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

Pull arm64 updates from Catalin Marinas:

 - Support for arm64 SME 2 and 2.1. SME2 introduces a new 512-bit
   architectural register (ZT0, for the look-up table feature) that
   Linux needs to save/restore

 - Include TPIDR2 in the signal context and add the corresponding
   kselftests

 - Perf updates: Arm SPEv1.2 support, HiSilicon uncore PMU updates, ACPI
   support to the Marvell DDR and TAD PMU drivers, reset DTM_PMU_CONFIG
   (ARM CMN) at probe time

 - Support for DYNAMIC_FTRACE_WITH_CALL_OPS on arm64

 - Permit EFI boot with MMU and caches on. Instead of cleaning the
   entire loaded kernel image to the PoC and disabling the MMU and
   caches before branching to the kernel bare metal entry point, leave
   the MMU and caches enabled and rely on EFI's cacheable 1:1 mapping of
   all of system RAM to populate the initial page tables

 - Expose the AArch32 (compat) ELF_HWCAP features to user in an arm64
   kernel (the arm32 kernel only defines the values)

 - Harden the arm64 shadow call stack pointer handling: stash the shadow
   stack pointer in the task struct on interrupt, load it directly from
   this structure

 - Signal handling cleanups to remove redundant validation of size
   information and avoid reading the same data from userspace twice

 - Refactor the hwcap macros to make use of the automatically generated
   ID registers. It should make new hwcaps writing less error prone

 - Further arm64 sysreg conversion and some fixes

 - arm64 kselftest fixes and improvements

 - Pointer authentication cleanups: don't sign leaf functions, unify
   asm-arch manipulation

 - Pseudo-NMI code generation optimisations

 - Minor fixes for SME and TPIDR2 handling

 - Miscellaneous updates: ARCH_FORCE_MAX_ORDER is now selectable,
   replace strtobool() to kstrtobool() in the cpufeature.c code, apply
   dynamic shadow call stack in two passes, intercept pfn changes in
   set_pte_at() without the required break-before-make sequence, attempt
   to dump all instructions on unhandled kernel faults

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (130 commits)
  arm64: fix .idmap.text assertion for large kernels
  kselftest/arm64: Don't require FA64 for streaming SVE+ZA tests
  kselftest/arm64: Copy whole EXTRA context
  arm64: kprobes: Drop ID map text from kprobes blacklist
  perf: arm_spe: Print the version of SPE detected
  perf: arm_spe: Add support for SPEv1.2 inverted event filtering
  perf: Add perf_event_attr::config3
  arm64/sme: Fix __finalise_el2 SMEver check
  drivers/perf: fsl_imx8_ddr_perf: Remove set-but-not-used variable
  arm64/signal: Only read new data when parsing the ZT context
  arm64/signal: Only read new data when parsing the ZA context
  arm64/signal: Only read new data when parsing the SVE context
  arm64/signal: Avoid rereading context frame sizes
  arm64/signal: Make interface for restore_fpsimd_context() consistent
  arm64/signal: Remove redundant size validation from parse_user_sigframe()
  arm64/signal: Don't redundantly verify FPSIMD magic
  arm64/cpufeature: Use helper macros to specify hwcaps
  arm64/cpufeature: Always use symbolic name for feature value in hwcaps
  arm64/sysreg: Initial unsigned annotations for ID registers
  arm64/sysreg: Initial annotation of signed ID registers
  ...

1 files changed, 31 insertions, 21 deletions

diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index b6ef1af0122e..692dfefbe0ed 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -299,7 +299,7 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
 /*
  * TIF_SME controls whether a task can use SME without trapping while
  * in userspace, when TIF_SME is set then we must have storage
- * alocated in sve_state and za_state to store the contents of both ZA
+ * alocated in sve_state and sme_state to store the contents of both ZA
  * and the SVE registers for both streaming and non-streaming modes.
  *
  * If both SVCR.ZA and SVCR.SM are disabled then at any point we
@@ -429,7 +429,8 @@ static void task_fpsimd_load(void)
 		write_sysreg_s(current->thread.svcr, SYS_SVCR);
 
 		if (thread_za_enabled(&current->thread))
-			za_load_state(current->thread.za_state);
+			sme_load_state(current->thread.sme_state,
+				       system_supports_sme2());
 
 		if (thread_sm_enabled(&current->thread))
 			restore_ffr = system_supports_fa64();
@@ -490,7 +491,8 @@ static void fpsimd_save(void)
 		*svcr = read_sysreg_s(SYS_SVCR);
 
 		if (*svcr & SVCR_ZA_MASK)
-			za_save_state(last->za_state);
+			sme_save_state(last->sme_state,
+				       system_supports_sme2());
 
