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

Pull arm64 updates from Will Deacon:
 "The big highlight is support for the Scalable Vector Extension (SVE)
  which required extensive ABI work to ensure we don't break existing
  applications by blowing away their signal stack with the rather large
  new vector context (<= 2 kbit per vector register). There's further
  work to be done optimising things like exception return, but the ABI
  is solid now.

  Much of the line count comes from some new PMU drivers we have, but
  they're pretty self-contained and I suspect we'll have more of them in
  future.

  Plenty of acronym soup here:

   - initial support for the Scalable Vector Extension (SVE)

   - improved handling for SError interrupts (required to handle RAS
     events)

   - enable GCC support for 128-bit integer types

   - remove kernel text addresses from backtraces and register dumps

   - use of WFE to implement long delay()s

   - ACPI IORT updates from Lorenzo Pieralisi

   - perf PMU driver for the Statistical Profiling Extension (SPE)

   - perf PMU driver for Hisilicon's system PMUs

   - misc cleanups and non-critical fixes"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (97 commits)
  arm64: Make ARMV8_DEPRECATED depend on SYSCTL
  arm64: Implement __lshrti3 library function
  arm64: support __int128 on gcc 5+
  arm64/sve: Add documentation
  arm64/sve: Detect SVE and activate runtime support
  arm64/sve: KVM: Hide SVE from CPU features exposed to guests
  arm64/sve: KVM: Treat guest SVE use as undefined instruction execution
  arm64/sve: KVM: Prevent guests from using SVE
  arm64/sve: Add sysctl to set the default vector length for new processes
  arm64/sve: Add prctl controls for userspace vector length management
  arm64/sve: ptrace and ELF coredump support
  arm64/sve: Preserve SVE registers around EFI runtime service calls
  arm64/sve: Preserve SVE registers around kernel-mode NEON use
  arm64/sve: Probe SVE capabilities and usable vector lengths
  arm64: cpufeature: Move sys_caps_initialised declarations
  arm64/sve: Backend logic for setting the vector length
  arm64/sve: Signal handling support
  arm64/sve: Support vector length resetting for new processes
  arm64/sve: Core task context handling
  arm64/sve: Low-level CPU setup
  ...

1 files changed, 169 insertions, 10 deletions

diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 0bdc96c61bc0..b120111a46be 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -31,6 +31,7 @@
 #include <linux/ratelimit.h>
 #include <linux/syscalls.h>
 
+#include <asm/daifflags.h>
 #include <asm/debug-monitors.h>
 #include <asm/elf.h>
 #include <asm/cacheflush.h>
@@ -63,6 +64,7 @@ struct rt_sigframe_user_layout {
 
 	unsigned long fpsimd_offset;
 	unsigned long esr_offset;
+	unsigned long sve_offset;
 	unsigned long extra_offset;
 	unsigned long end_offset;
 };
@@ -179,9 +181,6 @@ static int preserve_fpsimd_context(struct fpsimd_context __user *ctx)
 	struct fpsimd_state *fpsimd = &current->thread.fpsimd_state;
 	int err;
 
-	/* dump the hardware registers to the fpsimd_state structure */
-	fpsimd_preserve_current_state();
-
 	/* copy the FP and status/control registers */
 	err = __copy_to_user(ctx->vregs, fpsimd->vregs, sizeof(fpsimd->vregs));
 	__put_user_error(fpsimd->fpsr, &ctx->fpsr, err);
@@ -214,6 +213,8 @@ static int restore_fpsimd_context(struct fpsimd_context __user *ctx)
 	__get_user_error(fpsimd.fpsr, &ctx->fpsr, err);
 	__get_user_error(fpsimd.fpcr, &ctx->fpcr, err);
 
+	clear_thread_flag(TIF_SVE);
+
 	/* load the hardware registers from the fpsimd_state structure */
 	if (!err)
 		fpsimd_update_current_state(&fpsimd);
@@ -221,10 +222,118 @@ static int restore_fpsimd_context(struct fpsimd_context __user *ctx)
 	return err ? -EFAULT : 0;
 }
 
