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, 212 insertions, 47 deletions

diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index be279fd48248..06a02707f488 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -56,7 +56,9 @@ struct rt_sigframe_user_layout {
 	unsigned long fpsimd_offset;
 	unsigned long esr_offset;
 	unsigned long sve_offset;
+	unsigned long tpidr2_offset;
 	unsigned long za_offset;
+	unsigned long zt_offset;
 	unsigned long extra_offset;
 	unsigned long end_offset;
 };
@@ -168,6 +170,19 @@ static void __user *apply_user_offset(
 	return base + offset;
 }
 
+struct user_ctxs {
+	struct fpsimd_context __user *fpsimd;
+	u32 fpsimd_size;
+	struct sve_context __user *sve;
+	u32 sve_size;
+	struct tpidr2_context __user *tpidr2;
+	u32 tpidr2_size;
+	struct za_context __user *za;
+	u32 za_size;
+	struct zt_context __user *zt;
+	u32 zt_size;
+};
+
 static int preserve_fpsimd_context(struct fpsimd_context __user *ctx)
 {
 	struct user_fpsimd_state const *fpsimd =
@@ -186,25 +201,20 @@ static int preserve_fpsimd_context(struct fpsimd_context __user *ctx)
 	return err ? -EFAULT : 0;
 }
 
-static int restore_fpsimd_context(struct fpsimd_context __user *ctx)
+static int restore_fpsimd_context(struct user_ctxs *user)
 {
 	struct user_fpsimd_state fpsimd;
-	__u32 magic, size;
 	int err = 0;
 
-	/* check the magic/size information */
-	__get_user_error(magic, &ctx->head.magic, err);
-	__get_user_error(size, &ctx->head.size, err);
-	if (err)
-		return -EFAULT;
-	if (magic != FPSIMD_MAGIC || size != sizeof(struct fpsimd_context))
+	/* check the size information */
+	if (user->fpsimd_size != sizeof(struct fpsimd_context))
 		return -EINVAL;
 
 	/* copy the FP and status/control registers */
-	err = __copy_from_user(fpsimd.vregs, ctx->vregs,
+	err = __copy_from_user(fpsimd.vregs, &(user->fpsimd->vregs),
 			       sizeof(fpsimd.vregs));
-	__get_user_error(fpsimd.fpsr, &ctx->fpsr, err);
-	__get_user_error(fpsimd.fpcr, &ctx->fpcr, err);
+	__get_user_error(fpsimd.fpsr, &(user->fpsimd->fpsr), err);
+	__get_user_error(fpsimd.fpcr, &(user->fpsimd->fpcr), err);
 
 	clear_thread_flag(TIF_SVE);
 	current->thread.fp_type = FP_STATE_FPSIMD;
@@ -217,12 +227,6 @@ static int restore_fpsimd_context(struct fpsimd_context __user *ctx)
 }
 
 
-struct user_ctxs {
-	struct fpsimd_context __user *fpsimd;
-	struct sve_context __user *sve;
-	struct za_context __user *za;
-};
-
 #ifdef CONFIG_ARM64_SVE
 
 static int preserve_sve_context(struct sve_context __user *ctx)
@@ -267,15 +271,20 @@ static int preserve_sve_context(struct sve_context __user *ctx)
 
 static int restore_sve_fpsimd_context(struct user_ctxs *user)
 {
-	int err;
+	int err = 0;
 	unsigned int vl, vq;
 	struct user_fpsimd_state fpsimd;
-	struct sve_context sve;
+	u16 user_vl, flags;
 
-	if (__copy_from_user(&sve, user->sve, sizeof(sve)))
-		return -EFAULT;
+	if (user->sve_size < sizeof(*user->sve))
+		return -EINVAL;
+
+	__get_user_error(user_vl, &(user->sve->vl), err);
+	__get_user_error(flags, &(user->sve->flags), err);
+	if (err)
+		return err;
 
-	if (sve.flags & SVE_SIG_FLAG_SM) {
+	if (flags & SVE_SIG_FLAG_SM) {
 		if (!system_supports_sme())
 			return -EINVAL;
 
@@ -292,19 +301,19 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user)
 		vl = task_get_sve_vl(current);
 	}
 
