options */
-	if (strcmp(arg, "full"))
-		return -EINVAL;
-
-	rodata_enabled = true;
-	rodata_full = true;
-	return 0;
-}
-early_param("rodata", parse_rodata);
-
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 static int __init map_entry_trampoline(void)
 {

arch/arm64/tools/cpucaps

@@ -67,6 +67,7 @@ WORKAROUND_1902691
 WORKAROUND_2038923
 WORKAROUND_2064142
 WORKAROUND_2077057
+WORKAROUND_2457168
 WORKAROUND_TRBE_OVERWRITE_FILL_MODE
 WORKAROUND_TSB_FLUSH_FAILURE
 WORKAROUND_TRBE_WRITE_OUT_OF_RANGE

init/main.c

@@ -1446,13 +1446,25 @@ static noinline void __init kernel_init_freeable(void);
 
 #if defined(CONFIG_STRICT_KERNEL_RWX) || defined(CONFIG_STRICT_MODULE_RWX)
 bool rodata_enabled __ro_after_init = true;
+
+#ifndef arch_parse_debug_rodata
+static inline bool arch_parse_debug_rodata(char *str) { return false; }
+#endif
+
 static int __init set_debug_rodata(char *str)
 {
-	if (strtobool(str, &rodata_enabled))
+	if (arch_parse_debug_rodata(str))
+		return 0;
+
+	if (str && !strcmp(str, "on"))
+		rodata_enabled = true;
+	else if (str && !strcmp(str, "off"))
+		rodata_enabled = false;
+	else
 		pr_warn("Invalid option string for rodata: '%s'\n", str);
-	return 1;
+	return 0;
 }
-__setup("rodata=", set_debug_rodata);
+early_param("rodata", set_debug_rodata);
 #endif
 
 #ifdef CONFIG_STRICT_KERNEL_RWX