+
 struct user_ctxs {
 	struct fpsimd_context __user *fpsimd;
+	struct sve_context __user *sve;
 };
 
+#ifdef CONFIG_ARM64_SVE
+
+static int preserve_sve_context(struct sve_context __user *ctx)
+{
+	int err = 0;
+	u16 reserved[ARRAY_SIZE(ctx->__reserved)];
+	unsigned int vl = current->thread.sve_vl;
+	unsigned int vq = 0;
+
+	if (test_thread_flag(TIF_SVE))
+		vq = sve_vq_from_vl(vl);
+
+	memset(reserved, 0, sizeof(reserved));
+
+	__put_user_error(SVE_MAGIC, &ctx->head.magic, err);
+	__put_user_error(round_up(SVE_SIG_CONTEXT_SIZE(vq), 16),
+			 &ctx->head.size, err);
+	__put_user_error(vl, &ctx->vl, err);
+	BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved));
+	err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved));
+
+	if (vq) {
+		/*
+		 * This assumes that the SVE state has already been saved to
+		 * the task struct by calling preserve_fpsimd_context().
+		 */
+		err |= __copy_to_user((char __user *)ctx + SVE_SIG_REGS_OFFSET,
+				      current->thread.sve_state,
+				      SVE_SIG_REGS_SIZE(vq));
+	}
+
+	return err ? -EFAULT : 0;
+}
+
+static int restore_sve_fpsimd_context(struct user_ctxs *user)
+{
+	int err;
+	unsigned int vq;
+	struct fpsimd_state fpsimd;
+	struct sve_context sve;
+
+	if (__copy_from_user(&sve, user->sve, sizeof(sve)))
+		return -EFAULT;
+
+	if (sve.vl != current->thread.sve_vl)
+		return -EINVAL;
+
+	if (sve.head.size <= sizeof(*user->sve)) {
+		clear_thread_flag(TIF_SVE);
+		goto fpsimd_only;
+	}
+
+	vq = sve_vq_from_vl(sve.vl);
+
+	if (sve.head.size < SVE_SIG_CONTEXT_SIZE(vq))
+		return -EINVAL;
+
+	/*
+	 * Careful: we are about __copy_from_user() directly into
+	 * thread.sve_state with preemption enabled, so protection is
+	 * needed to prevent a racing context switch from writing stale
+	 * registers back over the new data.
+	 */
+
+	fpsimd_flush_task_state(current);
+	barrier();
+	/* From now, fpsimd_thread_switch() won't clear TIF_FOREIGN_FPSTATE */
+
+	set_thread_flag(TIF_FOREIGN_FPSTATE);
+	barrier();
+	/* From now, fpsimd_thread_switch() won't touch thread.sve_state */
+
+	sve_alloc(current);
+	err = __copy_from_user(current->thread.sve_state,
+			       (char __user const *)user->sve +
+					SVE_SIG_REGS_OFFSET,
+			       SVE_SIG_REGS_SIZE(vq));
+	if (err)
+		return -EFAULT;
+
+	set_thread_flag(TIF_SVE);
+
+fpsimd_only:
+	/* copy the FP and status/control registers */
+	/* restore_sigframe() already checked that user->fpsimd != NULL. */
+	err = __copy_from_user(fpsimd.vregs, user->fpsimd->vregs,
+			       sizeof(fpsimd.vregs));
+	__get_user_error(fpsimd.fpsr, &user->fpsimd->fpsr, err);
+	__get_user_error(fpsimd.fpcr, &user->fpsimd->fpcr, err);
+
+	/* load the hardware registers from the fpsimd_state structure */
+	if (!err)
+		fpsimd_update_current_state(&fpsimd);
+
+	return err ? -EFAULT : 0;
+}
+
+#else /* ! CONFIG_ARM64_SVE */
+
+/* Turn any non-optimised out attempts to use these into a link error: */
+extern int preserve_sve_context(void __user *ctx);
+extern int restore_sve_fpsimd_context(struct user_ctxs *user);
+
+#endif /* ! CONFIG_ARM64_SVE */
+
+
 static int parse_user_sigframe(struct user_ctxs *user,
 			       struct rt_sigframe __user *sf)
 {
@@ -237,6 +346,7 @@ static int parse_user_sigframe(struct user_ctxs *user,
 	char const __user *const sfp = (char const __user *)sf;
 
 	user->fpsimd = NULL;
+	user->sve = NULL;
 
 	if (!IS_ALIGNED((unsigned long)base, 16))
 		goto invalid;
@@ -287,6 +397,19 @@ static int parse_user_sigframe(struct user_ctxs *user,
 			/* ignore */
 			break;
 