-	if (sve.vl != vl)
+	if (user_vl != vl)
 		return -EINVAL;
 
-	if (sve.head.size <= sizeof(*user->sve)) {
+	if (user->sve_size == sizeof(*user->sve)) {
 		clear_thread_flag(TIF_SVE);
 		current->thread.svcr &= ~SVCR_SM_MASK;
 		current->thread.fp_type = FP_STATE_FPSIMD;
 		goto fpsimd_only;
 	}
 
-	vq = sve_vq_from_vl(sve.vl);
+	vq = sve_vq_from_vl(vl);
 
-	if (sve.head.size < SVE_SIG_CONTEXT_SIZE(vq))
+	if (user->sve_size < SVE_SIG_CONTEXT_SIZE(vq))
 		return -EINVAL;
 
 	/*
@@ -330,7 +339,7 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user)
 	if (err)
 		return -EFAULT;
 
-	if (sve.flags & SVE_SIG_FLAG_SM)
+	if (flags & SVE_SIG_FLAG_SM)
 		current->thread.svcr |= SVCR_SM_MASK;
 	else
 		set_thread_flag(TIF_SVE);
@@ -366,6 +375,34 @@ extern int preserve_sve_context(void __user *ctx);
 
 #ifdef CONFIG_ARM64_SME
 
+static int preserve_tpidr2_context(struct tpidr2_context __user *ctx)
+{
+	int err = 0;
+
+	current->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0);
+
+	__put_user_error(TPIDR2_MAGIC, &ctx->head.magic, err);
+	__put_user_error(sizeof(*ctx), &ctx->head.size, err);
+	__put_user_error(current->thread.tpidr2_el0, &ctx->tpidr2, err);
+
+	return err;
+}
+
+static int restore_tpidr2_context(struct user_ctxs *user)
+{
+	u64 tpidr2_el0;
+	int err = 0;
+
+	if (user->tpidr2_size != sizeof(*user->tpidr2))
+		return -EINVAL;
+
+	__get_user_error(tpidr2_el0, &user->tpidr2->tpidr2, err);
+	if (!err)
+		current->thread.tpidr2_el0 = tpidr2_el0;
+
+	return err;
+}
+
 static int preserve_za_context(struct za_context __user *ctx)
 {
 	int err = 0;
@@ -394,7 +431,7 @@ static int preserve_za_context(struct za_context __user *ctx)
 		 * fpsimd_signal_preserve_current_state().
 		 */
 		err |= __copy_to_user((char __user *)ctx + ZA_SIG_REGS_OFFSET,
-				      current->thread.za_state,
+				      current->thread.sme_state,
 				      ZA_SIG_REGS_SIZE(vq));
 	}
 
@@ -403,29 +440,33 @@ static int preserve_za_context(struct za_context __user *ctx)
 
 static int restore_za_context(struct user_ctxs *user)
 {
-	int err;
+	int err = 0;
 	unsigned int vq;
-	struct za_context za;
+	u16 user_vl;
 
-	if (__copy_from_user(&za, user->za, sizeof(za)))
-		return -EFAULT;
+	if (user->za_size < sizeof(*user->za))
+		return -EINVAL;
+
+	__get_user_error(user_vl, &(user->za->vl), err);
+	if (err)
+		return err;
 
-	if (za.vl != task_get_sme_vl(current))
+	if (user_vl != task_get_sme_vl(current))
 		return -EINVAL;
 
-	if (za.head.size <= sizeof(*user->za)) {
+	if (user->za_size == sizeof(*user->za)) {
 		current->thread.svcr &= ~SVCR_ZA_MASK;
 		return 0;
 	}
 
-	vq = sve_vq_from_vl(za.vl);
+	vq = sve_vq_from_vl(user_vl);
 
-	if (za.head.size < ZA_SIG_CONTEXT_SIZE(vq))
+	if (user->za_size < ZA_SIG_CONTEXT_SIZE(vq))
 		return -EINVAL;
 