 		/* If we are in streaming mode override regular SVE. */
 		if (*svcr & SVCR_SM_MASK) {
@@ -1257,30 +1259,30 @@ void fpsimd_release_task(struct task_struct *dead_task)
 #ifdef CONFIG_ARM64_SME
 
 /*
- * Ensure that task->thread.za_state is allocated and sufficiently large.
+ * Ensure that task->thread.sme_state is allocated and sufficiently large.
  *
  * This function should be used only in preparation for replacing
- * task->thread.za_state with new data.  The memory is always zeroed
+ * task->thread.sme_state with new data.  The memory is always zeroed
  * here to prevent stale data from showing through: this is done in
  * the interest of testability and predictability, the architecture
  * guarantees that when ZA is enabled it will be zeroed.
  */
 void sme_alloc(struct task_struct *task)
 {
-	if (task->thread.za_state) {
-		memset(task->thread.za_state, 0, za_state_size(task));
+	if (task->thread.sme_state) {
+		memset(task->thread.sme_state, 0, sme_state_size(task));
 		return;
 	}
 
 	/* This could potentially be up to 64K. */
-	task->thread.za_state =
-		kzalloc(za_state_size(task), GFP_KERNEL);
+	task->thread.sme_state =
+		kzalloc(sme_state_size(task), GFP_KERNEL);
 }
 
 static void sme_free(struct task_struct *task)
 {
-	kfree(task->thread.za_state);
-	task->thread.za_state = NULL;
+	kfree(task->thread.sme_state);
+	task->thread.sme_state = NULL;
 }
 
 void sme_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
@@ -1302,6 +1304,17 @@ void sme_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
  * This must be called after sme_kernel_enable(), we rely on the
  * feature table being sorted to ensure this.
  */
+void sme2_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
+{
+	/* Allow use of ZT0 */
+	write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_EZT0_MASK,
+		       SYS_SMCR_EL1);
+}
+
+/*
+ * This must be called after sme_kernel_enable(), we rely on the
+ * feature table being sorted to ensure this.
+ */
 void fa64_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
 {
 	/* Allow use of FA64 */
@@ -1322,7 +1335,6 @@ u64 read_smcr_features(void)
 	unsigned int vq_max;
 
 	sme_kernel_enable(NULL);
-	sme_smstart_sm();
 
 	/*
 	 * Set the maximum possible VL.
@@ -1332,11 +1344,9 @@ u64 read_smcr_features(void)
 
 	smcr = read_sysreg_s(SYS_SMCR_EL1);
 	smcr &= ~(u64)SMCR_ELx_LEN_MASK; /* Only the LEN field */
-	vq_max = sve_vq_from_vl(sve_get_vl());
+	vq_max = sve_vq_from_vl(sme_get_vl());
 	smcr |= vq_max - 1; /* set LEN field to maximum effective value */
 
-	sme_smstop_sm();
-
 	return smcr;
 }
 
@@ -1488,7 +1498,7 @@ void do_sme_acc(unsigned long esr, struct pt_regs *regs)
 
 	sve_alloc(current, false);
 	sme_alloc(current);
-	if (!current->thread.sve_state || !current->thread.za_state) {
+	if (!current->thread.sve_state || !current->thread.sme_state) {
 		force_sig(SIGKILL);
 		return;
 	}
@@ -1609,7 +1619,7 @@ static void fpsimd_flush_thread_vl(enum vec_type type)
 void fpsimd_flush_thread(void)
 {
 	void *sve_state = NULL;
-	void *za_state = NULL;
+	void *sme_state = NULL;
 
 	if (!system_supports_fpsimd())
 		return;
@@ -1634,8 +1644,8 @@ void fpsimd_flush_thread(void)
 		clear_thread_flag(TIF_SME);
 
 		/* Defer kfree() while in atomic context */
-		za_state = current->thread.za_state;
-		current->thread.za_state = NULL;
+		sme_state = current->thread.sme_state;
+		current->thread.sme_state = NULL;
 
 		fpsimd_flush_thread_vl(ARM64_VEC_SME);
 		current->thread.svcr = 0;
@@ -1645,7 +1655,7 @@ void fpsimd_flush_thread(void)
 
 	put_cpu_fpsimd_context();
 	kfree(sve_state);
-	kfree(za_state);
+	kfree(sme_state);
 }
 
 /*
@@ -1711,7 +1721,7 @@ static void fpsimd_bind_task_to_cpu(void)
 	WARN_ON(!system_supports_fpsimd());
 	last->st = &current->thread.uw.fpsimd_state;
 	last->sve_state = current->thread.sve_state;
-	last->za_state = current->thread.za_state;
+	last->sme_state = current->thread.sme_state;
 	last->sve_vl = task_get_sve_vl(current);
 	last->sme_vl = task_get_sme_vl(current);
 	last->svcr = &current->thread.svcr;