+		case SVE_MAGIC:
+			if (!system_supports_sve())
+				goto invalid;
+
+			if (user->sve)
+				goto invalid;
+
+			if (size < sizeof(*user->sve))
+				goto invalid;
+
+			user->sve = (struct sve_context __user *)head;
+			break;
+
 		case EXTRA_MAGIC:
 			if (have_extra_context)
 				goto invalid;
@@ -343,6 +466,10 @@ static int parse_user_sigframe(struct user_ctxs *user,
 			 */
 			offset = 0;
 			limit = extra_size;
+
+			if (!access_ok(VERIFY_READ, base, limit))
+				goto invalid;
+
 			continue;
 
 		default:
@@ -359,9 +486,6 @@ static int parse_user_sigframe(struct user_ctxs *user,
 	}
 
 done:
-	if (!user->fpsimd)
-		goto invalid;
-
 	return 0;
 
 invalid:
@@ -395,8 +519,19 @@ static int restore_sigframe(struct pt_regs *regs,
 	if (err == 0)
 		err = parse_user_sigframe(&user, sf);
 
-	if (err == 0)
-		err = restore_fpsimd_context(user.fpsimd);
+	if (err == 0) {
+		if (!user.fpsimd)
+			return -EINVAL;
+
+		if (user.sve) {
+			if (!system_supports_sve())
+				return -EINVAL;
+
+			err = restore_sve_fpsimd_context(&user);
+		} else {
+			err = restore_fpsimd_context(user.fpsimd);
+		}
+	}
 
 	return err;
 }
@@ -455,6 +590,18 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user)
 			return err;
 	}
 
+	if (system_supports_sve()) {
+		unsigned int vq = 0;
+
+		if (test_thread_flag(TIF_SVE))
+			vq = sve_vq_from_vl(current->thread.sve_vl);
+
+		err = sigframe_alloc(user, &user->sve_offset,
+				     SVE_SIG_CONTEXT_SIZE(vq));
+		if (err)
+			return err;
+	}
+
 	return sigframe_alloc_end(user);
 }
 
@@ -496,6 +643,13 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user,
 		__put_user_error(current->thread.fault_code, &esr_ctx->esr, err);
 	}
 
+	/* Scalable Vector Extension state, if present */
+	if (system_supports_sve() && err == 0 && user->sve_offset) {
+		struct sve_context __user *sve_ctx =
+			apply_user_offset(user, user->sve_offset);
+		err |= preserve_sve_context(sve_ctx);
+	}
+
 	if (err == 0 && user->extra_offset) {
 		char __user *sfp = (char __user *)user->sigframe;
 		char __user *userp =
@@ -595,6 +749,8 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
 	struct rt_sigframe __user *frame;
 	int err = 0;
 
+	fpsimd_signal_preserve_current_state();
+
 	if (get_sigframe(&user, ksig, regs))
 		return 1;
 
@@ -756,9 +912,12 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
 		addr_limit_user_check();
 
 		if (thread_flags & _TIF_NEED_RESCHED) {
+			/* Unmask Debug and SError for the next task */
+			local_daif_restore(DAIF_PROCCTX_NOIRQ);
+
 			schedule();
 		} else {
-			local_irq_enable();
+			local_daif_restore(DAIF_PROCCTX);
 
 			if (thread_flags & _TIF_UPROBE)
 				uprobe_notify_resume(regs);
@@ -775,7 +934,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
 				fpsimd_restore_current_state();
 		}
 
-		local_irq_disable();
+		local_daif_mask();
 		thread_flags = READ_ONCE(current_thread_info()->flags);
 	} while (thread_flags & _TIF_WORK_MASK);
 }