 	/*
 	 * Careful: we are about __copy_from_user() directly into
-	 * thread.za_state with preemption enabled, so protection is
+	 * thread.sme_state with preemption enabled, so protection is
 	 * needed to prevent a racing context switch from writing stale
 	 * registers back over the new data.
 	 */
@@ -434,13 +475,13 @@ static int restore_za_context(struct user_ctxs *user)
 	/* From now, fpsimd_thread_switch() won't touch thread.sve_state */
 
 	sme_alloc(current);
-	if (!current->thread.za_state) {
+	if (!current->thread.sme_state) {
 		current->thread.svcr &= ~SVCR_ZA_MASK;
 		clear_thread_flag(TIF_SME);
 		return -ENOMEM;
 	}
 
-	err = __copy_from_user(current->thread.za_state,
+	err = __copy_from_user(current->thread.sme_state,
 			       (char __user const *)user->za +
 					ZA_SIG_REGS_OFFSET,
 			       ZA_SIG_REGS_SIZE(vq));
@@ -452,11 +493,83 @@ static int restore_za_context(struct user_ctxs *user)
 
 	return 0;
 }
+
+static int preserve_zt_context(struct zt_context __user *ctx)
+{
+	int err = 0;
+	u16 reserved[ARRAY_SIZE(ctx->__reserved)];
+
+	if (WARN_ON(!thread_za_enabled(&current->thread)))
+		return -EINVAL;
+
+	memset(reserved, 0, sizeof(reserved));
+
+	__put_user_error(ZT_MAGIC, &ctx->head.magic, err);
+	__put_user_error(round_up(ZT_SIG_CONTEXT_SIZE(1), 16),
+			 &ctx->head.size, err);
+	__put_user_error(1, &ctx->nregs, err);
+	BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved));
+	err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved));
+
+	/*
+	 * This assumes that the ZT state has already been saved to
+	 * the task struct by calling the function
+	 * fpsimd_signal_preserve_current_state().
+	 */
+	err |= __copy_to_user((char __user *)ctx + ZT_SIG_REGS_OFFSET,
+			      thread_zt_state(&current->thread),
+			      ZT_SIG_REGS_SIZE(1));
+
+	return err ? -EFAULT : 0;
+}
+
+static int restore_zt_context(struct user_ctxs *user)
+{
+	int err;
+	u16 nregs;
+
+	/* ZA must be restored first for this check to be valid */
+	if (!thread_za_enabled(&current->thread))
+		return -EINVAL;
+
+	if (user->zt_size != ZT_SIG_CONTEXT_SIZE(1))
+		return -EINVAL;
+
+	if (__copy_from_user(&nregs, &(user->zt->nregs), sizeof(nregs)))
+		return -EFAULT;
+
+	if (nregs != 1)
+		return -EINVAL;
+
+	/*
+	 * Careful: we are about __copy_from_user() directly into
+	 * thread.zt_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);
+	/* From now, fpsimd_thread_switch() won't touch ZT in thread state */
+
+	err = __copy_from_user(thread_zt_state(&current->thread),
+			       (char __user const *)user->zt +
+					ZT_SIG_REGS_OFFSET,
+			       ZT_SIG_REGS_SIZE(1));
+	if (err)
+		return -EFAULT;
+
+	return 0;
+}
+
 #else /* ! CONFIG_ARM64_SME */
 
 /* Turn any non-optimised out attempts to use these into a link error: */
+extern int preserve_tpidr2_context(void __user *ctx);
+extern int restore_tpidr2_context(struct user_ctxs *user);
 extern int preserve_za_context(void __user *ctx);
 extern int restore_za_context(struct user_ctxs *user);
+extern int preserve_zt_context(void __user *ctx);
+extern int restore_zt_context(struct user_ctxs *user);
 
 #endif /* ! CONFIG_ARM64_SME */
 
@@ -473,7 +586,9 @@ static int parse_user_sigframe(struct user_ctxs *user,
 
 	user->fpsimd = NULL;
 	user->sve = NULL;
+	user->tpidr2 = NULL;
 	user->za = NULL;
+	user->zt = NULL;
 
 	if (!IS_ALIGNED((unsigned long)base, 16))
 		goto invalid;
@@ -516,10 +631,8 @@ static int parse_user_sigframe(struct user_ctxs *user,
 			if (user->fpsimd)
 				goto invalid;
 
