Merge branch 'for-next/sme-fixes' into for-next/core

* for-next/sme-fixes: (35 commits)
  arm64/fpsimd: Allow CONFIG_ARM64_SME to be selected
  arm64/fpsimd: ptrace: Gracefully handle errors
  arm64/fpsimd: ptrace: Mandate SVE payload for streaming-mode state
  arm64/fpsimd: ptrace: Do not present register data for inactive mode
  arm64/fpsimd: ptrace: Save task state before generating SVE header
  arm64/fpsimd: ptrace/prctl: Ensure VL changes leave task in a valid state
  arm64/fpsimd: ptrace/prctl: Ensure VL changes do not resurrect stale data
  arm64/fpsimd: Make clone() compatible with ZA lazy saving
  arm64/fpsimd: Clear PSTATE.SM during clone()
  arm64/fpsimd: Consistently preserve FPSIMD state during clone()
  arm64/fpsimd: Remove redundant task->mm check
  arm64/fpsimd: signal: Use SMSTOP behaviour in setup_return()
  arm64/fpsimd: Add task_smstop_sm()
  arm64/fpsimd: Factor out {sve,sme}_state_size() helpers
  arm64/fpsimd: Clarify sve_sync_*() functions
  arm64/fpsimd: ptrace: Consistently handle partial writes to NT_ARM_(S)SVE
  arm64/fpsimd: signal: Consistently read FPSIMD context
  arm64/fpsimd: signal: Mandate SVE payload for streaming-mode state
  arm64/fpsimd: signal: Clear PSTATE.SM when restoring FPSIMD frame only
  arm64/fpsimd: Do not discard modified SVE state
  ...

1 files changed, 74 insertions, 41 deletions

diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 45a55fe81788..a5ca15daeb8a 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -344,50 +344,34 @@ void arch_release_task_struct(struct task_struct *tsk)
 
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
-	if (current->mm)
-		fpsimd_preserve_current_state();
+	/*
+	 * The current/src task's FPSIMD state may or may not be live, and may
+	 * have been altered by ptrace after entry to the kernel. Save the
+	 * effective FPSIMD state so that this will be copied into dst.
+	 */
+	fpsimd_save_and_flush_current_state();
+	fpsimd_sync_from_effective_state(src);
+
 	*dst = *src;
 
 	/*
-	 * Detach src's sve_state (if any) from dst so that it does not
-	 * get erroneously used or freed prematurely.  dst's copies
-	 * will be allocated on demand later on if dst uses SVE.
-	 * For consistency, also clear TIF_SVE here: this could be done
-	 * later in copy_process(), but to avoid tripping up future
-	 * maintainers it is best not to leave TIF flags and buffers in
-	 * an inconsistent state, even temporarily.
+	 * Drop stale reference to src's sve_state and convert dst to
+	 * non-streaming FPSIMD mode.
 	 */
+	dst->thread.fp_type = FP_STATE_FPSIMD;
 	dst->thread.sve_state = NULL;
 	clear_tsk_thread_flag(dst, TIF_SVE);
+	task_smstop_sm(dst);
 
 	/*
-	 * In the unlikely event that we create a new thread with ZA
-	 * enabled we should retain the ZA and ZT state so duplicate
-	 * it here.  This may be shortly freed if we exec() or if
-	 * CLONE_SETTLS but it's simpler to do it here. To avoid
-	 * confusing the rest of the code ensure that we have a
-	 * sve_state allocated whenever sme_state is allocated.
+	 * Drop stale reference to src's sme_state and ensure dst has ZA
+	 * disabled.
+	 *
+	 * When necessary, ZA will be inherited later in copy_thread_za().
 	 */
-	if (thread_za_enabled(&src->thread)) {
-		dst->thread.sve_state = kzalloc(sve_state_size(src),
-						GFP_KERNEL);
-		if (!dst->thread.sve_state)
-			return -ENOMEM;
-
-		dst->thread.sme_state = kmemdup(src->thread.sme_state,
-						sme_state_size(src),
-						GFP_KERNEL);
-		if (!dst->thread.sme_state) {
-			kfree(dst->thread.sve_state);
-			dst->thread.sve_state = NULL;
-			return -ENOMEM;
-		}
-	} else {
-		dst->thread.sme_state = NULL;
-		clear_tsk_thread_flag(dst, TIF_SME);
-	}
-
-	dst->thread.fp_type = FP_STATE_FPSIMD;
+	dst->thread.sme_state = NULL;
+	clear_tsk_thread_flag(dst, TIF_SME);
+	dst->thread.svcr &= ~SVCR_ZA_MASK;
 
 	/* clear any pending asynchronous tag fault raised by the parent */
 	clear_tsk_thread_flag(dst, TIF_MTE_ASYNC_FAULT);
@@ -395,6 +379,31 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	return 0;
 }
 
+static int copy_thread_za(struct task_struct *dst, struct task_struct *src)
+{
+	if (!thread_za_enabled(&src->thread))
+		return 0;
+
+	dst->thread.sve_state = kzalloc(sve_state_size(src),
+					GFP_KERNEL);
+	if (!dst->thread.sve_state)
+		return -ENOMEM;
+
+	dst->thread.sme_state = kmemdup(src->thread.sme_state,
+					sme_state_size(src),
+					GFP_KERNEL);
+	if (!dst->thread.sme_state) {
+		kfree(dst->thread.sve_state);
+		dst->thread.sve_state = NULL;
+		return -ENOMEM;
+	}
+
+	set_tsk_thread_flag(dst, TIF_SME);
+	dst->thread.svcr |= SVCR_ZA_MASK;
+
+	return 0;
+}
+
 asmlinkage void ret_from_fork(void) asm("ret_from_fork");
 
 int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
@@ -427,8 +436,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		 * out-of-sync with the saved value.
 		 */
 		*task_user_tls(p) = read_sysreg(tpidr_el0);
-		if (system_supports_tpidr2())
-			p->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0);
 
 		if (system_supports_poe())
 			p->thread.por_el0 = read_sysreg_s(SYS_POR_EL0);
@@ -441,13 +448,39 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		}
 
 		/*
+		 * Due to the AAPCS64 "ZA lazy saving scheme", PSTATE.ZA and
+		 * TPIDR2 need to be manipulated as a pair, and either both
+		 * need to be inherited or both need to be reset.
+		 *
+		 * Within a process, child threads must not inherit their
+		 * parent's TPIDR2 value or they may clobber their parent's
+		 * stack at some later point.
+		 *
+		 * When a process is fork()'d, the child must inherit ZA and
+		 * TPIDR2 from its parent in case there was dormant ZA state.
+		 *
+		 * Use CLONE_VM to determine when the child will share the
+		 * address space with the parent, and cannot safely inherit the
+		 * state.
+		 */
+		if (system_supports_sme()) {
+			if (!(clone_flags & CLONE_VM)) {
+				p->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0);
+				ret = copy_thread_za(p, current);
+				if (ret)
+					return ret;
+			} else {
+				p->thread.tpidr2_el0 = 0;
+				WARN_ON_ONCE(p->thread.svcr & SVCR_ZA_MASK);
+			}
+		}
+
+		/*
 		 * If a TLS pointer was passed to clone, use it for the new
-		 * thread.  We also reset TPIDR2 if it's in use.
+		 * thread.
 		 */
-		if (clone_flags & CLONE_SETTLS) {
+		if (clone_flags & CLONE_SETTLS)
 			p->thread.uw.tp_value = tls;
-			p->thread.tpidr2_el0 = 0;
-		}
 
 		ret = copy_thread_gcs(p, args);
 		if (ret != 0)