-			if (size < sizeof(*user->fpsimd))
-				goto invalid;
-
 			user->fpsimd = (struct fpsimd_context __user *)head;
+			user->fpsimd_size = size;
 			break;
 
 		case ESR_MAGIC:
@@ -533,10 +646,19 @@ static int parse_user_sigframe(struct user_ctxs *user,
 			if (user->sve)
 				goto invalid;
 
-			if (size < sizeof(*user->sve))
+			user->sve = (struct sve_context __user *)head;
+			user->sve_size = size;
+			break;
+
+		case TPIDR2_MAGIC:
+			if (!system_supports_sme())
 				goto invalid;
 
-			user->sve = (struct sve_context __user *)head;
+			if (user->tpidr2)
+				goto invalid;
+
+			user->tpidr2 = (struct tpidr2_context __user *)head;
+			user->tpidr2_size = size;
 			break;
 
 		case ZA_MAGIC:
@@ -546,10 +668,19 @@ static int parse_user_sigframe(struct user_ctxs *user,
 			if (user->za)
 				goto invalid;
 
-			if (size < sizeof(*user->za))
+			user->za = (struct za_context __user *)head;
+			user->za_size = size;
+			break;
+
+		case ZT_MAGIC:
+			if (!system_supports_sme2())
 				goto invalid;
 
-			user->za = (struct za_context __user *)head;
+			if (user->zt)
+				goto invalid;
+
+			user->zt = (struct zt_context __user *)head;
+			user->zt_size = size;
 			break;
 
 		case EXTRA_MAGIC:
@@ -668,12 +799,18 @@ static int restore_sigframe(struct pt_regs *regs,
 		if (user.sve)
 			err = restore_sve_fpsimd_context(&user);
 		else
-			err = restore_fpsimd_context(user.fpsimd);
+			err = restore_fpsimd_context(&user);
 	}
 
+	if (err == 0 && system_supports_sme() && user.tpidr2)
+		err = restore_tpidr2_context(&user);
+
 	if (err == 0 && system_supports_sme() && user.za)
 		err = restore_za_context(&user);
 
+	if (err == 0 && system_supports_sme2() && user.zt)
+		err = restore_zt_context(&user);
+
 	return err;
 }
 
@@ -765,6 +902,11 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
 		else
 			vl = task_get_sme_vl(current);
 
+		err = sigframe_alloc(user, &user->tpidr2_offset,
+				     sizeof(struct tpidr2_context));
+		if (err)
+			return err;
+
 		if (thread_za_enabled(&current->thread))
 			vq = sve_vq_from_vl(vl);
 
@@ -774,6 +916,15 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
 			return err;
 	}
 
+	if (system_supports_sme2()) {
+		if (add_all || thread_za_enabled(&current->thread)) {
+			err = sigframe_alloc(user, &user->zt_offset,
+					     ZT_SIG_CONTEXT_SIZE(1));
+			if (err)
+				return err;
+		}
+	}
+
 	return sigframe_alloc_end(user);
 }
 
@@ -822,6 +973,13 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user,
 		err |= preserve_sve_context(sve_ctx);
 	}
 
+	/* TPIDR2 if supported */
+	if (system_supports_sme() && err == 0) {
+		struct tpidr2_context __user *tpidr2_ctx =
+			apply_user_offset(user, user->tpidr2_offset);
+		err |= preserve_tpidr2_context(tpidr2_ctx);
+	}
+
 	/* ZA state if present */
 	if (system_supports_sme() && err == 0 && user->za_offset) {
 		struct za_context __user *za_ctx =
@@ -829,6 +987,13 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user,
 		err |= preserve_za_context(za_ctx);
 	}
 
+	/* ZT state if present */
+	if (system_supports_sme2() && err == 0 && user->zt_offset) {
+		struct zt_context __user *zt_ctx =
+			apply_user_offset(user, user->zt_offset);
+		err |= preserve_zt_context(zt_ctx);
+	}
+
 	if (err == 0 && user->extra_offset) {
 		char __user *sfp = (char __user *)user->sigframe;
 		char __user *userp =